A rescue route planning method and system for an emergency rescue vehicle

Abstract

The embodiment of the application provides a rescue route planning method and system of an emergency rescue vehicle, and relates to the technical field of traffic control of road vehicles. The method comprises the following steps: obtaining target data, obtaining first output data based on a first preset algorithm, and determining a target vehicle, a starting place and a destination based on the first output data; wherein the target data comprises a node set, a vehicle type set, a fixed cost, a capacity cost and a time cost; the starting place is a current residence place of the target vehicle, and the destination is a to-be-rescued destination; obtaining the first output data, real-time traffic information and real-time weather information, obtaining second output data based on a second preset algorithm, and determining an optimal driving path of the target vehicle from the starting place to the destination based on the second output data. Through the application, the problem of low rescue efficiency in the related art is solved, and the effect of fast rescue is achieved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of traffic control of road vehicles, and in particular, to a rescue route planning method and system for emergency rescue vehicles. BACKGROUND

[0002] The history of emergency rescue vehicle route planning can be traced back to early navigation and path optimization technologies, which were originally designed to improve logistics and transportation efficiency. Over time, these technologies have been applied to the fields of emergency medical services and disaster response to ensure that rescue resources can quickly and effectively reach the scene of an accident. Early methods mainly focused on shortest path algorithms, but as computing power improved and algorithms developed, route planning began to integrate more dynamic factors, such as real-time traffic information and geographic information system (GIS) data, to improve the adaptability and accuracy of path planning.

[0003] In the latest related technologies, researchers have adopted a variety of solutions to address the problem of vehicle dispatching and path planning. Some studies have proposed methods based on optimization algorithms, such as genetic algorithms and ant colony algorithms, which can handle complex constraints and find the optimal solution among multiple candidate paths. In addition, there are studies that use machine learning techniques to analyze historical data to predict traffic patterns and accident-prone areas, thereby planning rescue routes in advance. The development of these technologies has made the dispatching and path planning of rescue vehicles more intelligent and automated.

[0004] Despite the significant progress made by the latest technologies in emergency rescue vehicle route planning, existing solutions often have the problem of considering only a single dimension. For example, some methods may focus on minimizing travel distance or time, while ignoring the urgency of the rescue mission and the rational allocation of resources. This single-dimensional optimization can result in a failure to fully adapt to the changing rescue environment in practical applications, leading to low rescue efficiency. SUMMARY

[0005] Embodiments of the present application provide a rescue route planning method and system for emergency rescue vehicles to at least solve the problem of low rescue efficiency in related technologies.

[0006] According to one embodiment of the present application, a rescue route planning method of an emergency rescue vehicle is provided, comprising: obtaining target data, obtaining first output data based on a first preset algorithm, and determining a target vehicle, a departure location and a destination based on the first output data; wherein the target data comprises a node set, a vehicle type set, a fixed cost, a capacity cost and a time cost; the departure location is a current residence location of the target vehicle, and the destination is a rescue destination; obtaining the first output data, real-time traffic information and real-time weather information, obtaining second output data based on a second preset algorithm, and determining an optimal driving path of the target vehicle from the departure location to the destination based on the second output data.

[0007] According to another embodiment of the present application, a rescue route planning system of an emergency rescue vehicle is also provided, characterized in that comprising: a dispatching model, configured to obtain target data, obtain first output data based on a first preset algorithm, and determine a target vehicle, a departure location and a destination based on the first output data; wherein the target data comprises a node set, a vehicle type set, a fixed cost, a capacity cost and a time cost; the departure location is a current residence location of the target vehicle, and the destination is a rescue destination; and a path selection model, configured to obtain the first output data, real-time traffic information and real-time weather information, obtain second output data based on a second preset algorithm, and determine an optimal driving path of the target vehicle from the departure location to the destination based on the second output data.

[0008] According to one embodiment of the present application, a rescue route planning method of an emergency rescue vehicle is provided, comprising: obtaining target data, obtaining first output data based on a first preset algorithm, and determining a target vehicle, a departure location and a destination based on the first output data; wherein the target data comprises a node set, a vehicle type set, a fixed cost, a capacity cost and a time cost; the departure location is a current residence location of the target vehicle, and the destination is a rescue destination; obtaining the first output data, real-time traffic information and real-time weather information, obtaining second output data based on a second preset algorithm, and determining an optimal driving path of the target vehicle from the departure location to the destination based on the second output data. BRIEF DESCRIPTION OF DRAWINGS

