A multi-source information fusion system and method for intelligent dispatch of road rescue

Abstract

The application provides a multi-source information fusion system and method for road rescue intelligent scheduling, which determines the optimal rescue path corresponding to each rescue service point; for the optimal rescue path corresponding to any rescue service point, the rescue return path corresponding to the optimal rescue path is obtained, the path traffic influence 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, the traffic influence prediction is performed according to the rescue service type and the path traffic influence characteristics, and the secondary accident rate of the rescue return path is determined; the rescue service intelligent scheduling is performed on the to-be-rescued vehicle according to the secondary accident rate, the secondary accident rate prediction can be performed according to the traffic influence of the rescue return path, and the intelligent scheduling of different rescue service points is performed, so that the secondary accident risk in the rescue process is reduced.

Description

Technical Field

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

[0002] With the continuous expansion of road networks and the sustained increase in traffic flow, the frequency of road traffic accidents is on the rise. Timely rescue in traffic accidents is not only related to the restoration of road capacity but also directly affects public travel safety. Therefore, in the emergency response process, how to efficiently and rationally allocate rescue service resources to deal with sudden traffic accidents has become an important issue for improving the level of road emergency management and ensuring public safety.

[0003] During road traffic accident rescue, large tow trucks and other on-site cleanup equipment typically need to travel from different rescue service points to the accident scene to provide remote support to vehicles awaiting rescue. In existing technologies, dispatching schemes use the shortest travel time of support vehicles as the optimization objective, selecting and dispatching multiple rescue service points. However, this approach only focuses on the time efficiency of the outbound route, ignoring the overall traffic factors during peak accident periods and the potential traffic impact on the return journey of rescue vehicles. This makes it easier for large rescue vehicles to enter congested road sections when returning from rescue missions, posing a risk of secondary accidents and making it difficult to guarantee the safety and efficiency of the overall rescue process. Summary of the Invention

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

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

[0006] Specifically, the method includes:

[0007] Obtain the location of the vehicle awaiting rescue and determine the optimal rescue route for each rescue service point;

[0008] For any rescue service point, obtain the optimal rescue route corresponding to the optimal rescue route. Based on the rescue vehicle information of the rescue service point and the route driving information of the rescue return route, determine the route traffic impact characteristics corresponding to each route segment in the rescue return route.

[0009] Obtain the rescue service type, and predict the traffic impact 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;

[0010] Based on the secondary accident rate corresponding to each rescue return path, intelligent dispatch of rescue services is performed on the vehicles awaiting rescue.

[0011] In conjunction with the first aspect, some implementations of the first aspect, after obtaining the location of the vehicle to be rescued, also include:

[0012] Obtain a preset search radius, perform a radius search based on the rescue location information of the location to be rescued and the search radius, and determine a list of rescue service points within the search range;

[0013] Based on the location information provided in the list of rescue service points, multiple rescue service points were identified.

[0014] In conjunction with the first aspect, in some implementations of the first aspect, determining the optimal rescue path corresponding to each rescue service point specifically includes: acquiring multi-source road rescue information, performing optimal path analysis on the location to be rescued 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.

[0015] In conjunction with the first aspect, in certain implementations of the first aspect, the optimal route analysis of the location to be rescued and multiple rescue service points based on the multi-source road rescue information, to determine the optimal rescue route corresponding to each rescue service point, specifically includes:

[0016] Construct a directed graph of the road network based on the static topology information of the road network in the multi-source road rescue information;

[0017] Based on the road network dynamic traffic information in the multi-source road rescue information, determine the road weights corresponding to each road segment in the directed graph of the road network.

[0018] For any rescue service point, a path search is performed based on the location coordinates of the rescue service point and the location to be rescued, resulting in multiple rescue paths. The optimal path is then selected based on the road weights of the multiple road segments corresponding to each rescue path, thus obtaining the optimal rescue path corresponding to the rescue service point.

[0019] In conjunction with the first aspect, in some implementations of the first aspect, obtaining the rescue return path corresponding to the optimal rescue path for any given rescue service point specifically includes:

[0020] For any optimal rescue route corresponding to a rescue service point, the location to be rescued on the optimal rescue route is taken as the starting point of the route, and the rescue service point on the optimal rescue route is taken as the ending point of the route. Based on the directed graph of the road network, a new route search is performed to obtain multiple initial rescue return routes.

