Multi-terminal data transmission detection method and system based on artificial intelligence

Abstract

The present invention discloses a multi-terminal data transmission detection method and system based on artificial intelligence, which relates to the field of network communication technology. To address the data consistency, security and efficiency issues in current heterogeneous networks, the method adopts the following solutions: building a cloud connection layer, configuring a number of edge nodes, each edge node is connected to a designated terminal; logically grouping the edge nodes corresponding to multiple terminals with interaction needs; each edge node is responsible for monitoring the real-time operating status of the terminals connected to it and collecting monitoring data; the cloud connection layer receives the monitoring data, evaluates the consistency between the monitoring data in the same group based on an artificial intelligence prediction model, and obtains a difference value; the cloud connection layer generates and sends an adjustment signal based on the difference value, and the edge node adjusts the corresponding terminal based on the adjustment signal to ensure that the data interaction between the associated terminals in the same group remains consistent. The present invention is applicable to the current complex heterogeneous Internet environment.

Description

Technical Field

[0001] The present invention relates to the field of network communication technology, and in particular to an artificial intelligence-based multi-terminal data transmission detection method and system. Background Art

[0002] Artificial intelligence, a cutting-edge discipline, is dedicated to exploring and developing theories, methods, and technologies that simulate and extend human intelligence. It is a key branch of computer science focused on understanding the essence of intelligence and striving to create intelligent systems that can perceive, learn, reason, and interact in a human-like manner.

[0003] Heterogeneous network transmission refers to the process of exchanging data across a comprehensive network system composed of different types of technologies and equipment. These networks may include, but are not limited to, wired networks, wireless networks, sensor networks, and satellite networks. By integrating these diverse subnetworks, heterogeneous networks enable seamless transmission and sharing of data and information across diverse environments.

[0004] In complex network environments, ensuring secure communication, data consistency, and privacy protection between different terminals is crucial. This is especially true in heterogeneous networks, where large amounts of data exchanged between multiple terminals are used for decision-making, analysis, processing, and control operations. Data inconsistencies or security vulnerabilities between terminals can not only lead to erroneous analysis results and poor decision-making, but can also cause privacy issues due to the leakage of sensitive information (such as personal identity information and financial information).

[0005] Therefore, it is necessary to provide an artificial intelligence-based multi-terminal data transmission detection method and system to solve the above technical problems. Summary of the Invention

[0006] In response to the needs and shortcomings of current technological development, the present invention provides an artificial intelligence-based multi-terminal data transmission detection method and system, which solves the problems of data consistency, security and efficiency in heterogeneous networks through the deep integration of edge computing and cloud computing.

[0007] In a first aspect, the present invention provides a multi-terminal data transmission detection method based on artificial intelligence, and the technical solutions adopted to solve the above technical problems are as follows:

[0008] An artificial intelligence-based multi-terminal data transmission detection method comprises the following steps:

[0009] Build a cloud connectivity layer;

[0010] In the cloud connection layer, several edge nodes are configured, each of which is connected to a designated terminal;

[0011] Logically group the edge nodes corresponding to multiple terminals with interaction requirements;

[0012] Each edge node is responsible for monitoring the real-time operating status of the terminals connected to it and collecting monitoring data;

[0013] The cloud connection layer receives all monitoring data from edge nodes and evaluates the consistency between each monitoring data in the same group based on the artificial intelligence prediction model to obtain the difference value;

[0014] The cloud connection layer generates and sends adjustment signals to the corresponding edge nodes based on the difference values;

[0015] The edge node that receives the adjustment signal adjusts the corresponding terminal according to the instruction to ensure that the data interaction between the terminals in the same group that have an interactive relationship remains highly consistent.

[0016] Optionally, the edge nodes corresponding to multiple terminals with interaction requirements are logically grouped. The logical grouping process is as follows:

[0017] The cloud connection layer identifies the interaction needs between terminals based on previous monitoring data and terminal interaction logs of each terminal;

[0018] Based on the above interaction requirements, a correlation graph is constructed. Each node in the correlation graph represents an edge node, and an edge represents the interaction relationship between the terminals connected by two edge nodes.

[0019] A clustering algorithm is used to group the nodes in the association graph to ensure that the interaction density between nodes within each group is the highest and the cross-group interaction is the least.

