Multi-device fault dispatching method, device, equipment and medium for voice control system

Abstract

The present application relates to a method, apparatus, device and medium for multi-device fault scheduling for a voice control system, which randomly obtains multiple candidate device populations that meet a preset population number by using a Circle chaos model to map in a candidate device set, and randomly extracts multiple candidate devices by using a Levy flight trajectory algorithm to map in various populations, and calculates the objective function according to the corresponding relevant parameters, and takes the candidate device with the smallest objective function calculation result as the optimal individual, and uses the optimal individual in various populations as the aggregation center to generate multiple populations for the next iteration until the number of iterations meets the preset number of iterations, then selects the optimal candidate device from all the optimal individuals obtained in multiple iterations according to the objective function, and replaces the current faulty device with the selected optimal candidate device to complete multi-device fault scheduling. This method can efficiently select the best replacement device that meets the cost requirements.

Description

Technical Field

[0001] The present application relates to the technical field of multi-device scheduling, and in particular to a multi-device fault scheduling method, apparatus, equipment and medium for a voice control system. Background Art

[0002] With the continuous development of science and technology, voice control systems have been widely used in many fields, including smart homes, industrial automation, medical equipment, and intelligent transportation. These systems rely on speech recognition and natural language processing technologies to enable users to control multiple devices through voice commands, thereby achieving more efficient operation and management. In this context, the multi-device collaboration of the voice control system is crucial to the overall performance of the system, especially in complex environments, where interconnection and information sharing between devices are particularly critical.

[0003] However, in actual operation, the multiple devices of the voice control system face many challenges. First, device failure is a key issue. Since the voice control system usually relies on multiple devices of different brands and models, the compatibility, stability and sensitivity of these devices to external factors (such as network conditions, power fluctuations, etc.) will affect the overall performance of the system. The failure of any single device may cause the entire system to operate unstably, fail to function, or even cause safety hazards, such as misoperation or inability to respond to emergencies. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, equipment and medium that can efficiently dispatch multiple device faults for a voice control system in response to the above technical problems.

[0005] A multi-device fault scheduling method for a voice control system, the method comprising:

[0006] Acquire a device scheduling instruction, and extract a candidate voice-controlled device set according to the device scheduling instruction, wherein the candidate voice-controlled device set includes a plurality of candidate devices;

[0007] A Circle chaos model is used to map the candidate device set, and a plurality of populations satisfying a preset population quantity are randomly obtained, each of the populations including a plurality of candidate devices;

[0008] Using the Levy flight trajectory algorithm to map in each of the populations, a plurality of candidate devices are randomly extracted, and the objective function is calculated according to the relevant parameters of the extracted plurality of candidate devices, and the candidate device with the smallest objective function calculation result is taken as the optimal individual;

[0009] Using the best individuals in each of the populations as aggregation centers to generate multiple populations for the next iteration, until the number of iterations meets the preset number of iterations, then selecting the best candidate device from all the best individuals obtained in multiple iterations according to the objective function;

[0010] The selected optimal candidate device will replace the current faulty device to complete multi-device fault scheduling.

[0011] In one embodiment, before the Circle chaos model is used to map the candidate device set, a random number generation algorithm is first used to generate multiple initial populations that meet the preset population number;

[0012] The Circle chaos model is then used to map the multiple initial populations to generate a population for subsequent iterations.

[0013] In one embodiment, the sum of candidate devices in all initial populations is less than the number of all candidate devices in the candidate device set.

[0014] In one embodiment, a Levy flight trajectory algorithm is used to map in each population, and a plurality of candidate devices are randomly extracted. It is first determined whether the extracted plurality of candidate devices meet the restriction conditions, and the objective function is calculated according to the relevant parameters of the candidate devices that meet the restriction conditions.

[0015] The constraint conditions include equality constraints and inequality constraints, wherein the equality constraints are constructed based on the power balance of the equipment, and the inequality constraints are constructed based on the power limitation of the power grid and the capacity limitation of the battery.

