A rescue aircraft path optimization scheduling system and method

Abstract

The application relates to the technical field of rescue aircrafts, and discloses a rescue aircraft path optimization scheduling system and method, which comprises the following steps: a cloud platform receives rescue task information and state information of a plurality of rescue aircrafts; according to the rescue task information and the state information, the cloud platform dynamically allocates tasks to the rescue aircrafts to obtain a rescue aircraft scheduling strategy; and according to the rescue aircraft scheduling strategy, the rescue paths of each rescue aircraft performing corresponding rescue tasks are optimized, the rescue aircrafts travel according to the optimized rescue paths, and the path optimization scheduling of the rescue aircrafts is realized. Based on the cloud platform, the rescue task is accurately matched with the corresponding rescue aircraft, the corresponding subtask network and the aircraft network are combined, the corresponding rescue task can be accurately performed, the path of the aircraft is optimized in real time, the complex and changeable situation of a rescue site can be adapted, and the success rate of the rescue task is improved.

Description

Technical Field

[0001] This invention relates to the field of rescue aircraft technology, and in particular to a rescue aircraft path optimization scheduling system and method. Background Technology

[0002] Current methods for dispatching rescue aircraft cannot achieve dynamic dispatching, making it difficult to adapt to the complex and ever-changing conditions at rescue sites, resulting in untimely rescues. In the dispatching of multiple rescue aircraft, there is a lack of centralized management and information sharing, which prevents the aircraft from achieving good collaboration during the dispatching process. When planning the path for rescue aircraft, a single path planning method is used, which cannot plan the optimal rescue path.

[0003] For example, Chinese Patent No. CN118778683B discloses a portable unmanned aerial vehicle (UAV) emergency rescue management system, including: a medical information interaction terminal for rescue personnel to send and input location information, demand information, and work status information; a task center processing terminal for inputting and dispatching corresponding exploration and scheduling tasks; a UAV execution terminal for collecting relevant information from the ground based on an information acquisition module; a base station transmission module to ensure communication signal transmission; and a flight execution module to control the UAV execution terminal to fly. This system enables exploration tasks to re-plan routes and adjust the locations of people gathered in the explored ground and disaster area based on relevant information, and enables scheduling tasks to re-plan routes and adjust routes based on location information, demand information, and work status information to understand the distribution of medical personnel. This ensures timely information exchange between the disaster area and the command center, provides data support for rescue mobilization, and improves rescue efficiency.

[0004] The existing technologies described above have the problems mentioned in this background: they cannot achieve dynamic scheduling, making it difficult to adapt to the complex and ever-changing conditions at the rescue site, resulting in untimely rescues; during the scheduling of multiple rescue aircraft, there is a lack of centralized management and information sharing, causing the aircraft to fail to achieve good collaboration during the scheduling process; when planning the path for rescue aircraft, a single path planning method is used, which cannot plan the optimal rescue path; in order to solve at least one of the above problems, this application proposes a rescue aircraft path optimization scheduling system and method. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the main objective of this application is to provide a rescue aircraft path optimization and scheduling system and method, which can effectively solve the problems in the background technology. The specific technical solution of this invention is as follows:

[0006] A method for optimizing the scheduling of rescue aircraft routes includes:

[0007] The cloud platform receives rescue mission information and status information from multiple rescue aircraft;

[0008] Based on the rescue mission information and status information, the cloud platform dynamically allocates tasks to the rescue aircraft to obtain a rescue aircraft scheduling strategy. The dynamic task allocation includes switching the rescue missions performed by the rescue aircraft.

[0009] According to the rescue aircraft scheduling strategy, the rescue path for each rescue aircraft to perform the corresponding rescue mission is optimized so that the rescue aircraft travels along the optimized rescue path, thereby achieving optimized scheduling of rescue aircraft paths.

[0010] Specifically, based on the rescue mission information and status information, the cloud platform dynamically allocates tasks to the rescue aircraft to obtain a rescue aircraft scheduling strategy. The dynamic task allocation includes switching the rescue missions performed by the rescue aircraft, including:

[0011] The cloud platform assigns tasks to rescue aircraft based on rescue mission information, thus obtaining an initial scheduling strategy;

[0012] By combining the status information of the rescue aircraft to switch the rescue mission performed by the rescue aircraft, the initial scheduling strategy is optimized to obtain the rescue aircraft scheduling strategy.

[0013] Specifically, the cloud platform allocates tasks to rescue aircraft based on rescue mission information to obtain an initial scheduling strategy, including:

[0014] Based on the rescue mission information, the priority of the rescue mission is calculated to obtain the mission priority;

[0015] Based on the task priorities from high to low, a two-way matching process is performed between rescue tasks and rescue aircraft to achieve task allocation for rescue aircraft and obtain an initial scheduling strategy.

[0016] Specifically, the step of calculating the priority of rescue missions based on rescue mission information to obtain mission priorities includes:

[0017] Obtain the corresponding priority influencing factors from the rescue mission information;

[0018] According to the preset influencing factor scoring rules, the priority influencing factors are scored to obtain the influencing factor values;

[0019] The weights of the priority influencing factors are initialized using preset expert scoring rules to obtain initial factor weights.

[0020] Based on real-time information from the rescue site, the initial factor weights are optimized using a preset weight optimization model to obtain optimized factor weights.

[0021] Based on the weights of the optimization factors and the corresponding influencing factor values, the priority of each rescue mission is calculated, thus obtaining the mission priority.

[0022] Specifically, the initial scheduling strategy involves bidirectional matching of rescue missions and rescue aircraft based on their priority from high to low, to achieve mission allocation for the rescue aircraft. This includes:

[0023] Extract information related to mission attributes from rescue mission information and establish a mission attribute information database;

[0024] Extract information related to the attributes of the rescue aircraft from its status information and establish an aircraft attribute information database;

[0025] Based on the task priority from high to low, rescue aircraft that meet the corresponding task attributes in the aircraft attribute information database are selected to obtain an aircraft set.

