Intelligent equipment control method and device, medium and intelligent equipment system

Abstract

The invention provides an intelligent device control method and device, a medium and an intelligent device system.The method comprises the steps that control instructions of multiple intelligent devices are received, and whether a conflict instruction exists or not is determined based on an intelligent device knowledge graph and the control instructions of all the intelligent devices, the intelligent equipment knowledge graph at least comprises relationships between parameters of the intelligent equipment and a circuit maximum load, a security strategy and an energy consumption budget; under the condition that the existence of the conflict instruction is determined, at least determining a conflict execution queue according to the conflict instruction, a preset priority and environment information by adopting a multi-objective optimization algorithm, the environment information including temperature, illumination and electricity price; and controlling the intelligent equipment corresponding to the conflict instruction at least according to the conflict execution queue. Therefore, the problem that the control conflict of the intelligent equipment is difficult to effectively manage in the existing scheme is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, in particular to a control method of a smart device, a control device of a smart device, a computer readable storage medium and a smart device system. BACKGROUND

[0002] At present, the existing technical scheme is that the smart home system generally adopts scene automatic control based on a rule engine or a cloud large model, which can trigger device linkage according to preset conditions. However, these schemes have significant defects: first, the system lacks a global perspective and cannot effectively coordinate deep conflicts caused by simultaneous or sequential triggering of multiple scenes, such as resource contention (e.g., the direct contradiction between starting a high-power water heater in the “bathing scene” and limiting the operation of high-energy-consumption devices in the “energy-saving scene”), safety and convenience conflicts (e.g., the contradiction between locking doors and windows in the “security scene” and unlocking the access control in the “homecoming scene”), and functional exclusion failure (e.g., the interference between turning off the lights in the “theater mode” and turning on the lights in the “reading scene”). Second, the existing conflict detection mechanism can only identify direct logical conflicts on the same device and is powerless against implicit resource competition (e.g., total power overload), leading to chaotic system behavior and even safety hazards such as circuit overload.

[0003] That is, the existing scheme cannot effectively manage the control conflicts of smart devices. SUMMARY

[0004] The main purpose of the present application is to provide a control method of a smart device, a control device of a smart device, a computer readable storage medium and a smart device system to at least solve the problem that the existing scheme cannot effectively manage the control conflicts of smart devices.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a control method of a smart device is provided, which comprises: receiving multiple control instructions of smart devices, and determining whether there is a conflict instruction based on a smart device knowledge graph and at least part of all the control instructions of the smart devices, wherein the smart device knowledge graph at least includes the relationship between the parameters of the smart devices and the constraint factors, and the constraint factors are at least one of the following: circuit maximum load, security strategy, energy consumption, operation constraint and compatibility information; in the case where it is determined that there is the conflict instruction, a multi-objective optimization algorithm is used to determine at least a conflict execution queue according to the conflict instruction, a preset priority and environmental information; and the smart devices corresponding to the conflict instruction are controlled according to the conflict execution queue and control requirements, wherein the control requirements at least include the control parameters of the smart devices to be controlled.

[0006] Optionally, a multi-objective optimization algorithm is used to determine at least the conflict execution queue based on the conflict instructions, preset priorities, and environmental information. This includes: using a multi-objective optimization algorithm to determine the conflict execution queue and control requirements based on the conflict instructions, preset priorities, and environmental information. The control requirements also include the control interval duration between adjacent smart devices to be controlled in the control sequence.

[0007] Optionally, a multi-objective optimization algorithm is used to determine at least a conflict execution queue based on the conflicting instructions, preset priorities, and environmental information, including: using a genetic algorithm to process the conflicting instructions, preset priorities, and environmental information to obtain multiple executable schemes and corresponding scores; determining the target execution scheme as the executable scheme corresponding to the maximum score; and determining the conflict execution queue based on the target execution scheme.

[0008] Optionally, before controlling the smart device corresponding to the conflicting instruction according to the conflicting execution queue and control requirements, the method further includes: using an LSTM network to evaluate the health indicators of the smart devices in the conflicting execution queue to obtain the failure probability and remaining lifetime; and determining whether to control the corresponding smart device based on the failure probability and the remaining lifetime.

[0009] Optionally, before controlling the smart device corresponding to the conflicting instruction according to the conflict execution queue and control requirements, the method further includes: using an isolated forest algorithm to analyze the degree of deviation of the motion trajectory of the smart device in the conflict execution queue; and determining whether to control the corresponding smart device based on the degree of deviation and the risk level of the smart device.

[0010] Optionally, after controlling the smart device corresponding to the conflict instruction according to the conflict execution queue and control requirements, the method includes: adjusting the weights of each parameter of the multi-objective optimization algorithm using historical conflict events and corresponding solutions.

[0011] Optionally, the method further includes: if it is determined that there are no conflicting instructions, executing all the control instructions of the smart device in chronological order.

[0012] According to another aspect of this application, a control device for a smart device is provided, comprising: a receiving unit, configured to receive multiple control commands for the smart device, and determine whether conflicting commands exist based on a smart device knowledge graph and at least a portion of all the control commands for the smart device, wherein the smart device knowledge graph includes at least the relationship between parameters of the smart device and constraints, and the constraints are at least one of the following: maximum load that the circuit can withstand, security strategy, energy consumption, operational constraints, and compatibility information; a first processing unit, configured to, upon determining the existence of the conflicting commands, employ a multi-objective optimization algorithm to determine at least a conflict execution queue based on the conflicting commands, a preset priority, and environmental information; and a second processing unit, configured to control the smart device corresponding to the conflicting commands according to the conflict execution queue and control requirements, wherein the control requirements include at least the control parameters of the smart device to be controlled.

[0013] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform any of the methods described.

[0014] According to another aspect of this application, a smart device system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any one of the methods described.

