Wireless internet of things networking method based on satellite flash technology

Abstract

The invention relates to the technical field of wireless Internet of Things, and provides a wireless Internet of Things networking method based on a star flash technology, which comprises the following steps of: acquiring a network topology structure set of a target Internet of Things area through a star flash networking control device, and coding Internet of Things equipment to be accessed to generate an identification group; performing signal coverage optimization on the network topological structure set to generate an optimization set, and splicing to form a regional network topological graph; generating an original network area model by combining a pre-trained network information generation model; obtaining model information of the Internet of Things equipment, and filling the original model in combination with the code identification group to obtain a target network area model; after networking equipment is controlled to complete networking based on the model, target network data are collected and connection verification is carried out, and closed-loop management is realized by marking equipment which does not pass the verification. According to the invention, the networking efficiency can be improved, the signal coverage is enhanced, and the reliability of equipment connection is ensured.

Description

Technical Field

[0001] The present invention relates to the field of wireless Internet of Things technology, and more specifically, to a wireless Internet of Things networking method based on Star Flash technology. Background Art

[0002] With the rapid development of the Internet of Things (IoT), wireless IoT networking has gained widespread application in fields such as smart homes, smart cities, and industrial automation. While traditional wireless IoT networking technologies, such as Wi-Fi and Bluetooth, have met the communication needs between devices to a certain extent, they have gradually exposed numerous issues when networking IoT devices in large-scale, complex environments. For example, Wi-Fi is prone to signal congestion when connecting multiple devices, resulting in increased transmission latency; Bluetooth has a limited transmission range and a restricted number of connected devices. Most of these technologies utilize star or mesh topologies. While these technologies can connect devices in simple scenarios, in complex IoT environments, the network topology lacks flexibility and is difficult to dynamically adjust based on device distribution and communication needs, thus impacting the overall performance and stability of the IoT system.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the existing technology: when large-scale devices are connected, the network topology structure of the existing wireless Internet of Things networking technology is fixed, and it is impossible to dynamically optimize according to the actual distribution and communication needs of the devices, resulting in blind spots in signal coverage and low communication efficiency between devices; at the same time, the device connection verification after the networking is completed is not perfect, and problems in the device connection cannot be discovered and resolved in time, affecting the reliability and stability of the Internet of Things system. Summary of the Invention

[0004] The present invention provides a wireless Internet of Things networking method based on Star Flash technology, comprising:

[0005] Collect network deployment data of the target IoT area through the Star Flash networking control device, wherein the network deployment data includes: a network topology structure set corresponding to the target IoT area;

[0006] Performing encoding processing on each IoT device to be connected in the target IoT area to generate an IoT device encoding identifier, thereby obtaining an IoT device encoding identifier group;

[0007] Generate an optimized network topology structure set through the network topology structure set, wherein the optimized network topology structure is a structure obtained by optimizing signal coverage of multiple network topologies;

[0008] Performing network splicing on each optimized network topology structure in the optimized network topology structure set to obtain a regional network topology map;

[0009] Generate an original network area model corresponding to the target IoT area based on the regional network topology map and the pre-trained network information generation model;

[0010] Obtaining IoT device model information corresponding to each IoT device code identifier in the IoT device code identifier group to obtain an IoT device model information group, wherein the IoT device model information includes: IoT device model, access location information, and communication parameter information;

[0011] Fill the original network area model according to the IoT device model information group and the IoT device code identification group to obtain the target network area model;

[0012] According to the target network area model, control the associated networking devices to perform networking processing on each IoT device to be connected;

[0013] In response to determining that the networking of each IoT device is completed, the Star Flash networking control device is controlled to collect the network deployment data of the target IoT area after the networking is completed as the target network data, and based on the target network data, the connection of each IoT device that has completed the networking is verified.

[0014] Furthermore, based on the regional network topology map and the pre-trained network information generation model, an original network regional model corresponding to the target IoT region is generated, including:

[0015] Generate an initial network area model and network area model information based on the regional network topology map and the network information generation model, wherein the network area model information includes: a network area model element information set, the network area model element information includes: a network element type, a network element feature vector, and network element position information, the network element position information representing the position of the network area model element corresponding to the network area model element information in the initial network area model;

[0016] For each network area model element information in the network area model element information set, the following processing steps are performed: determining whether there is a network area model element matching the network area model element information in a preset network area model element library based on the network element type and the network element feature vector included in the network area model element information;

[0017] In response to a matching network area model element existing in the network area model element library, determining the network area model element matching the network area model element information as a candidate network area model element;

[0018] The initial network area model is updated according to each candidate network area model element to generate an updated initial network area model as the original network area model.

[0019] Furthermore, an initial network regional model and network regional model information are generated based on the regional network topology map and the network information generation model, including:

[0020] Generate a topology map encoding feature corresponding to the regional network topology map based on an encoder included in the network information generation model;

[0021] Generate a topology map decoding feature corresponding to the topology map encoding feature through a decoder included in the network information generation model;

[0022] Generate a topology map extraction feature corresponding to the topology map decoding feature through a feature extraction model included in the network information generation model;

[0023] Generate adjustment parameters corresponding to the regional network topology map by adjusting the network using the threshold value included in the network information generation model;

[0024] By adjusting parameters and extracting features from the topology map, an initial network area model and network area model information are generated.

[0025] Furthermore, the original network area model is filled according to the IoT device model information group and the IoT device code identification group to obtain the target network area model, including:

[0026] For each piece of IoT device model information in the IoT device model information group, the following filling steps are performed: the IoT device model included in the IoT device model information is filled into the access position of the corresponding access position information in the original network area model;

[0027] Determine the IoT device coding identifier corresponding to the IoT device model information as the target IoT device coding identifier;

[0028] Marking the target IoT device code identifier on the IoT device model of the corresponding IoT device model information in the original network area model;

[0029] The filled original network area model is determined as the target network area model.

[0030] Furthermore, an optimized network topology set is generated through the network topology set, including:

[0031] For each network topology structure in the network topology structure set, the following optimization steps are performed: calculating the signal coverage parameters of the network topology structure, wherein the signal coverage parameters include a signal strength distribution value and a signal coverage blind area value; adjusting the network topology structure parameters of the network topology structure according to the signal coverage parameters, wherein the network topology structure parameters include a node distribution density value and an inter-node connection weight value; determining the network topology structure corresponding to the adjusted network topology structure parameters as the optimized network topology structure; and combining the various optimized network topologies into an optimized network topology structure set.

