Elevator AED Intelligent Scheduling Method and System, Equipment, Medium in Complex Scenarios

Abstract

The present invention discloses a method and system, device, and medium for intelligent scheduling of elevator AEDs in complex scenarios. The method includes: establishing an AED scheduling and allocation optimization model for a complex multi-elevator system, quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model, finely processing to obtain the optimal solution of the optimization problem based on the AED scheduling and allocation optimization model, and performing AED intelligent scheduling in the complex multi-elevator system; the complex multi-elevator system includes multiple elevator shafts, various types of elevators are selectively configured in each elevator shaft, the elevators are selectively configured to serve different zones, and AED devices are selectively configured in the elevators. After adopting the solution of the present invention, it will be possible to improve the emergency response efficiency in complex scenarios, ensure that patients in urgent need of cardiopulmonary resuscitation can be effectively treated in a timely manner, and enable defibrillation support to be obtained as early as possible after ventricular fibrillation occurs in patients with cardiac arrest, so as to improve the treatment speed and survival rate of patients.

Description

Technical Field

[0001] The present invention relates to the technical fields of elevators and cardiopulmonary resuscitation, and particularly relates to an intelligent scheduling method, system, device, and medium for an elevator AED in a complex scenario. Background Art

[0002] The statements in this part merely provide background technical information related to the present application and do not necessarily constitute prior art.

[0003] In a modern building environment, an elevator, as a vertical transportation means connecting different floors, has a very high usage frequency. However, due to various reasons, such as heart diseases and accidental injuries, first-aid events may occur inside or outside the elevator, especially emergency medical conditions such as cardiac arrest. Cardiac arrest is a sudden and life-threatening condition that requires immediate and effective first-aid measures. Among them, an automated external defibrillator (AED) is one of the most effective first-aid devices. External defibrillation using an AED is an important step in CPR (Cardio Pulmonary Resuscitation). The person using the AED is the AED operator, the person performing CPR is the CPR implementer (hereinafter referred to as the implementer), and the person receiving external defibrillation using the AED is the AED, CPR recipient (hereinafter referred to as the patient).

[0004] In the prior art, an AED is configured in or near the elevator to enable a patient to receive external defibrillation by the AED device in a timely manner when a first-aid event of a patient's cardiac arrest occurs inside or outside the building. However, currently, the acquisition and application of an AED in or near the elevator can only be applied to a simple elevator system. For example, in a simple elevator system, only one or two elevators serve all floors. When an AED (Automated External Defibrillator) needs to be delivered to a certain floor, only these one or two elevators need to be scheduled. The scenario is simple and the scheduling difficulty is small.

[0005] However, for high-rise buildings, there are complex multi-elevator systems. These complex multi-elevator systems usually include multiple elevator shafts and various types of elevators, such as high-speed elevators, low-speed elevators, shuttle elevators, service / freight elevators, etc. High-speed elevators are used to quickly reach high floors and usually have a relatively high speed. Low-speed elevators serve lower floors and have a relatively slow speed. Shuttle elevators are specifically designed to quickly transport passengers from the ground floor or transfer floor to specific intermediate floors or sky lobbies. Service / freight elevators are used to transport goods and service personnel and are sometimes also used for evacuation. For the above complex multi-elevator systems, the service floors, service categories, and operating speeds of various types of elevators are different, and each elevator does not reach all floors and there is a situation of cross-service areas. Therefore, it is no longer possible to use conventional scheduling means to apply to the AED device scheduling under complex multi-elevator systems. As a result, in the complex scenarios of high-rise buildings, there will be problems such as uncertainty about whether the AED device can be delivered, limited coverage, and difficult first aid scheduling in elevator AED scheduling. Thus, it is impossible to perform effective AED external defibrillation rescue for patients in the first place. In order to improve the coverage rate, it may be necessary to increase the number of AED devices, resulting in a relatively high cost.

[0006] In view of this, how to solve the problems such as uncertainty about whether the AED device can be delivered, limited coverage, and difficult first aid scheduling in elevator AED scheduling in the complex scenarios of high-rise buildings has become the subject to be studied and solved by the present invention. Summary of the Invention

[0007] The object of the present invention is to provide a method, system, device, and medium for intelligent scheduling of elevator AEDs in complex scenarios.

[0008] To achieve the above object, the first aspect of the present invention proposes a method for intelligent scheduling of elevator AEDs in complex scenarios, the method comprising:

[0009] Establish an AED scheduling and allocation optimization model under a complex multi-elevator system, summarize the allocation scheme of AED devices and first aid personnel who obtain AED devices under the complex multi-elevator system as an optimization problem, define prior parameters and decision variables for the shortest path arrival in the complex multi-elevator system based on this optimization problem, construct an objective function related to the macro scheduling of AED devices and first aid personnel and constraint conditions related to AED device resource allocation and floor capacity limits for the optimization problem with the prior parameters and decision variables, and establish an AED scheduling and allocation optimization model;

[0010] Based on the AED scheduling and allocation optimization model, quickly screen out the optimal solution direction of the optimization problem. The AED scheduling and allocation optimization model randomly generates one or more groups of candidate solutions. Each individual in the multiple candidate solutions represents an allocation scheme. Substitute the candidate solutions into the macro scheduling objective function to obtain the model results of the optimal decision variables of the corresponding objective function under the prior parameters in the complex multi-elevator system. Quickly screen out the optimal solution direction of the allocation scheme according to the model results, and selectively update the optimization parameters of the current optimal individual according to the optimal solution direction;

[0011] Based on the AED scheduling and allocation optimization model, finely process to obtain the optimal solution of the optimization problem. Conduct fine local optimization according to the optimal solution direction of the allocation scheme to ensure that the allocation scheme in the optimal solution direction meets all the constraint conditions related to the AED device resource configuration and floor capacity limit, and use the current optimal individual for iterative optimization until the maximum number of iterations is reached or the improvement amplitude corresponding to the optimization parameters of the optimal individual is less than the preset amplitude threshold. Output the optimal solution allocation scheme and retain at least one sub-optimal solution allocation scheme;

[0012] Execute AED intelligent scheduling in the complex multi-elevator system, and use the optimal solution allocation scheme to intelligently schedule the AED devices and the first aid personnel who obtain the AED devices. If the optimal solution allocation scheme is interrupted during execution, start the sub-optimal solution allocation scheme.

[0013] The second aspect of the present invention proposes a complex multi-elevator system for the method described in the first aspect. The complex multi-elevator system includes multiple elevator shafts, and various types of elevators are selectively configured in each elevator shaft. The elevators are selectively configured to serve different partitions, and AED devices are selectively configured in the elevators.

[0014] The third aspect of the present invention proposes an elevator AED intelligent scheduling system in a complex scenario. The elevator AED intelligent scheduling system in the complex scenario includes the complex multi-elevator system described in the second aspect of the present invention, and an AED intelligent scheduling system platform for scheduling the complex multi-elevator system, AED devices, and first aid personnel who obtain the AED devices. An AED scheduling and allocation optimization model under the complex multi-elevator system is established in the AED intelligent scheduling system platform. Based on the AED scheduling and allocation optimization model, quickly screen out the optimal solution direction of the optimization problem, finely process to obtain the optimal solution of the optimization problem based on the AED scheduling and allocation optimization model, and execute AED intelligent scheduling in the complex multi-elevator system to respond to first aid events.

[0015] The fourth aspect of the present invention proposes an intelligent AED lifting platform for the method described in the first aspect. The intelligent AED lifting platform device includes an elevator and an AED device configured in the elevator.

[0016] A fifth aspect of the present invention provides a readable storage medium, on which a control program is stored. When the control program is executed by a processor, the processor is caused to execute the steps of the elevator AED intelligent scheduling method in a complex scenario as described in the first aspect.

[0017] The relevant content of the present invention is explained as follows:

[0018] 1. Through the implementation of the above technical solutions of the present invention, aiming at the problems existing in the elevator AED scheduling in the complex scenarios of high-rise buildings, such as the uncertainty of whether the AED device can be delivered, limited coverage, and difficult first-aid scheduling, etc., a complex-scenario elevator AED intelligent scheduling method, a complex multi-elevator system, a complex-scenario elevator AED intelligent scheduling system, an intelligent AED lifting platform device and a readable storage medium are innovatively developed and designed. During the golden first-aid time, in the complex scenarios of high-rise buildings, the first-aid personnel and AED devices are macroscopically regulated to the first-aid scene to balance the elevator AED and the first-aid personnel fetching the AED to reach the target floor fastest with the minimum time (path); in this application, by establishing an AED scheduling and allocation optimization model under a complex multi-elevator system, the allocation scheme of AED devices and first-aid personnel in the complex scenarios under the original complex multi-elevator system is summarized as an optimization problem that can be solved by a mathematical model, thereby establishing a basic condition for the optimization and macroscopic regulation of the allocation scheme. When establishing the AED scheduling and allocation optimization model under a complex multi-elevator system, based on this optimization problem, the prior parameters in the complex multi-elevator system and the decision variables for reaching the shortest path are defined, so that the parameters and variables are scientific, reasonable and highly compatible when the model is established, thereby providing a clear mathematical description; and the prior parameters and decision variables are used to construct an objective function related to the macroscopic scheduling of AED devices and first-aid personnel for the optimization problem and constraint conditions related to AED device resource allocation and floor capacity limitations, so that the application and representation of the optimization problem under this AED scheduling and allocation optimization model are more accurate, which fits the goals corresponding to the elevator AED scheduling process in the actual complex scenarios and the limitations and constraints based on resource limitations, capacity limitations, etc., so that the final establishment of the AED scheduling and allocation optimization model fully takes into account the problems such as the uncertainty of whether the AED device can be delivered, limited coverage, and difficult first-aid scheduling. When performing the step of quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model, different from the general gradient-solving algorithm, in this application, when responding to the start of a first-aid event, the AED scheduling and allocation optimization model randomly generates one or more groups of candidate solutions. Different from the exhaustive solutions, in this application, the candidate solutions are substituted into the macroscopic scheduling objective function to obtain the model results of the optimal decision variables of the corresponding objective function under the prior parameters in the complex multi-elevator system, so as to quickly screen out the optimal solution direction of the allocation scheme, by substituting to simulate the possible large-scale adjustment of limited resources in the whole building, generally quickly finding out possible excellent configuration schemes, avoiding falling into local optima, but when implemented, being affected by other factors and instead not achieving the purpose of reaching the golden time, and after quickly screening out the optimal solution direction of the allocation scheme according to the model results, selectively updating the optimization parameters of the current optimal individual according to the optimal solution direction, so as to provide a more excellent allocation scheme for subsequent fine processing.In the step of obtaining the optimal solution of the optimization problem through fine processing of the AED scheduling and allocation optimization model, local fine optimization is carried out according to the optimal solution direction of the allocation plan to ensure that the allocation plan in the optimal solution direction meets all the constraint conditions related to the AED device resource configuration and floor capacity limit, so as to further perform more refined local optimization within the limited resource constraints, and use the current optimal individual for iterative optimization until the maximum number of iterations is reached or the improvement amplitude corresponding to the optimization parameters of the optimal individual is less than the preset amplitude threshold, so as to quickly obtain the optimal solution allocation plan, improve the emergency response efficiency, give the allocation plan in the shortest possible time, and avoid missing the golden time for first aid. Through the combination of the above two steps of quickly screening the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model and obtaining the optimal solution of the optimization problem through fine processing of the AED scheduling and allocation optimization model, it is possible to quickly screen the optimal solution direction of the optimization problem in a large range of the entire building with limited resources, avoid falling into local optima, and at the same time be able to obtain the optimal solution of the optimization problem through fine processing in the selected optimal solution direction, further optimize the resource allocation, improve the emergency response efficiency, ensure that patients in urgent need of cardiopulmonary resuscitation can be effectively treated in time, and enable defibrillation support to be obtained as early as possible after ventricular fibrillation occurs in patients with cardiac arrest, so as to improve the treatment speed and survival rate of patients.

[0019] 2. In the first aspect of the above technical solution, in the step of establishing the AED scheduling and allocation optimization model under a complex multi - elevator system:

[0020] The prior parameters are parameters set according to the floor partition, elevator partition, AED device layout in the elevator, and personnel flow situation in the complex multi - elevator system;

[0021] The decision variables are variables that enable the shortest path of the first - aid personnel and the elevator AED to reach the desired location within the planning period.

[0022] In this way, the parameters and variables of the AED scheduling and allocation optimization model are made more scientific, reasonable, and highly compatible locally during establishment, so as to provide a more accurate mathematical description and lay a foundation for the optimization problem of the allocation plan in the complex scenario under the complex multi - elevator system.

[0023] 3. In the first aspect of the above technical solution, the prior parameters include:

[0024] I, representing the configuration or location index of the AED device or the first - aid personnel;

[0025] J, representing the floor index in the building;

[0026] M, representing the total number of AED device configuration points;

[0027] N, representing the total number of floors;

[0028] B i , representing the initialization response probability of the AED device and the first aid personnel for the configuration area i within the planned period;

[0029] H i , representing the target response probability of the available AED devices for the configuration area i within the planned period;

[0030] E i , representing the target response probability of the available first aid personnel for the configuration area i within the planned period;

[0031] H j , representing the set of AED devices reaching the target floor for floor j within the planned period;

[0032] E j , representing the set of first aid personnel reaching the target floor for floor j within the planned period;

[0033] L j , representing the set of arrival efficiencies for floor j within the planned period;

[0034] U j , representing the set of efficiencies of AED devices and first aid personnel consumed on floor j;

[0035] M j , representing the set of elevator AED devices that can serve floor j;

[0036] N j , representing the set of elevators that can serve floor j.

[0037] Using such more specific and detailed prior parameters as the parameters set according to floor and elevator zoning, elevator AED layout, and personnel flow conditions makes the application of the AED scheduling and allocation optimization model more efficient and accurate.

[0038] 4. In the first aspect of the above technical solution, the decision variables include:

[0039] C ij , representing the response priority of the elevator set from the configuration point i to the floor j, as a decision variable in the AED scheduling and allocation optimization model;

[0040] W ij , representing the elevator resources allocated from the configuration point i to the floor j, as a decision variable in the AED scheduling and allocation optimization model.

[0041] Using such more specific and detailed decision variables as the variables for the first aid personnel and the elevator AED to reach the desired shortest path within the period makes the application of the AED scheduling and allocation optimization model more efficient and accurate.

[0042] 5. In the first aspect of the above technical solution, in the step of establishing the AED scheduling and allocation optimization model under a complex multi - elevator system, the objective function related to the macro - scheduling of AED devices and first - aid personnel corresponds to a multi - objective optimization problem with three objectives, namely J1, J2, and J3, where:

[0043] J1: Minimize the cumulative response probability of AED and first - aid personnel for the target floor to the maximum extent;

[0044] J2: Minimize the path of the AED elevator to reach the target floor in the floor system to the minimum extent;

[0045] J3: Minimize the path of the first - aid personnel elevator to reach the target floor in the floor system to the minimum extent.

[0046] In this way, in high - rise buildings, the macro - scheduling of AED (Automated External Defibrillator) and first - aid personnel can be regarded as a multi - objective optimization problem with three objectives - J1, J2, and J3. The construction of this optimization problem is scientific and reasonable, which can provide a guarantee for the correctness of the subsequent optimization and implementation of the allocation plan.

[0047] 6. In the first aspect of the above technical solution, in the step of establishing the AED scheduling and allocation optimization model under a complex multi - elevator system, the objective functions are defined as follows:

[0048] J1, within the planned period, maximize the cumulative response probability of AED devices and first - aid personnel for the target floor:

[0049] , aiming to maximize the cumulative response probability of AED and first - aid personnel;

[0050] J2, minimize the path of the AED device elevator to reach the target floor in the floor system to the minimum extent:

[0051] , aiming to minimize the total AED response cost or time and ensure that the AED device can reach the required floor with the optimal path;

[0052] J3, minimize the path of the first - aid personnel elevator to reach the target floor in the floor system to the minimum extent:

[0053] , aiming to minimize the total first - aid personnel response cost or time and ensure that the first - aid personnel can reach the required floor with the optimal path.

[0054] The further refinement and confirmation of the multi-objective optimization problem as described above enable the establishment of an AED scheduling and allocation optimization model in a complex scenario and a complex multi-elevator system. Moreover, with the goal of the fastest time and the lowest risk, it meets the urgency and necessity of obtaining defibrillation support after ventricular fibrillation occurs in patients with cardiac arrest. During the process of defining each formula adopted for the objective function, it further matches the problems and scenarios that need to be solved by the prior parameters and decision variables in each optimization problem, making the expression of the multi-objective optimization problem and the objective function more accurate.

[0055] 7. In the first aspect of the above technical solution, in the step of establishing an AED scheduling and allocation optimization model under a complex multi-elevator system, the constraint conditions related to AED device resource allocation and floor capacity limitation respectively include Constraint One, Constraint Two, and Constraint Three, where:

[0056] Constraint One is the resource limitation of the configuration point. The total amount of resources allocated by the configuration point i to each floor cannot exceed its available total resources: ;

[0057] Constraint Two is the minimum demand capacity limitation and the maximum demand capacity limitation of the floor. The minimum demand capacity limitation is and the maximum demand capacity limitation is ;

[0058] Constraint Three is the non-negativity constraint, where the allocated resource quantity cannot be negative, , and n represents the set of positive integers .

[0059] The establishment and definition of the above constraint conditions further match the resource limitations, capacity limitations, demand limitations, etc. existing in the prior parameters and decision variables in each constraint condition, providing more accurate and reasonable constraints for the establishment of the AED scheduling and allocation optimization model in the state of limited resource allocation, thereby ensuring the smooth implementation of the allocation plan generated when responding to emergency rescue events.

[0060] 8. In the first aspect of the above technical solution, in the step of quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model, the AED scheduling and allocation optimization model randomly generates candidate solutions. The candidate solutions include the response priority C ij of the elevator set from the configuration point i to the floor j and the elevator resource W ij allocated from the configuration point i to the floor j, that is , where K is the number of candidate solution populations, and this group of candidate solutions constitutes the initial population. Each candidate solution It represents a possible position in the search space. The candidate solution is directly substituted into the formulas corresponding to the objective functions J1, J2, and J3 to obtain the model results of the optimal decision variables under the respective prior parameters. This further differentiates from the conventional gradient-solving algorithms and can further quickly screen out the optimal solution direction of the optimization problem within a large range in the entire building with limited resources.

[0061] 9. In the first aspect of the above technical solution, during the process of switching from the step of quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model to the step of finely processing to obtain the optimal solution of the optimization problem based on the AED scheduling and allocation optimization model, it is determined by the migration factor TF whether to switch. , where t is the current iteration number, and t max is the maximum iteration number. When TF ≤ 0.5, continue to quickly screen out the optimal solution direction of the optimization problem; when TF > 0.5, enter the step of finely processing to obtain the optimal solution of the optimization problem. In this way, it is determined whether to switch from quickly screening out the optimal solution direction of the optimization problem to finely processing to obtain the optimal solution of the optimization problem. In the method of this application, the value set for the migration factor to determine the switching can also be set to 0.4, 0.6, etc.