[0015] Applying the technical solution of this application, the core of this application lies in constructing a smart device knowledge graph. This graph not only covers the basic parameters of the devices (such as power, safety functions, protocol compatibility, etc.), but also describes in detail the relationship between the devices and global home rules (maximum circuit load, security strategies, energy consumption budget). Through this detailed graph, the system can perform in-depth analysis and simulation based on rich semantic information and a global view at the very beginning of receiving control commands. This method surpasses traditional conflict detection, and can predict potential resource competition, security conflicts, and functional mutual exclusions before the command is issued, thereby taking measures in advance to avoid conflicts. Once a potential conflict is detected, this application does not simply process the conflicting command according to a preset single priority rule, but adopts an advanced multi-objective optimization algorithm. This algorithm can comprehensively consider multiple dimensions such as safety, energy consumption, comfort, and user preferences, rather than focusing on only one or a few objectives. Driven by algorithms, the system not only eliminates direct logical conflicts between instructions but also finds a balance point when conflicts occur. This ensures that decisions are made in a way that best meets user needs and experience while maintaining safety and economy. For example, it adjusts the device activation time window or dynamically adjusts scene priorities to achieve optimal resource allocation and user experience. Compared to traditional solutions, this application further enhances the system's flexibility and intelligence by dynamically adjusting device control strategies through real-time collection and analysis of environmental information (such as temperature, light intensity, and electricity prices). For instance, it prioritizes high-energy-consuming tasks when electricity prices are low and automatically reduces the power consumption of lighting equipment when there is sufficient light. This real-time adjustment based on environmental information allows the system to make timely and reasonable decisions in the ever-changing home environment, further optimizing resource utilization and reducing inconvenience caused by decision-making delays. This solves the problem of existing solutions' difficulty in effectively managing control conflicts of smart devices. Attached Figure Description

[0016] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 A flowchart illustrating a control method for a smart device according to an embodiment of this application is shown.

[0018] Figure 2 A structural block diagram of a control device for a smart device according to an embodiment of this application is shown. Detailed Implementation

[0019] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] As described in the background section, current solutions in smart home systems generally employ scene-based automated control based on rule engines or cloud-based large models, capable of triggering device linkage according to preset conditions. However, these solutions have significant drawbacks: First, the system lacks a global perspective and cannot effectively coordinate deep conflicts arising from the simultaneous or sequential triggering of multiple scenes, such as resource contention (e.g., the direct contradiction between "bathing scene" activating a high-power water heater and "energy-saving scene" restricting the operation of high-energy-consuming devices), conflicts between security and convenience (e.g., the contradiction between "security scene" locking doors and windows and "home scene" unlocking access control commands), and functional exclusivity failures (e.g., interference between "cinema mode" turning off lights and "reading scene" turning on lights). Second, existing conflict detection mechanisms can only identify direct logical conflicts involving the same device, and are powerless against implicit resource competition (e.g., total power overload), leading to chaotic system behavior and even safety hazards such as circuit overload. To address the problem of existing solutions' inability to effectively manage control conflicts of smart devices, embodiments of this application provide a control method for smart devices, a control device for smart devices, a computer-readable storage medium, and a smart device system.

[0023] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0024] This embodiment provides a control method for a smart device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0025] Figure 1 This is a flowchart of a control method for a smart device according to an embodiment of this application. For example... Figure 1 As shown, the method includes the following steps:

[0026] Step S101: Receive multiple control commands from smart devices, and determine whether there are conflicting commands based on the smart device knowledge graph and at least a portion of all the control commands from the aforementioned smart devices. The smart device knowledge graph includes at least the relationship between the parameters of the smart devices and the constraints. The constraints are at least one of the following: the maximum load that the circuit can withstand, security strategy, energy consumption, operational constraints, and compatibility information.

[0027] Parameters of smart devices: Physical characteristics: including device size, weight, and installation location. This information helps understand the device's placement and physical limitations in the home environment. Electrical parameters: such as rated power, voltage range, and current requirements. These are crucial for assessing the device's energy consumption and circuit load during startup. Functional characteristics: the operations the device can perform, such as switching lighting on and off, adjusting brightness, and changing colors; starting, stopping, and switching modes for home appliances. Safety functions: the device's built-in safety features, such as anti-pry and anti-tailgating functions for door locks, the sensitivity and alarm threshold of smoke detectors, and the night vision capabilities and motion detection sensitivity of smart cameras. Health status indicators: including device uptime, failure frequency, and maintenance records. These are used to predict the device's lifespan and potential failure risks.

[0028] In addition, constraint elements:

[0029] Maximum load capacity of a circuit: This refers to the maximum electrical demand that a household electrical system can safely handle. Every household's electrical circuit design has a rated capacity; exceeding this capacity may lead to circuit overload and safety hazards such as fires and equipment damage. The maximum load is usually determined by the rating of the fuses or circuit breakers in the circuit and is also limited by the power grid's supply capacity. In a smart home environment, understanding the circuit's maximum load is fundamental to avoiding resource conflicts and ensuring the safe operation of equipment.

[0030] Security strategies: refer to the rules and plans set to protect the safety of household property and personnel. These strategies may include, but are not limited to: automatically turning on or off the security system at scheduled times (such as arming the system automatically at night). Monitoring the status of doors and windows to ensure they are closed during specific periods. Linking security devices, such as automatically turning on all lights when an intrusion alarm is triggered and sending an alarm notification. Managing the permissions of specific users or visitors to control access to devices such as door locks.

[0031] Energy consumption: In the smart home scenario, energy consumption refers to the total amount of electricity used by household devices or the electrical energy consumption per unit time. Reasonable management of energy consumption not only helps to save energy and reduce electricity bills, but is also the key to improving the energy efficiency and environmental awareness of the home. The smart home system should be able to dynamically adjust the usage patterns of devices according to the energy consumption budget set by the user, prioritize the startup of energy-efficient devices, or perform high-energy-consuming tasks during periods of lower electricity prices.

