Intelligent home-oriented side cloud cooperative state synchronization and instruction execution management system and method

Abstract

The invention relates to the technical field of Internet of Things smart home control, and discloses a smart home-oriented side cloud collaborative state synchronization and instruction execution management system and method. The edge-cloud cooperation state synchronization and instruction execution management method is applied to edge gateway management equipment, and specifically comprises the following steps: S101, searching all local intelligent household equipment, registering on the searched local intelligent household equipment, establishing security authentication connection with a cloud platform, downloading an initial cooperation strategy, and initializing local management, through protocol conversion, resource evaluation and load pre-configuration, an edge cloud collaborative basic framework is constructed; and S102, adopting a self-adaptive synchronization strategy to monitor the state of the smart home equipment in real time. According to the invention, by constructing a deep collaborative edge-cloud integrated architecture, the performance of the smart home system is remarkably improved, a dynamic equipment registration and security initialization mechanism is obtained, seamless access and communication security of heterogeneous equipment are ensured, and a stable and reliable foundation is laid for the system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet of Things smart home control, in particular to a cloud-edge collaborative state synchronization and instruction execution management system and method for smart home. BACKGROUND

[0002] With the rapid development of Internet of Things technology, smart home systems are increasingly popular, and the types and quantities of smart devices deployed in modern homes are growing rapidly, from traditional smart lighting, temperature controllers to complex security cameras, environmental sensors, etc. The amount of data generated by these devices is huge and needs to be processed in real time.

[0003] The existing smart home system architecture mainly relies on a centralized cloud control mode, that is, all devices directly or through a gateway upload data to a cloud center server, and the cloud performs unified state management and instruction issuance. The advantage of this architecture is that the cloud has powerful computing and storage capabilities, which can perform complex data analysis and global optimization. However, its inherent defects are also increasingly prominent: first, all data interactions must go through the Internet, and network latency and bandwidth fluctuations will directly cause control instruction response to be sluggish, especially when executing emergency safety instructions (such as door lock closure), high latency can pose a serious risk. Second, once the connection between the cloud platform and the home network is interrupted, the entire system will be paralyzed, losing all remote control and automation functions, and the robustness is poor.

[0004] In order to overcome the disadvantages of pure cloud mode, edge computing mode is introduced into the field of smart home, emphasizing the completion of data processing and device control within the local home network, and only necessary data is synchronized to the cloud. This approach significantly reduces dependence on external networks, improves the real-time and reliability of local control, and still maintains basic functions in the event of a network outage, but pure edge computing mode also has obvious limitations: the computing and storage resources of edge gateway are limited, making it difficult to support complex intelligent decision-making; interconnection and centralized management between devices of different manufacturers and different protocols are difficult, and edge gateway is difficult to achieve global coordination and strategy update across homes, in addition, edge nodes themselves may become weak points of security attacks.

[0005] Therefore, there is an urgent need in the art for a more refined, intelligent and comprehensive edge-cloud collaborative management method to fundamentally improve the overall performance of smart home systems. SUMMARY

[0006] The application aims to provide a smart home-oriented edge cloud collaborative state synchronization and instruction execution management system and method, which realizes significant improvement of the performance of the smart home system by constructing a deep collaborative edge cloud integrated architecture, obtains a dynamic device registration and safe initialization mechanism, ensures seamless access and communication security of heterogeneous devices, and lays a stable and reliable foundation for the system; the adaptive state synchronization algorithm and the bidirectional differential synchronization mechanism can intelligently adjust the synchronization strategy according to the network condition and the key of the device, not only significantly reducing the network bandwidth occupation, but also ensuring the efficient consistency of the edge cloud state, aiming to solve the problems in the prior art.

[0007] The application is implemented as follows: a smart home-oriented edge cloud collaborative state synchronization and instruction execution management method is applied to an edge gateway management device, and specifically includes the following steps: S101: search all smart home devices locally, register on the searched local smart home devices, establish a secure authentication connection with the cloud platform, download the initial collaborative strategy and initialize the local management, construct an edge cloud collaborative basic framework through protocol conversion, resource evaluation and load preconfiguration; S102: adopt an adaptive synchronization strategy, monitor the smart home device state in real time, and keep the state consistent with the cloud platform through a bidirectional and differential synchronization mechanism, intelligently adjust the synchronization frequency according to the criticality of the smart home device and the network condition, and have local caching and recovery capability when the network is disconnected; S103: receive and verify multi-source user instructions, the cloud platform provides intelligent analysis based on global context, the instruction is decomposed, intelligent device mapping and conflict detection are performed by the edge cloud collaborative analysis engine, the edge gateway is responsible for fast local analysis, and finally an execution plan containing priority and dependency relationship is generated; S104: dynamically decide the execution path of the execution plan based on the factors of instruction complexity, network condition and resource load, and realize load balancing and risk assessment through a collaborative decision algorithm, so that the instruction is executed in a low-delay and high-reliability manner, and the system energy efficiency is optimized synchronously; S105: collect full-link feedback data of instruction execution, aggregate and analyze the data on the cloud platform to identify patterns, evaluate performance and generate optimization strategies, dynamically adjust system parameters and predict potential problems through the closed-loop feedback mechanism of edge cloud collaboration, realize self-learning and continuous optimization of the system.

