A data transmission method and system suitable for 5G communication

Abstract

The present invention relates to the field of wireless communication technology, and in particular to a data transmission method and system suitable for 5G communication. The method comprises the following steps: acquiring and analyzing network communication data to obtain regional communication demand data; performing communication transmission resource allocation according to regional communication demand data to obtain communication transmission resource allocation data; performing network slice transmission resource allocation on the communication transmission resource allocation data to obtain network slice transmission resource allocation data; acquiring real-time network communication data and performing interference source impact node identification to obtain interference source impact node data; performing communication interference optimization on the network slice transmission resource allocation data according to the interference source impact node data, thereby obtaining network slice transmission optimization resource allocation data, and uploading it to the communication management platform to perform data transmission tasks. The present invention improves the management efficiency of network resources.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technologies, and in particular to a data transmission method and system suitable for 5G communication. Background Art

[0002] Traditional mobile communication technologies mainly rely on 4G LTE (Long Term Evolution) and its predecessors (such as 3G and 2G networks). These technologies mainly use frequency division, time division, and multiple access technologies (such as TDMA, FDMA, CDMA, etc.) for data transmission. In 4G LTE networks, data transmission is carried out through high-speed OFDM (Orthogonal Frequency Division Multiplexing) technology, which supports high downlink rates and relatively low latency. However, despite the breakthroughs in high-speed data transmission, LTE and its related technologies still have some significant defects and limitations. With the surge in the number of mobile devices, traditional methods face serious network congestion and interference problems in high-density user environments. Especially in the scenario of large-scale connections, the existing network architecture and data transmission technology cannot effectively manage the concurrent connections of a large number of devices, resulting in a decrease in transmission speed and even disconnection. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a data transmission method and system suitable for 5G communication to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above object, a data transmission method suitable for 5G communication includes the following steps:

[0005] Step S1: Acquire network communication data, and perform communication network topology analysis based on the network communication data, thereby obtaining a communication network topology model; perform communication demand analysis based on the communication network topology model, thereby obtaining regional communication demand data;

[0006] Step S2: classifying user behavior patterns according to regional communication demand data, thereby obtaining regional user traffic behavior pattern data; allocating communication transmission resources according to the regional user traffic behavior pattern data, thereby obtaining communication transmission resource allocation data;

[0007] Step S3: Create an independent logical virtual network slice for the communication transmission resource allocation data to obtain virtual network slice data; perform network slice transmission resource allocation according to the virtual network slice data to obtain network slice transmission resource allocation data, and upload it to the communication management platform to execute the data transmission task;

[0008] Step S4: acquiring real-time network communication data, and performing communication interference identification on the real-time network communication data according to the network slice transmission resource allocation data, thereby obtaining real-time communication interference data; performing interference source impact node identification on the real-time communication interference data through the communication network topology structure model, thereby obtaining interference source impact node data;

[0009] Step S5: Perform communication interference optimization on the network slice transmission resource allocation data according to the interference source impact node data, so as to obtain the network slice transmission optimization resource allocation data, and upload it to the communication management platform to execute the data transmission task.

[0010] The present invention can fully understand the actual operation status and structural characteristics of the network by acquiring network communication data and analyzing the topological structure of the communication network. This provides a basis for subsequent communication demand analysis, and can more accurately identify the communication needs and coverage requirements of different regions, thereby providing data support for network optimization and resource allocation, ensuring that the network can meet the core needs of high-speed, large-capacity, low-latency and other communications. In a 5G network, base stations, user equipment, core networks and edge computing nodes constitute a complex network topology. Acquiring network communication data (such as traffic, delay, signal strength, etc.) and performing topological structure analysis can help understand the communication needs of different regions. These data can help design a flexible network architecture and support on-demand allocation of network resources. Based on regional communication demand data, user behavior pattern classification (such as video streaming, IoT devices, augmented reality / virtual reality (AR / VR), etc.) helps to dynamically adjust network resources and service quality (QoS) according to different scenarios and needs. This can ensure the reasonable allocation of resources, avoid network congestion, and optimize user experience. This process helps to accurately allocate communication resources to different user groups, thereby improving the utilization efficiency of network resources and avoiding the waste of resources or uneven allocation problems that may exist in traditional communication methods. By creating independent logical virtual network slices, virtualized and customized network services can be implemented according to different business needs (such as autonomous driving, smart cities, industrial Internet, etc.). The flexibility and independence of this network slice enable different types of services to run efficiently on the same physical network, while avoiding mutual interference between different services, improving network reliability and service quality. Interference identification for real-time communication data and identification of interference source-affected nodes help to achieve more accurate interference source management and positioning. Through dynamic monitoring and analysis, this process can timely discover and solve possible interference problems in the network, thereby effectively reducing the negative impact of communication interference on data transmission quality. By optimizing the allocation of network slice transmission resources, resources can be dynamically adjusted to ensure that the network can still operate stably and efficiently in high-density and complex environments, further improving the reliability and user experience of the network in high-load scenarios. Through this series of steps, resource allocation and optimization strategies can be updated and executed in real time on the communication management platform to ensure that the dynamic adjustment and optimization of the entire network are in a controllable state, improving the management efficiency and response speed of network resources. This automated and intelligent management method significantly reduces the complexity of human intervention, while improving the network's ability to respond to emergencies and changes in user needs, ensuring high network availability and service quality.

