Smart home network optimization method, device, equipment, medium and product

Abstract

The invention provides a smart home network optimization method, device and equipment, a medium and a product, and is applied to the technical field of smart home, and the method comprises the steps: obtaining the network state data of a smart home network through home host equipment; sending the network state data to a cloud platform through the home host device, so that the cloud platform determines a target network topology scheme from a plurality of network topology schemes according to the network state data; the target network topology scheme sent by the cloud platform is received through the home host device, and the connection relationship between the smart home devices is adjusted according to the target network topology scheme, so that the network topology scheme is generated by obtaining the network state data, the real-time sensing of the environment change is realized, the problem of network topology lag is solved, and the network topology delay is reduced. And the connection relationship between the devices is dynamically adjusted through a network topology scheme, so that network paralysis caused by communication path failure is avoided, and the requirements of the smart home scene for high reliability and adaptability are improved.

Description

Technical Field

[0001] This invention relates to the field of smart home technology, and in particular to a method, apparatus, device, medium, and product for optimizing smart home networks. Background Technology

[0002] Currently, smart home systems rely on a centralized gateway architecture for device connectivity and control. All devices must connect to a central gateway for unified management and control. This centralized gateway architecture features a fixed network topology (i.e., the layout of connections between devices and gateways, and between devices themselves).

[0003] In existing technologies, topology adjustments are achieved through preset link quality thresholds or periodic polling. This passive adjustment mode causes topology optimization to lag behind actual environmental changes. For example, when devices move, furniture obstructs signal attenuation, or new devices are added and change the network load, the topology cannot adapt in time. Once critical communication paths are interrupted or central nodes fail, it can easily lead to local or even overall network paralysis, failing to meet the core requirements of high reliability and adaptability in smart home scenarios. Summary of the Invention

[0004] In view of the above problems, a method, apparatus, device, medium, and product for optimizing smart home networks are proposed to overcome or at least partially solve the above problems, including: A method for optimizing a smart home network, wherein the smart home network is equipped with a home host device and smart home devices, the method comprising: The home host device acquires network status data of the smart home network. The network status data is sent to the cloud platform through the home host device, so that the cloud platform can determine the target network topology scheme from multiple network topology schemes based on the network status data; The home host device receives the target network topology scheme sent by the cloud platform and adjusts the connection relationship between the smart home devices according to the target network topology scheme.

[0005] Optionally, the smart home devices include routing devices, each equipped with a pheromone concentration table. After adjusting the connection relationships between the smart home devices according to the target network topology scheme, the system further includes: During packet forwarding, the transition probability of multiple routing paths is determined based on the pheromone concentration between routing devices, and the target routing path is determined from the multiple routing paths based on the transition probability. The routing device forwards data packets according to the target routing path.

[0006] Optionally, the transition probability of multiple routing paths is determined based on the pheromone concentration between routing devices, including: The transition probability of multiple routing paths is determined based on link quality, path load, remaining energy of devices, and pheromone concentration between routing devices.

[0007] Optionally, based on the network state data, determining the target network topology scheme from multiple network topology schemes includes: Based on the network status data, multiple network topology schemes are evaluated, and based on the evaluation results, a target network topology scheme is determined from the multiple network topology schemes.

[0008] Optionally, based on the network state data, multiple network topology schemes are evaluated to determine a target network topology scheme from the multiple network topology schemes based on the evaluation results, including: Create an undirected graph; wherein the undirected graph includes a vertex set, an edge set, and a weight matrix, wherein the vertices in the vertex set correspond to the smart home devices, the edges in the edge set correspond to the communication links between the smart home devices, and each edge in the edge set has a set of weight values ​​in the weight matrix, wherein each weight value in the set of weight values ​​corresponds to an evaluation score of an optimization objective, and the evaluation score is determined based on the network state data; Based on the vertex set and edge set of the undirected graph, multiple connected subgraphs are determined, and based on the weight matrix of the undirected graph, a target connected subgraph is determined from the multiple connected subgraphs; wherein, each connected subgraph corresponds to a network topology scheme; Based on the target connected subgraph, a target network topology scheme is generated.

[0009] Optionally, the optimization objectives include any one or more of the following: communication latency cost, energy consumption cost, reliability cost, and load balancing cost.

[0010] Optionally, the network status data includes any one or more of the following: link quality indicators, device load status, network performance data, and device energy consumption level.

[0011] A device for optimizing a smart home network, wherein the smart home network includes a home host device and smart home devices, the device comprising: The network status data acquisition module is used to acquire network status data of the smart home network through the home host device; The target network topology scheme determination module is used to send the network status data to the cloud platform through the home host device, so that the cloud platform can determine the target network topology scheme from multiple network topology schemes based on the network status data; The connection relationship adjustment module is used to receive the target network topology scheme sent by the cloud platform through the home host device, and adjust the connection relationship between the smart home devices according to the target network topology scheme.

[0012] A home console device includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the method described above.

[0013] A computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the method described above.

[0014] A computer program product includes a computer program that, when executed by a processor, implements the method described above.

