AI-driven 5G IoT data processing system

By adopting AI-driven 5G IoT data processing system in the Internet of Things system, using neural network modules to build auxiliary models and perform intelligent matching, the transmission delay and security problems in massive data processing of IoT devices are solved, and efficient and reliable are achieved data transmission and device management.

CN118075782BActive Publication Date: 2024-12-03YUNNAN YANBEN INFORMATION SECURITY TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410464482.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-17
Publication Date
2024-12-03
Estimated Expiration
2044-04-17

AI Technical Summary

Technical Problem

Existing IoT architectures are prone to problems such as increasing data transmission latency, increasing network bandwidth pressure and declining security when processing massive data, especially due to the surge in the number of IoT devices and the explosive growth of data volume.

Method used

Adopting an AI-driven 5G IoT data processing system, the IoT device information acquisition module, edge computing node information acquisition module, data processing module, neural network module, data analysis module and matching module work together to build an auxiliary model to judge objects The data transmission requirements of networked devices, and the devices are matched with edge computing nodes through intelligent matching strategies, optimizing resource allocation and data transmission.

Benefits of technology

It realizes intelligent matching and efficient data processing between IoT devices and edge computing nodes, improves the overall performance of the system, ensures the security and reliability of data transmission, meets different data transmission needs, and provides fast data processing and transmission capabilities. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118075782B_ABST
    Figure CN118075782B_ABST
Patent Text Reader

Abstract

The present invention discloses an AI-driven 5G Internet of Things data processing system, which specifically relates to the field of Internet of Things data processing, including an Internet of Things device information collection module for obtaining a main body operation information set and an environmental information set, an edge computing node information collection module for obtaining a state information set, a data processing module for processing various information sets, a neural network module for auxiliary model construction, and judging the type of target Internet of Things device data, a data analysis module for jointly analyzing the state processing data set and the target Internet of Things device data, and establishing a matching relationship between the target Internet of Things device and the edge computing node through a matching module and performing data transmission; the present invention can realize intelligent matching and efficient data processing of Internet of Things devices and edge computing nodes, meet different data transmission requirements, improve overall performance, realize effective management of Internet of Things devices and edge computing nodes, and ensure the security and reliability of data transmission.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things data processing technology, and more specifically, to an AI-driven 5G Internet of Things data processing system. Background Art

[0002] With the rapid development of information technology, the Internet of Things has become a key technology for connecting various devices, sensors, and systems, allowing these entities to collect and exchange data without human intervention. The introduction of 5G technology has further improved the speed and reliability of data transmission, providing a broader application space for IoT devices. However, with the surge in the number of IoT devices and the explosive growth in data volume, how to effectively manage these devices and process massive data in a timely manner through AI technology has become a challenge. In the existing IoT architecture, IoT devices usually transmit data directly to cloud servers or data centers for processing and analysis, which is prone to problems such as increased data transmission delays, increased network bandwidth pressure, and decreased security due to long-distance data transmission. Therefore, a 5G IoT data processing system based on AI is proposed. Summary of the invention

[0003] To achieve the above object, the present invention provides the following technical solutions:

[0004] AI-driven 5G IoT data processing system, including IoT device information collection module, edge computing node information collection module, data processing module, neural network module, data analysis module, and matching module;

[0005] The IoT device information collection module is used to collect the main body operation information and environmental information of the IoT devices in the target area, obtain the main body operation information set and the environmental information set and transmit them to the data processing module;

[0006] The edge computing node information collection module is used to collect the status information of the edge computing nodes in the target area, obtain the status information set and transmit it to the data processing module;

[0007] The data processing module is used to process the ontology operation information set to obtain an ontology operation processing data set, process the environment information set to obtain an environment processing data set, process the state information set to obtain a state processing data set, and then transmit the environment processing data set and the ontology operation processing data set to the neural network module together, and transmit the state processing data set to the data analysis module;

[0008] The neural network module is used to construct an auxiliary model based on the environment processing data set and the entity operation processing data set, and is used to determine the type of target IoT device data based on the output results of the auxiliary model;

[0009] The data analysis module is used to jointly analyze the state processing data set with different types of target IoT device data according to the preset analysis strategy, and transmit the obtained analysis results to the matching module;

[0010] The matching module is used to establish a matching relationship between the target IoT device and the edge computing node and perform data transmission according to the preset matching strategy.