[0026] The initial scheduling strategy is obtained when all rescue missions are matched with the corresponding set of aircraft.

[0027] Specifically, the initial scheduling strategy is optimized by combining the status information of the rescue aircraft to switch the rescue mission performed by the rescue aircraft, resulting in a rescue aircraft scheduling strategy, including:

[0028] Analyze the information for each rescue mission to obtain the corresponding rescue mission requirements;

[0029] The rescue scenario is divided into multiple rescue zones by using a pre-defined regional division model;

[0030] Based on the rescue mission requirements and the rescue area, the aircraft are grouped, with each group responsible for different rescue missions, resulting in multiple aircraft combinations. For fire rescue scenarios, the rescue missions include patrol missions, water spraying missions, search and rescue missions, and support missions.

[0031] Based on the patrol information obtained by the aircraft group responsible for patrol missions, the aircraft group responsible for non-patrol missions will go to the corresponding rescue area to complete the corresponding rescue mission.

[0032] Once a rescue aircraft completes its assigned rescue mission, it combines the aircraft's status information with the mission information to switch to a different mission, prioritizing joining the highest priority group. This process is repeated until all rescue missions are completed.

[0033] Specifically, the step of optimizing the rescue path for each rescue aircraft to perform its corresponding rescue mission according to the rescue aircraft scheduling strategy, so as to enable the rescue aircraft to travel along the optimized rescue path and achieve optimized scheduling of rescue aircraft paths, includes:

[0034] For each rescue mission, path planning is performed on each rescue aircraft in the aircraft combination responsible for performing the corresponding rescue mission to obtain the initial rescue path;

[0035] Based on the real-time status of the rescue aircraft and information on aerial obstacles, the initial rescue path is optimized to obtain an optimized rescue path;

[0036] Based on the optimized rescue path, the rescue aircraft is controlled to fly along the corresponding optimized rescue path and perform the corresponding rescue mission, so as to achieve optimized scheduling of the rescue aircraft path.

[0037] Specifically, for each rescue mission, path planning is performed on each rescue aircraft in the aircraft assembly responsible for performing the corresponding rescue mission to obtain an initial rescue path, including:

[0038] The rescue mission is broken down based on the rescue mission information, resulting in multiple sub-missions;

[0039] The execution order and coordination relationship of the multiple sub-tasks are analyzed to construct a sub-task network;

[0040] Based on the sub-task network and the sub-tasks undertaken by the rescue aircraft, an aircraft network is constructed, wherein each rescue aircraft is responsible for at least one sub-task.

[0041] Based on the aircraft network and in accordance with the execution sequence, the flight path and speed of each rescue aircraft are planned using a preset path planning model to obtain the initial rescue path.

[0042] Specifically, the optimization of the initial rescue path based on the real-time status of the rescue aircraft and information on aerial obstacles results in an optimized rescue path, including:

[0043] Based on the sensors carried by the rescue aircraft, image information is acquired during the flight process;

[0044] The cloud platform identifies the locations of aerial obstacles and people to be rescued based on the received image information, thus obtaining the locations of the obstacles and the people to be rescued.

[0045] By combining the location of the obstacle, the location to be rescued, and the real-time status of the rescue aircraft, a route to the location to be rescued is planned first through a preset path optimization model, and the initial rescue path is optimized to obtain an optimized rescue path.

[0046] A rescue aircraft path optimization scheduling system, used to implement the aforementioned rescue aircraft path optimization scheduling method, includes:

[0047] The cloud platform information acquisition module receives rescue mission information and status information from multiple rescue aircraft.

[0048] The rescue aircraft scheduling module, based on the rescue mission information and status information, dynamically allocates tasks to the rescue aircraft through the cloud platform to obtain a rescue aircraft scheduling strategy. The dynamic task allocation includes switching the rescue missions performed by the rescue aircraft.

[0049] The rescue aircraft path optimization module optimizes the rescue path for each rescue aircraft to perform its corresponding rescue mission according to the rescue aircraft scheduling strategy, so that the rescue aircraft travels along the optimized rescue path, thereby achieving path optimization scheduling of the rescue aircraft.

[0050] Compared with the prior art, this application has the following beneficial effects:

[0051] This application leverages a cloud platform to precisely match rescue missions with corresponding rescue aircraft. By combining sub-mission networks and aircraft networks, it can accurately execute rescue missions, optimize the paths of rescue aircraft in real time, adapt to the complex and ever-changing conditions at rescue sites, and improve the success rate of rescue missions. Through precise calculation and dynamic adjustment of rescue mission priorities, combined with the status information of rescue aircraft, it achieves precise allocation of rescue resources. Through sub-mission networks and aircraft networks, it clarifies the execution order and coordination relationships between various rescue missions and rescue aircraft, enhancing the synergy of rescue operations and improving the overall effectiveness of rescue operations. Attached Figure Description

[0052] Figure 1 This is a flowchart illustrating the path optimization and scheduling method for rescue aircraft according to Embodiment 1 of the present invention.

[0053] Figure 2 This is a schematic diagram of the matching process between the rescue mission and the rescue aircraft in Embodiment 1 of the present invention;

[0054] Figure 3 This is a schematic diagram of the initial scheduling strategy optimization process in Embodiment 1 of the present invention;

[0055] Figure 4 This is a flowchart of the initial rescue route planning method in Embodiment 1 of the present invention;

[0056] Figure 5 This is a schematic diagram of the structure of a rescue aircraft path optimization and scheduling system in Embodiment 2 of the present invention. Detailed Implementation

[0057] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0058] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0059] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0060] Example 1:

[0061] This embodiment provides a method for optimizing the scheduling of rescue aircraft routes, such as... Figure 1 The rescue aircraft path optimization scheduling method includes:

[0062] S101, the cloud platform receives rescue mission information and status information of multiple rescue aircraft;

[0063] S102. Based on the rescue mission information and status information, the cloud platform dynamically allocates tasks to the rescue aircraft to obtain a rescue aircraft scheduling strategy, wherein the dynamic task allocation includes switching the rescue missions performed by the rescue aircraft.

