Intensive operation and maintenance management method for information system integrating multi-source data

Abstract

The invention relates to the technical field of electric digital data processing, in particular to an information system intensive operation and maintenance management method integrating multi-source data, and the method comprises the steps: determining the vehicle number difference between adjacent moments in a road image, and determining the vehicle mainstream driving direction of a target traffic node through the vehicle number difference; determining the traffic flow characteristic peak value change similarity between adjacent traffic nodes by using the vehicle mainstream driving direction difference between the adjacent traffic nodes; determining the traffic flow pressure coefficient of the target traffic node by using the vehicle number difference and the traffic flow characteristic peak value change similarity; and determining the driving influence index of the current weather parameter on the road, and determining the bearing pressure coefficient of the target traffic node in combination with the traffic flow pressure coefficient, thereby realizing hierarchical operation and maintenance management of the traffic management information system. According to the technical scheme, the accuracy of urban road traffic pressure bearing evaluation is improved, and the operation and maintenance resource allocation efficiency is optimized.

Description

Technical Field

[0001] This invention relates to the field of electronic digital data processing technology, and specifically to a method for intensive operation and maintenance management of information systems that integrates multi-source data. Background Technology

[0002] Urban road traffic management is a crucial component of urban development, and its operation and maintenance level directly impacts urban traffic safety, smooth flow, and sustainable urban development. With the rapid development of information technology, refined processing of data from various urban monitoring nodes is gradually replacing traditional manual methods. This digital urban operation and maintenance information system supports the intelligent operation and maintenance management of urban transportation networks.

[0003] Existing traffic operation and maintenance management systems integrate floating car trajectory data from urban intersections with road network topology information to dynamically calculate regional traffic flow parameters and guide road infrastructure maintenance and signal optimization based on real-time traffic load levels, thereby achieving intelligent operation and maintenance management of urban traffic networks. However, regional road congestion events caused by extreme weather such as heavy rain and snowfall generate frequent dynamic changes in data, which can lead to distortion of traffic flow characteristic parameters through the injection of abnormal data, thereby weakening the support effectiveness of traffic management platforms for operation and maintenance decisions.

[0004] Existing methods quantify traffic flow characteristics by integrating floating car data from various urban intersections with road network topology information, and formulate road maintenance plans based on static flow thresholds. However, due to significant changes in the environment and data between nodes, it is difficult to effectively capture the local congestion transmission phenomenon caused by the dynamic coupling effect of traffic flow between traffic nodes. This results in maintenance strategies lagging behind actual traffic demand, leading to misallocation of maintenance resources and efficiency loss. Summary of the Invention

[0005] To address the technical problem that existing traffic operation and maintenance management methods often lead to operation and maintenance strategies lagging behind actual traffic demands, resulting in resource misallocation and low efficiency, the present invention aims to provide an intensive operation and maintenance management method for an information system that integrates multi-source data. The specific technical solution adopted is as follows: This invention provides a method for intensive operation and maintenance management of an information system that integrates multi-source data, the method comprising: Determine the difference in vehicle numbers between the target time and its adjacent time in the road image, and use the difference in vehicle numbers in each road image to determine the mainstream driving direction of vehicles at the target traffic node. By utilizing the differences in the mainstream driving directions of vehicles between the target traffic node and its neighboring traffic nodes, the similarity of the peak changes in traffic flow characteristics between the target traffic node and its neighboring traffic nodes can be determined. By utilizing the differences in the number of vehicles and the similarity in the peak changes of traffic flow characteristics, the traffic flow pressure coefficients of each upstream node on the target traffic node are determined. Determine the impact index of current weather parameters on road traffic, and use the traffic impact index and traffic flow pressure coefficient to determine the pressure coefficient of the target traffic node; The traffic management information system is operated and maintained using the pressure bearing coefficient and the corresponding overall pressure bearing benchmark value.

[0006] Furthermore, the determination of the difference in the number of vehicles between the target time and its adjacent time in the road image also includes: Obtain the number of target vehicles at a target time in a road image and the number of the same vehicles between its previous adjacent time points; The number of new vehicles at the target time is determined by using the target number of vehicles and the number of identical vehicles, and the rate of change of traffic flow is determined by using the target number of vehicles and the number of new vehicles. The period when the rate of change in traffic flow is greater than or equal to a preset traffic flow threshold is defined as the peak traffic flow period. During the peak traffic flow period, the step of determining the difference in the number of vehicles between the target time and its adjacent time in the road image is performed.

[0007] Furthermore, obtaining the number of target vehicles in the road image at the target time includes: Obtain the difference in the number of vehicles between the initial number of vehicles identified at the target time and the number of parked vehicles in the road image; The difference in the number of vehicles is taken as the target number of vehicles at the target time in the road image.