[0020] Optionally, monitoring data includes:

[0021] Network performance indicators: bandwidth, latency, and throughput;

[0022] Security indicators: traffic entropy, encryption protocol compliance;

[0023] Business indicator: task execution status code.

[0024] Optionally, after each edge node collects the monitoring data, it first performs preprocessing operations of data cleaning and normalization, and then sends it to the cloud connection layer.

[0025] Optionally, an artificial intelligence prediction model is constructed based on monitoring data of different indicators. The artificial intelligence prediction model construction method includes:

[0026] Build a database with three partitions, corresponding to network performance indicators, security indicators, and business indicators;

[0027] Collect monitoring data from edge nodes and store them in corresponding partitions according to the type of monitoring data;

[0028] Divide the historical monitoring data in the database into a training set and a test set;

[0029] Use the training set to train different preset machine learning algorithms to generate preliminary prediction models;

[0030] Use the test set to verify and evaluate multiple trained prediction models and select the prediction model with the best performance;

[0031] Three artificial intelligence prediction models suitable for network performance, security and business scenarios were obtained respectively.

[0032] Optionally, the consistency between monitoring data in the same group is evaluated based on an artificial intelligence prediction model. The evaluation process is divided into two stages: edge computing stage and cloud computing stage.

[0033] In the edge computing phase, the cloud connection layer assigns relatively simple evaluation tasks to edge nodes. These evaluation tasks belong to the edge node's group. The edge node is responsible for generating consistency reports and difference values and sending them back to the cloud connection layer. At the same time, the edge node also automatically generates adjustment signals based on the difference values and sends them to other edge nodes related to the task, so that the corresponding terminals can be adjusted immediately.

[0034] In the cloud computing stage, the cloud connection layer centrally handles relatively complex evaluation tasks, specifically those involving security and business levels.

[0035] Optionally, the consistency between monitoring data within the same group can be evaluated based on an AI prediction model. During the evaluation process, the edge nodes and the cloud connection layer jointly participate in the decision-making and control process, specifically including:

[0036] Create a task queue and add all newly arrived tasks to the queue in order;

[0037] The scheduler takes a task from the front of the queue and processes it until the queue is empty;

[0038] Based on the principle of shortest expected execution time of tasks, tasks are assigned to edge nodes for processing first to reduce delays.

[0039] Further optionally, the edge nodes and the cloud connection layer jointly participate in the decision-making and control process. In this process, the execution order is determined according to the priority of the tasks, wherein static priority allocation is pre-set based on the importance and urgency of the tasks.

[0040] In a second aspect, the present invention provides a multi-terminal data transmission detection system based on artificial intelligence, and the technical solutions adopted to solve the above technical problems are as follows:

[0041] An artificial intelligence-based multi-terminal data transmission detection system, based on the artificial intelligence-based multi-terminal data transmission detection method described in the first aspect, wherein its implementation structure includes:

[0042] Cloud connectivity layer;

[0043] Edge nodes: Several edge nodes are connected to the cloud connection layer at one end and to a designated terminal at the other end;

[0044] A grouping unit, configured to logically group edge nodes corresponding to multiple terminals with interaction requirements;

[0045] The monitoring unit is configured on the edge node to monitor the real-time operating status of the terminals connected to it and collect relevant data;

[0046] Artificial intelligence prediction model is used to evaluate the consistency between monitoring data in the same group and obtain the difference value;

[0047] an adjustment signal generating unit, generating an adjustment signal according to the difference value and sending the adjustment signal to the corresponding edge node;

[0048] The control unit is configured on the edge node, receives the adjustment signal, and implements necessary adjustment measures on the corresponding terminal to ensure that the data interaction between the terminals in the group with interactive relationships remains highly consistent.

[0049] Optionally, the construction process of the artificial intelligence prediction model involved includes:

[0050] Build a database with three partitions, corresponding to network performance indicators, security indicators, and business indicators;

[0051] Collect monitoring data from edge nodes and store them in corresponding partitions according to the type of monitoring data;

[0052] Divide the historical monitoring data in the database into a training set and a test set;

[0053] Use the training set to train different preset machine learning algorithms to generate preliminary prediction models;

[0054] Use the test set to verify and evaluate multiple trained prediction models and select the prediction model with the best performance;

[0055] Three artificial intelligence prediction models suitable for network performance, security and business scenarios were obtained respectively.