[0032] Operation constraints: Operation constraints define the conditions and limitations for the use of smart devices to ensure that the devices operate within a safe, reasonable and effective range. For example: the minimum and maximum operating times of the device to avoid overuse causing device fatigue or energy consumption waste. The operation sequence of specific devices, such as turning on the air conditioner first and then the air purifier to optimize the indoor air quality. The usage frequency limit of the device to avoid shortening the device life due to frequent state switching in a short period.

[0033] Compatibility information: Compatibility information involves the protocols, interfaces and functional compatibility between different smart devices in the home. In a smart home environment, devices may come from different brands and use different communication protocols (such as Wi-Fi, Zigbee, Bluetooth, etc.). Compatibility information ensures that all devices can cooperate seamlessly and there will be no linkage failures due to protocol mismatches or functional conflicts. In addition, compatibility also includes data sharing and interoperability between devices, such as whether the temperature data of the air conditioner can be synchronized to the smart light to achieve automatic dimming based on the indoor temperature.

[0034] Step S102, in the case of determining the existence of the above conflict instructions, at least determine a conflict execution queue according to the above conflict instructions, preset priorities and environmental information by using a multi-objective optimization algorithm;

[0035] The preset priority is the priority preset by the user.

[0036] Step S103, control the smart devices corresponding to the above conflict instructions according to the above conflict execution queue and control requirements, and the above control requirements at least include the control parameters of the smart devices to be controlled.

[0037] Relationship between smart device parameters and the maximum load a circuit can withstand: Water heater and total circuit load: Water heaters are common high-power devices in homes, with a rated power of 3000W. Assuming the current circuit's maximum load capacity is 8000W, when the system predicts that simultaneously starting the water heater, air conditioner (rated power 2000W), and microwave oven (rated power 1000W) will result in a total power of 6000W, close to but not exceeding the circuit's maximum load capacity, the system can allow these devices to operate simultaneously. However, if an oven (rated power 2500W) is added, the total power will exceed the limit. The system will recognize the risk of circuit overload and adjust the device operation strategy, such as delaying the oven's start-up time.

[0038] The Relationship Between Smart Device Parameters and Security Strategies: Smart Locks and Home Security Rules: Smart locks are an important component of security systems, featuring remote unlocking, password unlocking, and automatic locking. One home security rule is "automatic arming at night," meaning all doors and windows should remain closed during a preset time period at night. In the security diagram, smart lock parameters (such as lock status and unlocking method) are associated with the nighttime security rule. The system prioritizes executing the security command to close all doors and windows. If a "family member returning home" scenario triggers the lock unlock command, the system will assess whether this action violates the nighttime security rule and, under the premise of ensuring security, conduct intelligent arbitration. For example, if family members are notified via an app that the system is armed, manual confirmation to unlock is required.

[0039] The relationship between air conditioner-related smart device parameters and energy consumption budget: Air conditioners are the main source of household energy consumption in summer, and their operating time, set temperature, and power level directly affect the total energy consumption of the household. In the knowledge graph, air conditioner parameters (such as power and operating mode) are linked to the household's set daily energy consumption budget. For example, if the daily energy consumption is set to no more than 30 kWh, and the air conditioner consumes approximately 1.5 kWh per hour in "cooling mode," when the system predicts that continuous operation of the air conditioner will exceed the energy consumption budget during peak electricity consumption periods, it will intelligently adjust the air conditioner's operating mode or time, such as automatically switching to "energy-saving mode" or postponing non-urgent air conditioner use, to ensure that energy consumption is controlled within the budget.

[0040] The Relationship Between Smart Device Parameters and Operational Constraints: Smart curtains have multiple operating modes, including automatic, manual, and timed modes. Operational constraints may include "the time the curtains automatically open and close each day" and "manual operation is not allowed during specific times." For example, the automatic closing time of the curtains might be set between 3 PM and 4 AM to ensure privacy and security. In the knowledge graph, the operating mode parameters of the smart curtains are associated with the operation time constraints. The system ensures that the curtain closing command is automatically executed during the set time period. When responding to manual operation commands at other times, it checks whether the operational constraints are violated. For example, if a command to manually open the curtains is received at 3 PM, the system will evaluate and execute it. However, if the same command is received at 4 PM, the system will prevent execution to maintain the consistency of the operating rules.

[0041] Relationship between device parameters and compatibility information: Smart speakers may support both Wi-Fi and Bluetooth communication protocols, but some devices may only support ZigBee or proprietary protocols. When building the knowledge graph, the system records the protocol types supported by each device and considers protocol compatibility in device interaction scenarios. For example, when a user attempts to control a smart light bulb that only supports the ZigBee protocol via a smart speaker (Wi-Fi connection), the system will identify a protocol mismatch. To resolve this conflict, the system automatically invokes a protocol conversion middleware to convert Wi-Fi commands into ZigBee signals, ensuring the correct execution of control commands, and simultaneously updates the compatibility information in the knowledge graph to reflect this conversion process.

[0042] Smart devices can be smart home devices, such as refrigerators and televisions.

