An information system intensive operation and maintenance management method integrating multi-source data

Abstract

The application 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. The method comprises the following steps: determining the vehicle quantity difference between adjacent time points in a road image, determining the main vehicle flow direction of a target traffic node by using the vehicle quantity difference; determining the traffic flow characteristic peak value change similarity between adjacent traffic nodes by using the main vehicle flow direction difference between the adjacent traffic nodes; determining the traffic flow pressure coefficient of the target traffic node by using the vehicle quantity difference and the traffic flow characteristic peak value change similarity; determining the driving influence index of the current weather parameter on the road, combining the traffic flow pressure coefficient to determine the bearing pressure coefficient of the target traffic node, and then realizing the hierarchical operation and maintenance management of the traffic management information system. Through the technical scheme of the application, 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] The present application 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. BACKGROUND

[0002] Urban road traffic management is an important part of urban development, and its operation and maintenance management level directly affects the safety, smoothness of urban traffic and the sustainable development of the city. With the rapid development of information technology, the fine processing based on the data of various monitoring nodes in the city is gradually replacing the traditional manual method. This digital urban operation and maintenance information system supports the intelligent operation and maintenance management of urban traffic network.

[0003] The existing traffic operation and maintenance management system integrates the floating car trajectory data of urban intersections and the road network topology information, dynamically calculates the regional traffic flow parameters, and guides the road infrastructure maintenance and signal optimization configuration according to the real-time traffic load level, so as to realize the intelligent operation and maintenance management of urban traffic network. However, the data of regional road congestion events caused by extreme weather such as heavy rain and snow often changes dynamically, which can cause distortion of traffic flow characteristic parameters through abnormal data injection, and thus weaken the support efficiency of traffic management platform for operation and maintenance decision.

[0004] The existing method quantifies traffic flow characteristics by integrating floating car data of various intersections in the city and road network topology information, and formulates road maintenance plans according to static flow threshold classification. However, due to large changes in environmental and node data, it is difficult to effectively capture the local congestion conduction phenomenon caused by the dynamic coupling effect of traffic between traffic nodes, resulting in that the operation and maintenance strategy lags behind the actual traffic demand, causing operation and maintenance resource mismatch and efficiency loss. SUMMARY

[0005] In order to solve the technical problem that the existing traffic operation and maintenance management method easily leads to that the operation and maintenance strategy lags behind the actual traffic demand, causing operation and maintenance resource mismatch and low efficiency, the purpose of the present application is to provide an information system intensive operation and maintenance management method integrating multi-source data, and the technical solution adopted is as follows:

[0006] The present application provides an information system intensive operation and maintenance management method integrating multi-source data, which comprises:

[0007] Determining the vehicle quantity difference between the target time and its adjacent time in the road image, and determining the main flow driving direction of the vehicle of the target traffic node by using the vehicle quantity difference of each road image;

[0008] Determining the similarity of the peak value change of the traffic flow between the target traffic node and its adjacent traffic node by using the difference of the main flow driving direction of the vehicle between the target traffic node and its adjacent traffic node;

[0009] Determine the vehicle flow pressure coefficient of each upstream node of the target traffic node to the target traffic node by using the vehicle quantity difference and the similarity of the peak value change of the vehicle flow;

[0010] Determine the driving influence index of the current weather parameter on the road, and determine the bearing pressure coefficient of the target traffic node by using the driving influence index and the vehicle flow pressure coefficient;

[0011] Use the bearing pressure coefficient and the corresponding overall bearing reference value to perform operation and maintenance management on the traffic management information system.

[0012] Further, the determination of the vehicle quantity difference between the target time and its adjacent time in the road image further comprises:

[0013] Obtain the target vehicle quantity of the target time and the same vehicle quantity between the adjacent time in the road image;

[0014] Determine the new vehicle quantity of the target time by using the target vehicle quantity and the same vehicle quantity, and determine the vehicle flow change rate by using the target vehicle quantity and the new vehicle quantity;

[0015] The period when the vehicle flow change rate is greater than or equal to the preset vehicle flow threshold value is regarded as the vehicle flow peak period, and the step of determining the vehicle quantity difference between the target time and its adjacent time in the road image is executed in the vehicle flow peak period.

[0016] Further, the target vehicle quantity of the target time in the road image is obtained, comprising:

[0017] Obtain the vehicle quantity difference between the initial vehicle quantity and the parked vehicle quantity identified in the target time in the road image;

[0018] The vehicle quantity difference is regarded as the target vehicle quantity of the target time in the road image.

[0019] Further, the vehicle main flow driving direction of the target traffic node is determined by using the vehicle quantity difference of each road image, comprising:

[0020] Determine the maximum vehicle quantity difference in the vehicle quantity difference of each road image in the target traffic node, and regard the maximum vehicle quantity difference as the peak value of the vehicle flow of the target traffic node;

[0021] The vehicle driving direction of the intersection corresponding to the peak value of the vehicle flow of the target traffic node is regarded as the vehicle main flow driving direction of the target traffic node.