[0021] The optimal path is determined by filtering the paths based on the path weights of each path segment in each initial rescue return path and using it as the rescue return path.

[0022] In conjunction with the first aspect, in certain implementations of the first aspect, determining the path traffic impact characteristics corresponding to each path segment of 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:

[0023] Based on the rescue vehicle information of the rescue service point and the route driving information of the rescue return route, the real-time traffic characteristics, accident risk characteristics and road adaptability characteristics corresponding to each route segment in the rescue return route are determined.

[0024] Based on the real-time traffic characteristics, the accident risk characteristics, and the road adaptability characteristics, a multi-dimensional feature vector is constructed to determine the path traffic impact characteristics corresponding to each path segment.

[0025] In conjunction with the first aspect, in certain implementations of the first aspect, determining the secondary accident rate of the rescue return path by predicting traffic impact based on the rescue service type and the path traffic impact characteristics corresponding to each rescue path segment in the rescue return path specifically includes:

[0026] Obtain the path traffic impact features corresponding to each rescue path segment in the rescue return path;

[0027] For any given path segment, perform cluster analysis on the path traffic impact characteristics to determine the path traffic impact score for that path segment.

[0028] Obtain the road condition weights of each path segment in the rescue return route. Based on the road condition weights of each path segment, perform weighted fusion of the path traffic impact scores corresponding to each path segment in the rescue return route to determine the current accident rate of the rescue return route.

[0029] The rescue service time is determined based on the rescue service type of the vehicle to be rescued. The secondary accident rate corresponding to the rescue return path is determined by time series prediction based on the current accident rate of the rescue return path under different time series and the rescue service time.

[0030] Secondly, this application provides a multi-source information fusion system for intelligent dispatching of road rescue, which includes a multi-source information processing unit, the multi-source information processing unit comprising:

[0031] The rescue information acquisition module is used to obtain the location of the vehicle to be rescued and determine the optimal rescue route for each rescue service point.

[0032] The rescue feature extraction module is used to obtain the rescue return path corresponding to the optimal rescue path for any rescue service point, and determine the path traffic impact features 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.

[0033] The rescue feature extraction module is also used to obtain the rescue service type, perform 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 determine the secondary accident rate of the rescue return path.

[0034] The rescue service dispatch module is used to intelligently dispatch rescue services to the vehicles to be rescued based on the secondary accident rate corresponding to each rescue return path.

[0035] Thirdly, this application provides a computer terminal device, which includes a memory and a processor. The memory stores code, and the processor is configured to acquire the code and execute the above-described multi-source information fusion method for intelligent dispatching of road rescue.

[0036] Fourthly, this application provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to perform the operations described above in the multi-source information fusion method for intelligent dispatching of road rescue.

[0037] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0038] This application provides a multi-source information fusion system and method for intelligent dispatching of roadside assistance. First, the location of the vehicle to be rescued is obtained, and the optimal rescue route corresponding to each rescue service point is determined. For any optimal rescue route corresponding to a rescue service point, the return route corresponding to that optimal rescue route is obtained. Based on the rescue vehicle information of the rescue service point and the route driving information of the return route, the path traffic impact characteristics corresponding to each path segment in the return route are determined. 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 return route to determine the secondary accident rate of the return route. Based on the secondary accident rate corresponding to each return route, intelligent dispatching of rescue services is performed for the vehicle to be rescued.

[0039] Therefore, unlike traditional solutions that only optimize for the shortest outbound travel time of rescue vehicles while ignoring high-risk road sections on the return journey, this application obtains and analyzes the return route corresponding to each rescue service point. This allows the scheduling to consider not only outbound efficiency but also return safety, preventing secondary accidents caused by rescue vehicles entering high-risk road sections after completing their mission. Furthermore, by extracting the traffic impact features of each segment of the return route and combining the different disturbance effects of rescue service types on traffic, the secondary accident rate of the return route is predicted. Risk assessment indicators are generated for each rescue service point, with the secondary accident rate being one of the key optimization objectives of the scheduling algorithm. While ensuring rescue response efficiency, this approach prioritizes safer rescue routes and vehicle deployment plans, reducing the risk of secondary accidents during the rescue process and improving the safety of road rescue.