[0032] Furthermore, each optimized network topology structure in the optimized network topology structure set is spliced to obtain a regional network topology diagram, including:

[0033] Obtain the network topology node set and network topology edge set of each optimized network topology structure; determine the node overlap area between each optimized network topology structure according to the position coordinates of each network topology node set; perform node matching processing on the network topology node set of each optimized network topology structure according to the node overlap area to obtain a matching node pair set; perform edge fusion processing on the network topology edge set of each optimized network topology structure according to the matching node pair set to generate a spliced edge set; generate a regional network topology graph according to the matching node pair set and the spliced edge set.

[0034] Furthermore, after the IoT device model included in the IoT device model information is filled into the access location of the corresponding access location information in the original network area model, the method further includes:

[0035] Obtain communication parameter information from IoT device model information;

[0036] Adjust the communication parameters of the IoT device model corresponding to the original network area model according to the communication parameter information, wherein the communication parameters include transmission power parameters and communication frequency band parameters;

[0037] The IoT device model corresponding to the adjusted communication parameters is updated to the original network area model.

[0038] Furthermore, based on the target network data, the connection verification is performed on each IoT device that has been networked, including:

[0039] Determine the connection verification parameters of each IoT device based on the target network data, where the connection verification parameters include signal transmission delay value and data transmission success rate value;

[0040] Determine whether the connection verification parameters meet the preset connection verification conditions;

[0041] In response to the connection verification parameter satisfying the preset connection verification condition, determining that the corresponding IoT device passes the connection verification;

[0042] In response to the connection verification parameter not satisfying the preset connection verification condition, the IoT device that failed the connection verification is marked in the target network area model.

[0043] Furthermore, the encoder included in the network information generation model generates a topology map encoding feature corresponding to the regional network topology map, including:

[0044] Converting the regional network topology map into a topology matrix;

[0045] The topology map matrix is convolutionally encoded by the encoder to generate topology map convolution features;

[0046] The topology map convolution features are fully connected and encoded to generate topology map encoding features.

[0047] Further, determining whether there is a network area model element matching the network area model element information in a preset network area model element library includes:

[0048] Calculating a similarity value between a network element feature vector in the network area model element information and a feature vector of each network area model element in the network area model element library;

[0049] Determine whether the similarity value exceeds a preset similarity threshold;

[0050] In response to a similarity value exceeding a preset similarity threshold, it is determined that a network area model element matching the network area model element information exists in the network area model element library.

[0051] The above embodiments of the present invention have at least the following beneficial effects:

[0052] 1. The Star Flash networking control device can collect the network topology set of the target IoT area in real time, and use the signal coverage optimization algorithm to dynamically adjust the network topology structure, optimize the node distribution density and connection weight parameters, effectively solve the problems of uneven signal strength distribution and coverage blind spots in traditional wireless networking, and significantly improve the integrity and stability of network coverage.

[0053] 2. It can automatically build the initial network area model based on the pre-trained network information generation model, and realize the precise access of IoT devices and the automatic allocation of network resources through the intelligent matching of IoT device coding identification groups and device model information, greatly reducing the workload and error rate of manual configuration and improving networking efficiency and accuracy.

[0054] 3. After networking is completed, the target network data can be collected to perform multi-dimensional connection verification on each IoT device, including signal transmission delay detection and data transmission success rate analysis, and automatically identify and mark devices that fail the verification, effectively solving the problem of difficult fault location in traditional networking methods and ensuring the long-term stable operation of the entire IoT network. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily apparent by reading the following detailed description with reference to the accompanying drawings, in which several embodiments of the present invention are shown by way of example and not limitation, in which:

[0056] Figure 1 A flow chart of a wireless IoT networking method based on Star Flash technology provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0057] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided solely to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. Rather, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0058] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present invention may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software.

[0059] It should be noted that any number of elements in the drawings is for illustration only and not for limitation, and any naming is only for distinction and does not have any limiting meaning.

[0060] Reference below Figure 1 , Figure 1 This is a flow chart of a wireless IoT networking method based on Star Flash technology provided by an embodiment of the present invention. Figure 1 As shown, a wireless IoT networking method based on Star Flash technology includes:

[0061] S1. Collect network deployment data of a target IoT area through a Star Flash networking control device, wherein the network deployment data includes: a network topology structure set corresponding to the target IoT area;

[0062] S2. Encode each IoT device to be connected in the target IoT area to generate an IoT device code identifier, thereby obtaining an IoT device code identifier group;

[0063] S3. Generate an optimized network topology set based on the network topology set, where the optimized network topology is a structure obtained by optimizing signal coverage for multiple network topologies;

[0064] S4, performing network splicing on each optimized network topology structure in the optimized network topology structure set to obtain a regional network topology map;

[0065] S5. Generate an original network area model corresponding to the target IoT area based on the regional network topology map and the pre-trained network information generation model;

[0066] S6. Obtaining IoT device model information corresponding to each IoT device code identifier in the IoT device code identifier group to obtain an IoT device model information group, wherein the IoT device model information includes: IoT device model, access location information, and communication parameter information;

[0067] S7. Fill the original network area model according to the IoT device model information group and the IoT device code identification group to obtain the target network area model;

[0068] S8. Control the associated networking devices to perform networking processing on each IoT device to be connected according to the target network area model;

[0069] S9. In response to determining that the networking of each IoT device is completed, control the Star Flash networking control device to collect the network deployment data of the target IoT area after the networking is completed as the target network data, and perform connection verification on each IoT device that has completed the networking based on the target network data.

[0070] It should be noted that the present invention collects the network deployment data of the target IoT area through the Star Flash networking control device, wherein the network deployment data includes the network topology structure set of the target IoT area. The Star Flash networking control device is a device for managing and controlling IoT networking, which can collect various information related to network deployment. The network topology structure set refers to the collection of all possible network topologies within the target IoT area. These structures describe the connection relationship and layout between devices in the network. Each IoT device to be connected in the target IoT area is coded to generate an IoT device coding identifier to obtain an IoT device coding identifier group. The IoT device coding identifier is a code for uniquely identifying each IoT device, which is used to distinguish different devices during the networking process. Through the network topology structure set, an optimized network topology structure set is generated. The optimized network topology structure refers to a structure after signal coverage optimization of multiple network topologies, with the aim of improving the signal coverage effect and communication efficiency of the network.

