Multi-source information fusion system and method for intelligent scheduling of road rescue

Abstract

The invention provides a multi-source information fusion system and method for intelligent scheduling of road rescue. The method comprises the following steps: determining an optimal rescue path corresponding to each rescue service point; for an optimal rescue path corresponding to any rescue service point, acquiring a rescue return path corresponding to the optimal rescue path, and determining path traffic influence characteristics corresponding to each path section in the rescue return path according to rescue vehicle information of the rescue service point and path driving information of the rescue return path; acquiring a rescue service type, performing traffic influence prediction according to the rescue service type and the path traffic influence characteristics, and determining a secondary accident rate of a rescue return path; and according to the secondary accident rate, rescue service intelligent scheduling is carried out on the to-be-rescued vehicle, secondary accident rate prediction can be carried out according to the traffic influence condition of the rescue return path, intelligent scheduling of different rescue service points is carried out, and the secondary accident risk in the rescue process is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of multi-source information processing, and more specifically, to a multi-source information fusion system and method for intelligent road rescue dispatching. Background Art

[0002] With the continuous expansion of road networks and the continued increase in traffic volume, the frequency of road accidents is on the rise. Prompt rescue efforts are not only crucial for restoring road capacity but also directly impact public safety. Therefore, during emergency response, efficiently and rationally dispatching rescue service resources to address sudden traffic accidents has become a crucial issue for improving road emergency management and ensuring public safety.

[0003] During the rescue process of road traffic accidents, large tow trucks and other on-site clearing equipment usually need to travel from different rescue service points to the accident scene to provide remote support to rescue vehicles. In the existing technology, the scheduling plan uses the shortest outbound driving time of the support vehicle as the optimization goal to select and schedule multiple rescue service points. However, this method only focuses on the time efficiency of the outbound route, but ignores the overall traffic factors during the peak period of the accident and the possible traffic impact caused by the return of the rescue vehicle. As a result, large rescue vehicles are more likely to enter congested sections when returning after completing the rescue mission, which poses a risk of causing secondary accidents and makes it difficult to ensure the safety and efficiency of the overall rescue process. Summary of the Invention

[0004] The present application provides a multi-source information fusion system and method for intelligent dispatch of road rescue, which can predict the secondary accident rate based on the traffic impact of the rescue return path, and perform intelligent dispatch of different rescue service points, thereby reducing the risk of secondary accidents during the rescue process.

[0005] In a first aspect, the present application provides a multi-source information fusion method for intelligent dispatching of road rescue. The method can be executed by a network device, or can also be executed by a chip configured in the network device, and the present application does not limit this.

[0006] Specifically, the method includes: Obtain the rescue location of the vehicle to be rescued and determine the optimal rescue path corresponding to each rescue service point; For any rescue service point, the optimal rescue path corresponding to the optimal rescue path is obtained, and based on the rescue vehicle information of the rescue service point and the path travel information of the rescue return path, the path traffic impact characteristics corresponding to each path segment in the rescue return path are determined; Obtaining a rescue service type, performing a traffic impact prediction based on the rescue service type and the traffic impact characteristics corresponding to each rescue path segment in the rescue return path, and determining a secondary accident rate for the rescue return path; According to the secondary accident rates corresponding to the respective rescue return paths, the rescue service is intelligently dispatched for the vehicles to be rescued.

[0007] In conjunction with the first aspect, in certain implementations of the first aspect, after obtaining the rescue location of the vehicle to be rescued, the method further includes: Obtaining a preset search radius, performing a radius search based on the rescue location information of the location to be rescued and the search radius, and determining a list of rescue service points within the search range; Multiple rescue service points are determined based on the location information provided by the rescue service point list.

[0008] In combination with the first aspect, in certain implementations of the first aspect, determining the optimal rescue path corresponding to each rescue service point specifically includes: obtaining multi-source road rescue information, performing optimal path analysis on the rescue location and multiple rescue service points based on the multi-source road rescue information, and determining the optimal rescue path corresponding to each rescue service point.

[0009] In conjunction with the first aspect, in certain implementations of the first aspect, performing an optimal path analysis on the location to be rescued and multiple rescue service points based on the multi-source roadside rescue information, and determining the optimal rescue path corresponding to each rescue service point specifically includes: Constructing a road network directed graph based on the road network static topology information in the multi-source roadside assistance information; Determining, based on the road network dynamic traffic information in the multi-source roadside assistance information, a road weight corresponding to each road segment in the road network directed graph; For any rescue service point, a path search is performed based on the location coordinates corresponding to the rescue service point and the location to be rescued to obtain multiple rescue paths. The optimal path is screened based on the road weights of multiple road segments corresponding to each rescue path to obtain the optimal rescue path corresponding to the rescue service point.