[0040] In summary, this application can predict the secondary accident rate based on the traffic impact of the rescue return route and intelligently dispatch different rescue service points, thereby reducing the risk of secondary accidents during the rescue process. Attached Figure Description

[0041] Figure 1 This is an exemplary flowchart of a multi-source information fusion method for intelligent dispatching of road rescue, according to some embodiments of this application;

[0042] Figure 2 This is a schematic diagram of the structure of a multi-source information processing unit according to some embodiments of this application;

[0043] Figure 3 This is a schematic diagram of the structure of a computer terminal device that implements a multi-source information fusion method for intelligent dispatching of road rescue, according to some embodiments of this application. Detailed Implementation

[0044] This application obtains the location of the vehicle to be rescued and determines the optimal rescue route corresponding to each rescue service point. For any optimal rescue route corresponding to a rescue service point, it obtains the corresponding return route. Based on the rescue vehicle information of the rescue service point and the route driving information of the return route, it determines the path traffic impact characteristics corresponding to each path segment in the return route. It obtains the rescue service type and performs traffic impact prediction based on the rescue service type and the path traffic impact characteristics corresponding to each rescue path segment in the return route, determining the secondary accident rate of the return route. Based on the secondary accident rate corresponding to each return route, it performs intelligent dispatching of rescue services for the vehicle to be rescued. This allows for secondary accident rate prediction based on the traffic impact of the return route and intelligent dispatching of different rescue service points, reducing the risk of secondary accidents during the rescue process.

[0045] To better understand the above technical solutions, a detailed explanation will be provided below with reference to the accompanying drawings and specific implementation methods. (Reference) Figure 1 The figure is an exemplary flowchart of a multi-source information fusion method for intelligent dispatching of road rescue according to some embodiments of this application. The multi-source information fusion method 100 for intelligent dispatching of road rescue mainly includes the following steps:

[0046] In step S101, the location of the vehicle to be rescued is obtained, and the optimal rescue route corresponding to each rescue service point is determined.

[0047] Preferably, in some embodiments, the location of the vehicle to be rescued is obtained through the vehicle-mounted terminal of the vehicle to be rescued. In some other embodiments, the location of the vehicle to be rescued can also be determined through the mobile phone APP of the user 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 will not elaborate on this further.

[0048] Optionally, in some embodiments, after obtaining the location of the vehicle to be rescued, the method further includes: performing a proximity search based on the rescue location information of the location to be rescued to determine multiple rescue service points.

[0049] Preferably, in some embodiments, determining multiple rescue service points by performing a proximity search based on the rescue location information of the location to be rescued specifically includes:

[0050] Obtain a preset search radius, perform a radius search based on the rescue location information of the location to be rescued and the search radius, and determine a list of rescue service points within the search range;

[0051] Based on the location information provided in the list of rescue service points, multiple rescue service points were identified.

[0052] In specific implementation, during the process of obtaining the preset search radius parameter, the search radius can be dynamically adjusted according to road type (such as classifying roads as highways, urban expressways, and ordinary municipal roads), traffic flow, and weather conditions. Then, during the radius search based on the rescue location information and the search radius, this application can selectively use spatial indexing structures, such as R-trees, quadtrees, or GeoHash grids, to retrieve a list of rescue service points within the search range from the rescue service resource library. The retrieved list of rescue service points is then filtered and sorted according to geographical distance, road conditions, availability of rescue vehicles, and rescue capabilities to obtain multiple rescue service points that meet the rescue needs. In some optional embodiments of this application, if the number of rescue service points within the search range is less than a preset threshold, an extended search based on K-nearest neighbors can be further performed to supplement the candidate rescue service points.

[0053] Preferably, in some embodiments, determining the optimal rescue path corresponding to each rescue service point specifically includes: acquiring multi-source road rescue information, performing optimal path analysis on the location to be rescued 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.

[0054] It should be noted that the multi-source road rescue information described in this application is a multi-dimensional set of road information capable of characterizing the road environment, traffic operation status, and rescue safety risks. This 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, 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, 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 occurring on road segments in different time periods, accident types, and secondary accident rates.