[0008] Further, in S101, all smart home devices are searched locally, and registered on the searched local smart home devices, and a secure authentication connection is established with the cloud platform, including: The edge gateway management device adopts a multi-protocol adapter to concurrently scan local smart home devices of different communication protocols, performs capability negotiation and compatibility testing on discovered local smart home devices, and ensures seamless access of heterogeneous local smart home devices. The edge gateway management device dynamically allocates a local virtual ID for a newly registered local smart home device, establishes a mapping relationship with a unique global ID allocated by a cloud platform, and encrypts and stores the mapping relationship in a mapping table locally and synchronously in the cloud, thereby completing subsequent accurate control. The edge gateway management device and the cloud platform exchange and verify the certificate, negotiate to generate a one-time session key for subsequent communication encryption, periodically update the session key after the connection is established, and monitor whether the communication is abnormal in real time. If it is abnormal, a security reconstruction mechanism is triggered.

[0009] Further, in S102, an adaptive synchronization strategy is adopted to monitor the state of the smart home device in real time, and a bidirectional and differential synchronization mechanism is used to keep the state consistent with the cloud platform, including: A multi-dimensional evaluation model is established to input network bandwidth, device power, and state change frequency parameters in real time, and output an optimal synchronization period and data compression rate; For continuous state stream data, the edge gateway management device first performs key frame extraction and data desensitization processing, and then selects lossless or lossy compression mode for synchronization according to the evaluation result, thereby balancing data value and transmission overhead.

[0010] Further, the synchronization frequency is intelligently adjusted according to the criticality of the smart home device and the network status, and the edge gateway management device has local caching and recovery capabilities when the network is disconnected, including: The edge gateway management device maintains a ring buffer area to store all state change events and unsynchronized instructions during network disconnection in chronological order, and records the operation sequence number to prevent data overwrite; When the network is restored, the edge gateway management device first compares the state version with the cloud platform, performs incremental data synchronization based on the difference, and reorders the retained instructions according to the operation sequence number to ensure the final consistency of the state.

[0011] Further, in S103, the instruction decomposition, smart device mapping, and conflict detection are performed by the edge-cloud collaborative analysis engine. The edge gateway is responsible for fast local analysis, and finally generates an execution plan containing priority and dependency relationship, including: After the parsing engine decomposes the complex scene instruction into a sequence of atomic operations, a temporary instruction dependency graph is constructed to analyze the timing and conditional relationships between operations. The parsing engine simulates the execution of the dependency graph, compares the current state with other instructions that are currently queued, identifies resource competition or logical contradictions, and automatically resolves conflicts or reports user arbitration to obtain an execution plan. The priority of the execution plan is dynamically calculated based on the instruction type, user identity, and context. The edge gateway management device sets execution barriers and timeout monitoring for operations with strict dependency relationships to ensure that the preceding operations are successfully completed before triggering the subsequent operations. Otherwise, the overall plan will enter an abnormal processing flow.

[0012] Furthermore, in S104, based on factors such as instruction complexity, network conditions, and resource load, the execution path of the execution plan is dynamically decided, including: A dynamic decision matrix is established to quantify instruction complexity as a computational overhead index, quantify network conditions as delay and bandwidth scores, and convert resource load of edge nodes and cloud platforms into available resource indices. Weight threshold values are set for each evaluation factor, and a weighted scoring algorithm is designed. When the weighted total score of an instruction is below the set threshold, it is automatically decided to be executed on the edge. If the score is above the threshold, it is decided to be executed on the cloud or in a collaborative edge-cloud manner, realizing preliminary quantitative selection of the execution path. The actual execution effect of the decided instruction is continuously monitored. If a decision deviation is found, the weight parameters in the decision matrix are automatically fine-tuned or path rerouting is triggered. For collaborative execution tasks, the allocation ratio of sub-tasks between edge and cloud is dynamically divided, and a local degradation scheme is started when the network is jittering, ensuring that the decision always fits the real-time state and realizing dynamic optimization of the execution path.

[0013] Furthermore, load balancing and risk assessment are achieved through a collaborative decision algorithm, realizing the execution of instructions in a low-delay and high-reliability manner, and synchronously optimizing system energy efficiency, including: The collaborative decision algorithm constructs a unified decision model that real-time aggregates resource utilization data from CPU, memory, and network IO of each edge node, and combines instruction queue depth and type to calculate real-time load scores globally and locally using fuzzy logic or a weighted decision matrix. At the same time, the execution path of the instruction is risk assessed to predict the evaluation results that may fail due to node overload, network delay, or device offline. Based on the evaluation results, the collaborative decision algorithm dynamically executes load balancing strategies and implements risk avoidance. For high-load areas, new instructions or instructions in the queue are intelligently routed to edge nodes or cloud platforms with lighter load, and task migration between nodes can be triggered. Different risk level instruction execution plans are set up. Meanwhile, the collaborative decision-making algorithm introduces an energy efficiency factor, prioritizing the selection of execution nodes or instruction batch execution strategies with higher energy efficiency ratios during decision-making, ensuring both low latency and high reliability while optimizing performance.