[0011] In a preferred embodiment, the entity operation information set includes the location, type, and various operation parameter information of each IoT device in the target area.

[0012] In a preferred embodiment, the environmental information set includes various environmental parameter information of the environment in which each IoT device in the target area is located.

[0013] In a preferred embodiment, the specific construction steps of the neural network module for auxiliary model construction based on the environment processing data set and the ontology operation processing data set are as follows:

[0014] The neural network module receives the entity operation processing data set and the environment processing data set, and then uses the various operation parameter data of the IoT device in the entity operation processing data set and the various environmental parameter data of the environment in which the IoT device is located as the input data for model training, and uses the data transmission demand value of the target IoT device as the output data for model training, builds an auxiliary model for the target IoT device, and assigns it a value of 0 or 1 to train the model, where 0 indicates that the data transmission demand value of the target IoT device is less than or equal to the set threshold, and 1 indicates that the data transmission demand value of the target IoT device is greater than the set threshold;

[0015] The various operating parameter data of the IoT device in the main body operation processing data set of the target IoT device in the time planning window recently preset by the data processing module and the various environmental parameter data of the environment in which the IoT device is located are taken as the input data for model training. When the output data of the model in the target state is 0, the various operating parameter data of the IoT device in the main body operation processing data set of the target IoT device in the time planning window recently preset by the data processing module and the various environmental parameter data of the environment in which the IoT device is located are taken as the training data of the model to perform secondary training on the model and generate instruction one at the same time. When the output data of the model in the target state is 1, the various operating parameter data of the IoT device in the main body operation processing data set of the target IoT device in the time planning window recently preset by the data processing module and the various environmental parameter data of the environment in which the IoT device is located are taken as the training data of the model to perform secondary training on the model and generate instruction two at the same time. The instruction types generated by all IoT devices through the neural network module are summarized to obtain an instruction set and transmit it to the data analysis module.

[0016] In a preferred embodiment, the neural network module uses various operating parameter data of the IoT device in the main body operation processing data set and various environmental parameter data of the environment in which the IoT device is located as input data for model training, and uses the data transmission demand value of the target IoT device as output data for model training, which means:

[0017] Step 1: Obtain various operating parameter data of the IoT device in the entity operation processing data set and mark them as CSi respectively, and obtain various environmental parameter data of the environment in which the IoT device is located and mark them as SJi respectively;

[0018] Step 2: Get the operating value of the target IoT device by calculation: , is the preset standard value corresponding to various operating parameter data CSi of the IoT device, YXi is the operating value of the target IoT device, and ci is the preset proportional coefficient corresponding to various operating parameter data CSi of the IoT device;

[0019] Step 3: Obtain the environmental value of the target IoT device through calculation: , is the preset standard value corresponding to each environmental parameter data SJi of the IoT device, fi is the preset proportional coefficient corresponding to each environmental parameter data SJi of the IoT device, and HJi is the environmental value of the target IoT device;

[0020] Step 4: Obtain the data transmission demand value of the target IoT device through calculation. , XQi is the data transmission demand value of the target IoT device;

[0021] Step 5: Use the operating value and environmental value of the target IoT device as input data for model training, and use the data transmission demand value of the target IoT device as output data for model training to build the model.

[0022] In a preferred embodiment, the neural network module determines the type of target IoT device data according to the output result of the auxiliary model:

[0023] When instruction one is received, the type of the target IoT device data is type one, and when instruction two is received, the type of the target IoT device data is type two.

