Road condition analysis system and method based on multi-source data fusion

Abstract

The invention discloses a road condition analysis system and method based on multi-source data fusion, and belongs to the technical field of road condition analysis management, and the system comprises a data visualization module, a data management module, a multi-source data fusion module and a feature extraction early warning module. According to the method, the comprehensiveness, the accuracy and the timeliness of road condition analysis are improved, the utilization efficiency of system resources is optimized, the actual road condition can be comprehensively reflected through multi-source data fusion and integration of various kinds of road related data, the limitation of a single data source is avoided, a rich and accurate information basis is provided for analysis, and the method is suitable for popularization and application. The road damage risk is accurately evaluated, potential problems are predicted in advance, a reliable basis is provided for road maintenance decision making, potential safety hazards caused by road diseases are reduced, computing resources and visual display resources are dynamically configured according to the real-time state of the system, and on the basis of guaranteeing the data processing precision and real-time performance, resource waste is avoided, and the system operation efficiency is improved. Therefore, different road conditions can be adapted.

Description

Technical Field

[0001] The present invention relates to the technical field of road condition analysis and management, and particularly to a road condition analysis system and method based on multi-source data fusion. Background Art

[0002] In the fields of modern traffic management and road maintenance, accurately grasping the road conditions is crucial for ensuring traffic safety, improving traffic efficiency, and reasonably planning road maintenance work. With the rapid development of information technology, data from multiple data sources reflect the real-time road conditions from different perspectives, including road surface damage, water accumulation degree, icing risk, etc. The importance of data fusion technology is increasing day by day in many fields. It can integrate information from different channels to provide more comprehensive and accurate insights. In terms of road condition analysis, by fusing multi-source data, the advantages of each data source can be fully utilized to improve the accuracy and reliability of analysis, and provide more accurate, timely, and comprehensive road condition information.

[0003] For example, a state monitoring system and method for road and bridge anti-collision guardrails announced in the invention patent with the announcement number of CN118071114B identifies features related to road anti-collision guardrails through statistical analysis and chi-square test, and performs clustering analysis on the selected features by combining the DBSCAN algorithm to eliminate irrelevant features.

[0004] For example, a road quality intelligent evaluation method and system based on the Tantu index announced in the invention patent with the announcement number of CN119067511B. The method includes: obtaining the acquisition data of the urban road to be evaluated; dividing the urban road to be evaluated into different evaluation units; obtaining the health status indicators according to the acquisition data, and calculating the Tantu index corresponding to different evaluation units according to the health status indicators, where the health status indicators at least include road damage parameters and bump impact parameters; dividing according to the Tantu index corresponding to different evaluation units to obtain at least a multi-color evaluation map; outputting at least the multi-color evaluation map.

[0005] However, in the process of implementing the technical solutions of the present invention in the embodiments of the present application, it is found that the above technologies have at least the following technical problems: The current road condition analysis methods often focus on the collection and analysis of road condition data, ignoring the reasonable allocation of system resources in data processing. In actual processes, it is difficult to flexibly adjust resources according to the real-time state of the system, resulting in low resource utilization efficiency, which may affect the accuracy and real-time performance of data processing, reduce the reliability and efficiency of road condition analysis, and it is difficult to cope with complex and changeable actual application scenarios. Summary of the Invention

[0006] The first aspect of the present invention provides a road condition analysis system based on multi-source data fusion, including: A data visualization module, which is used to select a processing mode according to the length of the system real-time data processing queue, including a precision priority mode, a real-time priority mode, and a balance mode, and dynamically configure the system computing resources and visualization display resources based on the processing mode.

[0007] A data management module, which is used to collect road average stress and stress interference data, analyze the road average stress correction value, and thus obtain the pre-classification result of the road condition.

[0008] A multi-source data fusion module, which is used to obtain multi-source data of the road structure based on the pre-classification result of the road condition, dynamically adjust the sampling frequency and computing resources according to the data fluctuation characteristics, analyze the data confidence level and set the data fusion weight, and thus complete the data fusion and generate a fusion feature set.

[0009] A feature extraction and warning module, which is used to extract road damage features based on the fusion feature set, conduct road behavior analysis, and thus optimize and adjust the visualization display resources, and simultaneously display the road behavior analysis result and the resource allocation status through the visualization interface.

[0010] The second aspect of the present invention provides a road behavior analysis method based on multi-source data fusion, including the following steps: S1. Select a processing mode according to the length of the system real-time data processing queue, including a precision priority mode, a real-time priority mode, and a balance mode, and dynamically configure the system computing resources and visualization display resources based on the processing mode.

[0011] S2. Collect road average stress and stress interference data, analyze the road average stress correction value, and thus obtain the pre-classification result of the road condition.

[0012] S3. Obtain multi-source data of the road structure based on the pre-classification result of the road condition, dynamically adjust the sampling frequency and computing resources according to the data fluctuation characteristics, analyze the data confidence level and set the data fusion weight, and thus complete the data fusion and generate a fusion feature set.

[0013] S4. Extract road damage features based on the fusion feature set, conduct road behavior analysis, and thus optimize and adjust the visualization display resources, and simultaneously display the road behavior analysis result and the resource allocation status through the visualization interface.

[0014] One or more technical solutions provided in the present invention have at least the following technical effects or advantages: 1. The road condition analysis system and method based on multi-source data fusion provided by the present invention improve the comprehensiveness, accuracy, and timeliness of road condition analysis, and optimize the utilization efficiency of system resources. Through multi-source data fusion, various road-related data are integrated, which can comprehensively reflect the actual road conditions, avoid the limitations of a single data source, and provide a rich and accurate information basis for analysis. During the analysis process, the road damage risk is accurately evaluated, potential problems are predicted in advance, providing a reliable basis for road maintenance decisions and reducing the safety hazards caused by road diseases. At the same time, the computing resources and visualization display resources are dynamically configured according to the real-time state of the system. On the basis of ensuring the data processing accuracy and real-time performance, resource waste is avoided, and the system operation efficiency is improved to adapt to different road conditions.