[0009] Figure 1 is a flowchart of a rescue route planning method of an emergency rescue vehicle according to an embodiment of the present application;

[0010] Figure 2 is a flowchart of a method for determining basic rescue demand based on the type and severity of an accident according to an embodiment of the present application;

[0011] Figure 3 is a structural schematic diagram of a rescue route planning system of an emergency rescue vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0012] Embodiments of the present application will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0013] It should be noted that the terms "first", "second" and the like in the description and claims of the application and the above drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0014] A rescue route planning method of an emergency rescue vehicle is provided in the embodiment, Figure 1 The flow chart of the rescue route planning method of the emergency rescue vehicle according to the embodiment of the application is shown in Figure 1 The flow chart includes the following steps:

[0015] Step S101, obtaining target data, obtaining first output data based on a first preset algorithm, and determining a target vehicle, a starting location and a destination based on the first output data; wherein the target data includes a node set, a vehicle type set, a fixed cost, a capacity cost and a time cost; the starting location is a current residence location of the target vehicle, and the destination is a rescue destination;

[0016] In an exemplary embodiment, the related art mainly focuses on the shortest path algorithm, and does not fully consider the urgency of the rescue task and the reasonable allocation of resources. However, step S101 considers the fixed cost, the capacity cost and the time cost comprehensively, so that the application not only pays attention to the path length, but also pays attention to the reasonable allocation of resources and the urgency of the rescue task, thereby providing more comprehensive scheduling decisions. The node set can include nodes of geographic locations such as landmark buildings, intersections, tunnels, construction sites and temporary control areas in the city.

[0017] Step S102, obtaining the first output data, real-time traffic information and real-time weather information, obtaining second output data based on a second preset algorithm, and determining the best driving path of the target vehicle from the starting location to the destination based on the second output data.

[0018] In an exemplary embodiment, the related art relies more on static data or prediction models, and fails to respond to traffic and weather changes in real time. However, step S102 integrates real-time traffic and weather information and the first output data, so that the application can adapt to the current actual road conditions, select the best driving path, and improve the timeliness and accuracy of the rescue.

[0019] Through steps S101 to S102, since the scheduling cost and time cost of the rescue vehicle are considered, and the path selection is dynamically adjusted through the integration of real-time data, the rescue vehicle can quickly and accurately reach the rescue site. This method overcomes the single-dimensional optimization problem in the background art. Therefore, the problem of low rescue efficiency in the related art is solved, and the effect of rapid rescue is achieved.

[0020] In an embodiment, the objective function of the first preset algorithm is:

[0021] ;

[0022] ;

[0023] wherein, is a set of nodes, representing all possible nodes in the map; is a set of vehicle types; is a fixed cost; is a capacity cost; is a time cost; is the type of the target vehicle; is the departure location; is the destination; is the rescue demand; is the total number of vehicle types; is a decision variable, representing whether to dispatch a vehicle type from a node to a node , in the case where it is determined to dispatch a vehicle type from a node to a node .

[0024] In an exemplary embodiment, the objective function of the first preset algorithm is to minimize the total cost of emergency rescue vehicle route planning, which includes a fixed cost, a capacity cost, and a time cost. First, by minimizing the total cost, the objective function ensures efficient use of rescue resources and avoids unnecessary waste. Second, the introduction of the time cost allows the algorithm to consider the urgency of the rescue when making decisions, giving priority to rescue tasks with higher time costs, thereby improving the timeliness of the rescue. The capacity cost ensures reasonable allocation of rescue resources, avoiding excessive concentration or shortage of resources, and improves the efficiency of resource utilization. The binary nature of the decision variable makes the decision clear and easy to implement and monitor the dispatch of rescue vehicles.

[0025] The set of nodes , the set of vehicle types , the fixed cost , the capacity cost , the time cost , and the decision variable are used as inputs to the algorithm to determine the decision variable that meets the requirements, and in the case where the decision variable is determined, the decision variableCorresponding to: Target vehicle, i.e., the vehicle determined to go to rescue, Departure location of the target vehicle, Destination of the target vehicle, i.e., the location determined to go to rescue From the departure location Destination of the target vehicle To implement the rescue action. The first preset algorithm not only optimizes the scheduling of rescue vehicles, but also ensures that the path selection can adapt to dynamic changes in traffic and weather conditions, thereby improving the efficiency and effectiveness of rescue. In an exemplary embodiment, the fixed cost

[0026] Inherent to the rescue vehicle from node To node This can include the use of vehicles, fuel, vehicle wear and tear, etc. The calculation method of the fixed cost can be a pre-set standard fee, or it can be calculated based on historical data and empirical formula. Capacity cost