[0043] The core of this application lies in constructing a smart device knowledge graph. This graph not only covers the basic parameters of the devices (such as power, safety functions, protocol compatibility, etc.), but also describes in detail the relationship between the devices and global home rules (maximum circuit load, security strategies, energy consumption budget). Through this detailed graph, the system can perform in-depth analysis and simulation based on rich semantic information and a global view at the very beginning of receiving control commands. This method surpasses traditional conflict detection, enabling it to predict potential resource competition, security conflicts, and functional mutual exclusions before commands are issued, thereby taking measures in advance to avoid conflicts. Once a potential conflict is detected, this application does not simply process the conflicting command according to a preset single priority rule, but instead employs an advanced multi-objective optimization algorithm. This algorithm can comprehensively consider multiple dimensions such as safety, energy consumption, comfort, and user preferences, rather than focusing on only one or a few objectives. Driven by algorithms, the system not only eliminates direct logical conflicts between instructions but also finds a balance point when conflicts occur. This ensures that decisions are made in a way that best meets user needs and experience while maintaining safety and economy. For example, it adjusts the device activation time window or dynamically adjusts scene priorities to achieve optimal resource allocation and user experience. Compared to traditional solutions, this application further enhances the system's flexibility and intelligence by dynamically adjusting device control strategies through real-time collection and analysis of environmental information (such as temperature, light intensity, and electricity prices). For instance, it prioritizes high-energy-consuming tasks when electricity prices are low and automatically reduces the power consumption of lighting equipment when there is sufficient light. This real-time adjustment based on environmental information allows the system to make timely and reasonable decisions in the ever-changing home environment, further optimizing resource utilization and reducing inconvenience caused by decision-making delays. This solves the problem of existing solutions' difficulty in effectively managing control conflicts of smart devices.

[0044] To resolve command conflicts, there are two control methods: one is to control all devices involved in the conflict, and the other is to control only some devices to avoid control conflicts with other devices.

[0045] In a smart home environment, a conflict execution queue is an advanced mechanism for managing and optimizing device linkage commands. Its main function is to prevent immediate execution of commands when the system detects potential resource contention, security conflicts, or functional incompatibilities among multiple commands. Instead, these commands are temporarily placed in a special queue, the conflict execution queue, for subsequent evaluation and arbitration.

[0046] Specifically, the conflict execution queue may include:

[0047] Scene instruction information: Each item in the queue records in detail the scene instructions triggered by the user or automatically generated by the system, including the scene name, device operation list (such as "turn on the air conditioner" or "close the curtains"), trigger conditions (such as time, user location, external environment data), etc.

[0048] Conflict Identifier: When the system detects a potential conflict between instructions, it will mark the conflict type in the relevant instruction entries, such as resource contention, security conflict, or functional mutual exclusion, as well as the degree of conflict (minor, moderate, severe).

[0049] Device status information: This includes the current working status and operating parameters of all smart devices, such as whether they are running, remaining battery power, network connection status, etc., so that the actual operating conditions of the devices can be taken into account during arbitration.

[0050] Timestamps and priorities: Each instruction is marked with a trigger timestamp and assigned a priority value based on user-defined rules or system default settings, which facilitates execution according to priority or adjustment of execution order when resources are limited.

[0051] User preferences and environmental data: Records user preference settings and real-time environmental data, such as temperature and humidity. These are important factors to consider during the arbitration process to meet personalized needs and environmental adaptability.

[0052] Conflict prediction results: The simulation engine analyzes each combination of scenario commands to obtain the results, including possible conflicts, safety risk assessments, and energy consumption predictions.

[0053] In one embodiment of this application, a multi-objective optimization algorithm is used to determine at least the conflict execution queue based on the conflict instructions, preset priorities, and environmental information. This includes: using a multi-objective optimization algorithm to determine the conflict execution queue and control requirements based on the conflict instructions, preset priorities, and environmental information. The control requirements also include the control interval duration between adjacent smart devices to be controlled in the control sequence.

[0054] The process of determining the conflict execution queue and control requirements using a multi-objective optimization algorithm based on the aforementioned conflict instructions, preset priorities, and environmental information is as follows:

[0055] Conflict identification and data preparation:

[0056] Conflict detection and identification: The system first uses a multi-source knowledge graph (device attribute graph, resource constraint graph, user policy graph) to capture and identify instructions that have resource contention, security conflicts and functional mutual exclusion, such as the power conflict between the "shower" and "energy saving" scenarios, and the door lock instruction conflict between "security arming" and "family coming home".

[0057] Environmental information collection: Real-time acquisition of environmental data inside and outside the home, including but not limited to power grid load, weather forecast, real-time electricity price, and user's daily routine. This information is crucial for formulating the optimal control strategy.

[0058] Control requirements analysis:

[0059] Control interval calculation: For high-power devices that need to be prevented from starting simultaneously, the system needs to calculate a reasonable control interval to ensure that there is no power overload between devices, while also considering user waiting time and comfort requirements. For example, if multiple "shower" scenarios are triggered simultaneously, the system can calculate the heating time of each water heater and reasonably arrange the start-up sequence to meet the demand for continuous hot water use without causing power grid overload.

[0060] Control parameter optimization: Based on the operating range in the equipment manual and the user-set goals (such as energy saving priority and safety first), the system automatically adjusts control parameters, such as the temperature setting of the air conditioner and the washing mode of the washing machine, to achieve the best energy efficiency and safety performance.

[0061] Applications of multi-objective optimization algorithms:

[0062] Algorithm selection and configuration: Using weighted scoring, genetic algorithm or other multi-objective optimization mechanisms, the parameters of the algorithm are configured according to the nature of the conflicting instructions, the preset priority and the current environmental information, such as the weights of dimensions such as "safety", "energy consumption" and "comfort".

[0063] Decision tree generation: Construct a decision tree where each branch represents a possible control sequence, considering all possible control requirements (such as inter-device control intervals and parameter adjustments) and their impact on safety, energy consumption, and user experience.

[0064] Optimal control sequence generation:

[0065] Conflict Execution Queue Determination: By comparing the comprehensive scores of each sequence in the decision tree, the algorithm finally selects a conflict-free control sequence, namely the conflict execution queue, which contains device instructions executed in the optimal order and with the optimal parameters.

[0066] Refine control requirements: Further clarify control requirements, including the control interval duration between devices and the refined control parameters of each device, to ensure that the execution sequence not only resolves conflicts but also meets the goals of home operation and user needs in the most efficient way.

[0067] Implementation and Supervision:

[0068] Command issuance and execution: The defined conflict execution queue and control requirements are converted into specific operation commands. Through a cross-protocol command issuance mechanism, it is ensured that various smart devices can correctly understand and execute these commands.