[0008] Furthermore, determining the mainstream driving direction of vehicles at the target traffic node using the differences in the number of vehicles in various road images includes: Determine the maximum vehicle number difference among the differences in vehicle number among the road images in the target traffic node, and use the maximum vehicle number difference as the peak traffic flow of the target traffic node. The direction of vehicle travel at the intersection corresponding to the peak traffic flow of the target traffic node is taken as the mainstream direction of vehicle travel at the target traffic node.

[0009] Furthermore, the method of determining the similarity of peak traffic flow characteristics between the target traffic node and its neighboring traffic nodes by utilizing the difference in the mainstream driving direction of vehicles includes: Determine the peak dynamic time-normalized distance between the peak traffic flow of the target traffic node and its adjacent traffic nodes; Determine the first cosine similarity between the target traffic node and the vectors corresponding to the main driving directions of vehicles of their respective neighboring traffic nodes; Using the peak dynamic time-normalized distance and the first cosine similarity, the similarity of the peak changes in traffic flow characteristics between the target traffic node and its neighboring traffic nodes is calculated.

[0010] Furthermore, the method of determining the traffic flow pressure coefficient of each upstream node on the target traffic node by utilizing differences in vehicle numbers and similarities in peak changes of traffic flow characteristics includes: The traffic flow attenuation coefficient of a target traffic node compared to its neighboring traffic nodes is determined by utilizing the similarity of peak changes in traffic flow characteristics. By utilizing the traffic flow attenuation coefficient and the difference in the number of vehicles, the traffic flow pressure coefficient of each upstream node on the target traffic node is determined.

[0011] Furthermore, the step of determining the traffic flow attenuation coefficient of the target traffic node relative to its neighboring traffic nodes by utilizing the similarity of peak changes in traffic flow characteristics includes: Determine the change in traffic flow between the target traffic node and its adjacent traffic nodes at the target time. By utilizing the similarity of peak changes in traffic flow characteristics and the traffic flow change value, the traffic flow attenuation coefficient of the target traffic node compared to its neighboring traffic nodes is calculated.

[0012] Furthermore, determining the traffic flow pressure coefficient of each upstream node on the target traffic node using the traffic flow attenuation coefficient and the difference in the number of vehicles includes: Determine the reference traffic flow ratio of the difference in the number of vehicles at a reference intersection among adjacent traffic nodes at the target time, relative to the number of vehicles at adjacent traffic nodes. Determine the second cosine similarity between the vectors corresponding to the vehicle travel direction at the reference intersection and the mainstream vehicle travel direction at the target traffic node; Using the traffic flow attenuation coefficient, the reference traffic flow ratio, and the second cosine similarity, the traffic flow pressure coefficient of the adjacent traffic node as the upstream node of the target traffic node is calculated.

[0013] Furthermore, determining the driving impact index of current weather parameters on roads, and using the driving impact index and traffic flow pressure coefficient to determine the pressure coefficient of the target traffic node, includes: The impact index of current weather parameters on road driving is determined by the humidity deviation of the air humidity value of the target number of days within a preset period compared with the average air humidity. The pressure coefficient of the target traffic node is calculated by using the traffic impact index, traffic flow pressure coefficient and preset cycle number of days.

[0014] Furthermore, the operation and maintenance management of the traffic management information system using the pressure bearing coefficient and the corresponding overall pressure bearing benchmark value includes: Subtracting the corresponding overall pressure bearing benchmark value from the pressure bearing coefficient yields the actual pressure bearing deviation of the target traffic node. If the actual load-bearing deviation of a node is less than or equal to 0, the target traffic node is determined to be within the safe load-bearing range. When the actual pressure deviation of a node is greater than 0, the target traffic node is classified and warned based on the actual pressure deviation of the node.

[0015] The present invention has the following beneficial effects: This invention utilizes surrounding monitoring devices, such as surveillance cameras and temperature and humidity monitors, placed at various road traffic nodes within an urban traffic management information system to acquire multi-source data information about these nodes. Based on this multi-source data, it analyzes the traffic flow pressure index that different urban road nodes can withstand and compares it with the pressure index (benchmark value) designed for road construction. A tiered early warning mechanism is implemented based on the deviation analysis results. This enables a multi-level response-based, integrated operation and maintenance management process that triggers when the actual pressure value of a traffic node exceeds a threshold. This improves the accuracy of urban road traffic pressure assessment, optimizes the efficiency of operation and maintenance resource allocation, and ensures that traffic operation and maintenance strategies meet actual traffic needs. Attached Figure Description

