Urban operation risk early warning method and system based on big data analysis

Abstract

The invention discloses an urban operation risk early warning method and system based on big data analysis, and relates to the technical field of urban road monitoring, and the method comprises the steps: collecting urban road data and vehicle data, extracting vehicle health features, defining road network nodes and neighborhood ranges, calculating the health density of vehicles around the nodes, and generating a risk thermodynamic diagram; the method comprises the following steps: constructing a road network damage inversion neural network, generating a road network node comprehensive vector, constructing a road network node topological graph, mapping the road network node comprehensive vector into a road damage type by adopting an inversion layer, modeling a road chain reaction through a dynamic Bayesian failure chain propagation tree, and quantifying and predicting future urban road risks; a multi-strategy intervention simulation engine is adopted, an intervention scheme is generated based on predicted road risks, urban road risks are visually early warned, and the intervention scheme is recorded. According to the method, the urban road risk in the future is accurately quantified and predicted, and real-time early warning and accurate intervention of the road risk are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of urban road monitoring, and in particular to a method and system for early warning of urban operation risks based on big data analysis. Background Art

[0002] With the acceleration of urbanization, urban transportation systems have become increasingly complex, and the challenges faced by the maintenance and management of transportation facilities are becoming increasingly severe. Especially in modern cities, factors such as traffic accidents, aging facilities, and extreme weather have continued to have an increasing impact on road safety and smooth traffic, which has put higher demands on the stability of urban operations and traffic management. In recent years, with the rapid development of big data technology and artificial intelligence, urban road risk warning systems based on big data have gradually become a hot topic of research and application. By collecting, analyzing and processing a large amount of data in the urban transportation system, early warning of potential road risks and accurate deployment of risk prevention and control measures can be achieved. For example, the integration of urban road data, vehicle data, traffic accident information, and data mining and machine learning technologies can be used to analyze road health conditions, traffic flow, and areas with frequent traffic accidents, and then predict and evaluate potential risk points.

[0003] Existing technologies in urban road risk warning systems mainly focus on the monitoring and analysis of single factors, often focusing on the impact of road facility damage, traffic flow or weather conditions on traffic risks. They fail to fully consider the relationship between road networks and vehicle health characteristics, and lack real-time dynamic optimization capabilities based on big data analysis. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an urban operation risk warning method and system based on big data analysis to solve the problem that the existing technology fails to fully consider the relationship between road networks and vehicle health characteristics and lacks real-time dynamic optimization capabilities based on big data analysis.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a city operation risk early warning method based on big data analysis, which includes:

[0008] Collect urban road data and vehicle data, extract vehicle health characteristics, define road network nodes and neighborhood ranges, calculate vehicle health density around nodes and generate risk heat maps;

[0009] Construct a road network damage inversion neural network, generate comprehensive vectors of road network nodes, and build a road network node topology map. Use the inversion layer to map the comprehensive vectors of road network nodes to road damage types. Model road chain reactions using a dynamic Bayesian failure chain propagation tree to quantify and predict future urban road risks.

[0010] A multi-strategy intervention simulation engine is used to generate intervention plans based on predicted road risks, visually warn of urban road risks and record intervention plans.

[0011] As a preferred solution of the urban operation risk early warning method based on big data analysis described in the present invention, the collection of urban road data and vehicle data refers to using the OBD interface to obtain vehicle data from the vehicle's ECU, including vehicle sensor data and fault data, and synchronously collecting the vehicle's driving trajectory through the vehicle's GPS module, and obtaining urban road attribute information through the vehicle's driving trajectory.

[0012] As a preferred solution of the urban operation risk early warning method based on big data analysis described in the present invention, wherein: the extraction of vehicle health characteristics, definition of road network nodes and neighborhood ranges, and calculation of vehicle health density around nodes to generate a risk heat map refers to defining urban road nodes based on urban road topology information, generating an urban road node map based on urban road connection relationships, defining a neighborhood range for each urban road node, counting vehicle data within the neighborhood range, extracting fault data from the vehicle data, calculating the corresponding ratio of each fault data in the vehicle data as the fault ratio, performing normalized weighted summation on the fault ratio of each fault data, and generating the health density h of the urban road node. i ;

[0013] Calculate the average health density μ of all urban road nodes and calculate the deviation D(i) for each urban road node;

[0014] A deviation matrix is ​​generated based on the deviations of all urban road nodes, the deviation values ​​in the deviation matrix are normalized, and urban road nodes with deviation values ​​less than the preset deviation threshold are marked as risk. The normalized deviation value matrix is ​​converted into a risk heat map using a visualization tool, and the risk markers are simultaneously identified in the risk heat map.