[0015] The embodiments of the present invention have the following advantages: In this embodiment of the invention, network status data of the smart home network is acquired through a home host device; the network status data is then sent to a cloud platform, which determines a target network topology scheme from multiple network topology schemes based on the network status data; the home host device receives the target network topology scheme sent by the cloud platform and adjusts the connection relationships between smart home devices according to the target network topology scheme. This achieves the generation of a network topology scheme by acquiring network status data, enabling real-time perception of environmental changes, solving the problem of network topology lag, and dynamically adjusting the connection relationships between devices through the network topology scheme to avoid network paralysis caused by communication path failures, thereby improving the high reliability and adaptability requirements of smart home scenarios. Attached Figure Description

[0016] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a cloud-edge collaborative architecture diagram for smart home network optimization provided by some embodiments of the present invention; Figure 2 This is a flowchart of the steps of a second method for optimizing a smart home network provided in some embodiments of the present invention; Figure 3 This is a flowchart of the steps of a method for optimizing a smart home network according to some embodiments of the present invention; Figure 4This is a structural block diagram of a smart home network optimization device provided in some embodiments of the present invention. Detailed Implementation

[0018] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0019] In related technologies, the device connection and control of smart home systems rely on a centralized gateway architecture. All devices need to be connected to the central gateway, which will uniformly manage and control them. The centralized gateway architecture is a fixed network topology (i.e., the layout of the connection relationships between devices and gateways, and between devices).

[0020] However, the following problems exist when using the above method: 1. Since topology optimization is achieved through preset link quality thresholds or periodic adjustments, it lacks the ability to perceive network status in real time and to coordinate multi-objective optimization. This results in topology adjustments lagging behind environmental changes, a high risk of single-point failures, and difficulty in meeting the high reliability and adaptability requirements of smart home scenarios.

[0021] 2. It achieves self-organizing networks through simple broadcast retransmission or fixed routing tables. Due to the lack of intelligent path planning and predictive maintenance mechanisms, network recovery is slow when interrupted, and the reliability of control command transmission is insufficient when the link is unstable, making it difficult to meet the high availability requirements of IoT devices for real-time control.

[0022] Based on this, this invention proposes to collect network status data locally in real time on a home host, and then perform multi-objective optimization analysis on a cloud platform to generate the optimal topology configuration. By combining local real-time performance with global optimization capabilities, a topology optimization algorithm based on a multi-constraint graph model is adopted. This algorithm comprehensively considers multiple dimensions such as link quality, device load, and energy balance to achieve proactive predictive adjustment of the topology, thereby improving network robustness, reducing dependence on a single node, and enhancing the system's adaptability in dynamic environments.

[0023] like Figure 1 The cloud-edge collaborative architecture proposed in this invention can be divided into a cloud platform layer, a home host layer, and a device layer. The cloud platform layer is responsible for global optimization and configuration distribution, the home host layer is responsible for device management, data collection, protocol conversion, etc., and the nodes in the device layer (i.e. smart home devices) communicate through self-organized communication via a Thread Mesh network.

[0024] Secondly, this invention employs an adaptive routing mechanism based on bio-inspired algorithms, enabling devices to form an intelligent mesh network via the Thread protocol, supporting multi-path redundancy and rapid fault recovery. By introducing an improved ant colony optimization algorithm for path selection, combined with a link quality prediction model, real-time route optimization and load balancing are achieved, thereby improving the success rate and timeliness of command transmission. Even when parts of the network fail, effective communication can still be maintained, extending device battery life.

[0025] The following combination Figure 2 The present invention will be further described as follows: Reference Figure 2 The diagram illustrates a flowchart of a method for optimizing a smart home network according to some embodiments of the present invention, which may specifically include the following steps: Step 201: Obtain network status data of the smart home network through the home host device.

[0026] In some embodiments of the present invention, the network status data includes any one or more of the following: link quality indicators, device load status, network performance data, and device energy consumption level.

[0027] In some examples, the home host device can collect the real-time operating status of various smart home devices in the smart home network through the Thread network protocol. The data collection dimensions may include link quality indicators (received signal strength, signal-to-noise ratio, bit error rate), device load status (processing capacity utilization, memory usage), network performance data (end-to-end transmission latency, data throughput, packet loss rate), and device power consumption level.

[0028] The energy consumption level of the device can be reported by the power management module of the smart home device itself.

[0029] After collecting real-time operational data, noise suppression can be achieved using a Kalman filter algorithm in the data preprocessing module, combined with anomaly detection algorithms to identify invalid data, generating standardized network state data, such as a network state description vector. For example, standardized data from multiple dimensions (such as signal strength, delay, load, etc.) can be combined into a single digital vector to concisely represent the network state, facilitating algorithm processing.

[0030] As examples, smart home network initialization can be performed before acquiring network status data for the smart home network.

[0031] For example, when the system starts up, the home host device can initialize the Thread network protocol border router function, broadcast network beacon signals, announce the existence of the smart home network, and enable new smart home devices to discover and apply to join. New smart home devices can join the network through the Matter (Internet of Things) configuration protocol, using a two-way authentication mechanism based on X.509 certificates.

[0032] The device discovery process can combine active scanning and passive listening. The home host device can periodically send device discovery requests while listening for join requests actively reported by devices. Each successfully connected smart home device can be assigned a unique network identifier and a complete file can be created containing information such as device capability descriptions (e.g., temperature sensor, colored lighting device), communication protocol support (e.g., support for Thread 1.3 protocol, support for Matter over Wi-Fi), and computing power (e.g., CPU clock speed of 100MHz, memory of 256KB).

[0033] Step 202: The network status data is sent to the cloud platform through the home host device, so that the cloud platform can determine the target network topology scheme from multiple network topology schemes based on the network status data.