[0016] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the steps of an information system intensive operation and maintenance management method that integrates multi-source data, provided in one embodiment of the present invention. Figure 2 This is a detailed flowchart of the steps preceding step S1 in an information system intensive operation and maintenance management method that integrates multi-source data, provided in an embodiment of the present invention. Figure 3 This is a detailed flowchart of step S1 in an information system intensive operation and maintenance management method that integrates multi-source data, provided in an embodiment of the present invention. Figure 4 This is a detailed flowchart of step S2 in an information system intensive operation and maintenance management method that integrates multi-source data, provided in an embodiment of the present invention. Figure 5 This is a detailed flowchart of step S3 in an information system intensive operation and maintenance management method that integrates multi-source data, provided in an embodiment of the present invention. Figure 6This is a schematic diagram of the hardware operating environment of the information system centralized operation and maintenance management equipment that integrates multi-source data, as described in the embodiments of the present invention. Detailed Implementation

[0018] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a method for intensive operation and maintenance management of an information system integrating multi-source data proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0020] It should be noted that, in order to ensure that the calculation results are meaningful, when performing fractional operations, if the denominator is 0, a parameter adjustment factor greater than 0 needs to be added to the denominator to prevent the denominator from being 0. The value of the parameter adjustment factor shall be set by the implementer according to the actual situation, and this application does not impose any special restrictions.

[0021] The following description, in conjunction with the accompanying drawings, details a specific scheme for an information system intensive operation and maintenance management method that integrates multi-source data, provided by the present invention.

[0022] Example 1: For the integrated operation and maintenance management method of an information system that integrates multi-source data provided by this invention, please refer to [link / reference]. Figure 1 The diagram illustrates a flowchart of the steps of an information system intensive operation and maintenance management method that integrates multi-source data, provided by an embodiment of the present invention.

[0023] The method for intensive operation and maintenance management of information systems that integrate multi-source data includes: Step S1: Determine the difference in the number of vehicles between the target time and its adjacent time in the road image, and use the difference in the number of vehicles in each road image to determine the main driving direction of vehicles at the target traffic node. In this embodiment, multi-source data networks at urban road traffic network nodes (traffic nodes) are acquired through different monitoring devices.

[0024] Specifically, this includes acquiring data from urban road traffic cameras at the locations of road traffic network nodes and uploading this data to a traffic information system in real time. The system performs semantic segmentation on the collected road image (video) data to obtain the road traffic flow within the data. Simultaneously, the data is recorded in real time according to the monitoring time.

[0025] Please refer to Figure 2 In one embodiment, prior to step S1, the method further includes: Step S101: Obtain the number of target vehicles at the target time and the number of the same vehicles between the previous adjacent time points in the road image; Specifically, step S101 includes: Obtain the difference in the number of vehicles between the initial number of vehicles identified at the target time and the number of parked vehicles in the road image; The difference in the number of vehicles is taken as the target number of vehicles at the target time in the road image.

[0026] Step S102: Determine the number of new vehicles at the target time using the target number of vehicles and the number of identical vehicles, and determine the rate of change of traffic flow using the target number of vehicles and the number of new vehicles. Step S103: The period when the rate of change of traffic flow is greater than or equal to the preset traffic flow threshold is defined as the peak traffic flow period. During the peak traffic flow period, the step of determining the difference in the number of vehicles between the target time and its adjacent time in the road image is performed.

[0027] Monitoring data (including road images) of a single traffic network node can reflect the actual traffic flow within that node. Based on real-time road video (image) data acquired by cameras in the urban road traffic information system, semantic recognition is performed on single-frame image data to obtain vehicle data information within the image. However, at some intersections, temporary parked vehicles on the roadside cause distortion in the traffic flow data collected at a single moment. Therefore, by matching traffic flow between adjacent frames, information on the same moving vehicles in adjacent frames is obtained, and newly added vehicles and vehicles whose positions are moving are marked. Based on the above analysis, the number of target vehicles in the road image at the target time for a target traffic node can be determined. : In the formula, i is the target time, which is also the image number of a single frame; The target number of vehicles, i.e., the actual traffic flow; This refers to the number of parked vehicles, which is also the number of vehicle data distortions caused by parked vehicles. This represents the initial number of vehicles identified in a single frame of the image, which is also the initial traffic flow.

[0028] This algorithm uses a lightweight model called KNN (K-Nearest Neighbors) to match the same vehicle in adjacent road images, thereby obtaining the number of vehicles that are the same in adjacent frames. , The target number of vehicles. Given the actual number of vehicles at the time immediately preceding the target time, take the intersection of the two times to obtain the same number of vehicles. .

[0029] Then, the number of new vehicles is obtained by combining the number of target vehicles at target time i. : In the formula, The target number of vehicles. For the same number of vehicles.

[0030] The above implementation process uses the actual traffic flow obtained after filtering out the impact of illegally parked vehicles, thus avoiding the influence of temporarily parked vehicles on the identification of real traffic flow and improving the accuracy of traffic flow identification.