[0010] In conjunction with the first aspect, in certain implementations of the first aspect, for an optimal rescue path corresponding to any rescue service point, obtaining a rescue return path corresponding to the optimal rescue path specifically includes: For the optimal rescue path corresponding to any rescue service point, the rescue location of the optimal rescue path is used as the path starting point, and the rescue service point of the optimal rescue path is used as the path end point. A path search is performed again based on the road network directed graph to obtain multiple initial rescue return paths; Path screening is performed based on the path weights corresponding to the path segments in the initial rescue return paths, and the optimal path is determined as the rescue return path.

[0011] In conjunction with the first aspect, in certain implementations of the first aspect, determining, based on the rescue vehicle information of the rescue service point and the travel information of the rescue return path, the path traffic impact characteristics corresponding to each path segment in the rescue return path specifically include: Determine the real-time traffic characteristics, accident risk characteristics, and road adaptability characteristics corresponding to each path segment in the rescue return path based on the rescue vehicle information of the rescue service point and the path driving information of the rescue return path; A multidimensional feature vector is constructed according to the real-time traffic feature, the accident risk feature, and the road adaptability feature, and the path traffic impact feature corresponding to each path segment is determined.

[0012] In conjunction with the first aspect, in certain implementations of the first aspect, performing traffic impact prediction based on the rescue service type and the path traffic impact characteristics corresponding to each rescue path segment in the rescue return path, and determining the secondary accident rate of the rescue return path specifically includes: Obtaining the path traffic impact characteristics corresponding to each rescue path segment in the rescue return path; For the path traffic impact characteristics corresponding to any path segment, cluster analysis is performed on the path traffic impact characteristics to determine the path traffic impact score corresponding to the path segment; Obtaining the traffic weight of each path segment in the rescue return path, and performing weighted fusion on the path traffic impact scores corresponding to each path segment in the rescue return path based on the traffic weight of each path segment to determine the current accident rate of the rescue return path; The rescue service time is determined based on the rescue service type of the vehicle to be rescued, and a time series prediction is performed based on the current accident rate of the rescue return path at different time series and the rescue service time to determine the secondary accident rate corresponding to the rescue return path.

[0013] In a second aspect, the present application provides a multi-source information fusion system for intelligent road rescue dispatch, which includes a multi-source information processing unit, wherein the multi-source information processing unit includes: The rescue information acquisition module is used to obtain the rescue location of the vehicle to be rescued and determine the optimal rescue path corresponding to each rescue service point; A rescue feature extraction module is used to obtain the rescue return path corresponding to the optimal rescue path corresponding to any rescue service point, and determine the path traffic impact characteristics corresponding to each path segment in the rescue return path based on the rescue vehicle information of the rescue service point and the path travel information of the rescue return path; The rescue feature extraction module is further configured to obtain a rescue service type, perform traffic impact prediction based on the rescue service type and the path traffic impact features corresponding to each rescue path segment in the rescue return path, and determine a secondary accident rate for the rescue return path; The rescue service scheduling module is used to intelligently schedule rescue services for the vehicles to be rescued based on the secondary accident rates corresponding to each rescue return path.

[0014] In a third aspect, the present application provides a computer terminal device, which includes a memory and a processor, wherein the memory stores code, and the processor is configured to obtain the code and execute the above-mentioned multi-source information fusion method for intelligent road rescue scheduling.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, which stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned multi-source information fusion method for intelligent road rescue scheduling.

[0016] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: In a multi-source information fusion system and method for intelligent dispatching of road rescue provided by the present application, the rescue position of the vehicle to be rescued is first obtained and the optimal rescue path corresponding to each rescue service point is determined; for the optimal rescue path corresponding to any rescue service point, the rescue return path corresponding to the optimal rescue path is obtained, and the path traffic impact characteristics corresponding to each path segment in the rescue return path are determined based on the rescue vehicle information of the rescue service point and the path driving information of the rescue return path; the rescue service type is obtained, and the traffic impact is predicted based on the rescue service type and the path traffic impact characteristics corresponding to each rescue path segment in the rescue return path, and the secondary accident rate of the rescue return path is determined; and the rescue service is intelligently dispatched for the vehicle to be rescued based on the secondary accident rates corresponding to each rescue return path.

[0017] It can be seen that this is different from the traditional scheme that only takes the shortest outbound time of the rescue vehicle as the optimization goal and ignores the high-risk sections on the return journey. The present application obtains and analyzes the rescue return path corresponding to each rescue service point, so that the scheduling not only considers the efficiency of the outbound journey, but also fully considers the safety of the return journey. It can avoid the rescue vehicle from entering the high-risk section after completing the mission and causing a secondary accident. In addition, by extracting the path traffic impact characteristics of each path segment of the return path, combining the different disturbance effects of the rescue service type on the traffic, the traffic impact is predicted to predict the secondary accident rate of the return path, and a risk assessment index is generated for each rescue service point. The secondary accident rate is one of the key optimization goals of the scheduling algorithm. While ensuring the efficiency of the rescue response, it gives priority to the rescue path and vehicle dispatch plan with higher safety, reducing the risk of secondary accidents that may be caused during the rescue process and improving the safety of road rescue.

