Communication transmission optimization method and system based on artificial intelligence

Abstract

The invention relates to the technical field of communication networks, and discloses a communication transmission optimization method and system based on artificial intelligence, and the method comprises the following steps: S1, deploying a computing environment on a cloud server and a network edge node; s2, a sensor is installed at a network key node, and data acquisition is carried out through the Internet of Things technology; s3, performing real-time preprocessing and feature engineering on the acquired data; s4, an appropriate machine learning model is selected according to the task type, and training is carried out on the cloud; s5, deploying and operating the trained model at network edge nodes to perform real-time optimization; s6, realizing global optimization of communication transmission through cross-layer information coordination and decision; and S7, carrying out continuous monitoring and model adjustment on the system. Through cross-layer collaborative optimization, lightweight model deployment and real-time adaptive adjustment, and enhanced data encryption and access control measures, the overall performance, resource utilization efficiency and overall security of a communication network are significantly improved.

Description

Technical Field

[0001] The present invention relates to the field of communication network technology, and in particular to a communication transmission optimization method and system based on artificial intelligence. Background Art

[0002] In modern communication networks, with the rapid growth of data traffic and the increasing diversification of application scenarios, network structure and transmission requirements have become more complex. In order to ensure efficient data transmission and network reliability, communication transmission optimization methods based on artificial intelligence have gradually become key technologies. Artificial intelligence can effectively improve the network's adaptive capabilities, reduce human intervention, and meet the ever-changing network needs by analyzing large amounts of real-time data, predicting changes in network status, and dynamically adjusting transmission strategies.

[0003] Existing communication transmission optimization mainly relies on traditional methods, such as flow control based on preset rules, static routing algorithms, and simple adaptive mechanisms. These methods adjust network configuration and transmission strategies by monitoring specific network indicators (such as latency and bandwidth utilization). For example, load balancing technology distributes traffic to different servers to prevent overload, and flow control protocols reduce network congestion by adjusting data transmission rates.

[0004] Existing communication transmission optimization technologies have some shortcomings. First, there is a lack of effective cross-level coordination mechanisms, and optimization decisions at each network layer are often made in isolation, making it difficult to improve global performance. Second, traditional optimization methods are difficult to dynamically adjust and continuously optimize in the face of real-time changing network environments, resulting in a rapid decline in system performance under changing network conditions. Finally, there is insufficient security protection during data transmission, and a lack of effective encryption and access control measures, which can easily lead to data leakage and security risks. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a communication transmission optimization method and system based on artificial intelligence. The present invention significantly improves the global performance, resource utilization efficiency and overall security of the communication network through cross-layer collaborative optimization, lightweight model deployment and real-time adaptive adjustment, as well as enhanced data encryption and access control measures.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a communication transmission optimization method based on artificial intelligence, comprising the following steps:

[0007] S1, deploy computing environment on cloud servers and network edge nodes;

[0008] S2, install sensors at key network nodes and collect data through Internet of Things technology;

[0009] S3, perform real-time preprocessing and feature engineering on the collected data;

[0010] S4. Select the appropriate machine learning model according to the task type and train it in the cloud;

[0011] S5. Deploy and run the trained model at the network edge nodes for real-time optimization.

[0012] S6, achieve global optimization of communication transmission through cross-layer information coordination and decision-making;

[0013] S7, continuously monitor the system and adjust the model;

[0014] S8. Implement data security and privacy protection.

[0015] Preferably, the S1 comprises:

[0016] S11. Install and configure Hadoop and Spark clusters on cloud servers to support large-scale data processing;

[0017] S12. Install Docker on network edge nodes and deploy lightweight containerized applications to process real-time data.

[0018] Preferably, S2 includes:

[0019] S21. Select sensors with environmental data collection functions, including temperature, humidity and signal strength sensors;

[0020] S22. Use the MQTT protocol to transmit sensor data to the data processing platform in real time.

[0021] Preferably, S3 includes:

[0022] S31. Use Apache Kafka to process sensor data streams to ensure data real-time and reliability;

[0023] S32. Use Spark for data preprocessing, including data cleaning and standardization;

[0024] S33. Input the preprocessed data into the feature engineering module to extract key features of network performance.