[0024] In a preferred embodiment, the data analysis module is used to jointly analyze the state processing data set with different types of target IoT device data according to a preset analysis strategy, and transmit the obtained analysis results to the matching module, which means:

[0025] When the type of the target IoT device data is type 1, the resource data in the state processing data set of the edge computing node is obtained and marked as ZYi, and the satisfaction value MZi of the edge computing node is obtained by calculation. , zi is the preset proportional coefficient corresponding to each resource data ZYi in the state processing data set of the edge computing node, and then all edge computing nodes corresponding to the satisfaction value MZi that is not less than the data transmission demand value of the target IoT device are sorted, and a matching form is obtained and transmitted to the matching module;

[0026] When the type of the target IoT device data is type 2, the various security protection data in the state processing data set of the edge computing node are also obtained and marked as FHi, and the protection value FFi of the edge computing node is obtained by calculation. , is the standard value corresponding to each safety protection data FHi, wi is the preset safety factor corresponding to each safety protection data FHi, and then calculate the satisfaction degree MDi, , q1 and q2 are both preset specific proportional coefficients, and then all edge computing nodes corresponding to the satisfaction MDi of the data transmission demand value not less than the target IoT device are sorted to obtain a matching form and transmit it to the matching module.

[0027] Technical effects and advantages of the present invention:

[0028] The present invention works in collaboration through multiple modules: the IoT device information collection module is responsible for real-time monitoring and collecting the main body operation information of all IoT devices in the target area; the edge computing node information collection module collects the status information of the edge computing nodes; the data processing module pre-processes the data from the IoT devices and edge computing nodes. The processed data is sent to the neural network module and the data analysis module for more in-depth analysis; the neural network module uses a deep learning neural network to build an auxiliary model to predict the transmission requirements of the IoT devices based on the input environmental data and device operation data. The model training adopts a threshold method to divide the output results into two categories to determine the type of device data transmission requirements. The data analysis module, according to the preset analysis strategy, jointly analyzes the status information set and the target IoT device data, optimizes resource allocation, and improves the overall performance of the system.

[0029] The matching module in the present invention establishes a matching relationship with the Internet of Things device according to the top-ranked edge computing node to realize data transmission. The advantage of the present invention is that it can realize intelligent matching and efficient data processing of Internet of Things devices and edge computing nodes, meet different data transmission requirements, improve overall performance, realize effective management of Internet of Things devices and edge computing nodes, provide fast data processing and transmission capabilities, and ensure the security and reliability of data transmission. The present invention has broad application potential in smart cities, industrial automation and other fields requiring efficient data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0031] Figure 1 This is a schematic diagram of the AI-driven 5G IoT data processing system in the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] Example 1

[0034] The AI-driven 5G IoT data processing system realizes effective management and data processing of IoT devices and edge computing nodes through the collaborative work of multiple modules, including IoT device information collection module, edge computing node information collection module, data processing module, neural network module, data analysis module, and matching module; the IoT device information collection module, edge computing node information collection module, data processing module, neural network module, data analysis module, and matching module are communicated with each other.

[0035] The IoT device information collection module is used to collect the main operating information and environmental information of the IoT devices in the target area, obtain the main operating information set and the environmental information set and transmit them to the data processing module; the IoT device information collection module monitors and collects the operating information and environmental information of all IoT devices in the target area in real time. The main operating information set includes the location, type, and various operating parameter information of each IoT device in the target area, such as data size, operating time and other operating parameters. The environmental information set includes various environmental parameter information of the environment in which each IoT device in the target area is located, such as temperature, humidity and other environmental parameters. This information is organized into a data set and provided to subsequent modules for further processing.

[0036] The edge computing node information collection module is used to collect the status information of the edge computing nodes in the target area, obtain the status information set and transmit it to the data processing module; similar to the IoT device information collection module, the edge computing node information collection module is responsible for collecting the status information of the edge computing nodes, such as computing resource usage, network status, storage capacity, etc. Understanding the status of the edge computing nodes is crucial to ensuring the effectiveness and efficiency of data processing.

[0037] The data processing module is used to process the ontology operation information set to obtain the ontology operation processing data set, process the environment information set to obtain the environment processing data set, process the state information set to obtain the state processing data set, and then transmit the environment processing data set and the ontology operation processing data set to the neural network module together, and transmit the state processing data set to the data analysis module; the data processing module receives data from the Internet of Things devices and edge computing nodes, and performs necessary preprocessing, such as converting the data standardized format into a format that can be used for subsequent processing. The processed data is sent to the neural network module and the data analysis module for more in-depth analysis.