[0022] Further, the similarity of the peak value change of the vehicle flow between the target traffic node and its adjacent traffic node is determined by using the vehicle main flow driving direction difference between the target traffic node and its adjacent traffic node, comprising:

[0023] determining a peak dynamic time warping distance between the target traffic node and the peak traffic flow of each of the adjacent traffic nodes;

[0024] determining a first cosine similarity between the target traffic node and the corresponding vector of the main flow driving direction of each of the adjacent traffic nodes;

[0025] calculating the traffic flow characteristic peak value change similarity between the target traffic node and the adjacent traffic nodes by using the peak dynamic time warping distance and the first cosine similarity.

[0026] Further, the determination of the traffic flow pressure coefficient of each upstream node of the target traffic node by using the vehicle quantity difference and the traffic flow characteristic peak value change similarity comprises:

[0027] determining the traffic flow attenuation coefficient of the target traffic node compared with the adjacent traffic nodes by using the traffic flow characteristic peak value change similarity;

[0028] determining the traffic flow pressure coefficient of each upstream node of the target traffic node by using the traffic flow attenuation coefficient and the vehicle quantity difference.

[0029] Further, the determination of the traffic flow attenuation coefficient of the target traffic node compared with the adjacent traffic nodes by using the traffic flow characteristic peak value change similarity comprises:

[0030] determining the traffic flow change value between the target traffic node and the vehicle quantity of each of the adjacent traffic nodes at the target time;

[0031] determining the traffic flow attenuation coefficient of the target traffic node compared with the adjacent traffic nodes by using the traffic flow characteristic peak value change similarity and the traffic flow change value.

[0032] Further, the determination of the traffic flow pressure coefficient of each upstream node of the target traffic node by using the traffic flow attenuation coefficient and the vehicle quantity difference comprises:

[0033] determining a reference traffic flow proportion of the vehicle quantity difference of a reference intersection in the adjacent traffic nodes relative to the vehicle quantity of the adjacent traffic nodes at the target time;

[0034] determining a second cosine similarity between the corresponding vector of the intersection vehicle driving direction of the reference intersection and the main flow driving direction of the target traffic node;

[0035] determining the traffic flow pressure coefficient of each upstream node of the target traffic node by using the traffic flow attenuation coefficient, the reference traffic flow proportion and the second cosine similarity.

[0036] Further, the determination of the driving influence index of the current weather parameter on the road, the determination of the bearing pressure coefficient of the target traffic node by using the driving influence index and the traffic flow pressure coefficient comprises:

[0037] The driving influence index of the current weather parameter on the road is determined by using the humidity deviation of the air humidity value of the target number of days in the preset period of days compared with the air humidity average value;

[0038] The bearing pressure coefficient of the target traffic node is calculated by using the driving influence index, the traffic flow pressure coefficient and the preset period of days.

[0039] Further, the operation and maintenance management of the traffic management information system by using the bearing pressure coefficient and the corresponding overall bearing reference value comprises:

[0040] The node actual bearing deviation of the target traffic node is obtained by subtracting the corresponding overall bearing reference value from the bearing pressure coefficient;

[0041] In the case that the node actual bearing deviation is less than or equal to 0, it is determined that the target traffic node is in a safe bearing range;

[0042] In the case that the node actual bearing deviation is greater than 0, the target traffic node is graded and warned by using the node actual bearing deviation.

[0043] The present application has the following beneficial effects:

[0044] The present application obtains multi-source data information of traffic nodes based on the surrounding monitoring equipment such as monitoring cameras, temperature and humidity monitors and the like placed in each road traffic node in the urban traffic management information system, analyzes the traffic flow pressure index that can be borne by different nodes of urban roads based on the obtained multi-source data information, compares and analyzes it with the bearing pressure index (reference value) during road design, implements a graded warning mechanism according to the deviation analysis result, and then realizes the triggering of intensive operation and maintenance management process of multi-level response when the actual pressure value of the traffic node exceeds the threshold, so as to improve the accuracy of urban road traffic pressure evaluation, optimize the efficiency of operation and maintenance resource allocation, and make the traffic operation and maintenance strategy meet the actual traffic demand. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creating any creative labor.

[0046] Figure 1A step flow chart of an integrated multi-source data information system intensive operation and maintenance management method provided by an embodiment of the present application is shown in FIG. 1.

[0047] Figure 2 A detailed flow chart of steps before step S1 in an integrated multi-source data information system intensive operation and maintenance management method provided by an embodiment of the present application is shown in FIG. 2.

[0048] Figure 3 A detailed flow chart of step S1 in an integrated multi-source data information system intensive operation and maintenance management method provided by an embodiment of the present application is shown in FIG. 3.

[0049] Figure 4 A detailed flow chart of step S2 in an integrated multi-source data information system intensive operation and maintenance management method provided by an embodiment of the present application is shown in FIG. 4.