[0014] Furthermore, in S105, patterns are identified, performance is evaluated, and optimization strategies are generated. Through a closed-loop feedback mechanism of edge-cloud collaboration, system parameters are dynamically adjusted and potential problems are predicted, including: The cloud platform uses big data analytics and machine learning models to deeply mine the aggregated end-to-end feedback data. It identifies common features of high-frequency failure modes and successful execution paths through cluster analysis, evaluates the evolution trend of performance indicators through time series analysis, and generates data-driven optimization strategies to adjust the default execution path of instructions, optimize the state synchronization frequency, or update conflict detection rules. The generated optimization strategy is sent to the edge gateway management device through the edge-cloud collaboration channel. The feedback data generated by the edge gateway management device after applying the new strategy is reported again. The cloud platform receives the feedback data and dynamically adjusts the system parameters. A prediction model is built by training historical data. After the prediction model is trained in stages, potential problems are actively predicted and preventive measures are triggered.

[0015] Compared with existing technologies, the edge-cloud collaborative state synchronization and instruction execution management system and method for smart homes provided by this invention have the following beneficial effects: 1. By constructing a deeply collaborative edge-cloud integrated architecture, the performance of the smart home system has been significantly improved. A dynamic device registration and security initialization mechanism ensures seamless access and secure communication for heterogeneous devices, laying a stable and reliable foundation for the system. The adaptive state synchronization algorithm and bidirectional differential synchronization mechanism can intelligently adjust synchronization strategies based on network conditions and device criticality, significantly reducing network bandwidth consumption and ensuring efficient consistency between edge and cloud states. Even during network interruptions, basic functions can be maintained through local caching and intelligent recovery mechanisms, greatly enhancing system robustness and user experience. Furthermore, the dynamic execution path decision and load balancing algorithm based on a multi-dimensional evaluation model can intelligently select the optimal execution node based on real-time instruction complexity, network conditions, and resource load, effectively balancing the advantages of low latency in edge computing and high computing power in cloud computing. This achieves simultaneous optimization of low-latency, highly reliable instruction execution and system energy efficiency in complex home environments. 2、The edge cloud collaborative instruction analysis engine of the technical solution fuses global context and local real-time state, realizes accurate decomposition and conflict detection of complex instructions, generates reliable execution plans with priority and dependency relationship, and through the closed-loop optimization mechanism constructed based on full-link feedback data, continuously identifies performance bottlenecks and failure modes through big data analysis and machine learning models, and dynamically adjusts system parameters and strategies, and sets self-learning ability to enable the system to predict potential problems and implement preventive measures, thereby realizing the paradigm shift from passive response to active optimization, not only having excellent real-time response capability, but also having continuous evolution capability, significantly improving the long-term management efficiency, safety and intelligent level of the smart home system.

[0016] The edge cloud collaborative state synchronization and instruction execution management system for smart home is used to execute the edge cloud collaborative state synchronization and instruction execution management method described above, and the system comprises: An edge processing module is configured to search, register and manage local smart home devices, construct a local device network through protocol conversion and resource assessment, establish a secure authentication connection with a cloud service module, receive an initial collaborative strategy to complete the initialization of the edge cloud collaborative framework, and the like. A cloud service module is configured to perform global strategy management, state storage and big data analysis, and perform secure communication and data interaction with the edge processing module. A state synchronization module is configured to monitor device states in real time using an adaptive synchronization strategy, and maintain state consistency with the cloud service module through a bidirectional, differential synchronization mechanism, and has the ability to intelligently adjust synchronization frequency and offline cache recovery according to device criticality and network conditions. An instruction processing engine is configured to receive and verify multi-source user instructions, and is composed of a local analysis unit in the edge processing module and a global analysis unit in the cloud service module to perform instruction decomposition, device mapping and conflict detection, and generate an execution plan containing priority and dependency relationship. A collaborative decision engine is configured to dynamically decide the execution path of the execution plan based on instruction complexity, network conditions and resource load factors, and implement load balancing and risk assessment through a collaborative decision algorithm to execute instructions in a low-delay and high-reliability manner and optimize system energy efficiency. A feedback optimization module is configured to collect full-link feedback data of instruction execution, aggregate and analyze the data by the cloud service module to identify patterns, evaluate performance and generate optimization strategies, and dynamically adjust system parameters and predict potential problems through a closed-loop feedback mechanism of edge cloud collaboration, to realize self-learning and continuous optimization of the system.