[0062] 10. In the first aspect of the above technical solution, in the step of finely processing to obtain the optimal solution of the optimization problem based on the AED scheduling and allocation optimization model, the following steps are included:

[0063] Determine the number of individuals in the allocation plan and the maximum iteration number t max , and a group or multiple groups of candidate solutions are randomly generated by the AED scheduling and allocation optimization model. Each individual among the multiple candidate solutions represents an allocation plan for AED devices and first aid personnel obtaining AED devices, and the ranges of each constant parameter and acceleration are set;

[0064] After substituting the candidate solutions into the macroscopic scheduling objective function, obtain the model results of the optimal decision variables of the corresponding objective function under the prior parameters in the complex multi - elevator system, and quickly screen out the optimal solution direction of the allocation plan for AED devices and first aid personnel obtaining AED devices according to the model results;

[0065] Selectively update the optimization parameters of the current optimal individual according to the optimal solution direction, and update the optimization parameters of other individuals in the candidate solutions using the optimization parameters of the current optimal individual;

[0066] Calculate the migration factor and the parameter amplitude factor. It is determined by the migration factor whether to continue to quickly screen out the optimal solution direction of the optimization problem or enter the step of finely processing to obtain the optimal solution of the optimization problem, and the amplitude of updating the optimization parameters of the optimal individual and other individuals is adjusted by the parameter amplitude factor;

[0067] When the migration factor ≤ 0.5, continue to quickly screen out the optimal solution direction of the optimization problem.

[0068] By using the above more refined steps for quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model, the implementation of this step is further optimized, ensuring the accuracy and reliability of quickly screening out the optimal solution direction of the optimization problem.

[0069] 11. In the first aspect of the above technical solution, in the step of obtaining the optimal solution of the optimization problem through fine processing based on the AED scheduling and allocation optimization model, the following steps are included:

[0070] When the migration factor > 0.5, enter the process of obtaining the optimal solution of the optimization problem through fine processing;

[0071] Perform fine local optimization according to the optimal solution direction of the allocation scheme to ensure that the allocation scheme in the optimal solution direction satisfies all constraints related to AED device resource configuration and floor capacity limitations;

[0072] Use the current optimal individual as the initial point and perform local iterative optimization. During the iterative optimization process, if a better allocation scheme is found, use this better allocation scheme as the new current optimal individual and update the corresponding optimization parameters; if no better allocation scheme is found, continue to update the optimization parameters of the current optimal individual according to the parameter amplitude factor;

[0073] When the maximum number of iterations is reached or the update amplitude of the optimization parameters of the optimal individual is less than the preset amplitude threshold, stop this step and output the optimal solution allocation scheme; otherwise, continue with the step of selectively updating the optimization parameters of the current optimal individual according to the optimal solution direction and subsequent steps.

[0074] By using the above more refined steps for obtaining the optimal solution of the optimization problem through fine processing based on the AED scheduling and allocation optimization model, the implementation of this step is further optimized, ensuring the accuracy and reliability of quickly screening out the optimal solution allocation scheme of the optimization problem.

[0075] 12. In the first aspect of the above technical solution, in the step of performing AED intelligent scheduling in a complex multi - elevator system, simultaneously calculate the sub - optimal solution allocation scheme. If the optimal solution allocation scheme is interrupted during execution, start the sub - optimal solution allocation scheme. Finally, in the step of performing AED intelligent scheduling in a complex multi - elevator system, in addition to maintaining the execution of the optimal solution allocation scheme, also simultaneously calculate the sub - optimal solution allocation scheme to avoid immediately enabling the sub - optimal solution allocation scheme in the case where the optimal solution allocation scheme cannot be executed due to a small - probability accident, ensuring that patients in urgent need of cardiopulmonary resuscitation can be effectively treated in a timely manner.

[0076] 13. In the second aspect of the above technical solution, the elevators include high-speed elevators, low-speed elevators, shuttle elevators, service / freight elevators;

[0077] The high-speed elevators are used to quickly reach high floors;

[0078] The low-speed elevators are used to serve low floors;

[0079] The shuttle elevators are used to quickly transport from the ground floor or transfer floor to a specific intermediate floor or sky lobby;

[0080] The service / freight elevators are used to transport goods and service personnel, and for evacuation;

[0081] The zoned service includes zoned elevators and double-deck car elevators; the zoned elevators only serve a specific floor range; the double-deck car elevators stop at two adjacent floors simultaneously.

[0082] With the above design, the establishment of a complex multi-elevator system is made more perfect. In the complex multi-elevator system of the present application, the elevator types can include combinations of two or more of the listed ones.

[0083] Due to the application of the above solution, the present invention has the following advantages and effects compared with the prior art:

[0084] 1. Through the implementation of the technical solution of the present invention, aiming at the problems existing in the elevator AED scheduling in the complex scenarios of high-rise buildings, such as the uncertainty of whether the AED device can be delivered, limited coverage, and difficult first aid scheduling, etc., a complex-scenario elevator AED intelligent scheduling method, a complex multi-elevator system, a complex-scenario elevator AED intelligent scheduling system, an intelligent AED lifting platform device, and a readable storage medium are innovatively developed and designed. During the golden first aid time, in the complex scenarios of high-rise buildings, the first aid personnel and AED devices are macroscopically regulated to the first aid scene to balance the elevator AED and the first aid personnel fetching the AED to reach the target floor fastest with the minimum time (path); in the present application, by establishing an AED scheduling and allocation optimization model under the complex multi-elevator system, the allocation schemes of AED devices and first aid personnel fetching AED devices in the complex scenarios under the original complex multi-elevator system are summarized into optimization problems that can be solved by mathematical models, thus laying a basic condition for the optimization of the allocation scheme and macroscopic regulation.

[0085] 2. Through the implementation of the technical solution of the present invention, when establishing an AED scheduling and allocation optimization model for a complex multi-elevator system, the prior parameters in the complex multi-elevator system and the decision variables for reaching the shortest path are defined based on this optimization problem, so that the parameters and variables are scientific, reasonable and highly compatible when the model is established, thus providing a clear mathematical description; and the prior parameters and decision variables are used to construct the objective function related to the macro-scheduling of AED devices and first-aid personnel for the optimization problem and the constraint conditions related to the resource allocation of AED devices and floor capacity limitations, so that the application and representation of the optimization problem under this AED scheduling and allocation optimization model are more accurate, which conforms to the objectives corresponding to the elevator AED scheduling process in the actual complex scenario and the limitations and constraints based on resource limitations, capacity limitations, etc., so that the final establishment of the AED scheduling and allocation optimization model fully takes into account problems such as the uncertainty of whether the AED device can be delivered, limited coverage, and difficult first-aid scheduling.

[0086] 3. Through the implementation of the technical solution of the present invention, when performing the step of quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model, different from the general gradient-solving algorithm, when the first-aid event starts, this application randomly generates one or more groups of candidate solutions by the AED scheduling and allocation optimization model. Different from the exhaustive solutions, this application substitutes the candidate solutions into the macro-scheduling objective function to obtain the model results of the optimal decision variables of the corresponding objective function under the prior parameters in the complex multi-elevator system, so as to quickly screen out the optimal solution direction of the allocation plan, and through substitution, simulate the possible large-scale adjustment of limited resources in the whole building, generally quickly find out the possible excellent configuration plans, avoid falling into local optimality, but when implemented, it will be affected by other factors and instead fail to achieve the purpose of reaching the golden time, and after quickly screening out the optimal solution direction of the allocation plan according to the model results, selectively update the optimization parameters of the current optimal individual according to the optimal solution direction, so as to provide a more excellent allocation plan for subsequent fine processing.

[0087] 4. Through the implementation of the technical solution of the present invention, when performing the step of obtaining the optimal solution of the optimization problem through fine processing based on the AED scheduling and allocation optimization model, perform fine local optimization according to the optimal solution direction of the allocation plan to ensure that the allocation plan in the optimal solution direction meets all the constraint conditions related to the resource allocation of AED devices and floor capacity limitations, so as to further perform more fine local optimization within the limited resource limitations, and use the current optimal individual for iterative optimization until the maximum iteration number is reached or the improvement amplitude corresponding to the optimization parameters of the optimal individual is less than the preset amplitude threshold, so as to quickly obtain the optimal solution allocation plan, improve the emergency response efficiency, give the allocation plan within the shortest possible time, and avoid missing the first-aid golden time.

[0088] 5. In summary, after adopting the solution of the present invention, based on the establishment of a reliable and efficient AED scheduling and allocation optimization model, through the combination of the following two steps: quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model, and finely processing the optimal solution of the optimization problem based on the AED scheduling and allocation optimization model, it is possible to quickly screen out the optimal solution direction of the optimization problem within a large range in the entire building with limited resources, avoid falling into local optima, and be able to finely process the optimal solution of the optimization problem from the screened optimal solution directions, further optimizing resource allocation, improving the emergency response efficiency in complex scenarios, ensuring that patients in urgent need of cardiopulmonary resuscitation can be effectively treated in a timely manner, and enabling defibrillation support to be obtained as early as possible after ventricular fibrillation occurs in patients with cardiac arrest, thereby improving the treatment speed and survival rate of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 It is a schematic flowchart of the intelligent elevator AED scheduling method in a complex scenario according to an embodiment of the present invention;

[0090] Figure 2 It is a schematic diagram of a special scheduling strategy existing in an emergency scenario according to an embodiment of the present invention;

[0091] Figure 3 It is a schematic diagram of a complex multi - elevator system according to an embodiment of the present invention;

[0092] Figure 4 It is a schematic flowchart of the hybrid algorithm according to an embodiment of the present invention;

[0093] Figure 5 It is a schematic diagram of in - car TV floor - level navigation. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0094] To make the above - mentioned objects, features, and advantages of the present application more clearly understandable, the following will describe the specific embodiments of the present application in detail with reference to the accompanying drawings. Many specific details are set forth in the following description in order to fully understand the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the connotation of the present application. Therefore, the present application is not limited by the specific embodiments disclosed below.

[0095] The terms used herein are only for describing specific embodiments and are not intended to limit the present case. Singular forms such as "a", "this", "herein", "the present", and "the" also include plural forms as used herein.