[0056] The present invention provides an artificial intelligence-based multi-terminal data transmission detection method and system, which has the following beneficial effects compared with the prior art:

[0057] 1. This invention is applicable to the current complex heterogeneous internet environment, where network performance, security, and service indicators of different terminals often vary significantly. By deploying edge nodes to monitor the status of each terminal in real time and using advanced artificial intelligence prediction models to analyze and adjust the collected data, it can effectively monitor and ensure the reliability, consistency, and privacy protection of communication and data exchange between different terminals. This not only improves the stability of the entire heterogeneous internet network, but also ensures normal communication and efficient data exchange between terminals.

[0058] 2. This invention cleverly combines edge computing with cloud computing in the process of real-time monitoring of heterogeneous internet terminals. Edge nodes are responsible for performing some preliminary data processing and simple tasks, while more complex tasks are handled by the cloud connection layer. This approach not only reduces unnecessary data transmission and network load, but also alleviates the computing pressure on the cloud connection layer, thereby significantly shortening data processing time and improving the system's real-time responsiveness and operational efficiency.

[0059] 3. The present invention can dynamically allocate tasks that need to be evaluated to the cloud connection layer or edge nodes. This allocation automatically adjusts the detection cycle based on the real-time load and energy consumption, thereby achieving an optimal balance between load, energy consumption and delayed response. This not only improves the precision and accuracy of the system, but also enhances its real-time performance and further strengthens the stability and reliability of the system. In addition, continuous monitoring and in-depth analysis of terminal devices combined with artificial intelligence technology can significantly improve the overall performance and efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Attachment Figure 1 It is a flow chart of a method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the technical solution, the technical problems solved and the technical effects of the present invention more clear, the technical solution of the present invention is clearly and completely described below in conjunction with specific embodiments.

[0062] Example 1: Refer to the attached Figure 1 This embodiment proposes an artificial intelligence-based multi-terminal data transmission detection method, which includes the following steps:

[0063] S1. Use Kubernetes-based control nodes and edge computing frameworks (such as KubeEdge) to build a cloud connection layer to achieve unified management of cloud and edge nodes.

[0064] Generally speaking, the cloud connection layer needs to integrate the following modules:

[0065] Data synchronization and communication module: supports MQTT / HTTP protocols to ensure real-time data transmission between the cloud and edge nodes, and built-in TLS encryption to ensure communication security;

[0066] AI model deployment and update: Cloud-stored trained network performance, security, and business prediction models are dynamically distributed to edge nodes using containerization technology.

[0067] Elastic resource scheduling: Dynamically allocate computing resources based on edge node load, such as optimizing cloud computing capabilities through Kubernetes automatic scaling mechanisms.

[0068] S2. In the cloud connection layer, several edge nodes are configured, and each edge node is connected to a designated terminal.

[0069] Specifically, each edge node is connected to a designated terminal through a dedicated communication protocol (such as Modbus or OPC UA), which ensures low latency and data integrity. At the same time, a strong password policy (≥12 mixed characters) is set, non-essential services are disabled, security patches are updated regularly, and security is enhanced through Huawei Cloud ECS key login.

[0070] All edge nodes are connected to the cloud connection layer for interaction and data transmission.

[0071] S3. Logically group the edge nodes corresponding to multiple terminals with interaction requirements. The logical grouping process is as follows:

[0072] The cloud connection layer identifies the interaction needs between terminals based on past monitoring data and terminal interaction logs (such as task execution frequency and data traffic patterns).

[0073] Based on the above interaction requirements, a correlation graph is constructed. Each node in the correlation graph represents an edge node, and an edge represents the interaction relationship between the terminals connected by two edge nodes.

[0074] A clustering algorithm is used to group the nodes in the association graph to ensure that the interaction density between nodes within each group is the highest and the cross-group interaction is the least.

[0075] Subsequently, the group-specific AI prediction models constructed later (such as the AI prediction model for network performance, the AI prediction model for security, and the AI prediction model for business scenarios) are sent to the edge nodes, supporting local incremental updates to reduce cloud dependence.