[0018] In summary, this application can predict the secondary accident rate based on the traffic impact of the rescue return path, and perform intelligent scheduling of different rescue service points, thereby reducing the risk of secondary accidents during the rescue process. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is an exemplary flow chart of a multi-source information fusion method for intelligent roadside assistance dispatch according to some embodiments of the present application; Figure 2 is a schematic structural diagram of a multi-source information processing unit according to some embodiments of the present application; Figure 3 It is a structural diagram of a computer terminal device for implementing a multi-source information fusion method for intelligent dispatch of road rescue according to some embodiments of the present application. DETAILED DESCRIPTION

[0020] The present application obtains the rescue position of the vehicle to be rescued and determines the optimal rescue path corresponding to each rescue service point; for the optimal rescue path corresponding to any rescue service point, obtains the rescue return path corresponding to the optimal rescue path, and determines the path traffic impact characteristics corresponding to each path segment in the rescue return path according to the rescue vehicle information of the rescue service point and the path driving information of the rescue return path; obtains the rescue service type, and makes a traffic impact prediction based on the rescue service type and the path traffic impact characteristics corresponding to each rescue path segment in the rescue return path, and determines the secondary accident rate of the rescue return path; according to the secondary accident rates corresponding to each rescue return path, intelligently dispatches the rescue service for the vehicle to be rescued, can predict the secondary accident rate according to the traffic impact of the rescue return path, and conducts intelligent dispatch of different rescue service points, thereby reducing the risk of secondary accidents during the rescue process.

[0021] In order to better understand the above technical solution, the following will be combined with the accompanying drawings and specific implementation methods to describe the above technical solution in detail. Figure 1 This figure is an exemplary flow chart of a multi-source information fusion method for intelligent road rescue dispatch according to some embodiments of the present application. The multi-source information fusion method 100 for intelligent road rescue dispatch mainly includes the following steps: In step S101, the rescue location of the vehicle to be rescued is obtained, and the optimal rescue path corresponding to each rescue service point is determined.

[0022] Preferably, in some embodiments, the rescue position of the vehicle to be rescued is obtained through the on-board terminal of the vehicle to be rescued. In some other embodiments, data positioning can also be performed through the mobile phone APP of the user of the vehicle to be rescued to determine the rescue position of the vehicle to be rescued; in further embodiments, the real-time location information of the vehicle to be rescued can also be obtained through a road monitoring system, a traffic management platform or a third-party location service interface. This application does not go into details about this.

[0023] Optionally, in some embodiments, after obtaining the rescue location of the vehicle to be rescued, the method further includes: performing a neighboring search based on the rescue location information of the rescue location to determine a plurality of rescue service points.

[0024] Preferably, in some embodiments, performing a proximity search based on the rescue location information of the location to be rescued to determine multiple rescue service points specifically includes: Obtaining a preset search radius, performing a radius search based on the rescue location information of the location to be rescued and the search radius, and determining a list of rescue service points within the search range; Multiple rescue service points are determined based on the location information provided by the rescue service point list.

[0025] In specific implementation, in the process of obtaining the preset search radius parameters, the search radius can be dynamically adjusted according to the road type (such as making traffic road classifications such as expressways, urban expressways, and ordinary municipal roads), traffic flow, and weather conditions. Then, in the process of performing a radius search based on the rescue location information and the search radius, the present application can selectively retrieve a list of rescue service points within the search range from the rescue service resource library based on a spatial index structure, such as an R-tree, a quadtree, or a GeoHash grid, and screen and sort the retrieved list of rescue service points according to geographical distance, road conditions, available status of rescue vehicles, and rescue capabilities to obtain multiple rescue service points that meet the rescue needs. In some optional embodiments of the present application, if the number of rescue service points within the search range is less than the preset number threshold, an extended search based on a K-nearest neighbor search can be further performed to fill in the candidate rescue service points.

[0026] Preferably, in some embodiments, determining the optimal rescue path corresponding to each rescue service point specifically includes: obtaining multi-source road rescue information, performing optimal path analysis on the rescue location and multiple rescue service points based on the multi-source road rescue information, and determining the optimal rescue path corresponding to each rescue service point.

[0027] It should be noted that the multi-source road rescue information described in this application is a multi-dimensional road information collection that can characterize the road environment, traffic operation status, and rescue safety risks. It includes: static road network topology information, dynamic road network traffic information, and historical accident information. The static road network topology information includes the spatial structure of road nodes and road segments, road length, road grade, height, width, and weight restrictions, and the distribution of bridges and tunnels, etc., which is used to describe the distribution structure of the road network. The dynamic road network traffic information includes the real-time driving speed, real-time traffic flow, and traffic congestion level of each road segment, which is used to reflect the dynamic operation of the road network at the time of rescue. The historical accident information may include the probability of accidents, accident types, and secondary accident rates of road segments in different time periods.