[0015] 2. By dynamically configuring the system computing resources and visualization display resources based on the processing mode, the present invention can significantly improve the adaptability and operation efficiency of the system in different working scenarios. In the accuracy priority mode, the system invests more computing resources in data in-depth processing tasks and switches to a high-resolution view, making the road condition analysis results more accurate and detailed, meeting the needs of in-depth research and accurate assessment of road conditions. In the real-time priority mode, the switching of computing resource compression and dynamic summary view ensures that the system can still respond quickly under high load and timely provide users with key road information, meeting the urgent needs of real-time monitoring. The balanced mode reasonably allocates computing resources according to the system data volume fluctuation, avoids resource waste, and maintains the efficient and stable operation of the system.

[0016] 3. By extracting road damage features based on the fusion feature set and conducting road condition analysis, the present invention can timely and accurately evaluate the safety condition of the road. Analyzing based on the feature set generated by fusing multi-source data comprehensively covers all aspects of road information, making the extracted road damage features more comprehensive and accurate. On this basis, risk prediction can be carried out to effectively identify the potential disease risks existing in the road, which helps to formulate a reasonable maintenance plan in advance, take targeted measures, avoid the further deterioration of road diseases, and ensure the normal use of the road and traffic safety.

[0017] 4. By optimizing and adjusting the visualization display resources, the present invention can significantly improve the efficiency and quality of users' access to road condition information. When the road condition analysis is in the second state, the system intelligently reallocates the visualization display resources to highlight important display tasks, while for the first state, the current resource allocation is maintained and relevant information is displayed, which not only avoids resource waste but also ensures that users can view the basic road conditions at any time. Ensure that the information displayed on the visualization interface always matches the actual road risk condition, providing intuitive and effective data support for road management. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1Schematic diagram of the road condition analysis system based on multi-source data fusion provided by the embodiments of the present application; Figure 2 Flowchart of the road condition analysis method based on multi-source data fusion provided by the embodiments of the present application; Detailed implementation manners

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0020] Referring to Figure 1 As shown, the first aspect of the present invention provides a road condition analysis system based on multi-source data fusion, including: A data visualization module, configured to select a processing mode according to the length of the system real-time data processing queue, including a precision priority mode, a real-time priority mode, and a balance mode, and dynamically configure the system computing resources and visualization display resources based on the processing mode.

[0021] In this embodiment, the processing mode is selected according to the length of the system real-time data processing queue, and the specific analysis method is as follows: Obtain the length of the system real-time data processing queue.

[0022] Extract the first queue length threshold and the second queue length threshold preset in the database.

[0023] If the length of the system real-time data processing queue is less than or equal to the first queue length threshold, the processing mode is recorded as the precision priority mode.

[0024] If the length of the system real-time data processing queue is greater than or equal to the second queue length threshold, the processing mode is recorded as the real-time priority mode.

[0025] If the length of the system real-time data processing queue is greater than the first queue length threshold and less than the second queue length threshold, the processing mode is recorded as the balance mode.

[0026] In this embodiment, the system computing resources and visualization display resources are dynamically configured based on the processing mode, and the specific analysis process is as follows: If the processing mode is the precision priority mode, extract the computing resource allocation ratio value according to the length of the system real-time data processing queue, allocate the system computing resources to the data in-depth processing task based on the computing resource allocation ratio value, and synchronously switch the visualization display resources to the high-resolution view.

[0027] In a specific embodiment, a computing resource allocation ratio value is extracted according to the length of the system real-time data processing queue. The specific analysis process is as follows: Subtract the system real-time data processing queue length from the first queue length threshold to obtain the first deviation length of the system real-time data processing queue.

[0028] Extract the allocation ratio values corresponding to each queue deviation length interval stored in the database, and map and extract the allocation ratio value corresponding to the interval where the first deviation length of the system real-time data processing queue is located, which is denoted as the computing resource allocation ratio value.

[0029] It should be understood that the larger the first deviation length of the system real-time data processing queue, the fewer data processing queues the system is currently processing. To make full use of the system computing resources, improve the quality and depth of data processing, and enable data deep processing tasks to obtain more sufficient computing resources to achieve more accurate and detailed analysis of road condition data, the corresponding extracted computing resource allocation ratio value should be larger. In this way, in the precision-first mode, when the system load is low (i.e., there are fewer data processing queues), more computing resources can be tilted towards data deep processing tasks, and at the same time, the visualization display resources can be switched to a high-resolution view so that users can view road condition-related data more clearly and comprehensively, providing more powerful support for road behavior analysis.

[0030] The high-resolution view refers to a refined visualization mode enabled when system resources are sufficient, which displays the results of multi-dimensional data analysis through high rendering precision (such as stress three-dimensional distribution heat map, historical damage trend curve, sensor spatial topology relationship), supports interactive detail magnification and multi-layer overlay, and is applicable to deep diagnosis and offline backtracking scenarios.

[0031] If the processing mode is the real-time priority mode, a computing resource compression ratio is extracted according to the system real-time data processing queue length, and computing resource compression is performed accordingly. At the same time, the visualization display resources are switched to a dynamic summary view.

[0032] In a specific embodiment, a computing resource compression ratio is extracted according to the system real-time data processing queue length. The specific process is as follows: Subtract the second queue length threshold from the system real-time data processing queue length to obtain the second deviation length of the system real-time data processing queue.

[0033] Extract the compression ratios corresponding to each queue deviation length interval stored in the database, and map and extract the compression ratio corresponding to the interval where the second deviation length of the system real-time data processing queue is located, which is denoted as the computing resource compression ratio.

[0034] It should be understood that the larger the second deviation length of the system real-time data processing queue, the more queues the system is processing data for, and the greater the processing pressure the system faces. To ensure that the system can still respond quickly under high load, prioritize the real-time nature of data processing, and avoid processing delays caused by excessive backlog in the data processing queue, it is necessary to optimize resource allocation with limited resources. The corresponding compression ratio of the computing resources extracted should be larger, that is, compress the computing resources to a greater extent, reduce the resources occupied by a single task, so that more tasks can be processed in parallel and the overall processing efficiency can be improved.