[0064] S103. According to the rescue aircraft scheduling strategy, optimize the rescue path for each rescue aircraft to perform the corresponding rescue mission, so that the rescue aircraft travels along the optimized rescue path, thereby realizing the path optimization scheduling of the rescue aircraft.

[0065] This embodiment uses a cloud platform to accurately match rescue missions with corresponding rescue aircraft. It comprehensively considers multiple factors such as mission priority, aircraft performance, real-time status, and flight environment, and makes a comprehensive trade-off in mission allocation and path planning. It optimizes the rescue path of the rescue aircraft in real time. Compared with existing technologies that only consider one or a few factors, the decision-making is more scientific and reasonable, and it can plan better rescue paths, improve rescue efficiency, and overcome the problem that current methods for scheduling and planning rescue aircraft are difficult to cope with the dynamic changes at the rescue site.

[0066] In this embodiment, the scheduling process of rescue aircraft is centrally managed and controlled based on a cloud platform. As the core data hub of the entire rescue system, the cloud platform first acquires information from different data sources. It then establishes a communication bridge between the cloud platform, the rescue command center, and the rescue aircraft through technologies such as 5G and satellite communication. Communication modules are installed on the rescue aircraft to transmit their real-time status information to the cloud platform, which then acquires the real-time status information of each rescue aircraft. Through the rescue mission database, it acquires rescue mission information in real time. After acquiring comprehensive information, the cloud platform can analyze information such as the urgency and distribution range of the rescue missions and match the corresponding rescue aircraft to the appropriate rescue mission based on the aircraft's status.

[0067] Specifically, based on the received rescue mission information and aircraft status information, and taking into account factors such as mission priority, aircraft performance, and resource status, the rescue aircraft are rationally allocated tasks to achieve dynamic scheduling of the rescue aircraft. Rational task allocation can give full play to the advantages of each aircraft, so that the rescue mission can be executed efficiently, the rescue time can be shortened, and the rescue success rate can be improved.

[0068] Specifically, after calculating the dispatch strategy for rescue aircraft, the rescue path is optimized in real time based on the task sequence and coordination among multiple rescue aircraft during the specific execution of the rescue mission, combined with factors such as obstacle avoidance requirements, power consumption, and material transportation during the aircraft's movement. This ensures that the aircraft can complete the rescue mission safely and efficiently. Through real-time obstacle avoidance and collaborative mechanisms, collisions between the aircraft and obstacles or other aircraft are effectively prevented, ensuring the safe movement of the rescue aircraft. The optimized path enables the aircraft to reach the rescue site faster, reducing flight time and resource consumption, and improving the overall efficiency of the rescue operation.

[0069] This application leverages a cloud platform to precisely match rescue missions with corresponding rescue aircraft. By combining sub-mission networks and aircraft networks, it can accurately execute rescue missions, optimize the paths of rescue aircraft in real time, adapt to the complex and ever-changing conditions at rescue sites, and improve the success rate of rescue missions. Through precise calculation and dynamic adjustment of rescue mission priorities, combined with the status information of rescue aircraft, it achieves precise allocation of rescue resources. Through sub-mission networks and aircraft networks, it clarifies the execution order and coordination relationships between various rescue missions and rescue aircraft, enhancing the synergy of rescue operations and improving the overall effectiveness of rescue operations.

[0070] Furthermore, based on the rescue mission information and status information, the cloud platform dynamically allocates tasks to the rescue aircraft to obtain a rescue aircraft scheduling strategy. The dynamic task allocation includes switching the rescue missions performed by the rescue aircraft, including:

[0071] S201, the cloud platform allocates tasks to the rescue aircraft based on the rescue mission information and obtains the initial scheduling strategy;

[0072] S202. Combining the status information of the rescue aircraft, the rescue mission performed by the rescue aircraft is switched, and the initial scheduling strategy is optimized to obtain the rescue aircraft scheduling strategy.

[0073] In this embodiment, the cloud platform analyzes rescue mission information to obtain the characteristics of the rescue mission, such as mission type, location, and urgency. Combined with the attribute information of the rescue aircraft, such as aircraft type, range, and payload capacity, the platform assigns a corresponding rescue aircraft to each rescue mission. Depending on the scope of the rescue mission, multiple rescue aircraft can be assigned to one rescue mission. Through the task allocation of rescue aircraft, a preliminary match between mission and aircraft can be achieved in a short time, providing a basic scheduling plan for the rapid commencement of rescue operations and gaining valuable rescue time. Allocation based on the basic attributes of the mission and the aircraft avoids the blind allocation of rescue aircraft resources and improves the utilization efficiency of rescue resources to a certain extent.

[0074] Specifically, based on the initial scheduling strategy, the minimum number of rescue aircraft required to complete the task is analyzed according to the task requirements of the rescue mission and the real-time status of the rescue aircraft, such as location, battery level, and equipment operating status. The initial scheduling strategy is then optimized. This optimizes the allocation of rescue aircraft resources, avoiding idle or overused resources. It also prevents chaos caused by an excessive number of aircraft, reduces the difficulty of aircraft path planning, improves resource utilization efficiency, and lowers rescue costs. Real-time monitoring of aircraft status and mission changes allows for timely adjustments to the scheduling strategy, effectively responding to emergencies such as aircraft malfunctions and changes in mission requirements, ensuring the smooth progress of the rescue mission.