[0050] Figure 5 A detailed flow chart of step S3 in an integrated multi-source data information system intensive operation and maintenance management method provided by an embodiment of the present application is shown in FIG. 5.

[0051] Figure 6 A structure schematic diagram of a hardware operation environment of an integrated multi-source data information system intensive operation and maintenance management device involved in an embodiment of the present application is shown in FIG. 6. DETAILED DESCRIPTION

[0052] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined purposes, the following describes in detail the specific implementation, structure, features and effects of an integrated multi-source data information system intensive operation and maintenance management method according to the present application, with reference to the accompanying drawings and preferred embodiments. Different "one embodiment" or "another embodiment" in the following description do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0053] 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 the present application belongs.

[0054] It should be noted that, in order to ensure that the calculation result is meaningful, when performing fractional operation, the present embodiment needs to add a parameter adjustment factor greater than 0 to the denominator to prevent the denominator from being 0. The value of the parameter adjustment factor is set by the implementer according to the actual situation, and the present application does not make special limitations.

[0055] The specific scheme of the integrated multi-source data information system intensive operation and maintenance management method provided by the present application is described in detail below with reference to the accompanying drawings.

[0056] Embodiment one:

[0057] For the information system intensive operation and maintenance method for integrating multi-source data provided by the application, please refer to Figure 1 , which shows the step flow chart of the information system intensive operation and maintenance method for integrating multi-source data provided by an embodiment of the application.

[0058] The information system intensive operation and maintenance method for integrating multi-source data comprises:

[0059] Step S1, determining the vehicle quantity difference between the target time and its adjacent time in the road image, and determining the main driving direction of the vehicle flow of the target traffic node by using the vehicle quantity difference of each road image;

[0060] In this embodiment, the multi-source data network at the city road traffic network node (traffic node) is obtained by different monitoring devices.

[0061] Specifically, it includes obtaining the data information of the road traffic network node based on the city road traffic camera, and uploading the data information to the traffic information system in real time. The system performs semantic segmentation on the collected road image (video) data to obtain the road traffic flow in the data. At the same time, according to the monitoring time, the data is recorded in real time.

[0062] Please refer to Figure 2 , in an embodiment, before the step S1, the method further comprises:

[0063] Step S101, obtaining the target vehicle quantity at the target time in the road image and the same vehicle quantity between the adjacent time before the target time;

[0064] Among them, the step S101 specifically comprises:

[0065] Obtaining the vehicle quantity difference between the initial vehicle quantity and the parking vehicle quantity identified in the target time in the road image;

[0066] The vehicle quantity difference is taken as the target vehicle quantity at the target time in the road image.

[0067] Step S102, determining the new vehicle quantity at the target time by using the target vehicle quantity and the same vehicle quantity, and determining the traffic flow change rate by using the target vehicle quantity and the new vehicle quantity;

[0068] Step S103, taking the time period with the traffic flow change rate greater than or equal to the preset traffic flow threshold value as the traffic flow peak period, and executing the step of determining the vehicle quantity difference between the target time and its adjacent time in the road image in the traffic flow peak period.

[0069] The monitoring data (including road images) of a single traffic network node can reflect the actual traffic volume in the current node. Based on the real-time video (image) data of the road acquired by the camera in the urban road traffic information system, the vehicle data information existing in the image is acquired by performing semantic recognition on a single frame of image data. Meanwhile, due to the existence of temporary parked vehicles at the roadside, the traffic volume data collected at a single moment at the road intersection is distorted. Therefore, the same vehicle information moving in adjacent frames is acquired by matching the traffic volume of adjacent frames, and the newly added vehicles and positions of the moving vehicles in the image are marked. Through the above analysis, for the target traffic node, the number of target vehicles in the road image of the target moment :

[0070]

[0071] wherein i is the target moment, that is, the single frame image number; is the number of target vehicles, that is, the actual traffic volume; is the number of parked vehicles, that is, the number of vehicle data distorted by the parked vehicles; is the initial number of vehicles identified in the single frame image, that is, the initial traffic volume.

[0072] The same vehicle matching in the road image in adjacent frames is realized based on the light model KNN (K-Nearest Neighbors, K-Nearest Neighbor Algorithm), so as to acquire the number of the same vehicles in adjacent frames , is the number of target vehicles, is the actual number of vehicles at the previous adjacent moment of the target moment, and the intersection of the two is the number of the same vehicles .

[0073] Subsequently, the number of newly added vehicles is acquired in combination with the number of target vehicles at the target moment i :

[0074]

[0075] wherein is the number of target vehicles, is the number of the same vehicles.

[0076] The above implementation process takes the actual traffic volume obtained after filtering the parked vehicles and the like as the standard, avoids the influence of the temporarily parked vehicles on the identification of the real traffic volume, and thus improves the identification accuracy of the traffic volume.