[0035] The dynamic summary view refers to a lightweight visualization mode enabled in the resource-constrained or real-time priority mode. It uses data compression and summary generation technologies to only present key metrics (such as maximum stress value, risk level, abnormal area positioning box) and dynamically updated statistical charts (such as scrolling curves, threshold alarm marks), so as to ensure real-time monitoring efficiency with low rendering latency.

[0036] If the processing mode is the balanced mode, the computing resources are dynamically allocated according to the system data volume fluctuation.

[0037] It should be added that the specific process of dynamically allocating computing resources according to the system data volume fluctuation is as follows: Obtain the system data volume fluctuation value from the system program log according to the preset monitoring period.

[0038] Extract the preset data volume fluctuation threshold in the database.

[0039] Subtract the data volume fluctuation threshold from the system data volume fluctuation value to obtain the system data volume fluctuation deviation value.

[0040] It should be noted that the system data volume fluctuation deviation value can be greater than zero, less than zero, or equal to zero.

[0041] Extract the weight adjustment values corresponding to each data volume fluctuation deviation value interval stored in the database, and map and extract the weight adjustment value corresponding to the interval where the system data volume fluctuation deviation value is located, denoted as the second adjustment value of the computing resource allocation weight.

[0042] It should be noted that the larger the positive value of the system data volume fluctuation deviation, the more the data volume fluctuates, which means that the change range of the data volume generated or processed during the system operation is relatively large. In order to make full use of system resources to effectively process a large amount of fluctuating data and ensure the comprehensiveness and accuracy of data processing, the first adjustment value of the extracted weight is positive and the larger it is, so that more computing resources can be allocated to the data source or processing task with large data volume fluctuations, enabling it to better cope with data changes. On the contrary, the larger the absolute value of the negative value of the system data volume fluctuation deviation, the smaller the data volume fluctuates and the data is relatively stable. In this case, in order to avoid resource waste and reasonably optimize the system resource allocation, the first adjustment value of the extracted weight needs to be negative and the larger it is, that is, to reduce the resource allocation to the data source or processing task with small data volume fluctuations, and concentrate more resources on where they are more needed to improve the overall operation efficiency of the system.

[0043] Obtain the initial computing resource allocation weights for each data source.

[0044] Based on the initial computing resource allocation weights of each data source and calculate the first adjustment value of the computing resource allocation weight for each data source to perform dynamic adjustment of the computing resource allocation for each data source The data management module is used to collect the average road stress and stress interference data, analyze the corrected value of the average road stress, and thus obtain the preliminary classification result of the road condition; In this embodiment, the process of analyzing the corrected value of the average road stress and thus obtaining the preliminary classification result of the road condition is as follows: Within a preset collection period, collect the average road stress and stress interference data through the sensing device.

[0045] The stress interference data includes the temperature extreme difference, humidity extreme difference, load extreme difference, and wind speed extreme difference.

[0046] It should be noted that the sensing device includes a temperature sensor, a humidity sensor, a load sensor, a wind speed sensor, and a stress sensor.

[0047] It should be understood that the extreme difference refers to the difference between the maximum and minimum values of the collected data within a period. For example, the temperature extreme difference refers to the difference between the maximum temperature and the minimum temperature within a preset collection period.

[0048] Extract the reference stress interference data stored in the database, including the reference temperature extreme difference, reference humidity extreme difference, reference load extreme difference, and reference wind speed extreme difference.

[0049] Extract the preset temperature extreme difference weight value, humidity extreme difference weight value, load extreme difference weight value, and wind speed extreme difference weight value from the database. It should be noted that the value ranges of the temperature extreme difference weight value, humidity extreme difference weight value, load extreme difference weight value, and wind speed extreme difference weight value are all between 0 and 1. When using, the preset values can be directly extracted from the database. The specific extraction method is, for example, to construct a mapping set for the temperature extreme difference, humidity extreme difference, load extreme difference, and wind speed extreme difference with their corresponding temperature extreme difference weight value, humidity extreme difference weight value, load extreme difference weight value, and wind speed extreme difference one by one. When using, input the temperature extreme difference, humidity extreme difference, load extreme difference, and wind speed extreme difference obtained in real time into the corresponding mapping set, so as to extract the corresponding temperature extreme difference weight value, humidity extreme difference weight value, load extreme difference weight value, and wind speed extreme difference weight value.

[0050] Obtain the stress interference index based on the analysis and processing of the stress interference data.

[0051] The stress interference index represents a quantitative index of the combined stress collection interference degree of the temperature extreme difference, humidity extreme difference, load extreme difference, and wind speed extreme difference. The specific analysis method is to perform differential analysis on the stress interference data and the corresponding reference values, and perform coupling processing on the differential analysis results and the corresponding weight values to obtain the stress interference index.

[0052] It should be noted that there is an interaction between the temperature extreme difference and the humidity extreme difference. For example, when the temperature extreme difference in the environment increases, it will promote the acceleration of the water evaporation rate, and then cause a change in the humidity extreme difference. On the contrary, the change in the humidity extreme difference will also affect the heat transfer and storage, resulting in an impact on the temperature extreme difference.

[0053] In a specific embodiment, the stress interference index is specifically represented as follows: , Among them, is the stress interference index, is the temperature extreme difference, is the humidity extreme difference, is the load extreme difference, is the wind speed extreme difference, is the reference temperature extreme difference, is the reference humidity extreme difference, is the reference load extreme difference, is the reference wind speed extreme difference, is the temperature extreme difference weight value, is the humidity extreme difference weight value, is the load extreme difference weight value, is the wind speed extreme difference weight value.

[0054] Extract the interference correction values corresponding to each stress interference index interval stored in the database, and map to extract the interference correction value corresponding to the interval where the stress interference index is located, denoted as the stress interference correction value.

[0055] It should be understood that the larger the stress interference index, the higher the degree of interference of the temperature extreme difference, humidity extreme difference, load extreme difference, and wind speed extreme difference on stress acquisition. In order to more accurately reflect the true stress condition of the road, when correcting the road stress, for the case of high interference degree, it is necessary to make the extracted stress interference correction value smaller, so as to reasonably reduce the influence of interference factors on the stress acquisition result, make the corrected road stress correction value closer to the actual stress received by the road, thereby improving the accuracy of the road condition pre-classification result and providing a more reliable data basis for subsequent road behavior analysis.