[0028] Optionally, in some embodiments, performing an optimal path analysis on the location to be rescued and multiple rescue service points based on the multi-source roadside rescue information to determine the optimal rescue path corresponding to each rescue service point specifically includes: Constructing a road network directed graph based on the road network static topology information in the multi-source roadside assistance information; Determining, based on the road network dynamic traffic information in the multi-source roadside assistance information, a road weight corresponding to each road segment in the road network directed graph; For any rescue service point, a path search is performed based on the location coordinates corresponding to the rescue service point and the location to be rescued to obtain multiple rescue paths. The optimal path is screened based on the road weights of multiple road segments corresponding to each rescue path to obtain the optimal rescue path corresponding to the rescue service point.

[0029] In a specific implementation, a road network directed graph is constructed based on the static topology information of the road network in the multi-source road rescue information, the nodes of the road network directed graph represent road intersections, bifurcations and rescue service points, and the edges of the road network directed graph represent road segments; based on the dynamic traffic information of the road network in the multi-source road rescue information, the road weights corresponding to each road segment in the road network directed graph are determined, and the road weights are weighted fusion results of the real-time driving time, traffic congestion degree and road access constraint parameters of the road segments in the dynamic traffic information of the road network. In some embodiments, after normalizing each dimensional information in the dynamic traffic information of the road network according to a preset weight coefficient, the real-time driving time, traffic congestion degree and road access constraint parameters are weighted fused to obtain a unified road weight value, wherein the road access constraint parameters are Boolean parameters determined according to the vehicle type and the dynamic information of the road restriction, which will not be elaborated in this application.

[0030] For any rescue service point, a path search is performed in the directed graph of the road network based on the corresponding coordinates of the rescue service point and the location to be rescued, to obtain multiple candidate rescue paths from the rescue service point to the location to be rescued; a comprehensive calculation is performed based on the road weights of multiple road segments corresponding to each candidate rescue path, and the candidate rescue paths are sorted, with the path with the smallest comprehensive weight being preferentially selected to obtain the optimal rescue path corresponding to the rescue service point; In a further embodiment, if there are multiple candidate paths with similar comprehensive weights, a secondary screening can be performed based on path length, estimated arrival time, or path safety index to ensure the rationality of the optimal rescue path.

[0031] In step S102, for an optimal rescue path corresponding to any rescue service point, a rescue return path corresponding to the optimal rescue path is obtained, and based on the rescue vehicle information of the rescue service point and the path travel information of the rescue return path, the path traffic impact characteristics corresponding to each path segment in the rescue return path are determined; Optionally, in some embodiments, for an optimal rescue path corresponding to any rescue service point, obtaining a rescue return path corresponding to the optimal rescue path specifically includes: For the optimal rescue path corresponding to any rescue service point, the rescue location of the optimal rescue path is used as the path starting point, and the rescue service point of the optimal rescue path is used as the path end point. A new path search is performed based on the road network directed graph to obtain multiple initial rescue return paths; Path screening is performed based on the path weights corresponding to the path segments in the initial rescue return paths, and the optimal path is determined as the rescue return path.

[0032] It should be noted that, unlike the prior art method of determining the impact of traffic on vehicle driving efficiency, the path traffic impact characteristics described in this application are used to characterize the impact of the rescue vehicle on road traffic in the rescue return path, such as the risk of increased congestion, etc., and thus this application performs deep learning based on the multi-dimensional vector features in the path traffic impact characteristics, thereby predicting and comparing the secondary traffic accident rate caused by the rescue return process, effectively reducing the risk of secondary traffic accidents caused by the road rescue process. Preferably, in some embodiments, based on the rescue vehicle information of the rescue service point and the path driving information of the rescue return path, the path traffic impact characteristics corresponding to each path segment in the rescue return path are determined, specifically including: Determine the real-time traffic characteristics, accident risk characteristics, and road adaptability characteristics corresponding to each path segment in the rescue return path based on the rescue vehicle information of the rescue service point and the path driving information of the rescue return path; A multidimensional feature vector is constructed according to the real-time traffic feature, the accident risk feature, and the road adaptability feature, and the path traffic impact feature corresponding to each path segment is determined.

[0033] In specific implementation, the real-time traffic characteristics include the real-time speed, flow, congestion index and average delay time of the path segment; the accident risk characteristics include the historical accident rate of the path segment, the secondary accident rate after this type of rescue vehicle enters the path segment, and the density of traffic conflict points; the road adaptability characteristics include the corresponding traffic speed change rate after this type of rescue vehicle enters the path segment in the historical records of the path segment; the real-time traffic characteristics, accident risk characteristics and road adaptability characteristics are normalized and then vectorized to construct a multi-dimensional feature vector corresponding to the path segment, which is used as the path traffic impact characteristic corresponding to the path segment.

