Rescue scheduling method and device, electronic equipment, storage medium and product

Abstract

The invention provides a rescue scheduling method and device, electronic equipment, a storage medium and a product, and the method comprises the steps: building a multi-target optimization model based on a target function for minimizing travel time and resource cost, and constraint conditions of the target function; solving the multi-objective optimization model by adopting an evolutionary algorithm, determining an optimal rescue point corresponding to each accident point, and determining an optimal planning path with the shortest travel time from the optimal rescue point to the accident point; and based on the optimal rescue point and the optimal planning path corresponding to each accident point, determining a rescue scheduling strategy and carrying out rescue. According to the method, the optimal rescue point can be quickly and scientifically selected under the conditions of limited rescue resources and simultaneous occurrence of a plurality of accidents, and the optimal path can be planned while the optimal rescue point is selected, so that the overall rescue efficiency and the rescue effect are improved, and efficient and scientific rescue scheduling is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency rescue, and particularly to a rescue scheduling method, device, electronic device, storage medium and product. Background Art

[0002] An automobile emergency rescue system can automatically or manually send key information such as the accident location and time to a rescue center when a traffic accident occurs, greatly improving the accident response speed and rescue efficiency, and playing a crucial role in reducing accident losses and saving lives.

[0003] However, the algorithms for the two key links of rescue point location selection and optimal travel path selection of rescue vehicles in the current system are disjointed. When selecting a rescue point, the consideration of optimal path selection is not fully combined, resulting in the possible selection of a rescue point that seems close but actually has a complex and congested path; similarly, the optimal path selection algorithm does not base on accurate rescue point selection information, making the path planning unable to adapt to the actual situation of the rescue point, ultimately affecting the rescue efficiency and effect, and unable to quickly and scientifically deliver rescue resources to the accident scene, thus affecting the overall rescue effect.

[0004] Therefore, how to quickly and scientifically select the optimal rescue point and the optimal rescue path after an accident, so as to achieve efficient and scientific rescue scheduling is an urgent problem to be solved at present. Summary of the Invention

[0005] The present invention provides a rescue scheduling method, device, electronic device, storage medium and product, which are used to solve the defect in the prior art that it is difficult to efficiently schedule the rescue resources of each rescue point when multiple accidents occur under the condition of limited rescue resources, affecting the overall rescue effect, and to realize the selection of the optimal rescue point quickly and scientifically while planning the optimal path, so as to achieve efficient rescue scheduling.

[0006] The present invention provides a rescue scheduling method, and the method includes: Construct a multi-objective optimization model based on the objective function of minimizing travel time and resource cost, and the constraint conditions of the objective function; wherein, the travel time refers to the driving time required for a rescue vehicle to drive from a rescue point to an accident point according to the planned path. Solve the multi-objective optimization model by using an evolutionary algorithm to determine the optimal rescue point corresponding to each accident point, and determine the optimal planned path with the shortest travel time from the optimal rescue point to the accident point. Based on the optimal rescue point corresponding to each accident point and the optimal planned path, determine a rescue scheduling strategy and conduct a rescue.

[0007] According to a rescue scheduling method provided by the present invention, after solving the multi-objective optimization model by using an evolutionary algorithm and determining the optimal rescue points corresponding to each accident point, the method further includes: Obtain historical rescue information and real-time traffic condition information read from the traffic system; the historical rescue data includes at least one of historical scheduling information, historical environment information, and historical traffic condition information; Analyze the historical rescue information and extract key feature data affecting rescue efficiency; Input the key feature data into a time series prediction model to obtain the first future rescue demand and the prediction result of traffic condition changes; Based on the first future rescue demand and the prediction result of traffic condition changes, dynamically adjust the optimal rescue points corresponding to each accident point.

[0008] According to a rescue scheduling method provided by the present invention, after determining the optimal planning path with the shortest travel time from the optimal rescue point to the accident point, the method further includes: Obtain the resource status information of each rescue point, the rescue demand information of each accident point, and the real-time traffic condition information for analysis, and determine the rescue tasks of each rescue point; Based on the changes in the resource status information, the changes in the rescue demand information, and the changes in the real-time traffic condition information, perform AI-assisted decision-making analysis, and dynamically adjust the rescue tasks of each rescue point to adjust the optimal planning path.

[0009] According to a rescue scheduling method provided by the present invention, the step of using an evolutionary algorithm to solve the multi-objective optimization model and determine the optimal rescue points corresponding to each accident point includes: Use an evolutionary algorithm to solve the multi-objective optimization model and determine multiple candidate rescue points corresponding to each accident point; For each accident point, calculate the comprehensive cost of each candidate rescue point based on the travel time and resource cost of each candidate rescue point corresponding to the accident point; Based on the comprehensive costs of the candidate rescue points, determine the optimal rescue point corresponding to the accident point.

[0010] According to a rescue scheduling method provided by the present invention, the construction of the multi-objective optimization model based on the objective function of minimizing travel time and resource cost and the constraint conditions of the objective function includes: Based on the accident point set, the rescue point set, binary decision variables, the travel time from the rescue point to the accident point and the corresponding weight parameters, and the resource cost and the corresponding weight parameters, construct an objective function for minimizing travel time and resource cost; Determine the constraint conditions of the objective function; the constraint conditions include the resource demand constraint conditions at the accident point, the availability constraint conditions of the resources at the rescue point, and the binary decision variable constraint conditions; Based on the objective function and the constraint conditions of the objective function, construct a multi-objective optimization model.

[0011] According to a rescue scheduling method provided by the present invention, the travel time from the rescue point to the accident point is determined by the following method: Determine multiple influencing factors affecting the driving time of the rescue vehicle and the weight values of each influencing factor; Perform dimensionless processing on the time data corresponding to each influencing factor to obtain the dimensionless time results corresponding to each influencing factor; Based on the dimensionless time results corresponding to each influencing factor and the weight values of each influencing factor, calculate the travel time of the rescue vehicle from the rescue point to the accident point.

[0012] According to a rescue scheduling method provided by the present invention, the resource cost is the cost of sending rescue vehicles from the rescue point; the resource cost is determined by the following method: In the case where the number of rescue vehicles required at the accident point is less than or equal to the number of rescue vehicles that can be provided by the rescue point, based on the number of rescue vehicles arriving at each accident point from each rescue point and the average unit cost of the rescue point arriving at the accident point, determine the total cost of the rescue vehicles.

[0013] According to a rescue scheduling method provided by the present invention, the resources at the rescue point are reserved by the following method: Based on the analysis of real-time traffic condition information and weather information, obtain the predicted result of the future accident occurrence probability; Based on the predicted result of the future accident occurrence probability and historical rescue information, determine the reserved resources at the rescue point; Based on the real-time resource usage situation at the rescue point and the latest predicted result of the future accident occurrence probability, dynamically adjust the reserved resources at the rescue point.

[0014] According to a rescue scheduling method provided by the present invention, an emergency call system is deployed on the rescue vehicle; during the process of the rescue vehicle driving to the accident point, the method further includes: Obtain the key information sent by the rescue vehicle through the emergency call system in real time; the key information includes vehicle information and accident information; the vehicle information includes at least one of vehicle status information, vehicle driving environment information, and vehicle position information, and the emergency call information includes at least one of accident vehicle position information, accident severity information, and the number of people in the accident vehicle; Send the key information to a third-party platform for display.

[0015] The present invention also provides a rescue scheduling device, including: A construction module, configured to construct a multi-objective optimization model based on an objective function of minimizing travel time and resource cost, and constraint conditions of the objective function; wherein, the travel time refers to the driving time required for a rescue vehicle to travel from a rescue point to an accident point according to a planned path; A solution module, configured to solve the multi-objective optimization model by using an evolutionary algorithm, determine an optimal rescue point corresponding to each accident point, and determine an optimal planned path with the shortest travel time from the optimal rescue point to the accident point; A rescue scheduling module, configured to determine a rescue scheduling plan and conduct a rescue based on the optimal rescue points corresponding to the respective accident points and the optimal planned path.

[0016] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the rescue scheduling method as described in any one of the above is implemented.

[0017] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the rescue scheduling method as described in any one of the above is implemented.

[0018] The present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the rescue scheduling method as described in any one of the above is implemented.