[0075] Furthermore, the cloud platform allocates tasks to the rescue aircraft based on the rescue mission information to obtain an initial scheduling strategy, including:

[0076] S301. Based on the rescue mission information, calculate the priority of the rescue mission to obtain the mission priority;

[0077] S302. Based on the task priority from high to low, perform bidirectional matching between rescue tasks and rescue aircraft to achieve task allocation for rescue aircraft and obtain an initial scheduling strategy.

[0078] In this embodiment, the cloud platform analyzes rescue mission information and calculates the priority of each rescue mission based on factors such as urgency and timeliness. Different rescue missions differ in terms of urgency, scope of impact, and required resources. By quantitatively analyzing these factors, the priority of each mission can be calculated. After obtaining the mission priority, rescue resources can be allocated to the most urgent missions first, improving the success rate of rescue missions. This ensures that rescue operations are carried out in a scientific and reasonable order, prioritizing the resolution of the most pressing issues and minimizing disaster losses and casualties.

[0079] Specifically, rescue aircraft are assigned according to task priority from high to low, prioritizing those with high priority (i.e., urgent rescue missions) to ensure that urgent rescue missions are executed first. Different rescue aircraft have different performance and resource configurations, and different rescue missions also have their own requirements. Through two-way matching, the rescue capabilities of the aircraft are matched with the rescue requirements of the mission, achieving optimal resource utilization and improving the overall efficiency and success rate of the rescue operation. Two-way matching can also combine mission requirements and aircraft capabilities, making the combination of mission and aircraft more reasonable and improving the targeting and effectiveness of the rescue operation.

[0080] Furthermore, the step of calculating the priority of rescue missions based on rescue mission information to obtain mission priorities includes:

[0081] S401. Obtain the corresponding priority influencing factors from the rescue mission information;

[0082] S402. According to the preset influencing factor scoring rules, the priority influencing factors are scored to obtain the influencing factor values;

[0083] S403. The weights of the priority influencing factors are initialized using preset expert scoring rules to obtain initial factor weights.

[0084] S404. Based on real-time information from the rescue site, the initial factor weights are optimized using a preset weight optimization model to obtain optimized factor weights.

[0085] S405. Based on the weights of the optimization factors and the corresponding influencing factor values, calculate the priority of each rescue mission to obtain the mission priority.

[0086] In this embodiment, firstly, the rescue mission information is analyzed to extract priority influencing factors. Using structured data parsing tools, the following factors are obtained: rescue timeliness (the closer to the golden rescue time, the higher the priority), number of affected people, degree of danger in the disaster area (classified according to disaster type and severity), scarcity of required rescue resources, and mission difficulty (involving complex terrain, special rescue techniques, etc.). Secondly, based on the influencing factor information, the influencing factors are quantified and converted into specific numerical values ​​according to preset influencing factor scoring rules. The extracted priority influencing factor data is then scored against the scoring rule table. This quantitative calculation allows different types of priority influencing factors to be compared and calculated within the same quantitative system.

[0087] For example, regarding the timeliness of rescue, if less than 1 hour remains before the golden rescue time, the score is 10 points; 1-3 hours, the score is 8 points; 3-6 hours, the score is 6 points; and more than 6 hours, the score is 4 points. Regarding the number of people affected, if more than 100 people are affected, the score is 10 points; 50-100 people, the score is 8 points; 10-50 people, the score is 6 points; and less than 10 people, the score is 4 points.

[0088] Specifically, based on the preset expert scoring rules, the degree of influence of each priority factor on the task priority is scored, and the initial weight value of each factor is calculated. The weights of multiple priority factors are initialized to obtain the initial factor weights. Different priority factors have different degrees of influence on the task priority. Determining the initial weight of each factor through the expert scoring rules can reflect the relative importance of each factor in the task priority assessment. Based on their rich rescue experience and professional knowledge, experts comprehensively consider each factor, making the initial weights more reasonable and authoritative.

[0089] Furthermore, based on the real-time changes at the rescue site, the initial factor weights are optimized to adapt to changes in the rescue progress. A pre-set weight optimization model, specifically a neural network model, is used. This model is pre-trained with a large amount of historical data. Real-time information from the rescue site is then input into the pre-trained model to obtain the optimized factor weights. For example, the model calculates that if the fire intensifies, the danger level weight of the affected area increases from 0.2 to 0.3, and other factor weights are adjusted accordingly. This real-time weight optimization makes the assessment of task priorities more realistic, providing rescue commanders with a more scientific and accurate basis for decision-making and improving the success rate of rescue operations.

[0090] Specifically, the optimized factor weights are weighted and summed with the corresponding influencing factor values ​​to calculate the priority of each rescue mission. By combining multiple influencing factors and their weights, the mission priority is calculated, making the determination of priority more scientific and objective, avoiding subjective arbitrariness, helping rescue commanders to make more informed decisions, and improving the efficiency and success rate of rescue operations.

[0091] Furthermore, the initial scheduling strategy involves bidirectional matching of rescue missions and rescue aircraft based on their priority from high to low, to achieve mission allocation for the rescue aircraft. This includes:

[0092] S501. Obtain information related to mission attributes from rescue mission information and establish a mission attribute information database;

[0093] S502. Obtain information related to the attributes of the rescue aircraft from the status information of the rescue aircraft, and establish an aircraft attribute information database;

[0094] S503. Based on the task priority from high to low, select rescue aircraft that meet the corresponding task attributes in the aircraft attribute information database to obtain an aircraft set.

[0095] S504, until all rescue missions are matched with the corresponding set of aircraft, and the initial scheduling strategy is obtained.