[0076] S4. Each edge node is responsible for monitoring the real-time operating status of the terminals connected to it and collecting monitoring data. The monitoring data includes:

[0077] (1) Network performance indicators: bandwidth, latency, and throughput;

[0078] (2) Security indicators: traffic entropy value, encryption protocol compliance; for traffic entropy value, based on NetFlow data flow statistics, calculate the Shannon entropy value of source IP, destination IP, and port number, and trigger an abnormal alarm when the entropy value suddenly increases (such as exceeding 30% of the baseline); for encryption protocol compliance, parse the SNI (Server Name Indication) and ALPN (Application Layer Protocol Negotiation) fields of TLS traffic to verify whether only TLS 1.2 / 1.3 protocols are allowed. Use a preset whitelist (such as the National Encryption SM2 / SM4 certificate) to check the validity of the certificate chain and reject self-signed or expired certificates;

[0079] (3) Business indicators: task execution status code; for the task execution status code, the business log of the terminal is subscribed through HTTP API polling (interval of 1 second) or WebSocket long connection to extract the status code (such as 200 / success, 500 / server error), and supports custom business status code mapping (such as 0x0A01 means "control instruction execution timeout").

[0080] After each edge node collects the monitoring data, it first performs data cleaning and normalization preprocessing operations before sending it to the cloud connection layer.

[0081] Data cleaning specifically includes: ① Missing value processing: For time series data such as bandwidth and latency, linear interpolation (window size = 3) is used to fill short-term missing values; if the missing period exceeds 5 consecutive cycles, it is marked as "data unavailable" and the terminal is triggered to reconnect; ② Outlier filtering: Based on the Z-score algorithm (threshold |Z| ≥ 3), abnormal data is detected. For example, when the latency suddenly increases (such as jumping from 50ms to 500ms), the abnormal point is discarded and an alarm event is recorded; ③ The business status code is checked for legitimacy (if the non-preset status code is considered invalid), and the terminal log is associated with the source of the error.

[0082] Normalization specifically includes: ① Numerical indicators: Use Min-Max normalization to scale indicators such as bandwidth and latency to the [0,1] range; use logarithmic transformation for skewed distribution data (such as traffic entropy); ② Categorical indicators: One-hot encoding is performed on labels such as encryption protocol compliance; ③ Maintain consistency in the structure and format of each monitoring data in the same group to facilitate subsequent analysis and processing.

[0083] Of course, in actual preprocessing operations, after performing data cleansing and normalization, edge nodes also perform real-time stream processing: using lightweight stream processing engines (such as Apache Kafka Streams or Flink Edge), window aggregation (such as calculating average latency over a 10-second rolling window) and complex event processing (CEP) are implemented at the edge nodes. Furthermore, edge nodes implement resource optimization strategies: a) Data sampling: In high-load scenarios, random sampling (50% sampling rate) is enabled for non-critical metrics (such as historical throughput), using the Bernoulli sampling algorithm to reduce computational overhead; b) Compressed transmission: Preprocessed data is compressed using the LZ4 or Zstandard algorithms, achieving a compression ratio of up to 5:1, reducing the amount of data transmitted to the cloud.

[0084] S5. The cloud connection layer receives all monitoring data from edge nodes, and then evaluates the consistency between the monitoring data in the same group based on the artificial intelligence prediction model to obtain the difference value.

[0085] The artificial intelligence prediction model described in this step is constructed based on the monitoring data of different indicators. The specific construction process includes:

[0086] Build a database with three partitions, corresponding to network performance indicators, security indicators, and business indicators;

[0087] Collect monitoring data from edge nodes and store them in corresponding partitions according to the type of monitoring data;

[0088] Divide the historical monitoring data in the database into a training set and a test set;

[0089] Use the training set to train different preset machine learning algorithms to generate preliminary prediction models;

[0090] Use the test set to verify and evaluate multiple trained prediction models and select the prediction model with the best performance;

[0091] Three artificial intelligence prediction models suitable for network performance, security and business scenarios were obtained respectively.

[0092] Based on different indicators, corresponding AI prediction models are used to evaluate the consistency of monitoring data within the same group, generating a difference value. This evaluation process can be divided into two phases: the edge computing phase and the cloud computing phase. In the edge computing phase, the cloud connectivity layer assigns relatively simple evaluation tasks to edge nodes, assigned to their respective groups. The edge nodes are responsible for generating consistency reports and difference values, and sending them back to the cloud connectivity layer. Simultaneously, the edge nodes automatically generate adjustment signals based on the difference values and send them to other task-related edge nodes for immediate adjustment of the corresponding terminals. In the cloud computing phase, the cloud connectivity layer centrally handles the more complex evaluation tasks, specifically those related to security and business aspects. This approach, in which edge nodes perform some preliminary data processing and simple tasks, while the cloud connectivity layer handles more complex tasks, not only reduces unnecessary data transmission and network load, but also alleviates the computing pressure on the cloud connectivity layer, significantly shortening data processing time and improving the system's real-time responsiveness and operational efficiency.