[0077] Further, due to the large number of vehicles passing through the urban traffic node every day, the average daily traffic volume of the traffic volume obtained by a single frame may be distorted, for example, during the peak period of industrial and software park, the traffic volume is relatively large, and even more than half of the whole day traffic volume, while the traffic volume during working hours is relatively small, and there may be only a few vehicles passing through in a short time. Based on the traffic volume variation, the number of vehicles passing through during the day is divided into sections, and based on the time length range and traffic volume data, the monitoring time period-traffic volume matching is performed , that is, the number of vehicles at each time is matched with the corresponding time.

[0078] Subsequently, based on the traffic volume variation in different data segments, the time period vehicle quantity ratio, that is, the traffic volume change rate

[0079]

[0080] In the formula, is the target vehicle quantity at the first time, is the newly added vehicle quantity at the i-th time, is the total amount of traffic volume in the monitoring period, is the inverse value of the traffic volume statistical time (monitoring period, which can be set as needed, for example, 2 hours), and the first time is the last time of the monitoring period. The shorter the traffic volume time, the greater the traffic volume, is the relationship between the traffic volume variation and the time change in the monitoring period. The greater the value, the greater the traffic volume in the time period.

[0081] The preset traffic threshold is set to 0.7 (which can be adjusted specifically), when , the traffic volume in the monitoring period is relatively large, which belongs to the peak period of traffic flow, and can be used as the characteristic period of the daily traffic volume.

[0082] In the following embodiments and implementation processes, in order to save computing resources and improve analysis efficiency, only the traffic management information system in the peak period of traffic flow can be operated and managed.

[0083] Please refer to Figure 3 , in an embodiment, the step S1 specifically includes:

[0084] Step S11, determining the maximum vehicle quantity difference in the vehicle quantity difference of each road image in the target traffic node, and taking the maximum vehicle quantity difference as the peak traffic volume of the target traffic node;

[0085] ​​Step S12, taking the intersection vehicle driving direction corresponding to the peak traffic flow of the target traffic node as the main flow driving direction of the target traffic node.

[0086] For the detection data under a single camera (corresponding to a road image at time i), the vehicle flow information (vehicle number difference) in the camera is obtained. , is the target vehicle number, is the actual vehicle number of the previous adjacent time of the target time.

[0087] Combined with the increase and decrease state of the vehicle under different cameras, the camera with the maximum vehicle increment change is obtained, and the driving direction of the intersection monitored by the camera is the main flow driving direction of the vehicle. It can be further expressed in the following way:

[0088]

[0089] In the formula, is the maximum vehicle number difference in the vehicle number difference of each road image, that is, the peak traffic flow of the traffic node where it is located; is the total number of vehicle driving directions at each intersection in the traffic node; the maximum traffic flow (maximum vehicle number difference) is obtained by function to obtain the driving direction of the maximum traffic flow as the main flow driving direction of the vehicle.

[0090] Step S2, using the vehicle main flow driving direction difference between the target traffic node and its adjacent traffic nodes to determine the traffic flow characteristic peak value change similarity between the target traffic node and its adjacent traffic nodes;

[0091] The nodes in the urban traffic network are not isolated. Due to the route design, there may be an association between any two traffic nodes. For example, in the regional traffic network, there is an interval between the work area node 1 and the residential area node 3. Due to the up and down, the traffic changes of the two nodes are associated, so when the urban regional traffic network information system is operated and managed, the multi-source data of the traffic nodes are collected, the change trend and the correlation of the same type data between different nodes are analyzed, and the daily change curve is constructed based on the single-day data. It can also be identified by data clustering to screen and exclude abnormal data and retain effective information. Then, combined with the daily monitoring data and the historical change curve, the abnormal reasons of the traffic node are analyzed, and the intensive operation and management of the events reflected by the information system are implemented.

[0092] Further, in the urban traffic network, there is a dynamic correlation between adjacent intersections corresponding to traffic nodes. For example, in the urban trunk road, the vehicle flow is usually large, and the vehicles from both sides of the intersection continuously push up the vehicle flow intensity of the trunk road node (such as node a), and finally lead to the concentration of the vehicle flow in a single direction from the three directions of the node to the downstream node (node b). This process directly aggravates the vehicle flow pressure of node b. At the same time, although the adjacent node c of node a does not have a direct adjacent relationship with node b, the vehicle flow of node c can be indirectly transmitted to node b through node a due to the vehicle flow transfer effect of node a. Therefore, in the regional road network, non-adjacent nodes can form indirect correlation through intermediate nodes. Based on the analysis of the coupling relationship of the vehicle flow changes of each node in the characteristic peak state, the dynamic difference characteristics of the vehicle flow data of different road sections can be further quantified.

[0093] Please refer to Figure 4 , the step S2 specifically comprises:

[0094] Step S21, determining the peak dynamic time warping distance between the peak vehicle flow of the target traffic node and the peak vehicle flow of each adjacent traffic node of the target traffic node;

[0095] Step S22, determining the first cosine similarity between the vectors corresponding to the main flow directions of the target traffic node and the adjacent traffic nodes of the target traffic node;

[0096] Step S23, using the peak dynamic time warping distance and the first cosine similarity, to calculate the vehicle flow characteristic peak change similarity between the target traffic node and its adjacent traffic nodes.