[0034] As examples, home host devices can upload network status data to a cloud platform via an encrypted tunnel based on TLS (Transport Layer Security).

[0035] The multiple network topology schemes can be combinations of a large number of potential smart home device connection relationships generated iteratively through algorithms (such as genetic algorithms), with each network topology scheme being a connected subgraph that satisfies connectivity constraints. The target network topology scheme can be the network topology scheme with the best overall performance in the current state, calculated by the cloud platform through a multi-objective optimization algorithm.

[0036] In some examples, the cloud platform can model the received network state data as a weighted undirected graph and use an optimization engine, such as a genetic algorithm, to search and evaluate multiple network topology schemes (i.e., different connected subgraphs), select a scheme that achieves the optimal balance under multiple constraints such as latency, reliability, load balancing, and energy consumption, and then send it to the home host for execution as the target network topology scheme.

[0037] In some embodiments of the present invention, determining a target network topology scheme from multiple network topology schemes based on the network status data includes: evaluating multiple network topology schemes based on the network status data, and determining the target network topology scheme from the multiple network topology schemes based on the evaluation results.

[0038] As examples, cloud platforms can run multi-objective constrained optimization algorithms, evaluate each network topology scheme by calculating a comprehensive score through an objective optimization function, determine the evaluation results, and select a target network topology scheme from multiple network topology schemes based on the evaluation results.

[0039] The evaluation result can be the total score of each network topology scheme. Based on the evaluation result, the optimal network topology scheme can be selected from multiple network topology schemes as the target network topology scheme.

[0040] In some embodiments of the present invention, multiple network topology schemes are evaluated based on the network state data, and a target network topology scheme is determined from the multiple network topology schemes based on the evaluation results, including: Sub-step 11: Create an undirected graph; wherein the undirected graph includes a vertex set, an edge set, and a weight matrix, wherein the vertices in the vertex set correspond to the smart home devices, the edges in the edge set correspond to the communication links between the smart home devices, and each edge in the edge set has a set of weight values ​​in the weight matrix, wherein each weight value in the set of weight values ​​corresponds to an evaluation score of an optimization objective, and the evaluation score is determined based on the network state data.

[0041] In some embodiments of the present invention, the optimization objectives include any one or more of the following: communication latency cost, energy consumption cost, reliability cost, and load balancing cost.

[0042] As examples, after obtaining network status data, the network status data can be analyzed, and evaluation scores for communication latency costs, energy consumption costs, reliability costs, and load balancing costs can be calculated.

[0043] In some examples, the cloud platform can model the received network state data as a weighted undirected graph.

[0044] In this system, each vertex in the vertex set can represent a smart home device (such as a smart light or sensor); each edge in the edge set can represent a potential, evaluable communication link between two smart home devices; and the weight matrix can associate a set of weight values ​​with each edge, with each weight value corresponding to an evaluation score of an optimization objective (such as communication latency cost, energy consumption cost, reliability cost, or load balancing cost) to evaluate the quality of the communication link.

[0045] As examples, the cloud platform models network state data as a weighted undirected graph G=(V, E, W), where the vertex set V represents the set of smart home device nodes, with each vertex representing a smart home device (such as a living room light or a bedroom sensor); the edge set E represents the set of communication links, with each edge e(u, v) representing a potential direct communication link that can be established or evaluated between smart home devices u and v; and each edge in the edge set has a set of weight values ​​in the weight matrix W, with each weight value corresponding to an evaluation score for an optimization objective. For example, each edge e in the weighted undirected graph has a set of weight values ​​[W1(e), W2(e), ..., W...]. n (e)], where each weight value represents the optimization objective, namely the "cost" or "price" of using this communication link.

[0046] For example, W1(e) represents communication latency cost (the higher the latency, the higher the cost); W2(e) represents energy consumption cost (the higher the power consumption, the higher the cost); W3(e) represents reliability cost (the higher the packet loss rate, the higher the cost); W4(e) represents load balancing cost (if the devices at both ends of the link are already very busy, the cost is high).

[0047] Sub-step 12: Based on the vertex set and edge set in the undirected graph, determine multiple connected subgraphs, and based on the weight matrix in the undirected graph, determine the target connected subgraph from the multiple connected subgraphs; wherein each connected subgraph corresponds to a network topology scheme.

[0048] As examples, a subgraph structure can be obtained by selecting a subset of vertices and edges from a weighted undirected graph, where these vertices are fully connected through the selected edges. Each connected subgraph represents a feasible network topology scheme.

[0049] Among them, the target connected subgraph can be selected from multiple connected subgraphs based on a preset multi-objective optimization function (such as achieving Pareto optimality) to select the connected subgraph with the best evaluation result.

[0050] As examples, finding the optimal network topology can be understood as finding the optimal connected subgraph G' of a weighted undirected graph G. Let G be the objective function that makes the multi-objective optimization function F(G') Pareto optimal. The objective function F(G') is calculated as follows:

[0051] in, This represents summing all edges in the optimal connected subgraph G'; This represents the optimization objectives for n targets (i.e., W1(e), W2(e), ..., W...). n(e) Perform summation; n represents the total number of optimization objectives; The weight coefficients for each optimization objective (i.e., the evaluation scores mentioned above) are the importance weights assigned to the i-th optimization objective. They can determine which optimization objective is valued more in the global optimization. For example, if low latency is valued most, λ1=0.5 can be set, and if low energy consumption is valued second, λ2=0.3 can be set.