[0096] Regarding the use of "first", "second", etc. in this article, it does not particularly refer to the meaning of order or sequence, nor is it used to limit the present case. It is only used to distinguish components or operations described with the same technical terms.

[0097] Regarding the "connection" or "positioning" used in this text, it can refer to two or more components or lifting platforms making direct physical contact with each other, or making indirect physical contact with each other. It can also refer to two or more components or lifting platforms operating or acting on each other.

[0098] Regarding the "including", "comprising", "having", etc. used in this text, they are all open-ended terms, meaning including but not limited to.

[0099] Regarding the terms used in this text, unless otherwise specified, they generally have their ordinary meanings in this field, in the context of this case, and in the specific context. Some of the terms used to describe this case will be discussed below or elsewhere in this specification to provide additional guidance to those skilled in the art regarding the description of this case.

[0100] The present invention aims to solve the problem of intelligent macro-scheduling of the elevator AED in case of an emergency first aid situation, balance the elevator AED and the personnel retrieving the AED to reach the target floor as quickly as possible, and for a complex multi-elevator system including high-speed elevators, low-speed elevators, shuttle elevators, etc., within the golden first aid time, solve the problem of the overall arrival of both the allocated elevator AED and the personnel who can carry the AED to the target floor in the minimum time (path). Thus, an intelligent scheduling method for elevator AED in complex scenarios, a complex multi-elevator system, an intelligent scheduling system for elevator AED in complex scenarios, an intelligent AED lifting platform device, and a readable storage medium are innovatively developed and designed. Within the golden first aid time in the complex scenario of high-rise buildings, the first aid personnel and the AED device are macro-controlled to the first aid scene, and the elevator AED and the first aid personnel retrieving the AED reach the target floor as quickly as possible with the minimum time (path).

[0101] Embodiment 1, as Figure 1 shown, Embodiment 1 of the present invention proposes an intelligent scheduling method for elevator AED in complex scenarios, and the method includes:

[0102] Establish an AED scheduling and allocation optimization model for a complex multi-elevator system, summarize the allocation schemes of AED devices and first aid personnel obtaining AED devices in the complex multi-elevator system as an optimization problem, define prior parameters and decision variables for the shortest path to be obtained in the complex multi-elevator system based on this optimization problem, construct an objective function related to the macro-scheduling of AED devices and first aid personnel and constraint conditions related to AED device resource configuration and floor capacity limitation for the optimization problem with the prior parameters and decision variables, and establish an AED scheduling and allocation optimization model;

[0103] Based on the AED scheduling and allocation optimization model, quickly screen out the optimal solution direction of the optimization problem. According to the occurrence of emergency events, the AED scheduling and allocation optimization model randomly generates one or more groups of candidate solutions. Each individual in the multiple candidate solutions represents an allocation plan for AED devices and the first aid personnel who obtain the AED devices. Substitute the candidate solutions into the macro scheduling objective function to obtain the model results of the optimal decision variables of the corresponding objective function under the prior parameters in the complex multi - elevator system. According to the model results, quickly screen out the optimal solution direction of the allocation plan for AED devices and the first aid personnel who obtain the AED devices, and selectively update the optimization parameters of the current optimal individual according to the optimal solution direction;

[0104] Based on the AED scheduling and allocation optimization model, finely process to obtain the optimal solution of the optimization problem. Conduct fine - grained local optimization according to the optimal solution direction of the allocation plan for AED devices and the first aid personnel who obtain the AED devices to ensure that the allocation plan in the optimal solution direction meets all the constraint conditions related to AED device resource allocation and floor capacity limits, and use the current optimal individual for iterative optimization until the maximum number of iterations is reached or the improvement amplitude corresponding to the optimization parameters of the optimal individual is less than the preset threshold, and output the final optimal solution allocation plan;

[0105] Execute AED intelligent scheduling in the complex multi - elevator system, and use the optimal solution allocation plan to conduct intelligent scheduling for AED devices and the first aid personnel who obtain the AED devices.

[0106] In each step of the above - mentioned method, it includes establishing an AED scheduling and allocation optimization model under a complex multi - elevator system, quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model, finely processing to obtain the optimal solution of the optimization problem based on the AED scheduling and allocation optimization model, and executing AED intelligent scheduling in the complex multi - elevator system.

[0107] When establishing the AED scheduling and allocation optimization model under a complex multi - elevator system, define the prior parameters and the decision variables for the shortest path to reach the desired value in the complex multi - elevator system based on this optimization problem, so as to make the parameters and variables scientific, reasonable and highly compatible when the model is established, and provide a clear mathematical description; and construct the objective function related to the macro scheduling of AED devices and first aid personnel and the constraint conditions related to AED device resource allocation and floor capacity limits for the optimization problem with the prior parameters and decision variables, so that the application and representation of the optimization problem under this AED scheduling and allocation optimization model are more accurate, which fits the objectives corresponding to the elevator AED scheduling process in the actual complex scenario and the limitation constraints based on resource limitations, capacity limitations, etc., making the final establishment of the AED scheduling and allocation optimization model fully consider problems such as uncertainty in whether the AED device can be delivered, limited coverage, and difficult first aid scheduling.

[0108] When performing the step of quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model, different from the general gradient-solving algorithm, in this application, when an emergency rescue event starts, the AED scheduling and allocation optimization model randomly generates one or more groups of candidate solutions. Different from the exhaustive solutions, in this application, the candidate solutions are substituted into the macro scheduling objective function to obtain the model results of the optimal decision variables of the corresponding objective function under the prior parameters in the complex multi-elevator system, so as to quickly screen out the optimal solution direction of the allocation plan. By substituting and simulating the possible large-scale adjustments of limited resources in the entire building, generally quickly finding out possible excellent configuration plans, avoiding falling into local optima, but being affected by other factors during implementation and failing to reach the golden time for delivery. And after quickly screening out the optimal solution direction of the allocation plan according to the model results, selectively update the optimization parameters of the current optimal individual according to the optimal solution direction, so as to provide a better allocation plan for subsequent fine processing.

[0109] In the step of obtaining the optimal solution of the optimization problem through the fine processing of the AED scheduling and allocation optimization model, perform fine local optimization according to the optimal solution direction of the allocation plan to ensure that the allocation plan in the optimal solution direction meets all the constraint conditions related to the AED device resource configuration and floor capacity limit, so as to further perform more fine local optimization within the limited resource constraints, and use the current optimal individual for iterative optimization until the maximum number of iterations is reached or the improvement amplitude corresponding to the optimization parameters of the optimal individual is less than the preset amplitude threshold, so as to quickly obtain the optimal solution allocation plan, improve the emergency response efficiency, give the allocation plan within the shortest possible time, and avoid missing the golden time for first aid.

[0110] In the first embodiment of the present invention, in the step of establishing the AED scheduling and allocation optimization model under a complex multi-elevator system:

[0111] The prior parameters are parameters set according to the floor zoning, elevator zoning, AED device layout in the elevator, and personnel flow in the complex multi-elevator system;

[0112] The decision variable is the variable that enables the shortest path for the first aid personnel and the elevator AED to reach the desired location within the planned period.

[0113] In this way, further improve the more scientific, reasonable and highly compatible parameters and variables of the AED scheduling and allocation optimization model during establishment, so as to provide a more accurate mathematical description and provide basic conditions for the optimization problem of the allocation plan in the complex scenario under the complex multi-elevator system.

[0114] Specifically, the prior parameters include:

[0115] I, representing the configuration or location index of the AED device or the first aid personnel;

[0116] J represents the floor index in the building;

[0117] M represents the total number of AED device configuration points;

[0118] N represents the total number of floors;

[0119] B i represents the initial response probability of AED devices and first aid personnel for the configuration area i within the planned period;

[0120] H i represents the target response probability of available AED devices for the configuration area i within the planned period;

[0121] E i represents the target response probability of available first aid personnel for the configuration area i within the planned period;

[0122] H j represents the set of AED devices arriving at the target floor for floor j within the planned period;

[0123] E j represents the set of first aid personnel arriving at the target floor for floor j within the planned period;

[0124] L j represents the set of arrival efficiencies for floor j within the planned period, considering factors such as elevator accessibility, elevator operating speed, and congestion level;

[0125] U j represents the set of efficiencies of AED devices and first aid personnel consumed on floor j;

[0126] M j represents the set of elevator AED devices that can serve floor j;

[0127] N j represents the set of elevators that can serve floor j.

[0128] Based on such more specific and detailed prior parameters, parameters are set according to floor and elevator zoning, elevator AED layout, and personnel flow conditions, making the application of the AED scheduling and allocation optimization model more efficient and accurate.

[0129] Specifically, the decision variables include:

[0130] C ij represents the response priority of the elevator set from the configuration point i to the floor j, to be used as a decision variable in the AED scheduling and allocation optimization model;

[0131] W ij, which represents the elevator resources allocated from configuration point i to floor j and serves as a decision variable in the AED scheduling and allocation optimization model.

[0132] Using such a more specific and detailed decision variable as the variable that enables the shortest path for first aid personnel and the elevator AED to reach the desired location within the cycle, the application of the AED scheduling and allocation optimization model becomes more efficient and accurate.

[0133] In the first embodiment of the present invention, in the steps of establishing the AED scheduling and allocation optimization model under a complex multi-elevator system, the objective function related to the macro scheduling of AED devices and first aid personnel corresponds to a multi-objective optimization problem with three objectives, namely J1, J2, and J3, where:

[0134] J1: Minimize the cumulative response probability of AED and first aid personnel for the target floor to the maximum extent;

[0135] J2: Minimize the path of the AED elevator reaching the target floor in the floor system to the minimum extent;

[0136] J3: Minimize the path of the first aid personnel elevator reaching the target floor in the floor system to the minimum extent.