[0015] As a preferred solution of the urban operation risk early warning method based on big data analysis described in the present invention, the method comprises: constructing a road network damage inversion neural network, generating a comprehensive vector of road network nodes, constructing a road network node topology map, using an inversion layer to map the comprehensive vector of road network nodes to road damage type, extracting risk-marked urban road nodes in the risk heat map as road network nodes, extracting vehicle data in the neighborhood of the road network nodes, pre-processing them, and splicing them to form a vehicle health feature vector V i, synchronously obtain the road attribute information of the road network nodes, pre-process and splice to form the road feature vector F i , the vehicle health feature vector V of the road network node i and the road feature vector F i Splice to form the comprehensive vector X of the road network node i ;

[0016] DBSCAN clustering is used to classify the comprehensive vector X of the road network nodes i Perform cluster analysis to obtain clustering results. According to the clustering results, divide the road network nodes into road network node sets N(i). For each road network node set, calculate the comprehensive vector X of the road network nodes. i When the cosine similarity is greater than the similarity threshold, it is determined that there are connecting edges between the road network nodes, and a road network node topology graph of each road network node set is formed based on the road network nodes and the connecting edges;

[0017] Update the road network node topology graph using graph convolution operations based on graph neural networks;

[0018] The road network damage inversion neural network is constructed through a fully connected neural network. The input is the updated node feature representation generated by the graph neural network, and the output is the probability distribution P of the damage type. i , expressed as;

[0019] According to the damage probability distribution of the road network nodes, the damage type of the road network nodes is determined by the damage threshold and output;

[0020] The probability distribution of damage types of road network nodes is used as the damage vector, and the damage vectors of all road network nodes in the road network node set are summarized to analyze the main damage types of urban road network nodes.

[0021] As a preferred solution of the urban operation risk early warning method based on big data analysis described in the present invention, wherein: the road chain reaction modeling by dynamic Bayesian failure chain propagation tree to quantify and predict future urban road risks refers to treating the damage type of each road network node as a Bayesian network node, determining the causal relationship between the nodes and representing it using a causal graph, and using conditional probability reasoning to propagate node probabilities through the Bayesian network propagation mechanism;

[0022] Calculate the real-time risk value R of the road network node through the node propagation probability t ;

[0023] Construct an LSTM model as a risk prediction model, with the input being the real-time risk value R of the road network node t , the output is the future urban road risk, the risk prediction model is trained and optimized through the loss function and Adam optimizer, and the real-time risk value R tThe trained risk prediction model is input to obtain the future urban road risk, and the damage type with the largest propagation probability is selected as the cause of future urban road risk based on the node propagation probability inferred by the Bayesian network.

[0024] As a preferred solution of the urban operation risk early warning method based on big data analysis described in the present invention, the use of a multi-strategy intervention simulation engine to generate an intervention plan based on predicted road risks refers to using a multi-strategy intervention simulation engine to predefine an intervention plan template based on future urban road risks and future urban road risk causes, creating an urban road digital twin model based on vehicle information and urban road attribute information, inputting the intervention plan into the urban road digital twin model for real-time simulation, and calculating the real-time risk value of the city after simulation, and selecting the intervention plan that minimizes the real-time risk value as the final intervention plan.

[0025] As a preferred solution of the urban operation risk warning method based on big data analysis described in the present invention, the visual warning of urban road risks and recording of intervention plans refers to marking the predicted future urban road risks of each road network node in the risk heat map, simultaneously displaying the main damage types of urban road network nodes and recording the final intervention plan content in a database.