[0071] Specifically, each network topology in the network topology set describes the connectivity and layout between devices. For example, it can be a star topology, mesh topology, or hybrid topology. The IoT device identifier group contains the identifiers of all connected IoT devices. These identifiers can be numbers, letters, or a combination of these, and are used to uniquely identify each device. The optimized network topology set is derived from the original network topology set by using an algorithm to optimize signal coverage. The algorithm considers parameters such as signal strength distribution and signal coverage blind spot area to ensure that the optimized network topology better meets the communication needs of IoT devices. The optimized network topologies in the set are then spliced together to produce a regional network topology. Network splicing involves connecting multiple optimized network topologies to form a complete regional network topology. This process considers the connection points and methods between the various network topologies to ensure connectivity and stability across the entire regional network. Based on the regional network topology and a pre-trained network information generation model, an original network regional model corresponding to the target IoT area is generated. The network information generation model is a pre-trained model that can generate a corresponding network area model based on the input regional network topology map. The input parameters of the model include information such as the node location and connection relationship of the network topology structure. The output is the original network area model, which includes the basic structure of the network and the preliminary layout of the equipment.

[0072] Preferably, when generating the optimized network topology set, an optimization method based on a genetic algorithm can be employed. Genetic algorithms optimize network topologies by simulating the process of natural selection. First, a fitness function is defined, which uses the signal strength distribution value and the signal coverage blind area as parameters to evaluate the quality of the network topology. Then, a population is initialized, with each individual representing a network topology. Through continuous iterations such as crossover and mutation, the optimized network topology set is ultimately obtained. When generating the original network region model, the network information generation model can employ a generative adversarial network (GAN) from deep learning. A generator generates a network region model based on the regional network topology graph, and a discriminator evaluates the generated model. Through continuous training, the generator is able to produce network region models that are closer to actual requirements. The generator's input parameters include the node coordinates and connection weights of the network topology. The output is the original network region model, which includes network element types, feature vectors, and location information. When filling the original network area model, the IoT device model can be accurately placed at the corresponding position in the model according to the access location information in the IoT device model information, and the communication parameters of the device, such as transmission power and communication frequency band, can be adjusted according to the communication parameter information to ensure the communication performance of the device after networking.

[0073] In some embodiments, generating an original network area model corresponding to a target IoT area based on a regional network topology map and a pre-trained network information generation model includes:

[0074] Generate an initial network area model and network area model information based on the regional network topology map and the network information generation model, wherein the network area model information includes: a network area model element information set, the network area model element information includes: a network element type, a network element feature vector, and network element position information, the network element position information representing the position of the network area model element corresponding to the network area model element information in the initial network area model;

[0075] For each network area model element information in the network area model element information set, the following processing steps are performed: determining whether there is a network area model element matching the network area model element information in a preset network area model element library based on the network element type and the network element feature vector included in the network area model element information;

[0076] In response to a matching network area model element existing in the network area model element library, determining the network area model element matching the network area model element information as a candidate network area model element;

[0077] The initial network area model is updated according to each candidate network area model element to generate an updated initial network area model as the original network area model.

[0078] It should be noted that when the present invention generates the original network area model corresponding to the target IoT area, it is based on the regional network topology map and the pre-trained network information generation model. The regional network topology map is a graphic that describes the connection relationship and layout of network devices in the target IoT area, which intuitively reflects the structural characteristics of the network. The network information generation model is a trained model that can generate a corresponding network area model based on the input network topology information. The model contains the basic structure of the network and the preliminary layout information of the equipment. When the initial network area model and network area model information are generated, a network area model element information set will be obtained, wherein each network area model element information contains key data such as network element type, network element feature vector and network element location information. These data are used to describe each element and its attributes in the network area model. For each network area model element information in the network area model element information set, a matching process will be performed to determine whether there is a matching network area model element, thereby generating an original network area model.

[0079] Specifically, each network area model element in the network area model element information set can be a network element type, such as a router, sensor node, or gateway. These devices perform different functions within the network. A network element feature vector is a multidimensional vector that describes various attributes of a network element, such as the device's communication capabilities, processing power, and energy consumption. These parameters are quantified using feature vectors. Network element location information characterizes the specific location of the network element within the network area model and is typically represented by coordinate points in a coordinate system. For example, the device's location can be determined using (x, y) coordinates in a two-dimensional plane. The network area model element library is a pre-configured database that stores various possible network area model elements and their feature vectors. This is used for matching and selection during network area model generation. The matching process is performed by comparing the feature vectors in the network area model element information with the feature vectors of elements in the library. When a matching element is found, it is identified as a candidate network area model element. The initial network area model is then updated based on these candidate elements to generate the final original network area model.

[0080] Preferably, the network information generation model can be constructed using a deep neural network model based on machine learning. The model's input is a matrix representation of the regional network topology graph, where the rows and columns of the matrix correspond to the connections between nodes in the network, and the matrix element values represent information such as the connection weights or distances between nodes. The model training process involves learning from a large number of network topology samples. By adjusting the weights and bias parameters of the neural network, the model accurately generates network regional model information. When matching network regional model element information, cosine similarity can be used to calculate the similarity between feature vectors. Specifically, the cosine similarity is calculated by dividing the dot product of two feature vectors by the product of their moduli. The closer the resulting value is to 1, the more similar the two vectors are. When the similarity value exceeds a preset similarity threshold, a matching network regional model element is considered to have been found. Furthermore, to improve the accuracy and robustness of the model, regularization techniques such as L2 regularization can be introduced during training. By adding the sum of the squares of the weights as a penalty term in the loss function, the model can be prevented from overfitting, thereby improving the model's generalization ability in practical applications.

[0081] In some embodiments, generating an initial network area model and network area model information based on the regional network topology map and the network information generation model includes:

[0082] Generate a topology map encoding feature corresponding to the regional network topology map based on an encoder included in the network information generation model;

[0083] Generate a topology map decoding feature corresponding to the topology map encoding feature through a decoder included in the network information generation model;

[0084] Generate a topology map extraction feature corresponding to the topology map decoding feature through a feature extraction model included in the network information generation model;

[0085] Generate adjustment parameters corresponding to the regional network topology map by adjusting the network using the threshold value included in the network information generation model;

[0086] By adjusting parameters and extracting features from the topology map, an initial network area model and network area model information are generated.