[0056] Perform correction processing on the road average stress combined with the stress interference correction value to obtain the road average stress correction value. Specifically, multiply the road average stress by the stress interference correction value to obtain the road average stress correction value.

[0057] Extract the preset road average stress verification value in the database.

[0058] If the road average stress correction value is less than the road average stress verification value, record the road condition pre-classification result as a road with normal stress.

[0059] It should be understood that if the road average stress correction value is less than the road average stress verification value, it means that after considering the interference of interference factors and making corrections, the average stress borne by the road is within the normal range. This means that the stress on the current road structure is within the acceptable standard, the road is in a relatively stable mechanical state, and there are no obvious abnormalities in its structural integrity and safety in terms of stress. Based on this, it can be initially judged that the road condition is normal.

[0060] If the road average stress correction value is greater than or equal to the road average stress verification value, record the road condition pre-classification result as a road with abnormal stress.

[0061] It should be understood that if the road average stress correction value is greater than the road average stress verification value, it means that after considering the interference of interference factors and making corrections, the stress condition still deviates from the normal level, and there may be potential risks such as structural damage and reduced bearing capacity, which may lead to diseases such as cracks and settlements on the road, affecting the normal use of the road and traffic safety.

[0062] The multi-source data fusion module is used to obtain multi-source data of the road structure based on the road condition pre-classification result, dynamically adjust the sampling frequency and computing resources according to the data fluctuation characteristics, analyze the data confidence level and set the data fusion weight, thereby completing data fusion and generating a fusion feature set; In this embodiment, multi-source data of the road structure is obtained based on the pre-classification result of the road condition, and the sampling frequency and computing resources are dynamically adjusted according to the data fluctuation characteristics. The specific analysis process is as follows: Extract the initial data acquisition frequency set corresponding to the pre-classification result of the road condition preset in the database, and perform multi-source data acquisition of the road structure based on the initial data acquisition frequency set.

[0063] It should be added that if the pre-classification result of the road condition is a normal stress road, it indicates that the current road condition is good, so the corresponding extracted initial data acquisition frequency is low. If the pre-classification result of the road condition is an abnormal stress road, it indicates that the current road condition is abnormal, so the corresponding extracted initial data acquisition frequency is high.

[0064] The initial data acquisition frequency set is the initial data acquisition frequency of each data source.

[0065] The data fluctuation characteristics include the standard deviation of the data sequence and the number of data points.

[0066] It should be added that the number of data points refers to the number of data collected by each data source within a preset second data acquisition window.

[0067] Obtain the standard deviation of the data sequence of each data source based on a preset first data acquisition window.

[0068] Perform a difference operation on the standard deviation of the data sequence of each data source and the standard deviation threshold of the data sequence preset in the database to obtain the data sequence standard deviation deviation factor of each data source.

[0069] It should be noted that the difference operation refers to subtracting the standard deviation threshold of the data sequence preset in the database from the standard deviation of the data sequence of each data source, and the result of the difference operation can be greater than zero, less than zero, or equal to zero.

[0070] Extract the sampling frequency adjustment value corresponding to each standard deviation deviation factor interval stored in the database, and map and extract the sampling frequency adjustment value corresponding to the interval where the data sequence standard deviation deviation factor of each data source is located, denoted as the sampling frequency adjustment value of each data source.

[0071] It should be noted that the larger the positive value of the standard deviation deviation factor of the data sequence, the greater the deviation degree of the standard deviation of the data sequence of each data source compared to the preset standard deviation threshold of the data sequence in the database and the higher it is. In order to more accurately capture the fluctuations of the data, avoid missing key information due to abnormal fluctuations, and obtain more detailed data in a timely manner to accurately analyze the road conditions, the sampling frequency adjustment value should be a positive value and the larger it is, that is, the sampling frequency is increased. On the contrary, the larger the absolute value of the negative value of the standard deviation deviation factor of the data sequence, the greater the deviation degree of the standard deviation of the data sequence of each data source compared to the preset threshold and the lower it is, which means that the data fluctuations are relatively small. In order to reasonably utilize system resources and avoid resource waste caused by excessive collection, the sampling frequency adjustment value should be a negative value and the larger it is, that is, the sampling frequency is decreased.

[0072] Based on the initial data collection frequency set and the sampling frequency adjustment values of each data source, the dynamic adjustment of the sampling frequency is completed.

[0073] In a specific embodiment, for a data source, the specific operation of adjusting the sampling frequency is as follows: adding the sampling frequency adjustment value of the data source to the initial data collection frequency of the data source to obtain the updated value of the sampling frequency of the data source, thereby completing the adjustment of the sampling frequency of the data source.

[0074] Based on the preset second data collection window, the number of data points of each data source is obtained.

[0075] Based on the number of data points of each data source, the calculation resource allocation is dynamically adjusted.

[0076] In this embodiment, the dynamic adjustment of the calculation resource allocation based on the number of data points of each data source is specifically analyzed as follows: Extract the preset verification number of data points in the database.

[0077] Subtract the verification number of data points from the number of data points of each data source to obtain the data deviation number of data points of each data source.

[0078] It should be noted that the data deviation number of data points can be greater than zero, less than zero or equal to zero.

[0079] Extract the weight adjustment values corresponding to the preset intervals of the data deviation number of data points in the database, and map and extract the weight adjustment value corresponding to the interval where the data deviation number of data points of the data source is located, denoted as the first adjustment value of the calculation resource allocation weight.

[0080] It should be noted that the larger the positive value of the data deviation data points, the more the data volume of the data source is larger than the preset verification data points, which means that the data generated by the data source is rich and contains a large amount of information that may be valuable for road condition analysis. In order to process these data more fully, mine the key content therein, and thus analyze the road conditions more accurately, the first adjustment value of the weight corresponding to the extraction is positive and the larger it is, that is, more computing resources are allocated to the data source. On the contrary, the larger the absolute value of the negative value of the data deviation data points, the more the data volume is less than the verification data points, indicating that the data generated by the data source is less and the information contained therein is limited. In order to reasonably optimize the allocation of computing resources and avoid wasting resources on data sources with small data volumes, the first adjustment value of the weight corresponding to the extraction is negative and the larger it is, that is, the computing resources allocated to the data source are correspondingly reduced, so as to concentrate the resources on processing data sources with large data volumes and greater analysis value, thereby improving the efficiency and accuracy of the entire road condition analysis system.