[0038] The neural network module is used to build an auxiliary model based on the environment processing data set and the entity operation processing data set, and to judge the type of target IoT device data based on the output results of the auxiliary model; the neural network module uses advanced machine learning algorithms, which are deep learning neural networks in this invention, to build auxiliary models, which can predict the transmission needs of IoT devices based on the input environment and device operation data, and can respond more intelligently to the data transmission needs of different devices; the neural network module is part of AI technology. Artificial neural networks, or commonly referred to as neural networks, are a type of algorithm that imitates the behavioral characteristics of neural networks in animals, especially humans. They can perform distributed parallel information processing, which is particularly important in the fields of machine learning and deep learning. The following are some detailed explanations of the connection between neural networks and AI: Basic concepts: AI is a broad concept , covering a variety of technologies and algorithms from machine learning to deep learning, and neural network is one of the core components for implementing deep learning. It processes data by simulating the working method of neurons in the brain; structural characteristics: neural network consists of many interconnected nodes, these nodes or layers can process large amounts of data and learn patterns from them, this structure makes neural network particularly suitable for processing complex data sets; learning mechanism: neural network performs prediction or classification tasks by learning patterns in the data. This process involves continuous adjustment of weights and biases to minimize prediction errors, which is part of the machine learning process. The neural network module is not only part of AI technology, but also one of the key technologies for realizing many advanced functions in AI. By simulating the processing method of the human brain, neural networks are able to recognize complex patterns and thus play a role in various intelligent systems.

[0039] The data analysis module is used to jointly analyze the state processing data set with different types of target IoT device data according to the preset analysis strategy, and transmit the obtained analysis results to the matching module; combined with the preset analysis strategy, the state information set and the target IoT device data are jointly analyzed. This analysis helps to identify patterns, optimize resource allocation and improve the overall performance of the system.

[0040] The matching module is used to establish a matching relationship between the target IoT device and the edge computing node according to the preset matching strategy and perform data transmission; the matching module establishes a matching relationship between the IoT device and the edge computing node according to the preset matching strategy for effective data transmission, which ensures that data can flow quickly and securely between the device and the node.

[0041] Among them, the relevance of AI, 5G and neural network modules in this scenario is mainly reflected in the following aspects: AI-driven 5G IoT data processing. AI technology can be used to process and analyze large amounts of data generated by 5G IoT devices. By using machine learning and deep learning algorithms, AI can help identify patterns and trends in the data, thereby providing a basis for decision-making. At the same time, 5G technology provides AI with high-speed, low-latency data transmission capabilities, making real-time data processing possible; the neural network module is used to process data sets according to the environment. A neural network is a computing model that simulates the structure of neurons in the human brain and can be used to process complex data sets. In this scenario, the neural network module can learn and train based on environmental data to better understand environmental characteristics and device behavior, which helps to achieve intelligent management and control of equipment and improve the overall performance of the IoT system. AI, 5G and neural network modules are closely related and jointly provide support for IoT data processing and intelligent device management. AI and neural networks are responsible for learning and identifying data features, data analysis and decision-making, and 5G provides high-speed data transmission capabilities. These technologies work together to promote the development of the IoT system.

[0042] The entity operation information set includes the location, type, and various operation parameter information of each IoT device in the target area, and the environment information set includes various environmental parameter information of the environment in which each IoT device in the target area is located.

[0043] The specific construction steps of the neural network module for auxiliary model construction based on the environment processing data set and the ontology operation processing data set are as follows:

[0044] The neural network module receives the entity operation processing data set and the environment processing data set, and then uses the various operation parameter data of the IoT device in the entity operation processing data set and the various environmental parameter data of the environment in which the IoT device is located as the input data for model training, and uses the data transmission demand value of the target IoT device as the output data for model training, builds an auxiliary model for the target IoT device, and assigns it a value of 0 or 1 to train the model, where 0 indicates that the data transmission demand value of the target IoT device is less than or equal to a set threshold, and the set threshold is set according to the type of the target IoT device, and 1 indicates that the data transmission demand value of the target IoT device is greater than the set threshold;