[0087] It should be noted that the present invention utilizes the collaborative work of multiple components of the network information generation model to generate the initial network area model and network area model information. The network information generation model is a machine learning model that processes the regional network topology map through multiple modules, including an encoder, a decoder, a feature extraction model, and a threshold adjustment network, to generate the initial network area model and network area model information. The encoder converts the regional network topology map into a compact feature representation, namely the topology map encoding feature; the decoder decodes the encoding feature into a more easily processed form, namely the topology map decoding feature; the feature extraction model further extracts key information from the decoded feature to generate the topology map extraction feature; finally, the threshold adjustment network generates adjustment parameters based on these features, which are used to generate the initial network area model and network area model information. This process involves the collaborative work of multiple steps and modules to ensure that the generated model accurately reflects the network's topology and device information.

[0088] Specifically, the encoder portion of the network information generation model converts the regional network topology map into a topology matrix, then performs convolutional coding on this matrix to generate topology convolution features. Convolutional coding is a common image processing technique used to extract local features from images and is suitable for processing spatially structured data such as network topology maps. Fully connected encoding further compresses and encodes the convolution features to generate more compact topology encoding features. The decoder portion decodes the topology encoding features into topology decoding features. This process can be considered the inverse of the encoding process, aiming to restore the encoded features to a form closer to the original data while preserving the key information extracted during the encoding process. The feature extraction model further extracts key information from the decoded features to generate topology extraction features. These features more accurately describe the structure and properties of the network topology map. The threshold adjustment network generates adjustment parameters based on these features. These parameters are used to fine-tune the generated initial network regional model to better adapt to the actual network environment.

[0089] Preferably, the network information generation model can be constructed using a deep learning framework such as TensorFlow or PyTorch. The model input is a matrix representation of the regional network topology, where the rows and columns of the matrix correspond to the connections between nodes in the network, and the matrix elements represent information such as the connection weights or distances between nodes. In the encoder, a multi-layer convolutional neural network (CNN) can be used to extract local features of the topology. The convolution kernel size and step size of each convolutional network layer can be adjusted based on the size and complexity of the network topology. For example, for a complex network topology with a large number of nodes, a larger convolution kernel and a smaller step size can be used to extract more detailed features. The fully connected encoding process can be implemented using a multi-layer perceptron (MLP). By adjusting the number of MLP layers and the number of neurons in each layer, the dimensionality and complexity of the encoded features can be controlled. The decoder can use deconvolution operations to gradually restore the encoded features to a form close to the original data. The feature extraction model can use an attention mechanism to calculate the importance weights of features to extract the most critical components for describing the network topology. The threshold adjustment network dynamically generates adjustment parameters based on the extracted features. These parameters can include adjusting node weights and modifying connection strengths to optimize the generated initial network region model. During training, the mean squared error (MSE) is used as the loss function, and the model parameters are adjusted through the backpropagation algorithm to better fit the training data and generate an accurate network region model.

[0090] In some embodiments, the original network area model is filled according to the IoT device model information group and the IoT device code identification group to obtain the target network area model, including:

[0091] For each piece of IoT device model information in the IoT device model information group, the following filling steps are performed: the IoT device model included in the IoT device model information is filled into the access position of the corresponding access position information in the original network area model;

[0092] Determine the IoT device coding identifier corresponding to the IoT device model information as the target IoT device coding identifier;

[0093] Marking the target IoT device code identifier on the IoT device model of the corresponding IoT device model information in the original network area model;

[0094] The filled original network area model is determined as the target network area model.

[0095] It should be noted that when generating the target network area model, the present invention is achieved by filling the IoT device model information into the original network area model. The IoT device model information includes the IoT device model, access location information and communication parameter information, which are used to describe the characteristics of the IoT device and its location and communication capabilities in the network. Specifically, the IoT device model refers to the function and structure description of the IoT device, the access location information indicates the specific location of the IoT device in the network, and the communication parameter information involves the communication capabilities of the device, such as transmission power and communication frequency band. By filling this information into the original network area model, a more specific and detailed network area model, namely the target network area model, can be generated. This process ensures that the network area model can accurately reflect the actual layout and communication characteristics of the IoT device.

[0096] Specifically, each IoT device model information in the IoT device model information group includes the IoT device model, access location information, and communication parameter information. IoT device models can be models of different types of devices, such as sensors, actuators, and gateways, each with specific functions and interfaces. Access location information is typically a coordinate value that indicates the device's specific location within the network. For example, the device's location can be represented by (x, y) coordinates on a two-dimensional plane. Communication parameter information includes parameters such as transmission power and communication frequency band, which determine the device's communication capabilities and range. During the population process, the IoT device model is first placed at the corresponding access location in the original network area model. Then, the IoT device code identifier corresponding to the IoT device model information is determined and marked on the model. Finally, the populated model is determined as the target network area model. This process involves parsing and processing the IoT device model information, as well as updating and marking the original network area model.

[0097] Preferably, the process for populating IoT device model information can be further refined. First, a template-based matching approach can be used to populate the IoT device model. A set of templates are predefined based on the type and function of the IoT device model, with each template corresponding to a device type. During the populating process, the corresponding template is selected based on the device type in the IoT device model information and placed at the corresponding access location in the original network area model. Access location information can be processed through coordinate transformation to ensure the device model is placed in the correct location. Regarding the processing of communication parameter information, the communication capabilities of the device model can be adjusted based on the type and range of the communication parameters. For example, the transmission power parameter can be adjusted based on the actual needs of the device to ensure that the device can communicate within the required range. Adjustment of communication frequency band parameters requires consideration of the device's communication protocol and frequency band allocation to ensure that the device can communicate on the appropriate frequency band. Furthermore, to improve the accuracy and efficiency of the populating process, automated tools, such as scripting languages or graphical interface tools, can be introduced to quickly parse the IoT device model information and populate it into the original network area model.

