Intelligent heterogeneous network fusion optimization method and device based on large model

Abstract

The invention discloses an intelligent heterogeneous network fusion optimization method and device based on a large model, and the method comprises the steps: collecting real-time network state data, service demand data and user equipment data of various heterogeneous networks, and carrying out the preprocessing; key features capable of reflecting real-time changes of network states and service requirements are extracted from the preprocessed data; a self-adaptive multi-modal fusion algorithm is adopted, modal characteristics of heterogeneous network data are automatically identified, and weights and parameters in the fusion process are dynamically adjusted, so that the optimal fusion effect is achieved; building a large model driven by deep learning in combination with a cross-network context awareness optimization strategy; and the intelligent fusion module dynamically selects the optimal network path and transmission strategy according to the output result of the large model. According to the method and the device, intelligent fusion of the network is realized by adopting a self-adaptive multi-modal fusion algorithm and a cross-network context sensing optimization strategy based on a large model of deep learning.

Description

Technical Field

[0001] The present invention relates to the field of network fusion, and in particular to a large model-based intelligent heterogeneous network fusion optimization method and device. Background Art

[0002] With the rapid development of information technology, various heterogeneous networks (such as wide area networks, wireless local area networks, etc.) coexist, and each network has its own unique advantages and limitations. Traditional network convergence methods often adopt fixed convergence strategies, which cannot be dynamically adjusted according to real-time network status and business needs. Therefore, how to achieve intelligent network convergence to fully utilize the advantages of various networks and improve overall network performance has become an urgent problem to be solved. Summary of the invention

[0003] In order to solve the above-mentioned problems existing in traditional network fusion methods, the present invention provides an intelligent heterogeneous network fusion optimization method and device based on a large model. By constructing a large model of deep learning, the model can analyze the network status and business requirements of different types of networks in real time, and formulate intelligent fusion strategies based on this to achieve intelligent network fusion; the use of adaptive multimodal fusion algorithms and cross-network context-aware optimization strategies can make full use of the advantages of various networks to achieve more efficient and flexible network performance optimization, thereby improving cross-network data transmission efficiency and reducing network latency.

[0004] To achieve the above object, the present invention adopts the following technical solutions:

[0005] In one embodiment of the present invention, a large model-based intelligent heterogeneous network fusion optimization method is proposed, the method comprising:

[0006] Collect and pre-process real-time network status data, service demand data, and user equipment data of various heterogeneous networks;

[0007] Extract key features that can reflect real-time changes in network status and business needs from preprocessed data; use adaptive multimodal fusion algorithms to automatically identify the modal characteristics of heterogeneous network data and dynamically adjust weights and parameters in the fusion process to achieve the best fusion effect; combine cross-network context-aware optimization strategies to achieve the construction of large models driven by deep learning;

[0008] The intelligent fusion module dynamically selects the best network path and transmission strategy based on the output results of the large model.

[0009] Furthermore, the implementation steps of the adaptive multimodal fusion algorithm are as follows:

[0010] The adaptive multimodal fusion algorithm uses a pre-trained modal recognition module to perform modal recognition on the input heterogeneous network data and extract their respective representation vectors, which can capture the key features of the heterogeneous network data.

[0011] In the fusion process, the adaptive multimodal fusion algorithm uses attention mechanism or reinforcement learning technology to dynamically adjust the fusion weights between different modal data according to the characteristics of heterogeneous network data and task requirements;

[0012] The adaptive multimodal fusion algorithm designs a multimodal interaction layer that uses the powerful learning ability of deep neural networks to capture the association and complementary information between different modal data and generate a unified representation after fusion.

[0013] Furthermore, the implementation steps of the cross-network context-aware optimization strategy are as follows:

[0014] The cross-network context-aware optimization strategy uses graph neural network technology to construct a correlation graph between heterogeneous networks. The nodes and edges in the graph represent the correlation and dependency between heterogeneous networks and data, thereby capturing cross-network context information.

[0015] In the fusion process, the captured cross-network contextual information is input into the adaptive multimodal fusion algorithm as an important feature and fused together with the original data;

[0016] According to the fused data and task requirements, the cross-network context-aware optimization strategy dynamically adjusts the optimization objective function to ensure that the fusion result can maximize the actual needs.