[0017] Specifically, the collaborative decision engine specifically comprises: A load evaluation unit is configured to collect resource utilization data and instruction queue information of each edge node in real time, and to calculate global and local load scores by using a weighted decision matrix. A risk prediction unit is configured to predict failure probabilities of different execution paths caused by node overload, network delay or device offline, and to generate a risk evaluation report. A dynamic routing unit is configured to intelligently route instructions to optimal execution nodes or trigger task migration according to the load scores and the risk evaluation report, and to set up backup paths and resource reservation plans for critical instructions. An energy efficiency optimization unit is configured to introduce an energy efficiency factor in the routing decision, and to preferentially select execution nodes or instruction batch execution strategies with higher energy efficiency ratios, so as to optimize the overall system energy efficiency while ensuring performance. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A flowchart of a smart home-oriented edge-cloud collaborative state synchronization and instruction execution management method according to the present application is shown in the figure. Figure 2 A flowchart of searching for all local smart home devices, registering on the searched local smart home devices, and establishing a secure authentication connection with a cloud platform in a smart home-oriented edge-cloud collaborative state synchronization and instruction execution management method according to the present application is shown in the figure. Figure 3 A structural diagram of a smart home-oriented edge-cloud collaborative state synchronization and instruction execution management system according to the present application is shown in the figure. Figure 4 A structural diagram of a collaborative decision engine in a smart home-oriented edge-cloud collaborative state synchronization and instruction execution management system according to the present application is shown in the figure. DETAILED DESCRIPTION

[0019] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to 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.

[0020] The implementation of the present application will be described in detail below with reference to specific embodiments.

[0021] The same or similar reference numerals in the drawings of the embodiments correspond to the same or similar components; in the description of the present application, it is understood that if the orientations or positional relationships indicated by the terms "upper", "lower", "left", "right" and the like are based on the orientations or positional relationships shown in the drawings, they are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, therefore the terms describing the positional relationship in the drawings are only used for exemplary illustration, and cannot be understood as a limitation on the present application. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to the specific circumstances.

[0022] Referring to Figures 1-2 The smart home-oriented edge cloud cooperative state synchronization and instruction execution management method is applied to an edge gateway management device, and specifically includes the following steps: S101: Search for all local smart home devices, and register on the searched local smart home devices, establish a secure authentication connection with the cloud platform, download the initial cooperative strategy and initialize the local management, and build an edge cloud cooperative basic framework through protocol conversion, resource assessment and load pre-configuration; Among them, searching for all local smart home devices and registering on the searched local smart home devices, establishing a secure authentication connection with the cloud platform, includes: The edge gateway management device uses a multi-protocol adapter to concurrently scan local smart home devices of different communication protocols, and performs capability negotiation and compatibility testing on the discovered local smart home devices to ensure seamless access of heterogeneous local smart home devices; The edge gateway management device dynamically allocates a local virtual ID for the newly registered local smart home device, and establishes a mapping relationship with the unique global ID allocated by the cloud platform, and encrypts and stores it in the local and the synchronized cloud, and completes the subsequent precise control; The secure authentication connection adopts two-way verification based on digital certificates, and after the edge gateway management device and the cloud platform exchange and verify the certificates, a one-time session key is negotiated and generated for subsequent communication encryption, and after the connection is established, both parties periodically update the session key, and real-time monitor whether the communication is abnormal, if abnormal, trigger the security reconstruction mechanism; S102: Adopting an adaptive synchronization strategy, real-time monitoring of smart home device status, and keeping the status consistent with the cloud platform through a bidirectional, differential synchronization mechanism, intelligently adjusting the synchronization frequency according to the criticality of the smart home device and the network condition, and having local caching and recovery capability when the network is disconnected; Among them, adopting an adaptive synchronization strategy, real-time monitoring of smart home device status, and keeping the status consistent with the cloud platform through a bidirectional, differential synchronization mechanism, includes: A multi-dimensional evaluation model is established, real-time input network bandwidth, device power, state change frequency parameters, output optimal synchronization period and data compression rate; For continuous state flow data, the edge gateway management device first performs key frame extraction and data desensitization processing, and then selects lossless or lossy compression mode for synchronization according to the evaluation result, to balance data value and transmission overhead; S103: Receive and verify multi-source user instructions, cloud platform provides intelligent analysis based on global context, instruction decomposition, intelligent device mapping and conflict detection are performed by edge-cloud collaborative analysis engine, edge gateway is responsible for rapid local analysis, and finally an execution plan containing priority and dependency relationship is generated; Among them, instruction decomposition, intelligent device mapping and conflict detection are performed by edge-cloud collaborative analysis engine, edge gateway is responsible for rapid local analysis, and finally an execution plan containing priority and dependency relationship is generated, including: After the analysis engine decomposes the complex scene instruction into an atomic operation sequence, a temporary instruction dependency graph is constructed, the timing and conditional relationship between operations are analyzed, the analysis engine simulates the execution of the dependency graph, compares the current state with other instructions queuing, identifies resource competition or logical contradiction, and automatically solves the conflict or reports user arbitration to obtain an execution plan; The priority of the execution plan is dynamically calculated by the instruction type, user identity and context, the edge gateway management device sets execution barriers and timeout monitoring for operations with strict dependency relationship, ensures that the subsequent operation is triggered only after the pre-operation is successfully completed, otherwise the whole plan will enter the exception handling process; S104: Based on the factors of instruction complexity, network condition and resource load, the execution path of the execution plan is dynamically decided, and load balancing and risk assessment are realized through collaborative decision algorithm, so that the instruction is executed in a low delay and high reliability manner, and the system energy efficiency is optimized; Among them, load balancing and risk assessment are realized through collaborative decision algorithm, so that the instruction is executed in a low delay and high reliability manner, and the system energy efficiency is optimized, including: The collaborative decision algorithm constructs a unified decision model, the decision model real-time gathers CPU, memory, network IO resource utilization data from each edge node, combines with instruction queue depth and type, and calculates global and local real-time load score by using fuzzy logic or weighted decision matrix; At the same time, risk assessment is performed on the instruction execution path, and the evaluation result that may cause failure due to node overload, network delay or device offline is predicted; Based on the evaluation result, the collaborative decision algorithm dynamically executes load balancing strategy and implements risk avoidance, for high load area, the new instruction or instruction in queue is intelligently routed to the edge node or cloud platform with lighter load, and task migration between nodes can be triggered, and different risk level instruction execution preplan is set. The simultaneous collaborative decision algorithm introduces an energy efficiency factor, and in the decision-making process, the execution node or instruction batch execution strategy with higher energy efficiency ratio is preferentially selected to ensure low delay and high reliability while optimizing; S105: Collect full-link feedback data of instruction execution, aggregate and analyze in the cloud platform to identify patterns, evaluate performance and generate optimization strategies, dynamically adjust system parameters and predict potential problems through the closed-loop feedback mechanism of edge-cloud collaboration, realize self-learning and continuous optimization of the system, the edge-cloud collaborative instruction analysis engine of the technical solution fuses global context and local real-time state, realizes accurate decomposition and conflict detection of complex instructions, generates reliable execution plans with priority and dependency relationship, the closed-loop optimization mechanism based on full-link feedback data continuously identifies performance bottlenecks and failure modes through big data analysis and machine learning models, and dynamically adjusts system parameters and strategies, and sets self-learning ability to enable the system to predict potential problems and implement preventive measures, thereby realizing the paradigm shift from passive response to active optimization, not only having excellent real-time response ability, but also having continuous evolution ability, significantly improving the long-term management efficiency, safety and intelligent level of the smart home system.

