A 5G network intelligent switching management method based on artificial intelligence

Abstract

The present invention provides an artificial intelligence-based 5G network intelligent switching management method, comprising the following steps: collecting and processing network-related data to obtain a network data set; constructing a switching demand prediction model for predicting network switching time and target, and a switching effect prediction model for predicting network performance after switching; optimizing the initial switching strategy using reinforcement learning to obtain the optimal switching strategy; deploying a network switching engine model on an edge computing node, and adjusting the optimal switching strategy in real time according to changes in the network environment; constructing a virtual simulated digital environment for network simulation, evaluating the optimal switching strategy based on the simulated virtual network environment, and then optimizing the network switching engine model in real time based on the evaluation results. The present invention not only realizes intelligent switching decision-making, but also improves the accuracy and efficiency of switching decisions, enhances network adaptability and diversified needs, and improves user experience.

Description

Technical Field

[0001] The present invention relates to the field of network management technology, and in particular to an artificial intelligence-based 5G network intelligent switching management method. Background Art

[0002] In 5G networks, handover management is a key mechanism to ensure that user equipment (UE) maintains continuous connection when moving between different base stations. Existing handover management methods include but are not limited to: 1) When the user equipment detects that the signal strength of the neighboring base station exceeds the signal strength of the current base station, the handover is triggered. However, this may lead to a ping-pong effect, that is, the device frequently switches between two base stations, affecting the stability of the connection. 2) Handover is performed based on the distance between the user equipment and the base station, usually combined with the signal strength. However, considering only the distance may not be accurate because the signal quality is also affected by other factors (such as interference and obstacles). 3) Applicable to user equipment moving at high speeds, the handover timing is optimized by predicting its moving path and speed. The process requires accurate speed and path prediction, and errors will cause unnecessary switching or delays. Summary of the Invention

[0003] In order to overcome the shortcomings of the existing technology, the purpose of the present invention is to provide a 5G network intelligent switching management method based on artificial intelligence, which not only realizes intelligent switching decision-making, but also improves the accuracy and efficiency of switching decisions, enhances network adaptability and diversified needs, and improves user experience.

[0004] To achieve the above objectives, the present invention provides the following solution: a 5G network intelligent switching management method based on artificial intelligence, comprising the following steps:

[0005] Collecting network-related data and preprocessing the network-related data to obtain a network data set;

[0006] Using the network data set to construct a switching demand prediction model for predicting network switching time and target and a switching effect prediction model for predicting network performance after switching;

[0007] Formulate an initial switching strategy based on the constructed model, and optimize the initial switching strategy with reinforcement learning to obtain the optimal switching strategy;

[0008] Deploy a network switching engine model on the edge computing node and adjust the optimal switching strategy in real time according to changes in the network environment;

[0009] A virtual simulated digital environment is constructed to perform network simulation, the optimal switching strategy is evaluated based on the simulated virtual network environment, and then the network switching engine model is optimized in real time based on the evaluation result.

[0010] Optionally, the network-related data includes channel quality indicators, mobility data, network topology data, historical switching data, user behavior data, and environmental data;

[0011] The channel quality indicator is obtained from the channel quality information reported by the user equipment, the mobile data includes user location, speed, acceleration and moving direction, the network topology data includes base station location, coverage, adjacency and base station load, the historical switching data includes switching events, switching success rate, switching failure reasons and switching delay, the user behavior data includes user application type, traffic pattern, service quality requirements, and the environmental data includes weather conditions, geographical obstacle information and road traffic information.