[0016] In one embodiment, the relevant parameters of the candidate equipment include battery power generation cost, battery degradation cost, and cost required for operation and maintenance.

[0017] In one embodiment, the objective function is constructed according to the minimum comprehensive operating cost of the candidate equipment, which is expressed as:

[0018] ;

[0019] In the above formula, represents the battery power generation cost of the candidate device, represents the battery degradation cost of the candidate device, represents the public grid electricity cost, Represents the cost required to operate and maintain the candidate equipment.

[0020] In one embodiment, the battery degradation cost of the candidate device is the battery degradation cost in a continuous time interval, which is represented by a state transition signal and accumulated energy, and is expressed as:

[0021] ;

[0022] In the above formula, represents the accumulated energy, Indicates the state transition signal. Represents the energy change equation of the battery in discrete time, Represents the battery degradation cost corresponding to a discharge event.

[0023] The present application also provides a multi-device fault scheduling device for a voice control system, the device comprising:

[0024] A device scheduling instruction acquisition module, used to acquire a device scheduling instruction, and extract a candidate voice-controlled device set according to the device scheduling instruction, wherein the candidate voice-controlled device set includes a plurality of candidate devices;

[0025] A population obtaining module, used to use the Circle chaos model to perform mapping in the candidate device set, and randomly obtain multiple populations that meet the preset population quantity, each of which includes multiple candidate devices;

[0026] A local optimal individual obtaining module is used to use the Levy flight trajectory algorithm to perform mapping in each of the populations, randomly extract multiple candidate devices, and calculate the objective function based on the relevant parameters of the extracted multiple candidate devices, and take the candidate device with the smallest objective function calculation result as the optimal individual;

[0027] The optimal backend device obtaining module is used to generate multiple populations for the next iteration using the optimal individuals in each of the populations as aggregation centers until the number of iterations meets the preset number of iterations, and then select the optimal candidate device from all the optimal individuals obtained in multiple iterations according to the objective function;

[0028] The device fault scheduling module is used to replace the current faulty device with the selected optimal candidate device to complete multi-device fault scheduling.

[0029] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0030] Acquire a device scheduling instruction, and extract a candidate voice-controlled device set according to the device scheduling instruction, wherein the candidate voice-controlled device set includes a plurality of candidate devices;

[0031] A Circle chaos model is used to map the candidate device set, and a plurality of populations satisfying a preset population quantity are randomly obtained, each of the populations including a plurality of candidate devices;

[0032] Using the Levy flight trajectory algorithm to map in each of the populations, a plurality of candidate devices are randomly extracted, and the objective function is calculated according to the relevant parameters of the extracted plurality of candidate devices, and the candidate device with the smallest objective function calculation result is taken as the optimal individual;

[0033] Using the best individuals in each of the populations as aggregation centers to generate multiple populations for the next iteration, until the number of iterations meets the preset number of iterations, then selecting the best candidate device from all the best individuals obtained in multiple iterations according to the objective function;

[0034] The selected optimal candidate device will replace the current faulty device to complete multi-device fault scheduling.

[0035] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0036] Acquire a device scheduling instruction, and extract a candidate voice-controlled device set according to the device scheduling instruction, wherein the candidate voice-controlled device set includes a plurality of candidate devices;

[0037] A Circle chaos model is used to map the candidate device set, and a plurality of populations satisfying a preset population quantity are randomly obtained, each of the populations including a plurality of candidate devices;

[0038] Using the Levy flight trajectory algorithm to map in each of the populations, a plurality of candidate devices are randomly extracted, and the objective function is calculated according to the relevant parameters of the extracted plurality of candidate devices, and the candidate device with the smallest objective function calculation result is taken as the optimal individual;

[0039] Using the best individuals in each of the populations as aggregation centers to generate multiple populations for the next iteration, until the number of iterations meets the preset number of iterations, then selecting the best candidate device from all the best individuals obtained in multiple iterations according to the objective function;

[0040] The selected optimal candidate device will replace the current faulty device to complete multi-device fault scheduling.