[0023] In S102 of the embodiment, the synchronization frequency is intelligently adjusted according to the criticality of the smart home device and the network condition, and the local cache and recovery capability are provided when the network is disconnected, including: The edge gateway management device maintains a ring buffer area to store all state change events and unsynchronized instructions during network disconnection in chronological order, and records the operation sequence number to prevent data overwrite; When the network is restored, the edge gateway management device first compares the state version with the cloud platform, performs incremental data synchronization based on the difference points, and reorders the execution of the stranded instructions according to the operation sequence number to ensure the final consistency of the state.

[0024] In S104 of the embodiment, the execution path of the execution plan is dynamically decided based on factors such as instruction complexity, network condition, and resource load, including: A dynamic decision matrix is established, the instruction complexity is quantified as a calculation overhead index, the network condition is quantified as a delay and bandwidth score, the resource load of the edge node and the cloud platform is converted into an available resource index, a weight threshold is set for each evaluation factor, and a weighted scoring algorithm is designed; When the weighted total score of the instruction is lower than the set threshold, it is automatically decided to be executed on the edge, and when it is higher than the threshold, it is decided to be executed on the cloud or in edge-cloud collaboration, realizing the preliminary quantitative selection of the execution path; The actual execution effect of the decided instruction is continuously monitored, if the decision deviation is found, the weight parameter in the decision matrix is automatically fine-tuned or the path is rerouted, the allocation proportion of the dynamically divided sub-tasks between the edge cloud for the cooperative execution task is divided, and the local degradation scheme is started when the network is jittered, so that the decision always fits the real-time state, and the dynamic optimization of the execution path is realized.

[0025] In S105 of the embodiment, the mode is identified, the performance is evaluated, and the optimization strategy is generated, the system parameters are dynamically adjusted and the potential problems are predicted through the closed-loop feedback mechanism of edge cloud cooperation, including: The cloud platform uses big data analysis and machine learning models to deeply mine the aggregated full-link feedback data, identifies the common characteristics of high-frequency fault modes and successful execution paths through clustering analysis, evaluates the evolution trend of performance indicators through time series analysis, and the cloud platform generates data-driven optimization strategies to adjust the default execution path of the instruction, optimize the state synchronization frequency or update the conflict detection rules; The generated optimization strategy is issued to the edge gateway management device through the edge cloud cooperative channel, the feedback data generated after the edge gateway management device applies the new strategy is reported again, and the cloud platform receives the feedback data and dynamically adjusts the system parameters; The historical data training prediction model is established through historical data, and after the historical data training prediction model is trained periodically, the potential problems are actively predicted, and preventive measures are triggered.

[0026] The technical solution realizes the significant improvement of the performance of the smart home system by constructing a deep collaborative edge cloud integrated architecture, obtains a dynamic device registration and safe initialization mechanism, ensures the seamless access and communication security of heterogeneous devices, and lays a stable and reliable foundation for the system. The adaptive state synchronization algorithm and the bidirectional differential synchronization mechanism can intelligently adjust the synchronization strategy according to the network condition and the key intelligence of the device, not only significantly reducing the network bandwidth occupation, but also ensuring the efficient consistency of the edge cloud state. Even when the network is interrupted, the basic functions can be maintained through the local cache and intelligent recovery mechanism, greatly enhancing the robustness and user experience of the system. In addition, the dynamic execution path decision and load balancing algorithm based on the multi-dimensional evaluation model can intelligently select the optimal execution node according to the real-time instruction complexity, network condition and resource load, effectively balancing the advantages of low delay of edge computing and strong computing power of cloud computing, thereby realizing low delay, high reliable execution of instructions and synchronous optimization of system energy efficiency in complex home environment.