[0055] Optionally, in some embodiments, the optimal route analysis of the location to be rescued and multiple rescue service points based on the multi-source road rescue information, to determine the optimal rescue route corresponding to each rescue service point, specifically includes:

[0056] Construct a directed graph of the road network based on the static topology information of the road network in the multi-source road rescue information;

[0057] Based on the road network dynamic traffic information in the multi-source road rescue information, determine the road weights corresponding to each road segment in the directed graph of the road network.

[0058] For any rescue service point, a path search is performed based on the location coordinates of the rescue service point and the location to be rescued, resulting in multiple rescue paths. The optimal path is then selected based on the road weights of the multiple road segments corresponding to each rescue path, thus obtaining the optimal rescue path corresponding to the rescue service point.

[0059] In specific implementation, a directed graph of the road network is constructed based on the static topology information of the road network in the multi-source road rescue information. The nodes of the directed graph represent road intersections, bifurcation points, and rescue service points, and the edges of the 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 directed graph are determined. The road weights are the weighted fusion results of the real-time travel time, traffic flow congestion level, and road traffic constraint parameters of the road segments in the dynamic traffic information of the road network. In some embodiments, after normalizing the information of each dimension in the dynamic traffic information of the road network according to the preset weight coefficients, the real-time travel time, traffic flow congestion level, and road traffic constraint parameters are weighted and fused to obtain a unified road weight value. The road traffic constraint parameters are Boolean parameters determined according to vehicle type and dynamic road restriction information, which will not be elaborated in this application.

[0060] Specifically, for any rescue service point, a path search is performed in the directed road network graph based on the location 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; the candidate rescue paths are sorted according to the road weights of multiple road segments corresponding to each candidate rescue path, and the path with the smallest comprehensive weight is selected first to obtain the optimal rescue path corresponding to the rescue service point;

[0061] In a further embodiment, if multiple candidate paths have similar overall weights, a secondary screening can be performed based on path length, estimated arrival time, or path safety indicators to ensure the rationality of the optimal rescue path.

[0062] In step S102, for any optimal rescue route corresponding to a rescue service point, the rescue return route corresponding to the optimal rescue route is obtained. Based on the rescue vehicle information of the rescue service point and the route driving information of the rescue return route, the path traffic impact characteristics corresponding to each path segment in the rescue return route are determined.

[0063] Optionally, in some embodiments, for any given rescue service point, obtaining the rescue return path corresponding to that optimal rescue path specifically includes:

[0064] For any optimal rescue route corresponding to a rescue service point, the location to be rescued on the optimal rescue route is taken as the starting point of the route, and the rescue service point on the optimal rescue route is taken as the ending point of the route. Based on the directed graph of the road network, a new route search is performed to obtain multiple initial rescue return routes.

[0065] The optimal path is determined by filtering the paths based on the path weights of each path segment in each initial rescue return path and using it as the rescue return path.

[0066] It should be noted that, unlike existing technologies that determine the impact of traffic on vehicle driving efficiency, the path traffic impact features described in this application are used to characterize the impact of rescue vehicles on road traffic on the rescue return route, such as the risk of increased congestion. Furthermore, this application uses deep learning based on the multi-dimensional vector features in the path traffic impact features to predict and compare the rate of secondary traffic accidents caused by the rescue return process, effectively reducing the risk of secondary traffic accidents caused by road rescue. Preferably, in some embodiments, determining the path traffic impact features corresponding to each path segment in the rescue return route based on the rescue vehicle information of the rescue service point and the path driving information of the rescue return route specifically includes:

[0067] Based on the rescue vehicle information of the rescue service point and the route driving information of the rescue return route, the real-time traffic characteristics, accident risk characteristics and road adaptability characteristics corresponding to each route segment in the rescue return route are determined.

[0068] Based on the real-time traffic characteristics, the accident risk characteristics, and the road adaptability characteristics, a multi-dimensional feature vector is constructed to determine the path traffic impact characteristics corresponding to each path segment.