[0096] In this embodiment, as Figure 2 Based on the attributes of the rescue mission and the aircraft, a two-way matching process is performed between rescue missions and rescue aircraft, assigning rescue aircraft to corresponding rescue missions. This enables efficient allocation of rescue missions and aircraft, improving the response speed and execution efficiency of rescue operations. First, information related to mission attributes is extracted from the rescue mission information, such as mission type (e.g., fire rescue, earthquake rescue, water rescue), mission location (geographic coordinates or area description), estimated rescue duration, and the type and quantity of required rescue supplies. The extracted mission attribute information is then placed into a mission attribute information database for each rescue mission.

[0097] Secondly, different rescue aircraft have their own unique attributes and capabilities. Information related to the aircraft attributes is extracted from the status information of the rescue aircraft, including performance parameters (speed, range, payload, etc.), equipment carried (life detectors, fire extinguishing devices, medical supplies, etc.), remaining power, fuel quantity, etc. For example, a certain type of aircraft has a maximum payload of 500 kg and carries a life detector. The extracted attribute information of each rescue aircraft is put into the aircraft attribute information database.

[0098] Specifically, based on task priority ranking, suitable aircraft are matched to high-priority rescue missions first, ensuring that the most urgent rescue missions receive a timely response. For each mission, aircraft that meet the mission attribute requirements are selected from the aircraft attribute information database. For example, for a long-distance, large-scale material transportation mission, aircraft with a range greater than the mission distance and a payload capacity that meets the material transportation requirements are selected. The selected aircraft that meet the mission attributes are grouped into a set, and a corresponding aircraft candidate set is established for each rescue mission. By selecting aircraft through attribute matching, aircraft that meet the mission requirements can be found quickly and accurately, avoiding blind matching and improving the efficiency and accuracy of mission allocation.

[0099] Starting with the highest priority task, the aircraft screening and assembly operations in S503 are performed sequentially for each rescue task until all rescue tasks have completed aircraft matching and obtained an initial scheduling strategy, providing clear guidance for the rescue operation and ensuring coordination between various tasks and aircraft.

[0100] Furthermore, by combining the status information of the rescue aircraft to switch the rescue mission performed by the rescue aircraft, the initial scheduling strategy is optimized to obtain a rescue aircraft scheduling strategy, including:

[0101] S601. Analyze the information of each rescue mission to obtain the corresponding rescue mission requirements;

[0102] S602. The rescue scene is divided into multiple rescue areas by using a preset area division model;

[0103] S603. Based on the rescue mission requirements and the rescue area, the aircraft are grouped into groups, with each group of aircraft responsible for different rescue missions, resulting in multiple aircraft combinations. For fire rescue scenarios, the rescue missions include patrol missions, watering missions, search and rescue missions, and support missions.

[0104] S604. Based on the patrol information obtained by the aircraft combination responsible for patrol missions, the aircraft combination responsible for non-patrol missions shall go to the corresponding rescue area to complete the corresponding rescue mission.

[0105] S605. When the rescue mission corresponding to the rescue aircraft is completed, the idle rescue aircraft can switch rescue missions by combining the status information of the rescue aircraft and the rescue mission information, and will be given priority to join the group with the highest mission priority, so as to obtain the rescue aircraft scheduling strategy until all rescue missions are completed.

[0106] In this embodiment, as Figure 3Based on the specific needs of each rescue mission and the rescue site, the initial scheduling strategy is optimized to achieve optimal allocation of rescue resources and improve resource utilization efficiency. The rescue site is divided into areas, and the aircraft are grouped according to the real-time environmental status of each area. Each group performs a corresponding rescue mission. Based on the patrol information from the patrol robots, the cloud platform performs real-time scheduling, assigning corresponding tasks and planning corresponding paths to each group of aircraft. For example, in a fire rescue scenario, rescue missions include patrol missions, water spraying missions, search and rescue missions, and support missions. Clearly defining the actual rescue mission requirements can avoid resource misallocation or waste, ensuring that rescue operations are focused on the core mission and improving rescue effectiveness.

[0107] Specifically, the status of each rescue aircraft in the set of rescue aircraft corresponding to the mission is analyzed to assess the mission execution capability of each aircraft. The rescue mission information is analyzed to extract key elements, obtain specific rescue mission requirements, and clarify the requirements for resources, time, skills, etc., to complete the mission. For fire rescue missions, it is necessary to determine the amount of water needed, the type of aircraft to perform the water spraying mission, and whether there are trapped personnel, etc., based on the scale, location, and fire situation of the fire, in order to arrange the search and rescue mission.

[0108] For example, in a fire rescue scenario, a pre-defined regional division model can be used to divide the overall rescue scenario into multiple rescue areas. Based on factors such as geographical features, mission requirements, and traffic conditions, the rescue scenario can be reasonably divided into multiple smaller areas. This is conducive to formulating targeted rescue missions and allocating aircraft and resources more accurately according to the characteristics and needs of different areas, thereby improving resource utilization efficiency.

[0109] Based on the needs of the rescue mission and the designated rescue areas, the aircraft are grouped according to their status, capabilities, and mission suitability. For fire rescue scenarios, different rescue missions (patrol, water spraying, search and rescue, support) have different requirements for the aircraft. The aircraft are grouped according to the workload and priority of the mission, with each group assigned to a corresponding rescue area to perform the relevant rescue mission. Specifically, aircraft tasked with patrol missions conduct a comprehensive reconnaissance of the rescue area, obtaining crucial information such as the specific details of the fire and the location of personnel. Information can be shared among different groups of aircraft. Other groups of aircraft, based on the patrol information, determine the specific location and execution strategy of the mission. The water spraying group determines the spraying area and path based on the fire source location, and the search and rescue group determines the search area based on personnel distribution. Through cooperation and division of labor among the groups of aircraft, the rescue operation becomes more targeted, avoiding blind actions and improving rescue efficiency. With the support of patrol information, other groups of aircraft can execute their missions more accurately, reducing resource waste and mission errors. This collaborative operation between different groups of aircraft enhances the overall rescue capability.

