Road traffic intelligent operation and maintenance method and system based on multi-source data fusion

Abstract

The invention relates to the technical field of data analysis, in particular to a road traffic intelligent operation and maintenance method and system based on multi-source data fusion, and the method comprises the steps: constructing a three-dimensional model through a credibility calculation module by integrating three types of factors, namely a road environment, an equipment state and historical verification, generating a dynamically updated credibility index, and correcting a weight in real time based on feedback; the problem that the reliability of the multi-source data fluctuates dynamically due to the influence of environmental interference, equipment aging and historical deviation is solved; the road feature conflict resolution module maps to feature dimensions corresponding to road topology conflict features through dynamic credibility indexes, constructs a road conflict decision matrix, and fuses and generates a road anomaly decision set with credible labels according to the feature dimensions; the resource scheduling module is used for dividing three-level response areas based on credible indexes, executing accurate scheduling of triple constraints in combination with device priorities and credible labels and generating a resource-decision association graph, and self-adaptive optimal configuration of limited maintenance resources according to data reliability is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data analysis, in particular to a multi-source data fusion road traffic intelligent operation method and system. BACKGROUND

[0002] The existing road traffic operation system highly depends on heterogeneous multi-source data (such as road network monitoring sensor data, environmental sensor data, historical maintenance records, dynamic traffic flow data, etc.), but in actual application, it faces significant technical challenges:

[0003] Due to differences in collection accuracy, fluctuations in the running state of the device itself, external environmental interference (such as the influence of bad weather on the sensor), and the lack of completeness of historical verification information, the reliability of the data itself is significantly different and presents dynamic fluctuations, which directly weakens the reliability basis for decision-making.

[0004] At the same time, frequent conflicts in feature level occur between multi-source data, such as inconsistency in the judgment of the state of the same road segment by different devices (geometric shape or topological connection contradiction), and logical deviation of historical data patterns and real-time observation data. Existing methods cannot efficiently and objectively identify and fuse these conflicting features, resulting in confusion in decision-making basis.

[0005] In addition, traditional resource scheduling mechanisms are mostly based on static rules or preset thresholds, and cannot effectively respond to real-time reliability changes and conflict resolution results of multi-source data, resulting in a lack of precision and dynamic adaptability in resource allocation strategies, often showing response lag or resource mismatch.

[0006] Therefore, there is an urgent need for an intelligent operation system that can fuse multi-source data, dynamically quantify the reliability of the data, automatically resolve feature conflicts, and implement intelligent hierarchical scheduling of resources based on the above. SUMMARY

[0007] The present application relates to the technical field of data analysis, in particular to a multi-source data fusion road traffic intelligent operation method and system.

[0008] How to build a dynamic reliability evaluation model that fuses road environment, device state and verification history three-dimensional factors to solve the dynamic fluctuation problem caused by environmental interference, device aging and historical deviation of multi-source data reliability;

[0009] How to realize automatic resolution of multi-source road features based on reliability dimension and generation of decision-making set with trust label, and combine regional hierarchical response, device priority and trust label to implement precise resource scheduling, to solve the problem of decision confusion and resource rigid scheduling caused by multi-source data conflict.

[0010] In order to achieve the above-mentioned purpose, the present application aims at a multi-source data fusion road traffic intelligent operation and maintenance system, comprising a credibility calculation module, a road feature conflict resolution module and a resource credibility hierarchical scheduling module, wherein:

[0011] The credibility calculation module constructs a credibility three-dimensional evaluation model covering three dimensions of road environment factors (meteorological conditions, road surface physical conditions, traffic load characteristics), equipment state factors (operation stability, fault records, maintenance history) and verification factors (historical maintenance task success rate, time deviation, problem recurrence rate); the three types of factors are respectively mapped to the environment dimension, the equipment dimension and the verification dimension; the multidimensional integration model of the Bayesian network is used to analyze the complex nonlinear interaction between the factors in real time; after standardization preprocessing to eliminate the dimension difference, a dynamic weighting strategy is used to calculate the synergistic influence coefficient of the three dimensions; finally, a dynamic credibility index which is continuous and quantized and is dynamically updated with the state of each type of factor is generated by integrating the output values of the three dimensions through a weighted linear integration method, so as to overcome the limitations of a single index and provide a comprehensive, real-time and quantitative data reliability index;

[0012] The credibility calculation module automatically reallocates the weights of the road environment factors, the equipment state factors and the verification factors in the credibility three-dimensional evaluation model according to the real maintenance execution feedback data (such as the deviation between the task execution result and the model prediction) provided by the verification factors through the iterative learning method, so that the evaluation model has the ability of self-learning evolution and continuously improves the prediction accuracy.