[0097] The similarity index of the characteristic peak period vehicle flow variation time sequence (vehicle flow characteristic peak change similarity) between adjacent traffic nodes j, j+1 (j+1 as the target traffic node) is obtained :

[0098]

[0099] In the formula, indicates the vehicle flow characteristic peak change similarity between adjacent traffic nodes j, j+1; is the peak vehicle flow of adjacent traffic node j, is the (Dynamic Time Warping, dynamic time warping) distance between the peak vehicle flows of adjacent traffic nodes j, j+1, indicates the exponential function with natural constant as the base, and the normalization of the DTW distance is realized by to realize the negative correlation of the DTW distance to unify the dimension; The greater the value, the more similar the main flow driving directions of the adjacent nodes j, j+1 are. The greater the value, the more similar the main flow driving directions of the adjacent nodes j, j+1 are.

[0100] The greater the value, the more similar the main flow driving directions of the adjacent nodes j, j+1 are. .

[0101] Step S3, using the vehicle quantity difference and the traffic flow characteristic peak value change similarity, determining the traffic flow pressure coefficient of each upstream node of the target traffic node on the target traffic node;

[0102] During the driving of the vehicle, vehicles will continuously enter and exit the current node, and there may be large data changes between different nodes. Therefore, by analyzing the traffic flow change pressure parameters between nodes at different times, the traffic flow change pressure parameters between nodes can be obtained.

[0103] Specifically, referring to Figure 5 , the step S3 comprises:

[0104] Step S31, using the traffic flow characteristic peak value change similarity to determine the traffic flow attenuation coefficient of the target traffic node compared to its adjacent traffic nodes;

[0105] The step S31 specifically comprises:

[0106] Determining the traffic flow change value between the vehicle quantity of the target traffic node and its adjacent traffic nodes at the target time;

[0107] Using the traffic flow characteristic peak value change similarity and the traffic flow change value, the traffic flow attenuation coefficient of the target traffic node compared to its adjacent traffic nodes is calculated.

[0108] For adjacent nodes j, j+1, assume that node j is an upstream node of node j+1.

[0109] The traffic flow attenuation coefficient of the target traffic node j+1 compared to its adjacent traffic node j is :

[0110]

[0111] In the formula, is the traffic flow attenuation coefficient between adjacent nodes j, j+1, a traffic flow change value in a feature sequence of the adjacent node (including the number of vehicles at each time i), a corresponding change mean value, the greater the change mean value, the more the traffic flow in the adjacent node exits the main line. a traffic flow feature peak value change similarity between adjacent traffic nodes j and j+1, which is used as a similarity coefficient here, the greater the value, the higher the value authenticity. the serial number of the last time of the monitoring period.

[0112] In step S32, the traffic flow pressure coefficient of each upstream node of the target traffic node on the target traffic node is determined using the traffic flow attenuation coefficient and the vehicle number difference.

[0113] The step S32 specifically includes:

[0114] determining a reference traffic flow proportion of the vehicle number difference of the reference intersection in the adjacent traffic node at the target time relative to the vehicle number of the adjacent traffic node;

[0115] determining a second cosine similarity between the respective corresponding vectors of the intersection vehicle travel direction of the reference intersection and the vehicle mainstream travel direction of the target traffic node;

[0116] The traffic flow pressure coefficient of the adjacent traffic node as the upstream node of the target traffic node on the target traffic node is calculated using the traffic flow attenuation coefficient, the reference traffic flow proportion, and the second cosine similarity.

[0117] In this embodiment, the more the number of vehicles entering the upstream node, the more the number of vehicles entering the downstream node from the node, which in turn causes greater traffic flow pressure in the downstream node. Therefore, the proportion of vehicles entering the upstream node through different intersections and the attenuation coefficient of the traffic flow of vehicles entering the downstream node from the upstream node are used to obtain the traffic flow pressure coefficient of different nodes on the downstream node :

[0118]

[0119] In the formula, is the vehicle number difference of intersection k (denoted as the reference intersection) of node j at time i, is a reference traffic flow proportion of the vehicle number difference of intersection k relative to the total vehicle number of node j, is a mean value of the reference traffic flow proportion in the feature peak period (traffic flow peak period), is a traffic flow attenuation coefficient, is the product of the mean value of the reference traffic flow proportion in the feature peak period and the traffic flow attenuation coefficient, indicating the traffic flow pressure of vehicles of intersection k on node j, The cosine similarity between the respective vectors of the intersection vehicle driving direction of the intersection k and the vehicle mainstream driving direction of the node j+1 (hereinafter referred to as the second cosine similarity) is calculated using The sign function is used to obtain the sign value of The value relationship between different nodes is obtained by taking the value, and when the value is positive, the influence of the intersection k on the traffic flow is positively correlated, and vice versa.