[0017] Furthermore, the intelligent fusion module monitors changes in network status and business needs in real time, and adjusts the fusion strategy accordingly, including network path selection algorithm, transmission strategy optimization, load balancing and anomaly sorting.

[0018] In one embodiment of the present invention, a large model-based intelligent heterogeneous network fusion optimization device is also proposed, the device comprising:

[0019] The data acquisition module is used to collect real-time network status information, service demand information and user equipment information of various heterogeneous networks and send it to the data preprocessing module;

[0020] The data preprocessing module is used to preprocess the collected data and send the processed data to the large model;

[0021] The large model module is used to extract key features that can reflect the real-time changes of network status and business needs from pre-processed data; it uses an adaptive multimodal fusion algorithm to automatically identify the modal characteristics of heterogeneous network data and dynamically adjust the weights and parameters in the fusion process to achieve the best fusion effect; combined with the cross-network context-aware optimization strategy, it realizes the construction of a large model driven by deep learning;

[0022] The intelligent fusion module is used to dynamically select the best network path and transmission strategy based on the output results of the large model.

[0023] Furthermore, the implementation steps of the adaptive multimodal fusion algorithm are as follows:

[0024] The adaptive multimodal fusion algorithm uses a pre-trained modal recognition module to perform modal recognition on the input heterogeneous network data and extract their respective representation vectors, which can capture the key features of the heterogeneous network data.

[0025] In the fusion process, the adaptive multimodal fusion algorithm uses attention mechanism or reinforcement learning technology to dynamically adjust the fusion weights between different modal data according to the characteristics of heterogeneous network data and task requirements;

[0026] The adaptive multimodal fusion algorithm designs a multimodal interaction layer that uses the powerful learning ability of deep neural networks to capture the association and complementary information between different modal data and generate a unified representation after fusion.

[0027] Furthermore, the implementation steps of the cross-network context-aware optimization strategy are as follows:

[0028] The cross-network context-aware optimization strategy uses graph neural network technology to construct a correlation graph between heterogeneous networks. The nodes and edges in the graph represent the correlation and dependency between heterogeneous networks and data, thereby capturing cross-network context information.

[0029] In the fusion process, the captured cross-network contextual information is input into the adaptive multimodal fusion algorithm as an important feature and fused together with the original data;

[0030] According to the fused data and task requirements, the cross-network context-aware optimization strategy dynamically adjusts the optimization objective function to ensure that the fusion result can maximize the actual needs.

[0031] Furthermore, the intelligent fusion module monitors changes in network status and business needs in real time, and adjusts the fusion strategy accordingly, including network path selection algorithm, transmission strategy optimization, load balancing and anomaly sorting.

[0032] In one embodiment of the present invention, a computer device is also proposed, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the aforementioned large model-based intelligent heterogeneous network fusion optimization method is implemented.

[0033] In one embodiment of the present invention, a computer-readable storage medium is also proposed, which stores a computer program for executing a large model-based intelligent heterogeneous network fusion optimization method.

[0034] Beneficial effects:

[0035] 1. The large model of the present invention adopts an adaptive multimodal fusion algorithm and a cross-network context-aware optimization strategy, which can self-learn and adjust according to real-time data to adapt to the ever-changing network environment.

[0036] 2. The present invention can more comprehensively understand the network status by comprehensively analyzing data in multiple dimensions such as network performance, business traffic characteristics, and user behavior.

[0037] 3. The present invention can dynamically adjust the fusion strategy according to the real-time analysis results to achieve optimal data transmission efficiency and network performance.

[0038] 4. The present invention adopts a modular design, which is easy to expand and integrate into the existing network architecture, thereby improving practicality and flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic diagram of a flow chart of a large-model-based intelligent heterogeneous network fusion optimization method according to an embodiment of the present invention;

[0040] Figure 2 It is a schematic diagram of the structure of an intelligent heterogeneous network fusion optimization device based on a large model according to an embodiment of the present invention;

[0041] Figure 3 It is a schematic diagram of the computer device structure of the present invention. DETAILED DESCRIPTION

[0042] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0043] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a device, apparatus, equipment, method or computer program product. Therefore, the present disclosure may be implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0044] According to an implementation of the present invention, a large-model-based intelligent heterogeneous network fusion optimization method is proposed. By constructing a large deep learning model and adopting an adaptive multimodal fusion algorithm and a cross-network context-aware optimization strategy, the network status and business requirements of different types of networks can be analyzed, and intelligent fusion strategies can be formulated accordingly to achieve intelligent network fusion.