[0069] In specific implementation, the real-time traffic features include the real-time speed, flow rate, congestion index, and average delay time of the path segment; the accident risk features include the historical accident rate of the path segment, the secondary accident rate after the entry of this type of rescue vehicle into the path segment, and the density of traffic conflict points; the road adaptability features include the rate of change of traffic flow speed corresponding to the entry of this type of rescue vehicle into the path segment in the historical records of the path segment; after normalizing the real-time traffic features, accident risk features, and road adaptability features, vector concatenation is performed to construct the multi-dimensional feature vector corresponding to the path segment, which serves as the path traffic impact feature corresponding to that path segment.

[0070] 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.

[0071] Preferably, in some embodiments, determining the secondary accident rate of the rescue return path by 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 specifically includes:

[0072] Obtain the path traffic impact features corresponding to each rescue path segment in the rescue return path;

[0073] For any given path segment, perform cluster analysis on the path traffic impact characteristics to determine the path traffic impact score for that path segment.

[0074] Obtain the road condition weights of each path segment in the rescue return route. Based on the road condition weights of each path segment, perform weighted fusion of the path traffic impact scores corresponding to each path segment in the rescue return route to determine the current accident rate of the rescue return route.

[0075] The rescue service time is determined based on the rescue service type of the vehicle to be rescued. The secondary accident rate corresponding to the rescue return path is determined by time series prediction based on the current accident rate of the rescue return path under different time series and the rescue service time.

[0076] In some specific embodiments of this application, the path traffic impact feature is a standardized multidimensional feature vector. For any path traffic impact feature corresponding to a path segment, based on the multidimensional feature vector corresponding to the path traffic impact feature, K-means clustering is used for cluster analysis to divide the path segment into a preset risk cluster, obtain the initial path traffic impact score corresponding to the risk cluster, and determine the correction coefficient according to 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, the road condition weight of each path segment in the return path is obtained. The road condition weight is used to characterize the importance of the path segment in the return path and 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 according to the proportion of road length, travel time, and road grade of the path segment. Among them, 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 will not be elaborated in this application.

[0077] In some embodiments, the path traffic impact score and road condition weight are comprehensively calculated through weighted fusion. Preferably, a linear weighting method can be used to fuse the path traffic impact scores of each path segment in the return path to obtain the current accident rate of the rescue return path. In other embodiments, the scores of each path segment can be further fused nonlinearly based on the entropy weight method or machine learning training model to determine the current accident rate of the rescue return path. This application does not limit this. It should be noted that the current accident rate of the rescue return path in this application is a predicted value of the occurrence rate of secondary accidents on the rescue return path. The current accident rate of the rescue return path can provide a decision basis for the intelligent road rescue dispatch system, thereby taking into account both outbound efficiency and return safety during the dispatch process and reducing the risk of secondary traffic accidents caused by rescue vehicles during emergency road rescue.

[0078] Optionally, in some embodiments, a single hidden layer neural network can be used to perform cluster analysis on the traffic impact characteristics of the path to determine the path traffic impact score corresponding to the path segment.

[0079] The following is a specific implementation example of this application using a single hidden layer neural network to perform cluster analysis on the traffic impact features of this path and determine the path traffic impact score corresponding to this path segment:

[0080] In the process of learning and clustering the path traffic impact features using a single hidden layer neural network, the path traffic impact features can be input in the form of data vectors. The hidden layer of the single hidden layer neural network contains multiple activation function nodes for classification training, and the classification result is output through the output layer of the single hidden layer neural network. The path traffic impact score is mapped according to the clustering result corresponding to the path traffic impact features, and the corresponding traffic impact score is used as the risk indicator for the path segment.

[0081] The data vector of the path traffic impact features may include, but is not limited to, vector feature values ​​corresponding to the following dimensions: real-time average vehicle speed, traffic flow per unit time, road congestion delay index, historical accident frequency, road grade, road width, presence of height / weight / traffic restrictions, current weather conditions, whether it is an accident-prone period, and the rate of change in traffic flow speed after this type of rescue vehicle enters the path segment. During training, it is optional to use multiple pre-prepared path segment traffic samples and corresponding manual risk scoring results as the training set, inputting multiple path traffic impact feature samples into the single hidden layer neural network for classification training. The hidden layer of the single hidden layer neural network contains multiple activation function nodes for processing the input. The samples are trained for classification, and the clustering classification results are output through the output layer of a single hidden layer neural network. The classification results are then compared with the corresponding human risk score results. When the correlation between the clustering results and the human score results is lower than a 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 human risk score results reaches a preset standard. The mapping relationship between the clustering results and the human score of the path traffic impact is obtained, and the input path traffic impact features are mapped to the corresponding path traffic impact scores based on the mapping relationship. This quantitatively represents the risk level of the path segment during the rescue return process, providing a reliable basis for further determining the overall current accident rate of the return path.