[0098] In some embodiments, generating an optimized network topology set from the network topology set includes:

[0099] For each network topology structure in the network topology structure set, the following optimization steps are performed: calculating the signal coverage parameters of the network topology structure, wherein the signal coverage parameters include a signal strength distribution value and a signal coverage blind area value; adjusting the network topology structure parameters of the network topology structure according to the signal coverage parameters, wherein the network topology structure parameters include a node distribution density value and an inter-node connection weight value; determining the network topology structure corresponding to the adjusted network topology structure parameters as the optimized network topology structure; and combining the various optimized network topologies into an optimized network topology structure set.

[0100] It should be noted that when generating the optimized network topology set, the present invention performs a series of optimization steps for each network topology in the network topology set. These steps include calculating signal coverage parameters, adjusting network topology parameters, and finally determining the optimized network topology. Signal coverage parameters are used to evaluate the signal coverage effect of the network topology, including signal strength distribution values and signal coverage blind area values. Network topology parameters describe the characteristics of the network topology, such as node distribution density values and inter-node connection weight values. By adjusting these parameters, the network topology can be optimized to better adapt to the signal coverage requirements of the target IoT area, thereby improving the overall performance and reliability of the network.

[0101] Specifically, the signal strength distribution value within the signal coverage parameter refers to the distribution of signal strength at various locations within the network topology. This value can typically be represented as a two-dimensional array, with each element in the array corresponding to a location in the network, and its value representing the signal strength at that location. The signal coverage blind spot area value refers to the total area of regions within the network where signal strength falls below a certain threshold. A smaller value indicates better signal coverage. The node density value within the network topology parameter refers to the number of nodes per unit area, which influences signal propagation and coverage. The inter-node connection weight value represents the connection strength or communication cost between nodes, typically related to the distance between nodes and communication quality. During the optimization process, the signal coverage parameters for each network topology are first calculated. The network topology parameters are then adjusted based on these parameters. For example, increasing the node density value can reduce the signal coverage blind spot area value, or adjusting the inter-node connection weight value to optimize the signal propagation path. The network topology corresponding to the adjusted network topology parameters is determined as the optimized network topology, and these optimized structures are combined into an optimized network topology set.

[0102] Preferably, a calculation method based on a physical model can be used when calculating signal coverage parameters. For example, the signal strength distribution value can be calculated by simulating the signal propagation process in space, taking into account factors such as signal attenuation, reflection, and refraction. The specific steps include: first, calculating the signal coverage range of each node based on the node location and transmit power in the network topology; then, by superimposing the signal coverage ranges of each node, a signal strength distribution map for the entire network is obtained. The signal coverage blind area value can be determined by analyzing the signal strength distribution map, identifying areas where the signal strength is below a threshold, and calculating the total area of these areas. When adjusting network topology parameters, an optimization algorithm based on a genetic algorithm or simulated annealing algorithm can be used. Taking the genetic algorithm as an example, a fitness function is first defined. This function takes the signal coverage parameters as input and outputs the quality of the network topology. Then, a population is initialized, with each individual representing a configuration of the network topology parameters. Through selection, crossover, and mutation operations, the population is gradually optimized, ultimately obtaining the optimal network topology parameter configuration. These parameter configurations may include the specific location of the node, the transmission power of the node, etc. By adjusting these parameters, the signal coverage blind area value can be effectively reduced and the uniformity of signal strength distribution can be improved.

[0103] In some embodiments, network splicing is performed on each optimized network topology structure in the optimized network topology structure set to obtain a regional network topology map, including:

[0104] Obtain the network topology node set and network topology edge set of each optimized network topology structure; determine the node overlap area between each optimized network topology structure according to the position coordinates of each network topology node set; perform node matching processing on the network topology node set of each optimized network topology structure according to the node overlap area to obtain a matching node pair set; perform edge fusion processing on the network topology edge set of each optimized network topology structure according to the matching node pair set to generate a spliced edge set; generate a regional network topology graph according to the matching node pair set and the spliced edge set.

[0105] It should be noted that the main purpose of the present invention when performing network splicing on each optimized network topology structure in the optimized network topology structure set is to generate a complete regional network topology map. This process involves obtaining the node set and edge set of each optimized network topology structure, determining the node overlap area, and performing node matching and edge fusion processing. The node set refers to the set of all nodes in the network, and the edge set refers to the set of connection relationships between nodes. The node overlap area refers to the node area with the same position between different optimized network topologies, and these areas are the key parts of splicing. Through node matching and edge fusion processing, multiple optimized network topologies can be connected into a complete regional network topology map, thereby achieving network coverage of the entire target IoT area.

[0106] Specifically, each node in a network topology node set has its own location coordinates, which are used to determine the node's specific position in network space. Each edge in a network topology edge set represents the connection between two nodes and is typically represented by a node pair. For example, (node A, node B) indicates the existence of an edge between nodes A and B. Node overlap regions are determined by comparing the location coordinates of nodes in different optimized network topologies. When two or more nodes have the same location coordinates, these nodes constitute a node overlap region. Node matching involves matching nodes with identical locations in different optimized network topologies to generate a set of matching node pairs. Edge fusion involves merging edges from different optimized network topologies based on the set of matching node pairs to generate a set of spliced edges. Each edge in the spliced edge set represents the connection between the fused nodes. Ultimately, a regional network topology map is generated based on the set of matching node pairs and the spliced edge set.

[0107] Preferably, a spatial partitioning-based approach can be employed to determine node overlap regions. First, the target IoT area is divided into multiple small grid cells, each with a unique identifier and coordinate range. The node location coordinates in each optimized network topology are then mapped to these grid cells. By checking whether the nodes in different optimized network topologies are mapped to the same grid cells, the node overlap region is determined. This approach can improve the efficiency and accuracy of determining node overlap regions. During the node matching process, each matching node pair can be assigned a matching weight. This weight can be calculated based on factors such as node type and communication capabilities to reflect the similarity and matching degree between the nodes. During the edge fusion process, multiple edges connecting the same pair of matching nodes can be weighted averaged based on edge weights, such as communication quality and transmission delay, to generate new splicing edges, thereby optimizing the connectivity of the entire regional network topology. Furthermore, to ensure the connectivity and stability of the generated regional network topology, a connectivity check mechanism can be introduced during the splicing process. This uses graph theory algorithms, such as depth-first search or breadth-first search, to verify network connectivity and adjust the splicing strategy if necessary.