[0069] Real-time monitoring and adjustment: During execution, the system continuously monitors equipment status and environmental changes. In case of emergencies (such as power grid fluctuations or equipment failures), the system can adjust the execution queue and control requirements in real time to ensure that system stability and user experience are not affected.

[0070] By scientifically planning the intervals between control operations, resource contention caused by simultaneous device startup, such as power overload, is avoided, enhancing the safety and stability of home energy management. Control demand analysis ensures that devices meet basic user needs (such as hot water and a cool environment) while also considering comfort and personalized requirements, reducing unnecessary user intervention. Under a multi-objective optimization algorithm, the system can intelligently schedule high-energy-consuming tasks to periods with lower electricity prices, while ensuring coordination with other important activities, achieving energy conservation, emission reduction, and economical operation. Optimization of control parameters, such as locking doors and windows and monitoring cameras, ensures home security is not affected by conflicts caused by functional incompatibilities or resource competition. Extended equipment lifespan and reduced maintenance costs: The integration of equipment health monitoring and predictive maintenance helps identify potential faults in advance, preventing equipment from operating in high-risk conditions. It also optimizes energy consumption throughout the equipment's lifespan, extending equipment lifespan and reducing maintenance frequency and costs.

[0071] In one embodiment of this application, a multi-objective optimization algorithm is used to determine at least a conflict execution queue based on the conflict instructions, preset priorities, and environmental information. This includes: using a genetic algorithm to process the conflict instructions, preset priorities, and environmental information to obtain multiple executable schemes and corresponding scores; determining the target execution scheme as the executable scheme corresponding to the maximum value of the scores; and determining the conflict execution queue based on the target execution scheme.

[0072] The process of using a genetic algorithm to process the aforementioned conflicting instructions, preset priorities, and environmental information to obtain multiple executable solutions and their corresponding scores is as follows:

[0073] Encoding and initializing the population:

[0074] The conflicting instruction sequence, preset priority, and environmental parameters (such as current time, electricity price, equipment status, etc.) are converted into an encoded form that the algorithm can process, usually using binary or integer encoding.

[0075] Initialize the population by creating a series of random solutions as the initial population. Each solution represents an execution queue and scheduling strategy for conflicting instructions.

[0076] Fitness Function: A fitness function is defined to evaluate the merits of each solution, scoring it based on multiple dimensions such as safety, energy efficiency, user comfort, and personalized preferences. For example, a solution that achieves the lowest energy consumption while maximizing user preferences without violating any safety rules will have a high fitness score. The fitness score needs to consider the combined impact of all conflicting instructions, preset priorities, and environmental information to ensure the comprehensiveness and fairness of the scoring mechanism.

[0077] Genetic manipulation:

[0078] Selection: Based on fitness scores, select the better-performing solutions as parents for subsequent genetic manipulation.

[0079] Crossover: Crossover operation is performed on the selected parent solutions to generate new child solutions. By mixing execution queues and scheduling strategies of different parents, possible optimal solutions are explored.

[0080] Mutation: Randomly mutate the offspring solution to change the execution order of some instructions or the device scheduling strategy, so as to ensure the diversity of the population and avoid the algorithm getting stuck in local optima.

[0081] Genetic iteration: Perform multiple rounds of genetic iteration, update the population after each round of iteration, select the next generation of solutions with higher fitness scores, and gradually approach the global optimum.

[0082] Termination Conditions: Set iteration termination conditions, such as reaching a preset number of iterations, convergence of the population's fitness score, or reaching a set threshold. When the termination condition is met, select the solution with the highest fitness score from the current population as the final target execution solution.

[0083] Genetic algorithms (GALs) can perform global searches, avoiding the pitfalls of local optimization and helping to find the optimal instruction execution queue for best resource allocation. By defining multi-dimensional fitness scores, GALs can simultaneously optimize multiple objectives, such as safety, energy consumption, and user experience, ensuring comprehensive and balanced decision-making. The iterative nature of GALs allows them to continuously optimize solutions based on environmental changes (such as electricity price fluctuations and changes in user behavior patterns), improving system responsiveness. By intelligently adjusting instruction execution order and device scheduling, user intervention is reduced, enhancing the smoothness of automation scenarios and user satisfaction. In simulations, GALs can identify potential security risks and resource competition, proactively mitigating these issues in solutions and enhancing system security and stability. GALs can integrate user preference learning modules, dynamically adjusting the priority of execution strategies based on user feedback to achieve more personalized and user-friendly coordination of device linkage conflicts.

[0084] In one embodiment of this application, before controlling the smart device corresponding to the conflicting instruction according to the conflicting execution queue and control requirements, the method further includes: using an LSTM network to evaluate the health indicators of the smart devices in the conflicting execution queue to obtain the failure probability and remaining lifetime; and determining whether to control the corresponding smart device based on the failure probability and the remaining lifetime.

[0085] Data Acquisition and Preprocessing:

[0086] Operation log collection: The home host continuously collects operation logs from various devices, including but not limited to device startup count, running time, power consumption, temperature fluctuations, error codes, etc.

[0087] Historical data processing: The collected data is preprocessed to remove noise, fill in missing values, and encode non-numerical data (such as error codes) into numerical form so that they can be input into the LSTM model.

[0088] Feature engineering: Based on domain knowledge, useful features are extracted from raw logs, such as average daily power consumption, highest temperature records, continuous uptime, etc. These features are good indicators of device health.

[0089] LSTM model training:

[0090] Model building: The model architecture is constructed using LSTM units. LSTM units can remember information from long sequences, making them very suitable for tasks such as device health monitoring that require understanding the time series context.

[0091] Data input: The preprocessed feature sequence is used as input, and each device has its own historical record sequence.

[0092] Tag generation: For each device, a tag is needed for the probability of failure and the remaining lifespan, which can usually be approximated by the device's warranty information, failure history, or expert experience.