[0045] The principle and spirit of the present invention are explained in detail below with reference to several representative embodiments of the present invention.

[0046] Figure 1 FIG. 1 is a flow chart of a large-model-based intelligent heterogeneous network fusion optimization method according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0047] 1. Adaptive data acquisition and preprocessing

[0048] The data collection module collects real-time status data, business demand data, and user device information of heterogeneous networks such as wireless networks, metropolitan area networks, and wide area networks. These data include network status information such as network bandwidth, delay, and packet loss rate, as well as business demand information such as data transmission volume, data type, and transmission priority. At the same time, it is also necessary to collect information such as the type, location, and supported network type of user equipment.

[0049] After data collection is completed, the data needs to be preprocessed. Preprocessing includes operations such as data cleaning, feature extraction, and normalization so that subsequent models can better understand and utilize the data.

[0050] 2. Large model construction driven by deep learning

[0051] The key part of the large model architecture that supports heterogeneous network data processing and fusion adopts adaptive multimodal fusion algorithm and cross-network context-aware optimization strategy.

[0052] Extract key features from pre-processed heterogeneous network data (features cover multiple dimensions such as network performance, business traffic characteristics, user behavior, etc.). These features can reflect real-time changes in network status and business needs.

[0053] The adaptive multimodal fusion algorithm automatically identifies the modal characteristics of heterogeneous network data (such as text, image, time series, etc.) and dynamically adjusts the weights and parameters in the fusion process to achieve the optimal fusion effect.

[0054] The cross-network context-aware optimization strategy emphasizes taking full account of cross-network context information during the fusion process to improve fusion effect and decision accuracy.

[0055] Through the combination of adaptive multimodal fusion algorithm and cross-network context-aware optimization strategy, the construction of large models driven by deep learning is achieved.

[0056] 3. Dynamic intelligent fusion strategy implementation

[0057] After the large model is built, the intelligent fusion module is used to realize the intelligent fusion of the network. Based on the output of the large model, the module dynamically selects the best network path and transmission strategy to achieve efficient data transmission. At the same time, the module can also monitor the changes in network status and business needs in real time, and adjust the fusion strategy accordingly (the fusion strategy includes path selection algorithm, transmission strategy optimization, load balancing, anomaly sorting, etc.) to adapt to the ever-changing network environment.

[0058] It should be noted that, although the operations of the method of the present invention are described in a specific order in the above embodiments and the accompanying drawings, this does not require or imply that the operations must be performed in the specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0059] In order to explain the above-mentioned large model-based intelligent heterogeneous network fusion optimization method more clearly, a specific embodiment is used for illustration below. However, it should be noted that this embodiment is only for better illustrating the present invention and does not constitute an improper limitation to the present invention.

[0060] Example:

[0061] The specific implementation steps of the present invention are as follows:

[0062] 1. Data Collection and Preprocessing

[0063] 1. The data acquisition module collects real-time status data, business demand data and user equipment information of different types of networks in real time, and sends these data to the data preprocessing module.

[0064] The specific data are as follows:

[0065] (1) Network status data: including real-time information such as network bandwidth, latency, and packet loss rate.

[0066] (2) Business demand data: including data transmission volume, data type (such as video, file, real-time data, etc.), transmission priority, etc.

[0067] (3) User device information: including device type (such as mobile phone, computer, server, etc.), location, supported network types, etc.

[0068] 2. The data preprocessing module cleans, extracts features, and normalizes the collected data, and sends the processed data to subsequent processes.