[0034] In step S103, the rescue service type is obtained, and traffic impact prediction is performed based on the rescue service type and the path traffic impact characteristics corresponding to each rescue path segment in the rescue return path to determine the secondary accident rate of the rescue return path.

[0035] Preferably, in some embodiments, traffic impact prediction is performed based on the rescue service type and the path traffic impact characteristics corresponding to each rescue path segment in the rescue return path, and determining the secondary accident rate of the rescue return path specifically includes: Obtaining the path traffic impact characteristics corresponding to each rescue path segment in the rescue return path; For the path traffic impact characteristics corresponding to any path segment, cluster analysis is performed on the path traffic impact characteristics to determine the path traffic impact score corresponding to the path segment; Obtaining the traffic weight of each path segment in the rescue return path, and performing weighted fusion on the path traffic impact scores corresponding to each path segment in the rescue return path based on the traffic weight of each path segment to determine the current accident rate of the rescue return path; The rescue service time is determined based on the rescue service type of the vehicle to be rescued, and a time series prediction is performed based on the current accident rate of the rescue return path at different time series and the rescue service time to determine the secondary accident rate corresponding to the rescue return path.

[0036] In some specific embodiments of the present application, the path traffic impact feature is a standardized multidimensional feature vector. For the path traffic impact feature corresponding to any path segment, a K-means clustering method is used to perform cluster analysis based on the multidimensional feature vector corresponding to the path traffic impact feature, and the path segment is divided into a preset risk cluster. An initial path traffic impact score corresponding to the risk cluster is obtained, and a correction coefficient is determined based on the cluster center position and the vector similarity of the path segment feature vector. The initial path traffic impact score is corrected according to the correction coefficient to determine the path traffic impact score corresponding to the path segment. Then, a road condition weight is obtained for each path segment in the return path. The road condition weight is used to characterize the importance of the path segment in the return path. The road condition weight is used to represent the contribution of the path segment to the overall return path traffic risk. The road condition weight can be calibrated as a constant coefficient based on the road length ratio, travel time ratio, and road grade of the path segment. In particular, longer distances or complex types of roads correspond to higher road condition weights. Interval mapping can also be performed according to a preset mapping table, which is not described in detail in this application.

[0037] In some embodiments, the path traffic impact score and the road condition weight are comprehensively calculated through weighted fusion. Preferably, the path traffic impact score of each path segment in the return path can be fused in a linear weighted manner to obtain the current accident rate of the rescue return path; in other embodiments, the scores of each path segment can be further nonlinearly fused based on the entropy weight method or machine learning training model to determine the current accident rate of the rescue return path, which is not limited in this application; it should be noted that the current accident rate of the rescue return path described in this application is a predicted value of the occurrence rate of secondary accidents on the rescue return path, and the current accident rate of the rescue return path can provide a decision-making basis for the road rescue intelligent scheduling system, thereby taking into account the efficiency of the outbound trip and the safety of the return trip during the scheduling process, and reducing the risk of rescue vehicles causing secondary traffic accidents during road emergency rescue.

[0038] Optionally, in some embodiments, a single hidden layer neural network may be used to perform cluster analysis on the path traffic impact characteristics to determine the path traffic impact score corresponding to the path segment.

[0039] The following is a specific example of using a single hidden layer neural network to perform cluster analysis on the path traffic impact characteristics and determine the path traffic impact score corresponding to the path segment: In the process of learning and clustering the path traffic impact characteristics using a single hidden layer neural network, the path traffic impact characteristics can be input in the form of a data vector, the hidden layer of the single hidden layer neural network includes multiple activation function nodes for classification training, and the classification results are output through the output layer of the single hidden layer neural network. The path traffic impact score mapping is performed according to the clustering results corresponding to the path traffic impact characteristics, and the corresponding traffic impact score is obtained as the risk indicator corresponding to the path segment.

[0040] Among them, the data vector of the path traffic impact feature may include but is not limited to the vector feature values ​​corresponding to the following dimensions: real-time average road speed, traffic flow per unit time, road congestion delay index, historical accident frequency, road grade, road width, whether there are height / weight / traffic restrictions, current weather conditions, whether it is an accident-prone period, and the corresponding traffic speed change rate after the type of rescue vehicle enters the path segment; during the training process, it is optional to use a plurality of pre-prepared path segment traffic samples and the corresponding manual risk scoring results as the training set, and input a plurality of path traffic impact feature samples into the single hidden layer neural network for classification training, and the hidden layer of the single hidden layer neural network contains a plurality of activation function nodes for input The samples are classified and trained, and the clustering classification results are output through the output layer of the single hidden layer neural network; the classification results are then compared with the corresponding manual risk scoring results. When the correlation between the clustering results and the manual risk scoring results is lower than the preset threshold, the activation function parameters in the hidden layer of the single hidden layer neural network are adjusted until the correlation between the clustering results and the manual risk scoring results reaches the preset standard, and the mapping relationship between the clustering results and the manual score of the path traffic impact is obtained. Based on the mapping relationship, the input path traffic impact features are mapped to the corresponding path traffic impact score, thereby quantitatively characterizing the risk level of the path segment during the rescue return process, and providing a reliable basis for further determining the overall current accident rate of the return path.