[0013] The road feature conflict resolution module automatically detects the road geometric shape conflicts, topological connection logic conflicts and attribute level contradictions and other feature conflicts in the multi-source data through its decision matrix construction unit and the spatial feature analysis algorithm; the core innovation is that the dynamic credibility index generated by the credibility calculation module is accurately mapped to the corresponding credibility dimension according to the type of the conflict feature (such as the environment-related conflict associated with the environment factor dimension credibility value, the geometric shape conflict associated with the equipment state factor dimension credibility value, and the historical data conflict associated with the verification factor dimension credibility value); through this mapping mechanism, each identified conflict feature is endowed with the credibility value inherited from a specific dimension, thereby generating a road conflict decision matrix with a credibility label; thereby the abstract credibility index is landed to the specific conflict point, and the severity or reliability of the conflict is quantified.

[0014] The fusion unit in the road feature conflict resolution module adopts a weighted evidence fusion algorithm to aggregate meteorological relevance conflict evidence in the environmental credibility dimension, integrate sensor source data conflict evidence in the device credibility dimension, and fuse historical maintenance feedback conflict evidence in the verification credibility dimension. In this way, conflict evidence from different credibility dimensions is fused, and a road anomaly decision set containing three types of reliability labels, i.e., "environmental credibility label", "device credibility label" and "verification credibility label", is finally generated, thereby comprehensively resolving conflicts and providing clear, hierarchical and reliability-labeled decision basis for subsequent scheduling.

[0015] The resource credibility hierarchical scheduling module dynamically divides the entire road area into three levels of high credibility response area, medium credibility response area and low credibility response area based on a dynamic credibility index, using a continuous function segmentation mechanism (threshold setting), thereby macroscopically identifying the overall reliability level of the area and guiding the resource deployment framework

[0016] The generation of the scheduling strategy strictly follows three constraints, specifically including:

[0017] The total amount and type of resources are determined according to the level of the divided response area (e.g., high credibility area equipped with fast response units to pursue efficiency, and low credibility area deployed with intensive inspection groups to strengthen investigation); the coverage and inspection order of key equipment are sorted by referring to the equipment weight priority parameter stored in the road conflict decision matrix; the credibility labels (environment / device / verification) of each anomaly in the road anomaly decision set are combined for fine filtering and processing (e.g., anomaly items with a verification credibility label below a certain threshold are downgraded or prioritized for review); thereby achieving precise deployment of resources according to the overall reliability level of the area, the criticality of the equipment, and the individual credibility of the specific anomaly item;

[0018] The resource credibility hierarchical scheduling module constructs a resource-decision set association graph, the rule of which is to take each anomaly item in the road anomaly decision set as a node and take the maintenance resource type as the edge attribute connecting these nodes; the graph automatically establishes dynamic associations, in which anomaly nodes in the high credibility response area are preferentially connected to automated maintenance resource units; anomaly nodes with high device credibility labels are automatically associated with professional detection equipment resources; nodes with verification credibility warning labels are bound to a special review and verification team, thereby intuitively displaying the matching relationship between resources and specific decision items and improving scheduling transparency and efficiency.

[0019] The second object of the present application is to provide a method for operating a road traffic intelligent operation system based on multi-source data fusion, comprising the following method steps:

[0020] S1, a credibility three-dimensional evaluation model for road operation and maintenance is constructed, wherein input parameters of the credibility three-dimensional evaluation model include road environment factors, device state factors and verification factors, a dynamic credibility index is generated by multi-factor coupling by using the credibility three-dimensional evaluation model, and the weight of the credibility three-dimensional evaluation model is corrected in real time based on maintenance execution feedback of the verification factors;

[0021] S2, road topological conflict features in multi-source data are identified, the road topological conflict features are mapped to feature dimensions corresponding to the road topological conflict features through the dynamic credibility index, a road conflict decision matrix is constructed, and a road anomaly decision set with a credibility label is generated by fusion according to the feature dimensions;

[0022] S3, a road area is divided into three response zones based on the dynamic credibility index, a credible hierarchical scheduling is performed in combination with a device weight priority in the road conflict decision matrix and a credibility label in the road anomaly decision set, and a resource-decision set correlation graph is generated.