[0069] import numpy as np

[0070] from sklearn.preprocessing import StandardScaler,MinMaxScaler

[0071] from sklearn.decomposition import PCA

[0072] from sklearn.feature_selection import SelectKBest,chi2

[0073] #Assume X is the original data and y is the label (only for feature selection)

[0074] X=np.array([[1,2,3],[4,5,6],[7,8,9]])

[0075] y = np.array([0,1,0])

[0076] #Data normalization

[0077] min_max_scaler=MinMaxScaler()

[0078] X_normalized=min_max_scaler.fit_transform(X)

[0079] #Data Standardization

[0080] standard_scaler=StandardScaler()

[0081] X_standardized=standard_scaler.fit_transform(X)

[0082] # Dimensionality reduction

[0083] pca=PCA(n_components=2)

[0084] X_pca = pca.fit_transform(X)

[0085] #Feature selection

[0086] selector=SelectKBest(chi2,k=2)

[0087] X_selected=selector.fit_transform(X,y)

[0088] 2. Adaptive Multimodal Fusion Algorithm

[0089] 1. Modal recognition and representation: The algorithm uses the pre-trained modal recognition module to perform modal recognition on the input heterogeneous network data and extract their respective representation vectors. These representation vectors can capture the key features of heterogeneous network data and provide a basis for subsequent fusion.

[0090]

[0091]

[0092] 2. Adaptive weight adjustment: During the fusion process, the algorithm uses attention mechanisms or reinforcement learning techniques to dynamically adjust the fusion weights between different modal data according to the characteristics of heterogeneous network data and task requirements. This adaptive adjustment can ensure that the fusion results are more in line with the actual situation and improve the fusion accuracy.

[0093]

[0094]

[0095] 3. Multimodal interaction and fusion: The algorithm realizes the interaction and fusion between different modal data by designing a multimodal interaction layer. This layer uses the powerful learning ability of deep neural networks (such as Transformer, LSTM, etc.) to capture the association and complementary information between different modal data and generate a unified representation after fusion.

[0096]

[0097] 3. Cross-network context-aware optimization strategy

[0098] 1. Context information construction: This strategy first uses technologies such as graph neural networks (GNN) to construct a correlation graph between heterogeneous networks. The nodes and edges in the graph represent the association and dependency between heterogeneous networks and data, thereby capturing cross-network context information.

[0099] import torch

[0100] from torch_geometric.nn import GCNConv

[0101] from torch_geometric.data import Data

[0102] #Suppose we have the following node features and edge indexes of heterogeneous networks

[0103] node_features=torch.tensor([[1,2],[3,4],[5,6]],dtype=torch.float)

[0104] edge_index=torch.tensor([[0,1],[1,2]],dtype=torch.long)

[0105] #Create a graph data object

[0106] graph_data=Data(x=node_features,edge_index=edge_index)

[0107] #Define a graph convolutional network layer

[0108] gcn_layer=GCNConv(in_channels=2,out_channels=2)

[0109] #Use graph convolutional network layer for forward propagation

[0110] output=gcn_layer(graph_data.x,graph_data.edge_index)

[0111] print("Output of the GCN layer:",output)

[0112] 2. Contextual information fusion: During the fusion process, the captured cross-network contextual information is input into the adaptive multimodal fusion algorithm as an important feature and fused together with the original data. This fusion method can make the fusion result more comprehensive and accurate, taking into account the mutual influence and constraint relationship between heterogeneous networks.

[0113] The mutual influence and constraint relationship between heterogeneous networks are crucial to the final task completion. Through context information fusion, these complex relationships can be better understood and processed, thereby improving the accuracy and effect of the task.

[0114] import torch

[0115] from torch_geometric.data import Data

[0116] from torch_geometric.nn import GCNConv

[0117] #Suppose we have the following node features and edge indexes of heterogeneous networks

[0118] node_features=torch.tensor([[1,2],[3,4],[5,6]],dtype=torch.float)

[0119] edge_index=torch.tensor([[0,1],[1,2]],dtype=torch.long)

[0120] #Create a graph data object

[0121] graph_data=Data(x=node_features,edge_index=edge_index)

[0122] #Define a graph convolutional network layer

[0123] gcn_layer=GCNConv(in_channels=2,out_channels=2)

[0124] #Use the graph convolutional network layer for forward propagation to obtain context information

[0125] context_info=gcn_layer(graph_data.x,graph_data.edge_index)

[0126] #Assume that we still have the original data (represented here by a simple random tensor)

[0127] original_data=torch.randn(3,2)

[0128] #Merge context information with original data (here we simply add them together)

[0129] fused_data=context_info+original_data

[0130] print("Fused data:",fused_data)

[0131] 3. Optimization target adjustment: According to the fused data and task requirements, the strategy also dynamically adjusts the optimization target function to ensure that the fusion result can maximize the actual needs. This adjustment of the target function can make the algorithm more flexible and effective in complex network environments.