[0082] 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 determined statistically based on historical rescue records, and the level can be corrected by combining the real-time feedback of the rescue vehicle. The current accident rate corresponding to the rescue return path at multiple time-series sampling points within a past time window is 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.

[0083] In step S104, rescue services are intelligently dispatched for the vehicles to be rescued based on the secondary accident rate corresponding to each rescue return path.

[0084] Preferably, in some embodiments, intelligent dispatching of rescue services for the vehicles to be rescued based on the secondary accident rate corresponding to each rescue return path specifically includes:

[0085] Obtain the optimal rescue route and rescue return route for each rescue service point;

[0086] For any given rescue service point, based on the travel time of the optimal rescue route and the secondary accident rate of the rescue return route, construct the corresponding rescue objective function for that rescue service point.

[0087] Based on the rescue objective function corresponding to each rescue service point, the rescue service point with the smallest rescue objective function value is selected to provide rescue service to the vehicle to be rescued.

[0088] In practical 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:

[0089]

[0090] in, Let be the objective function value corresponding to the i-th rescue service point. Let be the travel time of the optimal rescue route corresponding to the i-th rescue service point. Let be the secondary accident rate of the rescue return path corresponding to the i-th rescue service point. , These are the preset maximum traffic time and maximum secondary accident rate, respectively. , The weights for traffic time and secondary accident rate are set to constants based on historical experience.

[0091] 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 position of the rescue vehicle. In some other embodiments, if a sudden change in traffic conditions or an increase in the risk of the return route is detected during the rescue execution process, the objective function can be recalculated and the scheduling plan can be updated, and the final determined rescue vehicle dispatch instruction can be sent to the on-board terminal or mobile device of the corresponding rescue vehicle.

[0092] It should be noted that this application takes into account the disturbance effect of different types of rescue vehicles on road traffic based on the rescue service type of the vehicle to be rescued. It uses the traffic impact characteristics of the route to predict traffic impact and then determines the secondary accident rate of the rescue return route. By comparing and analyzing the secondary accident rates corresponding to each rescue return route, this invention can intelligently dispatch vehicles to be rescued, selecting the rescue service point and corresponding rescue vehicle with the lowest return secondary accident rate while ensuring rescue response efficiency. Compared with the prior art, this invention can simultaneously consider the traffic conditions of the outbound and return routes during the rescue dispatch process. Through multi-dimensional route traffic impact characteristics and secondary accident rate prediction, it provides a data-driven safety optimization basis for the dispatch plan of rescue vehicles, 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 dispatch.

[0093] Furthermore, in another aspect of this application, in some embodiments, this application provides a multi-source information fusion system for intelligent dispatching of roadside assistance. This system includes a multi-source information processing unit, as referenced... Figure 2 The figure is a schematic diagram of the exemplary hardware and / or software structure of a multi-source information processing unit according to some embodiments of this 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 dispatch module 203, which are described below:

[0094] The rescue information acquisition module 201 is used to acquire the location of the vehicle to be rescued and determine the optimal rescue route corresponding to each rescue service point.

[0095] The rescue feature extraction module 202 is used to obtain the rescue return path corresponding to the optimal rescue path for any rescue service point, and determine the path traffic impact features 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.

[0096] The rescue feature extraction module 202 is also used to obtain the rescue service type, perform 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 determine the secondary accident rate of the rescue return path.

[0097] The rescue service dispatch module 203 is used to intelligently dispatch rescue services to the vehicles to be rescued based on the secondary accident rate corresponding to each rescue return path.

[0098] The foregoing detailed an example of a multi-source information fusion system and method for intelligent dispatching of road rescue provided in the embodiments of this application. It is understood that, in order to achieve the above functions, the corresponding device includes hardware structures and / or software modules for performing each function.