[0023] Compared with the prior art, the beneficial effects of the present application are:

[0024] The present application aims to improve the intelligent level and efficiency of road traffic intelligent operation and maintenance. Firstly, by generating a three-dimensional credibility model and a dynamic index, the reliability of multi-source data is quantified and dynamically evaluated, providing a solid and reliable foundation for subsequent decision-making. Secondly, feature conflict resolution and the generation of a decision set with a credibility label efficiently solve the multi-source data conflict problem, improving the objectivity and accuracy of the decision basis. Finally, based on the credibility grading and the resource scheduling and correlation graph of the three constraints, the precise and dynamic on-demand allocation of maintenance resources is realized, significantly optimizing the resource utilization rate, improving the timeliness and overall efficiency of operation and maintenance response, and effectively ensuring road safety and smoothness. BRIEF DESCRIPTION OF DRAWINGS

[0025] Figure 1 It is a schematic diagram of the overall module unit of the present application.

[0026] Figure 2 It is a schematic diagram of the overall method steps of the present application.

[0027] In the figure: 100, credibility calculation module; 200, road feature conflict resolution module; 201, decision matrix construction unit; 202, fusion unit; 300, resource credibility hierarchical scheduling module. DETAILED DESCRIPTION

[0028] In order to more clearly understand the purpose, technical scheme and advantages of the present application, the present application is described and explained below in conjunction with the drawings and examples.

[0029] Unless otherwise defined, technical terms or scientific terms used in the present application shall have the same meaning as those commonly understood by a person having ordinary skill in the art to which the present application belongs. In the present application, the terms "one", "a", "an", "the", "these", and similar words do not indicate a quantity restriction, and they can be singular or plural. In the present application, the terms "include", "contain", "have", and any variants thereof are intended to cover non-exclusive inclusion; for example, a process, method, and system, product or device containing a series of steps or modules (units) are not limited to the listed steps or modules (units), but can include steps or modules (units) not listed, or can include other steps or modules (units) inherent to the process, method, product or device. In the present application, the terms "connected", "connected", "coupled" and the like do not limit to physical or mechanical connection, but can include electrical connection, whether direct or indirect. In the present application, "multiple" means two or more. "And / or" describes the association between the associated objects, which means that there can be three relationships, for example, "A and / or B" can mean that A exists alone, A and B exist together, and B exists alone. Generally, the character " / " represents an "or" relationship between the objects before and after. In the present application, the terms "first", "second", "third", and the like are only used to distinguish similar objects, and do not represent a specific order of the objects.

[0030] Next, please refer to Figure 1 One of the purposes of the present embodiment is a multi-source data fusion road traffic intelligent operation system, which comprises a credibility calculation module 100, a road feature conflict resolution module 200 and a resource credibility hierarchical scheduling module 300.

[0031] The core task of the credibility calculation module 100 is to build a credibility three-dimensional evaluation model for road operation. The model is built by the following steps:

[0032] Input parameter mapping: mapping road environment factors to environment dimension, device state factors to device dimension, and verification factors to verification dimension;

[0033] Nonlinear relationship analysis: real-time analysis of nonlinear interaction between factors through a multidimensional integration model of Bayesian network;

[0034] Standardization and weighting: standardization preprocessing is performed on each dimension factor to eliminate dimensional difference, and the synergistic influence coefficient of environment / device / verification dimension is calculated based on dynamic weighting strategy;

[0035] Generation of dynamic credibility index: a weighted linear integration method is used to fuse three-dimensional output values to generate a dynamic credibility index.