[0019] The rescue scheduling method, device, electronic device, storage medium, and product provided by the present invention, by constructing a multi-objective optimization model based on an objective function and constraint conditions of minimizing travel time and resource cost, realizes unified modeling of the factors required for rescue point selection and path optimization; by using an evolutionary algorithm to solve the multi-objective optimization model, determines the rescue points corresponding to each accident point, and determines an optimal planned path with the shortest travel time from the optimal rescue point to the accident point, so that not only can the optimal rescue points be quickly and scientifically selected in the case of limited rescue resources and multiple accidents occurring simultaneously, but also the optimal path can be planned while selecting the optimal rescue points, improving the overall rescue efficiency and rescue effect, and realizing efficient and scientific rescue scheduling. Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 is one of the flow diagrams of the rescue scheduling method provided by the embodiments of the present invention.

[0022] Figure 2 is the flow diagram of AI-assisted decision-making and big data analysis provided by the embodiments of the present invention.

[0023] Figure 3 is the flow diagram of the judgment for dynamically adjusting the rescue route provided by the embodiments of the present invention.

[0024] Figure 4 is the flow chart of the real-time route optimization and dynamic scheduling strategy of the rescue vehicle provided by the embodiments of the present invention.

[0025] Figure 5 is the schematic diagram of the road network topology with time weights provided by the embodiments of the present invention.

[0026] Figure 6 is the second flow diagram of the rescue scheduling method provided by the embodiments of the present invention.

[0027] Figure 7 is the structural diagram of the rescue scheduling device provided by the embodiments of the present invention.

[0028] Figure 8 is the structural diagram of the electronic device provided by the embodiments of the present invention. Detailed implementation manners

[0029] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0030] In the description of the embodiments of the present invention, the term "comprising", "including" or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or further includes elements inherent to such process, method, article or device. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0031] Figure 1 is one of the flow diagrams of the rescue scheduling method provided by the embodiments of the present invention. Refer to Figure 1, an embodiment of the present invention provides a rescue scheduling method, and the method may specifically include the following steps: Step 101, construct a multi-objective optimization model based on the objective function of minimizing travel time and resource cost, and the constraint conditions of the objective function; wherein, the travel time refers to the driving time required for the rescue vehicle to travel from the rescue point to the accident point according to the planned path.

[0032] It should be noted that the execution subject of the rescue scheduling method provided by the embodiment of the present invention may be an electronic device, a component in the electronic device, an integrated circuit or a chip. The electronic device may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a handheld computer, a wearable device, an Ultra-mobile Personal Computer (UMPC), a netbook or a Personal Digital Assistant (PDA), etc., and the non-mobile electronic device may be a server, a Network Attached Storage (NAS), a Personal Computer (PC), a Television (TV), a teller machine or a self-service machine, etc. The embodiment of the present invention does not make specific limitations thereto. Hereinafter, the embodiment of the present invention will be described with an edge device as the execution subject.

[0033] The travel time may refer to the driving time required for the rescue vehicle to travel from the rescue point to the accident point according to the planned path. The resource cost may be defined based on the number of rescue vehicles required at the accident point, the number of rescue vehicles that can be provided at the rescue point, and the average unit cost. The constraint conditions of the objective function may include resource demand satisfaction constraints, resource availability constraints, and binary decision variable constraints, etc.

[0034] In the embodiment of the present invention, a multi-objective optimization model may be constructed based on the objective function of minimizing travel time and resource cost and the constraint conditions of the objective function, and an evolutionary algorithm may be used to solve the multi-objective optimization model to determine the optimal rescue point corresponding to each accident point, so as to determine a rescue scheduling strategy for rescue, so that each rescue point can make a reasonable division of labor according to its own advantages and comprehensive conditions.

[0035] Step 102, use an evolutionary algorithm to solve the multi-objective optimization model, determine the optimal rescue point corresponding to each accident point, and determine the optimal planned path with the shortest travel time from the optimal rescue point to the accident point.

[0036] In some embodiments, an evolutionary algorithm can be used to solve the multi-objective optimization model, determine at least one optimal rescue point corresponding to each accident point, and then use a path algorithm to determine the optimal planning path with the shortest travel time from the optimal rescue point to the accident point. Thus, the goal of planning the optimal path while selecting the optimal rescue point is achieved, enabling each rescue point to make a reasonable division of labor based on its own advantages and comprehensive conditions.

[0037] Step 103: Based on the optimal rescue points corresponding to the respective accident points and the optimal planning path, determine a rescue scheduling strategy and conduct the rescue.

[0038] In the embodiments of the present invention, when dealing with the optimization problem of rescue points and accident points, by using an evolutionary algorithm to solve the multi-objective optimization model with the objective function of minimizing travel time and resource cost, and then using a path algorithm to determine the optimal planning path from the optimal rescue point to the accident point, it is possible to plan the optimal path while selecting the optimal rescue point, thereby generating an optimal rescue scheduling strategy for the rescue and achieving efficient rescue scheduling. Among them, the rescue scheduling strategy may include at least one optimal rescue point corresponding to each accident point, and the optimal planning path (i.e., the driving route) for the rescue vehicle to travel from the optimal rescue point where the rescue vehicle is located to the accident point.

[0039] In some embodiments, the factors required for rescue point selection and path optimization may at least include factors such as travel time and resource cost.

[0040] Aiming at the problem that the rescue point location selection and path optimization algorithm are mutually disjoint, the embodiments of the present invention construct an integrated intelligent rescue decision-making system, unify the modeling of the factors required for rescue point selection and path optimization (travel time and resource cost), use an evolutionary algorithm to solve the constructed multi-objective optimization model, and then use a path algorithm to determine the optimal planning path with the shortest travel time from the optimal rescue point to the accident point, so as to achieve the goal of planning the optimal path while selecting the optimal rescue point.

[0041] The embodiments of the present invention construct a multi-objective optimization model based on the objective function and constraint conditions of minimizing travel time and resource cost, realizing the unified modeling of the factors required for rescue point selection and path optimization; by using an evolutionary algorithm to solve the multi-objective optimization model, determining the rescue points corresponding to each accident point, and determining the optimal planning path with the shortest travel time from the optimal rescue point to the accident point, it is possible not only to quickly and scientifically select the optimal rescue point in the case of limited rescue resources and multiple accidents occurring simultaneously, but also to plan the optimal path while selecting the optimal rescue point, improving the overall rescue efficiency and rescue effect, and achieving efficient and scientific rescue scheduling.

[0042] In an alternative embodiment, after solving the multi-objective optimization model using an evolutionary algorithm to determine the optimal rescue points corresponding to each accident point, the method may further include: Step 201, obtain historical rescue information and real-time traffic condition information read from the traffic system; the historical rescue data includes at least one of historical scheduling information, historical environment information, and historical traffic condition information; Step 202, analyze the historical rescue information to extract key feature data affecting rescue efficiency; Step 203, input the key feature data into a time series prediction model to obtain a first future rescue demand and a prediction result of traffic condition changes; Step 204, dynamically adjust the optimal rescue points corresponding to each accident point based on the first future rescue demand and the prediction result of traffic condition changes.

[0043] In the embodiments of the present invention, after a traffic accident occurs, rescue vehicles need to quickly reach the scene. AI technology can be used to deeply analyze historical rescue information and real-time traffic condition information read from the traffic system, and dynamically adjust the optimal rescue points corresponding to each accident point based on the analysis results, thereby significantly improving rescue efficiency.

[0044] Figure 2 It is a schematic flowchart of AI-assisted decision-making and big data analysis provided by the embodiments of the present invention. Refer to Figure 2 , in some embodiments, the historical rescue information may include historical scheduling information such as accident locations and rescue response times, historical environment information such as weather conditions (such as temperature, rainfall), historical traffic conditions such as traffic flow (such as vehicle flow during peak hours), and road conditions (such as construction, road closure conditions). Historical rescue information can be obtained from multiple sources such as rescue agencies, traffic management departments, and meteorological services, and the collected historical rescue information can be stored in a unified database in a standardized format to ensure the convenience of subsequent analysis.