[0041] Optionally, in some embodiments, the process of determining the rescue service time based on the rescue service type of the vehicle to be rescued can be statistically determined based on historical rescue records, and level correction can be performed in combination with real-time feedback from the rescue vehicle. The current accident rates corresponding to the rescue return path at multiple time sampling points within a past time window are calculated to form a sample sequence, and a moving average autoregressive model of the sample sequence is established. The current accident rate after the rescue service time is predicted by the moving average autoregressive model to obtain the secondary accident rate corresponding to the rescue return path.

[0042] In step S104, intelligent dispatching of rescue services is performed on the vehicles to be rescued according to the secondary accident rates corresponding to the respective rescue return paths.

[0043] Preferably, in some embodiments, performing intelligent dispatching of rescue services for the vehicles to be rescued according to the secondary accident rates corresponding to the respective rescue return paths specifically includes: Obtain the optimal rescue path and rescue return path corresponding to each rescue service point; For any rescue service point, the rescue objective function corresponding to the rescue service point is constructed based on the traffic time of the optimal rescue route and the secondary accident rate of the rescue return route; Based on the rescue objective functions corresponding to the respective rescue service points, a rescue service point with the smallest rescue objective function value is selected to provide rescue service to the vehicle to be rescued.

[0044] In specific implementation, for any rescue service point, based on the travel time of its optimal rescue route and the secondary accident rate of the rescue return route, the following rescue objective function is constructed:

[0045] in, is the rescue objective function value corresponding to the i-th rescue service point, is the travel time of the optimal rescue path corresponding to the i-th rescue service point, is the secondary accident rate of the rescue return path corresponding to the i-th rescue service point, 、 The preset maximum traffic time and maximum secondary accident rate are respectively, 、 is the weight of traffic time and secondary accident rate, which are calibrated as constants based on historical experience.

[0046] Optionally, in some embodiments, the objective function value of each rescue service point is calculated separately, and the rescue service point with the smallest objective function value is selected from all candidate rescue service points as the dispatch location for the rescue vehicle. In some other embodiments, during the rescue execution process, if a sudden change in traffic conditions or an increased risk on the return path is detected, the objective function can be recalculated and the scheduling plan can be updated, and the final rescue vehicle scheduling instruction can be sent to the on-board terminal or mobile device of the corresponding rescue vehicle.

[0047] It should be noted that this application takes into account the disturbance effects of different types of rescue vehicles on road traffic based on the rescue service type of the vehicle to be rescued, and uses the path traffic impact characteristics to predict traffic impact, and then determines the secondary accident rate of the rescue return path. By comparing and analyzing the secondary accident rates corresponding to each rescue return path, the present invention can intelligently dispatch the rescue vehicles to be rescued, and select the rescue service point and corresponding rescue vehicle with the lowest return secondary accident rate under the premise of ensuring the efficiency of the rescue response. Compared with the existing technology, the present invention can consider the traffic conditions of the outbound path and the return path at the same time during the rescue scheduling process, and provide a data-driven safety optimization basis for the dispatch plan of the rescue vehicle through multi-dimensional path traffic impact characteristics and secondary accident rate prediction, thereby effectively reducing the risk of secondary traffic accidents that may be caused during the rescue process and improving the safety and reliability of road rescue scheduling.

[0048] In addition, in another aspect of the present application, in some embodiments, the present application provides a multi-source information fusion system for road rescue intelligent dispatching, the system comprising a multi-source information processing unit, reference Figure 2 This figure is a schematic diagram of exemplary hardware and / or software structure of a multi-source information processing unit according to some embodiments of the present application. The multi-source information processing unit 200 includes: a rescue information acquisition module 201, a rescue feature extraction module 202, and a rescue service scheduling module 203, which are described as follows: The rescue information acquisition module 201 is used to obtain the rescue location of the vehicle to be rescued and determine the optimal rescue path corresponding to each rescue service point; The rescue feature extraction module 202 is configured to obtain, for each rescue service point, an optimal rescue path, a corresponding rescue return path, and determine, based on the rescue vehicle information of the rescue service point and the travel information of the rescue return path, the path traffic impact features corresponding to each path segment of the rescue return path. The rescue feature extraction module 202 is further configured to obtain a rescue service type, perform traffic impact prediction based on the rescue service type and the traffic impact features corresponding to each rescue path segment in the rescue return path, and determine a secondary accident rate for the rescue return path; The rescue service scheduling module 203 is used to perform intelligent rescue service scheduling for the vehicles to be rescued according to the secondary accident rates corresponding to the respective rescue return paths.