[0011] Optionally, step S1 specifically includes:

[0012] Step S11: acquiring network communication data, and performing data preprocessing on the network communication data, thereby obtaining communication data to be processed;

[0013] Step S12: extracting communication connection features according to the communication data to be processed, thereby obtaining communication connection data, and identifying communication base stations based on the communication connection data, thereby obtaining regional communication base station connection data;

[0014] Step S13: dividing the communication data to be processed into base station network cell communication data based on the regional communication base station connection data, thereby obtaining network cell communication data;

[0015] Step S14: performing a cell network topology analysis based on the network cell communication data to obtain a cell network topology model, and performing a communication topology merger on the cell network topology model according to the regional communication base station connection data to obtain a communication network topology model;

[0016] Step S15: Perform communication demand analysis based on the communication network topology model to obtain regional communication demand data.

[0017] The present invention can effectively eliminate useless data and improve the quality of data by acquiring and preprocessing network communication data, thereby ensuring the accuracy and effectiveness of subsequent analysis. After data preprocessing, the communication data to be processed obtained provides a reliable basis for subsequent steps, so that the data can more accurately reflect the network status and communication needs. The process of communication connection feature extraction can not only help identify the key features of different communication links, but also provide an accurate basis for communication base station identification, thereby effectively improving the quality and accuracy of regional communication base station connection data, and providing guarantee for subsequent base station positioning and optimization. By dividing network cell communication data based on regional communication base station connection data, the communication data can be effectively divided into more representative and targeted network cell data, providing strong support for the cell network topology analysis, and further improving the precision of network management. The analysis and merging of the cell network topology can reveal the connection and interaction between different cells, and provide a scientific decision-making basis for the overall optimization and resource allocation of 5G networks. The communication demand analysis based on the topology model can not only reveal the communication demand and load distribution of different cells in the region, but also effectively help operators to carry out accurate resource allocation and network capacity planning, thereby improving the overall performance and user experience of the network.

[0018] Optionally, step S14 is specifically:

[0019] Step S141: extracting cell communication signal strength features from network cell communication data, thereby obtaining cell communication signal strength data;

[0020] Step S142: performing signal strength gradient analysis according to the cell communication signal strength data, thereby obtaining cell signal strength gradient data, and determining adjacent cell boundaries according to the cell signal strength gradient data, thereby obtaining adjacent cell boundary data;

[0021] Step S143: integrating cell connection relationships based on adjacent cell boundary data, thereby obtaining cell connection relationship data;

[0022] Step S144: performing cell connection mode identification on the network cell communication data according to the cell connection relationship data, thereby obtaining cell connection mode data;

[0023] Step S145: constructing a cell network topology structure according to the cell connection mode data and the cell connection relationship data, thereby obtaining a cell network topology structure model;

[0024] Step S146: merging the cell network topology structure model according to the regional communication base station connection data to obtain a communication network topology structure model.