[0025] Preferably, S4 includes:

[0026] S41. For time series prediction tasks, choose long short-term memory network;

[0027] S42. For classification tasks, select random forest and convolutional neural network;

[0028] S43. For unsupervised tasks, select the K-means clustering algorithm;

[0029] S44. For dynamic decision-making tasks, choose a deep Q network;

[0030] S45. Use the TensorFlow framework to train and verify the selected model on the cloud server.

[0031] Preferably, S5 includes:

[0032] S51. Deploy the trained model on the network edge node and use ONNX Runt ime to perform lightweight operation of the model.

[0033] S52. Monitor the model performance of edge nodes in real time and dynamically update the model according to network conditions.

[0034] Preferably, S6 includes:

[0035] S61. By developing cross-layer protocols, the physical layer, link layer, and network layer share key network performance information;

[0036] S62. Apply multi-criteria decision analysis methods to comprehensively evaluate data and indicators at different levels and optimize communication paths and resource allocation.

[0037] Preferably, the S7 includes:

[0038] S71. Use the Grafana platform to monitor system performance indicators in real time, including latency, bandwidth utilization, and bit error rate;

[0039] S72. Based on monitoring data, use online learning technology to continuously adjust and optimize the model.

[0040] Preferably, the S8 includes:

[0041] S81. Use SSL / TLS protocol to encrypt data during data transmission;

[0042] S82. Ensure data and system security through role-based access control systems.

[0043] The present invention also provides a communication transmission optimization system based on artificial intelligence, comprising:

[0044] Cloud servers for large-scale data processing and model training;

[0045] Network edge nodes for real-time data processing and model deployment;

[0046] Sensors, used to collect network environment data;

[0047] Data processing platform, used for real-time data preprocessing and feature extraction;

[0048] Optimize model modules for deploying and running machine learning models for different task types;

[0049] Monitoring module, used to monitor network performance indicators in real time and adjust the model;

[0050] Security module for encryption during data transmission and ensuring system security through access control.

[0051] The present invention provides a communication transmission optimization method and system based on artificial intelligence.

[0052] Beneficial effects:

[0053] 1. The present invention realizes information sharing and collaborative optimization among the physical layer, link layer and network layer by adopting a cross-layer protocol and a multi-standard decision analysis method, thereby significantly improving the global performance and resource utilization efficiency of the communication network.

[0054] 2. The present invention realizes real-time optimization and adaptive adjustment of communication transmission by deploying lightweight models in the cloud and edge nodes and combining real-time monitoring and online learning technologies, so that the model can dynamically adapt to network changes and ensure the continuous and efficient operation of the system.

[0055] 3. The present invention strengthens the security of data transmission and access management of system resources through SSL / TLS encryption protocol and role-based access control system, enhances network security, reduces data risks, and thus improves the overall security protection capability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 is a flow chart of the method of the present invention;

[0057] Figure 2 It is a system structure diagram of the present invention. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the specification 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.

[0059] Please see attached Figure 1 The embodiment of the present invention provides a communication transmission optimization method and system based on artificial intelligence, comprising the following steps:

[0060] S1. Deploy computing environments on cloud servers and network edge nodes. The deployment of a collaborative computing environment between the cloud and the edge can effectively improve the efficiency and speed of data processing, reduce network latency, and optimize the overall system responsiveness. At the same time, the powerful computing power of the cloud can process large-scale data, while edge computing can effectively share the computing load and avoid network congestion.

[0061] S2. Install sensors at key network nodes and collect data through the Internet of Things technology. By installing sensors and using the Internet of Things technology, key environmental and network data can be obtained in real time, providing a basis for subsequent data processing and optimization. These real-time data provide a basis for dynamic adjustment of the system, which helps to achieve more accurate optimization;

[0062] S3. Real-time preprocessing and feature engineering of collected data can significantly improve data quality and model prediction capabilities. The key features extracted by feature engineering provide more representative data input for the training of machine learning models, improving the accuracy and robustness of the models.

[0063] S4. Select appropriate machine learning models according to the task type and train them in the cloud. Selecting appropriate machine learning models according to the task type can ensure that the system's optimization effect is maximized in different application scenarios. Through large-scale training in the cloud, the model can learn more complex patterns, thereby improving the accuracy and reliability of predictions and decisions.