[0012] Optionally, collecting network-related data and preprocessing the network-related data to obtain a network dataset includes:

[0013] Collect network-related data, perform denoising, anomaly detection, and missing data filling on the network data to obtain an initial data set;

[0014] Dividing the initial data set into two types: continuous values ​​and discrete values, selecting different data normalization methods for different data types, and completing the normalization operation of the initial data set;

[0015] Based on the normalized initial data set, calculating the time series characteristics of the signal strength, identifying the periodic pattern of the time series characteristics, obtaining a time series analysis result, constructing the interaction characteristics and statistical characteristics of the user equipment and the network base station based on the time series analysis result, and then using a feature selection algorithm to extract features to obtain relevant feature data;

[0016] The handover events in the initial data set are identified in combination with the relevant feature data, and the identified handover events are classified and labeled to complete the preprocessing of the network-related data.

[0017] Optionally, using the network dataset to construct a handover demand prediction model for predicting network handover time and target includes:

[0018] Extracting current and historical signal quality, user equipment mobility pattern, base station status, and environmental information from the relevant feature data, and organizing the extracted data into a time series data structure to obtain a first training data set;

[0019] An LSTM network is used to capture the temporal dependencies of channel quality, user mobility, and environmental characteristics to obtain a time series model. The sliding window technique is then used to input the first training dataset into the time series model for training, thereby learning and predicting the future state of network usage and determining the timing of network switching.

[0020] Constructing a graph neural network model based on the network topology structure, inputting the first training data set into the graph neural network model to obtain status and relationship changes of neighboring base stations; wherein each node in the graph neural network model represents a base station, and each edge represents a connection relationship between base stations;

[0021] Deploy and integrate the time series model and the graph neural network model to obtain a switching demand prediction model, use the switching demand prediction model to predict real-time data, and obtain the network switching time and the switching target base station.

[0022] Optionally, using the network dataset to construct a handover effect prediction model for predicting post-handover network performance includes:

[0023] Extracting base station features, connection device requirements, and overall network status from the relevant feature data, and integrating the extracted data into a second training data set;

[0024] Constructing a multilayer perceptron, introducing residual connections and batch normalization into the multilayer perceptron to obtain a deep neural network, training the deep neural network using the second training data set, and integrating a random forest and a gradient boosting tree into the deep learning network to obtain a deep learning model;

[0025] The deep learning model is trained using the network performance data after the switch to predict and evaluate the performance indicator trend of the network after the switch.

[0026] Optionally, an initial switching strategy is formulated based on the constructed prediction model, and the initial switching strategy is optimized by combining reinforcement learning to obtain an optimal switching strategy, including:

[0027] Acquire and integrate the current network state, user state, and environment state to obtain state information, encode the state information into a fixed-length feature vector, obtain a state representation, and complete the state definition;

[0028] Define the discrete action space and continuous action space after network switching, and define the immediate reward and long-term reward after network switching;

[0029] Integrate the defined states, actions, and rewards to obtain a reinforcement learning framework;

[0030] Continuously training the reinforcement learning framework using the initial data set to obtain a strategy model, and optimizing the initial switching strategy output by the prediction model using the strategy model to obtain an optimal switching strategy;

[0031] The policy model is deployed in access network and core network nodes to perform real-time online decision making.

[0032] Optionally, a network switching engine model is deployed on the edge computing node, and the optimal switching strategy is adjusted in real time according to changes in the network environment, including:

[0033] Selecting a lightweight model, and performing model compression and containerization operations on the lightweight model to obtain a network switching engine model;

[0034] The initial data set is input into the network handover engine model, and the network handover operation priority and target base station recommendation are output to perform real-time adjustment of the optimal handover strategy.

[0035] Optionally, constructing a virtual simulated digital environment to perform network simulation, evaluating the optimal switching strategy based on the simulated virtual network environment, and then optimizing the network switching engine model in real time based on the evaluation results, including:

[0036] Use physical simulation tools to simulate network infrastructure, signal interference, and user mobility, and then use simulation tools to integrate real user behavior patterns to perform network simulation;

[0037] Selecting a digital twin as a strategy testing platform and introducing a multi-dimensional simulation matrix into the strategy testing platform to evaluate the optimal switching strategy;

[0038] The network switching engine model is calibrated and the optimal switching strategy is adjusted according to the evaluation result of the optimal switching strategy.