[0045] An emergency call system can be used to monitor traffic flow and environmental information in real time and transmit the data to a third-party platform. Real-time data can be preliminarily processed on edge devices to ensure quick response, reduce data transmission latency at the same time, and establish a real-time data update mechanism to ensure that the system can continuously obtain the latest information.

[0046] In some embodiments, after data collection and integration, data analysis and pattern recognition can be performed. Machine learning and deep learning algorithms can be used to analyze historical rescue information to identify key feature factors affecting rescue efficiency, thereby achieving in-depth mining. For example, classification algorithms can be used to identify changes in rescue response times under specific weather conditions; for another example, key feature data such as typical times of accidents, common weather patterns, and their impacts on rescue times can be extracted from the data.

[0047] In some embodiments, a time series prediction model can be established. By analyzing historical rescue information to extract key feature data affecting rescue efficiency, future rescue needs and changes in traffic conditions can be predicted, realizing the prediction of change trends. By simulating rescue responses under different traffic conditions and weather conditions, their potential impacts on rescue efficiency can be analyzed, providing a basis for dispatching decisions.

[0048] In an embodiment of the present invention, after obtaining the prediction results of the first future rescue needs and changes in traffic conditions, the optimal rescue points corresponding to each accident point can be dynamically adjusted to achieve intelligent decision-making and optimization.

[0049] In some embodiments, real-time traffic flow and environmental data can be combined, and the preferred rescue points can be automatically adjusted through AI algorithms, thereby dynamically adjusting the rescue points. For example, the priority rescue points can be adjusted during peak hours to ensure the shortest arrival time. The optimal driving route can be calculated using a dynamic multi-objective algorithm based on an evolutionary algorithm, considering congestion and traffic signal changes in real-time data to generate the optimal driving path.

[0050] In some embodiments, an AI-assisted decision-making system can be established to calculate and provide the optimal rescue plan in real-time, including the shortest driving time and the lowest resource cost. Key indicators of the rescue plan, such as the estimated arrival time and resource utilization, are displayed in real-time on the decision-making interface to help decision-makers make quick responses.

[0051] In some embodiments, after each rescue operation, the rescue effect can be evaluated, such as the difference between the actual arrival time and the predicted time, and the actual usage of rescue resources; the evaluation results are fed back to the AI system and integrated into the historical data for subsequent analysis and model optimization. At the same time, the AI model can be retrained regularly to improve the accuracy of the model using newly collected data; through continuous learning, the AI system continuously optimizes its decision-making ability to adapt to different traffic and environmental conditions to improve rescue efficiency.

[0052] In an alternative embodiment, after determining the optimal planned path with the shortest travel time from the optimal rescue point to the accident point, the method may further include: Step 301: Obtain the resource status information of each rescue point, the rescue demand information of each accident point, and the real-time traffic condition information for analysis, and determine the rescue tasks of each rescue point; Step 302: Conduct AI-assisted decision-making analysis based on the changes in the resource status information, the changes in the rescue demand information, and the changes in the real-time traffic condition information, and dynamically adjust the rescue tasks of each rescue point to adjust the optimal planned path.

[0053] In the embodiment of the present invention, after a traffic accident occurs, not only does the rescue vehicle need to quickly reach the scene, but the status of the accident vehicle and its integration with the intelligent transportation system are also equally important. Through the linkage with traffic lights, road monitoring systems, and accident vehicles, the present invention can achieve the coordinated scheduling and path optimization of rescue vehicles and accident vehicles.

[0054] In some embodiments, it is possible to connect to the command center or information system of each rescue point to obtain the resource status information of each rescue point in real time. These resource status information includes, but is not limited to, whether the vehicle is available (such as whether the vehicle is on standby, under repair, etc.), the personnel allocation situation (such as the number of professional rescue personnel, the distribution of various skilled personnel, etc.), and at the same time obtain its location information and action planning information (such as the current rescue task arrangement, the estimated departure time, the estimated return time, etc.).

[0055] In some embodiments, it is possible to integrate data from traffic lights, road monitoring, and accident vehicles to generate a comprehensive traffic condition information database, including traffic flow, vehicle speed, road conditions, accident point characteristics, etc., so as to provide complete data support for subsequent decision-making.

[0056] In the embodiment of the present invention, data analysis and collaborative decision-making support can be provided.

[0057] In some embodiments, it is possible to intelligently and real-time analyze the advantages and disadvantages of each rescue point, considering various factors. For example, the geographical location of the rescue point and the distance and traffic convenience to the accident location; the type and quantity of resources equipped at the rescue point, including professional rescue equipment (such as fire extinguishing equipment, demolition tools, etc.) and the professional skills of personnel (such as medical first aid skills, fire fighting skills, etc.); the historical rescue performance of the rescue point, such as rescue response time, rescue success rate, etc.

[0058] In some embodiments, rescue tasks can be reasonably allocated to different rescue points according to the specific circumstances of the accident (such as accident type, severity, location, etc.), so as to achieve collaborative scheduling optimization. For example, for an accident involving a fire, rescue points equipped with professional fire-fighting equipment and personnel can be screened out first, and relevant tasks can be preferentially allocated according to their distance from the accident site, traffic conditions, and other rescue task arrangements. For an accident near a traffic congestion area, the location of each rescue point and its traffic guidance ability can be comprehensively considered, and a rescue point with a suitable distance and strong traffic guidance ability can be selected to ensure that rescue vehicles can quickly reach the accident site.

[0059] In some embodiments, the task allocation of different rescue points can be optimized through intelligent algorithms to avoid duplicate operations or rescue blank areas, thus achieving multi-rescue point collaboration. Ensure that each rescue task is responsible for a suitable rescue point, and the task allocation among rescue points is reasonable and efficient, forming a collaborative rescue whole.

[0060] In the embodiments of the present invention, dynamic feedback and real-time adjustment can be supported.

[0061] In some embodiments, the optimized driving route and scheduling plan can be real-time fed back to the rescue command center, rescue vehicles, and accident vehicles to ensure that all participating parties master the latest traffic information, respond quickly, and realize an intelligent information feedback mechanism.

[0062] Figure 3 is a schematic flowchart of the dynamic adjustment of the rescue route judgment provided by the embodiments of the present invention. Refer to Figure 3 , in some embodiments, AI analysis can be performed according to changes in resource status information, changes in rescue demand information, and changes in real-time traffic conditions information, reallocate rescue tasks to other suitable rescue points, and correspondingly adjust the driving routes of rescue vehicles (i.e., adjust the optimal planned path), achieving dynamic collaborative adjustment. For example, if a vehicle at a rescue point originally responsible for a certain task breaks down, the availability and task allocation of other rescue points can be immediately evaluated, and the task can be reallocated to a rescue point with a suitable distance, sufficient resources, and quick response.

[0063] In an alternative embodiment, the use of an evolutionary algorithm to solve the multi-objective optimization model to determine the optimal rescue scheduling strategy may specifically include: Step S11, using an evolutionary algorithm to solve the multi-objective optimization model to obtain multiple candidate rescue points corresponding to each accident point; Step S12, for each accident point, calculate the comprehensive cost of each candidate rescue point based on the travel time and resource cost of the candidate rescue points corresponding to the accident point; Step S13: Determine the optimal rescue point corresponding to the accident point based on the comprehensive costs of the respective candidate rescue points.

[0064] In the embodiments of the present invention, when dealing with the optimization problem of rescue points and accident points, an evolutionary algorithm is used to solve the dynamic multi-objective optimization model, and an optimal solution set (i.e., multiple candidate rescue points corresponding to each accident point) can be found.

[0065] Since the selection of a rescue point is a binary decision problem (i.e., select a certain rescue point or not), the evolutionary algorithm is particularly excellent in dealing with such problems due to its strong global search ability and adaptability to complex problems. In the embodiments of the present invention, binary variables can be defined to represent the selection of rescue points, a multi-objective optimization model can be constructed, dimensions such as the total cost, response time, and rescue efficiency can be considered, and constraint conditions can be established to ensure the effectiveness of the rescue. The evolutionary algorithm can simulate natural selection and genetic mechanisms, iteratively search for the optimal solution, and perform selection and crossover operations according to the performance of the solution set to generate new candidate solutions, and explore new regions through mutation operations.