[0025] The present invention can effectively improve the quality and efficiency of the communication network by systematically processing the cell communication signal data. By extracting the cell communication signal strength characteristics and performing gradient analysis, the signal strength change trend of the cell can be accurately obtained, so as to accurately determine the boundaries of adjacent cells. This process helps to identify the coverage and interference areas between different cells, and provides data support for subsequent optimization. Based on the adjacent cell boundary data, the cell connection relationship is integrated, and the interdependence and connection mode between the cells are further clarified, so that the integrity of the network architecture can be improved. The identification of the cell connection mode provides important information for understanding the communication interaction mode between the cells, which helps to optimize the network configuration and resource scheduling. The network topology model constructed according to the cell connection mode and the connection relationship can more accurately reflect the overall structure of the communication network, optimize the allocation of network resources, reduce signal interference, and improve the communication quality. The topological structure is merged in combination with the connection data of the regional communication base station, which effectively promotes the collaborative work between the cells, improves the stability and coverage of the entire communication network, and thus provides a scientific basis for network optimization and maintenance in the region.

[0026] Optionally, step S15 is specifically:

[0027] Step S151: extracting cell data throughput features from the communication network topology model, thereby obtaining cell data throughput data;

[0028] Step S152: performing time series statistics of cell data throughput according to the cell data throughput data, thereby obtaining cell high throughput time data and cell low throughput time data;

[0029] Step S153: Calculate the cell throughput time ratio based on the cell high throughput time data and the cell low throughput time data, thereby obtaining the cell throughput time ratio data;

[0030] Step S154: dividing the communication network topology model into communication cells according to the cell throughput time ratio data, thereby obtaining high-throughput and high-ratio cell data and low-throughput and high-ratio cell data;

[0031] Step S155: integrating cell communication demands according to the high-throughput and high-ratio cell data, thereby obtaining high-communication demand cell data; integrating cell communication demands according to the low-throughput and high-ratio cell data, thereby obtaining low-communication demand cell data;

[0032] Step S156: regional spatial merging of the high communication demand cell data and the low communication demand cell data to obtain regional communication demand data.

[0033] The present invention significantly improves the resource utilization efficiency and service quality of the network by gradually analyzing and optimizing the communication network topology. By extracting the cell data throughput characteristics, the throughput data of each cell can be accurately obtained, thereby providing a basis for subsequent network analysis and optimization. These data can help identify the load conditions of different cells, evaluate their performance differences, and provide a basis for further resource scheduling and load balancing. By performing time series statistics on the cell throughput, the time periods of high throughput and low throughput can be identified, which helps to analyze the load fluctuations of the network in different time periods. This process provides important information for dynamic optimization, and can identify the high-demand period and low-demand period of the network, so as to reasonably arrange network resources and avoid congestion. Based on the ratio calculation of high-throughput time and low-throughput time, the understanding of cell throughput fluctuations is further enhanced, making the performance evaluation of different cells more accurate. By combining these data with the network topology, the communication cells can be reasonably divided according to the throughput ratio, and the cells with high throughput and a large proportion can be distinguished from the cells with low throughput and a large proportion, thereby optimizing the communication resource allocation strategy and taking differentiated optimization measures for cells with different demands. By integrating the communication needs based on the divided cell data, it is possible to identify cells with high and low communication needs, providing clear data support for subsequent optimization decisions, ensuring that high-load cells can obtain sufficient resources, while low-load cells can reduce resource waste. By merging the regional space of high- and low-communication demand cells, it is possible to better understand the distribution of communication needs in different regions, optimize regional resource allocation, and ensure load balancing and stability of the entire communication network.

[0034] Optionally, step S2 specifically includes:

[0035] Step S21: Divide the regional communication demand data into time windows, thereby obtaining regional communication demand window data;

[0036] Step S22: extracting regional user connection features according to the regional communication demand window data, thereby obtaining regional user connection time period data and regional user flow window data;

[0037] Step S23: performing regional user connection period distribution analysis based on the regional user connection period data, thereby obtaining regional user connection period distribution data, and performing connected user mobility pattern recognition based on the user connection period distribution data, thereby obtaining user mobility pattern data;

[0038] Step S24: performing regional user traffic periodicity analysis according to the regional user traffic window data, thereby obtaining regional user traffic periodicity data, and performing user traffic behavior pattern recognition based on the regional user traffic periodicity data, thereby obtaining a user traffic behavior pattern;

[0039] Step S25: integrating the user behavior patterns based on the user mobility pattern data and the user traffic behavior patterns, thereby obtaining regional user traffic behavior pattern data;

[0040] Step S26: performing communication transmission resource allocation according to the regional user traffic behavior pattern data, thereby obtaining communication transmission resource allocation data.