[0026] In a second aspect, the present invention provides an urban operation risk early warning system based on big data analysis, comprising:

[0027] The data collection and analysis module is used to collect urban road data and vehicle data, extract vehicle health characteristics, define road network nodes and neighborhood ranges, calculate the vehicle health density around the nodes, and generate risk heat maps;

[0028] The risk prediction module is used to construct a road network damage inversion neural network, generate comprehensive vectors of road network nodes, and build a road network node topology map. The comprehensive vectors of road network nodes are mapped to road damage types using an inversion layer. The road chain reaction is modeled using a dynamic Bayesian failure chain propagation tree to quantify and predict future urban road risks.

[0029] The intervention recording module is used to adopt a multi-strategy intervention simulation engine to generate intervention plans based on predicted road risks, visually warn of urban road risks and record intervention plans.

[0030] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the urban operation risk warning method based on big data analysis as described in the first aspect of the present invention.

[0031] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the urban operation risk warning method based on big data analysis as described in the first aspect of the present invention.

[0032] The beneficial effects of the present invention are as follows: the present invention generates a risk heat map by calculating the health density of vehicles around nodes, effectively identifies high-risk areas in the urban road system and extracts risky road network nodes, and adopts a road network damage inversion neural network and a dynamic Bayesian failure chain propagation tree to model the chain reaction of road facilities, accurately quantify and predict future urban road risks, and realize real-time early warning and precise intervention of road risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0034] Figure 1 This is a flow chart of the urban operation risk early warning method based on big data analysis in Example 1.

[0035] Figure 2 This is a structural diagram of the urban operation risk early warning system based on big data analysis in Example 1. DETAILED DESCRIPTION

[0036] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0037] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0038] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0039] Example 1, with reference to Figure 1 and Figure 2, which is the first embodiment of the present invention, provides a city operation risk early warning method based on big data analysis, including the following steps:

[0040] S1. Collect urban road data and vehicle data, extract vehicle health characteristics, define road network nodes and neighborhood ranges, calculate vehicle health density around nodes, and generate risk heat maps.

[0041] Specifically, collecting urban road data and vehicle data means using the OBD interface to obtain vehicle data from the vehicle's ECU, including vehicle sensor data and fault data. Fault data includes engine failure, abnormal brake temperature, low tire pressure, etc., and synchronously collecting the vehicle's driving trajectory through the vehicle's GPS module, and obtaining urban road attribute information through the vehicle's driving trajectory, including road slope, curvature radius, etc.

[0042] Furthermore, vehicle health characteristics are extracted, road network nodes and neighborhood ranges are defined, and the vehicle health density around the nodes is calculated to generate a risk heat map. This refers to defining urban road nodes based on urban road topology information, generating an urban road node map based on urban road connection relationships, defining a neighborhood range for each urban road node, such as a radius of 500 or 1000 meters, counting vehicle data within the neighborhood range, and extracting fault data from the vehicle data to calculate the corresponding proportion of each fault data in the vehicle data as the fault proportion. For example, within the neighborhood of the node, 5 out of 20 vehicles have engine failures, then the engine failure rate of the node is 5 / 20=0.25. The fault proportion of each fault data is normalized and weighted summed to generate the health density h of the urban road node. i :

[0043] h i =1-m;

[0044] Where m is the normalized weighted sum of the fault proportion;

[0045] Calculate the average health density μ of all urban road nodes, and calculate the deviation D(i) for each urban road node:

[0046] D(i)=h i -μ;

[0047] A deviation matrix is ​​generated based on the deviations of all urban road nodes. Each element of the matrix represents the deviation value of a node. The deviation values ​​in the deviation matrix are normalized, and urban road nodes with deviation values ​​less than the preset deviation threshold are marked as risk. A visualization tool is used to convert the normalized deviation value matrix into a risk heat map, where urban road nodes with deviation values ​​greater than or equal to 0 are marked green, and urban road nodes with deviation values ​​less than 0 are marked red. The larger the absolute value of the deviation value, the darker the color. The risk marks are simultaneously identified in the risk heat map.