[0066] Compared with the traditional integer programming method, in the embodiments of the present invention, by using an evolutionary algorithm to solve the dynamic multi-objective optimization model, higher flexibility and robustness can be achieved in dealing with the binary decision problem in complex and changeable rescue scenarios.

[0067] In the embodiments of the present invention, after determining which rescue points or combinations of rescue points provide rescue for each accident point according to the multi-objective optimization solution results, the total travel time and resource costs of each candidate rescue point can be calculated, so as to obtain the comprehensive costs of each candidate rescue point.

[0068] In some embodiments, for each accident point i, the comprehensive cost of all candidate rescue points j can be calculated based on the travel time, resource cost, and their respective weight parameters . Where t ij is the travel time from rescue point j to accident point i, C is the resource cost of rescue point j, and α is the weight parameter.

[0069] In the embodiments of the present invention, after obtaining the comprehensive costs of the respective candidate rescue points corresponding to each accident point, for each accident point, the candidate rescue points can be sorted in ascending order of the comprehensive cost, so as to select the rescue point or combination of rescue points with the lowest comprehensive cost (i.e., select at least one candidate rescue point) as the optimal rescue point for this accident point, so as to ensure that the resource requirements are met.

[0070] In an embodiment of the present invention, an evolutionary algorithm is used to solve a multi-objective optimization model to obtain multiple candidate rescue points corresponding to each accident point. The comprehensive cost of each candidate rescue point is calculated based on the travel time and resource cost of each candidate rescue point corresponding to the accident point. Based on the comprehensive cost of each candidate rescue point, the optimal rescue point for dispatching rescue vehicles to the accident point for rescue is determined. It is possible to quickly and scientifically select the optimal rescue point in the case of limited rescue resources and multiple accidents occurring simultaneously, so as to efficiently dispatch the rescue resources of each rescue point, improve the rescue efficiency and success rate, and improve the overall rescue effect.

[0071] In an alternative embodiment, when encountering traffic jams, the rescue vehicle can dynamically adjust the planned route and time through GPS (Global Positioning System) and the actual traffic condition data obtained from the traffic monitoring system to ensure arriving at the accident point within the shortest time. If the jam cannot be avoided, vehicles can be immediately dispatched from other rescue points to share the task, and the dispatching strategy can be optimized by combining the results of AI-assisted decision-making and big data analysis and prediction.

[0072] When the rescue vehicle encounters situations such as traffic congestion on the way to the rescue, resulting in being unable to carry out the rescue according to the initially calculated travel time, the embodiment of the present invention can take the way of dynamically adjusting and re-optimizing the rescue dispatching strategy to ensure that the rescue can be completed within the shortest possible time.

[0073] In some embodiments, the rescue vehicle can obtain the current road condition data in real time through GPS and the traffic monitoring system, including key information such as traffic congestion, accidents, and road closures. These data can be input into the big data analysis model in real time, and advanced algorithms are used to evaluate the traffic condition in real time and predict possible future traffic changes.

[0074] The embodiment of the present invention can dynamically adjust the driving route of the rescue vehicle according to the results of big data analysis and prediction. The dynamic dispatching strategy can also be applied to the dispatching and management of rescue vehicles. According to the real-time road condition and the results of AI-assisted decision-making, the dispatching center can flexibly adjust the allocation and priority of rescue vehicles to ensure that the most urgent rescue tasks can be given priority.

[0075] Figure 4 It is a flowchart of the real-time route optimization and dynamic dispatching strategy of the rescue vehicle provided by the embodiment of the present invention. Referring to Figure 4 , the rescue vehicle can obtain the current road condition data in real time through GPS and the traffic monitoring system, including key information such as traffic congestion, accidents, and road closures, so as to update the real-time travel time t ij .

[0076] During the process of selecting a rescue point and dispatching rescue vehicles on the way, the route can be adjusted in real time according to the actual road traffic conditions to ensure that the rescue vehicles can reach the accident site within the shortest time, provide timely and effective rescue, and dynamically adjust the time weights of each section according to the latest road conditions to calculate the time cost. That is, without considering other situations, select the rescue point corresponding to the shortest travel time t ij and conduct rescue at the corresponding rescue point and dynamically adjust the driving route according to the path calculated by t ij .

[0077] When a rescue vehicle encounters an unavoidable traffic jam, vehicles can be immediately dispatched from other rescue points to share the rescue task, and other rescue points can also be selected according to the actual road conditions to choose the rescue point corresponding to the shortest driving time.

[0078] When rescue vehicles encounter emergencies such as traffic congestion, in addition to relying on GPS and traffic monitoring systems, the experience of rescue vehicle drivers and their familiarity with local road conditions can also be fully utilized. By establishing a real-time communication mechanism and a driver feedback system, drivers are encouraged to participate in route decision-making and provide the best route suggestions. At the same time, drivers are regularly trained to improve their ability to handle complex traffic conditions, ensuring that rescue vehicles can quickly and flexibly adjust their routes and reach the accident site in the shortest time.

[0079] In an alternative embodiment, a multi-objective optimization model is constructed based on the objective function of minimizing travel time and resource cost, and the constraint conditions of the objective function, which may specifically include: Step S21, construct an objective function for minimizing travel time and resource cost based on the accident point set, rescue point set, binary decision variables, travel time from the rescue point to the accident point and the corresponding weight parameters, resource cost and the corresponding weight parameters; Step S22, determine the constraint conditions of the objective function; the constraint conditions include accident point resource demand constraint conditions, availability constraint conditions of rescue point resources, and binary decision variable constraint conditions; Step S23, construct a multi-objective optimization model based on the objective function and the constraint conditions of the objective function.

[0080] In the embodiment of the present invention, an objective function for minimizing the total travel time and resource cost can be constructed: .

[0081] Where I is the accident point set; J is the rescue point set; t ij is the travel time from rescue point j to accident point i; c j is the resource cost of the rescue point; r i is the quantity of resources required at the accident point; R jThe quantity of resources available at rescue point j; x ij is a binary decision variable indicating whether rescue point j is selected to provide rescue for accident point i (1 means selected, 0 means not selected); α is a weight parameter, ranging from 0 to 1, which can control the relative importance of travel time and resource cost.

[0082] The constraint conditions can include the resource demand constraint conditions at accident points, the resource availability constraint conditions at rescue points, and the binary decision variable constraint conditions. The resource demand constraint conditions at accident points mean that for each accident point i, the required quantity of resources must meet the requirements. The resource availability constraint conditions at rescue points mean that for each rescue point j, the number of times it is selected cannot exceed its available quantity of resources. The binary decision variable constraint means whether rescue point j is selected to provide rescue for accident point i.

[0083] After determining the constraint conditions, initialization can be carried out to determine the set I of accident points, the set J of rescue points, the travel time matrix t, the resource cost c, the resource demand r at accident points, the resource availability R at rescue points, and construct an optimization model for solving based on an evolutionary algorithm's dynamic multi-objective algorithm according to the objective function and constraint conditions.

[0084] In an alternative embodiment, the travel time from the rescue point to the accident point is determined as follows: Step S31, determine multiple influencing factors affecting the travel time of the rescue vehicle and the weight values of each influencing factor; Step S32, perform dimensionless processing on the time data corresponding to each influencing factor to obtain the dimensionless time results corresponding to each influencing factor; Step S33, calculate the travel time of the rescue vehicle from the rescue point to the accident point based on the dimensionless time results corresponding to each influencing factor and the weight values of each influencing factor.

[0085] In the embodiment of the present invention, each influencing factor affecting the travel time of the rescue vehicle can be determined, so as to be used for big data analysis and prediction.

[0086] In some embodiments, the influencing factors affecting the travel time of the rescue vehicle can include the delay of travel time on the road section, the delay of travel time at the intersection, and the delay of road restrictions on the rescue vehicle.

[0087] In some embodiments, the delay of travel time on the road section can be determined based on factors such as road grade, road length, traffic control, traffic flow on the road section, and driving speed.

[0088] For the road grade factor: Roads of different levels have different impacts on the path selection of emergency rescue vehicles due to their different qualities and limited maximum speeds. For example, traffic patterns such as two-way fully enclosed and two-way semi-enclosed will directly affect the driving efficiency of rescue vehicles.