[0064] S5. Deploy and run the trained model at the edge of the network for real-time optimization. Deploying the model at the edge of the network can reduce the delay of data transmission and achieve real-time optimization. By dynamically adjusting the network configuration, the system can quickly respond to changes in network status, thereby improving the stability and efficiency of communication;

[0065] S6. Global optimization of communication transmission is achieved through cross-layer information coordination and decision-making. Through cross-layer information sharing and comprehensive decision-making, global optimization strategies can be implemented to avoid local optimality. The system can make more comprehensive decisions based on information at different levels, thereby improving the overall performance of communication;

[0066] S7. Continuously monitor the system and adjust the model. Through continuous monitoring and dynamic adjustment, it can maintain efficient operation, respond to changes in network status in a timely manner, and ensure the continued effectiveness of the model;

[0067] S8. Implement data security and privacy protection. By implementing comprehensive data security and privacy protection measures, the system can not only ensure the security of data during transmission, but also protect user privacy, and effectively reduce potential security vulnerabilities and enhance the overall security of the system.

[0068] Please see attached Figure 1 In a preferred embodiment of the present invention, S1 includes:

[0069] S11. Install and configure Hadoop and Spark clusters on cloud servers to support large-scale data processing. Hadoop provides powerful distributed data storage capabilities and can manage massive amounts of data, while Spark achieves efficient data processing through in-memory computing. This combination can process and analyze massive amounts of data generated in the network, thereby providing reliable data support for subsequent machine learning model training and real-time optimization. It can also efficiently process and analyze large-scale network data, ensuring the speed and accuracy of data processing, and providing a high-quality data foundation for the optimization model. At the same time, it enhances the scalability and fault tolerance of the system, enabling it to adapt to the rapid growth of data scale in the network environment;

[0070] S12. Install Docker on the network edge nodes and deploy lightweight containerized applications to process real-time data. Docker provides a highly portable and isolated operating environment through containerization technology, allowing applications on edge nodes to be quickly deployed and run. By using Docker to deploy containerized applications on edge nodes, the system can process data as soon as it is generated, thereby significantly reducing latency and improving real-time performance. At the same time, containerization technology ensures the consistency and portability of applications, simplifies the operation and management of edge nodes, and helps to quickly respond to and adapt to different network environments.

[0071] Please see attached Figure 1 In a preferred embodiment of the present invention, S2 includes:

[0072] S21. Select sensors with environmental data collection functions, including temperature, humidity and signal strength sensors. By deploying sensors, key data of these environments and network status can be obtained in real time, helping to identify and predict possible failure points or reasons for performance degradation. At the same time, environmental factors and signal quality that affect network performance are monitored in real time, thereby providing key basic data for optimizing communication transmission. This real-time monitoring helps to detect potential problems in advance and avoid network performance degradation or interruption caused by environmental or signal problems;

[0073] S22. Use the MQTT protocol to transmit sensor data to the data processing platform in real time. The MQTT protocol is suitable for real-time data transmission in the IoT environment due to its low bandwidth usage and efficient message transmission mechanism. Using the MQTT protocol to achieve real-time transmission of sensor data not only ensures data transmission efficiency and reliability, but also reduces network bandwidth consumption. This transmission method ensures that sensor data can reach the data processing platform in a timely manner, so that the system can quickly respond to changes in the environment and network status, and provide real-time communication transmission optimization.

[0074] Please see attached Figure 1 In a preferred embodiment of the present invention, S3 includes:

[0075] S31. Use Apache Kafka to process sensor data streams to ensure data real-time and reliability. Apache Kafka can achieve efficient data stream processing through its distributed architecture and publish / subscribe model. Kafka's high availability and fault-tolerant design ensure the reliability of data in network transmission. Even if some nodes fail, the system can continue to process data. This method not only improves the efficiency of data stream processing, but also enhances the stability and scalability of the system when facing large-scale data streams, ensuring the continuity of subsequent data processing and analysis;

[0076] S32. Use Spark for data preprocessing, including data cleaning and standardization. Data cleaning ensures the integrity and accuracy of the data set by removing or correcting invalid data. Data standardization maps data to a unified dimension or range, allowing subsequent processing steps to be more efficient and avoiding model bias caused by data scale differences. This preprocessing process provides high-quality input data for subsequent data analysis and model training, thereby improving the overall prediction and optimization performance of the system;

[0077] S33. Input the preprocessed data into the feature engineering module to extract key features of network performance. Feature engineering can significantly improve the prediction ability of the model by extracting and selecting meaningful features. Sliding window technology and aggregation operations can capture local and global change patterns of data, while dimensionality reduction technology improves computing efficiency and model generalization ability by reducing feature dimensions. These features provide key inputs for subsequent machine learning model training and improve the model's adaptability to complex network environments, thereby achieving more accurate communication transmission optimization.