[0036] The credibility three-dimensional evaluation model quantifies the reliability performance of the road system in the operation and maintenance process by fusing multi-dimensional input parameters. Specifically, the input parameters include road environment factors, device state factors, and verification factors, wherein:

[0037] The road environment factor covers factors such as weather conditions (including temperature, precipitation, etc.), road physical conditions (such as crack or pothole degree), and traffic load characteristics. This factor is collected in real time by a sensor network and pre-processed into structured data;

[0038] The device state factor focuses on the operation health of road monitoring devices (such as cameras or sensors), including their working stability, fault records, and maintenance history, to ensure the accuracy of their output data;

[0039] The verification factor is the actual feedback data of historical maintenance execution records, such as the success rate of previous maintenance tasks, time deviation, and problem recurrence rate, which serves as a benchmark for the calibration of the credibility three-dimensional evaluation model;

[0040] In the construction phase of the credibility three-dimensional evaluation model, the road environment factor, device state factor, and verification factor are mapped to the pre-set three dimensions (environment, device, and verification) to form a coupling framework. This framework uses a weighted linear integration method combined with interaction analysis between factors to generate a dynamic credibility index. The dynamic credibility index is generated through a multi-factor coupling algorithm that fuses factor values in real time into a continuous quantitative indicator to reflect the dynamic fluctuation state of the overall operation and maintenance credibility of the road. The process of generating the dynamic credibility index through multi-factor coupling is as follows:

[0041] The road environment factor, device state factor, and verification factor are input into the credibility three-dimensional evaluation model. Through the pre-set factor-dimension mapping mechanism, a coupling algorithm based on a multi-dimensional integration model, i.e., a Bayesian network, is used to analyze the non-linear interaction between factors in real time. Specifically, it includes:

[0042] First, through the pre-set mapping mechanism, the road environment factor (such as weather conditions, road physical conditions) is classified into the environment dimension, the device state factor (such as working stability, fault records) is classified into the device dimension, and the verification factor (such as historical maintenance success rate) is classified into the verification dimension, forming a three-dimensional structured framework. Then, a multi-dimensional integration model based on Bayesian network is used to analyze the complex non-linear interaction between these factors in real time. For example, adverse weather in the environment factor may affect the accuracy of the sensor in the device factor, while the historical problem recurrence rate in the verification factor is related to the trend of the environment factor. This model dynamically captures the coupling effects between factors (such as the chain reaction of weather anomalies leading to an increase in device failure rate) through a probabilistic reasoning mechanism, ensuring that these interactive effects can be identified and quantified in real time during road operation and maintenance, thereby providing basic data support for credibility evaluation;

[0043] In the coupling process, first, the dimensional factors are standardized to eliminate dimensional differences, then the synergistic influence coefficient is calculated according to the dynamic weighting strategy, and the three-dimensional output value is fused by the weighted linear integration method; specifically including:

[0044] After the standardized preprocessing eliminates the dimensional differences of each dimension factor, the synergistic influence coefficient between the environmental dimension, the equipment dimension and the verification dimension is calculated by using the dynamic weighting strategy; the specific strategy dynamically adjusts the weight proportion according to the real-time fluctuation characteristics of the dimension factor (such as the frequency of weather changes in the environmental dimension, the fault occurrence trend in the equipment dimension, and the feedback deviation amplitude in the verification dimension); for example, when the state of the equipment dimension fluctuates significantly, the system automatically increases its weight proportion, and vice versa, to reflect the contribution degree of each dimension to the overall reliability; this weighting process is continuously optimized through learnable parameters (based on maintenance feedback data iterative adjustment), and finally generates a comprehensive synergistic coefficient that integrates the output values of the environmental, equipment and verification dimensions, ensuring that the reliability of multi-dimensional data can be accurately quantified in road anomaly decision-making;

[0045] Finally, a dynamic reliability index reflecting the real-time reliability of the road operation and maintenance system is generated, which is output in the form of continuous quantization and is updated at a minute level with the state changes of input factors (such as meteorological mutations or equipment fault alarms), forming a dynamic reliability index that can drive subsequent decision-making.

[0046] The specific process of multi-factor coupling is to input the road environment factors, equipment state factors and verification factors into the reliability three-dimensional evaluation model, through the preset factor-dimension mapping mechanism, and use the coupling algorithm based on multi-dimensional integration model (i.e. Bayesian network) to analyze the nonlinear interaction between factors in real time; in the coupling process, first, the dimensional factors are standardized to eliminate dimensional differences, then the synergistic influence coefficient is calculated according to the dynamic weighting strategy, and the three-dimensional output value is fused by the weighted linear integration method; finally, a dynamic reliability index is generated.