[0027] The cost generated when allocating vehicles according to rescue needs. This can include the load, passenger capacity or special equipment requirements of the vehicle. The calculation of the capacity cost can be related to the capacity requirements of the vehicle and the size of the rescue task. For example, if a task requires multiple vehicles or special equipment, the capacity cost will increase accordingly. The calculation of the capacity cost can be determined by analyzing the rescue needs and vehicle capacity. Time cost

[0028] The cost incurred by the time required for the rescue vehicle to travel from node To node This can include the operating cost of the vehicle, personnel wages, and additional costs that may arise due to delayed rescue. The calculation of the time cost can be based on the average speed of the vehicle, road conditions, traffic congestion, etc. The formula for calculating the time cost can be: Where is the distance from node To node , is the average speed of the vehicle . k In an embodiment, the rescue demand satisfaction constraint is:

[0029]

[0030] ≥ ,∀ ∈ ;

[0031] Where, Basic rescue demand, indicating the number of rescue vehicles needed from the node to the node The minimum number of rescue vehicles needed, determined based on the type and severity of the accident.

[0032] Figure 2 is a flowchart of a method for determining a basic rescue demand based on the type and severity of an accident according to an embodiment of the present application, in one implementation, as shown in Figure 2 determining a basic rescue demand based on the type and severity of an accident includes:

[0033] Step S201, obtaining keywords based on the voice information of the rescue call;

[0034] In an exemplary implementation, for example, when a rescue call information is obtained, the voice information in the call describes a traffic accident. The rescue call information can be a recorded audio or a real-time call based on the authorization of both parties calling and receiving. Through voice recognition technology, the system can convert the voice into text and extract keywords from it. For example, the keywords can include "traffic accident", "multiple vehicles", "four people injured", "fracture", "death", etc.

[0035] Step S202, matching the keywords with stored historical accident data and historical rescue response situations to obtain a matching result to determine the type and severity of the accident;

[0036] In an exemplary implementation, for example, the extracted keywords are matched with a historical accident database. The database contains records of similar past accidents, such as accident type (such as traffic accident, fire, medical emergency, etc.), severity (such as minor, moderate, severe), and corresponding rescue response situations (such as number of vehicles, rescue time, rescue equipment used, etc.).

[0037] Specifically, for example, the system finds through matching that the keywords "multiple vehicles" and "injured" are associated with "serious traffic accident" recorded in history. Further analysis of the rescue response situations of these accidents finds that at least 3 ambulances and 1 fire truck are usually needed.

[0038] Step S203, determining the basic rescue demand based on the matching result.

[0039] In an exemplary implementation, for example, according to the matching result in step S202, the system determines that at least 3 ambulances and 1 fire truck are needed as the basic rescue demand for the current accident. This demand will be used as an input to the rescue dispatch model, i.e. the basic rescue demand , ensuring that there are enough rescue vehicles dispatched from the current rescue vehicle's stopover location (departure location) to the accident site (destination).

[0040] Specifically, the system inputs this information as a constraint condition into the upper-layer scheduling model, ensuring that the total number of rescue vehicles meets ≥ In this example, the basic rescue demand is at least 4, representing at least 4 vehicles (3 ambulances and 1 fire truck) are needed.

[0041] Through steps S201 to S203, the emergency rescue vehicle rescue route planning method can automatically determine the basic rescue demand of the accident, thereby improving the efficiency and accuracy of rescue response. This method reduces the need for human judgment, speeds up the scheduling process of rescue resources, and helps to ensure that rescue operations can be launched quickly and effectively.

[0042] Here, the rescue demand satisfaction constraint ensures that the number of rescue vehicles dispatched from each departure location to each destination can meet the predetermined rescue demand .

[0043] For example: In a city area with 3 nodes (intersections): V={A, B, C}, and there are 2 types of rescue vehicles: K={1, 2}. There are the following rescue demands:

[0044] At least 2 rescue vehicles are needed from node A to node B.

[0045] At least 1 rescue vehicle is needed from node A to node C.

[0046] At least 1 rescue vehicle is needed from node B to node C.