[0078] Please see attached Figure 1 In a preferred embodiment of the present invention, S4 includes:

[0079] S41. For time series prediction tasks, choose the long short-term memory network. The long short-term memory network can effectively predict future network states and trends by capturing long-term dependencies in time series. The gate mechanism of the model allows it to selectively remember or forget certain information during training, thereby improving the accuracy and stability of predictions. By using the long short-term memory network model, the system can accurately predict the changing trends of network traffic and other time series data, thereby identifying potential network bottlenecks and problems in advance. This early warning function can effectively improve the reliability and operation efficiency of the network;

[0080] S42. For classification tasks, select random forest and convolutional neural network. Random forest reduces the overfitting problem that may occur in a single model by integrating the results of multiple decision trees, thereby improving the accuracy of classification. Convolutional neural network can effectively identify different categories of patterns in complex data sets by extracting and combining data features layer by layer. Using random forest or convolutional neural network for classification tasks, the system can efficiently and accurately identify different types of network traffic or detect abnormal behavior, thereby achieving rapid response and security protection of the network. The classification results provide a reliable basis for subsequent network optimization and security strategies;

[0081] S43. For unsupervised tasks, the K-means clustering algorithm is selected. K-means can effectively divide the data set into several clusters by minimizing the distance between the data point and the center of the cluster to which it belongs. This clustering method can reveal the inherent structure of the data in the data set without clear labels, help identify the potential patterns in the data, and provide a basis for further network optimization, such as adjusting bandwidth allocation according to user behavior or identifying abnormal traffic patterns to enhance network security;

[0082] S44. For dynamic decision-making tasks, choose deep Q network. Deep Q network can handle complex state space and decision problems by combining Q-learning algorithm in reinforcement learning with neural network. The model continuously optimizes its strategy through repeated trials and feedback learning to make the best decision in a dynamic environment, so that it can optimize resource allocation and routing selection in real time in a constantly changing network environment, thereby improving the overall performance and stability of the network, reducing human intervention, and improving the efficiency of network management;

[0083] S45. Use the TensorFlow framework to train and verify the selected model on the cloud server. TensorFlow enables the model training process to be carried out quickly on large-scale data sets through its efficient computational graph and automatic differentiation mechanism. Using TensorFlow to train and verify the model on the cloud server, the system can quickly build a high-performance machine learning model and ensure its robustness and accuracy in practical applications. This method greatly shortens the model development cycle, enables the system to quickly respond to changes in the network environment, and provides continuous optimization capabilities.

[0084] Please see attached Figure 1 In a preferred embodiment of the present invention, S5 includes:

[0085] S51. Deploy the trained model on the edge node of the network and use ONNX Runt ime to run the model in a lightweight manner. ONNX Runt ime can provide fast and low-power model inference services on the edge node by optimizing the operating efficiency of the neural network model. ONNX format models are highly compatible and can be exported and inferred from multiple different deep learning frameworks, which makes it easier to deploy models on various hardware platforms, thereby enabling real-time decision-making and optimization close to the data source and reducing data transmission delays. This not only improves the efficiency of model inference, but also enhances the system's response speed and overall performance;

[0086] S52. Monitor the model performance of edge nodes in real time and dynamically update the model according to the network status. Through real-time monitoring, the system can timely capture the changes in model performance and take corresponding adjustment measures. The mechanism of real-time monitoring and dynamic model update ensures the stability and efficiency of the system in long-term operation. The system can quickly adapt and adjust the optimization strategy according to the changes in network conditions, so as to continuously provide high-quality communication transmission optimization services. This adaptive capability greatly reduces the need for human intervention and improves the automation and intelligence level of the system.