[0047] To improve the adaptability of the credibility three-dimensional evaluation model, the credibility calculation module 100 is built-in with a real-time correction mechanism, which dynamically adjusts the weight parameters of the credibility three-dimensional evaluation model based on the maintenance execution feedback provided by the verification factor. Specifically, when the maintenance execution feedback data (such as the latest task report or abnormal event feedback) is received, the credibility calculation module 100 triggers the weight correction process by comparing the deviation between the feedback result and the actual model prediction: using iterative learning method (such as back propagation or online reinforcement learning technology), re-evaluate the weight distribution of each factor; for example, if the maintenance feedback shows that the influence of environmental factors on a specific road section is underestimated, the automatically increased human-adjustable weight adjustment coefficient makes the credibility three-dimensional evaluation model more sensitive to environmental changes; on the contrary, if the verification factor feedback proves that the contribution of the equipment state factor is too high, the credibility three-dimensional evaluation model reduces the weight proportion of this dimension; this closed-loop feedback process ensures the adaptability and real-time optimization capability of the credibility three-dimensional evaluation model, which can continuously adapt to the complex changing environment of road operation, and ultimately enhance the prediction accuracy of the dynamic credibility index and the decision support efficiency; wherein the weight correction process of the credibility three-dimensional evaluation model is implemented as follows:

[0048] When the maintenance execution feedback data provided by the verification factor (including the latest task completion report, abnormal event processing record or problem reoccurrence status) is input into the credibility calculation module 100, the deviation magnitude and distribution characteristics of the feedback data and the existing prediction results are automatically compared; trigger the weight redistribution process based on iterative learning method, which uses back propagation or online reinforcement learning technology to analyze the weight deviation contribution of road environment factors, equipment state factors and verification factors through gradient optimization mechanism; in the weight correction link, if the deviation analysis shows that the influence of environmental factors is underestimated (for example, consecutive weather disasters are not effectively warned), the weight adjustment coefficient of the environmental dimension is automatically increased; if the verification factor feedback confirms that the credibility evaluation of the equipment state factor is too high (such as abnormal data output of a faulty device is not identified), the weight proportion of the equipment dimension is reduced; this closed-loop process takes maintenance events as the driving unit, and outputs optimized weight parameters in real time after receiving each feedback, ensuring that the credibility three-dimensional evaluation model continuously adapts to the dynamic changes of road operation scenarios.

[0049] The core function of the decision matrix construction unit 201 in the road feature conflict resolution module 200 is to solve the topological inconsistency problem in multi-source road data through a systematic method, and to assign reliability labels to abnormal decisions based on the credibility quantification system.

[0050] The decision matrix construction unit 201 first identifies road topological conflict features existing in multi-source data (such as remote sensing images, vehicle-mounted sensor streams, and historical road network topology libraries) through a spatial feature analysis algorithm. Typical scenarios include meteorological data conflicts, road segment geometric shape conflicts (such as lane line position deviation), topological connection logic conflicts (such as missing intersection associations), or attribute level conflicts (such as speed limit information conflicts). During the identification process, a dynamic credibility index is mapped to the feature dimensions corresponding to various road topological conflict features. The credibility values of the environment factor dimension are associated with environmental state-related conflicts (such as meteorological data conflicts or road surface condition judgment conflicts). For geometric shape conflicts, the credibility values of the device state factor dimension are associated. For historical data conflicts, the credibility values of the verification factor dimension are associated. Through this mapping mechanism, each conflict feature automatically inherits the credibility values of the specific dimensions, forming a three-dimensional road conflict decision matrix. This matrix quantitatively records the types, spatial distribution, and corresponding multi-dimensional reliability indicators of conflict features. The three dimensions include environmental credibility, device credibility, and verification credibility.

[0051] In the decision fusion stage, the fusion unit 202 in the road feature conflict resolution module 200 uses a feature dimension-oriented weighted evidence fusion algorithm to adaptively aggregate conflict features of the same type in the decision matrix according to credibility weights. The specific process is as follows:

[0052] In the environmental credibility dimension, meteorological-related conflict evidence is aggregated. In the device credibility dimension, sensor source data conflict evidence is integrated. In the verification credibility dimension, historical maintenance feedback conflict evidence is fused. Each aggregation unit automatically generates a "abnormal type-location coordinate-multi-dimensional credibility score" triple, and finally synthesizes a road anomaly decision set with credibility labels. The innovation of this decision set lies in the addition of environmental credibility labels, device credibility labels, and verification credibility labels to each abnormal conclusion, which enables downstream modules to finely assess the credibility level of abnormal decisions based on multi-dimensional reliability scores, providing a hierarchical response basis for subsequent maintenance resource scheduling. The generation process of the road anomaly decision set is as follows:

[0053] In the environmental credibility dimension, meteorological-related conflict evidence is aggregated. In the device credibility dimension, sensor source data conflict evidence is integrated. In the verification credibility dimension, historical maintenance feedback conflict evidence is fused. Each aggregation unit automatically generates a "abnormal type-location coordinate-multi-dimensional credibility score" triple, and finally synthesizes a road anomaly decision set with credibility labels. The innovation of this decision set lies in the addition of environmental credibility labels, device credibility labels, and verification credibility labels to each abnormal conclusion, which enables downstream modules to finely assess the credibility level of abnormal decisions based on multi-dimensional reliability scores, providing a hierarchical response basis for subsequent maintenance resource scheduling. The generation process of the road anomaly decision set is as follows:

[0054] In the device credibility dimension, sensor source data conflict evidence is integrated, and the geometric shape or state judgment differences of different monitoring devices (such as cameras and radars) on the same road segment (such as lane line position deviation exceeding a threshold) are analyzed. Based on the historical accuracy records of the devices, evidence credibility weights are assigned.

[0055] In the verification credibility dimension, the history maintenance feedback conflict evidence is fused, the current abnormal characteristics are compared with the disposal results (such as the pit problem recurrence rate) of similar cases in the history maintenance record, and the history verification success rate is taken as the confidence benchmark of the conflict evidence.

[0056] The resource credibility hierarchical scheduling module 300 divides the global road into three response regions of a high credibility response region, a medium credibility response region and a low credibility response region according to the dynamic credibility index, and the division logic adopts a continuous function segmentation mechanism based on the dynamic credibility index threshold.

[0057] The resource credibility hierarchical scheduling module 300 synchronously accesses the device weight priority parameter (that is, the key device influence coefficient marked in the matrix according to the device state factor dimension) in the road conflict decision matrix and the credibility label (including the environment credibility, the device credibility and the verification credibility score) of each abnormal item in the road abnormal decision set, and performs the credibility hierarchical scheduling, which specifically includes:

[0058] First, the total amount of resource allocation is determined according to the response region level (the fast response unit is equipped in the high credibility region, and the strengthened inspection group is deployed in the low credibility region), secondly, the key device coverage order is sorted according to the device weight priority (such as the high weight sensor fault is repaired first), and finally, the low reliability decision is filtered in combination with the credibility label (such as the abnormal item with a verification credibility label lower than the threshold is downgraded).

[0059] In the hierarchical scheduling implementation phase, the resource credibility hierarchical scheduling module 300 dynamically generates a resource-decision set association graph by using a multi-objective optimization engine, the graph takes the entries of the road abnormal decision set as nodes, takes the maintenance resource type (manpower, device and vehicle) as edge attributes, and establishes a mapping through the following rules:

[0060] The abnormal node in the high credibility response region is connected to the automatic maintenance resource unit;

[0061] The node carrying the high device credibility label is associated with the professional detection device resource;

[0062] The node with the verification credibility warning label is bound to the review verification team;

[0063] The graph construction process fuses the topological feature coordinates of the conflict decision matrix to form a four-element relationship network of "spatial position- abnormal type- resource type- credibility dimension", and finally outputs a visual scheduling scheme, which provides the maintenance department with a decision support with reliability traceability capability and resource dynamic adaptability.

[0064] As known from the above description, the road traffic intelligent operation and maintenance system with multi-source data fusion provided in the embodiment has the following technical effects:

[0065] The three-dimensional evaluation model is constructed by fusing the road environment factor, the equipment state factor and the verification factor through the credibility calculation module 100, the minute-level dynamic updated credibility index is generated, and the model weight is corrected through the maintenance feedback closed loop, so that the reliability dynamic fluctuation problem caused by environmental interference, equipment aging and historical deviation of multi-source data is solved; The road feature conflict resolution module 200 identifies and quantifies the road topology, geometric shape and historical logic conflict based on the credibility index dimension mapping, constructs a three-dimensional conflict decision matrix with environment credibility, equipment credibility and verification credibility label, and generates a road anomaly decision set marked with three credibility labels by using a weighted evidence fusion algorithm, which solves the problem of chaotic decision basis caused by multi-source data feature conflict; The resource credibility hierarchical scheduling module 300 divides the high, medium and low three response areas according to the credibility index, and executes the three-constraint scheduling strategy according to the device weight priority in the conflict matrix and the credibility label in the anomaly decision set, that is, the differentiated resources are put into the response area level, the execution order is sorted according to the key degree of the equipment, and the low reliability anomaly items are filtered according to the credibility label, finally a four-dimensional resource decision association graph integrating space position, anomaly type, resource type and credibility dimension is constructed, the precise matching and dynamic adaptation of maintenance resources are realized, the rigid mismatching bottleneck of traditional scheduling mechanism is eliminated, and the operation and maintenance efficiency and decision reliability are significantly improved.

[0066] Please refer to Figure 2 The second purpose of the embodiment is to provide a method of a multi-source data fusion road traffic intelligent operation and maintenance system, and the method steps are as follows:

[0067] S1, a credibility three-dimensional evaluation model for road operation and maintenance is constructed, wherein the input parameters of the credibility three-dimensional evaluation model include road environment factors, equipment state factors and verification factors, a dynamic credibility index is generated by using the credibility three-dimensional evaluation model through multi-factor coupling, and the weight of the credibility three-dimensional evaluation model is corrected in real time based on the maintenance execution feedback of the verification factors;

[0068] S2, identify the road topology conflict features in the multi-source data, map the dynamic credibility index to the feature dimension corresponding to the road topology conflict features, construct a road conflict decision matrix, and generate a road anomaly decision set with a credibility label by fusion according to the feature dimension;

[0069] S3, divide the road area into three response areas based on the dynamic credibility index, combine the device weight priority in the road conflict decision matrix and the credibility label in the road anomaly decision set, execute the credibility hierarchical scheduling, and generate a resource-decision set association graph.

[0070] The above shows and describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above-mentioned embodiments, and the above-mentioned embodiments and descriptions in the specification are only preferred examples of the present application and are not intended to limit the present application. Various changes and improvements can be made to the present application without departing from the spirit and scope of the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. The road traffic intelligent operation and maintenance system with multi-source data fusion is characterized by: It includes a credibility calculation module (100), a road feature conflict resolution module (200) and a resource credibility hierarchical scheduling module (300), wherein: The credibility calculation module (100) constructs a credibility three-dimensional evaluation model for road operation and maintenance, wherein the input parameters of the credibility three-dimensional evaluation model include road environment factors, equipment status factors and verification factors, and uses the credibility three-dimensional evaluation model to generate a dynamic credibility index through multi-factor coupling, and based on the maintenance execution feedback of the verification factor, the weight of the credibility three-dimensional evaluation model is corrected in real time; The road feature conflict resolution module (200) identifies road topology conflict features in multi-source data, maps them to feature dimensions corresponding to the road topology conflict features through dynamic credibility indexes, constructs a road conflict decision matrix, and generates a road anomaly decision set with credible labels by fusing the feature dimensions. The resource trusted hierarchical scheduling module (300) divides the road area into three levels of response areas based on the dynamic credibility index, performs trusted hierarchical scheduling in combination with the equipment weight priority in the road conflict decision matrix and the trusted labels in the road abnormality decision set, and generates a resource-decision set association map.

2. The multi-source data fusion road traffic intelligent operation and maintenance system according to claim 1 is characterized in that: The road environment factors include meteorological conditions, road surface physical conditions and traffic load characteristics; The equipment status factors include the working stability, fault records and maintenance history of road monitoring equipment; the verification factors include the success rate, timeliness deviation and problem recurrence rate of historical maintenance tasks.

3. The road traffic intelligent operation and maintenance system based on multi-source data fusion according to claim 1 is characterized in that: The generation process of the dynamic credibility index specifically includes: Road environment factors are mapped to the environmental dimension, equipment status factors are mapped to the equipment dimension, and verification factors are mapped to the verification dimension. The nonlinear interaction relationship between factors is analyzed in real time through the multidimensional integration model of the Bayesian network. After performing standardized preprocessing to eliminate dimensional differences, the synergistic influence coefficients of the environmental dimension, equipment dimension, and verification dimension are calculated based on the dynamic weighting strategy. The weighted linear integration method is used to fuse the three-dimensional output values ​​to generate a dynamic credibility index that is continuously quantified and dynamically updated with the factor status.