[0027] Referring to Figures 3-4 The edge cloud cooperative state synchronization and instruction execution management system for smart home is used to execute the edge cloud cooperative state synchronization and instruction execution management method described above, and the system includes: The edge processing module is used for searching, registering and managing local smart home devices, building a local device network through protocol conversion and resource assessment, and establishing a secure authentication connection with the cloud service module, receiving an initial collaborative strategy to complete the initialization of the edge-cloud collaborative framework; the cloud service module is used for global policy management, state storage and big data analysis, and secure communication and data interaction with the edge processing module; the state synchronization module is used for real-time monitoring of device states using adaptive synchronization strategies, and maintaining state consistency with the cloud service module through a bidirectional, differential synchronization mechanism, with the ability to intelligently adjust synchronization frequency and offline cache recovery according to device criticality and network conditions; the instruction processing engine is used for receiving and verifying multi-source user instructions, which is composed of a local analysis unit in the edge processing module and a global analysis unit in the cloud service module to perform instruction decomposition, device mapping and conflict detection, and generate an execution plan containing priority and dependency relationship; the collaborative decision engine is used for dynamically deciding the execution path of the execution plan based on instruction complexity, network conditions, resource load factors, and achieving load balancing and risk assessment through a collaborative decision algorithm to execute instructions in a low-delay, high-reliability manner and optimize system energy efficiency; the feedback optimization module is used for collecting full-link feedback data of instruction execution, which is aggregated and analyzed by the cloud service module to identify patterns, evaluate performance and generate optimization strategies, and then dynamically adjust system parameters and predict potential problems through the closed-loop feedback mechanism of edge-cloud collaboration, realizing self-learning and continuous optimization of the system, the adaptive state synchronization algorithm and the bidirectional differential synchronization mechanism can intelligently adjust the synchronization strategy according to the network conditions and the criticality of the device, not only significantly reducing the network bandwidth occupation, but also ensuring the efficient consistency of the edge-cloud state, even in the case of network interruption, the basic functions can be maintained through local cache and intelligent recovery mechanism, greatly enhancing the robustness and user experience of the system.

[0028] In the embodiment, the cooperative decision engine specifically comprises: a load evaluation unit, configured to collect resource utilization data and instruction queue information of each edge node in real time, and calculate global and local load scores through a weighted decision matrix; a risk prediction unit, configured to predict failure probabilities of different execution paths caused by node overload, network delay or device offline, and generate a risk evaluation report; a dynamic routing unit, configured to intelligently route instructions to optimal execution nodes or trigger task migration according to the load scores and the risk evaluation report, and set up backup paths and resource reservation plans for critical instructions; and an energy efficiency optimization unit, configured to introduce an energy efficiency factor in the routing decision, and preferentially select execution nodes or instruction batch execution strategies with higher energy efficiency ratios, so as to optimize overall system energy efficiency while ensuring performance.

[0029] The technical solution constructs a deep cooperative edge-cloud integrated architecture, significantly improves the performance of the smart home system, acquires a dynamic device registration and safe initialization mechanism, ensures seamless access and communication security of heterogeneous devices, lays a stable and reliable foundation for the system, sets a self-learning ability to enable the system to predict potential problems and implement preventive measures, thereby realizing a paradigm shift from passive response to active optimization, not only has excellent immediate response capability, but also has continuous evolution capability, and significantly improves the long-term management efficiency, security and intelligent level of the smart home system.

[0030] The technical solution is based on a dynamic execution path decision and load balancing algorithm of a multi-dimensional evaluation model, can intelligently select optimal execution nodes according to real-time instruction complexity, network conditions and resource load, effectively balances the advantages of low delay of edge computing and strong computing power of cloud computing, and thus realizes low-delay, high-reliable execution of instructions and synchronous optimization of system energy efficiency in a complex home environment.

[0031] In the embodiment, the entire operation process can be controlled by a computer, signal feedback is performed, and the steps are sequentially performed, which are all conventional knowledge of automatic control, and will not be described one by one in the embodiment.