[0087] Please see attached Figure 1 In a preferred embodiment of the present invention, S6 includes:

[0088] S61. By developing a cross-layer protocol, the physical layer, link layer, and network layer share key network performance information. The cross-layer protocol breaks the information barriers in the network layer model by establishing a unified communication interface and data exchange mechanism, so that the physical layer, link layer, and network layer can be optimized collaboratively. This information sharing mechanism helps each layer consider the global network status when making local optimization decisions, thereby avoiding conflicts and inefficiencies that may be caused by independent optimization of each layer, thereby improving the overall performance and resource utilization of the network and avoiding the local optimality problem that may be caused by single-layer optimization;

[0089] S62. Apply multi-standard decision analysis methods to comprehensively evaluate data and indicators at different levels, optimize communication paths and resource allocation. After obtaining support for cross-layer information sharing, apply multi-standard decision analysis methods to comprehensively evaluate different data and indicators from the physical layer, link layer and network layer. The multi-standard decision analysis method can select the optimal solution in complex decision-making scenarios by weighting and comprehensively evaluating multiple indicators. It can balance multiple optimization goals, such as the trade-off between low latency and high bandwidth utilization, to ensure that the decision is not only optimal in a single indicator, but also achieves a good balance in the global effect. This method ensures the comprehensiveness and rationality of communication path selection and resource allocation decisions, improves the utilization efficiency of network resources, and enhances the adaptability and stability of the network, so that the system can continuously optimize performance under different network conditions.

[0090] Please see attached Figure 1 In a preferred embodiment of the present invention, S7 includes:

[0091] S71. Use the Grafana platform to monitor the system's performance indicators in real time, including latency, bandwidth utilization, and bit error rate. In order to ensure the continued effective operation of the communication transmission optimization system, use the Grafana platform to monitor the system's key performance indicators in real time. Grafana visualizes the performance data collected in real time, allowing system administrators to monitor and evaluate the network's operating status in a timely manner. By monitoring key indicators such as latency, bandwidth utilization, and bit error rate, network performance problems can be quickly located, and necessary adjustments or optimizations can be made based on the monitoring data, so that the system can continuously track and evaluate network performance and ensure the effectiveness and reliability of communication transmission optimization. Real-time visualization helps to quickly identify potential network bottlenecks or failures, and provides data support for subsequent automatic optimization and manual intervention, improving the stability and operating efficiency of the system;

[0092] S72. Based on monitoring data, the system uses online learning technology to continuously adjust and optimize the model. With the support of real-time monitoring data, the system further uses online learning technology to continuously adjust and optimize the deployed machine learning model. Online learning is a machine learning method that allows the model to continuously update parameters when acquiring new data without retraining the entire model. Online learning technology allows machine learning models to continue to adapt to new data and new environments after deployment. By gradually updating model parameters, the system can cope with dynamic changes in the network environment and maintain the model's predictive ability and optimization effect. This continuous adjustment capability reduces the frequency of retraining the model, reduces operation and maintenance costs, and improves the system's response speed to a changing environment, allowing communication transmission optimization to continue to remain efficient and stable.

[0093] Please see attached Figure 1 In a preferred embodiment of the present invention, S8 includes:

[0094] S81. Apply SSL / TLS protocol for encryption during data transmission. By applying SSL / TLS protocol during data transmission, the system can effectively prevent data leakage and attacks, and ensure the security of sensitive information when it is transmitted on the network. The implementation of encryption mechanism not only protects user privacy, but also enhances the overall security of the system and prevents potential security threats from affecting network communications;

[0095] S82. Ensure data and system security through a role-based access control system. To further enhance system security, a role-based access control system is used to manage access rights to data and system resources. An access control system is an access control mechanism that assigns permissions based on user roles rather than managing permissions directly based on user identities. By binding access rights to user roles, the access control system simplifies the permission management process and avoids complex direct user permission allocation, thereby effectively controlling access rights to data and resources and preventing unauthorized access and operations. This permission management mechanism ensures system security and data confidentiality, especially in a multi-user environment, which can significantly reduce internal threats and security vulnerabilities and enhance the overall protection capabilities of the system.

[0096] The artificial intelligence-based communication transmission optimization system described below and the artificial intelligence-based communication transmission optimization method described above can refer to each other.