[0047] These rescue demands can be represented as: =2, , =1;

[0048] For example, the calculated fixed cost, capacity cost, and time cost are as follows:

[0049] =10, =15, =12, =18;

[0050] =5, =8, =6, =9;

[0051] = 3, = 4, = 2, = 3;

[0052] Then it needs to determine whether the rescue demand constraints are met. For example, the output of the first preset algorithm is:

[0053] = 1, = 0, = 1, = 0;

[0054] Then it can check whether the constraint conditions are met:

[0055] = 1 + 1 = 2 ≥ = 2 (satisfied);

[0056] = 0 + 0 = 0 ≥ = 1 (not satisfied);

[0057] = 1 + 0 = 1 ≥ = 1 (satisfied).

[0058] In the above example, the rescue demand from node A to node C is not met because only 0 vehicles are dispatched. This indicates that the decision variable needs to be adjusted to ensure that all rescue demand constraints are met.

[0059] In the above manner, the rescue demand satisfaction constraint ensures that the dispatch of rescue vehicles can meet the rescue demand of each specific route, thereby improving the efficiency and effectiveness of rescue.

[0060] In an embodiment, the total number of vehicle types satisfies the constraint:

[0061] The total number of vehicle types , for all .

[0062] In an exemplary embodiment, for example, there are 3 nodes (intersections) in a city area: V = {A, B, C}, and there are 2 types of rescue vehicles: K = {1, 2}. It is found that the total number of vehicles in the database is as follows:

[0063] The total number of vehicle type 1 is 3.

[0064] The total number of vehicle type 2 is 2.

[0065] Now, it is determined whether the total number of vehicle type constraints is satisfied. For example, the output of the first preset algorithm is:

[0066] =1, =0, =1, =0;

[0067] =0, =1, =1, =0;

[0068] Check if the constraint condition is satisfied:

[0069] (satisfied);

[0070] (satisfied);

[0071] In the above example, the total number of two types of vehicles is satisfied. This ensures that the total number of each type of rescue vehicle does not exceed the available number of vehicles, thereby avoiding over-scheduling and wasting resources.

[0072] In the above manner, the total number of vehicle types satisfies the constraints, ensuring that the dispatch of rescue vehicles meets the rescue needs while considering the limitations of available resources, improving rescue efficiency and resource utilization efficiency.

[0073] In one embodiment, the objective function of the second preset algorithm is:

[0074] ;

[0075] , , , ;

[0076] wherein, is the weight of path P; is the path set; is the path selection.

[0077] In an exemplary embodiment, the objective function of the second preset algorithm is an optimization problem for determining the best driving path of an emergency rescue vehicle from a starting location to a destination. This objective function considers all possible paths and tries to find a path with the smallest total weight, where the weight can be the length of the path, the driving time or any other relevant cost indicator. The following examples are explained in conjunction with the objective function:

[0078] For example, there is a simple rescue scenario with two nodes (departure location A and destination B), and two types of rescue vehicles (type 1 and type 2). There are two possible paths P1 and P2 from A to B.

[0079] The weight of path P1 is = 5 (for example, this can represent the length or travel time of the path).

[0080] The weight of path P2 is = 7.

[0081] For example, the following values are calculated for the decision variables:

[0082] , which means that a vehicle of type 1 chooses path P1 from node A to node B.

[0083] , which means that a vehicle of type 2 chooses path P2 from node A to node B.

[0084] According to the objective function, it is desired to minimize the total weight, so the algorithm will choose the path with the smallest weight. In this example, for a vehicle of type 1, path P1 is chosen because it has a smaller weight than path P2. For a vehicle of type 2, path P2 is chosen because it is the only option for that type of vehicle (for example ).

[0085] Therefore, the objective function of the second pre-set algorithm selects the best path for each type of rescue vehicle from the departure location to the destination by considering all possible paths and their weights. This approach ensures that the rescue vehicles can choose the optimal driving path according to the current traffic and weather conditions, thereby improving rescue efficiency.

[0086] In one implementation, the path selection satisfies the constraint:

[0087] , , .

[0088] In an exemplary implementation, the constraint that the path selection satisfies is to ensure that in the emergency rescue vehicle route planning method, the path selection and scheduling decisions for each type of vehicle from each departure location to each destination are consistent. This constraint ensures that once it is decided to dispatch a vehicle of a certain type from node to node , one or more paths P are selected for that vehicle.

[0089] For example, in a simple rescue scenario, there are 3 nodes: V = {A, B, C}, and 2 types of rescue vehicles: K = {1, 2}. There are 2 possible paths from node A to node B, for example: = {P1, P2}.

[0090] For example, the output of the first preset algorithm is:

[0091] = 1, indicating that a type 1 vehicle is decided to be dispatched from node A to node B.

[0092] = 0, indicating that a type 2 vehicle is not dispatched from node A to node B.