[0089] For the road length factor: The driving time can be proportional to the road length. The farther the distance, the longer the required driving time; the shorter the distance, the shorter the required driving time.

[0090] For the traffic control factor: Traffic control factors (such as road maintenance or large-scale gatherings, etc.) will temporarily close or restrict the passage of certain sections. If the planned route of the emergency rescue vehicle is affected, it can coordinate with the relevant departments to release or find a detour route.

[0091] For the traffic flow factor: The traffic flow of a section will change over time, and this factor will affect the driving time of the rescue vehicle.

[0092] For the driving speed factor: Although the driving speed of the emergency rescue vehicle is relatively fast and the time to reach the rescue location will be shortened, it can be not considered in the model because this factor can be subjectively determined by the driver and the emergency vehicle is less restricted by traffic rules.

[0093] In some embodiments, the driving time delay at intersections can be determined based on factors such as traffic signal control, intersection traffic flow, left-turn delay, left-turn delay, etc.

[0094] For the signal control factor: Signal control is the main form of intersection traffic control. Although the emergency rescue vehicle belongs to an emergency vehicle, for driving safety, it still needs to abide by traffic rules, which will have a certain impact on the time it takes to reach the rescue location.

[0095] For the traffic flow factor: The intersection traffic flow will change over time, and this factor will affect the driving time of the rescue vehicle.

[0096] For the left-turn delay factor: At some intersections, there may be a traffic jam when turning left, resulting in an increase in traffic flow, thus affecting the driving time of the rescue vehicle.

[0097] For the right-turn delay factor: Similar to the left-turn delay, there will also be a traffic jam when turning right at some intersections, affecting the driving time of the rescue vehicle.

[0098] In some embodiments, the delay caused by road restrictions on the rescue vehicle can include factors such as height limit, width limit, weight limit, etc. Emergency rescue vehicles are usually special vehicles, and their height, width, and weight are different from ordinary vehicles, so they have special requirements for the road passing capacity. If a certain section of the road or bridge has restrictions on the height, width, or weight of passing vehicles, the rescue vehicle must detour through other routes.

[0099] In the embodiments of the present invention, a real map can be simulated to construct a road network topology graph with time weights.

[0100] Figure 5 It is a schematic diagram of a road network topology with time weights provided by an embodiment of the present invention. Referring to Figure 5 , a rescue point set and an accident point set can be set, and a road network topology graph can be constructed. The time weight of each edge in the road network topology graph can be adjusted according to real-time traffic data, indicating the time it takes for the rescue vehicle to arrive.

[0101] In an embodiment of the present invention, a dimensionless standard function can be used to unify data of different units.

[0102] During the emergency rescue process, the data units of different road attributes affecting the driving of the rescue vehicle are different. For example, the length can be expressed in meters (m) or kilometers (km), while the time can be expressed in seconds (s) or minutes (min). In order to integrate and calculate these data, the embodiment of the present invention can perform dimensionless quantization processing on the time data corresponding to each influencing factor, that is, eliminate the unit of the data so that it can be compared and processed on the same dimension. The dimensionless quantization processing enables data of different units to be unified within the same calculation framework, facilitating comprehensive analysis and calculation. The dimensionless quantization processing step is crucial in the path selection and time prediction of emergency rescue.

[0103] In an embodiment of the present invention, a dimensionless quantization process can be achieved using standardization or normalization methods. Standardization refers to converting data into a standard normal distribution, that is, with a mean of 0 and a standard deviation of 1. Normalization refers to scaling data to a specific range, usually between 0 and 1.

[0104] In some embodiments, the dimensionless-quantized data can be integrated, and the influence of each factor can be considered by means of weighted average, that is, a certain weight is assigned to each factor, and then a total driving time (i.e., travel time) is calculated comprehensively.

[0105] Specifically, standard functions for dimensionless quantization of various attribute data can be cited, and for each data affecting the driving time of the rescue vehicle , then, .

[0106] Specifically, by calculating factors such as those affecting the time for the rescue unit to reach the rescued location, the weights affecting driving are sorted and substituted to obtain the dimensionless quantization result , then the time t for the emergency rescue unit i to reach the rescued location j ij , , thereby calculating the driving time cost of the rescue vehicle. Among them, are the respective weights, is the driving time for each small section of the road, To obtain a dimensionless time result.

[0107] Without considering other factors, the shortest time from each rescue point to the accident scene can be calculated based on the path algorithm. Select the rescue vehicle at the rescue point with the shortest driving time for rescue.

[0108] In an alternative embodiment, the resource cost is the cost of dispatching rescue vehicles from the rescue point; the resource cost is determined as follows: when the number of rescue vehicles required at the accident point is less than or equal to the number of rescue vehicles that the rescue point can provide, based on the number of rescue vehicles from each rescue point to each accident point and the average unit cost of the rescue point reaching the accident point, determine the total cost of rescue vehicles.

[0109] In some embodiments, the resource cost can be defined based on the number of emergency rescue vehicles required at the accident point, the number of emergency rescue vehicles that the rescue point can provide, and the average unit cost. By calculating the total cost of emergency rescue vehicles and combining the results of big data analysis and prediction, the allocation of rescue resources can be optimized.

[0110] In some embodiments, if the number of emergency rescue vehicles required at each traffic accident location is b j , and the number of emergency rescue vehicles that each rescue center can provide is a i , and it satisfies , that is, the total number of emergency rescue vehicles required at the traffic accident point is less than or equal to the total number of emergency rescue vehicles that the emergency rescue center can provide, then the resource cost can be further calculated.

[0111] The average unit cost from the rescue center (i.e., the rescue point) to the accident point can be set as c ij , the number of rescue vehicles from each rescue center to each accident point is x ij , and the total cost of emergency rescue vehicles can be: .

[0112] In an alternative embodiment, the resource cost is the cost of dispatching rescue vehicles from the rescue point; the resource cost is determined as follows: Step S41, analyze based on real-time traffic condition data and weather data to obtain a prediction result of the future accident probability; Step S42, determine the reserved resources of the rescue point based on the future accident probability prediction result and historical rescue information; Step S43, dynamically adjust the reserved resources of the rescue point based on the real-time resource usage situation of the rescue point and the latest prediction result of the future accident probability.

[0113] In the embodiments of the present invention, the limited nature of rescue resources requires reasonable resource reservation planning. Big data analysis and AI prediction models can be used to estimate the accident probabilities in different regions and at different times.

[0114] In some embodiments, a large amount of historical rescue data can be analyzed, including information such as the location, time, type of accidents, and the corresponding rescue resource usage. The patterns and trends therein can be mined. At the same time, real-time traffic data, weather data, and other relevant factors can be combined to make more accurate predictions of future accident probabilities. By combining the predicted results of future accident probabilities with historical rescue data, the types and quantities of resources to be reserved at each rescue point can be determined. In some embodiments, factors such as the cost of rescue resources, the effectiveness of different types of resources in dealing with various accidents, and the impact of the traffic conditions around the rescue points on resource allocation can also be considered. For example, in areas where serious accidents are prone to occur and traffic congestion is frequent, more diverse rescue resources should be reserved, such as professional medical rescue vehicles, special rescue equipment, and a sufficient number of professional rescue personnel. In areas with relatively smooth traffic and a low accident rate, the amount of reserved resources can be appropriately reduced, but the basic rescue capabilities still need to be ensured.

[0115] The relationship between the rescue duration and the available resources can be as shown in Table 1: Table 1

[0116] In the embodiments of the present invention, a dynamic adjustment mechanism for resource reservation can be established to monitor the usage of resources and the development trend of accidents in real time.

[0117] Specifically, by setting up resource monitoring systems at each rescue point, information such as the usage status of vehicles, the attendance of personnel, and the loss and replenishment of rescue equipment can be obtained in real time. At the same time, closely monitor the changes in the number and type of accidents in different regions. If the number of accidents in a certain region suddenly increases or special types of accidents occur, the resource reservation plan should be adjusted in a timely manner.