[0093] It should be added that the consistency between monitoring data within the same group is evaluated based on the artificial intelligence prediction model. During the evaluation process, the edge nodes and the cloud connection layer jointly participate in the decision-making and control process, specifically including:

[0094] Create a task queue and add all newly arrived tasks to the queue in order;

[0095] The scheduler takes a task from the front of the queue and processes it until the queue is empty;

[0096] Based on the principle of shortest expected execution time of tasks, tasks are assigned to edge nodes for processing first to reduce delays.

[0097] Edge nodes and the cloud connection layer jointly participate in the decision-making and control process. During this process, the execution order is determined according to the priority of the tasks. Among them, static priority allocation is pre-set based on the importance and urgency of the tasks.

[0098] S6. The cloud connection layer generates and sends an adjustment signal to the corresponding edge node based on the difference value. Specifically:

[0099] If the bandwidth difference is ≥20% or the delay difference is ≥30ms, dynamic bandwidth allocation or routing optimization policy is triggered;

[0100] A sudden increase in traffic entropy (e.g., Δ≥1.5) triggers traffic cleaning or protocol blocking policies.

[0101] Cryptographic protocol violations (such as SSLv3 detection) trigger a mandatory protocol upgrade policy.

[0102] Continuous status code errors (such as 5xx errors lasting for 10 seconds) trigger task rescheduling or redundant terminal switching strategies.

[0103] For the above strategies, you can set the following strategy priority mechanism:

[0104] Security adjustments (such as protocol blocking) have a priority of P0, network optimization has a priority of P1, and service adjustments have a priority of P2.

[0105] The conflicting strategies generate the final instructions through weighted voting (e.g., security weight = 0.6, network weight = 0.3).

[0106] Transmission Protocol: Based on MQTT 5.0's QoS 2 (Exactly Once) protocol, it guarantees command delivery and supports offline caching (Retain Message). A two-way confirmation process is used: the cloud connection layer sends a command to the edge node, marking it as UNACK. When the edge node responds with an ACK, the command status changes to PROCESSING. Upon completion, a result code (0 = success, 1 = failure) is returned, and the cloud layer updates the status to COMPLETED or FAILED.

[0107] S7. The edge node that receives the adjustment signal adjusts the corresponding terminal according to the instruction to ensure that data interaction between terminals in an interactive relationship within the same group maintains a high degree of consistency.

[0108] Example 2: Based on the artificial intelligence-based multi-terminal data transmission detection method described in Example 1, this example proposes an artificial intelligence-based multi-terminal data transmission detection system, whose implementation structure includes:

[0109] Cloud connectivity layer;

[0110] Edge nodes: Several edge nodes are connected to the cloud connection layer at one end and to a designated terminal at the other end;

[0111] A grouping unit, configured to logically group edge nodes corresponding to multiple terminals with interaction requirements;

[0112] The monitoring unit is configured on the edge node to monitor the real-time operating status of the terminals connected to it and collect relevant data;

[0113] Artificial intelligence prediction model is used to evaluate the consistency between monitoring data in the same group and obtain the difference value;

[0114] an adjustment signal generating unit, generating an adjustment signal according to the difference value and sending the adjustment signal to the corresponding edge node;

[0115] The control unit is configured on the edge node, receives the adjustment signal, and implements necessary adjustment measures on the corresponding terminal to ensure that the data interaction between the terminals in the group with interactive relationships remains highly consistent.

[0116] The control unit at the edge node receives the adjustment signal and implements necessary adjustment measures on the corresponding terminal, which may include:

[0117] 1. Data processing and synchronization: Data correction is performed. If monitoring data indicates discrepancies between terminals within the same group, the control unit will correct the data based on the discrepancies assessed by the AI prediction model. For example, in a multi-sensor monitoring system, if the data collected by some sensor terminals deviates from that of other sensors in the same group, the control unit at the edge node will correct the discrepancies to align them with the normal data within the group.