[0093] Training process: The model is trained using supervised learning, with the goal of minimizing the gap between the model's predictions and the actual labels. Through training on a large amount of historical data, the LSTM model learns to predict the probability of failure and remaining lifespan from the operational characteristics of the equipment.

[0094] Fault prediction and equipment control adjustment:

[0095] Prediction and evaluation: After training is complete, the LSTM model can receive the latest equipment operation data and output the failure probability and remaining life of the equipment.

[0096] Threshold setting: Defines the critical value of failure risk. For example, if the failure probability of a device exceeds a certain threshold, or the remaining lifespan is less than a predetermined warning period, the system will label the device as high risk.

[0097] Control strategy adjustment: Based on the health assessment results of the equipment, the system dynamically adjusts the priority and runtime of the equipment in the conflict execution queue. For example, high-risk equipment may be scheduled to run during low-load periods to reduce stress on the circuitry; or, the system may suggest that the user perform maintenance in advance to prevent failures at critical moments.

[0098] User notifications and action guidance:

[0099] Notify users: Through the app or smart speaker, the system will promptly report to users which devices have a high risk of failure and their estimated remaining lifespan.

[0100] Action Recommendation: Provide specific maintenance guidelines, such as recommended repair service providers, information on replacement parts, or simple self-maintenance steps.

[0101] Feedback collection: Users can confirm the maintenance suggestions they receive, and even provide feedback on the actual status of the equipment, which will further help the model improve the accuracy of its predictions.

[0102] By predicting equipment failure risks in advance, homeowners can take timely measures for maintenance or replacement, effectively extending equipment lifespan and reducing the inconvenience and costs caused by unexpected malfunctions. Understanding equipment health allows the system to allocate resources more intelligently, preventing high-risk equipment from operating during high-load periods, thus reducing the likelihood of circuit overload. Preventing equipment failure at critical moments ensures the stability and comfort of the home environment, while also reducing the need for frequent user intervention due to equipment malfunctions. LSTM networks, based on data, enable the system to make more rational and user-friendly equipment control decisions, rather than relying solely on fixed rules or thresholds, increasing the system's flexibility and intelligence.

[0103] In one embodiment of this application, before controlling the smart device corresponding to the conflicting instruction according to the conflicting execution queue and control requirements, the method further includes: using an isolated forest algorithm to analyze the degree of deviation of the movement trajectory of the smart device in the conflicting execution queue; and determining whether to control the corresponding smart device based on the degree of deviation and the risk level of the smart device.

[0104] Data Preparation: Collect and organize historical motion trajectory data of smart devices, including but not limited to device usage frequency, startup time, and continuous running time. This data should cover a sufficiently long period to capture the periodicity and changes in device usage patterns.

[0105] Feature engineering: Extract key features from the device's motion trajectory data, such as the number of daily startups, the maximum number of consecutive startup days, and the deviation of startup time from the normal time, and construct a feature matrix for training.

[0106] Model Training: The extracted features are trained using the Isolation Forest algorithm. Isolation Forest is an unsupervised learning algorithm, particularly suitable for anomaly detection, as it effectively finds points that are "isolated" in the dataset. These "isolated" points often represent anomalous behavior.

[0107] Anomaly Score Calculation: For each instruction in the current conflict execution queue, the Isolation Forest algorithm generates an anomaly score based on its expected trajectory (e.g., device startup time and sustained runtime predicted based on historical data). A higher score indicates that the device's trajectory deviates more from the normal range.

[0108] Risk Assessment: Each instruction is assessed for risk based on the inherent risk level of the equipment (e.g., high-power devices, critical safety devices) and the anomaly score of its movement trajectory. In this step, a risk threshold can be set; when the risk of an instruction exceeds the threshold, the system will make a more cautious decision.

[0109] Decision Adjustment: Based on the risk assessment results, decide whether to execute the instructions in the conflict execution queue. If the deviation of the device's movement trajectory and the level of risk are high, the execution of the instructions may be postponed, or the user may be required to confirm further; if the risk is low, the instructions will continue to be executed as originally planned.

[0110] Results Feedback and Model Updates: Decision results and their causes are recorded as data sources for subsequent learning and model optimization. Through a continuous feedback mechanism, the system can continuously adjust the parameters of the Isolation Forest model, improving the accuracy of anomaly detection and risk assessment.

[0111] By detecting anomalies in device movement trajectories, abnormal behavior can be identified in advance, preventing safety hazards caused by device malfunctions or improper use, such as circuit overload or device malfunction. The Isolation Forest algorithm can identify minute anomalies, allowing the system to make more detailed and personalized device control decisions, avoiding potential resource waste and a decline in user experience. Continuous monitoring of device movement trajectories helps predict potential device failures, enabling timely maintenance, extending device lifespan, and reducing the impact of unexpected events on family life. Demonstrating how the system makes decisions based on the degree of deviation and risk level of device movement trajectories increases system transparency and enhances user trust in smart home systems, especially when facing complex conflicts and security considerations. Feedback data collected after each decision is used for continuous model training and optimization, enabling the system to continuously improve its anomaly detection capabilities and decision-making efficiency over time, better adapting to changes in the home environment.

[0112] In one embodiment of this application, after controlling the smart device corresponding to the conflict instruction according to the conflict execution queue and control requirements, the method includes: adjusting the weights of each parameter of the multi-objective optimization algorithm by using historical conflict events and corresponding solutions.

[0113] The process of implementing experiential learning:

[0114] Historical data collection: The system continuously records detailed information about each conflict event, including the type of conflict (such as resource contention, security conflict), the equipment involved, the time of the conflict, environmental parameters (such as temperature, light intensity), the final solution, and user feedback.

[0115] Case Classification and Analysis: Based on the collected historical data, the system will classify similar conflict events through cluster analysis or classification algorithms to identify common factors, such as frequent equipment resource competition during specific time periods (such as peak electricity consumption periods) or safety conflicts of heating equipment related to specific environmental conditions (such as extremely cold weather).