[0118] Exemplarily, if multiple major accidents occur continuously in a certain area, exceeding the original reserved resources, resources are allocated from other relatively idle rescue points or emergency procurement is carried out to replenish resources. Specifically, in terms of operation, if it is found that a certain resource is in shortage at a rescue point, the remaining situation of this resource at other rescue points can be queried first, and then through a reasonable allocation plan, such as dispatching vehicles to transport personnel or equipment, the resources are transferred from the rescue points with surplus to the shortage rescue points. If the overall resources are in shortage, emergency procurement of relevant resources can be considered to ensure that the rescue resources can meet the rescue needs and avoid delaying the rescue time. The rescue duration and the available resource market table will be updated in real time to reflect the usage of resources and the development trend of accidents, helping the dispatching personnel to adjust the resource reservation plan according to the real-time data.

[0119] In an alternative embodiment, an emergency call system is deployed on the rescue vehicle; during the process of the rescue vehicle driving to the accident site, the method may further include: Step S51, obtaining in real time the key information sent by the rescue vehicle through the emergency call system; the key information includes vehicle information and accident information; the vehicle information includes at least one of vehicle status information, vehicle driving environment information, and vehicle location information, and the emergency call information includes at least one of accident vehicle location information, accident severity information, and the number of people in the accident vehicle; Step S52, sending the key information to a third-party platform for display.

[0120] In the embodiment of the present invention, an emergency call system (i.e., eCall system) can be deployed on each rescue vehicle to monitor vehicle information such as vehicle status information (such as fuel level, engine temperature, tire pressure), vehicle driving environment information (such as weather conditions, road conditions), and vehicle location information. The rescue vehicle can collect vehicle status and environment information in real time and send the data to a third-party platform for display through a set communication protocol. Before sending it to the third-party platform, the received data can be cleaned and formatted to ensure the accuracy and consistency of the data.

[0121] In some embodiments, a real-time monitoring panel can be built on the rescue platform (i.e., the third-party platform) to display key information (such as fuel level, weather changes, etc.), and when an abnormal situation (such as insufficient fuel, bad weather) is found, an abnormal reminder notice is automatically sent to notify the rescue command center and relevant personnel.

[0122] MSD (Minimum Set of Data) data can refer to the minimum data transmission unit transmitted from the rescue vehicle terminal to the edge computing device, which may include accident vehicle location information, accident severity information, the number of people in the accident vehicle, etc. In the embodiments of the present invention, the edge computing device can directly process emergency call data at the edge node (i.e., the edge computing device) near the accident point. The edge computing device can analyze and integrate MSD and on-site environmental data, extract key information and quickly provide it to the third-party platform. The edge computing device can also utilize the driver's route knowledge to optimize the rescue route.

[0123] In some embodiments, the edge computing device can perform intelligent traffic flow analysis. It can collect traffic flow data in real time, identify traffic patterns through machine learning algorithms, predict peak hours, identify common congestion nodes, and dynamically provide optimal route suggestions. This analysis process is directly completed on the edge device, reducing the data processing burden on the third-party platform and ensuring that the rescue vehicle obtains updated route information in real time.

[0124] In some embodiments, the edge computing device can perform environmental anomaly detection and instant alarm. Based on the distributed processing of edge computing, it can analyze environmental data (such as road conditions, meteorology) in real time, and use machine learning algorithms to automatically identify abnormal events (such as major accidents, extreme weather). When this module detects a sudden abnormal situation, it immediately generates a warning message and sends the alarm to the third-party platform through a fast communication link to support timely emergency decision-making and route replanning.

[0125] In some embodiments, the edge computing device can automatically generate an adaptive rescue plan based on the analysis results to achieve instant intelligent decision-making generation. The system can calculate the best driving path in real time, propose route adjustment suggestions, and notify the dispatching to send additional rescue resources when needed, thereby reducing the response time.

[0126] In some embodiments, the edge computing device can have an information feedback and intelligent notification mechanism. It can quickly feedback key decisions and real-time data to the third-party platform, and the third-party platform then quickly feedbacks it to the rescue center to ensure that the commanders have a comprehensive understanding of the on-site dynamics. The edge node supports low-latency communication with the third-party platform so that the rescue center can obtain the necessary information in the first time and flexibly adjust the rescue strategy.

[0127] In the embodiments of the present invention, the driving route of the rescue vehicle can be dynamically adjusted based on real-time data to ensure arriving at the accident scene within the shortest time, reducing rescue delays and achieving route optimization; the scheduling and allocation of rescue resources can be optimized according to the real-time monitored data to ensure that each accident point can receive timely and effective responses, realizing resource management, thereby achieving dynamic scheduling and optimization.

[0128] In view of the problem that the current rescue dispatching method does not fully consider the actual road environment and real-time traffic conditions when selecting rescue points, resulting in low rescue efficiency, limited rescue resources, and difficulty in efficiently dispatching in case of multiple accidents, which affects the overall rescue effect, the embodiments of the present invention comprehensively consider multiple factors such as the actual driving distance, real-time traffic conditions, and rescue resource costs, and through dynamic adjustment and optimization algorithms, achieve an improvement in the emergency rescue response speed, optimization of resource allocation, and reduction of rescue costs, ensuring the rapid and scientific selection of the best rescue point in a complex and changeable environment, and significantly enhancing the efficiency of emergency rescue and the scientific nature of decision-making.

[0129] How to quickly and scientifically select the best rescue point after receiving accident information provided by the vehicle emergency rescue system is an urgent problem to be solved at present. Although the vehicle emergency rescue system performs well in information transmission after an accident, in actual applications, the selection of rescue points still faces many challenges: (1) Multi-rescue point coordination: During the rescue process, the cooperation of multiple rescue points is often involved, but the current system has deficiencies in this regard. There is a lack of an effective coordination mechanism between rescue points, which may lead to chaotic rescue operations and the inability to form an efficient rescue force. The resources, operation plans, etc. of different rescue points cannot be well integrated, easily resulting in duplicate operations or rescue blank areas, affecting the overall rescue efficiency.

[0130] (2) Resource reservation: Due to the limited and uneven distribution of rescue resources, it is necessary to reasonably plan the resource reserves of each rescue point. This can avoid delays in rescue opportunities when, in case of a traffic accident, some areas lack key resources (such as specific types of rescue vehicles or professional rescue personnel) and need to be allocated from other areas with sufficient resources.

[0131] (3) Disconnection between location point selection and path optimization algorithm: The algorithms for the two key links of rescue point location selection and rescue vehicle driving path optimization in the current system are mutually disconnected. When selecting a rescue point, the consideration of path optimization is not fully combined, resulting in the possible selection of a rescue point that seems close in distance but actually has a complex and congested path. Similarly, the path optimization algorithm does not base on accurate rescue point selection information, making the path planning unable to adapt to the actual situation of the rescue point, ultimately affecting the rescue efficiency and effect, and unable to quickly and scientifically deliver rescue resources to the accident scene.

[0132] In order to improve the efficiency of emergency rescue and reduce accident losses, the embodiments of the present invention provide a rescue point selection method applicable to vehicle emergency rescue, which can comprehensively consider multiple factors, including the actual driving distance between the accident location and the rescue point, real-time traffic conditions, the distribution of rescue resources, and their dispatching costs, etc. Specifically, it may include: (1)Comprehensively consider multiple factors such as the actual driving distance between each rescue point and the incident location, road conditions, real-time traffic information, availability of rescue resources, and costs. Establish a rescue coordination mechanism to enable each rescue point to make a reasonable division of labor based on its own advantages and comprehensive situation, and at the same time have the ability to adjust the rescue plan in a timely manner according to dynamic changes in traffic and resources. Appropriately use AI technology to analyze and model the status and resources of rescue points to assist in coordination. The integration of intelligent transportation systems can provide information for collaborative dispatching and route optimization, and edge computing processes emergency call data to reduce latency and enhance system coordination.

[0133] (2)Utilize historical data and AI: Based on historical rescue data, introduce an AI prediction model to assist in estimating the accident probability in each region, thereby determining the types and quantities of resources that should be reserved at each rescue point. In this process, comprehensively consider resource costs, such as vehicle purchase costs, maintenance costs, and labor costs; as well as the spatial distribution of specific resources, such as special rescue vehicles. Also, pay attention to the impact of traffic conditions on resource allocation. For example, more flexibly deployable resources may need to be reserved in traffic-congested areas.