[0045] The various operating parameter data of the IoT device in the main body operation processing data set of the target IoT device in the time planning window recently preset by the data processing module and the various environmental parameter data of the environment in which the IoT device is located are used as input data for model training. When the output data of the model in the target state is 0, it means that the data transmission requirement of the IoT device is lower than the normal standard. The various operating parameter data of the IoT device in the main body operation processing data set of the target IoT device in the time planning window recently preset by the data processing module and the various environmental parameter data of the environment in which the IoT device is located are used as the training data of the model to perform secondary training on the model and generate instruction one at the same time. When the output data of the model in the target state is 1, it means that the data transmission requirement of the IoT device has reached the normal standard. The normal standard requirements are exemplified as: security, storage capacity, computing power and other comprehensive demand indicators. The various operating parameter data of the IoT device in the body operation processing data set of the target IoT device in the time planning window recently preset by the data processing module and the various environmental parameter data of the environment in which the IoT device is located are used as the training data of the model to perform secondary training on the model and generate instructions at the same time. The instruction types generated by the neural network module for all IoT devices are summarized to obtain the instruction set and transmit it to the data analysis module. The neural network module can effectively build and train auxiliary models to predict the data transmission needs of IoT devices and generate corresponding instructions, which helps the entire system to more intelligently manage and schedule data transmission between IoT devices and edge computing nodes.

[0046] The neural network module uses the various operating parameter data of the IoT devices in the main body operation processing data set and the various environmental parameter data of the environment in which the IoT devices are located as the input data for model training, and uses the data transmission demand value of the target IoT device as the output data for model training.

[0047] Step 1: Obtain various operating parameter data of the IoT device in the entity operation processing data set and mark them as CSi respectively, and obtain various environmental parameter data of the environment in which the IoT device is located and mark them as SJi respectively;

[0048] Step 2: Get the operating value of the target IoT device by calculation: , is the preset standard value corresponding to various operating parameter data CSi of the IoT device, YXi is the operating value of the target IoT device, ci is the preset proportional coefficient corresponding to various operating parameter data CSi of the IoT device, reflecting the influence of various operating parameter data CSi on the operating value of the target IoT device; the operating value of the target IoT device reflects the current working status of the IoT device, including parameters such as the temperature of the IoT device, the power consumption of the IoT device, etc. These parameters are combined with the preset standard value and the proportional coefficient ci to calculate a value summarizing the operating status of the device;

[0049] Step 3: Obtain the environmental value of the target IoT device through calculation: , is the preset standard value corresponding to each environmental parameter data SJi of the IoT device, fi is the preset proportional coefficient corresponding to each environmental parameter data SJi of the IoT device, HJi is the environmental value of the target IoT device, and fi reflects the degree of influence of each environmental parameter data of the IoT device on the environmental value of the target IoT device; the environmental value of the target IoT device takes into account the environmental conditions of the IoT device, such as the humidity of the environment, the light intensity of the environment, and other parameters. Similarly, these environmental parameters are also calculated through the preset standard value and the proportional coefficient fi.

[0050] Step 4: Obtain the data transmission demand value of the target IoT device through calculation. , XQi is the data transmission demand value of the target IoT device; the setting significance of t1 and t2 is to ensure that the function as a whole meets the calculation requirements during calculation. The data transmission demand value is a function that combines the operating value and the environmental value, and k1 and k2 are coefficients in this function, which are used to adjust the relative importance of the operating value and the environmental value. If k1 is larger, it means that the operating value has a greater impact on the data transmission demand; if k2 is larger, it means that the impact of the environmental value is more important;

[0051] Step 5: Use the operating value and environmental value of the target IoT device as input data for model training, and use the data transmission demand value of the target IoT device as output data for model training to build the model.

[0052] The neural network module determines the type of target IoT device data based on the output of the auxiliary model:

[0053] When instruction one is received, the type of the target IoT device data is type one, indicating that the data transmission requirements for the IoT device are lower than the normal standards. When instruction two is received, the type of the target IoT device data is type two, indicating that the data transmission requirements for the IoT device meet the normal standards. Compared with type one, the target IoT device data of type two has higher requirements for edge computing nodes during data transmission, such as security performance and computing performance.