[0048] By collecting vehicle data and extracting vehicle health characteristics, the health density of each urban road node is calculated, which helps to obtain an intuitive reflection of the health status of vehicles across the city. By calculating the health density of each node and comparing it with the city's average, nodes with poor health can be effectively identified. By generating a deviation matrix for each node, the deviation of a single fault type in risk assessment is effectively avoided, allowing the system to fully reflect the differences between different nodes in the road network. This risk assessment method based on deviation values ​​is extremely sensitive and accurate, and can promptly detect high-risk nodes that are easily overlooked. The normalized deviation value matrix is ​​converted into a risk heat map through visualization tools, which can intuitively and clearly display the health status of urban roads.

[0049] S2. Construct a road network damage inversion neural network to generate comprehensive vectors of road network nodes and build a road network node topology map. Use the inversion layer to map the comprehensive vectors of road network nodes to road damage types. Model the road chain reaction using a dynamic Bayesian failure chain propagation tree to quantify and predict future urban road risks.

[0050] Specifically, a road network damage inversion neural network is constructed to generate a comprehensive vector of road network nodes and a road network node topology map. The comprehensive vector of road network nodes is mapped to a road damage type using an inversion layer. Risk-marked urban road nodes in the risk heat map are extracted as road network nodes. Vehicle data in the neighborhood of the road network nodes are pre-processed and spliced ​​to form a vehicle health feature vector V. i , synchronously obtain the road attribute information of the road network nodes, pre-process and splice to form the road feature vector F i , the vehicle health feature vector V of the road network node i and the road feature vector F i Splice to form the comprehensive vector X of the road network node i ;

[0051] DBSCAN clustering is used to classify the comprehensive vector X of the road network nodes i Perform cluster analysis to obtain clustering results. According to the clustering results, divide the road network nodes into road network node sets N(i). For each road network node set, calculate the comprehensive vector X of the road network nodes. i When the cosine similarity is greater than the similarity threshold, it is determined that there are connecting edges between the road network nodes, and a road network node topology graph of each road network node set is formed based on the road network nodes and the connecting edges;

[0052] Based on the graph neural network, the graph convolution operation is used to update the road network node topology graph:

[0053]

[0054] Among them H k+1 is the node feature representation of the k+1th layer in the graph convolution operation, c iu is the cosine similarity between network node i and network node u, W (k) is the weight matrix of the kth layer, σ is the activation function;

[0055] The road network damage inversion neural network is constructed through a fully connected neural network. The input is the updated node feature representation generated by the graph neural network, and the output is the probability distribution P of the damage type. i , expressed as:

[0056] P i =softmax(W out *H k +b out );

[0057] Among them, P i is the probability distribution of the damage type of network node i, W out and b out Output weight matrix and bias term of the road network damage inversion neural network, where damage types include road surface settlement, traffic light phase conflict, road cracks, etc.

[0058] According to the damage probability distribution of the road network nodes, the damage type of the road network nodes is determined by the damage threshold and output;

[0059] The probability distribution of damage types of road network nodes is used as the damage vector, and the damage vectors of all road network nodes in the road network node set are summarized to analyze the main damage types of urban road network nodes.

[0060] Splicing the vehicle health feature vector and the road feature vector to form a comprehensive vector of the road network node helps to comprehensively consider multi-dimensional data in the same dimension, and can accurately describe the health status of each road network node from multiple angles. By fusing multivariate data, the evaluation of the node status is more comprehensive, avoiding the one-sidedness of the information. In addition, combining vehicle health data with road facility data helps to identify those potential high-risk areas, especially those nodes where the risk is increased due to the combined effect of road damage and vehicle health problems. The use of cosine similarity provides an ideal method for similarity evaluation of road network nodes. Through the clustering algorithm, the system can identify similar nodes and classify these nodes into the same group, which can effectively reduce the impact of data noise, especially when the dimensions of vehicle health data and road facility data are high. Cosine similarity The degree can avoid the deviation caused by the inconsistency of dimensions between data of different dimensions. Through cluster analysis, the system can accurately group the road network to form a more reasonable topology map, ensuring that subsequent graph convolution operations can be performed on a more realistic structure, thereby improving the accuracy of damage prediction. The combination of graph neural network and graph convolution operations effectively utilizes the topological structure of the urban road network and realizes multi-level node feature transmission. It can capture the complex interdependence between nodes, thereby improving the ability to predict facility damage. Through the probability distribution of damage types, managers can obtain accurate risk predictions and provide decision support for subsequent maintenance and repair work. The prediction method based on neural network can automatically learn different types of facility damage patterns from data, improving the accuracy and adaptability of prediction.