[0049] The above describes in detail an example of a multi-source information fusion system and method for intelligent dispatch of road rescue provided in an embodiment of the present application. It can be understood that in order to achieve the above functions, the corresponding device includes a hardware structure and / or software module corresponding to the execution of each function.

[0050] Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function in the application is executed in hardware or in a computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Therefore, professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0051] In addition, the present application also provides a computer terminal device, which includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute the above-mentioned multi-source information fusion method for intelligent road rescue scheduling.

[0052] In some embodiments, reference Figure 3 , which is a schematic diagram of the structure of a computer terminal device for implementing a multi-source information fusion method for intelligent dispatching of road rescue according to some embodiments of the present application. A multi-source information fusion method for intelligent dispatching of road rescue in the above embodiment can be achieved by Figure 3 The computer terminal device 300 shown in FIG. 1 is implemented as shown in FIG. 1 , and the computer terminal device 300 includes at least one communication bus 301 , a communication interface 302 , a processor 303 and a memory 304 .

[0053] The processor 303 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more processors for controlling the execution of a multi-source information fusion method for intelligent dispatching of road rescue in the present application.

[0054] The communication bus 301 may include a path for transmitting information between the aforementioned components.

[0055] Memory 304 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer. Memory 304 may be independent and connected to processor 303 via communication bus 301. Memory 304 may also be integrated with processor 303.

[0056] Memory 304 is used to store program code for executing the solution of the present application, and is controlled by processor 303 for execution. Processor 303 is used to execute the program code stored in memory 304. The program code may include one or more software modules. The determination of the secondary accident rate in the above embodiment can be implemented by processor 303 and one or more software modules in the program code in memory 304.

[0057] The communication interface 302 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0058] Optionally, the computer terminal device 300 may further include a power supply 305 for providing power to various devices or circuits in the real-time computer terminal device.

[0059] In a specific implementation, as an example, a computer terminal device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0060] The aforementioned computer terminal device can be a general-purpose computer terminal device or a dedicated computer terminal device. In a specific implementation, the computer terminal device can be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of this application do not limit the type of computer terminal device.

[0061] In addition, in other aspects of the present application, a computer-readable storage medium is provided, which stores at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above-mentioned multi-source information fusion method for intelligent road rescue scheduling.

[0062] In summary, in a multi-source information fusion system and method for intelligent scheduling of road rescue disclosed in an embodiment of the present application, first, the rescue position of the vehicle to be rescued is obtained and the optimal rescue path corresponding to each rescue service point is determined; for the optimal rescue path corresponding to any rescue service point, the rescue return path corresponding to the optimal rescue path is obtained, and the path traffic impact characteristics corresponding to each path segment in the rescue return path are determined according to the rescue vehicle information of the rescue service point and the path driving information of the rescue return path; the rescue service type is obtained, and the traffic impact is predicted according to the rescue service type and the path traffic impact characteristics corresponding to each rescue path segment in the rescue return path, and the secondary accident rate of the rescue return path is determined; according to the secondary accident rates corresponding to each rescue return path, the rescue service is intelligently scheduled for the vehicle to be rescued, and the secondary accident rate can be predicted according to the traffic impact of the rescue return path, and intelligent scheduling of different rescue service points is performed, thereby reducing the risk of secondary accidents during the rescue process.

[0063] The above description is merely an embodiment of the present application. Common knowledge such as the specific technical solutions or features of the solutions is not described in detail herein. It should be noted that those skilled in the art may make various modifications and improvements without departing from the technical solution of the present application, and these modifications and improvements should also be considered within the scope of protection of the present application. These modifications and improvements will not affect the effectiveness of the implementation of the present application or the practical application of the patent.

[0064] The scope of protection claimed by this application shall be determined by the content of the claims. The specific embodiments and other descriptions in the specification may be used to interpret the content of the claims. Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of the invention. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application is intended to include such modifications and variations.

Claims

1. A multi-source information fusion method for intelligent road rescue dispatch, characterized in that: include: Obtain the rescue location of the vehicle to be rescued and determine the optimal rescue path corresponding to each rescue service point; For any rescue service point, the optimal rescue path corresponding to the optimal rescue path is obtained, and based on the rescue vehicle information of the rescue service point and the path travel information of the rescue return path, the path traffic impact characteristics corresponding to each path segment in the rescue return path are determined; Obtaining a rescue service type, performing a traffic impact prediction based on the rescue service type and the traffic impact characteristics corresponding to each rescue path segment in the rescue return path, and determining a secondary accident rate for the rescue return path; According to the secondary accident rates corresponding to the respective rescue return paths, the rescue service is intelligently dispatched for the vehicles to be rescued.