[0093] Now, it is necessary to ensure that the path selection meets the constraints. For the path selection of a type 1 vehicle from node A to node B, there are:

[0094] , indicating that path P1 is selected.

[0095] , indicating that path P2 is not selected.

[0096] According to the constraint condition, it is checked that:

[0097] ;

[0098] This equation holds, indicating that the path selection of a type 1 vehicle from node A to node B is consistent with the scheduling decision. That is, since it is decided to dispatch this type of vehicle, a path is selected for it (in this example, path P1).

[0099] In this way, the path selection that meets the constraints ensures that the scheduling decision of the rescue vehicle matches the actual path selection, so that the rescue vehicle can effectively perform the rescue task according to the predetermined plan and path. This method improves the accuracy and reliability of the rescue route planning, ensuring the rational use of rescue resources and the timely completion of rescue tasks.

[0100] In an embodiment, the method further comprises:

[0101] obtaining real-time traffic information and real-time weather information, and adjusting the weights of paths P based on a third preset algorithm ;

[0102] wherein the real-time traffic information is obtained based on a real-time traffic monitoring system, and the real-time weather information is obtained based on a geographic information system.

[0103] In an exemplary embodiment, this step involves obtaining real-time traffic information and real-time weather information, and adjusting the weights of paths using a third preset algorithm based on these information The purpose of this process is to dynamically adjust path selection to cope with real-time traffic and weather changes, thereby optimizing the driving path of the rescue vehicle.

[0104] For example, an emergency rescue vehicle needs to perform a rescue mission from node A to node B, and there are two paths P1 and P2 to choose from.

[0105] First, real-time traffic information is obtained:

[0106] For example, through a real-time traffic monitoring system, it is obtained that path P1 is currently experiencing traffic congestion, while path P2 has smooth traffic flow.

[0107] Among them, the data provided by the traffic monitoring system includes the traffic volume, speed, accident reports, etc. of each road section.

[0108] At the same time, real-time weather information is obtained:

[0109] For example, using a geographic information system (GIS), it is obtained that the area of path P1 is currently experiencing heavy rain, while the area of path P2 is sunny.

[0110] Among them, these weather information may include rainfall, visibility, road surface slipperiness, etc.

[0111] Then adjust the path weight :

[0112] According to the real-time traffic and weather information, the weights of paths P1 and P2 are adjusted based on a third preset algorithm.

[0113] For example, if path P1 is slow due to traffic congestion and bad weather, its weight will be increased to reflect its lower priority.

[0114] On the contrary, the weight of path P2 will remain low because it is a better choice.

[0115] By dynamically adjusting the path weight, the rescue vehicle will be guided to choose path P2 from node A to node B, thereby avoiding the impact of traffic congestion and bad weather.

[0116] This method can significantly improve the efficiency of rescue and ensure that the rescue vehicle reaches the destination quickly and safely.

[0117] In addition, this method also improves the adaptability and accuracy of route planning, as it can respond to changes in traffic and weather conditions in real time.

[0118] This approach not only optimizes the driving routes of rescue vehicles but also enhances the flexibility and effectiveness of emergency rescue vehicle route planning methods, enabling them to fully adapt to changing rescue environments.

[0119] In one implementation, the third preset algorithm is:

[0120] ;

[0121] in, is the basic weight of path P; T is the traffic congestion coefficient; W is the weather impact coefficient; , To adjust the coefficients, the influence of traffic and weather on the path weights is controlled separately. The extent of the impact.

[0122] In one exemplary implementation, the third preset algorithm is for dynamically adjusting path weights. This algorithm optimizes emergency rescue vehicle routes by adjusting path weights to reflect current traffic congestion and weather conditions, thus taking into account real-time traffic and weather changes.

[0123] For example, there are two paths P1 and P2 from node A to node B, with their base weights being respectively... and .

[0124] The real-time traffic monitoring system provides information indicating that route P1 is currently experiencing moderate traffic congestion, with a traffic congestion coefficient of [missing information]. Traffic flow is smooth along route P2, with a low traffic congestion rate. .

[0125] The Geographic Information System provides information indicating that path P1 will pass through a rainstorm area, and the weather impact factor is [not specified]. The weather conditions along route P2 are good, and the weather impact coefficient is low. .

[0126] For example, adjustment coefficient and .

[0127] According to the third preset algorithm, the adjusted weights of the two paths can be calculated:

[0128] =11.9;

[0129] =12;

[0130] In the above example, the weight of path P1 is adjusted to 11.9, while the weight of path P2 remains at 12. Although the base weight of path P1 is lower, due to the adverse effects of traffic and weather, its adjusted weight is higher, which will lead the path selection model to prefer path P2 as the driving path of the rescue vehicle.