[0061] Furthermore, a dynamic Bayesian failure chain propagation tree is used to model road chain reactions and quantify and predict future urban road risks. This involves treating the damage type of each road network node as a Bayesian network node, determining the causal relationship between nodes, and representing it using a causal graph. For example, roadbed settlement can lead to potholes. These causal relationships can be determined through historical data, engineering expert knowledge, or survey data. The conditional probability inference node propagation probability is then used through the Bayesian network propagation mechanism:

[0062]

[0063] where v j and v i are the parent node and child node in the Bayesian network respectively, P(v i |v j ) is the probability of occurrence of a child node under a given parent node, P(v j |v i ) is the probability of occurrence of the parent node under a given child node, P(v i ) and P(v j) are the occurrence probabilities of child nodes and parent nodes, respectively, which are obtained by extracting the damage probability distribution of road network nodes;

[0064] Calculate the real-time risk value R of the road network node through the node propagation probability t :

[0065]

[0066] where w i is the risk weight of the i-th injury type, and n is the total number of injury types;

[0067] Construct an LSTM model as a risk prediction model, with the input being the real-time risk value R of the road network node t , the output is the future urban road risk, the risk prediction model is trained and optimized through the loss function and Adam optimizer, and the real-time risk value R t The trained risk prediction model is input to obtain the future urban road risk, and the damage type with the largest propagation probability is selected as the cause of future urban road risk based on the node propagation probability inferred by the Bayesian network.

[0068] Bayesian networks can combine historical data, expert knowledge and survey data to effectively infer the causal relationship between nodes. Unlike the traditional risk assessment method based on a single data source in the existing technology, the present invention constructs a more accurate and comprehensive damage propagation model through multi-dimensional information fusion, which can capture the interaction between damage to different facilities. This method can provide more detailed and dynamic risk assessment for urban traffic management, and help to identify potential high-risk nodes and chain reactions in advance. The Bayesian network reasoning mechanism is used to update the real-time risk value of the road network node by calculating the node propagation probability. The risk level of different nodes can be dynamically adjusted, and the propagation and changes of facility damage can be reflected in real time. The LSTM model can extract time series information from real-time risk data and capture the long-term dependency of facility damage and its chain reaction. It enables the system to not only assess current risks in real time, but also effectively predict future road risks.

[0069] S3. Use a multi-strategy intervention simulation engine to generate intervention plans based on predicted road risks, visually warn of urban road risks, and record intervention plans;

[0070] Specifically, using a multi-strategy intervention simulation engine to generate an intervention plan based on predicted road risks means using a multi-strategy intervention simulation engine to predefine an intervention plan template based on future urban road risks and future urban road risk causes. The intervention plan template includes but is not limited to temporary speed limits, signal timing adjustments, traffic control, emergency maintenance, etc. A digital twin model of an urban road is created based on vehicle information and urban road attribute information, the intervention plan is input into the digital twin model of the urban road for real-time simulation, and the real-time risk value of the city is calculated after the simulation, and the intervention plan that minimizes the real-time risk value is selected as the final intervention plan.

[0071] By comprehensively considering multiple intervention strategies, complex urban traffic problems can be effectively addressed. For example, in certain road sections, simple speed limits may not be sufficient to resolve traffic congestion. Adjusting traffic signal timing or implementing traffic control measures to optimize flow is necessary. The introduction of multiple strategies makes the system more flexible and adaptable, enabling rapid adjustment and selection of the most appropriate intervention measures for different traffic conditions. The introduction of digital twin technology enables real-time simulation of changes in urban road conditions in a virtual environment. This approach has significant advantages, namely, its ability to dynamically reflect the actual operating conditions of roads and evaluate the effectiveness of intervention measures through simulation. By establishing a digital twin model, the simulation engine can accurately capture the dynamic changes in urban roads, such as the impact of road failures, traffic density, and weather changes. By dynamically assessing risk values, the real-time effectiveness of each intervention measure can be ensured, avoiding ineffective or inefficient response strategies. Urban traffic management often faces differences in traffic conditions across different regions and time periods. Real-time risk value calculation can help accurately assess various risks and, in turn, help managers formulate the most appropriate intervention strategy.