[0039] The present invention provides an artificial intelligence-based 5G network intelligent switching management method, which discloses the following technical effects:

[0040] 1. High handover decision accuracy: By building a handover demand prediction model, we can predict when a handover is needed and which target base station to switch to. By building a handover effect prediction model, we can predict post-handover network performance, such as throughput, latency, and signal strength. Furthermore, by combining diverse approaches such as time series models, graph neural networks, and deep neural networks, the prediction model effectively captures temporal and spatial characteristics and the complex relationships between them, improving the quality of intelligent handover decisions in dynamic 5G network environments. This intelligent and innovative approach to data processing and predictive modeling ensures continuous optimization of network performance and user experience.

[0041] 2. Strong handover strategy stability: By integrating reinforcement learning, it can learn optimal handover strategies, balancing immediate benefits (such as network performance) with long-term benefits (such as overall network health and user experience). It also enables 5G network handover management to dynamically adapt to complex and changing network environments, implementing adaptive, intelligently optimized handover strategies. This significantly improves the accuracy and efficiency of 5G network handover decisions, ultimately enhancing user experience and network resource utilization.

[0042] 3. High switching decision efficiency: By deploying a lightweight network switching engine model, real-time adjustment of the optimal switching strategy is achieved. At the same time, model compression technologies (such as knowledge distillation and quantization) are used in model design to ensure efficient model operation. Containerization using Docker or Kubernetes facilitates management and expansion, greatly improving the switching decision efficiency and response speed.

[0043] 4. Continuous optimization: By building a virtual environment, policy evaluation can be performed to estimate the impact on throughput, latency, user feedback, etc., and achieve continuous optimization of switching strategies.

[0044] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 A schematic diagram of a method flow chart provided in an embodiment of the present invention;

[0047] Figure 2 A schematic diagram of a process for constructing a prediction model according to an embodiment of the present invention;

[0048] Figure 3 A schematic diagram of the network switching management process provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0050] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0051] like Figure 1-3 As shown, the present invention provides a 5G network intelligent switching management method based on artificial intelligence, comprising the following steps:

[0052] 1. Collect network-related data and pre-process the network-related data to obtain a network dataset.

[0053] 1.1 Network-related data collection

[0054] Channel Quality Index (CQI): This collects channel quality information reported by user equipment (UE). User equipment (UE) periodically reports CQIs to the base station. These CQIs reflect the current state of the wireless channel. The base station monitors CQIs in real time through physical layer signal measurements to ensure data timeliness. The base station aggregates CQI data from multiple UEs to provide a comprehensive view of regional channel quality.

[0055] Mobility data: This includes user location, speed, acceleration, and direction of movement. This data is obtained using technologies such as GPS, Wi-Fi positioning, and Bluetooth beacons. The device's built-in sensors, such as the accelerometer and gyroscope, are used to obtain speed, acceleration, and direction of movement. The user's movement path and speed are inferred by analyzing changes in signal strength.

[0056] Network topology data: Base station location, coverage, adjacency, and load. Base stations automatically discover neighboring base stations and update adjacency relationships through the SON function. Base station location, coverage, and load information are regularly obtained from the Network Management System (NMS). Base station load is monitored in real time, identifying high- and low-load areas.

[0057] Historical switching data: past switching events, success rates, failure reasons, switching delays, etc. Storing historical switching data in a data warehouse facilitates subsequent analysis and model training.

[0058] User behavior data: User application types, traffic patterns, and service quality requirements. Deep packet inspection (DPI) technology is used to identify user application types and traffic patterns. Real-time monitoring of user service quality requirements, such as bandwidth, latency, and jitter, is performed. Based on historical user behavior data, user profiles are constructed to predict future needs.

[0059] Environmental data: such as weather conditions, geographic obstacles, and road traffic. Real-time weather conditions are obtained through interfaces with meteorological service providers. GIS data is used to identify geographic obstacles and road traffic conditions. Drones are used to monitor the environment in specific areas and obtain real-time geographic and traffic information.