[0118] 2. In terms of communication optimization, communication frequency adjustment or communication link switching is performed. Specifically, (a) the control unit will adjust the terminal's communication frequency based on the real-time operating status and data interaction of the monitored terminal. If it is found that the data interaction volume of certain terminals is large and the network bandwidth is limited, the control unit may appropriately reduce the communication frequency of some non-critical data to avoid network congestion and ensure that critical data can be transmitted in a timely and accurate manner. For example, in a smart factory, when the operating data transmission volume of production equipment is large, the control unit may reduce the transmission frequency of some equipment status monitoring data to prioritize the stable transmission of production data. (b) If the current communication link is detected to be faulty or unstable, the control unit will promptly switch to a backup communication link. For example, in an IoT application, the edge node originally connects to the terminal via Wi-Fi, but if the Wi-Fi signal is interfered with or interrupted, the control unit will automatically switch the terminal's connection to Bluetooth or other available communication methods to ensure uninterrupted data interaction.

[0119] 3. In terms of terminal device configuration, parameter adjustments are made, or the device is restarted or reset. Specifically, (a) based on monitoring data and system requirements, the control unit may adjust some parameters of the terminal. For example, in an intelligent lighting system, the control unit can adjust the brightness parameters of the lighting terminal according to the ambient light intensity and personnel activities; in a video surveillance system, the resolution parameters of the camera are adjusted according to the image quality and storage capacity to achieve the best operating effect and data interaction quality. (b) When a terminal device fails or is abnormal, resulting in problems with data interaction, the control unit can restart or reset the terminal device. For example, when a smart terminal freezes or has a software failure, the control unit of the edge node can remotely send instructions to restart the terminal device, restore it to normal working state, and ensure that data interaction with other terminals in the group can proceed normally.

[0120] The process of building the artificial intelligence prediction model involved in this embodiment includes:

[0121] Build a database with three partitions, corresponding to network performance indicators, security indicators, and business indicators;

[0122] Collect monitoring data from edge nodes and store them in corresponding partitions according to the type of monitoring data;

[0123] Divide the historical monitoring data in the database into a training set and a test set;

[0124] Use the training set to train different preset machine learning algorithms to generate preliminary prediction models;

[0125] Use the test set to verify and evaluate multiple trained prediction models and select the prediction model with the best performance;

[0126] Three artificial intelligence prediction models suitable for network performance, security and business scenarios were obtained respectively.

[0127] In summary, the artificial intelligence-based multi-terminal data transmission detection method and system of the present invention deploys edge nodes to monitor the status of each terminal in real time, and uses advanced artificial intelligence prediction models to analyze and adjust the collected data. It can effectively monitor and ensure the reliability, consistency and privacy protection of communication and data interaction between different terminals, which not only improves the stability of the entire heterogeneous Internet network, but also ensures normal communication and efficient data exchange between terminals.

[0128] The above specific examples are used to illustrate the principles and implementation methods of the present invention in detail. These examples are only used to help understand the core technical content of the present invention. Based on the above specific embodiments of the present invention, any improvements and modifications made by those skilled in the art without departing from the principles of the present invention should fall within the scope of patent protection of the present invention.

Claims

1. A multi-terminal data transmission detection method based on artificial intelligence, characterized in that: The following steps are involved: Build a cloud connectivity layer; In the cloud connection layer, several edge nodes are configured, each of which is connected to a designated terminal; Logically group the edge nodes corresponding to multiple terminals with interaction requirements; Each edge node is responsible for monitoring the real-time operating status of the terminals connected to it and collecting monitoring data, including: a) network performance indicators: bandwidth, latency, throughput; b) security indicators: traffic entropy, encryption protocol compliance; c) business indicators: task execution status code; The cloud connection layer receives all monitoring data from edge nodes and evaluates the consistency between each monitoring data in the same group based on the artificial intelligence prediction model to obtain the difference value; The cloud connection layer generates and sends adjustment signals to the corresponding edge nodes based on the difference values; The edge node that receives the adjustment signal adjusts the corresponding terminal according to the instruction to ensure that the data interaction between the terminals in the same group that have an interaction relationship remains consistent.

2. The multi-terminal data transmission detection method based on artificial intelligence according to claim 1 is characterized in that: The edge nodes corresponding to multiple terminals with interaction requirements are logically grouped. The logical grouping process is as follows: The cloud connection layer identifies the interaction needs between terminals based on previous monitoring data and terminal interaction logs of each terminal; Based on the above interaction requirements, a correlation graph is constructed. Each node in the correlation graph represents an edge node, and an edge represents the interaction relationship between the terminals connected by two edge nodes. A clustering algorithm is used to group the nodes in the association graph to ensure that the interaction density between nodes within each group is the highest and the cross-group interaction is the least.