[0110] Furthermore, once a group of aircraft has completed its assigned rescue mission, the tasks assigned to the aircraft can be adjusted to prevent idle aircraft from affecting resource utilization. Based on the mission completion status and status information of the aircraft, once an aircraft completes its current mission, it is marked as idle and its current status parameters, such as the remaining battery percentage and whether the equipment is functioning properly, are recorded. The remaining rescue missions are evaluated to determine their priorities. Based on the aircraft's status information and mission priorities, it is determined whether an idle aircraft is suitable to join a mission group.

[0111] For example, if an aircraft has low battery power and is not suitable for joining a patrol mission group that requires long-duration flights, it can join a short-duration support mission group. If an idle aircraft is suitable for joining a mission group, it is assigned to that group, and the aircraft's mission information and status are updated. At the same time, the mission group is notified to coordinate and cooperate until all rescue missions are completed. By adjusting the rescue missions of aircraft in real time, the resource utilization rate of aircraft is improved, the idle waste of aircraft after mission completion is avoided, and the flexible adjustment of mission allocation ensures that important missions are executed in a timely manner. This enhances the flexibility and adaptability of rescue operations and enables better response to various changes and emergencies that occur during the rescue process.

[0112] Furthermore, the step of optimizing the rescue path for each rescue aircraft to perform its corresponding rescue mission according to the rescue aircraft scheduling strategy, so that the rescue aircraft travels along the optimized rescue path, to achieve optimized scheduling of rescue aircraft paths, includes:

[0113] S701. For each rescue mission, perform path planning for each rescue aircraft in the aircraft combination responsible for performing the corresponding rescue mission to obtain the initial rescue path.

[0114] S702. Based on the real-time status of the rescue aircraft and information on aerial obstacles, the initial rescue path is optimized to obtain an optimized rescue path;

[0115] S703. According to the optimized rescue path, control the rescue aircraft to fly along the corresponding optimized rescue path and perform the corresponding rescue mission, so as to realize the optimized scheduling of the rescue aircraft path.

[0116] In this embodiment, based on the rescue aircraft scheduling strategy, the rescue missions assigned to each aircraft are obtained. According to the mission target location, the current location of the aircraft, and geographical information, a path planning algorithm is used to plan an initial flight route for each aircraft under the conditions of meeting the mission execution requirements and flight constraints, thus obtaining the initial rescue path. By quickly generating the initial rescue path, the path planning time can be saved, and more time can be gained for the rescue operation.

[0117] Specifically, the initial rescue path is optimized based on the aircraft's real-time status and information on aerial obstacles. This is achieved through real-time monitoring of the aircraft's status (such as battery level, fuel level, and equipment malfunction) and aerial obstacles (such as other aircraft and building debris). For example, when an aerial obstacle is detected ahead, a new path is searched to avoid it based on the obstacle's location and the aircraft's current status. When the aircraft's battery is low, a path is planned to the nearest charging point or alternative landing site. By monitoring the aircraft's status and aerial obstacle information in real time and optimizing the path accordingly, collisions and other safety accidents can be effectively avoided, ensuring that the rescue mission can be carried out safely.

[0118] The cloud platform will optimize rescue route information, including coordinates of points along the route, estimated arrival time at each point, flight speed, and other parameters, and send this information to the corresponding rescue aircraft via a communication link. After receiving the route instructions, the aircraft will control its flight accordingly. During flight, the aircraft will perform rescue tasks as required by the mission, such as dropping supplies and searching for rescue targets. At the same time, the cloud platform will continuously monitor the aircraft's position, status, and mission progress in real time. If any abnormalities are detected, timely measures will be taken to make adjustments. This will enable the aircraft to accurately reach the rescue site along the optimized route and perform the corresponding rescue tasks, improving the accuracy and success rate of rescue operations.

[0119] Furthermore, such as Figure 4For each rescue mission, path planning is performed on each rescue aircraft in the aircraft assembly responsible for performing the corresponding rescue mission to obtain an initial rescue path, including:

[0120] S801. Decompose the rescue mission based on the rescue mission information to obtain multiple sub-tasks;

[0121] S802. Analyze the execution order and coordination relationship of the multiple sub-tasks, and construct a sub-task network;

[0122] S803. Based on the sub-task network and the sub-tasks undertaken by the rescue aircraft, construct an aircraft network, wherein each rescue aircraft is responsible for at least one sub-task.

[0123] S804. Based on the aircraft network and in accordance with the execution sequence, the flight path and speed of each rescue aircraft are planned using a preset path planning model to obtain an initial rescue path.

[0124] In this embodiment, the rescue mission is decomposed into multiple sub-tasks. Initial planning of the aircraft's rescue path is performed based on these sub-tasks, making the rescue mission execution more refined, increasing path planning speed, and thus improving rescue efficiency. First, the rescue mission is decomposed into multiple sub-tasks using a top-down decomposition method, progressively refining the mission according to its logical structure and process. For example, an earthquake rescue mission can be decomposed into sub-tasks such as searching for survivors, establishing rescue channels, and transporting rescue supplies and medical equipment. Key attributes are defined for each sub-task, including its name, objective, estimated time, and required resources. Decomposing complex rescue missions into multiple sub-tasks makes the mission structure clearer, easier to understand and execute, and avoids confusion and omissions during mission execution.

[0125] Specifically, subtasks have sequential and collaborative relationships. By analyzing the conditions and objectives of each subtask, the sequence and dependencies between them can be determined. For example, in fire rescue, the firefighting subtask depends on the fire water supply subtask; only when the fire water supply is sufficient can firefighting operations be carried out. Based on the sequence and dependencies between subtasks, a subtask network is constructed. Through the subtask network, the execution order and coordination between subtasks can be clarified, which helps to optimize the overall process of the rescue mission and improve rescue efficiency.