[0031] Furthermore, due to the large number of vehicles flowing through urban traffic nodes daily, using the average daily traffic flow at a single frame to represent traffic flow can be distorted. For example, traffic flow is high during rush hour in industrial and software parks, sometimes exceeding half of the total daily traffic flow, while traffic flow is low during working hours, with only a few vehicles passing through in short periods. Therefore, the daily vehicle traffic volume is segmented based on traffic flow fluctuations, and monitoring time periods are matched with traffic flow data based on time duration ranges and traffic flow data. This means matching the number of vehicles at each time point with the corresponding time point.

[0032] Subsequently, based on the changes in traffic flow within different data segments, the ratio of the number of vehicles per time period, i.e., the rate of change of traffic flow, is constructed. : In the formula, The target number of vehicles at time 1. The number of new vehicles at time i. for Total traffic volume during the monitoring period This is an inverse proportional value to the traffic flow statistics time (monitoring period, which can be set as needed, such as 2 hours), where the first... The timeframe represents the last moment of the monitoring period. The shorter the time it takes for traffic to pass through, the greater the traffic volume. To monitor the relationship between changes in traffic flow and time within a given period, the larger this value, the greater the traffic flow within that period.

[0033] Set the preset traffic flow threshold to 0.7 (adjustable). If the traffic volume is high during that monitoring period, it is considered a peak traffic period and can be used as a characteristic period for the day's traffic volume.

[0034] In order to save computing resources and improve analysis efficiency, the following embodiments and implementation processes can focus on the operation and maintenance management of the traffic management information system during peak traffic hours.

[0035] Please refer to Figure 3 In one embodiment, step S1 specifically includes: Step S11: Determine the maximum vehicle number difference among the differences in vehicle number among the road images in the target traffic node, and use the maximum vehicle number difference as the peak traffic flow of the target traffic node. Step S12: The direction of vehicle travel at the intersection corresponding to the peak traffic flow of the target traffic node is taken as the mainstream direction of vehicle travel of the target traffic node.

[0036] For detection data from a single camera (one road image at time i), obtain traffic flow information (differences in the number of vehicles) within the camera's view. , The target number of vehicles. This represents the actual number of vehicles in the time immediately preceding the target time.

[0037] By combining the increase and decrease of vehicles under different cameras, the camera with the largest change in vehicle volume is identified. The direction of travel at the intersection monitored by this camera is then the mainstream travel direction of vehicles. This can be further represented as follows: In the formula, The maximum difference in the number of vehicles among the differences in the number of vehicles in each road image is the peak traffic flow at the traffic node where it is located. This represents the total number of possible travel directions for vehicles at all intersections within a traffic node; through The function obtains the drivable direction with the maximum traffic flow (maximum difference in the number of vehicles) as the mainstream driving direction for vehicles.

[0038] Step S2: Utilize the differences in the mainstream driving directions of vehicles between the target traffic node and its neighboring traffic nodes to determine the similarity of peak changes in traffic flow characteristics between the target traffic node and its neighboring traffic nodes. Urban transportation network nodes are not isolated. Due to route design, any two traffic nodes may be related. For example, within a regional transportation network, the traffic flow changes at work area node 1 and residential area node 3, which are separated from each other, are related due to commuting hours. Therefore, when operating and managing an urban regional transportation network information system, multi-source data from traffic nodes is collected, the changing trends and correlations of similar data between different nodes are analyzed, and daily change curves are constructed based on daily data. Data clustering can also be used to identify similar nodes, filter and remove abnormal data, and retain valid information. Subsequently, by combining daily monitoring data with historical change curves, the causes of traffic node anomalies are analyzed, and based on this, centralized operation and maintenance management is implemented for events reflected in the information system.

[0039] Furthermore, in urban traffic networks, there are dynamic correlations between traffic nodes at adjacent intersections. Taking urban arterial roads as an example, they typically handle large traffic volumes. Vehicles merging from intersections on both sides continuously increase the traffic flow intensity at nodes on the arterial road (such as node a), ultimately causing traffic from three directions to converge at this node and then concentrate in a single direction towards the downstream node (node ​​b). This process directly exacerbates the traffic pressure at node b. Simultaneously, although node c, the neighboring node of node a, is not directly adjacent to node b, due to the traffic flow transfer effect of node a, the traffic flow of node c can still be indirectly transmitted to node b through node a. This indicates that in this regional road network, non-adjacent nodes can form indirect connections through intermediary nodes. Based on the coupling relationship analysis of traffic flow changes at each node under characteristic peak conditions, the dynamic differences in traffic flow data across different road segments can be further quantified.