[0134] (3)Regarding the problem of the mutual disconnection between location point selection and path optimization algorithms, construct an integrated intelligent rescue decision-making system to uniformly model the factors required for rescue point selection and path optimization. For example, integrate data such as the distance between the incident location and the rescue point, actual road conditions, traffic information, and resource costs, and use a dynamic multi-objective algorithm based on evolutionary algorithms, combined with a neural network model, with historical rescue data as the training basis, to achieve the goal of selecting a rescue point and planning a path simultaneously. During the rescue operation, continuously optimize the algorithm according to dynamic changes in traffic conditions and resources, utilize the information of the intelligent transportation system and use edge computing to process emergency call data to reduce latency and ensure the smooth progress of the rescue operation. At the same time, analyze rescue data to mine patterns and improve the adaptability of the algorithm to complex rescue situations.

[0135] In summary, the present invention has the following technical advantages: The present invention comprehensively considers multiple key factors, enables rescue points to make a reasonable division of labor through a rescue coordination mechanism, and avoids blindness and disorder. It can adjust the plan according to dynamic changes in traffic and resources, use AI technology for assistance, combine the integration of intelligent transportation systems and edge computing to process eCall data, and enhance coordination and efficiency. Compared with the prior art that only considers some factors, the present invention is more comprehensive and can significantly improve the rescue efficiency and success rate.

[0136] The present invention combines historical data to determine the resource reservation at rescue points, comprehensively considers costs, effectiveness, and traffic impacts, and introduces an AI prediction model. This data-driven method is scientific and reasonable. Compared with the prior art, it can more accurately determine the resource reservation plan, ensure the reasonable allocation and efficient utilization of resources, and improve the timeliness and effectiveness of rescue.

[0137] The present invention constructs an integrated system aiming at algorithm fragmentation, unifies modeling and integrates key data, and uses specific algorithms and models to synchronize point selection and path planning. During the rescue process, the algorithm is continuously optimized, relevant technologies are used to reduce latency, and data is analyzed to improve adaptability. Compared with the problems caused by algorithm fragmentation in the prior art, this method can make efficient decisions and plan paths, improving the rescue efficiency and success rate.

[0138] The rescue point selection method provided by the embodiments of the present invention can comprehensively consider various factors such as the actual driving distance between the accident location and the rescue point, the real-time traffic conditions, the availability of rescue resources and their scheduling costs, and introduces AI-assisted decision-making and big data analysis and prediction. Through dynamic adjustment and scientific optimization, the selection of the best rescue point is realized to ensure that all accidents can be rescued in a timely and effective manner.

[0139] Figure 6 is the second schematic flowchart of the rescue scheduling method provided by the embodiments of the present invention. Refer to Figure 6 , in some embodiments, the specific cooperation process of the rescue scheduling method can be as follows: S1: Simulate the real map and construct the road network graph. Map construction: Set the set of rescue points and the set of accident points, and construct the road network graph. Time weight: The time weight of each edge is adjusted according to the real-time traffic data, indicating the factors affecting the arrival time of the rescue vehicle.

[0140] S2: Influence factors and big data analysis and prediction. Factor list: road grade, length, traffic control, traffic flow, driving speed, traffic signal control, weight and width limit, etc. Data integration: Use a dimensionless quantization standard function to unify data of different units.

[0141] S3: Real-time accident response of the emergency call system. Deploy the emergency call function on the rescue vehicle. Once an accident occurs, the system will be automatically activated and quickly send key data (including information such as the exact location of the accident vehicle, the severity of the accident, and the number of passengers in the vehicle) to a preset third-party platform. This mechanism ensures that the rescue team can immediately obtain the latest situation at the accident scene, so as to quickly respond and carry out effective rescue operations.

[0142] S4: Edge computing. Through edge computing, emergency call data can be directly processed at edge nodes near the accident (such as nearby base stations). Edge computing will analyze and integrate on-site environmental data (such as real-time traffic flow, weather conditions), extract key information and quickly provide it to the third-party platform center to reduce latency.

[0143] S5: Integration of Intelligent Transportation Systems. Integrate the rescue system with the intelligent transportation system to obtain real-time traffic signal status, traffic flow, and road condition information. Combine this data with the key data returned by emergency calls to provide an accurate information basis for the dispatching of rescue vehicles, ensuring flexible route adjustment in complex traffic situations.

[0144] S6: AI-Assisted Decision-Making and Big Data Analysis and Prediction. Utilize AI technology to deeply mine and analyze historical rescue data, traffic data, and environmental data to discover patterns and trends in the data. Based on the real-time data provided by emergency calls and edge computing, AI algorithms can dynamically adjust the rescue point optimization process to improve the scientific nature and accuracy of decision-making.

[0145] S7: Travel Time Calculation and Shortest Path Selection. Calculation method: Calculate the travel time of rescue vehicles through influencing factors to obtain a dimensionless result. Shortest path: Use path algorithms to calculate the shortest-time path, dynamically adjust the time weights of road segments, and combine the results of AI-assisted decision-making to select the rescue point with the shortest-time path.

[0146] S8: Real-Time Route Optimization and Dynamic Dispatching Strategy for Rescue Vehicles. When encountering traffic jams, rescue vehicles need to dynamically adjust routes and times through GPS and traffic monitoring systems to ensure reaching the accident site within the shortest time. If the traffic jam cannot be avoided, immediately dispatch vehicles from other rescue points to share the task, and combine the results of AI-assisted decision-making and big data analysis and prediction to optimize the dispatching strategy.

[0147] S9: Resource Reservation and Determination of Resource Costs. The limited nature of rescue resources requires reasonable resource reservation planning. Definition of resource costs: The number of first-aid vehicles required at the accident site, the number of first-aid vehicles that the rescue center can provide, and the average unit cost. Total cost: Calculate the total cost of emergency rescue vehicles and combine the results of big data analysis and prediction to optimize resource allocation. S10: Objective Function. Objective: Minimize the total travel time and resource costs. Constraints: Resource demand satisfaction constraint, resource availability constraint, binary decision variable constraint.

[0148] S11: Algorithm Steps. Initialization: Determine the set of accident sites, the set of rescue points, the travel time matrix, resource costs, resource demands at accident sites, and resource availability at rescue points. Build an optimization model: Build a linear programming model based on the objective function and constraints, and introduce the results of AI-assisted decision-making and big data analysis and prediction. Solve the model: Use linear programming or heuristic algorithms to solve the model to obtain the optimal solution. Result analysis: Determine which rescue points provide rescue for each accident site, and calculate the total travel time and resource costs. Select the optimal plan: Calculate the comprehensive cost, sort and select the rescue point or combination with the lowest cost to ensure meeting resource demands.

[0149] The rescue dispatching device provided by the present invention will be described below. The rescue dispatching device described below can be correspondingly referred to the rescue dispatching method described above.

[0150] Figure 7 It is a schematic structural diagram of the rescue dispatching device provided by an embodiment of the present invention. Referring to Figure 7 , an embodiment of the present invention provides a rescue dispatching device, and the device may specifically include the following modules: A construction module 710, configured to construct a multi-objective optimization model based on an objective function of minimizing travel time and resource cost, and constraint conditions of the objective function; wherein, the travel time refers to the driving time required for a rescue vehicle to travel from a rescue point to an accident point according to a planned path; A solving module 720, configured to solve the multi-objective optimization model by using an evolutionary algorithm, determine an optimal rescue point corresponding to each accident point, and determine an optimal planned path with the shortest travel time from the optimal rescue point to the accident point; A rescue dispatching module 730, configured to determine a rescue dispatching plan and perform rescue based on the optimal rescue points corresponding to the respective accident points and the optimal planned path.

[0151] Through the construction of a multi-objective optimization model based on the objective function and constraint conditions of minimizing travel time and resource cost, the embodiment of the present invention realizes the unified modeling of the factors required for rescue point selection and path optimization; by using an evolutionary algorithm to solve the multi-objective optimization model, the rescue points corresponding to each accident point are determined, and the optimal planned path with the shortest travel time from the optimal rescue point to the accident point is determined. Therefore, not only can the optimal rescue point be quickly and scientifically selected in the case of limited rescue resources and multiple accidents occurring simultaneously, but also the optimal path can be planned while selecting the optimal rescue point, improving the overall rescue efficiency and rescue effect, and realizing efficient and scientific rescue dispatching.