3. The multi-terminal data transmission detection method based on artificial intelligence according to claim 1 is characterized in that: After each edge node collects the monitoring data, it first performs data cleaning and normalization preprocessing operations before sending it to the cloud connection layer.

4. The multi-terminal data transmission detection method based on artificial intelligence according to claim 1 is characterized in that: Based on the monitoring data of different indicators, an artificial intelligence prediction model is constructed. The artificial intelligence prediction model construction method includes: Build a database with three partitions, corresponding to network performance indicators, security indicators, and business indicators; Collect monitoring data from edge nodes and store them in corresponding partitions according to the type of monitoring data; Divide the historical monitoring data in the database into a training set and a test set; Use the training set to train different preset machine learning algorithms to generate preliminary prediction models; Use the test set to verify and evaluate multiple trained prediction models and select the prediction model with the best performance; Three artificial intelligence prediction models suitable for network performance, security and business scenarios were obtained respectively.

5. The multi-terminal data transmission detection method based on artificial intelligence according to claim 4 is characterized in that: The consistency between monitoring data within the same group is evaluated based on the artificial intelligence prediction model. The evaluation process is divided into two stages: edge computing stage and cloud computing stage; In the edge computing phase, the cloud connection layer assigns relatively simple evaluation tasks to edge nodes. These evaluation tasks belong to the edge node's group. The edge node is responsible for generating consistency reports and difference values and sending them back to the cloud connection layer. At the same time, the edge node also automatically generates adjustment signals based on the difference values and sends them to other edge nodes related to the task, so that the corresponding terminals can be adjusted immediately. In the cloud computing stage, the cloud connection layer centrally handles relatively complex evaluation tasks, specifically those involving security and business levels.

6. The multi-terminal data transmission detection method based on artificial intelligence according to claim 5 is characterized in that: The consistency between monitoring data within the same group is evaluated based on an AI prediction model. During the evaluation process, edge nodes and the cloud connection layer jointly participate in the decision-making and control process, including: Create a task queue and add all newly arrived tasks to the queue in order; The scheduler takes a task from the front of the queue and processes it until the queue is empty; Based on the principle of shortest expected execution time of tasks, tasks are assigned to edge nodes for processing first to reduce delays.

7. The multi-terminal data transmission detection method based on artificial intelligence according to claim 6 is characterized in that: Edge nodes and the cloud connection layer jointly participate in the decision-making and control process. During this process, the execution order is determined according to the priority of the tasks. Among them, static priority allocation is pre-set based on the importance and urgency of the tasks.

8. A multi-terminal data transmission detection system based on artificial intelligence, characterized in that: An artificial intelligence-based multi-terminal data transmission detection method according to any one of claims 1 to 7, wherein the implementation structure includes: Cloud connectivity layer; Edge nodes: Several edge nodes are connected to the cloud connection layer at one end and to a designated terminal at the other end; A grouping unit, configured to logically group edge nodes corresponding to multiple terminals with interaction requirements; The monitoring unit is configured on the edge node to monitor the real-time operating status of the terminals connected to it and collect relevant data; Artificial intelligence prediction model is used to evaluate the consistency between monitoring data in the same group and obtain the difference value; an adjustment signal generating unit, generating an adjustment signal according to the difference value and sending the adjustment signal to the corresponding edge node; The control unit is configured on the edge node, receives the adjustment signal, and implements adjustment measures on the corresponding terminal to ensure that the data interaction between the terminals in the group that have an interactive relationship remains consistent.

9. The artificial intelligence-based multi-terminal data transmission detection system according to claim 8, characterized in that: The process of building the artificial intelligence prediction model includes: Build a database with three partitions, corresponding to network performance indicators, security indicators, and business indicators; Collect monitoring data from edge nodes and store them in corresponding partitions according to the type of monitoring data; Divide the historical monitoring data in the database into a training set and a test set; Use the training set to train different preset machine learning algorithms to generate preliminary prediction models; Use the test set to verify and evaluate multiple trained prediction models and select the prediction model with the best performance; Three artificial intelligence prediction models suitable for network performance, security and business scenarios were obtained respectively.

Images