[0041] The above-mentioned method, apparatus, equipment and medium for multi-device fault scheduling of voice control system extracts a candidate voice control device set including multiple candidate devices according to the device scheduling instruction, uses the Circle chaos model for mapping in the candidate device set, and randomly obtains multiple populations that meet the preset population number, each population includes multiple candidate devices, and uses the Levy flight trajectory algorithm for mapping in each population, randomly extracts multiple candidate devices, and calculates the objective function based on the relevant parameters of the extracted multiple candidate devices, and takes the candidate device with the smallest objective function calculation result as the optimal individual, and uses the optimal individual in each population as the aggregation center to generate multiple populations for the next iteration until the number of iterations meets the preset number of iterations, then selects the optimal candidate device from all the optimal individuals obtained in multiple iterations according to the objective function, and replaces the current faulty device with the selected optimal candidate device to complete multi-device fault scheduling. This method can efficiently select the best replacement device that meets the cost requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flowchart of a multi-device fault scheduling method for a voice control system in one embodiment;

[0043] Figure 2 is a structural block diagram of a multi-device fault scheduling device for a voice control system in one embodiment;

[0044] Figure 3 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] In view of the problem in the prior art that when a voice control device fails in a voice control system deployed in a large industrial scene, it is necessary to select the best voice control device suitable for the current scene from a large number of candidate devices, but there is no efficient scheduling method, in this application, Figure 1 As shown, a multi-device fault scheduling method for a voice control system is provided, which specifically includes the following steps:

[0047] Step S100: acquiring a device scheduling instruction, and extracting a candidate voice-controlled device set according to the device scheduling instruction, wherein the candidate voice-controlled device set includes a plurality of candidate devices.

[0048] Step S110, using the Circle chaos model to perform mapping in the candidate device set, randomly obtaining a plurality of populations that meet a preset population quantity, each of the populations including a plurality of candidate devices.

[0049] Step S120, using the Levy flight trajectory algorithm to map in various groups, randomly extracting multiple candidate devices, and calculating the objective function based on the relevant parameters of the extracted multiple candidate devices, and taking the candidate device with the smallest objective function calculation result as the optimal individual.

[0050] Step S130, using the best individuals in various populations as aggregation centers to generate multiple populations for the next iteration, until the number of iterations meets the preset number of iterations, then selecting the best candidate device from all the best individuals obtained in multiple iterations according to the objective function.

[0051] Step S140: Replace the current faulty device with the selected optimal candidate device to complete multi-device fault scheduling.

[0052] In the present application, the best candidate device is quickly selected from a large number of candidate voice-controlled devices based on a genetic algorithm.

[0053] In step S100, when a certain voice control device in the voice control system fails, a device dispatch instruction is issued to select a suitable candidate device from a large number of candidate voice control devices in the candidate voice control device set for dispatch to replace the currently failed device. The candidate device in the candidate voice control device set is not a candidate device currently operating in the voice control system.

[0054] In step S110, before using the Circle chaos model to map the candidate device set, a random number generation algorithm is first used to generate multiple initial populations that meet the preset population size. Each population includes l samples represented as , each sample Include Feature Components . Each sample in the population represents a random candidate device, and the multiple feature components corresponding to each candidate device are different attributes or parameters.

[0055] Specifically, candidate devices are randomly selected from the candidate device set to form different initial populations, rather than directly grouping the candidate devices in the candidate device set, so that the sum of candidate devices in all initial populations is less than the number of all candidate devices in the candidate device set.