[0097] Please see attached Figure 2 The present invention also provides a communication transmission optimization system based on artificial intelligence, comprising:

[0098] Cloud servers for large-scale data processing and model training;

[0099] Network edge nodes for real-time data processing and model deployment;

[0100] Sensors, used to collect network environment data;

[0101] Data processing platform, used for real-time data preprocessing and feature extraction;

[0102] Optimize model modules for deploying and running machine learning models for different task types;

[0103] Monitoring module, used to monitor network performance indicators in real time and adjust the model;

[0104] Security module for encryption during data transmission and ensuring system security through access control.

[0105] The present method embodiment can be used to execute the above-mentioned system embodiment, and its principle and technical effect are similar, which will not be described in detail here.

[0106] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A communication transmission optimization method based on artificial intelligence, characterized in that: The following steps are involved: S1, deploy computing environment on cloud servers and network edge nodes; S2, install sensors at key network nodes and collect data through Internet of Things technology; S3, perform real-time preprocessing and feature engineering on the collected data; S4. Select the appropriate machine learning model according to the task type and train it in the cloud; S5. Deploy and run the trained model at the network edge nodes for real-time optimization. S6, achieve global optimization of communication transmission through cross-layer information coordination and decision-making; S7, continuously monitor the system and adjust the model; S8. Implement data security and privacy protection.

2. The communication transmission optimization method based on artificial intelligence according to claim 1, characterized in that: The S1 includes: S11. Install and configure Hadoop and Spark clusters on cloud servers to support large-scale data processing; S12. Install Docker on network edge nodes and deploy lightweight containerized applications to process real-time data.

3. The communication transmission optimization method based on artificial intelligence according to claim 1, characterized in that: The S2 includes: S21. Select sensors with environmental data collection functions, including temperature, humidity and signal strength sensors; S22. Use the MQTT protocol to transmit sensor data to the data processing platform in real time.

4. The method for optimizing communication transmission based on artificial intelligence according to claim 1, characterized in that: The S3 includes: S31. Use Apache Kafka to process sensor data streams to ensure data real-time and reliability; S32. Use Spark for data preprocessing, including data cleaning and standardization; S33. Input the preprocessed data into the feature engineering module to extract key features of network performance.

5. The communication transmission optimization method based on artificial intelligence according to claim 1 is characterized in that: The S4 includes: S41. For time series prediction tasks, choose long short-term memory network; S42. For classification tasks, select random forest and convolutional neural network; S43. For unsupervised tasks, select the K-means clustering algorithm; S44. For dynamic decision-making tasks, choose a deep Q network; S45. Use the TensorFlow framework to train and validate the selected model on the cloud server.

6. The communication transmission optimization method based on artificial intelligence according to claim 1 is characterized in that: The S5 includes: S51. Deploy the trained model on the network edge nodes and use ONNXRuntime to run the model in a lightweight manner. S52. Monitor the model performance of edge nodes in real time and dynamically update the model according to network conditions.

7. The communication transmission optimization method based on artificial intelligence according to claim 1 is characterized in that: The S6 includes: S61. By developing cross-layer protocols, the physical layer, link layer, and network layer share key network performance information; S62. Apply multi-criteria decision analysis methods to comprehensively evaluate data and indicators at different levels and optimize communication paths and resource allocation.

8. The communication transmission optimization method based on artificial intelligence according to claim 1 is characterized in that: The S7 includes: S71. Use the Grafana platform to monitor system performance indicators in real time, including latency, bandwidth utilization, and bit error rate; S72. Based on monitoring data, use online learning technology to continuously adjust and optimize the model.

9. The communication transmission optimization method based on artificial intelligence according to claim 1, characterized in that: The S8 includes: S81. Use SSL / TLS protocol to encrypt data during data transmission; S82. Ensure data and system security through role-based access control systems.

10. A communication transmission optimization system based on artificial intelligence, characterized in that: A communication transmission optimization method based on artificial intelligence according to any one of claims 1 to 9, comprising: Cloud servers for large-scale data processing and model training; Network edge nodes for real-time data processing and model deployment; Sensors, used to collect network environment data; Data processing platform, used for real-time data preprocessing and feature extraction; Optimize model modules for deploying and running machine learning models for different task types; Monitoring module, used to monitor network performance indicators in real time and adjust the model; Security module for encryption during data transmission and ensuring system security through access control.

Images