[0131] In this way, the third preset algorithm can dynamically adjust the path weight to adapt to real-time traffic and weather changes, thereby improving the adaptability and accuracy of the rescue route planning. This method can ensure that the rescue vehicle selects the optimal path and quickly and safely reaches the destination, improving the efficiency of rescue.

[0132] In summary, the present application effectively solves the problem of low rescue efficiency in related technologies by using an innovative emergency rescue vehicle rescue route planning method, and significantly improves the effect of rapid rescue. The key features of the present application and their contribution to improving rescue efficiency are as follows:

[0133] 1. Comprehensive cost consideration:

[0134] The objective function of the first preset algorithm considers the fixed cost, capacity cost and time cost, not only focusing on the path length, but also focusing on the reasonable allocation of resources and the urgency of rescue tasks, providing more comprehensive scheduling decisions.

[0135] 2. Real-time data integration:

[0136] The second preset algorithm dynamically adjusts the path weight by integrating real-time traffic and weather information, so that the path planning can adapt to the current actual road conditions and select the best driving path, improving the timeliness and accuracy of rescue.

[0137] 3. Multi-dimensional decision and constraint:

[0138] The rescue demand satisfaction constraint ensures that the number of rescue vehicles dispatched from each starting point to each destination can meet the predetermined rescue demand, and the total number of vehicle types satisfies the constraint to avoid excessive scheduling and resource waste.

[0139] 4. Intelligent scheduling:

[0140] By automatically extracting keywords from the voice information of the rescue call and matching with historical accident data, the present application can quickly determine the type and severity of the accident, thereby determining the basic rescue demand, reducing human judgment and speeding up the scheduling of rescue resources.

[0141] 5. Dynamic path adjustment:

[0142] The third preset algorithm dynamically adjusts the path weight by considering real-time traffic and weather conditions, optimizing the driving path of the rescue vehicle and improving the efficiency of rescue.

[0143] 6. Overall optimization:

[0144] The embodiment of the present application not only optimizes the scheduling of the rescue vehicle, but also dynamically adjusts the path selection through the integration of real-time data, to ensure that the rescue vehicle can quickly and accurately reach the rescue site.

[0145] Through the above features, the scheme of the present application overcomes the single dimension optimization problem in the background art, and provides a more comprehensive and flexible emergency rescue vehicle route planning solution. This method not only improves the rescue efficiency, but also ensures the timeliness and effectiveness of the rescue task, so that the rescue vehicle can quickly and safely reach the destination, improving the utilization efficiency of rescue resources and the overall effect of rescue operations.

[0146] Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by adding the necessary general hardware platform through software, of course, it can also be realized through hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes a plurality of instructions for making a terminal device (which can be a mobile phone, computer, server, or network device, etc.) execute the method described in each embodiment of the present application.

[0147] The embodiment of the present application also provides a rescue route planning system for an emergency rescue vehicle, which is used to realize the above embodiments and preferred embodiments, which have been described. The term "module" as used below can be a combination of software and / or hardware that realizes a predetermined function. Although the devices described in the following embodiments are preferably realized in software, hardware or a combination of software and hardware is also possible and is contemplated.

[0148] Figure 3 is a structural schematic diagram of the rescue route planning system for an emergency rescue vehicle according to the embodiment of the present application, as shown in Figure 3 The system comprises:

[0149] The scheduling model 31 is used to obtain target data, obtain first output data based on a first preset algorithm, and determine a target vehicle, a departure location and a destination based on the first output data; wherein the target data comprises a node set, a vehicle type set, a fixed cost, a capacity cost and a time cost; the departure location is a current residence location of the target vehicle, and the destination is a destination to be rescued;

[0150] The path selection model 32 is configured to obtain the first output data, real-time traffic information, real-time weather information, obtain second output data based on a second preset algorithm, and determine a best driving path of the target vehicle from the starting location to the destination based on the second output data.

[0151] By using the above technical solution, through the double-layer planning model (combination of the scheduling model and the path selection model), the scheduling cost and time cost of the rescue vehicle are considered, and the path selection is dynamically adjusted through integration of real-time data, so that the rescue vehicle can quickly and accurately reach the rescue site. This method overcomes the single-dimensional optimization problem in the background technology, provides a more comprehensive and flexible emergency rescue vehicle route planning solution, effectively improves the rescue efficiency, and ensures the timeliness and effectiveness of the rescue task.