[0056] The Circle chaos model, generally referred to as the "Circle Map chaos model", is a typical one-dimensional discrete dynamic system. From a geometric point of view, the model can be regarded as an iterative mapping of points on a unit circle according to certain rules. When the parameters and take different values, the system will exhibit different dynamic behaviors, including periodic motion, quasi-periodic motion and chaotic motion. This model provides a simple and effective model for studying the chaos generation mechanism and transition process of nonlinear systems. For example, it can be used as a basic model when studying nonlinear vibrations and chaotic phenomena in circuits in the fields of physics and engineering. It is also commonly used in signal processing and communication. Chaotic signals have broadband and noise-like characteristics. The signals generated by the Circle chaos model can be used for encrypted communications, using its sensitivity to initial conditions to increase the confidentiality of communications; it can also be used to generate complex test signals for detecting and analyzing the performance of nonlinear systems.

[0057] Furthermore, the Circle chaos model is used to map multiple initial populations to improve the population quality and generate a population for subsequent iterations. The improved initial population generation is expressed as:

[0058] ;

[0059] In step S120, the Levy flight trajectory algorithm is used to perform mapping in each population, and multiple candidate devices are randomly extracted to prevent the result from falling into a local optimal solution too early.

[0060] Levy flight trajectory algorithm, namely Levy Flight, is a random walk model. Levy flight is a non-Gaussian random process. In two-dimensional or multi-dimensional space, the movement trajectory of an individual (such as in animal foraging, particle diffusion, etc.) consists of a series of relatively long linear displacements (large step length) and frequent short-distance movements (small step length). The probability distribution of the step length obeys the Levy distribution, and its probability density function has a heavy-tailed characteristic, which means that the probability of long-distance movement is smaller than that of short-distance movement, but it is still not negligible. The advantages of this algorithm include strong global search capability, effective simulation of natural phenomena, and high flexibility.

[0061] Specifically, for these further randomly extracted candidate devices, it is necessary to first determine whether the restriction conditions are met, so that at any given moment, the candidate devices must ensure the stable operation of the voice control system.

[0062] In this embodiment, the constraint conditions include equality constraints and inequality constraints, wherein the equality constraints are constructed based on the power balance of the equipment and are expressed as:

[0063] ;

[0064] In the above formula, Indicates the electrical load. Indicates the power generated by the public grid. Indicates that the candidate device is within a certain period of time. The average power within.

[0065] In this embodiment, the inequality constraint is constructed based on the power limit of the power grid and the capacity limit of the battery, and is expressed as:

[0066] ;

[0067] In this embodiment, before determining the restriction conditions of a plurality of candidate devices randomly extracted from various groups, a compliance check is also performed to prevent the restriction from causing damage to the device or making the solution infeasible.

[0068] Specifically, first determine whether the multiple candidate devices extracted meet the constraints, and then calculate the objective function based on the relevant parameters of the candidate devices that meet the constraints. Only among the candidate devices that meet the constraints, the objective function will be calculated based on the relevant parameters of these devices. These conditions ensure that the system can maintain stable operation when scheduling equipment, avoid selecting equipment that cannot work properly under specific environments or conditions, prevent equipment damage or safety accidents caused by overload, reduce risks in subsequent operations, and improve the success rate of scheduling plans.

[0069] In this embodiment, after randomly extracting multiple candidate devices from each population and judging the constraints of these candidate devices, the objective function is calculated according to the relevant parameters of the candidate devices that meet the constraints, and the candidate device with the smallest calculation result is saved as the optimal individual. Among them, the objective function is constructed according to the minimum comprehensive operating cost of the candidate device, which is expressed as:

[0070] ;

[0071] In the above formula, represents the battery power generation cost of the candidate device, represents the battery degradation cost of the candidate device, represents the public grid electricity cost, Represents the cost required to operate and maintain the candidate equipment.

[0072] Specifically, when calculating the battery power generation cost of candidate equipment When , the relationship between cost and power is:

[0073] ;

[0074] In the above formula, , , are constants, is the output power of the battery, is the cost of generating electricity.

[0075] Specifically, when calculating the cost of public grid electricity When , the public grid power generation cost can be expressed as:

[0076] ;

[0077] In the above formula, for The electricity price at the time, is the power generated by the public grid.