[0108] In some embodiments, after filling the IoT device model included in the IoT device model information into the access location of the corresponding access location information in the original network area model, the method further includes:

[0109] Obtain communication parameter information from IoT device model information;

[0110] Adjust the communication parameters of the IoT device model corresponding to the original network area model according to the communication parameter information, wherein the communication parameters include transmission power parameters and communication frequency band parameters;

[0111] The IoT device model corresponding to the adjusted communication parameters is updated to the original network area model.

[0112] It should be noted that after the IoT device model in the IoT device model information is populated into the corresponding access location in the original network area model, the present invention further obtains the communication parameter information in the IoT device model information and adjusts the communication parameters of the corresponding IoT device model in the original network area model based on this communication parameter information. The purpose of this process is to ensure that the communication performance of the IoT device is optimized after networking. The communication parameter information includes transmission power parameters and communication frequency band parameters, which directly affect the communication quality and coverage range between devices. By adjusting these parameters, the communication capabilities of the devices can be optimized, improving the performance and stability of the entire IoT system.

[0113] Specifically, the transmission power parameter in the communication parameter information refers to the power level of the signal transmitted by the IoT device during communication. This parameter determines the signal propagation distance and strength. Higher transmission power can increase signal coverage, but may also result in increased energy consumption. The communication frequency band parameter refers to the wireless frequency band used by the IoT device. Different frequency bands have different propagation characteristics and interference resistance. For example, signals in lower frequency bands have longer propagation distances but narrower bandwidths, while signals in higher frequency bands have wider bandwidths but shorter propagation distances and are more susceptible to interference. When adjusting communication parameters, these parameters should be set based on the specific application scenarios and performance requirements of the IoT device. For example, in scenarios requiring long-distance communication, the transmission power can be appropriately increased; in scenarios requiring high data rates, a higher frequency band can be selected. Furthermore, when adjusting communication parameters, it is necessary to consider inter-device compatibility and overall network performance to ensure that all devices can operate together under optimized communication conditions.

[0114] Preferably, a dynamic adjustment method based on performance evaluation can be employed when adjusting communication parameters. First, a set of performance metrics, such as signal transmission delay, data transmission success rate, and energy consumption, are defined to evaluate the communication performance of IoT devices under the current communication parameters. Then, through simulations or actual testing, performance data is collected from devices under different communication parameter configurations. Based on this data, a performance evaluation model is developed that can predict device performance under different communication parameter configurations. In practice, the communication parameters of IoT devices are dynamically adjusted based on the predictions of the performance evaluation model to achieve optimal communication performance. For example, if a device's signal transmission delay is high, its transmission power can be appropriately increased; if interference in a particular frequency band is significant, a different frequency band can be switched. Furthermore, to improve the efficiency and accuracy of these adjustments, machine learning algorithms, such as reinforcement learning, can be introduced to automatically adjust communication parameters through continuous learning and optimization to adapt to complex IoT environments.

[0115] In some embodiments, a connection check is performed on each IoT device that has been networked based on the target network data, including:

[0116] Determine the connection verification parameters of each IoT device based on the target network data, where the connection verification parameters include signal transmission delay value and data transmission success rate value;

[0117] Determine whether the connection verification parameters meet the preset connection verification conditions;

[0118] In response to the connection verification parameter satisfying the preset connection verification condition, determining that the corresponding IoT device passes the connection verification;

[0119] In response to the connection verification parameter not satisfying the preset connection verification condition, the IoT device that failed the connection verification is marked in the target network area model.

[0120] It should be noted that when the present invention performs connection verification on each IoT device that has completed networking, it mainly determines the connection verification parameters of each IoT device based on the target network data, and judges whether the device has passed the verification based on these parameters. The connection verification parameters include the signal transmission delay value and the data transmission success rate value. These parameters are used to evaluate the communication performance of the IoT device after networking. The signal transmission delay value reflects the time required for the signal to travel from the sending end to the receiving end, while the data transmission success rate value indicates the proportion of data that successfully reaches the receiving end during the transmission process. Through these parameters, the connection quality between IoT devices can be effectively evaluated to ensure the stability and reliability of the network.

[0121] Specifically, the signal transmission delay value refers to the time required for a signal to be sent from one IoT device to another and received, usually in milliseconds (ms). The data transmission success rate value refers to the ratio of the number of successfully transmitted data packets to the total number of transmitted data packets within a certain period of time, usually expressed as a percentage. During the connection verification process, the connection verification parameters of each IoT device are first calculated based on the target network data. The preset connection verification conditions are thresholds set according to actual application requirements. For example, the signal transmission delay value should not exceed a certain set maximum delay value, and the data transmission success rate value should not be lower than a certain set minimum success rate value. If the connection verification parameters of an IoT device meet these preset conditions, the device is considered to have passed the connection verification; otherwise, the device fails the verification and is marked in the target network area model for subsequent troubleshooting and repair.

[0122] Preferably, when calculating the signal transmission delay value, a timestamp-based method can be used. At the sending end, a timestamp is added to each sent data packet to record the sending time of the data packet; at the receiving end, the time of the received data packet is recorded, and the difference with the sending timestamp is calculated to obtain the signal transmission delay value. In order to improve the accuracy of the measurement, multiple measurements can be made and the average value is taken. When evaluating the success rate of data transmission, a series of data packets can be sent within a certain period of time, and the number of successfully received data packets can be counted to calculate the success rate. In addition, in order to more comprehensively evaluate the connection quality of IoT devices, other parameters such as signal strength and packet loss rate can be introduced. When marking IoT devices that have not passed the connection check in the target network area model, different colors or symbols can be used to distinguish the status of the devices, for example, red is used to mark devices that have not passed the check, and green is used to mark devices that have passed the check. This can intuitively display the connection status of devices in the network, making it easier for network administrators to manage and maintain.

[0123] In some embodiments, generating a topology map encoding feature corresponding to a regional network topology map by an encoder included in a network information generation model includes:

[0124] Converting the regional network topology map into a topology matrix;

[0125] The topology map matrix is convolutionally encoded by the encoder to generate topology map convolution features;

[0126] The topology map convolution features are fully connected and encoded to generate topology map encoding features.

[0127] It should be noted that when the present invention generates the topology encoding features corresponding to the regional network topology through the encoder of the network information generation model, it mainly involves converting the regional network topology into a topology matrix and performing convolution coding and full connection coding on the matrix. The purpose of this process is to convert the complex network topology structure into a compact feature representation for subsequent processing and analysis. The topology matrix is a mathematical representation used to describe the connection relationship between nodes in the network, while convolution coding and full connection coding are feature extraction methods commonly used in deep learning. These methods can be used to extract the key features of the network topology, providing a basis for generating the initial network regional model and network regional model information.