[0032] The above merely describes preferred embodiments of the present application and is not intended to limit the present application, and any modification, equivalent replacement and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for edge-cloud collaborative state synchronization and command execution management for smart homes, characterized in that, Applied to edge gateway management devices, the specific steps include: S101: Search for all local smart home devices, register them on the found devices, establish a secure authentication connection with the cloud platform, download the initial collaboration strategy and initialize local management, and build the edge-cloud collaboration framework through protocol conversion, resource assessment and load pre-configuration. S102: Adopts an adaptive synchronization strategy to monitor the status of smart home devices in real time, and maintains consistency with the cloud platform through a two-way, differential synchronization mechanism. It intelligently adjusts the synchronization frequency according to the criticality of smart home devices and network conditions, and has local caching and recovery capabilities when the network is disconnected. S103: Receives and verifies multi-source user commands. The cloud platform provides intelligent parsing based on the global context. The edge-cloud collaborative parsing engine performs command decomposition, smart device mapping, and conflict detection. The edge gateway is responsible for fast local parsing and finally generates an execution plan containing priorities and dependencies. S104: Based on factors such as instruction complexity, network conditions, and resource load, the execution path of the execution plan is dynamically determined, and then load balancing and risk assessment are achieved through collaborative decision-making algorithms, so as to enable instructions to be executed in a low-latency and highly reliable manner, and simultaneously optimize system energy efficiency. S105: Collects end-to-end feedback data of instruction execution, aggregates and analyzes it on the cloud platform to identify patterns, evaluate performance and generate optimization strategies. Through the closed-loop feedback mechanism of edge-cloud collaboration, it dynamically adjusts system parameters and predicts potential problems, enabling the system to learn and continuously optimize itself.

2. The edge-cloud collaborative state synchronization and instruction execution management method for smart homes as described in claim 1, characterized in that, In S101, all local smart home devices are searched, and registration is performed on the found devices to establish a secure authentication connection with the cloud platform, including: The edge gateway management device uses a multi-protocol adapter to concurrently scan local smart home devices with different communication protocols, and performs capability negotiation and compatibility testing on the discovered local smart home devices to ensure seamless access of heterogeneous local smart home devices. The edge gateway management device dynamically assigns a local virtual ID to newly registered local smart home devices and establishes a mapping relationship with the unique global ID assigned by the cloud platform. The mapping relationship is encrypted and stored locally and synchronously in the cloud in the mapping table, so as to complete subsequent precise control. The establishment of a secure authentication connection adopts two-way verification based on digital certificates. After the edge gateway management device and the cloud platform exchange and verify the certificates, they negotiate to generate a one-time session key for subsequent communication encryption. After the connection is established, both parties periodically update the session key and monitor the communication in real time for any abnormalities. If an abnormality is detected, a security reconstruction mechanism is triggered.

3. The edge-cloud collaborative state synchronization and instruction execution management method for smart homes as described in claim 2, characterized in that, In S102, an adaptive synchronization strategy is adopted to monitor the status of smart home devices in real time, and maintain consistency with the cloud platform through a two-way, differential synchronization mechanism, including: Establish a multi-dimensional evaluation model, input network bandwidth, device power consumption, and status change frequency parameters in real time, and output the optimal synchronization cycle and data compression rate; For continuous state stream data, the edge gateway management device first extracts key frames and performs data anonymization, and then selects lossless or lossy compression mode for synchronization based on the evaluation results, so as to achieve a balance between data value and transmission overhead.

4. The edge-cloud collaborative state synchronization and instruction execution management method for smart homes as described in claim 3, characterized in that, It intelligently adjusts the synchronization frequency based on the criticality of smart home devices and network conditions, and has local caching and recovery capabilities when the network is down, including: The edge gateway management device maintains a ring buffer to store all state change events and out-of-synchronization instructions during the network outage in chronological order, and records the operation sequence number to prevent data overwriting; When the network recovers, the edge gateway management device first compares the status version with the cloud platform, performs incremental data synchronization based on the differences, and reorders the execution of the delayed instructions according to the operation sequence number to ensure eventual consistency of the status.

5. The edge-cloud collaborative state synchronization and instruction execution management method for smart homes as described in claim 4, characterized in that, In S103, the edge-cloud collaborative parsing engine performs instruction decomposition, smart device mapping, and conflict detection, while the edge gateway is responsible for fast local parsing, ultimately generating an execution plan that includes priorities and dependencies, including: After decomposing complex scene instructions into atomic operation sequences, the parsing engine constructs a temporary instruction dependency graph, analyzes the timing and conditional relationships between operations, simulates the execution dependency graph, compares the current state with other instructions that are in the queue, identifies resource competition or logical contradictions, and automatically resolves conflicts or reports to user arbitration to obtain an execution plan. The priority of the execution plan is dynamically calculated based on the instruction type, user identity, and context. The edge gateway management device will set execution barriers and timeout monitoring for operations with strict dependencies to ensure that subsequent operations are triggered only after the preceding operations are successfully completed; otherwise, the overall plan will enter the exception handling process.

6. The edge-cloud collaborative state synchronization and instruction execution management method for smart homes as described in claim 5, characterized in that, In S104, the execution path of the execution plan is dynamically determined based on factors such as instruction complexity, network conditions, and resource load, including: A dynamic decision matrix is ​​established, which quantifies instruction complexity into a computational overhead index, network conditions into latency and bandwidth scores, and the resource load of edge nodes and cloud platforms into an available resource index. Weight thresholds are set for each evaluation factor, and a weighted scoring algorithm is designed. When the weighted total score of an instruction is lower than a set threshold, it automatically decides to execute it at the edge; if it is higher than the threshold, it decides to execute it in the cloud or perform edge-cloud collaborative execution, thus achieving a preliminary quantitative selection of the execution path. Continuously monitor the actual execution effect of the decided instructions. If a decision deviation is found, automatically fine-tune the weight parameters in the decision matrix or trigger path rerouting. For collaborative execution tasks, dynamically divide the distribution ratio of subtasks between the edge and cloud, and start the local degradation scheme when the network jitter occurs to ensure that the decision always fits the real-time state and realizes dynamic optimization of the execution path.