[0078] Power generation is priced using valley and peak electricity prices, and public grid electricity prices are divided into three stages: valley, flat and peak.

[0079] Specifically, when calculating the costs required for operation and maintenance When , the processing cost is expressed as:

[0080] ;

[0081] In the above formula, and are the weight coefficients of operation and maintenance of the i-th equipment, is the output power of the voice-controlled device; The output power of the main network.

[0082] Specifically, when calculating the battery degradation cost Consider a charging event that starts at time t and lasts for a period of time The average power in , then the battery charge depth during this time interval is It can be expressed as:

[0083] ;

[0084] In the formula, Is the actual capacity at time t. Charge and discharge efficiency coefficient and The average degradation cost per unit energy can be expressed as:

[0085] ;

[0086] By simply multiplying the energy delivered by the battery, the battery degradation cost corresponding to this discharge event can be obtained:

[0087] ;

[0088] Considering the charging and discharging efficiency, the energy change equation of the battery in discrete time is: ,Since the degradation cost of the battery in each time interval can only be determined after the charging or discharging event is over, the power flow direction of the battery must be specified. To this end, g(t) is first expressed as an auxiliary binary variable, representing the state transition of the charging and discharging events in two consecutive time intervals as:

[0089] ;

[0090] Furthermore, Expressed as the accumulated energy in kWh before the change cycle event. It can be expressed as ,Therefore, the battery degradation cost of the candidate device is the battery degradation cost in consecutive time intervals, represented by the state transition signal and the accumulated energy, which is expressed as:

[0091] ;

[0092] In the above formula, represents the accumulated energy, Indicates the state transition signal. Represents the energy change equation of the battery in discrete time, Represents the battery degradation cost corresponding to a discharge event.

[0093] Furthermore, according to the objective function, the best individuals in each population are selected, and then the next iteration is performed with each best individual as the aggregation center until the number of iterations meets the preset number of times and all individuals in the population are close to or equal to the best individual, then the optimal scheduling plan for multiple devices of the voice control system is found.

[0094] In step S140, after completing multiple iterations, the final optimal scheduling solution, that is, a candidate device, is selected from multiple optimal individuals according to the objective function, and the candidate device is used to replace the faulty device, thereby completing the scheduling of the faulty device.

[0095] In the above-mentioned multi-device fault scheduling method for the voice control system, a candidate voice control device set including multiple candidate devices is extracted according to the device scheduling instruction, and the Circle chaos model is used for mapping in the candidate device set to randomly obtain multiple populations that meet the preset population number, each population includes multiple candidate devices, and the Levy flight trajectory algorithm is used for mapping in each population, and multiple candidate devices are randomly extracted. The objective function is calculated based on the relevant parameters of the extracted multiple candidate devices, and the candidate device with the smallest objective function calculation result is taken as the optimal individual. The optimal individuals in each population are used as the aggregation center to generate multiple populations for the next iteration until the number of iterations meets the preset number of iterations. Then, the optimal candidate device is selected from all the optimal individuals obtained in multiple iterations according to the objective function, and the selected optimal candidate device replaces the current faulty device to complete the multi-device fault scheduling. This method not only considers the cost-effectiveness of operation and maintenance, but also adds equipment degradation to the comprehensive cost considerations, establishes the objective function with the lowest comprehensive operating cost, and uses the Circle chaos mapping and Levy flight trajectory strategies to improve the sine-cosine optimization algorithm, so that the improved algorithm has a significant improvement in optimization performance. The improved sine-cosine optimization algorithm is used to optimize the operating cost of the multi-device system of the voice control system, resulting in a lower-cost multi-device scheduling solution for the voice control system.