[0052] In some examples, multiple possible connected subgraphs G' can be generated randomly or iteratively through a genetic algorithm. For each connected subgraph, it can be evaluated using the multi-objective optimization function described above. Based on the evaluation results, the target connected subgraph is determined. For example, the lower the total evaluation score (assuming cost minimization), the better the overall performance of this connected subgraph. Then, among all connected subgraphs, the target connected subgraph with the smallest F(G') can be found.

[0053] In some examples, multi-objective optimization algorithms can employ a genetic algorithm framework with an elitist retention strategy, where the crossover operator uses edge recombination and the mutation operator combines a local search strategy to adaptively adjust genetic parameters to balance exploration and exploitation.

[0054] For example, chromosome encoding (edge ​​set representation) in genetic algorithms uses a string of binary codes to indicate whether each edge in graph G is selected to enter subgraph G' (ensuring that there are no broken or invalid cases in the connected subgraph). The objective optimization function F(G') has a larger (or smaller, depending on the definition) value, the better the connected subgraph. Strategies such as elitism retention retain excellent connected subgraphs during iterations and generate new connected subgraphs through crossover and mutation, eventually converging to the optimal or near-optimal connected subgraph (i.e., the target connected subgraph).

[0055] Sub-step 13: Generate the target network topology scheme based on the target connected subgraph.

[0056] After determining the target connected subgraph, the corresponding vertices and edges can be selected based on the structure and connection relationships of the target connected subgraph to generate the corresponding target network topology scheme, which can then be sent to the home host device.

[0057] Step 203: Receive the target network topology scheme sent by the cloud platform through the home host device, and adjust the connection relationship between the smart home devices according to the target network topology scheme.

[0058] After the home host device receives the target network topology scheme sent by the cloud platform, the local execution engine in the home host device can dynamically adjust the connection relationship between devices through Matter control commands, such as establishing or disconnecting direct Thread network links between certain smart home devices, thereby changing the actual communication topology.

[0059] In some embodiments of the present invention, the smart home device includes a routing device, each routing device being equipped with a pheromone concentration table. After adjusting the connection relationship between the smart home devices according to the target network topology scheme, the device further includes: During packet forwarding, the transition probability of multiple routing paths is determined based on the pheromone concentration between routing devices, and a target routing path is determined from the multiple routing paths based on the transition probability; the packets are then forwarded through the routing devices according to the target routing path.

[0060] In some examples, the pheromone concentration table is a numerical table maintained by each routing device to record the historical communication success experience of the routing device to its neighboring routing devices. The higher the pheromone concentration, the better the past performance of the path.

[0061] In practical applications, each routing device can be configured with a pheromone concentration table. When a data packet needs to be forwarded, the routing device can query its own pheromone concentration table and calculate the transition probability of multiple routing paths based on the pheromone concentration values ​​recorded in the table, combined with an improved ant colony optimization algorithm.

[0062] After determining the transition probability, the route with the highest transition probability among multiple routes can be selected as the target route, in order of the calculated transition probability values.

[0063] For example, if there are three routing paths A, B, and C, with corresponding transition probabilities of 0.5, 0.3, and 0.2 respectively, routing path A can be chosen as the target routing path. After determining the target routing path, the routing device can forward data packets according to the target routing path, accurately sending the data packets to the next routing device until the data packets reach their final destination.

[0064] In some examples, routing devices can establish a self-organizing mesh network based on the Thread protocol according to the target network topology. The routing protocol employs an improved on-demand distance vector routing mechanism. Multiple routing paths can be determined based on the target network topology, which may include multiple communication links between routing devices.

[0065] The routing device can also detect network topology changes in real time through periodic Hello message exchange and bidirectional link quality assessment, so as to trigger route recalculation in a timely manner when the device moves, fails, or the signal changes, thus maintaining smooth communication.

[0066] In some embodiments of the present invention, determining the transition probability of multiple routing paths based on the pheromone concentration between routing devices includes: determining the transition probability of multiple routing paths based on link quality, path load, remaining energy of devices, and pheromone concentration between routing devices.

[0067] As examples, the link quality, path load, and remaining energy of multiple routing paths between routing devices can be collected, and the transition probability of multiple routing paths can be calculated by combining the pheromone concentration between routing devices.

[0068] For example, the transition probability can be calculated using the following formula:

[0069] in, This refers to the transition probability; α represents the pheromone heuristic factor, which controls the ant's choice of path based on historical experience (pheromone concentration). The greater the α value, the more likely the ant is to choose the old path that many other ants have successfully taken before; β is the heuristic factor; β is the expected heuristic factor, which can control how much importance the ants attach to the current link's immediate quality estimate (η, usually the inverse of link quality or the inverse of delay). The larger β is, the more the ants tend to choose the "shortcut" that looks like it has better quality.

[0070] in, This represents the summation of the sets of all neighboring routing devices k of the current routing device i; This represents the current pheromone concentration on the path from the current routing device i to its neighboring routing device k. A higher concentration indicates more successful historical communication experiences. This represents the heuristic information from routing device i to neighboring routing device k, and is usually defined as the reciprocal of the link quality estimate (e.g., 1 / delay). The pheromone concentration from routing device i to routing device j (reflects historical successful communication experience; higher concentration is better).

[0071] In the above embodiments, the load balancing module can also monitor network traffic distribution in real time and dynamically adjust the path selection probability to avoid network congestion and the formation of hotspots.