[0152] In an embodiment, the objective function of the first preset algorithm is:

[0153] ;

[0154] ;

[0155] wherein, is a node set, representing all possible nodes in the map; is a vehicle type set; is a fixed cost; is a capacity cost; is a time cost; is a type of the target vehicle; is a starting location; is a destination; is a rescue demand; is a total number of vehicle types; is a decision variable, representing whether a vehicle type is dispatched from a node to a node , in the case of , it is determined that the vehicle type is dispatched from the node to the node .

[0156] In an embodiment, the rescue demand satisfaction constraint is:

[0157] ≥ , for all ∈ ;

[0158] wherein, is a basic rescue demand, representing from a node to a node The minimum number of required rescue vehicles is determined based on the type and severity of the accident.

[0159] In an embodiment, the basic rescue demand is determined based on the type and severity of the accident, comprising:

[0160] Obtaining keywords based on the voice information of the rescue call;

[0161] Matching the keywords with stored historical accident data and historical rescue response situations to obtain a matching result to determine the type and severity of the accident;

[0162] Determining the basic rescue demand based on the matching result.

[0163] In an embodiment, the total number of vehicle types satisfies the constraint:

[0164] The total number of vehicle types for all .

[0165] In an embodiment, the objective function of the second preset algorithm is:

[0166] ;

[0167] , , , ;

[0168] wherein, is the weight of the path P; is the path set; is the path selection.

[0169] In an embodiment, the path selection satisfies the constraint:

[0170] , , .

[0171] In an embodiment, the system is further used for comprising:

[0172] Obtaining real-time traffic information and real-time weather information, and adjusting the weight of the path P based on a third preset algorithm ;

[0173] wherein, the real-time traffic information is obtained based on a real-time traffic monitoring system, and the real-time weather information is obtained based on a geographic information system.

[0174] In an embodiment, the third preset algorithm is:

[0175] ;

[0176] wherein, is the basic weight of path P; T is the traffic congestion coefficient; W is the weather influence coefficient; 、 is the adjustment coefficient, respectively controlling the influence degree of traffic and weather on the path weight .

[0177] It should be noted that the above various modules can be realized by software or hardware, and for the latter, the following implementation manners can be used, but are not limited thereto: the above modules are located in the same processor; or the above various modules are located in different processors in any combination.

[0178] Embodiments of the present application also provide a computer readable storage medium, which stores a computer program, wherein the computer program is configured to execute the steps in any of the method embodiments described above when running.

[0179] In an exemplary embodiment, the above computer readable storage medium can include, but is not limited to: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store computer programs.

[0180] Embodiments of the present application also provide an electronic device, which comprises a memory and a processor, the memory stores a computer program, and the processor is configured to execute the computer program to perform the steps in any of the method embodiments described above.

[0181] In an exemplary embodiment, the above electronic device can further comprise a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0182] Embodiments of the present application also provide a computer program product, which comprises computer instructions, and the computer instructions are executed by a processor to realize the steps of the method described in various embodiments of the present application.

[0183] The specific examples in the present embodiment can refer to the examples described in the above embodiments and exemplary implementation manners, and the present embodiment will not be described here again.

[0184] It should be apparent to those skilled in the art that the modules or steps of the application described above can be implemented with general computing devices, which can be centralized on a single computing device or distributed on a network of multiple computing devices, which can be implemented with program codes executable by the computing devices, so that they can be stored in storage devices and executed by the computing devices, and in some cases, the steps shown or described can be executed in different orders than shown, or made into individual integrated circuit modules, or made into a single integrated circuit module. Thus, the application is not limited to any particular combination of hardware and software.

[0185] The preferred embodiments of the application described above are intended to be merely exemplary and those skilled in the art will readily suggest modifications and variations to the specific embodiments disclosed without departing from the principles of the application. Any and all such modifications and variations are intended to be included herein within the scope of the present application.