[0128] Specifically, the topology matrix is a two-dimensional array, in which the rows and columns represent the nodes in the network, and the element values in the matrix represent the connection relationship between the nodes. For example, an element value of 1 indicates that there is a connection between the two nodes, and a value of 0 indicates that there is no connection. Convolutional coding is a technology based on convolutional neural networks (CNNs). It extracts local features by sliding the convolution kernel on the matrix. Fully connected coding further compresses and encodes the convolution features to generate a more compact feature representation. In this process, parameters such as the size of the convolution kernel, the step size, and the number of neurons in the fully connected layer can be set according to the complexity of the network topology and the requirements of feature extraction. For example, for a complex network topology with a large number of nodes, a larger convolution kernel and a smaller step size can be used to extract more detailed local features, while increasing the number of neurons in the fully connected layer to ensure the richness of the features.

[0129] Preferably, when constructing the encoder of the network information generation model, a deep learning framework such as TensorFlow or PyTorch can be used. First, define the input layer of the network, and the input is a matrix representation of the regional network topology map. Next, add multiple convolutional layers, and the convolution kernel size and step size of each layer can be adjusted according to the size and complexity of the topology map. For example, the first convolutional layer can use a 3x3 convolution kernel and a step size of 1 to extract basic local features. Then, add a pooling layer to reduce the dimension of the features and improve the computational efficiency of the model. After that, add a fully connected layer to control the dimension of the encoded features by adjusting the number of neurons. During the training process, the mean square error (MSE) can be used as the loss function, and the parameters of the model can be adjusted through the backpropagation algorithm so that the model can accurately generate the topology map encoding features. In addition, in order to improve the generalization ability of the model, regularization techniques such as L2 regularization can be introduced in the training process to prevent the model from overfitting by adding the sum of the squares of the weights as a penalty term in the loss function.

[0130] In some embodiments, determining whether a network area model element matching the network area model element information exists in a preset network area model element library includes:

[0131] Calculating a similarity value between a network element feature vector in the network area model element information and a feature vector of each network area model element in the network area model element library;

[0132] Determine whether the similarity value exceeds a preset similarity threshold;

[0133] In response to a similarity value exceeding a preset similarity threshold, it is determined that a network area model element matching the network area model element information exists in the network area model element library.

[0134] It should be noted that when the present invention determines whether there is a network area model element in the network area model element library that matches the network area model element information, it is mainly achieved by calculating the similarity value between the network element feature vector in the network area model element information and the feature vector of each network area model element in the network area model element library. The purpose of this process is to find the known network area model element that is most similar to the current network area model element information, thereby providing a basis for subsequent model updates and optimizations. The similarity value is calculated by comparing the degree of proximity of the two feature vectors, and is usually measured using methods such as cosine similarity. When the similarity value exceeds a preset similarity threshold, it can be considered that a matching network area model element has been found.

[0135] Specifically, the network element feature vector in the network area model element information is a multidimensional vector used to describe various attributes of the network element, such as device type, communication capability, processing capability, etc. The network area model element library is a pre-set database that stores various possible network area model elements and their feature vectors. The similarity value is usually calculated by calculating the ratio of the dot product of two feature vectors to the product of their modulus lengths. This method is called cosine similarity. The preset similarity threshold is a value set according to actual application requirements and is used to determine whether two feature vectors are similar enough. For example, if the similarity threshold is set to 0.8, then when the calculated similarity value is greater than or equal to 0.8, it can be considered that a matching network area model element has been found.

[0136] Preferably, when calculating similarity values, a machine learning-based approach can be used to optimize the representation of feature vectors and the similarity calculation process. First, the feature vectors in the network area model element library are preprocessed, using dimensionality reduction techniques such as principal component analysis (PCA) to reduce the dimensionality of the feature vectors while retaining the key feature information. Then, a deep learning model, such as an autoencoder, is used to further encode and learn the feature vectors, enabling the model to automatically extract key information from the feature vectors. When calculating similarity, cosine similarity or other more complex similarity metrics, such as Euclidean distance or Mahalanobis distance, can be used. Furthermore, to improve matching accuracy, more feature vector samples can be introduced into the network area model element library, and similar feature vectors can be grouped using a clustering algorithm. This allows for faster identification of the closest feature vector during the matching process. In practical applications, the preset similarity threshold can be dynamically adjusted based on different network topologies and device types to accommodate varying matching requirements.

[0137] The above embodiments of the present invention have the following beneficial effects:

[0138] 1. The Star Flash networking control device can collect the network topology set of the target IoT area in real time, and use the signal coverage optimization algorithm to dynamically adjust the network topology structure, optimize the node distribution density and connection weight parameters, effectively solve the problems of uneven signal strength distribution and coverage blind spots in traditional wireless networking, and significantly improve the integrity and stability of network coverage.

[0139] 2. It can automatically build the initial network area model based on the pre-trained network information generation model, and realize the precise access of IoT devices and the automatic allocation of network resources through the intelligent matching of IoT device coding identification groups and device model information, greatly reducing the workload and error rate of manual configuration and improving networking efficiency and accuracy.

[0140] 3. After networking is completed, the target network data can be collected to perform multi-dimensional connection verification on each IoT device, including signal transmission delay detection and data transmission success rate analysis, and automatically identify and mark devices that fail the verification, effectively solving the problem of difficult fault location in traditional networking methods and ensuring the long-term stable operation of the entire IoT network.

[0141] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or a terminal device such as a computer, a server, a mobile phone, or a tablet.

[0142] The above descriptions are merely some preferred embodiments of the present invention and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also encompass other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned inventive concept. For example, a technical solution formed by mutually replacing the above-mentioned features with (but not limited to) technical features having similar functions disclosed in the embodiments of the present invention.