[0040] Please refer to Figure 4 Step S2 specifically includes: Step S21: Determine the peak dynamic time normalization distance between the peak traffic flow of the target traffic node and its neighboring traffic nodes. Step S22: Determine the first cosine similarity between the target traffic node and the vectors corresponding to the main driving directions of vehicles of their respective neighboring traffic nodes; Step S23: Using the peak dynamic time normalization distance and the first cosine similarity, calculate the similarity of the peak change of traffic flow characteristics between the target traffic node and its neighboring traffic nodes.

[0041] Similarity index (similarity of peak traffic flow changes) is obtained for the time series of traffic flow changes during the characteristic peak periods between adjacent traffic nodes j and j+1 (j+1 is the target traffic node). : In the formula, This indicates the similarity of peak changes in traffic flow characteristics between adjacent traffic nodes j and j+1; Let j be the peak traffic flow of the adjacent traffic node. The peak traffic flow between adjacent traffic nodes j and j+1 (Dynamic Time Warping) Distance Represents an exponential function with base to the natural constant, expressed as... Normalize the negative correlation of the DTW distance to unify the units; The cosine similarity between the vectors corresponding to the main driving directions of vehicles at adjacent traffic nodes j and j+1 (to distinguish it from the other cosine similarity mentioned below, it is referred to as the first cosine similarity here). The larger this value is, the more similar the main driving directions of vehicles at adjacent nodes j and j+1 are. This represents the similarity of traffic flow changes at peak times of traffic flow characteristics at similar nodes j and j+1 in the mainstream driving direction of vehicles. norm represents a linear normalization function, such as a maximum-minimum normalization function.

[0042] The above implementation process is used to obtain the similarity of peak changes in traffic flow characteristics between any other adjacent nodes. .

[0043] Step S3: Using the differences in the number of vehicles and the similarity of peak changes in traffic flow characteristics, determine the traffic flow pressure coefficient of each upstream node of the target traffic node. During the journey, vehicles will continuously enter and exit the current node. Correspondingly, there may be significant data changes between different nodes. Therefore, by analyzing the traffic flow changes between different nodes in real time, pressure parameters of traffic flow changes between nodes can be obtained.

[0044] Specifically, please refer to Figure 5 Step S3 includes: Step S31: Determine the traffic flow attenuation coefficient of the target traffic node compared to its neighboring traffic nodes by utilizing the similarity of peak changes in traffic flow characteristics. Specifically, step S31 includes: Determine the change in traffic flow between the target traffic node and its adjacent traffic nodes at the target time. By utilizing the similarity of peak changes in traffic flow characteristics and the traffic flow change value, the traffic flow attenuation coefficient of the target traffic node compared to its neighboring traffic nodes is calculated.

[0045] For adjacent nodes j and j+1, assume that node j is the upstream node of node j+1.

[0046] Traffic flow attenuation coefficient of target traffic node j+1 compared to its neighboring traffic node j : In the formula, The traffic flow attenuation coefficient between adjacent nodes j and j+1 This represents the change in traffic flow within the feature sequence of adjacent nodes (including the number of vehicles at time i). This represents the corresponding mean change. The larger the mean change, the more traffic flows away from the main line within adjacent nodes. This represents the similarity of peak traffic flow characteristics between adjacent traffic nodes j and j+1, and is used here as a similarity coefficient. The larger this value, the better. The higher the accuracy of the value. This is the sequence number of the last moment of the monitoring period.

[0047] Step S32: Using the traffic flow attenuation coefficient and the difference in the number of vehicles, determine the traffic flow pressure coefficient of each upstream node of the target traffic node.

[0048] Specifically, step S32 includes: Determine the reference traffic flow ratio of the difference in the number of vehicles at a reference intersection among adjacent traffic nodes at the target time, relative to the number of vehicles at adjacent traffic nodes. Determine the second cosine similarity between the vectors corresponding to the vehicle travel direction at the reference intersection and the mainstream vehicle travel direction at the target traffic node; Using the traffic flow attenuation coefficient, the reference traffic flow ratio, and the second cosine similarity, the traffic flow pressure coefficient of the adjacent traffic node as the upstream node of the target traffic node is calculated.

[0049] In this embodiment, the more vehicles enter the upstream node, the more vehicles will flow from that node to the downstream node, leading to greater traffic pressure within the downstream node. Therefore, by using the proportion of vehicles entering the upstream node from different intersections and the attenuation coefficient of the traffic flow from the upstream node to the downstream node, the traffic pressure coefficient of different nodes on the downstream node is obtained. : In the formula, Let be the difference in the number of vehicles at intersection k (denoted as the reference intersection) at time i for node j. This represents the percentage of the difference in the number of vehicles at intersection k relative to the total number of vehicles at node j, serving as a reference for traffic flow. This represents the average percentage of reference traffic flow during the characteristic peak period (peak traffic hours). This is the traffic flow attenuation coefficient. The value is the product of the average proportion of reference traffic flow during the characteristic peak period and the traffic flow attenuation coefficient, representing the traffic flow pressure of vehicle k at intersection k on node j. Let cosine similarity (denoted here as second cosine similarity) be the vectors corresponding to the main traffic directions at intersection k and node j+1. Describing function The sign value of k is used to obtain the numerical relationship between different nodes. When the value is positive, the influence of intersection k on traffic flow is positively correlated, and vice versa.