4. The road traffic intelligent operation and maintenance system based on multi-source data fusion according to claim 1 is characterized in that: The weight correction process of the three-dimensional credibility evaluation model specifically includes: According to the deviation between the maintenance execution feedback data provided by the verification factor and the actual model prediction, the weights of the road environment factor, equipment status factor and verification factor are redistributed through the iterative learning method.

5. The road traffic intelligent operation and maintenance system based on multi-source data fusion according to claim 1 is characterized in that: The road feature conflict resolution module (200) comprises a decision matrix construction unit (201), wherein the decision matrix construction unit (201) is used to generate a road conflict decision matrix, specifically comprising: Road geometry conflicts, topology connection logic conflicts, and attribute hierarchy conflicts are detected through a spatial feature analysis algorithm. The dynamic credibility index is mapped to the feature dimensions corresponding to the conflict features. Conflicts related to environmental conditions are associated with the credibility value of the environmental factor dimension, conflicts related to geometric conditions are associated with the credibility value of the device status factor dimension, and conflicts related to historical data are associated with the credibility value of the verification factor dimension. Through this mapping mechanism, each conflict feature automatically inherits the credibility value of a specific dimension to generate a road conflict decision matrix.

6. The road traffic intelligent operation and maintenance system based on multi-source data fusion according to claim 1 is characterized in that: The road feature conflict resolution module (200) includes a fusion unit (202), and the fusion unit (202) is used to generate a road anomaly decision set, specifically including: A weighted evidence fusion algorithm is used to aggregate conflicting evidence of meteorological correlation in the environmental credibility dimension, integrate conflicting evidence of sensor source data in the equipment credibility dimension, and fuse conflicting evidence of historical maintenance feedback in the verification credibility dimension, generating a road anomaly decision set containing three types of reliability labels: environmental credibility labels, equipment credibility labels, and verification credibility labels.

7. The road traffic intelligent operation and maintenance system based on multi-source data fusion according to claim 1 is characterized in that: The three-level response area division adopts a continuous function segmentation mechanism of a dynamic credibility index threshold, and the three-level response areas are respectively a high credibility response area, a medium credibility response area and a low credibility response area.

8. The road traffic intelligent operation and maintenance system based on multi-source data fusion according to claim 1 is characterized in that: The construction rules of the resource-decision set association graph are: The entries of the road anomaly decision set are nodes, and the maintenance resource type is the edge attribute; Abnormal nodes in the high-confidence response area are connected to the automated maintenance resource unit, nodes with high equipment credibility labels are associated with professional detection equipment resources, and nodes with verification credibility warning labels are bound to the review and verification team.

9. The road traffic intelligent operation and maintenance system based on multi-source data fusion according to claim 1 is characterized in that: The process of the resource trusted hierarchical scheduling module (300) performing trusted hierarchical scheduling specifically includes: The total amount of resources deployed is determined by the level of the response area. High-confidence response areas are equipped with rapid response units, while low-confidence response areas are deployed with enhanced inspection teams. The coverage order of key devices is sorted according to the device weight priority parameters; low-reliability anomalies are filtered in combination with trusted labels, that is, anomalies with verified credibility labels below the threshold are downgraded.

10. A method for using a road traffic intelligent operation and maintenance system comprising the multi-source data fusion according to any one of claims 1 to 9, characterized in that: The method comprises the following steps: S1. Construct a three-dimensional credibility assessment model for road operation and maintenance. The input parameters of the three-dimensional credibility assessment model include road environment factors, equipment status factors, and verification factors. Utilizing the three-dimensional credibility assessment model, a dynamic credibility index is generated through multi-factor coupling. The weights of the three-dimensional credibility assessment model are modified in real time based on maintenance execution feedback from the verification factors. S2. Identify road topology conflict features in multi-source data, map them to the feature dimensions corresponding to the road topology conflict features through dynamic credibility index, construct a road conflict decision matrix, and generate a road anomaly decision set with credible labels by fusing the feature dimensions. S3. Divide the road area into three levels of response areas based on the dynamic credibility index. Combined with the equipment weight priority in the road conflict decision matrix and the trusted labels in the road anomaly decision set, perform trusted hierarchical scheduling and generate a resource-decision set association map.

Images