[0120] When , the influence of the intersection k on the traffic flow pressure of the downstream node j+1 is 0.

[0121] Based on the above implementation process, the traffic flow pressure coefficients between the nodes in the region are traversed, and the traffic flow pressure coefficients are accumulated to obtain the pressure parameters of the nodes on the road .

[0122] Step S4, determine the driving influence index of the current weather parameter on the road, and determine the bearing pressure coefficient of the target traffic node by using the driving influence index and the traffic flow pressure coefficient;

[0123] Specifically, the step S4 comprises:

[0124] The humidity offset of the air humidity value of the target number of days in the preset period of days compared to the average air humidity value is used to determine the driving influence index of the current weather parameter on the road.

[0125] The bearing pressure coefficient of the target traffic node is calculated by using the driving influence index, the traffic flow pressure coefficient, and the preset period of days.

[0126] In this embodiment, the weather conditions in different regions of the city can also be obtained based on the division of the city region, for example, the city is in a rainy weather, and the air humidity information in different regions is analyzed.

[0127] The congestion of urban road traffic is not constant, for example, in sunny weather, vehicles drive quickly, and more vehicles pass through the node in a short time, and the traffic flow is larger, while in rainy and snowy weather, the road is slippery, and in order to ensure the safety of driving, vehicles need to pass slowly, which leads to that although the traffic flow is large, the number of vehicles passing through the node in a short time is small, thereby causing the change of the traffic flow influence pressure parameters between different nodes.

[0128] Therefore, by comparing the traffic flow pressure coefficients of each node in a single month, and obtaining the current weather parameter, the air humidity value deviating from its average value is used as the driving influence index of the weather environment on the road traffic :

[0129]

[0130] In the formula, is the number of days, is the traffic influence index of the tth day (denoted as the target day, referring to any day), is the air humidity value of the tth day, is the average air humidity value in a preset period of days (for example, 30 days); is the humidity offset of the air humidity value of the tth day in the preset period of days from the average air humidity value, and norm represents a linear normalization function, so that the greater the humidity offset, the greater the environmental disturbance to the vehicle driving condition of the node.

[0131] Further, in combination with the environment, the traffic influence index and the traffic flow pressure coefficient corresponding to the traffic flow pressure coefficient , and further obtain the bearing pressure coefficient of the node :

[0132]

[0133] In the formula, denotes the node number, and in the above embodiments, the adjacent node of the target traffic node, denotes the traffic influence index of the jth node on the tth day, Here, it can also be the bearing pressure coefficient of the adjacent node j, and the bearing pressure coefficient of any traffic node including the target traffic node can be obtained by the same reasoning , denotes the traffic flow pressure coefficient of the jth node on the tth day.

[0134] is the overall bearing pressure of the road node under the natural traffic flow and environmental disturbance in a single day, is the average bearing pressure in a 30-day preset period, which is the bearing pressure coefficient of the node The greater this value, the greater the traffic flow pressure that the node needs to bear, and the higher the index of the road section where the node is located needs to be maintained.

[0135] Step S5, using the bearing pressure coefficient and the corresponding overall bearing pressure reference value, the traffic management information system is operated and maintained.

[0136] Specifically, the step S5 comprises:

[0137] The bearing pressure coefficient is subtracted from the corresponding overall bearing pressure reference value to obtain the actual bearing pressure deviation of the target traffic node;

[0138] In a case that the actual bearing deviation of the node is less than or equal to 0, it is determined that the target traffic node is in a safe bearing range.

[0139] In a case that the actual bearing deviation of the node is greater than 0, the target traffic node is graded and warned by using the actual bearing deviation of the node.

[0140] In the embodiment, based on the bearing pressure coefficients of the nodes, and in combination with the bearing pressure difference relationship between different nodes in the region, the operation and maintenance management of the traffic management information system is realized.

[0141] Specifically, by integrating the multi-source heterogeneous data of different nodes through the above embodiments, the bearing pressure coefficients of the single nodes in the region are calculated, and in combination with the overall bearing pressure reference value of the current node region , the actual bearing deviation of the node is derived . When , it indicates that the node is currently in a safe bearing range, and no road operation intervention is needed; if , the node is implemented with graded intensive operation and maintenance according to the actual bearing deviation of the node.

[0142] For example, based on quantitative values, the operation and maintenance levels (such as three-level warning: yellow warning, orange warning, red warning) are divided, and corresponding resource allocation schemes of different intensities are started; the red warning node can temporarily requisition adjacent low-load road section manpower / equipment, and realizes dynamic balance of cross-regional operation and maintenance resources through the tidal lane technology.