[0132]

[0133]

[0134] 4. After the large model is built, the intelligent fusion module is used to realize the intelligent fusion of the network. This module dynamically selects the best network path and transmission strategy based on the output results of the large model. The intelligent fusion module also monitors the changes in network status and business needs in real time, and adjusts the fusion strategy accordingly, including network path selection algorithm, transmission strategy optimization, load balancing and anomaly sorting.

[0135] Here are some examples:

[0136] For example, there is an online video live broadcast platform that needs to provide users with high-definition, low-latency video streaming services. In order to ensure the quality of service, a large-scale intelligent heterogeneous network fusion optimization device is used.

[0137] 1. Data collection and processing

[0138] Real-time monitoring: Collect network status data in real time, including key indicators such as bandwidth, latency, and packet loss rate.

[0139] Business demand analysis: It also receives demand information from the business system, such as the current number of online users, video resolution, encoding format, etc.

[0140] 2. Construction of adaptive multimodal fusion algorithm

[0141] Modal recognition and representation: Use the pre-trained modal recognition module to perform modal recognition on the acquired data and extract their respective representation vectors.

[0142] Adaptive weight adjustment: Based on the characteristics of the data and task requirements (such as whether the user is currently watching a video, whether an emergency response is required, etc.), the fusion weights between different modal data are dynamically adjusted using techniques such as attention mechanisms or reinforcement learning.

[0143] Multimodal interaction and fusion: Design a multimodal interaction layer and use deep neural networks (such as Transformer, LSTM, etc.) to capture the correlation and complementary information between different modalities and generate a unified representation after fusion.

[0144] 3. Cross-network context-aware optimization strategy

[0145] Context information construction: Use technologies such as graph neural networks (GNN) to build association graphs between heterogeneous networks and capture cross-network context information (such as associations between devices, user behavior patterns, etc.).

[0146] Contextual information fusion: The captured contextual information is used as an important input feature and fused with the original data to improve the accuracy and efficiency of data transmission.

[0147] Optimization target adjustment: According to the fused data and task requirements (such as the user's current demand priority, network status, etc.), dynamically adjust the optimization objective function (such as transmission path selection, rate control, priority sorting, etc.) to ensure that the fusion result can maximize the actual needs.

[0148] 4. Large model generation

[0149] Based on the output results of the above steps, formulate a fusion strategy for data transmission, including selecting a transmission path, determining transmission rate and priority, etc.

[0150] 5. Support real-time monitoring of changes in network status and business needs, and feedback of these changes so as to adjust the integration strategy in real time.

[0151] Based on the same inventive concept, the present invention also proposes an intelligent heterogeneous network fusion optimization device based on a large model. The implementation of the device can refer to the implementation of the above method, and the repeated parts will not be repeated. The term "module" used below can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0152] Figure 2 FIG. 1 is a diagram of the architecture of an intelligent heterogeneous network fusion optimization device based on a large model according to an embodiment of the present invention. Figure 2 As shown, the device comprises:

[0153] The data collection module 101 is used to collect real-time network status information, service demand information and user equipment information of various heterogeneous networks, and send them to the data preprocessing module.

[0154] The data preprocessing module 102 is used to preprocess the collected data and send the processed data to the large model.

[0155] The large model module 103 is used to extract key features that can reflect the real-time changes of network status and business needs from the preprocessed data; adopt an adaptive multimodal fusion algorithm to automatically identify the modal characteristics of heterogeneous network data, and dynamically adjust the weights and parameters in the fusion process to achieve the best fusion effect; and combine the cross-network context-aware optimization strategy to realize the construction of a deep learning-driven large model.

[0156] The implementation steps of the adaptive multimodal fusion algorithm are as follows:

[0157] The adaptive multimodal fusion algorithm uses a pre-trained modal recognition module to perform modal recognition on the input heterogeneous network data and extract their respective representation vectors, which can capture the key features of the heterogeneous network data.