[0081] Obtain the initial computing resource allocation weights of each data source.

[0082] Based on the initial computing resource allocation weights of each data source and calculate the first adjustment value of the computing resource allocation weight of each data source to perform dynamic adjustment of the computing resource allocation of each data source.

[0083] In a specific embodiment, the process of dynamic adjustment of computing resource allocation is as follows: add the first adjustment value of the computing resource allocation weight of a data source to the initial computing resource allocation weight of the data source to obtain the updated value of the computing resource allocation weight of the data source, traverse each data source in turn to obtain the updated values of the computing resource allocation weights of each data source, perform normalization processing on the updated values of the computing resource allocation weights of each data source to obtain the updated implementation values of the computing resource allocation weights of each data source, and perform re-allocation of the computing resources of each data source based on the updated implementation values of the computing resource allocation weights of each data source, thereby completing the dynamic adjustment of the computing resource allocation of each data source.

[0084] In this embodiment, analyze the data confidence and set the data fusion weight, thereby completing the data fusion and generating a fusion feature set. The specific analysis process is as follows: Obtain the basic parameters of the sensing devices corresponding to each data source with a preset third data acquisition window, denoted as the basic parameters of each sensing device.

[0085] The basic parameters of each sensing device include the average signal amplitude, average signal drift amount, power supply voltage fluctuation amount, and average working circuit temperature of each sensing device.

[0086] It should be understood that the power supply voltage fluctuation amount refers to the difference between the maximum value and the minimum value of the power supply voltage within a preset third data acquisition window. By connecting a voltage sensor to the power supply circuit of the sensing device, the change of the power supply voltage is monitored in real time.

[0087] It should be noted that the average signal amplitude and the average signal drift amount can be obtained through a signal acquisition circuit and a signal processing algorithm. When the sensing device acquires data, the internal signal conditioning circuit first performs preprocessing such as filtering and amplifying on the original signal, and then converts the analog signal into a digital signal through analog-to-digital conversion. Using digital signal processing technology, statistical analysis of the signal within a period of time can calculate the average signal amplitude and the average signal drift amount. For example, the sliding window algorithm is used to calculate the mean value and the drift amount of the signal within consecutive time windows.

[0088] The average temperature of the working circuit can be collected by a thermistor.

[0089] Extract the basic parameters of the reference sensing device stored in the database, including the reference average signal amplitude, the reference average signal drift amount, the reference power supply voltage fluctuation amount, and the reference average temperature of the working circuit.

[0090] Analyze the data confidence of each sensing device according to the basic parameters of each sensing device.

[0091] In this embodiment, by analyzing the data confidence of each sensing device according to the basic parameters of each sensing device, the mutual influence between these parameters is considered. For example, when the average temperature of the working circuit increases, the performance of electronic components will change, which may cause the average signal drift amount to increase, and may also affect the transmission and amplification of the signal, thereby changing the average signal amplitude. The change of the power supply voltage fluctuation amount will directly affect the power supply stability of the circuit. Unstable voltage may interfere with signal transmission, resulting in fluctuations in the average signal amplitude, and will also affect the normal operation of electronic components, causing changes in the average signal drift amount. The abnormal change of the average signal amplitude may mean a change in the working state of the circuit, which will further affect the average temperature of the working circuit, and at the same time reflect the instability of the power supply voltage fluctuation amount or other factors, further affecting the average signal drift amount.

[0092] The data confidence of each sensing device represents the quantitative data of the degree of influence of the average signal amplitude, the average signal drift amount, the power supply voltage fluctuation amount, and the average temperature of the working circuit of each sensing device on the credible state of the data source. Specifically, it is expressed as performing differential analysis on the basic parameters of the sensing device and the corresponding reference values respectively, and performing coupling analysis on the differential results combined with the corresponding weights to obtain the data confidence of each sensing device.

[0093] In a specific embodiment, the specific method for obtaining the data confidence of each sensing device is as follows: , wherein, is the data confidence of the i-th sensing device, is the average signal amplitude of the i-th sensing device, is the average signal drift of the i-th sensing device, is the power supply voltage fluctuation of the i-th sensing device, is the average temperature of the working circuit of the i-th sensing device, is the reference average signal amplitude, is the reference average signal drift, is the reference power supply voltage fluctuation, is the reference average temperature of the working circuit, is the weight of the average signal amplitude, is the weight of the average signal drift, is the weight of the power supply voltage fluctuation, is the weight of the average temperature of the working circuit.

[0094] It should be noted that the value ranges of the weight of the average signal amplitude, the weight of the average signal drift, the weight of the power supply voltage fluctuation, and the weight of the average temperature of the working circuit are all between 0 and 1. When used, the preset values can be directly extracted from the database. For example, the specific extraction method is to construct a one-to-one mapping set between the average signal amplitude, the average signal drift, the power supply voltage fluctuation, and the average temperature of the working circuit and the corresponding weights of the average signal amplitude, the average signal drift, the power supply voltage fluctuation, and the average temperature of the working circuit one by one. When used, the average signal amplitude, the average signal drift, the power supply voltage fluctuation, and the average temperature of the working circuit obtained in real time are respectively input into the corresponding mapping sets, so as to extract the corresponding weights of the average signal amplitude, the average signal drift, the power supply voltage fluctuation, and the average temperature of the working circuit.

[0095] Extract the fusion weights corresponding to each confidence interval stored in the database, and map and extract the fusion weight corresponding to the interval where the data confidence of the sensing device is located, denoted as the data fusion weight.

[0096] It should be understood that the greater the data confidence level, the higher the degree of influence of factors such as the average signal amplitude, average signal drift, power supply voltage fluctuation, and average operating circuit temperature of each sensing device on the credibility state of the data source when combined, that is, the stronger the data reliability and the higher the credibility of the data source. In order to give full play to the value of high-credibility data during the multi-source data fusion process and enable the fused feature set to more accurately and reliably reflect the road conditions, the corresponding data fusion weight extracted will be greater. In this way, when performing data fusion, high-confidence data will occupy a larger proportion in the fusion result, thereby improving the accuracy and reliability of the entire road condition analysis.