[0060] 1.2 Preprocess the network-related data to obtain a network dataset

[0061] 1.21 Collect network-related data, perform denoising, anomaly detection, and missing data filling on the network data to obtain an initial data set.

[0062] 1) Denoising method: Use a low-pass filter to filter out high-frequency noise in signal transmission and retain useful low-frequency information.

[0063] 2) Statistical methods: Use statistical indicators such as mean and median to identify and remove abnormal data points.

[0064] 3) Anomaly Detection

[0065] IQR (interquartile range) method: By calculating the interquartile range of the data, we can identify and eliminate significantly deviated large and small values.

[0066] Machine learning methods: such as the Isolation Forest model, automatically detect abnormal data.

[0067] 4) Filling in missing data:

[0068] Interpolation method: Use linear interpolation and Lagrange interpolation methods to fill missing data.

[0069] Regression imputation: Predict missing values ​​using a simple regression model.

[0070] Multiple imputation: Fill in the gaps by training multiple models fusion results.

[0071] 1.22 Divide the initial dataset into two types: continuous values ​​and discrete values. Select different data normalization methods for different data types to complete the standardization operation of the initial dataset. For example, normalization and standardization are used for continuous values, and one-hot encoding or binarization is used for discrete values.

[0072] 1.23 Based on the normalized initial data set, calculate the time series characteristics of the signal strength, identify the periodic patterns of the time series characteristics, and obtain time series analysis results. Based on the time series analysis results, construct interaction characteristics and statistical characteristics of the user equipment and the network base station, and then use a feature selection algorithm to extract features to obtain relevant feature data.

[0073] Time series analysis: Calculates time series characteristics such as signal strength trends and volatility (e.g., standard deviation). Identifies periodic patterns (e.g., short-lived load peaks) to predict switching needs.

[0074] Interaction feature construction: Generate interaction features such as signal-to-noise ratio (SNR) and coverage overlap rate based on the association data between devices and base stations.

[0075] Statistical features: Features such as maximum value, minimum value, mean, variance, kurtosis, and skewness can be used to describe signal quality.

[0076] 1.24 Identify handover events in the initial data set in combination with the relevant feature data, and classify and label the identified handover events to complete preprocessing of the network-related data.

[0077] Event classification: For example, using historical switching logs to identify and label each switching event (success, failure, delay, etc.). The classification process corresponds one-to-one with the model training labels.

[0078] Annotation: For example, automatically annotating common switching events using predefined rules (e.g., signal loss exceeding a certain threshold is considered a failure).

[0079] 2. Using the network data set, a switching demand prediction model for predicting network switching time and target and a switching effect prediction model for predicting network performance after switching are constructed.

[0080] 2.1 Switching Demand Forecasting Model

[0081] Current and historical signal quality, user equipment mobility pattern (position, speed and direction), base station status (load, available resources) and environmental information (weather, traffic) are extracted from the relevant feature data, and the extracted data are organized into a time series data structure to obtain a first training data set.

[0082] An LSTM network is used to capture the temporal dependencies of channel quality, user mobility, and environmental characteristics to obtain a time series model. Then, using sliding window technology, the first training data set is input into the time series model for training, so as to learn and predict the future state of network usage and determine the timing of network switching.

[0083] A graph neural network model is constructed based on the network topology structure, and the first training data set is input into the graph neural network model to obtain the status and relationship changes of neighboring base stations; wherein, each node in the graph neural network model represents a base station, and each edge represents the connection relationship between base stations; information propagation and aggregation are performed on the network graph, so that the model captures the status and relationship changes of neighboring base stations.

[0084] Use historical switching records for supervised learning, implement cross-validation and hyperparameter optimization techniques (such as random search and Bayesian optimization) to improve model performance.

[0085] Deploy and integrate the time series model and the graph neural network model to obtain a switching demand prediction model, use the switching demand prediction model to predict real-time data, and obtain the network switching time and the switching target base station.