[0137] In this way, in high-rise buildings, the macro scheduling of AED (Automated External Defibrillator) and first aid personnel can be regarded as a multi-objective optimization problem with three objectives - J1, J2, and J3. The construction of this optimization problem is scientific and reasonable, which can provide a guarantee for the correctness of the subsequent optimization and implementation of the allocation plan.

[0138] In the first embodiment of the present invention, in the steps of establishing the AED scheduling and allocation optimization model under a complex multi-elevator system, the objective function is defined as follows:

[0139] J1, within the planned cycle, maximize the cumulative response probability of AED devices and first aid personnel for the target floor:

[0140] , aiming to maximize the cumulative response probability of AED and first aid personnel;

[0141] J2, minimize the path of the AED device elevator reaching the target floor in the floor system to the minimum extent:

[0142] , aiming to minimize the total AED response cost or time and ensure that the AED device can reach the required floor with the optimal path;

[0143] J3, minimize the path of the first aid personnel elevator reaching the target floor in the floor system to the minimum extent:

[0144] , aiming to minimize the total emergency responder response cost or time and ensure that emergency responders can reach the required floors along the optimal path.

[0145] Through the further refinement and confirmation of the multi-objective optimization problem above, the process of establishing an AED scheduling and allocation optimization model in a complex scenario and a complex multi-elevator system is realized, and it can aim at the fastest time and the lowest risk, meeting the urgency and necessity of obtaining defibrillation support after ventricular fibrillation occurs in cardiac arrest patients. Moreover, in the process of defining each formula adopted by the objective function, it further matches the problems and scenarios that need to be solved by the prior parameters and decision variables in each optimization problem, making the expression of the multi-objective optimization problem and the objective function more accurate.

[0146] In the first embodiment of the present invention, in the step of establishing an AED scheduling and allocation optimization model under a complex multi-elevator system, the constraint conditions related to AED device resource configuration and floor capacity limit respectively include Constraint One, Constraint Two, and Constraint Three, where:

[0147] Constraint One is the resource limit of the configuration point. The total amount of resources allocated from configuration point i to each floor cannot exceed its available total resources: ;

[0148] Constraint Two is the minimum demand capacity limit and the maximum demand capacity limit of the floor. The minimum demand capacity limit is and the maximum demand capacity limit is ;

[0149] Constraint Three is the non-negativity constraint, where the allocated resource quantity cannot be negative, , and n represents the set of positive integers .

[0150] Through the establishment and definition of the above constraint conditions, it further matches the resource limitations, capacity limitations, demand limitations, etc. existing in the prior parameters and decision variables in each constraint condition, providing more accurate and reasonable constraints for the establishment of the AED scheduling and allocation optimization model under the state of limited resource allocation, so as to ensure the smooth implementation of the allocation plan generated when responding to emergency events.

[0151] In the first embodiment of the present invention, in the step of quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model, the AED scheduling and allocation optimization model randomly generates candidate solutions. The candidate solutions include the response priority C ij of the elevator set from configuration point i to floor j and the elevator resource W ij allocated from configuration point i to floor j, that is , where K is the number of candidate solution populations, and this group of candidate solutions constitutes the initial population. Each candidate solution Represents a possible position in the search space. The candidate solution is directly substituted into the formulas corresponding to the objective functions J1, J2, and J3 to obtain the model results of the optimal decision variables under the respective prior parameters. This further differentiates from the conventional gradient-solving algorithms and can quickly screen out the optimal solution direction of the optimization problem within a large range in the entire building with limited resources.

[0152] In the first embodiment of the present invention, during the process of switching from the step of quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model to the step of finely processing to obtain the optimal solution of the optimization problem based on the AED scheduling and allocation optimization model, it is determined by the migration factor TF whether to switch. , where t is the current iteration number, and t max is the maximum iteration number. When TF ≤ 0.5, continue to quickly screen out the optimal solution direction of the optimization problem; when TF > 0.5, enter the step of finely processing to obtain the optimal solution of the optimization problem. In this way, it is determined whether to switch from quickly screening out the optimal solution direction of the optimization problem to finely processing to obtain the optimal solution of the optimization problem. In the method of the present application, the value set for the migration factor to determine the switching can also be set to 0.4, 0.6, etc.

[0153] In the first embodiment of the present invention, the step of finely processing to obtain the optimal solution of the optimization problem based on the AED scheduling and allocation optimization model includes the following steps:

[0154] Determine the number of individuals in the allocation scheme and the maximum iteration number t max , and a group or multiple groups of candidate solutions are randomly generated by the AED scheduling and allocation optimization model. Each individual in the multiple candidate solutions represents an allocation scheme of AED devices and first aid personnel obtaining AED devices, and the ranges of each constant parameter and acceleration are set;

[0155] After substituting the candidate solutions into the macro scheduling objective function, obtain the model results of the optimal decision variables of the corresponding objective function under the prior parameters in the complex multi - elevator system, and quickly screen out the optimal solution direction of the allocation scheme of AED devices and first aid personnel obtaining AED devices according to the model results;

[0156] Selectively update the optimization parameters of the current optimal individual according to the optimal solution direction, and update the optimization parameters of other individuals in the candidate solutions using the optimization parameters of the current optimal individual;

[0157] Calculate the migration factor and the parameter amplitude factor. It is determined by the migration factor whether to continue to quickly screen out the optimal solution direction of the optimization problem or enter the step of finely processing to obtain the optimal solution of the optimization problem, and the amplitude of updating the optimization parameters of the optimal individual and other individuals is adjusted by the parameter amplitude factor;

[0158] When the migration factor ≤ 0.5, continue to quickly screen out the optimal solution direction of the optimization problem.

[0159] Adopting the above more refined steps of quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model further optimizes the implementation of this step, ensuring the accuracy and reliability of quickly screening out the optimal solution direction of the optimization problem.

[0160] In the first embodiment of the present invention, in the step of performing AED intelligent scheduling in a complex multi - elevator system, while maintaining the calculation of the sub - optimal solution allocation plan, if the optimal solution allocation plan is interrupted during execution, then start the sub - optimal solution allocation plan. Finally, in the step of performing AED intelligent scheduling in a complex multi - elevator system, in addition to maintaining the execution of the optimal solution allocation plan, it also simultaneously maintains the calculation of the sub - optimal solution allocation plan to avoid the situation where the optimal solution allocation plan cannot be executed due to a small - probability accidental event and immediately enable the sub - optimal solution allocation plan, ensuring that patients in urgent need of cardiopulmonary resuscitation can be effectively treated in a timely manner.

[0161] Next, the first embodiment of the present invention will be further described with a more specific detailed embodiment. The following are the detailed contents included in the elevator AED intelligent scheduling method in a complex scenario of this detailed embodiment.

[0162] The detailed embodiment of the present invention mainly aims to provide an intelligent operation solution for AED device scheduling and first - aid personnel scheduling in elevator AED scheduling in a complex scenario of high - rise buildings.

[0163] In this intelligent computing solution, first, an AED scheduling and allocation optimization model for a complex multi - elevator system is established. The allocation scheme of AED devices and first - aid personnel who obtain AED devices in the complex multi - elevator system is summarized as an optimization problem. Based on this optimization problem, prior parameters and decision variables for the shortest path to the desired destination in the complex multi - elevator system are defined. The prior parameters are parameters set according to floor zoning, elevator zoning, the layout of AED devices in elevators, and personnel flow in the complex multi - elevator system. The decision variables are variables that enable first - aid personnel and the elevator AED to reach the desired destination in the shortest path within the planned period. The objective function related to the macro - scheduling of AED devices and first - aid personnel corresponds to a multi - objective optimization problem with three objectives, namely J1, J2, and J3, where: J1: Minimize the cumulative response probability of AED and first - aid personnel for the target floor to the maximum extent; J2: Minimize the path of the AED elevator to reach the target floor in the floor system; J3: Minimize the path of the first - aid personnel elevator to reach the target floor in the floor system. In the step of establishing the AED scheduling and allocation optimization model for the complex multi - elevator system, the constraint conditions related to AED device resource allocation and floor capacity limitations include Constraint One, Constraint Two, and Constraint Three, where: Constraint One is the resource limitation of the configuration point. The total amount of resources allocated from configuration point i to each floor cannot exceed its available total resources: ; Constraint Two is the minimum demand capacity limit and the maximum demand capacity limit of the floor. The minimum demand capacity limit is , and the maximum demand capacity limit is ; Constraint Three is the non - negativity constraint, where the quantity of allocated resources cannot be negative, , n represents the set of positive integers . Using the prior parameters and decision variables to construct the objective function related to the macro - scheduling of AED devices and first - aid personnel for the optimization problem and the constraint conditions related to AED device resource allocation and floor capacity limitations, an AED scheduling and allocation optimization model is established.

[0164] When a first - aid event occurs, the elevator AED intelligent scheduling system in a complex scenario receives a first - aid notice and uses the AED scheduling and allocation optimization model. Based on the AED scheduling and allocation optimization model, the optimal solution direction of the optimization problem is quickly screened out, including the following steps:

[0165] Determine the number of individuals in the allocation scheme and the maximum number of iterations t max , and generate one or more groups of candidate solutions randomly by the AED scheduling and allocation optimization model. Each individual in the multiple candidate solutions represents an allocation scheme of AED devices and first - aid personnel who obtain AED devices, and set the range of each constant parameter and acceleration;

[0166] After substituting the candidate solution into the macro-scheduling objective function, the model result of the optimal decision variable of the corresponding objective function under the prior parameters in the complex multi-elevator system is obtained. According to the model result, the optimal solution direction of the allocation plan of AED devices and the first-aid personnel obtaining the AED devices is quickly screened out;

[0167] Selectively update the optimization parameters of the current optimal individual according to the optimal solution direction, and use the optimization parameters of the current optimal individual to update the optimization parameters of other individuals in the candidate solution;

[0168] Calculate the migration factor and the parameter amplitude factor. The migration factor determines whether to continue to quickly screen out the optimal solution direction of the optimization problem or enter the fine processing to obtain the optimal solution of the optimization problem, and the parameter amplitude factor is used to adjust the update amplitude of the optimization parameters of the optimal individual and other individuals;

[0169] When the migration factor ≤ 0.5, continue to quickly screen out the optimal solution direction of the optimization problem.