7. The edge-cloud collaborative state synchronization and instruction execution management method for smart homes as described in claim 6, characterized in that, Then, load balancing and risk assessment are achieved through collaborative decision-making algorithms, enabling commands to be executed in a low-latency, highly reliable manner, while simultaneously optimizing system energy efficiency, including: The collaborative decision-making algorithm constructs a unified decision-making model, which aggregates resource utilization data of CPU, memory, and network I / O from each edge node in real time. It combines instruction queue depth and type and uses fuzzy logic or weighted decision matrix to calculate global and local real-time load scores. At the same time, it performs risk assessment on instruction execution paths and predicts assessment results that may fail due to node overload, network latency, or device offline. Based on the evaluation results, the collaborative decision-making algorithm dynamically executes load balancing strategies and implements risk avoidance. For high-load areas, new instructions or queued instructions are intelligently routed to edge nodes or cloud platforms with lighter loads, and task migration between nodes can be triggered by setting up instruction execution contingency plans with different risk levels. Meanwhile, the collaborative decision-making algorithm introduces an energy efficiency factor, prioritizing the selection of execution nodes or instruction batch execution strategies with higher energy efficiency ratios during decision-making, ensuring both low latency and high reliability while optimizing performance.

8. The edge-cloud collaborative state synchronization and instruction execution management method for smart homes as described in claim 7, characterized in that, In S105, patterns are identified, performance is evaluated, and optimization strategies are generated. Through a closed-loop feedback mechanism involving edge-cloud collaboration, system parameters are dynamically adjusted and potential problems are predicted, including: The cloud platform uses big data analytics and machine learning models to deeply mine the aggregated end-to-end feedback data. It identifies common features of high-frequency failure modes and successful execution paths through cluster analysis, evaluates the evolution trend of performance indicators through time series analysis, and generates data-driven optimization strategies to adjust the default execution path of instructions, optimize the state synchronization frequency, or update conflict detection rules. The generated optimization strategy is sent to the edge gateway management device through the edge-cloud collaboration channel. The feedback data generated by the edge gateway management device after applying the new strategy is reported again. The cloud platform receives the feedback data and dynamically adjusts the system parameters. A prediction model is built by training historical data. After the prediction model is trained in stages, potential problems are actively predicted and preventive measures are triggered.

9. A cloud-edge collaborative status synchronization and command execution management system for smart homes, characterized in that: The system is used to execute the edge-cloud collaborative state synchronization and instruction execution management method according to any one of claims 1-8, the system comprising: The edge processing module is used to search, register and manage local smart home devices. It builds a local device network through protocol conversion and resource assessment, establishes a secure authentication connection with the cloud service module, and receives the initial collaboration strategy to complete the initialization of the edge-cloud collaboration framework. The cloud service module is used for global policy management, state storage and big data analysis, and to communicate and interact securely with the edge processing module. The status synchronization module is used to monitor the device status in real time using an adaptive synchronization strategy, and maintains consistency with the cloud service module through a two-way, differential synchronization mechanism. It has the ability to intelligently adjust the synchronization frequency and recover from network outages based on the criticality of the device and network conditions. The instruction processing engine is used to receive and verify multi-source user instructions. It is composed of the local parsing unit in the edge processing module and the global parsing unit in the cloud service module to perform instruction decomposition, device mapping and conflict detection, and generate an execution plan that includes priority and dependency relationships. The collaborative decision engine is used to dynamically determine the execution path of the execution plan based on instruction complexity, network conditions, and resource load factors. It also achieves load balancing and risk assessment through collaborative decision algorithms, so as to execute instructions in a low-latency and highly reliable manner and optimize system energy efficiency. The feedback optimization module collects feedback data from the entire instruction execution process. This data is then aggregated and analyzed by the cloud service module to identify patterns, evaluate performance, and generate optimization strategies. Finally, through a closed-loop feedback mechanism involving edge-cloud collaboration, the system parameters are dynamically adjusted and potential problems are predicted, enabling the system to learn and continuously optimize itself.

10. The edge-cloud collaborative state synchronization and instruction execution management system for smart homes as described in claim 9, characterized in that, The collaborative decision-making engine specifically includes: The load assessment unit is used to aggregate resource utilization data and instruction queue information from each edge node in real time, and calculate global and local load scores through a weighted decision matrix. The risk prediction unit is used to predict the probability of failure of different execution paths due to node overload, network latency or device offline, and generate a risk assessment report. The dynamic routing unit is used to intelligently route instructions to the optimal execution node or trigger task migration based on the load score and risk assessment report, and to establish backup paths and resource reservation plans for critical instructions. The energy efficiency optimization unit is used to introduce energy efficiency factors into routing decisions, prioritizing the selection of execution nodes or instruction batch execution strategies with higher energy efficiency ratios, thereby optimizing the overall system energy efficiency while ensuring performance.

Images