[0096] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0097] In one embodiment, Figure 2 As shown, a multi-device fault scheduling device for a voice control system is provided, comprising: a device scheduling instruction acquisition module 200, a population acquisition module 210, a local optimal individual acquisition module 220, an optimal back-end device acquisition module 230 and a device fault scheduling module 240, wherein:

[0098] The device scheduling instruction acquisition module 200 is used to acquire the device scheduling instruction and extract a candidate voice-controlled device set according to the device scheduling instruction, wherein the candidate voice-controlled device set includes a plurality of candidate devices;

[0099] A population obtaining module 210 is used to use the Circle chaos model to perform mapping in the candidate device set, and randomly obtain multiple populations that meet a preset population quantity, each of which includes multiple candidate devices;

[0100] The local optimal individual obtaining module 220 is used to use the Levy flight trajectory algorithm to perform mapping in each of the populations, randomly extract multiple candidate devices, and calculate the objective function according to the relevant parameters of the extracted multiple candidate devices, and take the candidate device with the smallest objective function calculation result as the optimal individual;

[0101] The optimal backend device obtaining module 230 is used to generate multiple populations for the next iteration using the optimal individuals in each of the populations as aggregation centers until the number of iterations meets the preset number of iterations, and then select the optimal candidate device from all the optimal individuals obtained in multiple iterations according to the objective function;

[0102] The device fault scheduling module 240 is used to replace the current faulty device with the selected optimal candidate device to complete multi-device fault scheduling.

[0103] For the specific definition of the multi-device fault scheduling device for the voice control system, please refer to the definition of the multi-device fault scheduling method for the voice control system mentioned above, which will not be repeated here. Each module in the above-mentioned multi-device fault scheduling device for the voice control system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0104] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store candidate voice control device set data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a multi-device fault scheduling method for a voice control system is implemented.

[0105] Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0106] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0107] Acquire a device scheduling instruction, and extract a candidate voice-controlled device set according to the device scheduling instruction, wherein the candidate voice-controlled device set includes a plurality of candidate devices;

[0108] A Circle chaos model is used to map the candidate device set, and a plurality of populations satisfying a preset population quantity are randomly obtained, each of the populations including a plurality of candidate devices;

[0109] Using the Levy flight trajectory algorithm to map in each of the populations, a plurality of candidate devices are randomly extracted, and the objective function is calculated according to the relevant parameters of the extracted plurality of candidate devices, and the candidate device with the smallest objective function calculation result is taken as the optimal individual;

[0110] Using the best individuals in each of the populations as aggregation centers to generate multiple populations for the next iteration, until the number of iterations meets the preset number of iterations, then selecting the best candidate device from all the best individuals obtained in multiple iterations according to the objective function;

[0111] The selected optimal candidate device will replace the current faulty device to complete multi-device fault scheduling.

[0112] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0113] Acquire a device scheduling instruction, and extract a candidate voice-controlled device set according to the device scheduling instruction, wherein the candidate voice-controlled device set includes a plurality of candidate devices;

[0114] A Circle chaos model is used to map the candidate device set, and a plurality of populations satisfying a preset population quantity are randomly obtained, each of the populations including a plurality of candidate devices;

[0115] Using the Levy flight trajectory algorithm to map in each of the populations, a plurality of candidate devices are randomly extracted, and the objective function is calculated according to the relevant parameters of the extracted plurality of candidate devices, and the candidate device with the smallest objective function calculation result is taken as the optimal individual;

[0116] Using the best individuals in each of the populations as aggregation centers to generate multiple populations for the next iteration, until the number of iterations meets the preset number of iterations, then selecting the best candidate device from all the best individuals obtained in multiple iterations according to the objective function;

[0117] The selected optimal candidate device will replace the current faulty device to complete multi-device fault scheduling.

[0118] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0119] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0120] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A multi-device fault scheduling method for a voice control system, characterized in that: The method comprises: Acquire a device scheduling instruction, and extract a candidate voice-controlled device set according to the device scheduling instruction, wherein the candidate voice-controlled device set includes a plurality of candidate devices; A Circle chaos model is used to map the candidate device set, and a plurality of populations satisfying a preset population quantity are randomly obtained, each of the populations including a plurality of candidate devices; Using the Levy flight trajectory algorithm to map in each of the populations, a plurality of candidate devices are randomly extracted, and the objective function is calculated according to the relevant parameters of the extracted plurality of candidate devices, and the candidate device with the smallest objective function calculation result is taken as the optimal individual; Using the best individual in each of the populations as the aggregation center to generate multiple populations for the next iteration, until the number of iterations meets the preset number of iterations, then selecting the best candidate device from all the best individuals obtained in multiple iterations according to the objective function; The selected optimal candidate device will replace the current faulty device to complete multi-device fault scheduling.