[0170] Based on the AED scheduling and allocation optimization model, the optimal solution of the optimization problem is obtained through fine processing, including the following steps:

[0171] When the migration factor > 0.5, enter the fine processing to obtain the optimal solution of the optimization problem;

[0172] Perform fine local optimization according to the optimal solution direction of the allocation plan to ensure that the allocation plan in the optimal solution direction meets all the constraint conditions related to AED device resource allocation and floor capacity limitation;

[0173] Use the current optimal individual as the initial point to perform local iterative optimization. During the iterative optimization process, if a better allocation plan is found, use the better allocation plan as the new current optimal individual and update the corresponding optimization parameters; if no better allocation plan is found, continue to update the optimization parameters of the current optimal individual according to the parameter amplitude factor;

[0174] When the maximum number of iterations is reached or the update amplitude of the optimization parameters of the optimal individual is less than the preset amplitude threshold, stop this step and output the optimal solution allocation plan; otherwise, continue with the step of selectively updating the optimization parameters of the current optimal individual according to the optimal solution direction and subsequent steps.

[0175] Execute the AED intelligent scheduling in the complex multi-elevator system, use the optimal solution allocation plan to perform intelligent scheduling on AED devices and the first-aid personnel obtaining the AED devices, and at the same time keep calculating the sub-optimal solution allocation plan. If the optimal solution allocation plan is interrupted during execution, start the sub-optimal solution allocation plan.

[0176] In the process of implementing this application, in the scheduling of AED devices and first aid personnel in a complex multi-elevator system, the main factors to be considered involve balancing the elevator AED and the personnel (first aid personnel) retrieving the AED to reach the target floor as quickly as possible in the shortest time (path). It solves the problem of the overall arrival of the elevator AED and the personnel who can carry the AED at the target floor in the shortest time (path) within the golden first aid time. It should be noted that in the first aid scenario, even when the first aid personnel and the elevator storing the AED device are not in the same elevator, the elevator with the AED device and the elevator carrying the first aid personnel can be independently scheduled to reach the target floor respectively, as Figure 2 In the special scheduling strategy existing in the shown first aid scenario, when an AED (Automated External Defibrillator) needs to be delivered to a certain floor, it is necessary to design the scheduling method of the elevator system, mainly by designing a complete scheduling logic for adjusting the priority of elevator operation, so as to complete the scheduling of personnel and AED.

[0177] Example 2, as Figure 3 shown, Embodiment 2 of the present invention proposes a complex multi-elevator system, which includes a plurality of elevator shafts, and various types of elevators are selectively configured in each elevator shaft. The elevators are selectively configured to serve different partitions, and AED devices are selectively configured in the elevators.

[0178] In this complex multi-elevator system, the elevators include high-speed elevators, low-speed elevators, shuttle elevators, service / cargo elevators;

[0179] The high-speed elevators are used to quickly reach high-rise floors;

[0180] The low-speed elevators are used to serve low floors;

[0181] The shuttle elevators are used to quickly transport from the ground floor or transfer floor to a specific intermediate floor or sky lobby;

[0182] The service / cargo elevators are used to transport goods and service personnel, and for evacuation;

[0183] The partition service includes partition elevators and double-deck car elevators; the partition elevators only serve a specific floor range; the double-deck car elevators stop at two adjacent floors at the same time.

[0184] With the above design, the establishment of the complex multi-elevator system is made more perfect. In the complex multi-elevator system of this application, the elevator types can include two or more combinations of those listed.

[0185] For the above complex multi - elevator system, we take a high - rise system of a complex elevator system including high - speed elevators, low - speed elevators, and shuttle elevators as an example. To optimize the flow of people and improve efficiency, these elevators are usually divided into zones for service. The assumed elevator zone services are as follows:

[0186] Low - speed elevators: mainly serve the lower floors (such as floors 1 - 10) because they are slower but have a larger capacity, which is suitable for handling a large number of short - distance passenger transports.

[0187] High - speed elevators: are divided into two groups or more, and each group serves different high - floor areas. For example:

[0188] The first group of high - speed elevators serves floors 10 - 35.

[0189] The second group of high - speed elevators serves floors 25 - 50.

[0190] Shuttle elevators: are specifically used for quickly transporting from the ground floor to the transfer floor or sky lobby. For example, directly from the 1st floor to the 30th or 50th floor, and then passengers can transfer to other elevators to continue going to higher floors.

[0191] Embodiment 3: Embodiment 3 of the present invention proposes an elevator AED intelligent scheduling system in a complex scenario. The elevator AED intelligent scheduling system in the complex scenario includes the complex multi - elevator system as described in Embodiment 2 of the present invention, and an AED intelligent scheduling system platform for scheduling the complex multi - elevator system, AED devices, and obtaining first - aid personnel of AED devices. An AED scheduling and allocation optimization model is established in the AED intelligent scheduling system platform. Based on the AED scheduling and allocation optimization model, the optimal solution direction of the optimization problem is quickly screened out, the optimal solution of the optimization problem is finely processed based on the AED scheduling and allocation optimization model, and AED intelligent scheduling is performed in the complex multi - elevator system to respond to emergency events.

[0192] Embodiment 4: Embodiment 4 of the present invention proposes an intelligent AED lifting platform for the method described in the first aspect. The intelligent AED lifting platform device includes an elevator and an AED device configured in the elevator.

[0193] Embodiment 5: Embodiment 5 of the present invention proposes a readable storage medium. A control program is stored on the readable storage medium. When the control program is executed by a processor, the processor is caused to execute the steps of the elevator AED intelligent scheduling method in a complex scenario as described in Embodiment 1.

[0194] Next, the content related to the algorithm part of the elevator AED intelligent scheduling method in the present invention will be described.

[0195] In the steps of establishing the AED scheduling and allocation optimization model under a complex multi - elevator system, as defined in Embodiment 1 of the present invention, the objective function is defined as follows:

[0196] J1, within the planned period, maximize the cumulative response probability of AED devices and first - aid personnel for the target floors:

[0197] (1);

[0198] J2, minimize the path of the elevator with the AED device in the floor system to reach the target floor:

[0199] (2);

[0200] J3, minimize the path of the elevator with the first - aid personnel in the floor system to reach the target floor:

[0201] (3);

[0202] Constraint 1, for the resource limit of the configuration point, the total amount of resources allocated from the configuration point i to each floor cannot exceed its available total resources:

[0203] (4);

[0204] Constraint 2, for the minimum demand capacity limit and the maximum demand capacity limit of the floor, the minimum demand capacity limit is:

[0205] (5);

[0206] The maximum demand capacity limit is:

[0207] (6);

[0208] Constraint 3, for the non - negativity constraint, where the quantity of allocated resources cannot be negative:

[0209] (7);

[0210] n represents the set of positive integers , and Constraint 3 can specifically be .

[0211] In the step of quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model, the optimal solution direction of the optimization problem can be quickly screened out based on the AED scheduling and allocation optimization model and the AOA algorithm (Archimedes Optimization Algorithm). In the AED scheduling and allocation optimization model, it is mainly necessary to solve the optimal decision parameters C of the objectives J1, J2, and J3 under the prior parameters ij and W ij . Different from the general optimal value search by gradient, at the beginning of the algorithm, a group of candidate solutions is randomly generated , where K is the number of candidate solution populations. This group of candidate solutions constitutes the initial population, and each solution represents a possible position in the search space. Each individual represents a configuration plan of an AED and first aid personnel, and can be directly substituted into formulas (1), (2), and (3) to obtain the results of J1, J2, and J3 under the prior parameters. However, different from the exhaustive solution, its solution characteristics are described by volume (vol), density (den), and acceleration (acc), and the optimal solution direction is quickly screened out. The AOA algorithm realizes the search for the optimal solution allocation plan by simulating the movement of individuals in the solution space, which is divided into the stage of quickly screening out the optimal solution direction of the optimization problem and the stage of obtaining the optimal solution of the optimization problem through fine processing

[0212] Stage of quickly screening out the optimal solution direction of the optimization problem: Simulate the large-scale adjustment of resources in the whole building, aiming to find possible excellent configuration plans and avoid falling into local optima

[0213] Stage of obtaining the optimal solution of the optimization problem through fine processing: Conduct detailed adjustments in the neighborhood of the current excellent plan to further optimize resource allocation and improve the emergency response efficiency

[0214] The switching between the two stages is determined by the migration factor (TF), and its definition is as follows

[0215] (8);

[0216] where t is the current iteration number, and t max is the maximum iteration number. When TF ≤ 0.5, the algorithm enters the stage of quickly screening out the optimal solution direction of the optimization problem; otherwise, it enters the stage of obtaining the optimal solution of the optimization problem through fine processing

[0217] In the initialization stage, AOA randomly generates a group of resource configuration plans (i.e., individuals in the population), and initializes the volume (vol i ), density (den i ), and acceleration (acc i). By evaluating the fitness of each solution, the current optimal individual (x best ) is selected, and its parameters (den best , vol best , acc best ) are used to update the density and volume of other individuals as follows:

[0218] (9);

[0219] (10)

[0220] When TF ≤ 0.5, the algorithm enters the stage of quickly screening out the optimal solution direction of the optimization problem, and the acceleration of the individual is updated:

[0221] (11).

[0222] When TF > 0.5, it enters the stage of obtaining the optimal solution of the optimization problem through fine processing, and the acceleration of the individual is based on the formula:

[0223] (12).

[0224] According to the following formula, AOA normalizes the acceleration of the individual to update the position of the individual, and u and l are used to adjust the normalization range:

[0225] (13).