[0086] 2.2 Switching effect prediction model:

[0087] Base station characteristics (signal strength, load, historical performance indicators), connection device requirements (bandwidth, delay sensitivity) and overall network status (congestion level, interference situation) are extracted from the relevant feature data, and the extracted data are integrated into a second training data set.

[0088] A multilayer perceptron (MLP) is constructed to process nonlinear feature combinations. Residual connections and batch normalization are introduced into the multilayer perceptron to optimize the training stability and speed of the deep network and obtain a deep neural network.

[0089] The deep neural network is trained using the second training data set, and a random forest (which automatically selects the optimal switching target base station through voting output from multiple decision trees) and a gradient boosting tree (which gradually adjusts the decision error and combines multiple weak learners to improve the predictive ability of the overall model) are integrated into the deep learning network to obtain a deep learning model.

[0090] The deep learning model is trained using the network performance data after the switch to predict and evaluate the performance indicator trend of the network after the switch.

[0091] 3. Formulate an initial switching strategy based on the constructed model, and optimize the initial switching strategy using reinforcement learning to obtain the optimal switching strategy. This includes:

[0092] 3.1 State definition:

[0093] Current network status: including signal quality, base station load, throughput, latency, etc.

[0094] User status: location information, speed, service requirements, etc.

[0095] Environmental conditions: information such as weather and road traffic.

[0096] The current network state, user state and environment state are acquired and integrated to obtain state information, and the state information is encoded into a feature vector of a fixed length to obtain a state representation, thereby completing the state definition.

[0097] 3.2 Action Definition

[0098] Discrete action space: such as switching to a specific base station, enabling or disabling a specific function.

[0099] Continuous action space: Adjusting switching parameters (such as switching thresholds and power control parameters).

[0100] 3.3 Reward Definition

[0101] Instant rewards: Instant rewards are given based on network performance indicators (such as throughput and signal strength) and user experience (such as latency and packet loss rate) after switching.

[0102] Long-term rewards: Consider the long-term optimization of network resources, such as reducing network jitter and improving system stability.

[0103] 3.4 Integrate the defined states, actions, and rewards to obtain a reinforcement learning framework. Use the initial dataset to continuously train the reinforcement learning framework to obtain a policy model. Use the policy model to optimize the initial handover policy output by the prediction model to obtain the optimal handover policy. Deploy the policy model on access and core network nodes for real-time online decision-making.

[0104] When training the reinforcement learning framework, a Deep Q-Network (DQN) can be used to handle scenarios with limited switching options (discrete actions). A Deep Neural Network (DNN) is used to estimate the Q-value function, which assesses the value of each possible action in each state.

[0105] 4. Deploy the network switching engine model on the edge computing node and adjust the optimal switching strategy in real time according to changes in the network environment. This includes:

[0106] Edge computing nodes (MEC) are located close to user devices. Deploying models on MEC servers can significantly reduce data transmission latency and improve the real-time and responsiveness of handoff decisions. Within MEC nodes, protocols can be established to ensure that neighboring edge nodes can efficiently share necessary status information, using distributed ledger technology to ensure data consistency and integrity during information sharing.

[0107] Choose lightweight models (such as MobileNet and TinyML, which are suitable for running on the limited resources of terminal devices) to reduce network burden. Integrate the device's CPU, GPU, NPU and other hardware resources to optimize model inference speed and power consumption.

[0108] The lightweight model is subjected to model compression (such as knowledge distillation and quantization to ensure efficient operation) and containerization operations (such as containerization using Docker or Kubernetes to facilitate management and expansion) to obtain a network switching engine model.

[0109] The initial data set is input into the network switching engine model, and the network switching operation priority and target base station recommendation are output. A deep learning or reinforcement learning model is used to evaluate the trust level of available base stations, and a switching recommendation is generated to make real-time adjustments to the optimal switching strategy.