Claims

1. A wireless IoT networking method based on Star Flash technology, characterized in that: include: The network deployment data of the target IoT area is collected through the Star Flash networking control device, and the network deployment data includes a network topology structure set corresponding to the target IoT area; Performing encoding processing on each IoT device to be connected in the target IoT area to generate an IoT device encoding identifier, thereby obtaining an IoT device encoding identifier group; Generate an optimized network topology structure set through the network topology structure set, wherein the optimized network topology structure is a structure obtained by optimizing signal coverage of multiple network topologies; Performing network splicing on each optimized network topology structure in the optimized network topology structure set to obtain a regional network topology map; Generate an original network area model corresponding to the target IoT area based on the regional network topology map and the pre-trained network information generation model; Obtaining the IoT device model information corresponding to each IoT device code identifier in the IoT device code identifier group to obtain an IoT device model information group, where the IoT device model information includes: IoT device model, access location information, and communication parameter information; Fill the original network area model according to the IoT device model information group and the IoT device code identification group to obtain the target network area model; According to the target network area model, control the associated networking devices to perform networking processing on each IoT device to be connected; In response to determining that the networking of each IoT device is completed, the Star Flash networking control device is controlled to collect the network deployment data of the target IoT area after the networking is completed as the target network data, and based on the target network data, the connection of each IoT device that has completed the networking is verified.

2. The wireless IoT networking method based on Star Flash technology according to claim 1 is characterized in that: Based on the regional network topology and pre-trained network information generation model, the original network regional model corresponding to the target IoT area is generated, including: Generate an initial network area model and network area model information based on the regional network topology map and the network information generation model, wherein the network area model information includes: a network area model element information set, the network area model element information includes: a network element type, a network element feature vector, and network element position information, the network element position information representing the position of the network area model element corresponding to the network area model element information in the initial network area model; For each network area model element information in the network area model element information set, the following processing steps are performed: determining whether there is a network area model element matching the network area model element information in a preset network area model element library based on the network element type and the network element feature vector included in the network area model element information; In response to a matching network area model element existing in the network area model element library, determining the network area model element matching the network area model element information as a candidate network area model element; The initial network area model is updated according to each candidate network area model element to generate an updated initial network area model as the original network area model.

3. The wireless IoT networking method based on Star Flash technology according to claim 2 is characterized in that: Generate a model based on the regional network topology and network information, and generate an initial network regional model and network regional model information, including: Generate a topology map encoding feature corresponding to the regional network topology map based on an encoder included in the network information generation model; Generate a topology map decoding feature corresponding to the topology map encoding feature through a decoder included in the network information generation model; Generate a topology map extraction feature corresponding to the topology map decoding feature through a feature extraction model included in the network information generation model; Generate adjustment parameters corresponding to the regional network topology map by adjusting the network using the threshold value included in the network information generation model; By adjusting parameters and extracting features from the topology map, an initial network area model and network area model information are generated.

4. The wireless IoT networking method based on Star Flash technology according to claim 2, characterized in that: According to the IoT device model information group and the IoT device code identification group, the original network area model is filled to obtain the target network area model, including: For each piece of IoT device model information in the IoT device model information group, the following filling steps are performed: the IoT device model included in the IoT device model information is filled into the access position of the corresponding access position information in the original network area model; Determine the IoT device coding identifier corresponding to the IoT device model information as the target IoT device coding identifier; Marking the target IoT device code identifier on the IoT device model of the corresponding IoT device model information in the original network area model; The filled original network area model is determined as the target network area model.

5. The wireless IoT networking method based on Star Flash technology according to claim 1, characterized in that: Generate an optimized network topology set through the network topology set, including: For each network topology structure in the network topology structure set, the following optimization steps are performed: calculating the signal coverage parameters of the network topology structure, wherein the signal coverage parameters include a signal strength distribution value and a signal coverage blind area value; adjusting the network topology structure parameters of the network topology structure according to the signal coverage parameters, wherein the network topology structure parameters include a node distribution density value and an inter-node connection weight value; determining the network topology structure corresponding to the adjusted network topology structure parameters as the optimized network topology structure; and combining the various optimized network topologies into an optimized network topology structure set.

6. The wireless IoT networking method based on Star Flash technology according to claim 1, characterized in that: Perform network splicing on each optimized network topology structure in the optimized network topology structure set to obtain a regional network topology diagram, including: Obtain the network topology node set and network topology edge set of each optimized network topology structure; determine the node overlap area between each optimized network topology structure according to the position coordinates of each network topology node set; perform node matching processing on the network topology node set of each optimized network topology structure according to the node overlap area to obtain a matching node pair set; perform edge fusion processing on the network topology edge set of each optimized network topology structure according to the matching node pair set to generate a spliced edge set; generate a regional network topology graph according to the matching node pair set and the spliced edge set.

7. The wireless IoT networking method based on Star Flash technology according to claim 4 is characterized in that: After filling the IoT device model included in the IoT device model information into the access location of the corresponding access location information in the original network area model, the method further includes: Obtain communication parameter information from IoT device model information; Adjust the communication parameters of the IoT device model corresponding to the original network area model according to the communication parameter information, wherein the communication parameters include transmission power parameters and communication frequency band parameters; The IoT device model corresponding to the adjusted communication parameters is updated to the original network area model.

8. The wireless IoT networking method based on Star Flash technology according to claim 1, characterized in that: Based on the target network data, perform connection verification on each IoT device that has been networked, including: Determine the connection verification parameters of each IoT device based on the target network data, where the connection verification parameters include signal transmission delay value and data transmission success rate value; Determine whether the connection verification parameters meet the preset connection verification conditions; In response to the connection verification parameter satisfying the preset connection verification condition, determining that the corresponding IoT device passes the connection verification; In response to the connection verification parameter not satisfying the preset connection verification condition, the IoT device that failed the connection verification is marked in the target network area model.

9. The wireless IoT networking method based on Star Flash technology according to claim 3, characterized in that: The encoder included in the network information generation model generates topology map encoding features corresponding to the regional network topology map, including: Converting the regional network topology map into a topology matrix; The topology map matrix is convolutionally encoded by the encoder to generate topology map convolution features; The topology map convolution features are fully connected and encoded to generate topology map encoding features.

10. The wireless IoT networking method based on Star Flash technology according to claim 2, characterized in that: Determine whether there is a network area model element matching the network area model element information in the preset network area model element library, including: Calculating a similarity value between a network element feature vector in the network area model element information and a feature vector of each network area model element in the network area model element library; Determine whether the similarity value exceeds a preset similarity threshold; In response to a similarity value exceeding a preset similarity threshold, it is determined that a network area model element matching the network area model element information exists in the network area model element library.

Images