[0126] Specifically, based on the requirements of the sub-tasks and the functions of the rescue drones, the sub-tasks are assigned to the corresponding rescue robots. After completing the current sub-task, one of the rescue robots can continue to execute the subsequent sub-tasks. According to the sub-task network, the rescue robots that execute the corresponding sub-tasks are constructed into a drone network. Each rescue drone in the drone network executes the corresponding sub-tasks in the order of the network. The drone network can clearly show the collaborative relationship between the rescue robots, which helps them to work together better and improve the overall coordination of the rescue team.

[0127] Furthermore, after constructing the aircraft network and clarifying the execution order of sub-tasks, a pre-defined path planning model is used to plan an initial flight path and speed for each aircraft, taking into account factors such as the aircraft's current position, mission objectives, and flight environment. This enables the aircraft to efficiently and safely execute rescue missions according to the predetermined mission flow. The path planning model adopts the A* model. Based on the input information, the model plans a flight path and speed for each aircraft according to the execution order of sub-tasks, taking into account the obstacle avoidance and coordination requirements between aircraft, to avoid collisions between aircraft and obtain the initial rescue path.

[0128] Furthermore, the initial rescue path is optimized based on the real-time status of the rescue aircraft and information on aerial obstacles to obtain an optimized rescue path, including:

[0129] S901. Based on the sensors carried by the rescue aircraft, acquire image information during the flight process;

[0130] S902: The cloud platform identifies the locations of aerial obstacles and people to be rescued based on the received image information, and obtains the locations of obstacles and people to be rescued.

[0131] S903. Combining the location of the obstacle, the location to be rescued, and the real-time status of the rescue aircraft, a route to the location to be rescued is planned first through a preset path optimization model, and the initial rescue path is optimized to obtain an optimized rescue path.

[0132] In this embodiment, the sensors on the rescue aircraft collect images of the surrounding environment in real time, obtaining image information during the flight process, and send the image information to the cloud platform. The images contain rich details, such as terrain, building distribution, existing aerial obstacles, and signs of people to be rescued. After receiving the image data, the cloud platform first performs image preprocessing, including image denoising to remove interference noise and make the image clearer; enhancing contrast to highlight key information in the image; and using a preset image recognition model to analyze and recognize the image. In this embodiment, the image recognition model is a CNN model, which is trained using a large amount of pre-collected image data containing various aerial obstacles and human features. The pre-trained image recognition model is then input into the pre-trained image recognition model. The model extracts and analyzes image features to identify aerial obstacles and people to be rescued and determine their locations. Through image recognition, the locations of aerial obstacles and people to be rescued can be accurately identified and located, providing key information for path optimization, enabling rescue operations to be carried out more effectively and improving the accuracy and efficiency of rescue.

[0133] Specifically, after determining the locations of obstacles, the location to be rescued, and the real-time status of the aircraft (such as position, speed, and battery level), a preset path optimization model is used. In this embodiment, the path optimization model is the A* model. The primary goal is to reach the location to be rescued as quickly as possible, while also considering the avoidance of obstacles and the performance limitations of the aircraft. The initial rescue path is adjusted and optimized to obtain an optimized rescue path. By avoiding obstacles, collisions during flight are effectively prevented, ensuring flight safety and providing a guarantee for the smooth progress of the rescue mission. Prioritizing the planning of routes to the location to be rescued enables the aircraft to reach the rescue site as quickly as possible, gaining valuable time for the rescue operation and improving rescue efficiency. By comprehensively considering the real-time status of the aircraft and on-site information, the optimal rescue path is quickly planned, reducing rescue time and improving rescue efficiency.

[0134] Example 2:

[0135] In this embodiment, as Figure 5 A rescue aircraft path optimization scheduling system is provided to implement the aforementioned rescue aircraft path optimization scheduling method, comprising:

[0136] The cloud platform information acquisition module receives rescue mission information and status information from multiple rescue aircraft.

[0137] The rescue aircraft scheduling module, based on the rescue mission information and status information, dynamically allocates tasks to the rescue aircraft through the cloud platform to obtain a rescue aircraft scheduling strategy. The dynamic task allocation includes switching the rescue missions performed by the rescue aircraft.

[0138] The rescue aircraft path optimization module optimizes the rescue path for each rescue aircraft to perform its corresponding rescue mission according to the rescue aircraft scheduling strategy, so that the rescue aircraft travels along the optimized rescue path, thereby achieving path optimization scheduling of the rescue aircraft.

[0139] In this embodiment, the cloud platform information acquisition module includes a communication unit, a data acquisition interface unit, and a data preprocessing unit. Through the communication link established by the communication unit, the data acquisition interface unit acquires rescue mission information (such as mission type, location, priority, etc.) and status information of multiple rescue aircraft (such as location, battery level, equipment operating status, etc.) from different data sources. After being processed by the data preprocessing unit, the standardized data is provided to the rescue aircraft scheduling module and the rescue aircraft path optimization module.

[0140] Specifically, the rescue aircraft scheduling module includes a task priority calculation unit, an aircraft attribute database, a task allocation unit, and a strategy optimization unit. Based on the data provided by the cloud platform information acquisition module, the task priority calculation unit determines the task priority, and the task and aircraft are initially matched according to the aircraft attribute database and the task allocation unit to generate an initial scheduling strategy. The strategy optimization unit then optimizes the strategy based on the real-time status of the aircraft, ultimately providing a reasonable scheduling strategy for the rescue aircraft path optimization module, thereby realizing the task allocation and scheduling management of rescue aircraft.