[0072] In some examples, self-organizing mesh networks can be extended based on the AODV (Ad-hoc On-Demand Distance Vector Routing Protocol) framework, combining link quality, path load, remaining energy of devices, and pheromone concentration between routing devices to determine the quality of routing paths and then select the optimal path (i.e., the target routing path).

[0073] For example, the target routing path can be selected using an ant colony optimization algorithm. Each routing device maintains a pheromone concentration table. Ant packets (probe packets) are sent from the source node (i.e., the first routing device) and the next hop is selected based on the transition probability.

[0074] In this context, "ant packets" refer to a special type of route probing data packet. When a routing device needs to find a new route to a target routing device, it can send out one or more probing packets. Like ants, these probing packets crawl randomly in the network (i.e., choose the next hop) and record path information and link quality along the way. After finally reaching the target routing device, the path information traversed by this "ant" is fed back to update the network state (pheromone concentration).

[0075] The pheromone concentration update can include local updates and global updates. Local updates are performed immediately when the data packet traverses the path, while global updates are evaluated based on end-to-end performance after the path is successfully established. For example, the pheromone update rules are as follows:

[0076] Where ρ is the pheromone evaporation coefficient, a constant between 0 and 1 (such as 0.1), which simulates the natural evaporation of pheromones over time; ρ can be preset, and its magnitude determines the rate at which historical information is forgotten. A large ρ results in faster pheromone evaporation, making the algorithm more sensitive to network changes but prone to losing stable paths; a small ρ results in slower convergence but more stable paths.

[0077] in, The pheromone increment is determined by the actual transmission results of the ant packets. If an "ant" successfully reaches its destination from i through j, and the entire path is of high quality (e.g., low latency), then it will release pheromones on each segment (i, j) of this path. =Q / Total Path Cost, where Q is a constant, and path cost can be the total delay. A better path increases... The more. If the transmission fails, it may not increase, or even become negative (penalty).

[0078] In this embodiment of the invention, network status data of the smart home network is acquired through a home host device; the network status data is then sent to a cloud platform, which determines a target network topology scheme from multiple network topology schemes based on the network status data; the home host device receives the target network topology scheme sent by the cloud platform and adjusts the connection relationships between smart home devices according to the target network topology scheme. This achieves the generation of a network topology scheme by acquiring network status data, enabling real-time perception of environmental changes, solving the problem of network topology lag, and dynamically adjusting the connection relationships between devices through the network topology scheme to avoid network paralysis caused by communication path failures, thereby improving the high reliability and adaptability requirements of smart home scenarios.

[0079] Reference Figure 3 The diagram illustrates a flowchart of another method for optimizing a smart home network according to some embodiments of the present invention, which may specifically include the following steps: Step 301: Obtain network status data of the smart home network through the home host device.

[0080] In some embodiments of the present invention, the network status data includes any one or more of the following: link quality indicators, device load status, network performance data, and device energy consumption level.

[0081] In some examples, the home host device can collect the real-time operating status of various smart home devices in the smart home network through the Thread network protocol. The data collection dimensions may include link quality indicators (received signal strength, signal-to-noise ratio, bit error rate), device load status (processing capacity utilization, memory usage), network performance data (end-to-end transmission latency, data throughput, packet loss rate), and device power consumption level.

[0082] The energy consumption level of the device can be reported by the power management module of the smart home device itself.

[0083] After collecting real-time operational data, noise suppression can be achieved using a Kalman filter algorithm in the data preprocessing module, combined with anomaly detection algorithms to identify invalid data, generating standardized network state data, such as a network state description vector. For example, standardized data from multiple dimensions (such as signal strength, delay, load, etc.) can be combined into a single digital vector to concisely represent the network state, facilitating algorithm processing.

[0084] As examples, smart home network initialization can be performed before acquiring network status data for the smart home network.

[0085] For example, when the system starts up, the home host device can initialize the Thread network protocol border router function, broadcast network beacon signals, announce the existence of the smart home network, and enable new smart home devices to discover and apply to join. New smart home devices can join the network through the Matter (Internet of Things) configuration protocol, using a two-way authentication mechanism based on X.509 certificates.

[0086] The device discovery process can combine active scanning and passive listening. The home host device can periodically send device discovery requests while listening for join requests actively reported by devices. Each successfully connected smart home device can be assigned a unique network identifier and a complete file can be created containing information such as device capability descriptions (e.g., temperature sensor, colored lighting device), communication protocol support (e.g., support for Thread 1.3 protocol, support for Matter over Wi-Fi), and computing power (e.g., CPU clock speed of 100MHz, memory of 256KB).

[0087] Step 302: Send the network status data to the cloud platform through the home host device.

[0088] As examples, home host devices can upload network status data to a cloud platform via an encrypted tunnel based on TLS (Transport Layer Security).

[0089] The multiple network topology schemes can be combinations of a large number of potential smart home device connection relationships generated iteratively through algorithms (such as genetic algorithms), with each network topology scheme being a connected subgraph that satisfies connectivity constraints. The target network topology scheme can be the network topology scheme with the best overall performance in the current state, calculated by the cloud platform through a multi-objective optimization algorithm.