[0097] Statistically calculate the data fusion weights of each data source, and perform normalization processing to obtain the fusion weights corresponding to each data source, denoted as the data fusion weights of each data source.

[0098] Based on the data fusion weights of each data source, set the data fusion weights, and thereby perform the data fusion of each data source to generate a fused feature set.

[0099] It should be added that the purpose of normalizing the data fusion weights of each data source is to make the sum of each weight equal to 1, so as to allocate the data fusion weights of each data source.

[0100] It should be noted that in a specific embodiment, model-level fusion can be used for data fusion.

[0101] The feature extraction and warning module is used to extract road damage features based on the fused feature set, perform road condition analysis, thereby optimize the adjustment of visualization display resources, and synchronously display the road condition analysis results and resource allocation status through a visualization interface.

[0102] In this embodiment, based on the fused feature set, extract road damage features and perform road condition analysis. The specific analysis steps are as follows: Extracting road damage features based on the fused feature set includes road surface flatness, maximum crack width, and settlement.

[0103] In a specific embodiment, the road surface flatness can be obtained through time-domain analysis based on the fused feature set. Specifically: obtain the vibration acceleration signal based on the fused feature set, and determine the road surface flatness according to the root mean square value of the vibration acceleration signal. The larger the root mean square value of the vibration acceleration signal, the more uneven the road surface.

[0104] The maximum crack width can be obtained by performing edge detection on the image data of the fused feature set to locate the maximum crack and obtain the maximum crack width.

[0105] The settlement can be obtained by extracting strain displacement through the fused feature set.

[0106] Extract the reference road damage characteristics stored in the database, including reference road smoothness, reference maximum crack width, and reference settlement amount.

[0107] Obtain the road damage risk assessment value through analysis and processing based on the road damage characteristics.

[0108] In a specific embodiment, obtaining the road damage risk assessment value through analysis and processing based on the road damage characteristics takes into account the mutual influence of these parameters. For example, when there is a settlement amount on the road, it will disrupt the original road smoothness, causing uneven forces on the vehicle when driving on this section and further exacerbating the damage to the road surface. Over time, this unevenness will lead to local stress concentration on the road surface. In the stress concentration area, cracks are more likely to appear on the road surface and the maximum crack width will continue to expand. The increase in crack width will, in turn, reduce the overall strength and stability of the road surface, making the road surface more likely to generate new settlements under external forces such as vehicle loads, further deteriorating the road smoothness. In addition, poor road smoothness will cause a greater impact force on the road surface when the vehicle is driving, which will not only accelerate the development of settlements but also prompt the further expansion of cracks and increase the maximum crack width.

[0109] The road damage risk assessment value is quantitative data on the degree of influence of road smoothness, maximum crack width, and settlement amount on the road damage state. Specifically, it is obtained by differentiating the road damage characteristics from the corresponding reference values respectively and then coupling the differentiation results with the corresponding weights.

[0110] In a specific embodiment, the method for specifically obtaining the road damage risk assessment value is as follows: , wherein, is the road damage risk assessment value, is the road smoothness, is the maximum crack width, is the settlement amount, is the reference road smoothness, is the reference maximum crack width, is the reference settlement amount, is the weight value of road smoothness, is the weight value of maximum crack width, is the weight value of settlement amount.

[0111] It should be noted that the value ranges of the road evenness weight, the maximum crack width weight, and the settlement amount weight are all between 0 and 1. When used, the preset values can be directly extracted from the database. For example, the specific extraction method is to construct a one-to-one mapping set between the road evenness, the maximum crack width, and the settlement amount and their corresponding weights. When used, the real-time obtained road evenness, the maximum crack width, and the settlement amount are input into the corresponding mapping sets one by one, so as to extract the corresponding road evenness weight, the maximum crack width weight, and the settlement amount weight.

[0112] Extract the preset road damage risk assessment threshold from the database.

[0113] If the road damage risk assessment value is less than or equal to the road damage risk assessment threshold, record the road condition analysis result as the first condition.

[0114] If the road damage risk assessment value is less than or equal to the road damage risk assessment threshold, it means that after comprehensive evaluation based on damage characteristics such as road evenness, crack degree, and settlement amount, the damage risk faced by the road is within an acceptable range. The current conditions of the road are relatively good, its structural integrity and service performance are not greatly threatened, the road damage risk is small, and the current road condition is good.

[0115] If the road damage risk assessment value is greater than the road damage risk assessment threshold, record the road condition analysis result as the second condition.

[0116] If the road damage risk assessment value is greater than the road damage risk assessment threshold, it means that the damage risk of the road analyzed based on evenness, crack degree, and settlement amount has exceeded the normal safety standard. The road has a high damage risk and may have relatively serious diseases, such as large-area unevenness, excessive crack width, or serious settlement. The road damage risk is large, and the current road condition is low.

[0117] In this embodiment, the optimization adjustment of the visualization display resources is carried out accordingly, and the road condition analysis result and the resource allocation status are displayed through the visualization interface. The specific analysis steps are as follows: If the road condition analysis result is the second condition, the optimization adjustment of the visualization display resources is carried out. The specific optimization adjustment steps are as follows: Extract the importance ratio and the importance ratio threshold of each road condition display task preset in the database.

[0118] Record the road condition display task with an importance ratio less than the importance ratio threshold as an unimportant display task.

[0119] Record the road condition display task with an importance ratio greater than or equal to the importance ratio threshold as an important display task.

[0120] Traverse each road condition display task in sequence, and thus statistically obtain each important display task and each non-important display task.

[0121] Extract the importance ratios corresponding to each important display task and each non-important display task based on the importance ratios of each road condition display task, and perform normalization processing respectively to obtain the updated importance ratios of each important display task and the updated importance ratios of each non-important task.