[0054] The data analysis module is used to jointly analyze the state processing data set with different types of target IoT device data according to the preset analysis strategy, and transmit the obtained analysis results to the matching module.

[0055] When the type of the target IoT device data is type 1, the resource data in the state processing data set of the edge computing node is obtained and marked as ZYi, and the satisfaction value MZi of the edge computing node is obtained by calculation. , zi is the preset proportional coefficient corresponding to each resource data ZYi in the state processing data set of the edge computing node, zi reflects the importance of each resource data in the state processing data set of the edge computing node to the satisfaction value of the edge computing node, and then all edge computing nodes corresponding to the satisfaction value MZi that is not less than the data transmission demand value of the target IoT device are sorted, and a matching form is obtained and transmitted to the matching module;

[0056] When the type of the target IoT device data is type 2, the various security protection data in the state processing data set of the edge computing node are also obtained and marked as FHi, and the protection value FFi of the edge computing node is obtained by calculation. , is the standard value corresponding to each security protection data FHi, wi is the preset safety factor corresponding to each security protection data FHi, which reflects the importance of each security protection data FHi to the protection value of the edge computing node. Compared with type 1, type 2 target IoT device data has higher requirements for edge computing nodes during data transmission, so further analysis is needed: calculate the satisfaction degree MDi, , q1 and q2 are both preset specific proportional coefficients, and the sum of q1 and q2 is one, which is used to reflect the influence ratio of the protection value FFi and the satisfaction value MZi on the data transmission requirements of the target IoT device data. The larger the satisfaction value MZi, the stronger the computing power and data transmission capacity of the edge computing node. The larger the protection value FFi, the more serious the network attack on the edge computing node and the higher the risk of leakage. The satisfaction degree MDi is set under comprehensive consideration and the comprehensive performance of the edge computing node is calculated. Then, all edge computing nodes corresponding to the satisfaction degree MDi that is not less than the data transmission requirement value of the target IoT device are sorted, and the matching form is obtained and transmitted to the matching module.

[0057] The matching module is used to establish a matching relationship between the target IoT device and the edge computing node according to the preset matching strategy and perform data transmission, which means: establishing a matching relationship between the target IoT device and the edge computing node with the best comprehensive performance that ranks first in the matching form and performing data transmission to achieve fast and reliable data processing and transmission.