[0116] Weighted model training: This involves training a model using machine learning (such as reinforcement learning or supervised learning) that can learn how to adjust the parameter weights in a multi-objective optimization algorithm based on categorized cases. For example, if it is found that users are more inclined to prioritize safety than energy conservation at night, the model might increase the weight of "safety" and decrease the weight of "energy efficiency."

[0117] Real-time weight updates: When a new conflict event occurs, the system will immediately call the pre-trained weight adjustment model and quickly calculate the appropriate parameter weights based on the current conflict type and environment to guide the multi-objective optimization algorithm to make decisions that are closer to user expectations and situational needs.

[0118] Continuous iteration and optimization: The system regularly reviews the effectiveness of historical solutions and iterates and adjusts the model based on the latest user feedback and equipment operation data to ensure that decisions are always in an optimal state.

[0119] By learning user preferences and behavioral patterns, the system can consider individual habits in conflict resolution, providing more personalized solutions and improving user experience. Historical data contains conflict cases in various scenarios, enabling the system to make appropriate decisions quickly when similar situations occur again, reducing uncertainty and errors in equipment operation. Leveraging the consistency of historical solutions, the system can follow the same processing logic and priorities when handling similar conflicts, which helps build user trust and avoids confusion or dissatisfaction caused by fluctuating decision-making. By analyzing past resource contention, the system can more intelligently allocate electricity and other resources within the household, avoiding waste and reducing safety risks associated with overuse. Historical records of equipment maintenance and malfunctions help the system predict and prevent equipment problems in advance, reducing the high costs and inconvenience of emergency repairs.

[0120] In one embodiment of this application, the method further includes: if it is determined that there are no conflicting instructions, executing all the control instructions of the smart devices in chronological order.

[0121] When the system can execute device control commands in the user-preset time sequence without conflict, the home automation process becomes extremely smooth.

[0122] Executing instructions sequentially helps the system better manage household energy use. By avoiding resource contention between devices, the system ensures that high-energy-consuming devices are activated during optimal times, such as when electricity prices are lower, maximizing energy efficiency and reducing household energy costs. In the absence of conflicts, safety rules (such as automatically closing windows and doors at night) can be strictly adhered to, preventing security vulnerabilities caused by instruction conflicts and ensuring the safety of family members. Reasonable sequential execution prevents devices from being overloaded simultaneously, reducing wear and tear caused by overheating or overcooling, extending the lifespan of smart devices, and reducing maintenance costs. By pre-detecting and resolving conflicts, the system avoids frequent interruptions and rescheduling during execution, reducing the consumption of computing resources.

[0123] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0124] This application also provides a control device for a smart device. It should be noted that the control device for the smart device in this application can be used to execute the control method for a smart device provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0125] The control device for the smart device provided in the embodiments of this application will be described below.

[0126] Figure 2 This is a schematic diagram of a control device for a smart device according to an embodiment of this application. Figure 2 As shown, the device includes: a receiving unit 21, configured to receive multiple control commands from smart devices, and determine whether conflicting commands exist based on a smart device knowledge graph and at least a portion of all the control commands from the aforementioned smart devices, wherein the smart device knowledge graph includes at least the relationship between the parameters of the smart devices and constraints, and the constraints are at least one of the following: maximum load that the circuit can withstand, security strategy, energy consumption, operational constraints, and compatibility information; a first processing unit 22, configured to, upon determining the existence of the aforementioned conflicting commands, use a multi-objective optimization algorithm to determine at least a conflict execution queue based on the aforementioned conflicting commands, preset priorities, and environmental information; and a second processing unit 23, configured to control the smart device corresponding to the aforementioned conflicting commands based on the aforementioned conflict execution queue and control requirements, wherein the control requirements include at least the control parameters of the aforementioned smart device to be controlled.

[0127] In one embodiment of this application, the first processing unit includes: a processing module for using a multi-objective optimization algorithm to determine a conflict execution queue and control requirements based on the conflict instructions, preset priorities and environmental information, wherein the control requirements also include the control interval duration between adjacent smart devices to be controlled in the control sequence.

[0128] In one embodiment of this application, the processing module includes: a first processing submodule for processing the conflicting instructions, the preset priority, and the environmental information using a genetic algorithm to obtain multiple executable schemes and corresponding scores; a second processing submodule for determining the target execution scheme as the executable scheme corresponding to the maximum value of the scores; and a third processing submodule for determining the conflicting execution queue based on the target execution scheme.

[0129] In one embodiment of this application, the first control unit further includes: a second processing module for evaluating the health indicators of the smart devices in the conflict execution queue using an LSTM network before controlling the smart devices corresponding to the conflict instructions according to the conflict execution queue and control requirements, to obtain the failure probability and remaining lifetime; and a third processing module for determining whether to control the corresponding smart devices based on the failure probability and the remaining lifetime.

[0130] In one embodiment of this application, the above-mentioned apparatus further includes: a third processing unit configured to analyze the degree of deviation of the motion trajectory of the smart device in the conflict execution queue using an isolated forest algorithm before controlling the smart device corresponding to the conflict instruction according to the conflict execution queue and control requirements; and a fourth processing unit configured to determine whether to control the corresponding smart device based on the degree of deviation and the risk level of the smart device.

[0131] In one embodiment of this application, the above-mentioned apparatus further includes: a fifth processing unit configured to, after controlling the smart device corresponding to the conflict instruction according to the conflict execution queue and control requirements, adjust the weights of each parameter of the multi-objective optimization algorithm by using historical conflict events and corresponding solutions.

[0132] In one embodiment of this application, the above-mentioned apparatus further includes: a sixth processing unit configured to execute all the control instructions of the above-mentioned smart devices in chronological order if it is determined that there are no conflicting instructions.