[0072] Furthermore, visual warning of urban road risks and recording of intervention plans means marking the predicted future urban road risks of each road network node in the risk heat map, simultaneously displaying the main damage types of urban road network nodes and recording the final intervention plan content in the database.

[0073] This embodiment also provides an urban operation risk early warning system based on big data analysis, including:

[0074] The data collection and analysis module is used to collect urban road data and vehicle data, extract vehicle health characteristics, define road network nodes and neighborhood ranges, calculate the vehicle health density around the nodes, and generate risk heat maps;

[0075] The risk prediction module is used to construct a road network damage inversion neural network, generate comprehensive vectors of road network nodes, and build a road network node topology map. The comprehensive vectors of road network nodes are mapped to road damage types using an inversion layer. The road chain reaction is modeled using a dynamic Bayesian failure chain propagation tree to quantify and predict future urban road risks.

[0076] The intervention recording module is used to adopt a multi-strategy intervention simulation engine to generate intervention plans based on predicted road risks, visually warn of urban road risks and record intervention plans.

[0077] This embodiment also provides a computer device, which is suitable for the urban operation risk warning method based on big data analysis, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the urban operation risk warning method based on big data analysis proposed in the above embodiment.

[0078] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0079] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the urban operation risk warning method based on big data analysis proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk.

[0080] In summary, the present invention generates a risk heat map by calculating the health density of vehicles around nodes, effectively identifying high-risk areas in the urban road system and extracting risky road network nodes. It also adopts a road network damage inversion neural network and models the chain reaction of road facilities through a dynamic Bayesian failure chain propagation tree, accurately quantifying and predicting future urban road risks, and realizing real-time early warning and precise intervention of road risks.

[0081] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A city operation risk early warning method based on big data analysis, characterized by: include, Collect urban road data and vehicle data, extract vehicle health characteristics, define road network nodes and neighborhood ranges, calculate vehicle health density around nodes and generate risk heat maps; Construct a road network damage inversion neural network, generate comprehensive vectors of road network nodes, and build a road network node topology map. Use the inversion layer to map the comprehensive vectors of road network nodes to road damage types. Model road chain reactions using a dynamic Bayesian failure chain propagation tree to quantify and predict future urban road risks. A multi-strategy intervention simulation engine is used to generate intervention plans based on predicted road risks, visually warn of urban road risks and record intervention plans.

2. The urban operation risk early warning method based on big data analysis according to claim 1 is characterized by: The collection of urban road data and vehicle data refers to using the OBD interface to obtain vehicle data from the vehicle's ECU, including vehicle sensor data and fault data, and synchronously collecting the vehicle's driving trajectory through the vehicle's GPS module to obtain urban road attribute information through the vehicle's driving trajectory.

3. The urban operation risk early warning method based on big data analysis according to claim 2 is characterized by: The extraction of vehicle health characteristics, definition of road network nodes and neighborhood ranges, and calculation of vehicle health density around nodes to generate a risk heat map refers to defining urban road nodes according to urban road topology information, generating an urban road node map according to urban road connection relationships, defining a neighborhood range for each urban road node, counting vehicle data within the neighborhood range, extracting fault data from the vehicle data, calculating the corresponding ratio of each fault data in the vehicle data as the fault ratio, performing normalized weighted summation on the fault ratio of each fault data, and generating the health density h of the urban road node. i ; Calculate the average health density μ of all urban road nodes and calculate the deviation D(i) for each urban road node; A deviation matrix is ​​generated based on the deviations of all urban road nodes, the deviation values ​​in the deviation matrix are normalized, and urban road nodes with deviation values ​​less than the preset deviation threshold are marked as risk. The normalized deviation value matrix is ​​converted into a risk heat map using a visualization tool, and the risk markers are simultaneously identified in the risk heat map.