Claims

1. A method for planning rescue routes for emergency rescue vehicles, characterized in that, include: The system acquires target data and obtains first output data based on a first preset algorithm. The target vehicle, departure point, and destination are then determined based on the first output data. The target data includes: a set of nodes, a set of vehicle types, fixed costs, capacity costs, and time costs. The departure point is the current location of the target vehicle, and the destination is the location awaiting rescue. The set of nodes includes: landmark buildings, intersections, tunnels, construction sites, and temporary control areas within the city. The fixed costs include: vehicle usage fees, fuel costs, and vehicle wear and tear costs. The capacity costs include: vehicle load capacity, passenger capacity, and the need for special equipment. The time costs include: vehicle operating costs, personnel wages, and additional costs incurred due to delayed rescue. The system acquires the first output data, real-time traffic information, and real-time weather information, and obtains the second output data based on the second preset algorithm, so as to determine the optimal driving route for the target vehicle from the starting point to the destination based on the second output data. Also includes: Obtain real-time traffic and weather information, and adjust the weight of path P based on a third preset algorithm. The optimal driving route is the best one among the routes P. The real-time traffic information is obtained based on a real-time traffic monitoring system, and the real-time weather information is obtained based on a geographic information system. Also includes: Keyword extraction based on voice information from emergency calls; The keywords are matched with stored historical accident data and historical rescue response information to obtain matching results, thereby determining the type and severity of the accident; Based on the matching results, basic rescue needs are determined; The objective function of the first preset algorithm is: ； ; in, Let be the set of nodes, representing all possible nodes in the map; A set of vehicle types; For fixed costs; Cost of capacity; For time cost; The type of the target vehicle; The departure point; For destination; For rescue needs; This represents the total number of vehicle types. For decision variables, indicating whether to include vehicle type From node Sent to node ,exist In this case, determine the vehicle type From node Sent to node ; The rescue request meets the following constraints: ≥ ,∀ ∈ ； in, Based on basic rescue needs, indicating from the node To the node The minimum number of rescue vehicles required is determined based on the type and severity of the accident; The total number of vehicle types satisfies the following constraint: Vehicle type The total number, ∀ ; The objective function of the second preset algorithm is: ； ， ， ， ； in, Let P be the weight of the path. A set of paths; Select a route; The third preset algorithm is: ； in, is the basic weight of path P; T is the traffic congestion coefficient; W is the weather impact coefficient; , To adjust the coefficients, the influence of traffic and weather on the path weights is controlled separately. The degree of impact; The path selection satisfies the following constraints: ， ， 。 2. A rescue route planning system for an emergency rescue vehicle, characterized in that, include: A scheduling model is used to acquire target data, obtain first output data based on a first preset algorithm, and determine the target vehicle, departure point, and destination based on the first output data. The target data includes: a set of nodes, a set of vehicle types, fixed costs, capacity costs, and time costs. The departure point is the current location of the target vehicle, and the destination is the destination awaiting rescue. The set of nodes includes: landmark buildings, intersections, tunnels, construction sites, and temporary control areas within the city. The fixed costs include: vehicle usage fees, fuel costs, and vehicle wear and tear costs. The capacity costs include: vehicle load capacity, passenger capacity, or special equipment requirements. The time costs include: vehicle operating costs, personnel wages, and additional costs incurred due to delayed rescue. A path selection model is used to acquire the first output data, real-time traffic information, and real-time weather information, and to obtain second output data based on a second preset algorithm, so as to determine the optimal driving route for the target vehicle from the starting point to the destination based on the second output data; and to acquire real-time traffic information and real-time weather information, and to adjust the weight of path P based on a third preset algorithm. The optimal driving route is the best one among the routes P; the real-time traffic information is obtained based on a real-time traffic monitoring system, and the real-time weather information is obtained based on a geographic information system; and keywords are obtained from voice information based on emergency calls; the keywords are matched with stored historical accident data and historical emergency response information to obtain matching results, so as to determine the type and severity of the accident; and basic emergency needs are determined based on the matching results. The objective function of the first preset algorithm is: ； ; in, Let be the set of nodes, representing all possible nodes in the map; A set of vehicle types; For fixed costs; Cost of capacity; For time cost; The type of the target vehicle; The departure point; For destination; For rescue needs; This represents the total number of vehicle types. For decision variables, indicating whether to include vehicle type From node Sent to node ,exist In this case, determine the vehicle type From node Sent to node ; The rescue request meets the following constraints: ≥ ,∀ ∈ ； in, Based on basic rescue needs, indicating from the node To the node The minimum number of rescue vehicles required is determined based on the type and severity of the accident; The total number of vehicle types satisfies the following constraint: Vehicle type The total number, ∀ ; The objective function of the second preset algorithm is: ； ， ， ， ； in, Let P be the weight of the path. A set of paths; Select a route; The third preset algorithm is: ； in, is the basic weight of path P; T is the traffic congestion coefficient; W is the weather impact coefficient; , To adjust the coefficients, the influence of traffic and weather on the path weights is controlled separately. The degree of impact; The path selection satisfies the following constraints: ， ， 。

Images