[0143] The present application is based on the surrounding monitoring equipment placed in each road traffic node in the urban traffic management information system, such as monitoring camera, temperature and humidity monitor, etc., to obtain multi-source data information of the traffic node, and based on the obtained multi-source data information, the traffic pressure index that can be borne by different nodes of the urban road is analyzed, and compared with the bearing pressure index (reference value) during the design of the road, and according to the deviation analysis result, a graded warning mechanism is implemented, and then when the actual pressure value of the traffic node exceeds the threshold value, a multi-level response intensive operation and maintenance management process is triggered, so as to improve the accuracy of the urban road traffic bearing evaluation, optimize the operation and maintenance resource allocation efficiency, and make the traffic operation and maintenance strategy meet the actual traffic demand.

[0144] Embodiment two:

[0145] The embodiment of the present application also provides an information system intensive operation and maintenance management device integrating multi-source data. The device can be a computer, a server or a combination of multiple data processing devices.

[0146] As shown in Figure 6 ,Figure 6 is a structural schematic diagram of a hardware operation environment of an integrated multi-source data information system intensive operation and maintenance management device involved in an embodiment of the present application.

[0147] As shown in Figure 6 , the integrated multi-source data information system intensive operation and maintenance management device can 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 the connection and communication between these components. The user interface 1003 can include a display, an input unit such as a control panel, and the optional user interface 1003 can further include a standard wired interface and a wireless interface. The network interface 1004 can optionally include a standard wired interface and a wireless interface (such as a WIFI interface). The memory 1005 can be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 can optionally be a storage device independent of the aforementioned processor 1001. The memory 1005, as a computer storage medium, can include an information system intensive operation and maintenance management program.

[0148] Those skilled in the art can understand that Figure 6 the hardware structure shown in the foregoing embodiments does not constitute a limitation on the device, and can include more or fewer components than those shown, or combine certain components, or arrange different components.

[0149] Continuing to refer to Figure 6 , Figure 6 the memory 1005, as a computer readable storage medium, can include an operation device, a user interface module, a network communication module, and an information system intensive operation and maintenance management program.

[0150] In ​ , the network communication module is mainly used to connect to a server and can communicate data with the server; and the processor 1001 can call the information system intensive operation and maintenance management program stored in the memory 1005 and execute the steps in the above various embodiments.

[0151] Based on the hardware structure of the integrated multi-source data information system intensive operation and maintenance management device, each embodiment of the information system intensive operation and maintenance management method of the present application is realized.

[0152] In addition, the present application also provides a computer readable storage medium. The computer readable storage medium of the present application stores an information system intensive operation and maintenance management program, wherein when the information system intensive operation and maintenance management program is executed by a processor, the steps of the integrated multi-source data information system intensive operation and maintenance management method as described above are realized.

[0153] The method realized when the information system intensive operation and management program is executed can refer to each embodiment of the information system intensive operation and management method of integrating multi-source data of the present application, which will not be repeated here.

[0154] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0155] Each embodiment in the specification is described in a progressive manner, and the same and similar parts between each embodiment can be referred to each other. Each embodiment mainly describes the differences from other embodiments.

[0156] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, device, or computer program product. Therefore, the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0157] The above only describes the preferred embodiments of the present application, and does not limit the protection scope of the present application. Any equivalent structure / method transformation made according to the present application specification and drawings, or direct / indirect application in other related technical fields is included in the protection scope of the present application.