[0110] 5. Construct a virtual simulated digital environment to perform network simulation, evaluate the optimal switching strategy based on the simulated virtual network environment, and then optimize the network switching engine model in real time based on the evaluation results. This includes:

[0111] Use physical simulation tools (such as NS-3 or Omnet++) to simulate network infrastructure, signal interference, and user mobility. Then use simulation tools to integrate real user behavior patterns, consider the interaction between different user devices and applications, and perform network simulation.

[0112] A digital twin is selected as a strategy testing platform, and a multi-dimensional simulation matrix is ​​introduced into the strategy testing platform to evaluate the optimal switching strategy and its impact on throughput, latency, user feedback, etc.

[0113] Among them, 1) Digital Twin is a conceptual system for the interaction between the physical world and the digital space. It is both a new technology and a new paradigm. Digital twins make full use of physical models, sensor updates, operating history and other data, integrate simulation technology, and map in three-dimensional space to reflect the entire life cycle of the corresponding physical equipment. Simply put, a digital twin is to create a digital version of a "clone". 2) A multidimensional simulation matrix refers to a matrix with multiple dimensions (such as two-dimensional, three-dimensional, etc.), whose elements can be numerical, symbolic, or other data types. This type of matrix is ​​very useful in simulation systems, especially when it is necessary to deal with complex systems or perform multidimensional data analysis.

[0114] The network switching engine model is calibrated and the optimal switching strategy is adjusted according to the evaluation result of the optimal switching strategy to achieve continuous optimization.

[0115] Therefore, the present invention provides an artificial intelligence-based 5G network intelligent switching management method, which not only realizes intelligent switching decision-making, but also improves the accuracy and efficiency of switching decisions, enhances network adaptability and diversified needs, and improves user experience.

[0116] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0117] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. A 5G network intelligent switching management method based on artificial intelligence, characterized in that: The following steps are involved: Collecting network-related data and preprocessing the network-related data to obtain a network data set; Using the network dataset, a handover demand prediction model and a handover effect prediction model are constructed. A time series model and a graph neural network model are deployed and integrated to obtain a handover demand prediction model. The handover demand prediction model is used to predict real-time data to obtain the network handover time and the handover target base station. The handover effect prediction model is used to predict and evaluate the performance indicator trend of the network after the handover. Formulate an initial handover strategy based on the constructed handover demand prediction model and handover effect prediction model, train a reinforcement learning framework to obtain a strategy model, use the strategy model to optimize the initial handover strategy, obtain the optimal handover strategy, and deploy the strategy model on access network and core network nodes to make real-time online decisions; Deploying a network switching engine model on an edge computing node, wherein a lightweight model is selected and subjected to model compression and containerization operations to obtain a network switching engine model. The network switching engine model is used to output a network switching operation priority and a target base station recommendation. A deep learning or reinforcement learning model is used to evaluate the trustworthiness of available base stations, generate a switching recommendation, and perform real-time adjustments to the optimal switching strategy. A virtual simulated digital environment is constructed to perform network simulation, the optimal switching strategy is evaluated based on the simulated virtual network environment, and then the network switching engine model is optimized in real time based on the evaluation result.

2. The 5G network intelligent switching management method based on artificial intelligence according to claim 1 is characterized in that: The network-related data includes channel quality indicators, mobility data, network topology data, historical switching data, user behavior data and environmental data; The channel quality indicator is obtained from the channel quality information reported by the user equipment, the mobile data includes user location, speed, acceleration and moving direction, the network topology data includes base station location, coverage, adjacency and base station load, the historical switching data includes switching events, switching success rate, switching failure reasons and switching delay, the user behavior data includes user application type, traffic pattern, service quality requirements, and the environmental data includes weather conditions, geographical obstacle information and road traffic information.