[0090] In some examples, the cloud platform can model the received network state data as a weighted undirected graph and use an optimization engine, such as a genetic algorithm, to search and evaluate multiple network topology schemes (i.e., different connected subgraphs), select a scheme that achieves the optimal balance under multiple constraints such as latency, reliability, load balancing, and energy consumption, and then send it to the home host for execution as the target network topology scheme.

[0091] Step 303: The cloud platform creates an undirected graph based on the network state data; wherein the undirected graph includes a vertex set, an edge set, and a weight matrix, wherein the vertices in the vertex set correspond to the smart home devices, the edges in the edge set correspond to the communication links between the smart home devices, and each edge in the edge set has a set of weight values ​​in the weight matrix, wherein each weight value in the set of weight values ​​corresponds to an evaluation score of an optimization objective, and the evaluation score is determined based on the network state data.

[0092] In some embodiments of the present invention, the optimization objectives include any one or more of the following: communication latency cost, energy consumption cost, reliability cost, and load balancing cost.

[0093] As examples, after obtaining network status data, the network status data can be analyzed, and evaluation scores for communication latency costs, energy consumption costs, reliability costs, and load balancing costs can be calculated.

[0094] In some examples, the cloud platform can model the received network state data as a weighted undirected graph.

[0095] In this system, each vertex in the vertex set can represent a smart home device (such as a smart light or sensor); each edge in the edge set can represent a potential, evaluable communication link between two smart home devices; and the weight matrix can associate a set of weight values ​​with each edge, with each weight value corresponding to an evaluation score of an optimization objective (such as communication latency cost, energy consumption cost, reliability cost, or load balancing cost) to evaluate the quality of the communication link.

[0096] As examples, the cloud platform models network state data as a weighted undirected graph G = (V, E, W), where the vertex set V represents the set of smart home device nodes, with each vertex representing a smart home device (such as a living room light or a bedroom sensor); the edge set E represents the set of communication links, with each edge e(u, v) representing a potential direct communication link that can be established or evaluated between smart home devices u and v; and each edge in the edge set has a set of weight values ​​in the weight matrix W, with each weight value corresponding to an evaluation score for an optimization objective. For example, each edge e in the weighted undirected graph has a set of weight values ​​[W1(e), W2(e), ..., W...]. n (e)], where each weight value represents the optimization objective, namely the "cost" or "price" of using this communication link.

[0097] For example, W1(e) represents communication latency cost (the higher the latency, the higher the cost); W2(e) represents energy consumption cost (the higher the power consumption, the higher the cost); W3(e) represents reliability cost (the higher the packet loss rate, the higher the cost); W4(e) represents load balancing cost (if the devices at both ends of the link are already very busy, the cost is high).

[0098] Step 304: Based on the vertex set and edge set in the undirected graph, determine multiple connected subgraphs, and based on the weight matrix in the undirected graph, determine the target connected subgraph from the multiple connected subgraphs; wherein each connected subgraph corresponds to a network topology scheme.

[0099] As examples, a subgraph structure can be obtained by selecting a subset of vertices and edges from a weighted undirected graph, where these vertices are fully connected through the selected edges. Each connected subgraph represents a feasible network topology scheme.

[0100] Among them, the target connected subgraph can be selected from multiple connected subgraphs based on a preset multi-objective optimization function (such as achieving Pareto optimality) to select the connected subgraph with the best evaluation result.

[0101] In some examples, multiple possible connected subgraphs G' can be generated randomly or iteratively through a genetic algorithm. For each connected subgraph, it can be evaluated using the multi-objective optimization function described above. Based on the evaluation results, the target connected subgraph is determined. For example, the lower the total evaluation score (assuming cost minimization), the better the overall performance of this connected subgraph. Then, among all connected subgraphs, the target connected subgraph with the smallest F(G') can be found.

[0102] In some examples, multi-objective optimization algorithms can employ a genetic algorithm framework with an elitist retention strategy, where the crossover operator uses edge recombination and the mutation operator combines a local search strategy to adaptively adjust genetic parameters to balance exploration and exploitation.

[0103] For example, chromosome encoding (edge ​​set representation) in genetic algorithms uses a string of binary codes to indicate whether each edge in graph G is selected to enter subgraph G' (ensuring that there are no broken or invalid cases in the connected subgraph). The objective optimization function F(G') has a larger (or smaller, depending on the definition) value, the better the connected subgraph. Strategies such as elitism retention retain excellent connected subgraphs during iterations and generate new connected subgraphs through crossover and mutation, eventually converging to the optimal or near-optimal connected subgraph (i.e., the target connected subgraph).

[0104] Step 305: Generate the target network topology scheme based on the target connected subgraph.

[0105] After determining the target connected subgraph, the corresponding vertices and edges can be selected based on the structure and connection relationships of the target connected subgraph to generate the corresponding target network topology scheme, which can then be sent to the home host device.

[0106] Step 306: The home host device receives the target network topology scheme sent by the cloud platform and adjusts the connection relationship between the smart home devices according to the target network topology scheme.

[0107] After the home host device receives the target network topology scheme sent by the cloud platform, the local execution engine in the home host device can dynamically adjust the connection relationship between devices through Matter control commands, such as establishing or disconnecting direct Thread network links between certain smart home devices, thereby changing the actual communication topology.

[0108] In some embodiments of the present invention, the smart home device includes a routing device, each routing device being equipped with a pheromone concentration table. After adjusting the connection relationship between the smart home devices according to the target network topology scheme, the device further includes: During packet forwarding, the transition probability of multiple routing paths is determined based on the pheromone concentration between routing devices, and a target routing path is determined from the multiple routing paths based on the transition probability; the packets are then forwarded through the routing devices according to the target routing path.