Claims

1. An information system intensive operation and maintenance management method for integrating multi-source data, characterized in that, The method comprises: determining the vehicle quantity difference between the target time and the adjacent time of the road image, determining the vehicle mainstream running direction of the target traffic node by using the vehicle quantity difference of each road image; determining the traffic flow characteristic peak value change similarity between the target traffic node and the adjacent traffic node by using the vehicle mainstream running direction difference between the target traffic node and the adjacent traffic node; determining the traffic flow pressure coefficient of each upstream node of the target traffic node to the target traffic node by using the vehicle quantity difference and the traffic flow characteristic peak value change similarity; determining the driving influence index of the current weather parameter on the road, and determining the bearing pressure coefficient of the target traffic node by using the driving influence index and the traffic flow pressure coefficient; using the bearing pressure coefficient and the corresponding overall bearing reference value to perform operation and maintenance management on the traffic management information system; The determination method of the traffic flow characteristic peak value change similarity between the target traffic node and the adjacent traffic node comprises: determining the peak dynamic time warping distance between the peak traffic flow of the target traffic node and the adjacent traffic node; determining the first cosine similarity between the corresponding vectors of the vehicle mainstream running direction of the target traffic node and the adjacent traffic node; using the peak dynamic time warping distance and the first cosine similarity to calculate the traffic flow characteristic peak value change similarity between the target traffic node and the adjacent traffic node, and the corresponding calculation formula comprises: wherein, denotes the similarity of the peak value change of the traffic volume between adjacent traffic nodes j, j+1; is the peak traffic volume of the adjacent traffic node j, is the distance, denotes an exponential function with a natural constant as the base; is the first cosine similarity between the corresponding vectors of the main flow directions of vehicles of the adjacent traffic nodes j, j+1, and norm denotes a linear normalization function. The determination method of the traffic flow pressure coefficient of each upstream node of the target traffic node to the target traffic node comprises: determining the traffic flow attenuation coefficient of the target traffic node compared with the adjacent traffic node by using the traffic flow characteristic peak value change similarity; determining the traffic flow pressure coefficient of each upstream node of the target traffic node to the target traffic node by using the traffic flow attenuation coefficient and the vehicle quantity difference; The determination method of the traffic flow attenuation coefficient of the target traffic node compared with the adjacent traffic node comprises: determining the traffic flow change value between the vehicle quantity of the target time of the target traffic node and the adjacent traffic node; using the traffic flow characteristic peak value change similarity and the traffic flow change value to calculate the traffic flow attenuation coefficient of the target traffic node compared with the adjacent traffic node, and the corresponding calculation formula comprises: wherein, is the traffic flow decay coefficient between adjacent nodes j, j+1, is the traffic flow change value within the adjacent node feature sequence, is the corresponding change mean value, is the traffic flow feature peak value change similarity between adjacent traffic nodes j, j+1, is the sequence number of the last time of the monitoring period; The determination method of the traffic flow pressure coefficient of each upstream node of the target traffic node to the target traffic node comprises: determining the reference traffic flow proportion of the vehicle quantity difference of the reference intersection in the adjacent traffic node relative to the vehicle quantity of the adjacent traffic node at the target time; determining the second cosine similarity between the corresponding vectors of the intersection vehicle running direction of the reference intersection and the vehicle mainstream running direction of the target traffic node; using the traffic flow attenuation coefficient, the reference traffic flow proportion and the second cosine similarity to calculate the traffic flow pressure coefficient of the adjacent traffic node as the upstream node of the target traffic node to the target traffic node, and the corresponding calculation formula is: ; wherein, represents the traffic flow pressure coefficient of node j+1, is the vehicle quantity difference of node j at the ith moment of intersection k, is the reference traffic flow proportion of the vehicle quantity difference of intersection k in the total vehicle quantity of node j, is the traffic flow decay coefficient, is the second cosine similarity between the respective corresponding vectors of the vehicle running direction of intersection k and the vehicle mainstream running direction of node j+1, is the max function; The determination method of the bearing pressure coefficient of the target traffic node comprises: determining the driving influence index of the current weather parameter on the road by using the humidity offset of the air humidity value of the target day relative to the air humidity average value in the preset period of days; The bearing pressure coefficient of the target traffic node is calculated by using the traffic influence index, the traffic flow pressure coefficient and a preset period of days, and a corresponding calculation formula is as follows: ; wherein, denotes the node number, denotes the traffic influence index of the jth node on the tth day, is the pressure bearing coefficient of the adjacent node j, denotes the traffic flow pressure coefficient of the jth node on the tth day, and the preset period is 30 days.

2. The information system intensive operation and management method of integrating multi-source data according to claim 1, characterized in that, The determining the vehicle quantity difference between the target moment and the adjacent moment in the road image further includes: Obtaining the target vehicle quantity of the target moment and the same vehicle quantity between the target moment and the adjacent moment in the road image; Determining the new vehicle quantity of the target moment by using the target vehicle quantity and the same vehicle quantity, and determining the traffic flow change rate by using the target vehicle quantity and the new vehicle quantity; The time period in which the traffic flow change rate is greater than or equal to the preset traffic threshold is regarded as a traffic peak time period, and the step of determining the vehicle quantity difference between the target moment and the adjacent moment in the road image is performed in the traffic peak time period.

3. The information system intensive operation and management method of integrating multi-source data according to claim 2, characterized in that, The obtaining the target vehicle quantity of the target moment in the road image includes: Obtaining the vehicle quantity difference between the initial vehicle quantity and the parking vehicle quantity identified in the target moment in the road image; The vehicle quantity difference is regarded as the target vehicle quantity of the target moment in the road image.

4. The information system integrated operation and maintenance management method of claim 1, wherein, The determining the main flow driving direction of the vehicle in the target traffic node by using the vehicle quantity difference of each road image includes: Determining the maximum vehicle quantity difference in the vehicle quantity difference of each road image in the target traffic node, and regarding the maximum vehicle quantity difference as the peak traffic flow of the target traffic node; The driving direction of the vehicle at the intersection corresponding to the peak traffic flow of the target traffic node is regarded as the main flow driving direction of the vehicle in the target traffic node.

5. The information system integration operation and management method of claim 1, wherein, The using the bearing pressure coefficient and the corresponding overall bearing reference value to perform operation and maintenance management on the traffic management information system includes: Obtaining the node actual bearing deviation of the target traffic node by subtracting the corresponding overall bearing reference value from the bearing pressure coefficient; In the case that the node actual bearing deviation is less than or equal to 0, it is determined that the target traffic node is in a safe bearing range; In the case that the node actual bearing deviation is greater than 0, the target traffic node is graded and warned by using the node actual bearing deviation.

Images