[0099] Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a certain function in the application is executed in a manner that drives hardware or computer software depends on the specific application and design constraints of the technical solution. Therefore, those skilled in the art can use different methods to implement the described function for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0100] In addition, this application also provides a computer terminal device, which includes a memory and a processor. The memory stores code, and the processor is configured to acquire the code and execute the above-described multi-source information fusion method for intelligent dispatching of road rescue.

[0101] In some embodiments, reference Figure 3 The figure is a schematic diagram of the structure of a computer terminal device implementing a multi-source information fusion method for intelligent dispatching of road rescue, according to some embodiments of this application. The multi-source information fusion method for intelligent dispatching of road rescue in the above embodiments can... Figure 3 The computer terminal device 300 shown is used to implement this, and the computer terminal device 300 includes at least one communication bus 301, communication interface 302, processor 303 and memory 304.

[0102] The processor 303 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more devices used to control the execution of a multi-source information fusion method for intelligent dispatching of road rescue as described in this application.

[0103] The communication bus 301 may include a path for transmitting information between the aforementioned components.

[0104] Memory 304 may be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, 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, but not limited thereto. Memory 304 may exist independently and be connected to processor 303 via communication bus 301. Memory 304 may also be integrated with processor 303.

[0105] The memory 304 stores program code for executing the scheme of this application, and its execution is controlled by the processor 303. The processor 303 executes the program code stored in the memory 304. The program code may include one or more software modules. In the above embodiments, the determination of the secondary accident rate can be achieved by the processor 303 and one or more software modules in the program code in the memory 304.

[0106] Communication interface 302 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0107] Optionally, the computer terminal device 300 may also include a power supply 305 for providing power to various devices or circuits in the real-time computer terminal device.

[0108] In a specific implementation, as one 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. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0109] The aforementioned computer terminal device can be a general-purpose computer terminal device or a dedicated computer terminal device. In specific implementations, the computer terminal device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer terminal device.

[0110] In addition, other aspects of this application also provide a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to perform the operations described above in a multi-source information fusion method for intelligent dispatching of road rescue.

[0111] In summary, the multi-source information fusion system and method for intelligent dispatching of roadside assistance disclosed in this application first obtains the location of the vehicle to be rescued and determines the optimal rescue route corresponding to each rescue service point. For any optimal rescue route corresponding to a rescue service point, the return route corresponding to the optimal rescue route is obtained. Based on the rescue vehicle information of the rescue service point and the route driving information of the return route, the path traffic impact characteristics corresponding to each path segment in the return route are determined. 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 return route to determine the secondary accident rate of the return route. Based on the secondary accident rate corresponding to each return route, intelligent dispatching of rescue services is performed on the vehicle to be rescued. This system can predict the secondary accident rate based on the traffic impact of the return route and perform intelligent dispatching of different rescue service points, thereby reducing the risk of secondary accidents during the rescue process.

[0112] The above descriptions are merely embodiments of this application, and common knowledge such as specific technical solutions or characteristics in the solutions are not described in detail here. It should be noted that those skilled in the art can make several modifications and improvements without departing from the technical solutions of this application, and these should also be considered within the scope of protection of this application, without affecting the effectiveness of the implementation of this application or the practicality of the patent.

[0113] The scope of protection claimed in this application shall be determined by the content of its claims. The specific embodiments described in the specification can be used to interpret the content of the claims. Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of the invention. Therefore, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

Claims

1. A multi-source information fusion method for intelligent dispatching of road rescue, characterized in that, include: Obtain the location of the vehicle awaiting rescue and determine the optimal rescue route for each rescue service point; For any rescue service point, obtain the optimal rescue route corresponding to the optimal rescue route. Based on the rescue vehicle information of the rescue service point and the route driving information of the rescue return route, determine the route traffic impact characteristics corresponding to each route segment in the rescue return route. Obtain the rescue service type, and based on the rescue service type and the corresponding path traffic impact characteristics of each rescue path segment in the rescue return path, perform traffic impact prediction to determine the secondary accident rate of the rescue return path, specifically including: Obtain the path traffic impact features corresponding to each rescue path segment in the rescue return path; For any given path segment, perform cluster analysis on the path traffic impact characteristics to determine the path traffic impact score for that path segment. Obtain the road condition weights of each path segment in the rescue return route. Based on the road condition weights of each path segment, perform weighted fusion of the path traffic impact scores corresponding to each path segment in the rescue return route to determine the current accident rate of the rescue return route. The rescue service time is determined based on the rescue service type of the vehicle to be rescued. The secondary accident rate corresponding to the rescue return path is determined by time series prediction based on the current accident rate of the rescue return path under different time series and the rescue service time. Based on the secondary accident rate corresponding to each rescue return path, intelligent dispatch of rescue services is performed on the vehicles awaiting rescue.