[0109] In some examples, the pheromone concentration table is a numerical table maintained by each routing device to record the historical communication success experience of the routing device to its neighboring routing devices. The higher the pheromone concentration, the better the past performance of the path.

[0110] In practical applications, each routing device can be configured with a pheromone concentration table. When a data packet needs to be forwarded, the routing device can query its own pheromone concentration table and calculate the transition probability of multiple routing paths based on the pheromone concentration values ​​recorded in the table, combined with an improved ant colony optimization algorithm.

[0111] After determining the transition probability, the route with the highest transition probability among multiple routes can be selected as the target route, in order of the calculated transition probability values.

[0112] For example, if there are three routing paths A, B, and C, with corresponding transition probabilities of 0.5, 0.3, and 0.2 respectively, routing path A can be chosen as the target routing path. After determining the target routing path, the routing device can forward data packets according to the target routing path, accurately sending the data packets to the next routing device until the data packets reach their final destination.

[0113] In some examples, routing devices can establish a self-organizing mesh network based on the Thread protocol according to the target network topology. The routing protocol employs an improved on-demand distance vector routing mechanism. Multiple routing paths can be determined based on the target network topology, which may include multiple communication links between routing devices.

[0114] The routing device can also detect network topology changes in real time through periodic Hello message exchange and bidirectional link quality assessment, so as to trigger route recalculation in a timely manner when the device moves, fails, or the signal changes, thus maintaining smooth communication.

[0115] In some embodiments of the present invention, determining the transition probability of multiple routing paths based on the pheromone concentration between routing devices includes: determining the transition probability of multiple routing paths based on link quality, path load, remaining energy of devices, and pheromone concentration between routing devices.

[0116] As examples, the link quality, path load, and remaining energy of multiple routing paths between routing devices can be collected, and the transition probability of multiple routing paths can be calculated by combining the pheromone concentration between routing devices.

[0117] In some examples, self-organizing mesh networks can be extended based on the AODV protocol (Self-Organizing On-Demand Distance Vector Routing Protocol) framework, combining link quality, path load, device remaining energy, and pheromone concentration between routing devices to determine the quality of routing paths and then select the optimal path (i.e., the target routing path).

[0118] For example, the target routing path can be selected using an ant colony optimization algorithm. Each routing device maintains a pheromone concentration table. Ant packets (probe packets) are sent from the source node (i.e., the first routing device) and the next hop is selected based on the transition probability.

[0119] In this context, "ant packets" refer to a special type of route probing data packet. When a routing device needs to find a new route to a target routing device, it can send out one or more probing packets. Like ants, these probing packets crawl randomly in the network (i.e., choose the next hop) and record path information and link quality along the way. After finally reaching the target routing device, the path information traversed by this "ant" is fed back to update the network state (pheromone concentration).

[0120] The pheromone concentration update can include local updates and global updates. Local updates are performed immediately when the data packet passes through the path, while global updates are evaluated based on end-to-end performance after the path is successfully established.

[0121] In this embodiment of the invention, network status data of the smart home network is acquired through a home host device; the network status data is then sent to a cloud platform, which determines a target network topology scheme from multiple network topology schemes based on the network status data; the home host device receives the target network topology scheme sent by the cloud platform and adjusts the connection relationships between smart home devices according to the target network topology scheme. This achieves the generation of a network topology scheme by acquiring network status data, enabling real-time perception of environmental changes, solving the problem of network topology lag, and dynamically adjusting the connection relationships between devices through the network topology scheme to avoid network paralysis caused by communication path failures, thereby improving the high reliability and adaptability requirements of smart home scenarios.

[0122] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0123] Reference Figure 4 The diagram illustrates a structural schematic of a smart home network optimization device according to some embodiments of the present invention, which may specifically include the following modules: The network status data acquisition module 401 is used to acquire network status data of the smart home network through the home host device; The target network topology scheme determination module 402 is used to send the network status data to the cloud platform through the home host device, so that the cloud platform can determine the target network topology scheme from multiple network topology schemes based on the network status data; The connection relationship adjustment module 403 is used to receive the target network topology scheme sent by the cloud platform through the home host device, and adjust the connection relationship between the smart home devices according to the target network topology scheme.

[0124] In some embodiments of the present invention, the smart home device includes a routing device, each routing device being equipped with a pheromone concentration meter, and the device further includes: The target routing path determination module is used to determine the transition probability of multiple routing paths based on the pheromone concentration between routing devices during packet forwarding, and to determine the target routing path from the multiple routing paths based on the transition probability. The packet forwarding module is used to forward packets according to the target routing path through the routing device.

[0125] In some embodiments of the present invention, the target routing path determination module includes: The transition probability determination submodule is used to determine the transition probability of multiple routing paths based on link quality, path load, remaining energy of devices, and pheromone concentration between routing devices.

[0126] In some embodiments of the present invention, the target network topology scheme determination module 402 includes: The network topology scheme evaluation submodule is used to evaluate multiple network topology schemes based on the network status data, and to determine the target network topology scheme from the multiple network topology schemes based on the evaluation results.