[0133] The control unit of the aforementioned intelligent device includes a processor and a memory. The receiving unit, the first processing unit, and the second processing unit, etc., are all stored as program units in the memory. The processor executes the program units stored in the memory to achieve the corresponding functions. All of the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0134] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can address the problem of existing solutions' ineffective management of control conflicts in smart devices.

[0135] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0136] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the control method of the smart device.

[0137] This invention provides a processor for running a program, wherein the program executes the control method of the smart device during runtime.

[0138] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps: receiving multiple control commands from intelligent devices, and determining whether conflicting commands exist based on an intelligent device knowledge graph and at least a portion of all the aforementioned control commands. The intelligent device knowledge graph includes at least the relationship between intelligent device parameters and constraints, and the constraints are at least one of the following: maximum circuit load capacity, security strategy, energy consumption, operational constraints, and compatibility information. If conflicting commands are determined to exist, a multi-objective optimization algorithm is used to determine at least a conflict execution queue based on the conflicting commands, preset priorities, and environmental information. The intelligent device corresponding to the conflicting command is controlled according to the conflict execution queue and control requirements, whereby the control requirements include at least the control parameters of the intelligent device to be controlled. The device described herein can be a server, PC, PAD, mobile phone, etc.

[0139] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps: receiving multiple control commands from intelligent devices, and determining whether conflicting commands exist based on an intelligent device knowledge graph and at least a portion of all the aforementioned intelligent device control commands, wherein the aforementioned intelligent device knowledge graph includes at least the relationship between intelligent device parameters and constraints, and the aforementioned constraints are at least one of the following: maximum load that the circuit can withstand, security strategy, energy consumption, operational constraints, and compatibility information; if the existence of the aforementioned conflicting commands is determined, employing a multi-objective optimization algorithm to determine at least a conflict execution queue based on the aforementioned conflicting commands, preset priorities, and environmental information; and controlling the intelligent device corresponding to the aforementioned conflicting commands according to the aforementioned conflict execution queue and control requirements, wherein the aforementioned control requirements include at least the control parameters of the aforementioned intelligent device to be controlled.

[0140] This application also provides an intelligent device system, including: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for performing any of the above-described methods.

[0141] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0142] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0143] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0144] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0145] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0146] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0147] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0148] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0149] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0150] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0151] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A control method for an intelligent device, characterized in that, include: The system receives control commands from multiple smart devices and determines whether there are conflicting commands based on a smart device knowledge graph and at least a portion of all the control commands from the smart devices. The smart device knowledge graph includes at least the relationship between the parameters of the smart devices and the constraints, and the constraints are at least one of the following: maximum load that the circuit can withstand, security strategy, energy consumption, operational constraints, and compatibility information. If the existence of the conflicting instructions is determined, a multi-objective optimization algorithm is used to determine at least the conflict execution queue based on the conflicting instructions, preset priorities, and environmental information. The smart device corresponding to the conflicting instruction is controlled according to the conflict execution queue and control requirements, wherein the control requirements include at least the control parameters of the smart device to be controlled.

2. The method according to claim 1, characterized in that, A multi-objective optimization algorithm is used to determine at least the conflict execution queue based on the conflict instructions, preset priorities, and environmental information, including: A multi-objective optimization algorithm is used to determine the conflict execution queue and control requirements based on the conflict instructions, preset priorities and environmental information. The control requirements also include the control interval duration between adjacent smart devices to be controlled in the control sequence.

3. The method according to claim 1, characterized in that, A multi-objective optimization algorithm is used to determine at least the conflict execution queue based on the conflict instructions, preset priorities, and environmental information, including: A genetic algorithm is used to process the conflicting instructions, the preset priority, and the environmental information to obtain multiple executable solutions and corresponding scores. The target execution plan is determined as the executable plan corresponding to the maximum value of the score; The conflict execution queue is determined based on the target execution plan.

4. The method according to claim 1, characterized in that, Before controlling the smart device corresponding to the conflicting instruction according to the conflict execution queue and control requirements, the method further includes: The health indicators of the intelligent devices in the conflict execution queue are evaluated using an LSTM network to obtain the failure probability and remaining lifetime. Based on the failure probability and the remaining lifespan, determine whether to control the corresponding smart device.

5. The method according to claim 1, characterized in that, Before controlling the smart device corresponding to the conflicting instruction according to the conflict execution queue and control requirements, the method further includes: The Isolation Forest algorithm is used to analyze the degree of deviation of the movement trajectory of the intelligent devices in the conflict execution queue; Based on the degree of deviation and the risk level of the smart device, determine whether to control the corresponding smart device.

6. The method according to claim 1, characterized in that, After controlling the smart device corresponding to the conflicting instruction according to the conflict execution queue and control requirements, the process includes: The weights of each parameter in the multi-objective optimization algorithm are adjusted by using historical conflict events and corresponding solutions.

7. The method according to claim 1, characterized in that, The method further includes: If it is determined that there are no conflicting instructions, all control instructions of the smart devices are executed in chronological order.

8. A control device for an intelligent device, characterized in that, include: A receiving unit is configured to receive multiple control commands from intelligent devices and determine whether there are conflicting commands based on an intelligent device knowledge graph and at least a portion of all the control commands from the intelligent devices. The intelligent device knowledge graph includes at least the relationship between the parameters of the intelligent devices and the constraints, and the constraints are at least one of the following: the maximum load that the circuit can withstand, security strategies, energy consumption, operational constraints, and compatibility information. The first processing unit is configured to, upon determining the existence of the conflicting instruction, use a multi-objective optimization algorithm to determine at least a conflict execution queue based on the conflicting instruction, a preset priority, and environmental information. The second processing unit is used to control the smart device corresponding to the conflict instruction according to the conflict execution queue and control requirements, wherein the control requirements include at least the control parameters of the smart device to be controlled.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the control method of the smart device according to any one of claims 1 to 7.

10. An intelligent device system, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising methods for performing any one of claims 1 to 7.

Images