2. The method as described in claim 1, characterized in that, Determining the optimal rescue route for each rescue service point specifically includes: acquiring multi-source road rescue information, performing optimal route analysis on the location to be rescued and multiple rescue service points based on the multi-source road rescue information, and determining the optimal rescue route for each rescue service point.

3. The method as described in claim 2, characterized in that, Based on the multi-source road rescue information, an optimal route analysis is performed on the location to be rescued and multiple rescue service points to determine the optimal rescue route for each rescue service point, specifically including: Construct a directed graph of the road network based on the static topology information of the road network in the multi-source road rescue information; Based on the road network dynamic traffic information in the multi-source road rescue information, determine the road weights corresponding to each road segment in the directed graph of the road network. For any rescue service point, a path search is performed based on the location coordinates of the rescue service point and the location to be rescued, resulting in multiple rescue paths. The optimal path is then selected based on the road weights of the multiple road segments corresponding to each rescue path, thus obtaining the optimal rescue path corresponding to the rescue service point.

4. The method as described in claim 1, characterized in that, For any given rescue service point, obtaining the optimal rescue route specifically includes: For any optimal rescue route corresponding to a rescue service point, the location to be rescued on the optimal rescue route is taken as the starting point of the route, and the rescue service point on the optimal rescue route is taken as the ending point of the route. Based on the directed graph of the road network, a new route search is performed to obtain multiple initial rescue return routes. The optimal path is determined by filtering the paths based on the path weights of each path segment in each initial rescue return path and using it as the rescue return path.

5. The method as described in claim 1, characterized in that, Based on the rescue vehicle information of the rescue service point and the route driving information of the rescue return route, the specific route traffic impact characteristics corresponding to each route segment of the rescue return route are determined, including: Based on the rescue vehicle information of the rescue service point and the route driving information of the rescue return route, the real-time traffic characteristics, accident risk characteristics and road adaptability characteristics corresponding to each route segment in the rescue return route are determined. Based on the real-time traffic characteristics, the accident risk characteristics, and the road adaptability characteristics, a multi-dimensional feature vector is constructed to determine the path traffic impact characteristics corresponding to each path segment.

6. The method as described in claim 1, characterized in that, After obtaining the location of the vehicle to be rescued, the following steps are also included: Obtain a preset search radius, perform a radius search based on the rescue location information of the location to be rescued and the search radius, and determine a list of rescue service points within the search range; Based on the location information provided in the list of rescue service points, multiple rescue service points were identified.

7. A multi-source information fusion system for intelligent dispatching of road rescue, comprising a multi-source information processing unit, wherein the multi-source information processing unit is used to execute the multi-source information fusion method for intelligent dispatching of road rescue as described in any one of claims 1 to 6, characterized in that, The multi-source information processing unit includes: The rescue information acquisition module is used to obtain the location of the vehicle to be rescued and determine the optimal rescue route for each rescue service point. The rescue feature extraction module is used to obtain the rescue return path corresponding to the optimal rescue path for any rescue service point, and determine the path traffic impact features 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. The rescue feature extraction module is also used to obtain the rescue service type, perform 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 determine the secondary accident rate of the rescue return path. The rescue service dispatch module is used to intelligently dispatch rescue services to the vehicles to be rescued based on the secondary accident rate corresponding to each rescue return path.

8. 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 acquire the code and execute a multi-source information fusion method for intelligent dispatching of road rescue as described in any one of claims 1 to 6.

9. 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 perform the operations described in any one of claims 1 to 6 of the multi-source information fusion method for intelligent dispatching of road rescue.

Images