[0127] In some embodiments of the present invention, the network topology scheme evaluation submodule includes: An undirected graph creation unit is used to create an undirected graph; wherein the undirected graph includes a vertex set, an edge set, and a weight matrix, wherein the vertices in the vertex set correspond to the smart home devices, the edges in the edge set correspond to the communication links between the smart home devices, and each edge in the edge set has a set of weight values ​​in the weight matrix, wherein each weight value in the set of weight values ​​corresponds to an evaluation score of an optimization objective, and the evaluation score is determined based on the network state data; The target connected subgraph determination unit is used to determine multiple connected subgraphs based on the vertex set and edge set of the undirected graph, and to determine the target connected subgraph from the multiple connected subgraphs based on the weight matrix of the undirected graph; wherein each connected subgraph corresponds to a network topology scheme. The target network topology scheme generation unit is used to generate a target network topology scheme based on the target connected subgraph.

[0128] In some embodiments of the present invention, the optimization objectives include any one or more of the following: communication latency cost, energy consumption cost, reliability cost, and load balancing cost.

[0129] In some embodiments of the present invention, the network status data includes any one or more of the following: link quality indicators, device load status, network performance data, and device energy consumption level.

[0130] In this embodiment of the invention, network status data of the smart home network is acquired through a home host device; the network status data is then sent to a cloud platform, which determines a target network topology scheme from multiple network topology schemes based on the network status data; the home host device receives the target network topology scheme sent by the cloud platform and adjusts the connection relationships between smart home devices according to the target network topology scheme. This achieves the generation of a network topology scheme by acquiring network status data, enabling real-time perception of environmental changes, solving the problem of network topology lag, and dynamically adjusting the connection relationships between devices through the network topology scheme to avoid network paralysis caused by communication path failures, thereby improving the high reliability and adaptability requirements of smart home scenarios.

[0131] Some embodiments of the present invention also provide a home host device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the method described above.

[0132] Some embodiments of the present invention also provide a computer-readable storage medium on which a computer program is stored, and which, when executed by a processor, implements the method described above.

[0133] Some embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the method described above.

[0134] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0135] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0136] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0137] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented 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.

[0138] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. 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 terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0139] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate 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.

[0140] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal 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.

[0141] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0142] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes the aforementioned element.

[0143] The above provides a detailed description of the method, apparatus, device, medium, and product for optimizing a smart home network. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for optimizing a smart home network, characterized in that, The smart home network is equipped with a home host device and smart home devices, and the method includes: The home host device acquires network status data of the smart home network. The network status data is sent to the cloud platform through the home host device, so that the cloud platform can determine the target network topology scheme from multiple network topology schemes based on the network status data; The home host device receives the target network topology scheme sent by the cloud platform and adjusts the connection relationship between the smart home devices according to the target network topology scheme.

2. The method according to claim 1, characterized in that, The smart home devices include routing devices, each equipped with a pheromone concentration table. After adjusting the connectivity between the smart home devices according to the target network topology scheme, the system further includes: During packet forwarding, the transition probability of multiple routing paths is determined based on the pheromone concentration between routing devices, and the target routing path is determined from the multiple routing paths based on the transition probability. The routing device forwards data packets according to the target routing path.

3. The method according to claim 2, characterized in that, Based on the pheromone concentration between routing devices, the transition probability of multiple routing paths is determined, including: The transition probability of multiple routing paths is determined based on link quality, path load, remaining energy of devices, and pheromone concentration between routing devices.

4. The method according to any one of claims 1-3, characterized in that, Based on the network status data, a target network topology scheme is determined from multiple network topology schemes, including: Based on the network status data, multiple network topology schemes are evaluated, and based on the evaluation results, a target network topology scheme is determined from the multiple network topology schemes.

5. The method according to claim 4, characterized in that, Based on the network status data, multiple network topology schemes are evaluated, and based on the evaluation results, a target network topology scheme is determined from the multiple network topology schemes, including: Create an undirected graph; wherein the undirected graph includes a vertex set, an edge set, and a weight matrix, wherein the vertices in the vertex set correspond to the smart home devices, the edges in the edge set correspond to the communication links between the smart home devices, and each edge in the edge set has a set of weight values ​​in the weight matrix, wherein each weight value in the set of weight values ​​corresponds to an evaluation score of an optimization objective, and the evaluation score is determined based on the network state data; Based on the vertex set and edge set of the undirected graph, multiple connected subgraphs are determined, and based on the weight matrix of the undirected graph, a target connected subgraph is determined from the multiple connected subgraphs; wherein, each connected subgraph corresponds to a network topology scheme; Based on the target connected subgraph, a target network topology scheme is generated.

6. The method according to claim 5, characterized in that, The optimization objectives include any one or more of the following: communication latency cost, energy consumption cost, reliability cost, and load balancing cost.

7. The method according to claim 1, characterized in that, The network status data includes any one or more of the following: link quality indicators, device load status, network performance data, and device energy consumption level.

8. A device for optimizing a smart home network, characterized in that, The smart home network is equipped with a home host device and smart home devices, the device including: The network status data acquisition module is used to acquire network status data of the smart home network through the home host device; The target network topology scheme determination module is used to send the network status data to the cloud platform through the home host device, so that the cloud platform can determine the target network topology scheme from multiple network topology schemes based on the network status data; The connection relationship adjustment module is used to receive the target network topology scheme sent by the cloud platform through the home host device, and adjust the connection relationship between the smart home devices according to the target network topology scheme.

9. A home console device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the method as described in any one of claims 1 to 7.

11. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 7.

Images