[0141] Specifically, the rescue aircraft path optimization module includes a path planning unit, a real-time information acquisition and processing unit, a path optimization unit, and a path command generation and transmission unit. Based on the scheduling strategy generated by the rescue aircraft scheduling module, the path planning unit plans an initial rescue path for each aircraft. The real-time information acquisition and processing unit obtains the real-time status and flight environment information of the aircraft and inputs it into the path optimization unit to optimize the initial rescue path. Finally, the path command generation and transmission unit sends the optimized path command to the aircraft, thereby realizing the optimized scheduling of the rescue aircraft path and ensuring that the aircraft can safely and efficiently perform rescue missions.

[0142] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for optimizing the scheduling of rescue aircraft routes, characterized in that, include: The cloud platform receives rescue mission information and status information from multiple rescue aircraft; Based on the rescue mission information, the priority of the rescue mission is calculated to obtain the mission priority; Based on the task priorities from high to low, a two-way matching process is performed between rescue tasks and rescue aircraft to achieve task allocation for rescue aircraft and obtain an initial scheduling strategy. By combining the status information of the rescue aircraft to switch the rescue mission performed by the rescue aircraft, the initial scheduling strategy is optimized to obtain the rescue aircraft scheduling strategy; The rescue mission is broken down based on the rescue mission information, resulting in multiple sub-missions; The execution order and coordination relationship of the multiple sub-tasks are analyzed to construct a sub-task network; Based on the sub-task network and the sub-tasks undertaken by the rescue aircraft, an aircraft network is constructed, wherein each rescue aircraft is responsible for at least one sub-task. Based on the aircraft network and in accordance with the execution order, the flight path and speed of each rescue aircraft are planned using a preset path planning model to obtain the initial rescue path; Based on the real-time status of the rescue aircraft and information on aerial obstacles, the initial rescue path is optimized to obtain an optimized rescue path; Based on the optimized rescue path, the rescue aircraft is controlled to fly along the corresponding optimized rescue path and perform the corresponding rescue mission, so as to achieve optimized scheduling of the rescue aircraft path.

2. The method for optimizing the scheduling of rescue aircraft paths according to claim 1, characterized in that, The step of calculating the priority of rescue missions based on rescue mission information to obtain mission priorities includes: Obtain the corresponding priority influencing factors from the rescue mission information; According to the preset influencing factor scoring rules, the priority influencing factors are scored to obtain the influencing factor values; The weights of the priority influencing factors are initialized using preset expert scoring rules to obtain initial factor weights. Based on real-time information from the rescue site, the initial factor weights are optimized using a preset weight optimization model to obtain optimized factor weights. Based on the weights of the optimization factors and the corresponding influencing factor values, the priority of each rescue mission is calculated, thus obtaining the mission priority.

3. The method for optimizing the scheduling of rescue aircraft paths according to claim 1, characterized in that, The initial scheduling strategy is obtained by bidirectionally matching rescue missions and rescue aircraft according to the mission priority from high to low, in order to achieve mission allocation for rescue aircraft. This includes: Extract information related to mission attributes from rescue mission information and establish a mission attribute information database; Extract information related to the attributes of the rescue aircraft from its status information and establish an aircraft attribute information database; Based on the task priority from high to low, rescue aircraft that meet the corresponding task attributes in the aircraft attribute information database are selected to obtain an aircraft set. The initial scheduling strategy is obtained when all rescue missions are matched with the corresponding set of aircraft.

4. The method for optimizing the scheduling of rescue aircraft paths according to claim 1, characterized in that, The rescue mission executed by the rescue aircraft is switched by combining the status information of the rescue aircraft, and the initial scheduling strategy is optimized to obtain a rescue aircraft scheduling strategy, including: Analyze the information for each rescue mission to obtain the corresponding rescue mission requirements; The rescue scenario is divided into multiple rescue zones by using a pre-defined regional division model; Based on the rescue mission requirements and the rescue area, the aircraft are grouped, with each group responsible for different rescue missions, resulting in multiple aircraft combinations. For fire rescue scenarios, the rescue missions include patrol missions, water spraying missions, search and rescue missions, and support missions. Based on the patrol information obtained by the aircraft group responsible for patrol missions, the aircraft group responsible for non-patrol missions will go to the corresponding rescue area to complete the corresponding rescue mission. Once a rescue aircraft completes its assigned rescue mission, it combines the aircraft's status information with the mission information to switch to a different mission, prioritizing joining the highest priority mission group. This process continues until all rescue missions are completed.

5. The method for optimizing the scheduling of rescue aircraft paths according to claim 1, characterized in that, The process of optimizing the initial rescue path based on the real-time status of the rescue aircraft and information on aerial obstacles to obtain an optimized rescue path includes: Based on the sensors carried by the rescue aircraft, image information is obtained during the flight process; The cloud platform identifies the locations of aerial obstacles and people to be rescued based on the received image information, thus obtaining the locations of the obstacles and the people to be rescued. By combining the location of the obstacle, the location to be rescued, and the real-time status of the rescue aircraft, a route to the location to be rescued is planned first through a preset path optimization model, and the initial rescue path is optimized to obtain an optimized rescue path.

6. A rescue aircraft path optimization and scheduling system, characterized in that, A method for optimizing the scheduling of rescue aircraft paths as described in any one of claims 1 to 5, comprising: The cloud platform information acquisition module receives rescue mission information and status information from multiple rescue aircraft. The rescue aircraft scheduling module, based on the rescue mission information and status information, dynamically allocates tasks to the rescue aircraft through the cloud platform to obtain a rescue aircraft scheduling strategy. The dynamic task allocation includes switching the rescue missions performed by the rescue aircraft. The rescue aircraft path optimization module optimizes the rescue path for each rescue aircraft to perform its corresponding rescue mission according to the rescue aircraft scheduling strategy, so that the rescue aircraft travels along the optimized rescue path, thereby achieving path optimization scheduling of the rescue aircraft.

Images