[0122] Extract the resource increase amounts corresponding to each risk assessment value interval stored in the database, and map and extract the resource increase amount corresponding to the interval where the road damage risk assessment value is located, denoted as the increased resource demand for visual display.

[0123] Analyze and obtain the released resource demand for visual display of each non-important task based on the updated importance ratios of each non-important task and the increased resource demand for visual display.

[0124] Increase the visual display resources of each important display task according to the updated importance ratios of each important display task and the increased resource demand for visual display, thereby completing the dynamic adjustment of the visual display resources.

[0125] If the result of the road condition analysis is the first condition, do not perform optimization adjustment of the computing resources, and display the result of the road condition analysis and the current resource allocation status through the visual interface.

[0126] Refer to Figure 2 As shown, the second aspect of the present invention provides a road condition analysis method based on multi-source data fusion, including the following steps: S1. Select a processing mode according to the length of the system real-time data processing queue, including the accuracy priority mode, the real-time priority mode, and the balance mode, and dynamically configure the system computing resources and visual display resources based on the processing mode.

[0127] S2. Collect the average road stress and stress interference data, analyze the corrected value of the average road stress, and thus obtain the preliminary classification result of the road condition.

[0128] S3. Obtain multi-source data of the road structure based on the preliminary classification result of the road condition, dynamically adjust the sampling frequency and computing resources according to the data fluctuation characteristics, analyze the data confidence level and set the data fusion weight, and thus complete the data fusion and generate a fusion feature set.

[0129] S4. Extract road damage characteristics based on the fusion feature set, perform road condition analysis, and thus optimize and adjust the visual display resources, and simultaneously display the result of the road condition analysis and the resource allocation status through the visual interface.

[0130] Those skilled in the art will appreciate that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can 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.) that contain computer-usable program code.

[0131] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0132] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are performed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0134] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0135] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.

Claims

1. The road behavior analysis system based on multi-source data fusion is characterized by: The following steps are involved: Data visualization module, used to select processing mode according to the length of the system real-time data processing queue, including accuracy priority mode, real-time priority mode and balance mode, and dynamically configure system computing resources and visualization display resources based on the processing mode; A data management module is used to collect road average stress and stress interference data, analyze the road average stress correction value, and thereby obtain the road condition pre-classification result; The multi-source data fusion module is used to obtain multi-source data of road structure based on the pre-classification results of road conditions, dynamically adjust the sampling frequency and computing resources according to the data fluctuation characteristics, analyze the data confidence and set the data fusion weight, thereby completing data fusion and generating a fusion feature set; The feature extraction and warning module is used to extract road damage features based on the fused feature set, conduct road performance analysis, optimize and adjust the visualization resources, and simultaneously display the road performance analysis results and resource allocation status through the visualization interface.

2. The road behavior analysis system based on multi-source data fusion as claimed in claim 1, characterized in that: The processing mode is selected according to the length of the real-time data processing queue of the system. The specific analysis method is as follows: Get the length of the system's real-time data processing queue; Extracting a first queue length threshold and a second queue length threshold preset in a database; If the length of the system real-time data processing queue is less than or equal to the first queue length threshold, the processing mode is recorded as the accuracy priority mode; If the length of the system real-time data processing queue is greater than or equal to the second queue length threshold, the processing mode is recorded as the real-time priority mode; If the length of the system real-time data processing queue is greater than the first queue length threshold and less than the second queue length threshold, the processing mode is recorded as the balanced mode.

3. The road behavior analysis system based on multi-source data fusion as claimed in claim 1, characterized in that: The specific analysis process of dynamically configuring system computing resources and visual display resources based on processing mode is as follows: If the processing mode is the precision priority mode, the computing resource allocation ratio value is extracted according to the system real-time data processing queue length, and the system computing resources are allocated to the data depth processing tasks based on the computing resource allocation ratio value, and the visualization display resources are switched to the high-resolution view simultaneously; If the processing mode is the real-time priority mode, the computing resource compression ratio is extracted according to the length of the system real-time data processing queue, and the computing resources are compressed accordingly, and the visual display resources are switched to the dynamic summary view simultaneously; If the processing mode is balanced mode, computing resources are dynamically allocated according to the fluctuation of system data volume.

4. The road behavior analysis system based on multi-source data fusion as claimed in claim 1, characterized in that: The analysis of the average road stress correction value, thereby obtaining the road condition pre-classification result, is specifically performed as follows: Within a preset collection period, the average stress and stress disturbance data of the road are collected by the sensor device; The stress interference data include temperature extreme value difference, humidity extreme value difference, load extreme value difference and wind speed extreme value difference; According to the stress interference data analysis and processing, the stress interference index is obtained; The stress interference index represents a quantitative index of the degree of interference of the temperature extreme value difference, humidity extreme value difference, load extreme value difference and wind speed extreme value difference on stress collection. The specific analysis method is to perform differential analysis on the stress interference data and the corresponding reference value, and couple the differential analysis result with the corresponding weight value to obtain the stress interference index; Extract the interference correction value corresponding to each stress interference index interval stored in the database, and map the interference correction value corresponding to the interval where the stress interference index is located, which is recorded as the stress interference correction value; The road average stress is combined with the stress interference correction value to obtain the road average stress correction value; Extract the road average stress verification value preset in the database; If the road average stress correction value is less than the road average stress verification value, the road condition pre-classification result is recorded as a normal stress road; If the road average stress correction value is greater than or equal to the road average stress verification value, the road condition pre-classification result is recorded as an abnormal stress road.

5. The road behavior analysis system based on multi-source data fusion as claimed in claim 1, characterized in that: The multi-source data of road structure is obtained based on the road condition pre-classification results, and the sampling frequency and computing resources are dynamically adjusted according to the data fluctuation characteristics. The specific analysis process is as follows: Extracting an initial data collection frequency set corresponding to a road condition pre-classification result preset in a database, and performing multi-source data collection of a road structure based on the initial data collection frequency set; The initial data collection frequency set is the initial data collection frequency of each data source; The data fluctuation characteristics include the data sequence standard deviation and the number of data points; Obtaining a data series standard deviation of each data source based on a preset first data collection window; Perform difference processing on the data sequence standard deviation of each data source and the data sequence standard deviation threshold preset in the database to obtain the data sequence standard deviation deviation factor of each data source; Extract the sampling frequency adjustment value corresponding to each standard deviation deviation factor interval stored in the database, and map and extract the sampling frequency adjustment value corresponding to the interval where the standard deviation deviation factor of the data sequence of each data source is located, and record it as the sampling frequency adjustment value of each data source; Dynamically adjust the sampling frequency based on the initial data collection frequency set and the sampling frequency adjustment value of each data source; Acquire the number of data points from each data source based on a preset second data collection window; Dynamically adjust computing resource allocation based on the number of data points in each data source.