[0050] when When the intersection k has zero impact on the traffic flow pressure of the downstream node j+1, then the impact of the intersection k on the traffic flow pressure of the downstream node j+1 is zero.

[0051] Based on the above implementation process, the traffic flow pressure coefficient between traffic nodes in the region is... Perform a traversal and analyze the traffic flow pressure coefficient for each vehicle. By accumulating these parameters, the pressure on each road node from the traffic flow of other nodes can be obtained. .

[0052] Step S4: Determine the impact index of current weather parameters on road traffic, and use the traffic impact index and traffic flow pressure coefficient to determine the pressure coefficient of the target traffic node. Specifically, step S4 includes: The impact index of current weather parameters on road driving is determined by the humidity deviation of the air humidity value of the target number of days within a preset period compared with the average air humidity. The pressure coefficient of the target traffic node is calculated by using the traffic impact index, traffic flow pressure coefficient and preset cycle number of days.

[0053] In this embodiment, the weather conditions in different areas of the city can also be obtained based on the division of urban areas. For example, if the city is experiencing rainy weather, the air humidity information in different areas can be analyzed.

[0054] Traffic congestion in urban areas is not static. For example, in sunny weather, vehicles travel quickly, and more vehicles pass through nodes in a short period of time, resulting in a larger traffic flow. However, in rainy or snowy weather, the roads are slippery, and vehicles need to pass slowly to ensure driving safety. This leads to a situation where, despite a large traffic flow, fewer vehicles pass through nodes in a short period of time, causing changes in the pressure parameters of traffic flow between different nodes.

[0055] Therefore, by comparing traffic flow pressure parameters at various points within a single month and obtaining current weather parameters, the deviation of air humidity from its average value is used as the index of the impact of weather conditions on road traffic. : In the formula, Number the days. The driving impact index refers to the driving impact index on day t (denoted as the target day, referring to any given day). Let be the air humidity value on day t. The average air humidity over a preset period of days (e.g., 30 days); The humidity offset is the deviation of the air humidity value on day t within a preset period of days from the average air humidity. norm represents a linear normalization function, which makes the larger the humidity offset, the greater the environmental interference on the vehicle driving status of the node.

[0056] Furthermore, combining the environmental impact index on driving Traffic flow pressure coefficient Corresponding traffic flow pressure parameters This allows us to obtain the stress coefficient of the node. : In the formula, This indicates the node number, which in the above embodiments serves as an adjacent node to the target traffic node. This represents the driving impact index at the j-th node on day t. This could also be the pressure coefficient of the adjacent node j. Similarly, the pressure coefficient of any traffic node including the target traffic node can be obtained. , This represents the traffic flow pressure parameter at node j on day t.

[0057] This represents the overall pressure that a road node can withstand under natural traffic flow and environmental disturbances within a single day. The average pressure borne within a preset 30-day period is used as the pressure coefficient of the node. The larger this value, the greater the traffic pressure the node needs to bear, and the higher the index of road operation and maintenance required for the road section where the node is located.

[0058] Step S5: Use the pressure bearing coefficient and the corresponding overall pressure bearing benchmark value to perform operation and maintenance management of the traffic management information system.

[0059] Specifically, step S5 includes: Subtracting the corresponding overall pressure bearing benchmark value from the pressure bearing coefficient yields the actual pressure bearing deviation of the target traffic node. If the actual load-bearing deviation of a node is less than or equal to 0, the target traffic node is determined to be within the safe load-bearing range. When the actual pressure deviation of a node is greater than 0, the target traffic node is classified and warned based on the actual pressure deviation of the node.

[0060] In this embodiment, the operation and maintenance management of the traffic management information system is achieved by obtaining the pressure coefficient of each node and combining the pressure difference relationship between different nodes in the region.

[0061] Specifically, by integrating multi-source heterogeneous data from different nodes through the above embodiments, the pressure coefficient of traffic flow at each single node within the region is calculated, and combined with the overall pressure benchmark value of the current node region. The actual bearing pressure deviation of the node is derived. .when If the node is within a safe carrying capacity range, no road maintenance intervention is required at this time; if Therefore, it is necessary to implement hierarchical and intensive operation and maintenance management of nodes based on the actual pressure deviation of the nodes.