[0152] Figure 8 It exemplifies a schematic structural diagram of an electronic device, as Figure 8As shown in the figure, the electronic device may include: a processor 810, a communications interface 820, a memory 830, and a communication bus 840. Among them, the processor 810, the communications interface 820, and the memory 830 complete communication with each other through the communication bus 840. The processor 810 may call the logical instructions in the memory 830 to execute a rescue scheduling method, which includes: constructing a multi-objective optimization model based on an objective function of minimizing travel time and resource cost, and constraint conditions of the objective function; where the travel time refers to the driving time required for a rescue vehicle to travel from a rescue point to an accident point according to a planned path; using an evolutionary algorithm to solve the multi-objective optimization model, determining the optimal rescue point corresponding to each accident point, and determining the optimal planned path with the shortest travel time from the optimal rescue point to the accident point; based on the optimal rescue points corresponding to each accident point and the optimal planned path, determining a rescue scheduling strategy and performing a rescue.

[0153] In addition, when the logical instructions in the above-mentioned memory 830 can be implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc that can store program codes.

[0154] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the rescue scheduling method provided by each of the above methods. The method includes: constructing a multi-objective optimization model based on an objective function of minimizing travel time and resource cost, and constraint conditions of the objective function; wherein, the travel time refers to the driving time required for a rescue vehicle to travel from a rescue point to an accident point according to a planned path; using an evolutionary algorithm to solve the multi-objective optimization model, determining an optimal rescue point corresponding to each accident point, and determining an optimal planned path with the shortest travel time from the optimal rescue point to the accident point; based on the optimal rescue points corresponding to each accident point and the optimal planned path, determining a rescue scheduling strategy and conducting a rescue.

[0155] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it realizes the rescue scheduling method provided by each of the above methods. The method includes: constructing a multi-objective optimization model based on an objective function of minimizing travel time and resource cost, and constraint conditions of the objective function; wherein, the travel time refers to the driving time required for a rescue vehicle to travel from a rescue point to an accident point according to a planned path; using an evolutionary algorithm to solve the multi-objective optimization model, determining an optimal rescue point corresponding to each accident point, and determining an optimal planned path with the shortest travel time from the optimal rescue point to the accident point; based on the optimal rescue points corresponding to each accident point and the optimal planned path, determining a rescue scheduling strategy and conducting a rescue.

[0156] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative labor.

[0157] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0158] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A rescue dispatching method, characterized in that: The method comprises: A multi-objective optimization model is constructed based on the objective function of minimizing travel time and resource cost, and the constraints of the objective function; wherein the travel time refers to the travel time required for the rescue vehicle to travel from the rescue point to the accident point according to the planned path; An evolutionary algorithm is used to solve the multi-objective optimization model, to determine the optimal rescue point corresponding to each accident point, and to determine the optimal planning path with the shortest travel time from the optimal rescue point to the accident point; Based on the optimal rescue points corresponding to the various accident points and the optimal planned paths, a rescue dispatch strategy is determined and rescue is carried out.

2. The rescue dispatch method according to claim 1, characterized in that: After solving the multi-objective optimization model using an evolutionary algorithm to determine the optimal rescue point corresponding to each accident point, the method further includes: Acquiring historical rescue information and real-time traffic status information read from a traffic system; the historical rescue data includes at least one of historical dispatch information, historical environmental information and historical traffic status information; Analyze the historical rescue information to extract key feature data that affects rescue efficiency; Inputting the key feature data into a time series prediction model to obtain a first future rescue demand and traffic condition change prediction result; Based on the first future rescue demand and traffic condition change prediction results, the optimal rescue points corresponding to the various accident points are dynamically adjusted.

3. The rescue dispatch method according to claim 1, characterized in that: After determining the optimal planned path with the shortest travel time from the optimal rescue point to the accident point, the method further includes: Obtain resource status information of each rescue point, rescue demand information of each accident point and real-time traffic condition information for analysis, and determine the rescue mission of each rescue point; Based on the changes in the resource status information, the changes in the rescue demand information and the changes in the real-time traffic condition information, AI-assisted decision analysis is performed to dynamically adjust the rescue tasks of the various rescue points to adjust the optimal planned path.

4. The rescue dispatch method according to claim 1, characterized in that: The method of solving the multi-objective optimization model by using an evolutionary algorithm to determine the optimal rescue point corresponding to each accident point includes: An evolutionary algorithm is used to solve the multi-objective optimization model to determine a plurality of candidate rescue points corresponding to each accident point; For each accident point, based on the travel time and resource cost of each candidate rescue point corresponding to the accident point, calculate the comprehensive cost of each candidate rescue point; Based on the comprehensive costs of the candidate rescue points, an optimal rescue point corresponding to the accident point is determined.

5. The rescue dispatching method according to claim 1, characterized in that: The objective function based on minimizing travel time and resource cost, and the constraint conditions of the objective function, construct a multi-objective optimization model, including: Based on the set of accident points, the set of rescue points, binary decision variables, the travel time from the rescue point to the accident point and the corresponding weight parameters, the resource cost and the corresponding weight parameters, an objective function for minimizing the travel time and resource cost is constructed; Determining the constraint conditions of the objective function; the constraint conditions include the resource demand constraint conditions of the accident point, the availability constraint conditions of the rescue point resources and the binary decision variable constraint conditions; Based on the objective function and the constraints of the objective function, a multi-objective optimization model is constructed.

6. The rescue dispatch method according to claim 5, characterized in that: The travel time from the rescue point to the accident point is determined in the following way: Determine multiple influencing factors affecting the travel time of the rescue vehicle and the weight of each influencing factor; Perform dimensionless quantization processing on the time data corresponding to each influencing factor to obtain the dimensionless time result corresponding to each influencing factor; Based on the dimensionless time results corresponding to the various influencing factors and the weights of the various influencing factors, the travel time of the rescue vehicle from the rescue point to the accident point is calculated.

7. The rescue dispatch method according to claim 5, characterized in that: The resource cost is the cost of sending a rescue vehicle from a rescue point; the resource cost is determined by: When the number of rescue vehicles required at the accident point is less than or equal to the number of rescue vehicles that the rescue point can provide, the total rescue vehicle cost is determined based on the number of rescue vehicles arriving at each accident point from each rescue point and the average unit cost of the rescue point to the accident point.

8. The rescue dispatch method according to claim 5, characterized in that: The rescue point resources are reserved in the following ways: Analyze real-time traffic conditions and weather information to predict the probability of future accidents; Determining reserved resources at the rescue point based on the predicted results of the probability of future accidents and historical rescue information; Based on the real-time resource usage of the rescue point and the latest prediction results of the probability of future accidents, the reserved resources of the rescue point are dynamically adjusted.

9. The rescue dispatch method according to claim 1, characterized in that: The rescue vehicle is equipped with an emergency call system; when the rescue vehicle is driving to the accident site, the method further includes: Acquire in real time the key information sent by the rescue vehicle through the emergency call system; the key information includes vehicle information and accident information; the vehicle information includes at least one of vehicle status information, vehicle driving environment information and vehicle location information, and the emergency call information includes at least one of accident vehicle location information, accident severity information and information on the number of people in the accident vehicle; The key information is sent to a third-party platform for display.

10. A rescue dispatching device, characterized in that: include: A construction module is used to construct a multi-objective optimization model based on an objective function of minimizing travel time and resource cost, and constraints of the objective function; wherein the travel time refers to the travel time required for the rescue vehicle to travel from the rescue point to the accident point according to the planned path; A solution module, used to solve the multi-objective optimization model using an evolutionary algorithm, determine the optimal rescue point corresponding to each accident point, and determine the optimal planning path with the shortest travel time from the optimal rescue point to the accident point; The rescue dispatch module is used to determine the rescue dispatch plan and carry out rescue based on the optimal rescue points and the optimal planned paths corresponding to the various accident points.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the rescue dispatch method according to any one of claims 1 to 9 is implemented.

12. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the rescue dispatch method according to any one of claims 1 to 9 is implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the rescue dispatch method according to any one of claims 1 to 9 is implemented.

Images