[0226] In the stage of quickly screening out the optimal solution direction of the optimization problem, the position of the individual is updated according to the following formula, where and x represent the positions of the i-th individual in the (t + 1)-th and t-th generations respectively, x rand is the position of a random individual in the t-th generation, rand is a random number between 0 and 1, C 1 is a constant, d is the density factor, and its update formula is as shown in the following formula:

[0227] (14);

[0228] (15).

[0229] In the stage of obtaining the optimal solution of the optimization problem through fine processing, the position of the individual is updated according to the following formula, where is a fixed constant, , and ; F is the direction factor, which is used to determine the direction of position update in the iteration, and its definition is shown in formulas (16) and (17):

[0230] (16);

[0231] (17).

[0232] In the stage of obtaining the optimal solution of the optimization problem through fine processing, the L-BFGS-B algorithm can be used. L-BFGS-B (Limited-memory BFGS with Bounds) is an iterative algorithm for solving constrained or unconstrained nonlinear optimization problems. It updates variables by approximating the Hessian matrix of the objective function, thus accelerating convergence while considering variable boundary constraints. In the optimization of AED and emergency responder allocation, the L-BFGS-B algorithm can be used to perform fine local optimization on the current optimal solution to further improve the rationality of resource allocation.

[0233] In the steps of implementing the optimal solution direction of the optimization problem quickly screened out based on the AED scheduling and allocation optimization model and obtaining the optimal solution of the optimization problem through fine processing based on the AED scheduling and allocation optimization model, the specific process of the hybrid algorithm can be referred to Figure 4 as shown, and its steps are referred to as follows:

[0234] Step 1: Initialize the algorithm parameters.

[0235] 1. Determine the population size (number of individuals), the maximum number of iterations t max .

[0236] 2. Set the constant parameters C 1 , C 2 , C 3 , C 4 and the range [l, u] of the acceleration.

[0237] 3. Randomly generate the initial population, and each individual represents a resource allocation plan.

[0238] Step 2: Evaluate the fitness and record the optimal individual.

[0239] 1. Calculate the fitness value of each individual in the population, that is, evaluate the performance of the resource allocation plan in meeting emergency response requirements, minimizing response time and resource deviation, etc.

[0240] 2. Update the optimization parameters x best , density den best , volume vol best and acceleration acc best .

[0241] Step 3: Update the density and volume.

[0242] 1. Update the density and volume of other individuals in the population using the density and volume of the current optimal individual according to formulas (9) and (10).

[0243] Step 4: Calculate the migration factor and the density factor.

[0244] 1. Calculate the migration factor TF, which is used to determine whether the algorithm enters the global exploration or local exploitation stage.

[0245] 2. Calculate the density factor d t+1 , which is used to adjust the amplitude of individual position update

[0246] Step 5: Quickly screen out the optimal solution direction stage of the optimization problem (when TF ≤ 0.5).

[0247] 1. Update the acceleration: Update the acceleration of the individual according to formulas (11) and (12).

[0248] 2. Update the position: Update the position of the individual according to formula (13).

[0249] Step 6: Refine to obtain the optimal solution stage of the optimization problem (when TF > 0.5).

[0250] 1. Use the current optimal individual x best as the initial point and execute the L-BFGS-B algorithm for local optimization;

[0251] 2. If a better resource allocation scheme is found, update x best and its corresponding parameters.

[0252] 3. Otherwise, update the acceleration: Update the acceleration of the individual according to formula (10); update the position: Update the position of the individual according to formula (14).

[0253] Step 7: Check the stopping condition.

[0254] 1. If the maximum number of iterations t max is reached or the improvement amplitude of the optimal solution is less than the preset threshold, the algorithm terminates and outputs the optimal solution allocation scheme.

[0255] 2. Otherwise, set t = t + 1, return to Step 2, and continue the next iteration.

[0256] 3. Finally, output the optimal solution individual

[0257] With the implementation of the above embodiments, after an emergency actually occurs in a high-rise building, the main dispatching process can be referred to as follows:

[0258] 1. Receive a request:

[0259] When an emergency occurs on a certain floor and an AED is needed, the personnel on that floor send a request through the emergency button or communication device.

[0260] After receiving the request, the system confirms the specific floor where the AED is needed and determines j as the target response floor.

[0261] 2. Determine the location of the AED:

[0262] The system queries the current location of the AED. If the AED is placed on a fixed floor, the system will directly know its location; if the AED is movable, the system needs to determine the current location of the AED through sensors or other means, and determine the elevator AED set and the response probability H i and H j .

[0263] The system queries the current location of the first aid personnel's response and determines the elevator first aid personnel set and the response probability E i and E j .

[0264] 3. Calculate the optimal path:

[0265] The system calculates the optimal scheduling path from the current location of the AED to the target floor using the method of this patent. This includes considering the current state of the elevator (such as whether it is running, the current floor it is on, etc.) and the needs of other passengers.

[0266] If the elevator has no other tasks currently, it will directly go to the floor where the AED is located.

[0267] If the elevator has other tasks, the system will evaluate whether it can immediately change the route to prioritize the AED request.

[0268] 4. Adjust the elevator task:

[0269] If the elevator is performing other tasks, the system will evaluate whether it can interrupt the current task to prioritize the AED request. For example, if the elevator is going up and approaching the floor where the AED is located, it may choose to pick up the AED first and then continue to complete the previous task.

[0270] If the elevator cannot respond immediately, the system will notify the requester of the estimated arrival time and may suggest using the stairs or other emergency measures.

[0271] 5. Transport the AED:

[0272] Once the elevator arrives at the floor where the AED is located, the system will prompt the operator to put the AED into the elevator.

[0273] After the elevator closes the door, it will directly go to the target floor where the AED is needed.

[0274] 6. Arrival at the target floor:

[0275] After the elevator arrives at the target floor, the system will prompt the operator to take out the AED and quickly send it to the location where first aid is needed.

[0276] The elevator can stay briefly at the target floor to give the operator enough time to take out the AED.

[0277] The navigation map within the floor where the target position is reached can be displayed in the elevator's suitcase so that the operator and the first aid personnel can quickly reach the target position. The in-car TV floor navigation schematic diagram of the elevator can also provide the navigation map, and the navigation map can be referred to as shown. Figure 5 as shown.

[0278] 7. Resume regular service:

[0279] Once the AED is successfully delivered, the elevator system will resume the normal service mode and continue to handle the requests of other passengers.

[0280] 8. Monitoring and recording:

[0281] Throughout the process, the system will continuously monitor the status of the elevator and the delivery situation of the AED.

[0282] After the event ends, the system will record the situation of this emergency response for subsequent analysis and improvement.

[0283] 9. Backup plan:

[0284] In the elevator dispatching system, in addition to maintaining the execution of the optimal first dispatching plan, the sub-optimal dispatching plan is also calculated and started when the first optimization plan cannot be executed.

[0285] If the elevator breaks down or fails to respond, the system should have a backup plan, such as notifying the staff on other floors to manually carry the AED to the target floor or using other available vertical transportation means.

[0286] Through the implementation of the above embodiments of the present invention, based on the establishment of a reliable and efficient AED scheduling and allocation optimization model, and then through the combination of the following two steps: quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model, and finely processing to obtain the optimal solution of the optimization problem based on the AED scheduling and allocation optimization model, it is possible to quickly screen out the optimal solution direction of the optimization problem within a large range of the entire building with limited resources, avoid falling into local optima, and at the same time be able to finely process to obtain the optimal solution of the optimization problem in the selected optimal solution direction, further optimize the resource allocation, improve the emergency response efficiency, ensure that patients in urgent need of cardiopulmonary resuscitation can be effectively treated in a timely manner, and enable defibrillation support to be obtained as early as possible after ventricular fibrillation occurs in patients with cardiac arrest, so as to improve the treatment speed and survival rate of patients, achieving the purpose of the present invention.

[0287] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable those familiar with this technology to understand the content of the present invention and implement it accordingly, and cannot be used to limit the protection scope of the present invention. Any equivalent changes or modifications made according to the spirit and essence of the present invention should be covered within the protection scope of the present invention.

Claims

1. An intelligent dispatching method for elevator AED in complex scenarios, characterized in that: The method comprises: Establish an AED dispatching and allocation optimization model under a complex multi-elevator system, summarize the allocation plan of AED equipment and emergency personnel who obtain AED equipment under a complex multi-elevator system into an optimization problem, define the prior parameters in the complex multi-elevator system and the shortest path to the required decision variables based on the optimization problem, construct the objective function related to the macro-dispatching of AED equipment and emergency personnel for the optimization problem and the constraints related to the AED equipment resource allocation and floor capacity limit with the prior parameters and decision variables, and establish an AED dispatching and allocation optimization model; Based on the AED dispatch allocation optimization model, the optimal solution direction of the optimization problem is quickly screened out. The AED dispatch allocation optimization model randomly generates one or more groups of candidate solutions. Each individual in the multiple candidate solutions represents an allocation plan. After substituting the candidate solution into the macro dispatch objective function, the model result of the optimal decision variable of the corresponding objective function under the prior parameters in the complex multi-elevator system is obtained. According to the model result, the optimal solution direction of the allocation plan is quickly screened out, and the optimization parameters of the current optimal individual are selectively updated according to the optimal solution direction. Based on the refined processing of the AED dispatch allocation optimization model, the optimal solution of the optimization problem is obtained, and refined local optimization is performed according to the optimal solution direction of the allocation plan to ensure that the allocation plan in the optimal solution direction meets all constraints related to the AED equipment resource configuration and floor capacity restrictions, and the current optimal individual is used for iterative optimization until the maximum number of iterations is reached or the improvement corresponding to the optimization parameter of the optimal individual is less than the preset amplitude threshold, and the optimal solution allocation plan is output; Perform intelligent AED dispatch in complex multi-elevator systems, and use the optimal solution allocation plan to intelligently dispatch AED equipment and emergency personnel who obtain AED equipment.