[0062] For example, based on Quantitative values ​​are used to classify operation and maintenance levels (e.g., Level 3 early warning). Yellow alert. Orange alert issued. (For red alerts), resource allocation plans of different intensities will be activated accordingly; red alert nodes can temporarily requisition manpower / equipment from adjacent low-load road sections, and achieve dynamic balance of cross-regional operation and maintenance resources through tidal lane technology.

[0063] This invention utilizes surrounding monitoring devices, such as surveillance cameras and temperature and humidity monitors, placed at various road traffic nodes within an urban traffic management information system to acquire multi-source data information about these nodes. Based on this multi-source data, it analyzes the traffic flow pressure index that different urban road nodes can withstand and compares it with the pressure index (benchmark value) designed for road construction. A tiered early warning mechanism is implemented based on the deviation analysis results. This enables a multi-level response-based, integrated operation and maintenance management process that triggers when the actual pressure value of a traffic node exceeds a threshold. This improves the accuracy of urban road traffic pressure assessment, optimizes the efficiency of operation and maintenance resource allocation, and ensures that traffic operation and maintenance strategies meet actual traffic needs.

[0064] Example 2: This invention also proposes an information system centralized operation and maintenance management device that integrates multi-source data. The device can be a data processing device such as a computer or a server, or a combination of multiple devices.

[0065] like Figure 6 As shown, Figure 6 This is a schematic diagram of the hardware operating environment of the information system centralized operation and maintenance management equipment that integrates multi-source data, which is involved in the embodiments of the present invention.

[0066] like Figure 6As shown, the integrated multi-source data information system centralized operation and maintenance management device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to realize communication between these components. The user interface 1003 may include a display or an input unit such as a control panel; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WIFI interface). The memory 1005 may be high-speed RAM or stable non-volatile memory, such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001. The memory 1005, as a computer storage medium, may include an information system centralized operation and maintenance management program.

[0067] Those skilled in the art will understand that Figure 6 The hardware structure shown does not constitute a limitation on the device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0068] Continue to refer to Figure 6 , Figure 6 The memory 1005, which is a computer-readable storage medium, may include an operating device, a user interface module, a network communication module, and an information system integrated operation and maintenance management program.

[0069] exist Figure 6 In this embodiment, the network communication module is mainly used to connect to the server and can communicate with the server for data; while the processor 1001 can call the information system centralized operation and maintenance management program stored in the memory 1005 and execute the steps in the above embodiments.

[0070] Based on the hardware structure of the information system centralized operation and maintenance management device that integrates multi-source data described above, various embodiments of the information system centralized operation and maintenance management method integrating multi-source data of the present invention are implemented.

[0071] Furthermore, the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores an information system centralized operation and maintenance management program, wherein, when executed by a processor, the information system centralized operation and maintenance management program implements the steps of the information system centralized operation and maintenance management method for integrating multi-source data as described above.

[0072] The method implemented when the information system centralized operation and maintenance management program is executed can be referred to in various embodiments of the information system centralized operation and maintenance management method integrating multi-source data of the present invention, and will not be repeated here.

[0073] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0074] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0075] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] The above description is only a preferred embodiment of the present invention and does not limit the scope of protection of the present invention. All equivalent structural / method transformations made under the inventive concept of the present invention using the contents of the present invention specification and drawings, or direct / indirect applications in other related technical fields, are included within the scope of protection of the present invention.

Claims

1. A method for intensive operation and maintenance management of an information system that integrates multi-source data, characterized in that, The method includes: Determine the difference in vehicle numbers between the target time and its adjacent time in the road image, and use the difference in vehicle numbers in each road image to determine the mainstream driving direction of vehicles at the target traffic node. By utilizing the differences in the mainstream driving directions of vehicles between the target traffic node and its neighboring traffic nodes, the similarity of the peak changes in traffic flow characteristics between the target traffic node and its neighboring traffic nodes can be determined. By utilizing the differences in the number of vehicles and the similarity in the peak changes of traffic flow characteristics, the traffic flow pressure coefficients of each upstream node on the target traffic node are determined. Determine the impact index of current weather parameters on road traffic, and use the traffic impact index and traffic flow pressure coefficient to determine the pressure coefficient of the target traffic node; The traffic management information system is operated and maintained using the pressure bearing coefficient and the corresponding overall pressure bearing benchmark value.

2. The method for intensive operation and maintenance management of information systems integrating multi-source data according to claim 1, characterized in that, The determination of the difference in the number of vehicles between a target time and its adjacent times in a road image also includes, prior to: Obtain the number of target vehicles at a target time in a road image and the number of the same vehicles between its previous adjacent time points; The number of new vehicles at the target time is determined by using the target number of vehicles and the number of identical vehicles, and the rate of change of traffic flow is determined by using the target number of vehicles and the number of new vehicles. The period when the rate of change in traffic flow is greater than or equal to a preset traffic flow threshold is defined as the peak traffic flow period. During the peak traffic flow period, the step of determining the difference in the number of vehicles between the target time and its adjacent time in the road image is performed.