[0058] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0059] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0060] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0061] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0062] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0063] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The AI-driven 5G IoT data processing system is characterized by: It includes IoT device information collection module, edge computing node information collection module, data processing module, neural network module, data analysis module, and matching module; The IoT device information collection module is used to collect the main body operation information and environmental information of the IoT devices in the target area, obtain the main body operation information set and the environmental information set and transmit them to the data processing module; The edge computing node information collection module is used to collect the status information of the edge computing nodes in the target area, obtain the status information set and transmit it to the data processing module; The data processing module is used to process the ontology operation information set to obtain an ontology operation processing data set, process the environment information set to obtain an environment processing data set, process the state information set to obtain a state processing data set, and then transmit the environment processing data set and the ontology operation processing data set to the neural network module together, and transmit the state processing data set to the data analysis module; The neural network module is used to construct an auxiliary model based on the environment processing data set and the entity operation processing data set, and is used to determine the type of target IoT device data based on the output results of the auxiliary model; The data analysis module is used to jointly analyze the state processing data set with different types of target IoT device data according to the preset analysis strategy, and transmit the obtained analysis results to the matching module; The matching module is used to establish a matching relationship between the target IoT device and the edge computing node according to a preset matching strategy and perform data transmission; The ontology operation information set includes the location, type, and various operation parameter information of each IoT device in the target area; The environmental information set contains various environmental parameter information of the environment in which each IoT device in the target area is located; The specific construction steps of the neural network module for auxiliary model construction based on the environment processing data set and the ontology operation processing data set are as follows: The neural network module receives the entity operation processing data set and the environment processing data set, and then uses the various operation parameter data of the IoT device in the entity operation processing data set and the various environmental parameter data of the environment in which the IoT device is located as the input data for model training, and uses the data transmission demand value of the target IoT device as the output data for model training, builds an auxiliary model for the target IoT device, and assigns it a value of 0 or 1 to train the model, where 0 indicates that the data transmission demand value of the target IoT device is less than or equal to the set threshold, and 1 indicates that the data transmission demand value of the target IoT device is greater than the set threshold; The various operating parameter data of the IoT device in the main body operation processing data set of the target IoT device in the time planning window recently preset by the data processing module and the various environmental parameter data of the environment in which the IoT device is located are used as the input data for model training. When the output data of the model in the target state is 0, the various operating parameter data of the IoT device in the main body operation processing data set of the target IoT device in the time planning window recently preset by the data processing module and the various environmental parameter data of the environment in which the IoT device is located are used as the training data of the model to perform secondary training on the model and generate instruction one at the same time. When the output data of the model in the target state is 1, the various operating parameter data of the IoT device in the main body operation processing data set of the target IoT device in the time planning window recently preset by the data processing module and the various environmental parameter data of the environment in which the IoT device is located are used as the training data of the model to perform secondary training on the model and generate instruction two at the same time. The instruction types generated by all IoT devices through the neural network module are summarized to obtain an instruction set and transmit it to the data analysis module. The neural network module uses the various operating parameter data of the IoT devices in the main operation processing data set and the various environmental parameter data of the environment in which the IoT devices are located as the input data for model training, and uses the data transmission demand value of the target IoT device as the output data for model training. Step 1: Obtain various operating parameter data of the IoT device in the entity operation processing data set and mark them as CSi respectively, and obtain various environmental parameter data of the environment in which the IoT device is located and mark them as SJi respectively; Step 2: Get the operating value of the target IoT device by calculation: , is the preset standard value corresponding to various operating parameter data CSi of the IoT device, YXi is the operating value of the target IoT device, and ci is the preset proportional coefficient corresponding to various operating parameter data CSi of the IoT device; Step 3: Obtain the environmental value of the target IoT device through calculation: , is the preset standard value corresponding to each environmental parameter data SJi of the IoT device, fi is the preset proportional coefficient corresponding to each environmental parameter data SJi of the IoT device, and HJi is the environmental value of the target IoT device; Step 4: Obtain the data transmission demand value of the target IoT device through calculation. , XQi is the data transmission demand value of the target IoT device; t1 and t2 ensure that the function as a whole meets the calculation requirements during calculation, and k1 and k2 are the coefficients in the data transmission demand value calculation function, which are used to adjust the relative importance of the operating value and the environmental value; Step 5: Use the operating value and environmental value of the target IoT device as input data for model training, and use the data transmission demand value of the target IoT device as output data for model training to build the model; The neural network module determines the type of target IoT device data based on the output of the auxiliary model: When instruction one is received, the type of the target IoT device data is type one, and when instruction two is received, the type of the target IoT device data is type two; The data analysis module is used to jointly analyze the state processing data set with different types of target IoT device data according to the preset analysis strategy, and transmit the obtained analysis results to the matching module. When the type of the target IoT device data is type 1, the resource data in the state processing data set of the edge computing node is obtained and marked as ZYi, and the satisfaction value MZi of the edge computing node is obtained by calculation. , zi is the preset proportional coefficient corresponding to each resource data ZYi in the state processing data set of the edge computing node, and then all edge computing nodes corresponding to the satisfaction value MZi that is not less than the data transmission demand value of the target IoT device are sorted, and a matching form is obtained and transmitted to the matching module; When the type of the target IoT device data is type 2, the various security protection data in the state processing data set of the edge computing node are also obtained and marked as FHi, and the protection value FFi of the edge computing node is obtained by calculation. , is the standard value corresponding to each safety protection data FHi, wi is the preset safety factor corresponding to each safety protection data FHi, and then calculate the satisfaction degree MDi, , q1 and q2 are both preset specific proportional coefficients, the sum of q1 and q2 is one, and then all edge computing nodes corresponding to the satisfaction MDi of the data transmission demand value not less than the target IoT device are sorted, and a matching form is obtained and transmitted to the matching module.