[0158] In the fusion process, the adaptive multimodal fusion algorithm uses attention mechanism or reinforcement learning technology to dynamically adjust the fusion weights between different modal data according to the characteristics of heterogeneous network data and task requirements;

[0159] The adaptive multimodal fusion algorithm designs a multimodal interaction layer that uses the powerful learning ability of deep neural networks to capture the association and complementary information between different modal data and generate a unified representation after fusion.

[0160] The implementation steps of the cross-network context-aware optimization strategy are as follows:

[0161] The cross-network context-aware optimization strategy uses graph neural network technology to construct a correlation graph between heterogeneous networks. The nodes and edges in the graph represent the correlation and dependency between heterogeneous networks and data, thereby capturing cross-network context information.

[0162] In the fusion process, the captured cross-network contextual information is input into the adaptive multimodal fusion algorithm as an important feature and fused together with the original data;

[0163] According to the fused data and task requirements, the cross-network context-aware optimization strategy dynamically adjusts the optimization objective function to ensure that the fusion result can maximize the actual needs.

[0164] The intelligent fusion module 104 is used to dynamically select the best network path and transmission strategy based on the output results of the large model; this module also monitors the changes in network status and business needs in real time, and adjusts the fusion strategy accordingly, including network path selection algorithm, transmission strategy optimization, load balancing and anomaly sorting.

[0165] It should be noted that although several modules of the intelligent heterogeneous network fusion optimization device based on a large model are mentioned in the above detailed description, this division is only exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules described above can be concretized in one module. Conversely, the features and functions of one module described above can be further divided into multiple modules for concretization.

[0166] Based on the above invention concept, Figure 3 As shown, the present invention also proposes a computer device 200, including a memory 210, a processor 220, and a computer program 230 stored in the memory 210 and executable on the processor 220. When the processor 220 executes the computer program 230, the aforementioned large model-based intelligent heterogeneous network fusion optimization method is implemented.

[0167] Based on the aforementioned inventive concept, the present invention also proposes a computer-readable storage medium, which stores a computer program for executing the aforementioned large-model-based intelligent heterogeneous network fusion optimization method.

[0168] The large-model-based intelligent heterogeneous network fusion optimization method and device proposed in the present invention have the following highlights:

[0169] 1. Adaptive learning capability: The large model of the present invention adopts an adaptive multimodal fusion algorithm and a cross-network context-aware optimization strategy, which can self-learn and adjust according to real-time data to adapt to the ever-changing network environment.

[0170] 2. Multi-dimensional data analysis: By comprehensively analyzing data from multiple dimensions such as network performance, business traffic characteristics, and user behavior, the present invention can provide a more comprehensive understanding of the network status.

[0171] 3. Dynamic fusion strategy: The present invention can dynamically adjust the fusion strategy according to the real-time analysis results to achieve optimal data transmission efficiency and network performance.

[0172] 4. Modular design: The present invention adopts modular design, which is easy to expand and integrate into the existing network architecture, thereby improving practicality and flexibility.

[0173] Although the spirit and principle of the present invention have been described with reference to several specific embodiments, it should be understood that the present invention is not limited to the disclosed specific embodiments, and the division of various aspects does not mean that the features in these aspects cannot be combined to benefit, and such division is only for the convenience of expression. The present invention is intended to cover various modifications and equivalent arrangements contained in the spirit and scope of the attached claims.

[0174] Regarding the limitation of the protection scope of the present invention, those skilled in the art should understand that, based on the technical solution of the present invention, various modifications or variations that can be made by those skilled in the art without creative work are still within the protection scope of the present invention.

Claims

1. A large-model-based intelligent heterogeneous network fusion optimization method, characterized in that: The method includes: Collect and pre-process real-time network status data, service demand data, and user equipment data of various heterogeneous networks; Extract key features that can reflect real-time changes in network status and business needs from preprocessed data; use adaptive multimodal fusion algorithms to automatically identify the modal characteristics of heterogeneous network data and dynamically adjust weights and parameters in the fusion process to achieve the best fusion effect; combine cross-network context-aware optimization strategies to achieve the construction of large models driven by deep learning; The intelligent fusion module dynamically selects the best network path and transmission strategy based on the output results of the large model.