6. The road behavior analysis system based on multi-source data fusion as claimed in claim 5, characterized in that: The specific analysis process of dynamically adjusting the computing resource allocation based on the number of data points of each data source is as follows: Extract the preset verification data points in the database; Subtract the number of verification data points from the number of data points of each data source to obtain the number of data deviation data points of each data source; Extract the weight adjustment value corresponding to each data deviation data point number interval preset in the database, and map the weight adjustment value corresponding to the interval where the data deviation data point number of the extracted data source is located, and record it as the first adjustment value of the computing resource allocation weight; Obtaining the initial computing resource allocation weights of each data source; Dynamic adjustment of the computing resource allocation of each data source is performed based on the initial computing resource allocation weight of each data source and the first adjustment value of the computing resource allocation weight of each data source.

7. The road behavior analysis system based on multi-source data fusion as claimed in claim 1, characterized in that: The data confidence is analyzed and the data fusion weight is set, thereby completing the data fusion and generating a fusion feature set. The specific analysis process is as follows: Acquire basic parameters of the sensor devices corresponding to each data source in a preset third data acquisition window, and record them as basic parameters of each sensor device; The basic parameters of each sensor device include the average signal amplitude, average signal drift, power supply voltage fluctuation and average working circuit temperature of each sensor device; Analyze the confidence of data of each sensor device according to the basic parameters of each sensor device; The data confidence of each sensor device represents the quantitative data of the influence degree of the average signal amplitude, average signal drift, power supply voltage fluctuation and average working circuit temperature of each sensor device on the trustworthy state of the data source, which is specifically expressed as performing differential analysis on the basic parameters of the sensor device and the corresponding reference values, and performing coupling analysis on the differential results combined with the corresponding weights to obtain the data confidence of each sensor device; Extract the fusion weight corresponding to each confidence interval stored in the database, and map the fusion weight corresponding to the interval where the confidence of the sensor device data is located, which is recorded as the data fusion weight; The data source data fusion weights corresponding to each data source are counted, and normalized to obtain the fusion weights corresponding to each data source, which are recorded as the data fusion weights of each data source; The data fusion weight is set based on the data fusion weight of each data source, thereby fusing the data of each data source to generate a fusion feature set.

8. The road behavior analysis system based on multi-source data fusion as claimed in claim 1, characterized in that: The road damage features are extracted based on the fusion feature set to perform road behavior analysis. The specific analysis steps are as follows: Extract road damage features based on the fused feature set, including road smoothness, maximum crack width, and settlement; Obtain a road damage risk assessment value based on road damage characteristic analysis and processing; The road damage risk assessment value is quantitative data of the influence of road flatness, maximum crack width and settlement on the road damage state, which is specifically expressed as differentiating the road damage characteristics with the corresponding reference values, and coupling the differentiation results with the corresponding weights to obtain the road damage risk assessment value; Extracting the preset road damage risk assessment threshold value in the database; If the road damage risk assessment value is less than or equal to the road damage risk assessment threshold, the road state analysis result is recorded as the first state; If the road damage risk assessment value is greater than the road damage risk assessment threshold, the road state analysis result is recorded as the second state.

9. The road behavior analysis system based on multi-source data fusion as claimed in claim 1, characterized in that: The optimization adjustment of resources is performed by visual display, and the road performance analysis results and resource allocation status are displayed through the visual interface simultaneously. The specific analysis steps are as follows: If the road state analysis result is the second state, the visualization display resources are optimized and adjusted. The specific optimization and adjustment steps are as follows: Extract the importance ratio and importance ratio threshold of each road condition display task preset in the database; The road condition display tasks whose importance ratio is less than the importance ratio threshold are recorded as non-important display tasks; The road condition display tasks whose importance ratio is greater than or equal to the importance ratio threshold are recorded as important display tasks; Traverse each road condition display task in turn, thereby obtaining each important display task and each non-important display task by counting; Based on the importance ratio of each road condition display task, the importance ratios of each important display task and each non-important display task are extracted, and normalized respectively to obtain the importance update ratio of each important display task and the importance update ratio of each non-important task; Extract the resource increase corresponding to each risk assessment value interval stored in the database, and map the resource increase corresponding to the interval where the road damage risk assessment value is located, and record it as the visual display resource demand increase; According to the updated importance ratio of each non-important task and the increase in the visual display resource demand, the release amount of the visual display resource demand of each non-important task is obtained; The visualization display resources of each important display task are increased according to the updated importance ratio of each important display task and the increase in the demand for visualization display resources, thereby completing the dynamic adjustment of the visualization display resources; If the road behavior analysis result is the primary state, no optimization adjustment of computing resources is performed, and the road behavior analysis result and the current resource allocation status are displayed through a visual interface.

10. The method for road behavior analysis system based on multi-source data fusion according to any one of claims 1 to 9, characterized in that: include: S1, selects a processing mode according to the length of the system real-time data processing queue, including accuracy priority mode, real-time priority mode and balance mode, and dynamically configures system computing resources and visualization display resources based on the processing mode; S2, collecting road average stress and stress interference data, analyzing the road average stress correction value, and thereby obtaining a road condition pre-classification result; S3, based on the road condition pre-classification results, obtain multi-source data of road structure, dynamically adjust sampling frequency and computing resources according to data fluctuation characteristics, analyze data confidence and set data fusion weights, thereby completing data fusion and generating a fusion feature set; S4, extracts road damage features based on the fused feature set, performs road behavior analysis, optimizes and adjusts visualization resources, and simultaneously displays road behavior analysis results and resource allocation status through a visualization interface.

Images