2. The intelligent dispatching method for elevator AED in complex scenarios according to claim 1 is characterized in that: In the steps of establishing the AED dispatch allocation optimization model under a complex multi-elevator system: The a priori parameters are parameters set according to the floor partitions, elevator partitions, AED equipment layout in the elevators, and personnel flow in the complex multi-elevator system; The decision variables are the variables that enable the emergency personnel and the elevator AED to reach the desired destination by the shortest path within the planning period.

3. The intelligent dispatching method of elevator AED in complex scenarios according to claim 2 is characterized in that: The prior parameters include: I, indicating the configuration or location index of the AED device or first aid personnel; J, represents the floor index in the building; M, represents the total number of AED equipment configuration points; N, represents the total number of floors; B i , represents the probability of initialization response of AED equipment and emergency personnel in the configuration area i within the planning period; H i , represents the probability of target response of available AED equipment in configuration area i within the planning period; E i , represents the probability of target response of available first aid personnel in the configuration area i within the planning period; H j , represents the set of AED devices on floor j that arrive at the target floor within the planning period; E j , represents the set of emergency personnel arriving at the target floor on floor j within the planning period; L j , indicating that floor j reaches the efficiency set within the planning period; U j , represents the set of AED equipment and first aid personnel efficiency consumed on floor j; M j , represents the set of serviceable elevator AED devices on floor j; N j , represents the set of elevators that can serve floor j.

4. The intelligent dispatching method for elevator AED in complex scenarios according to claim 3 is characterized in that: The decision variables include: C ij , represents the response priority of the elevator set from configuration point i to floor j, which is used as the decision variable in the AED scheduling allocation optimization model; W ij , represents the elevator resources allocated from configuration point i to floor j, which serves as the decision variable in the AED scheduling allocation optimization model.

5. The intelligent dispatching method for elevator AED in complex scenarios according to claim 4 is characterized in that: In the step of establishing the AED dispatching and allocation optimization model under the complex multi-elevator system, the objective function related to the macro-dispatching of AED equipment and emergency personnel corresponds to a multi-objective optimization problem with three objectives, namely J1, J2 and J3, where: J1: Minimize the cumulative response probability of AED and emergency personnel for the target floor; J2: Minimize the path for the AED elevator to reach the target floor in the minimized floor system; J3: Minimize the path for emergency personnel's elevator to reach the target floor in the minimized floor system.

6. The intelligent dispatching method for elevator AED in complex scenarios according to claim 5 is characterized in that: In the step of establishing the AED dispatching and allocation optimization model under a complex multi-elevator system, the objective function is defined as follows: J1: During the planning period, maximize the cumulative response probability of AED equipment and emergency personnel for the target floor: , which aims to maximize the cumulative response probability of AED and first responders; J2, minimize the path of the AED equipment elevator to the target floor in the minimized floor system: , aims to minimize the total AED response cost or time and ensure that the AED equipment can reach the required floor via the optimal path; J3, minimize the path of the emergency personnel elevator reaching the target floor in the minimized floor system: , aims to minimize the total emergency personnel response cost or time and ensure that emergency personnel can reach the required floor via the optimal path.

7. The intelligent dispatching method for elevator AED in complex scenarios according to claim 6 is characterized in that: In the step of establishing the AED dispatching and allocation optimization model under the complex multi-elevator system, the constraints related to the AED equipment resource configuration and floor capacity limitation include constraint one, constraint two, and constraint three, respectively, where: Constraint 1 is the resource limit of the configuration point. The total amount of resources allocated to each floor by configuration point i cannot exceed its total available resources: ; Constraint 2 is the minimum demand capacity limit and maximum demand capacity limit of the floor. The minimum demand capacity limit is , the maximum demand capacity limit is ; Constraint three is a non-negativity constraint, where the number of allocated resources cannot be negative. , n represents a positive integer set .

8. The intelligent dispatching method for elevator AED in complex scenarios according to claim 7 is characterized in that: In the step of quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling allocation optimization model, the AED scheduling allocation optimization model randomly generates candidate solutions, and the candidate solutions include the response priority C of the elevator set from the configuration point i to the floor j. ij and the elevator resources W allocated from configuration point i to floor j ij ,Right now , where K is the number of candidate solution populations, this group of candidate solutions constitutes the initial population, and each candidate solution Represents a possible position in the search space, and the candidate solution is directly substituted into the formula corresponding to the objective functions J1, J2 and J3 to obtain the model results of the optimal decision variables under each corresponding prior parameter.

9. The intelligent dispatching method for elevator AED in complex scenarios according to claim 8 is characterized in that: In the process of switching from the step of quickly screening out the optimal solution direction of the optimization problem based on the AED dispatch allocation optimization model to the step of fine processing based on the AED dispatch allocation optimization model to obtain the optimal solution of the optimization problem, the migration factor TF determines whether to switch. , where t is the current iteration number, t max is the maximum number of iterations. When TF≤0.5, continue to quickly screen out the optimal solution direction of the optimization problem; when TF>0.5, enter the fine processing to obtain the optimal solution of the optimization problem.

10. The intelligent dispatching method for elevator AED in complex scenarios according to claim 9 is characterized in that: The steps of quickly screening out the optimal solution direction of the optimization problem based on the AED scheduling and allocation optimization model include the following steps: Determine the number of individuals and the maximum number of iterations t of the allocation scheme max , a group or multiple groups of candidate solutions are randomly generated by the AED dispatch allocation optimization model, each individual in the multiple candidate solutions represents an allocation scheme for an AED device and emergency personnel who obtain the AED device, and the range of each constant parameter and acceleration is set; Substituting the candidate solution into the macro scheduling objective function, the model result of the optimal decision variable of the corresponding objective function under the prior parameters in the complex multi-elevator system is obtained, and the optimal solution direction of the allocation plan of AED equipment and emergency personnel who obtain AED equipment is quickly screened out according to the model result; Selectively update the optimization parameters of the current best individual according to the direction of the optimal solution, and use the optimization parameters of the current best individual to update the optimization parameters of other individuals in the candidate solution; Calculate the migration factor and parameter amplitude factor. The migration factor determines whether to continue to quickly screen out the optimal solution direction of the optimization problem or to enter the fine processing to obtain the optimal solution of the optimization problem. The parameter amplitude factor is used to adjust the amplitude of the optimization parameter update of the optimal individual and other individuals. When the migration factor is ≤0.5, continue to quickly screen out the optimal solution direction of the optimization problem.

11. The intelligent dispatching method for elevator AED in complex scenarios according to claim 10 is characterized in that: The steps of obtaining the optimal solution of the optimization problem based on the AED scheduling and allocation optimization model include the following steps: When the migration factor is greater than 0.5, fine processing is performed to obtain the optimal solution to the optimization problem; Perform fine local optimization according to the optimal solution direction of the allocation plan to ensure that the allocation plan in the optimal solution direction meets all constraints related to AED equipment resource configuration and floor capacity restrictions; Use the current optimal individual as the starting point and perform local iterative optimization. If a better allocation scheme is found during the iterative optimization process, the better allocation scheme is used as the new current optimal individual and the corresponding optimization parameters are updated. If no better allocation scheme is found, the optimization parameters of the current best individual are continuously updated according to the parameter amplitude factor; When the maximum number of iterations is reached or the update amplitude of the optimization parameters of the best individual is less than the preset amplitude threshold, stop this step and output the optimal solution allocation plan; Otherwise, continue with the step of selectively updating the optimization parameters of the current optimal individual according to the direction of the optimal solution and subsequent steps.

12. The intelligent dispatching method for elevator AED in complex scenarios according to any one of claims 1 to 11, characterized in that: In the step of executing AED intelligent dispatch in a complex multi-elevator system, a suboptimal solution allocation scheme is calculated simultaneously. If the optimal solution allocation scheme is interrupted during execution, the suboptimal solution allocation scheme is started.

13. A complex multi-elevator system, used in the method according to any one of claims 1 to 12, characterized in that: The complex multi-elevator system includes multiple elevator shafts, each elevator shaft is selectively configured with various types of elevators, the elevators are selectively configured to serve different partitions, and the elevators are selectively configured with AED equipment.

14. The complex multi-elevator system according to claim 13, characterized in that: The elevators include high-speed elevators, low-speed elevators, shuttle elevators, and service / freight elevators; The high-speed elevator is used to quickly reach high floors; The low-speed elevator is used to serve the lower floors; The shuttle elevator is used to quickly transport from the ground floor or transfer floor to a specific intermediate floor or sky lobby; The service / cargo elevator is used for transporting goods and service personnel, as well as for evacuation; The zoning service includes zoning elevators and double-decker elevators; The zoned elevator only serves a specific range of floors; the double-deck elevator stops at two adjacent floors at the same time.

15. An elevator AED intelligent dispatching system in complex scenarios, characterized by: The elevator AED intelligent dispatching system in complex scenarios includes a complex multi-elevator system as described in claim 13 or 14, and an AED intelligent dispatching system platform for dispatching the complex multi-elevator system and AED equipment and first aid personnel who obtain AED equipment. An AED dispatching allocation optimization model for the complex multi-elevator system is established in the AED intelligent dispatching system platform. The optimal solution direction of the optimization problem is quickly screened out based on the AED dispatching allocation optimization model, and the optimal solution of the optimization problem is obtained through fine processing based on the AED dispatching allocation optimization model, and AED intelligent dispatching is performed in the complex multi-elevator system to respond to first aid events.

16. An intelligent AED lifting platform device, used in the method according to any one of claims 1 to 12, characterized in that: The intelligent AED lifting platform equipment includes an elevator and an AED device configured in the elevator.

17. A readable storage medium, characterized in that: The readable storage medium stores a control program, and when the control program is executed by a processor, the processor executes the steps of the method according to any one of claims 1 to 12.

Images