2. The large model-based intelligent heterogeneous network fusion optimization method according to claim 1 is characterized in that: The implementation steps of the adaptive multimodal fusion algorithm are as follows: The adaptive multimodal fusion algorithm uses a pre-trained modal recognition module to perform modal recognition on the input heterogeneous network data and extract their respective representation vectors, which can capture the key features of the heterogeneous network data. In the fusion process, the adaptive multimodal fusion algorithm uses attention mechanism or reinforcement learning technology to dynamically adjust the fusion weights between different modal data according to the characteristics of heterogeneous network data and task requirements; The adaptive multimodal fusion algorithm designs a multimodal interaction layer that uses the powerful learning ability of deep neural networks to capture the association and complementary information between different modal data and generate a unified representation after fusion.

3. The large model-based intelligent heterogeneous network fusion optimization method according to claim 1 is characterized in that: The implementation steps of the cross-network context-aware optimization strategy are as follows: The cross-network context-aware optimization strategy uses graph neural network technology to construct a correlation graph between heterogeneous networks. The nodes and edges in the graph represent the correlation and dependency between heterogeneous networks and data, thereby capturing cross-network context information. In the fusion process, the captured cross-network contextual information is input into the adaptive multimodal fusion algorithm as an important feature and fused together with the original data; According to the fused data and task requirements, the cross-network context-aware optimization strategy dynamically adjusts the optimization objective function to ensure that the fusion result can maximize the actual needs.

4. The large model-based intelligent heterogeneous network fusion optimization method according to claim 1 is characterized in that: The intelligent fusion module monitors the changes in network status and business requirements in real time, and adjusts the fusion strategy accordingly, including network path selection algorithm, transmission strategy optimization, load balancing and anomaly sorting.

5. An intelligent heterogeneous network fusion optimization device based on a large model, characterized in that: The device includes: The data acquisition module is used to collect real-time network status information, service demand information and user equipment information of various heterogeneous networks and send it to the data preprocessing module; The data preprocessing module is used to preprocess the collected data and send the processed data to the large model; The large model module is used to extract key features that can reflect the real-time changes of network status and business needs from pre-processed data; it uses an adaptive multimodal fusion algorithm to automatically identify the modal characteristics of heterogeneous network data and dynamically adjust the weights and parameters in the fusion process to achieve the best fusion effect; combined with the cross-network context-aware optimization strategy, it realizes the construction of a large model driven by deep learning; The intelligent fusion module is used to dynamically select the best network path and transmission strategy based on the output results of the large model.

6. The large model-based intelligent heterogeneous network fusion optimization device according to claim 5 is characterized in that: The implementation steps of the adaptive multimodal fusion algorithm are as follows: The adaptive multimodal fusion algorithm uses a pre-trained modal recognition module to perform modal recognition on the input heterogeneous network data and extract their respective representation vectors, which can capture the key features of the heterogeneous network data. In the fusion process, the adaptive multimodal fusion algorithm uses attention mechanism or reinforcement learning technology to dynamically adjust the fusion weights between different modal data according to the characteristics of heterogeneous network data and task requirements; The adaptive multimodal fusion algorithm designs a multimodal interaction layer that uses the powerful learning ability of deep neural networks to capture the association and complementary information between different modal data and generate a unified representation after fusion.

7. The large model-based intelligent heterogeneous network fusion optimization device according to claim 5 is characterized in that: The implementation steps of the cross-network context-aware optimization strategy are as follows: The cross-network context-aware optimization strategy uses graph neural network technology to construct a correlation graph between heterogeneous networks. The nodes and edges in the graph represent the correlation and dependency between heterogeneous networks and data, thereby capturing cross-network context information. In the fusion process, the captured cross-network contextual information is input into the adaptive multimodal fusion algorithm as an important feature and fused together with the original data; According to the fused data and task requirements, the cross-network context-aware optimization strategy dynamically adjusts the optimization objective function to ensure that the fusion result can maximize the actual needs.

8. The large model-based intelligent heterogeneous network fusion optimization device according to claim 5 is characterized in that: The intelligent fusion module monitors the changes in network status and business requirements in real time, and adjusts the fusion strategy accordingly, including network path selection algorithm, transmission strategy optimization, load balancing and anomaly sorting.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program for executing the method according to any one of claims 1 to 4.

Images