2. The multi-device fault scheduling method for a voice control system according to claim 1, characterized in that: Before using the Circle chaos model to map the candidate device set, a random number generation algorithm is first used to generate multiple initial populations that meet the preset population number; The Circle chaos model is then used to map the multiple initial populations to generate a population for subsequent iterations.

3. The multi-device fault scheduling method for a voice control system according to claim 2, characterized in that: The sum of candidate devices in all initial populations is less than the number of all candidate devices in the candidate device set.

4. The multi-device fault scheduling method for a voice control system according to claim 3, characterized in that: A Levy flight trajectory algorithm is used to map in each of the populations, and a plurality of candidate devices are randomly extracted. It is first determined whether the plurality of candidate devices extracted meet the restriction conditions, and an objective function is calculated according to relevant parameters of the candidate devices that meet the restriction conditions. The constraint conditions include equality constraints and inequality constraints, wherein the equality constraints are constructed based on the power balance of the equipment, and the inequality constraints are constructed based on the power limitation of the power grid and the capacity limitation of the battery.

5. The multi-device fault scheduling method for a voice control system according to claim 4, characterized in that: The relevant parameters of the candidate equipment include battery power generation cost, battery degradation cost, and cost required for operation and maintenance.

6. The multi-device fault scheduling method for a voice control system according to any one of claims 1 to 5, characterized in that: The objective function is constructed according to the minimum comprehensive operating cost of the candidate equipment and is expressed as: In the above formula, represents the battery power generation cost of the candidate device, represents the battery degradation cost of the candidate device, represents the public grid electricity cost, Represents the cost required to operate and maintain the candidate equipment.

7. The multi-device fault scheduling method for a voice control system according to claim 6, characterized in that: The battery degradation cost of the candidate device is the battery degradation cost in a continuous time interval, which is represented by the state transition signal and the accumulated energy, and is expressed as: In the above formula, The accumulated energy is expressed as: in, It is represented as a charging event starting at time t, and its average power within a time interval ∆t is , is an auxiliary binary variable, which indicates the state transition signal of the charge and discharge events in two consecutive time intervals, and is expressed as: ， The energy change equation of the battery in discrete time is expressed as: in, and represents the charge and discharge efficiency coefficient, Represents the battery degradation cost corresponding to a discharge event.

8. A multi-device fault dispatching device for a voice control system, characterized in that: The device comprises: A device scheduling instruction acquisition module, used to acquire a device scheduling instruction, and extract a candidate voice-controlled device set according to the device scheduling instruction, wherein the candidate voice-controlled device set includes a plurality of candidate devices; A population obtaining module, used to use the Circle chaos model to perform mapping in the candidate device set, and randomly obtain multiple populations that meet the preset population quantity, each of which includes multiple candidate devices; A local optimal individual obtaining module is used to use the Levy flight trajectory algorithm to perform mapping in each of the populations, randomly extract multiple candidate devices, and calculate the objective function based on the relevant parameters of the extracted multiple candidate devices, and take the candidate device with the smallest objective function calculation result as the optimal individual; The optimal backend device obtaining module is used to generate multiple populations for the next iteration using the optimal individuals in each of the populations as aggregation centers until the number of iterations meets the preset number of iterations, and then select the optimal candidate device from all the optimal individuals obtained in multiple iterations according to the objective function; The device fault scheduling module is used to replace the current faulty device with the selected optimal candidate device to complete multi-device fault scheduling.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 6 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 6 to 7 are implemented.

Images