3. The method for intensive operation and maintenance management of information systems integrating multi-source data according to claim 2, characterized in that, The acquisition of the number of target vehicles in the road image at the target time includes: Obtain the difference in the number of vehicles between the initial number of vehicles identified at the target time and the number of parked vehicles in the road image; The difference in the number of vehicles is taken as the target number of vehicles at the target time in the road image.

4. The method for intensive operation and maintenance management of information systems integrating multi-source data according to claim 1, characterized in that, The method of determining the main driving direction of vehicles at the target traffic node by utilizing the differences in the number of vehicles in various road images includes: Determine the maximum vehicle number difference among the differences in vehicle number among the road images in the target traffic node, and use the maximum vehicle number difference as the peak traffic flow of the target traffic node. The direction of vehicle travel at the intersection corresponding to the peak traffic flow of the target traffic node is taken as the mainstream direction of vehicle travel at the target traffic node.

5. The method for intensive operation and maintenance management of information systems integrating multi-source data according to claim 1, characterized in that, The method of determining the similarity of peak traffic flow characteristics between a target traffic node and its neighboring traffic nodes by utilizing the differences in the mainstream driving directions of vehicles includes: Determine the peak dynamic time-normalized distance between the peak traffic flow of the target traffic node and its adjacent traffic nodes; Determine the first cosine similarity between the target traffic node and the vectors corresponding to the main driving directions of vehicles of their respective neighboring traffic nodes; Using the peak dynamic time-normalized distance and the first cosine similarity, the similarity of the peak changes in traffic flow characteristics between the target traffic node and its neighboring traffic nodes is calculated.

6. The method for intensive operation and maintenance management of information systems integrating multi-source data according to claim 1, characterized in that, The method of determining the traffic flow pressure coefficient of each upstream node on the target traffic node by utilizing differences in vehicle numbers and similarities in peak changes in traffic flow characteristics includes: The traffic flow attenuation coefficient of a target traffic node compared to its neighboring traffic nodes is determined by utilizing the similarity of peak changes in traffic flow characteristics. By utilizing the traffic flow attenuation coefficient and the difference in the number of vehicles, the traffic flow pressure coefficient of each upstream node on the target traffic node is determined.

7. The method for intensive operation and maintenance management of information systems integrating multi-source data according to claim 6, characterized in that, The method of determining the traffic flow attenuation coefficient of a target traffic node relative to its neighboring traffic nodes by utilizing the similarity of peak changes in traffic flow characteristics includes: Determine the change in traffic flow between the target traffic node and its adjacent traffic nodes at the target time. By utilizing the similarity of peak changes in traffic flow characteristics and the traffic flow change value, the traffic flow attenuation coefficient of the target traffic node compared to its neighboring traffic nodes is calculated.

8. The method for intensive operation and maintenance management of information systems integrating multi-source data according to claim 6, characterized in that, The step of determining the traffic flow pressure coefficient of each upstream node on the target traffic node by utilizing the traffic flow attenuation coefficient and the difference in the number of vehicles includes: Determine the reference traffic flow ratio of the difference in the number of vehicles at a reference intersection among adjacent traffic nodes at the target time, relative to the number of vehicles at adjacent traffic nodes. Determine the second cosine similarity between the vectors corresponding to the vehicle travel direction at the reference intersection and the mainstream vehicle travel direction at the target traffic node; Using the traffic flow attenuation coefficient, the reference traffic flow ratio, and the second cosine similarity, the traffic flow pressure coefficient of the adjacent traffic node as the upstream node of the target traffic node is calculated.

9. The method for intensive operation and maintenance management of an information system integrating multi-source data according to claim 1, characterized in that, The process of determining the impact index of current weather parameters on road traffic, and using the traffic impact index and traffic flow pressure coefficient to determine the pressure coefficient of the target traffic node, includes: The impact index of current weather parameters on road driving is determined by the humidity deviation of the air humidity value of the target number of days within a preset period compared with the average air humidity. The pressure coefficient of the target traffic node is calculated by using the traffic impact index, traffic flow pressure coefficient and preset cycle number of days.

10. The method for intensive operation and maintenance management of an information system integrating multi-source data according to claim 1, characterized in that, The operation and maintenance management of the traffic management information system using the pressure bearing coefficient and the corresponding overall pressure bearing benchmark value includes: Subtracting the corresponding overall pressure bearing benchmark value from the pressure bearing coefficient yields the actual pressure bearing deviation of the target traffic node. If the actual load-bearing deviation of a node is less than or equal to 0, the target traffic node is determined to be within the safe load-bearing range. When the actual pressure deviation of a node is greater than 0, the target traffic node is classified and warned based on the actual pressure deviation of the node.

Images