4. The urban operation risk early warning method based on big data analysis according to claim 3 is characterized by: The invention constructs a road network damage inversion neural network, generates a comprehensive vector of road network nodes, constructs a road network node topology map, uses an inversion layer to map the comprehensive vector of road network nodes into road damage type, extracts risk-marked urban road nodes in the risk heat map as road network nodes, extracts vehicle data in the neighborhood of the road network nodes, performs preprocessing, and splices them to form a vehicle health feature vector V i , synchronously obtain the road attribute information of the road network nodes, pre-process and splice to form the road feature vector F i , the vehicle health feature vector V of the road network node i and the road feature vector F i Splice to form the comprehensive vector X of the road network node i ; DBSCAN clustering is used to classify the comprehensive vector X of the road network nodes i Perform cluster analysis to obtain clustering results. According to the clustering results, divide the road network nodes into road network node sets N(i). For each road network node set, calculate the comprehensive vector X of the road network nodes. i When the cosine similarity is greater than the similarity threshold, it is determined that there are connecting edges between the road network nodes, and a road network node topology graph of each road network node set is formed based on the road network nodes and the connecting edges; Update the road network node topology graph using graph convolution operations based on graph neural networks; The road network damage inversion neural network is constructed through a fully connected neural network. The input is the updated node feature representation generated by the graph neural network, and the output is the probability distribution P of the damage type. i , expressed as; According to the damage probability distribution of the road network nodes, the damage type of the road network nodes is determined by the damage threshold and output; The probability distribution of damage types of road network nodes is used as the damage vector, and the damage vectors of all road network nodes in the road network node set are summarized to analyze the main damage types of urban road network nodes.

5. The urban operation risk early warning method based on big data analysis according to claim 4 is characterized by: The method of modeling road chain reactions through a dynamic Bayesian failure chain propagation tree to quantify and predict future urban road risks refers to treating the damage type of each road network node as a Bayesian network node, determining the causal relationship between the nodes and representing it using a causal graph, and using conditional probability reasoning to propagate node probabilities through a Bayesian network propagation mechanism; Calculate the real-time risk value R of the road network node through the node propagation probability t ; Construct an LSTM model as a risk prediction model, with the input being the real-time risk value R of the road network node t , the output is the future urban road risk, the risk prediction model is trained and optimized through the loss function and Adam optimizer, and the real-time risk value R t The trained risk prediction model is input to obtain the future urban road risk, and the damage type with the largest propagation probability is selected as the cause of future urban road risk based on the node propagation probability inferred by the Bayesian network.

6. The urban operation risk early warning method based on big data analysis according to claim 5 is characterized by: The use of a multi-strategy intervention simulation engine to generate an intervention plan based on predicted road risks refers to using a multi-strategy intervention simulation engine to predefine an intervention plan template based on future urban road risks and future urban road risk causes, creating an urban road digital twin model based on vehicle information and urban road attribute information, inputting the intervention plan into the urban road digital twin model for real-time simulation, calculating the real-time risk value of the city after the simulation, and selecting the intervention plan that minimizes the real-time risk value as the final intervention plan.

7. The urban operation risk early warning method based on big data analysis according to claim 6 is characterized by: The visual warning of urban road risks and recording of intervention plans refers to marking the predicted future urban road risks of each road network node in the risk heat map, simultaneously displaying the main damage types of urban road network nodes and recording the final intervention plan content in a database.

8. An urban operation risk early warning system based on big data analysis, based on the urban operation risk early warning method based on big data analysis according to any one of claims 1 to 7, characterized in that: include, The data collection and analysis module is used to collect urban road data and vehicle data, extract vehicle health characteristics, define road network nodes and neighborhood ranges, calculate the vehicle health density around the nodes, and generate risk heat maps; The risk prediction module is used to construct a road network damage inversion neural network, generate comprehensive vectors of road network nodes, and build a road network node topology map. The comprehensive vectors of road network nodes are mapped to road damage types using an inversion layer. The road chain reaction is modeled using a dynamic Bayesian failure chain propagation tree to quantify and predict future urban road risks. The intervention recording module is used to adopt a multi-strategy intervention simulation engine to generate intervention plans based on predicted road risks, visually warn of urban road risks and record intervention plans.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the urban operation risk early warning method based on big data analysis according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the urban operation risk early warning method based on big data analysis according to any one of claims 1 to 7 are implemented.

Images