2. The method according to claim 1, wherein Performing traffic impact prediction based on the rescue service type and the traffic impact characteristics corresponding to each rescue path segment in the rescue return path to determine the secondary accident rate of the rescue return path specifically includes: Obtaining the path traffic impact characteristics corresponding to each rescue path segment in the rescue return path; For the path traffic impact characteristics corresponding to any path segment, cluster analysis is performed on the path traffic impact characteristics to determine the path traffic impact score corresponding to the path segment; Obtaining the traffic weight of each path segment in the rescue return path, and performing weighted fusion on the path traffic impact scores corresponding to each path segment in the rescue return path based on the traffic weight of each path segment to determine the current accident rate of the rescue return path; The rescue service time is determined based on the rescue service type of the vehicle to be rescued, and a time series prediction is performed based on the current accident rate of the rescue return path at different time series and the rescue service time to determine the secondary accident rate corresponding to the rescue return path.

3. The method according to claim 1, wherein Determining the optimal rescue path corresponding to each rescue service point specifically includes: obtaining multi-source road rescue information, performing optimal path analysis on the rescue location and multiple rescue service points based on the multi-source road rescue information, and determining the optimal rescue path corresponding to each rescue service point.

4. The method according to claim 3, wherein Performing an optimal path analysis on the location to be rescued and multiple rescue service points based on the multi-source roadside rescue information, and determining the optimal rescue path corresponding to each rescue service point specifically includes: Constructing a road network directed graph based on the road network static topology information in the multi-source roadside assistance information; Determining, based on the road network dynamic traffic information in the multi-source roadside assistance information, a road weight corresponding to each road segment in the road network directed graph; For any rescue service point, a path search is performed based on the location coordinates corresponding to the rescue service point and the location to be rescued to obtain multiple rescue paths. The optimal path is screened based on the road weights of multiple road segments corresponding to each rescue path to obtain the optimal rescue path corresponding to the rescue service point.

5. The method according to claim 1, wherein For the optimal rescue path corresponding to any rescue service point, obtaining the rescue return path corresponding to the optimal rescue path specifically includes: For the optimal rescue path corresponding to any rescue service point, the rescue location of the optimal rescue path is used as the path starting point, and the rescue service point of the optimal rescue path is used as the path end point. A new path search is performed based on the road network directed graph to obtain multiple initial rescue return paths; Path screening is performed based on the path weights corresponding to the path segments in the initial rescue return paths, and the optimal path is determined as the rescue return path.

6. The method according to claim 1, wherein Determining the path traffic impact characteristics corresponding to each path segment in the rescue return path based on the rescue vehicle information of the rescue service point and the path driving information of the rescue return path specifically includes: Determine the real-time traffic characteristics, accident risk characteristics, and road adaptability characteristics corresponding to each path segment in the rescue return path based on the rescue vehicle information of the rescue service point and the path driving information of the rescue return path; A multidimensional feature vector is constructed according to the real-time traffic feature, the accident risk feature, and the road adaptability feature, and the path traffic impact feature corresponding to each path segment is determined.

7. The method according to claim 1, wherein After obtaining the rescue location of the vehicle to be rescued, the following steps are also included: Obtaining a preset search radius, performing a radius search based on the rescue location information of the location to be rescued and the search radius, and determining a list of rescue service points within the search range; Multiple rescue service points are determined based on the location information provided by the rescue service point list.

8. A multi-source information fusion system for intelligent road rescue dispatch, comprising a multi-source information processing unit, wherein the multi-source information processing unit is configured to execute the multi-source information fusion method for intelligent road rescue dispatch according to any one of claims 1 to 7, characterized in that: The multi-source information processing unit includes: The rescue information acquisition module is used to obtain the rescue location of the vehicle to be rescued and determine the optimal rescue path corresponding to each rescue service point; A rescue feature extraction module is used to obtain the rescue return path corresponding to the optimal rescue path corresponding to any rescue service point, and determine the path traffic impact characteristics corresponding to each path segment in the rescue return path based on the rescue vehicle information of the rescue service point and the path travel information of the rescue return path; The rescue feature extraction module is further configured to obtain a rescue service type, perform traffic impact prediction based on the rescue service type and the path traffic impact features corresponding to each rescue path segment in the rescue return path, and determine a secondary accident rate for the rescue return path; The rescue service scheduling module is used to intelligently schedule rescue services for the vehicles to be rescued based on the secondary accident rates corresponding to each rescue return path.

9. A computer terminal device, characterized in that: The computer terminal device includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute a multi-source information fusion method for road rescue intelligent dispatching as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing at least one computer program, characterized in that: The computer program is loaded and executed by a processor to implement the operations performed by the multi-source information fusion method for road rescue intelligent dispatching as described in any one of claims 1 to 7.

Images