3. The 5G network intelligent switching management method based on artificial intelligence according to claim 2 is characterized in that: Collect network-related data and pre-process the network-related data to obtain a network data set, including: Collect network-related data, perform denoising, anomaly detection, and missing data filling on the network data to obtain an initial data set; Dividing the initial data set into two types: continuous values ​​and discrete values, selecting different data normalization methods for different data types, and completing the normalization operation of the initial data set; Based on the normalized initial data set, calculating the time series characteristics of the signal strength, identifying the periodic pattern of the time series characteristics, obtaining a time series analysis result, constructing the interaction characteristics and statistical characteristics of the user equipment and the network base station based on the time series analysis result, and then using a feature selection algorithm to extract features to obtain relevant feature data; The handover events in the initial data set are identified in combination with the relevant feature data, and the identified handover events are classified and labeled to complete the preprocessing of the network-related data.

4. The 5G network intelligent switching management method based on artificial intelligence according to claim 3 is characterized in that: The network data set is used to construct a switching demand prediction model for predicting network switching time and target, including: Extracting current and historical signal quality, user equipment mobility pattern, base station status, and environmental information from the relevant feature data, and organizing the extracted data into a time series data structure to obtain a first training data set; An LSTM network is used to capture the temporal dependencies of channel quality, user mobility, and environmental characteristics to obtain a time series model. Then, a sliding window technique is used to input the first training dataset into the time series model for training, thereby learning and predicting the future state of network usage and determining the network switching time. Constructing a graph neural network model based on the network topology structure, inputting the first training data set into the graph neural network model to obtain the status and relationship changes of neighboring base stations; wherein each node in the graph neural network model represents a base station, and each edge represents a connection relationship between base stations; Deploy and integrate the time series model and the graph neural network model to obtain a switching demand prediction model, use the switching demand prediction model to predict real-time data, and obtain the network switching time and the switching target base station.

5. The 5G network intelligent switching management method based on artificial intelligence according to claim 4 is characterized in that: Constructing a handover effect prediction model for predicting post-handover network performance using the network data set, including: Extracting base station features, connection device requirements, and overall network status from the relevant feature data, and integrating the extracted data into a second training data set; Constructing a multilayer perceptron, introducing residual connections and batch normalization into the multilayer perceptron to obtain a deep neural network, training the deep neural network using the second training data set, and integrating a random forest and a gradient boosting tree into the deep learning network to obtain a deep learning model; The deep learning model is trained using the network performance data after the switch to predict and evaluate the performance indicator trend of the network after the switch.

6. The 5G network intelligent switching management method based on artificial intelligence according to claim 5 is characterized in that: An initial switching strategy is formulated based on the constructed prediction model, and the initial switching strategy is optimized by combining reinforcement learning to obtain the optimal switching strategy, including: Acquire and integrate the current network state, user state, and environment state to obtain state information, encode the state information into a fixed-length feature vector, obtain a state representation, and complete the state definition; Define the discrete action space and continuous action space after network switching, and define the immediate reward and long-term reward after network switching; Integrate the defined states, actions, and rewards to obtain a reinforcement learning framework; Continuously training the reinforcement learning framework using the initial data set to obtain a strategy model, and optimizing the initial switching strategy output by the prediction model using the strategy model to obtain an optimal switching strategy; The policy model is deployed in access network and core network nodes to perform real-time online decision making.

7. The 5G network intelligent switching management method based on artificial intelligence according to claim 6 is characterized in that: Constructing a virtual simulated digital environment to perform network simulation, evaluating the optimal switching strategy based on the simulated virtual network environment, and then optimizing the network switching engine model in real time based on the evaluation results, including: Use physical simulation tools to simulate network infrastructure, signal interference, and user mobility, and then use simulation tools to integrate real user behavior patterns to perform network simulation; Selecting a digital twin as a strategy testing platform and introducing a multi-dimensional simulation matrix into the strategy testing platform to evaluate the optimal switching strategy; The network switching engine model is calibrated and the optimal switching strategy is adjusted according to the evaluation result of the optimal switching strategy.

Images