[0041] The present invention can effectively extract the communication demand characteristics in different time periods by dividing the regional communication demand data into time windows, which helps to accurately analyze and predict the communication resource requirements in different time windows. Further, the extraction of regional user connection characteristics can accurately reflect the user's connection status, including the connection period and traffic demand, laying the foundation for subsequent traffic prediction and resource optimization. By analyzing the distribution of connection time periods, the user's connection mode in different time periods can be revealed, thereby identifying the user's mobile mode, which provides a basis for optimizing network coverage and improving service quality. The development of traffic periodic analysis can help identify the regular changes in user traffic demand, especially the concentration trend of traffic during peak hours and specific time periods, and provide guidance for network capacity planning and resource scheduling. Through the identification of traffic behavior patterns, the user's traffic usage habits in different time periods can be further excavated, and these data are crucial for dynamic scheduling and network optimization. After integrating the user's mobile mode and traffic behavior pattern, the overall communication demand of users in the region can be fully depicted, forming more accurate behavior pattern data, thereby realizing the refined allocation of regional communication resources.

[0042] Optionally, step S3 specifically includes:

[0043] Step S31: integrating the regional communication resource demand model according to the regional communication demand data, thereby obtaining the regional communication resource demand data;

[0044] Step S32: dividing the slice resource pool based on the communication transmission resource allocation data, thereby obtaining slice resource pool data;

[0045] Step S33: dividing the network topology structure according to the communication network topology structure model, thereby obtaining network topology structure data;

[0046] Step S34: Creating a virtual network slice according to the network topology data, the slice resource pool data, and the regional communication resource demand data, thereby obtaining virtual network slice data, and performing slice priority division on the virtual network slice data, thereby obtaining virtual network slice priority data;

[0047] Step S35: extracting the priority slice configuration of the virtual network slice priority data to obtain the priority slice configuration data, and estimating the slice resource demand according to the priority slice configuration data to obtain the priority slice resource demand data;

[0048] Step S36: Allocate transmission resources for virtual network slice data according to the priority slice resource demand data, thereby obtaining network slice transmission resource allocation data, and upload it to the communication management platform to execute the data transmission task.

[0049] By integrating regional communication demand data, the present invention can accurately understand the communication demand in different regions, thereby providing data support for subsequent resource allocation and network slice design, so that the configuration of network resources is more in line with actual needs and avoids resource waste or insufficient configuration. Slice resource pool division based on communication transmission resource allocation data helps to better allocate and manage slice resources, ensuring that the communication needs of different services or different regions can be flexibly and efficiently supported by resources. This process can lay the foundation for the elastic adjustment and optimization of the network and support dynamic resource adjustment. Through the division of network topology structure, the necessary structural basis can be provided for the creation of slice resource pool and virtual network slice, effectively realizing the optimization of network level and the reasonable allocation of topology resources, and further enhancing the stability and scalability of the network. The creation of virtual network slices, combined with slice priority division, can allocate corresponding network resources according to different business types or service requirements, ensuring that the transmission of high-priority services is not affected, thereby improving the service quality and response speed of the network. Priority slice configuration extraction and resource demand estimation further optimize the precise configuration of resources, avoid over-allocation or resource shortage, and ensure the smooth operation and efficient utilization of the network.

[0050] Optionally, step S4 is specifically:

[0051] Step S41: acquiring real-time network communication data, and dividing the real-time network communication data into slice communication data, thereby obtaining real-time 5G slice communication data;

[0052] Step S42: Performing network slice communication transmission simulation according to the network slice transmission resource allocation data, thereby obtaining network slice communication transmission simulation data;

[0053] Step S43: Calculate the slice communication performance error of the network slice communication transmission simulation data and the real-time 5G slice communication data, so as to obtain slice communication performance error data;

[0054] Step S44: performing high error amplitude slice statistics according to the slice communication performance error data, thereby obtaining communication interference slice data, and identifying communication interference sources based on the communication interference slice data, thereby obtaining real-time communication interference data;

[0055] Step S45: using the communication network topology model to identify interference source impact nodes on the real-time communication interference data, thereby obtaining interference source impact node data.

[0056] The steps of obtaining real-time network communication data and dividing the slice communication data in the present invention are helpful for accurately monitoring and managing the real-time communication of the 5G network. By dividing the slice communication data, differentiated resource allocation for different user groups or application scenarios can be achieved, thereby improving the flexibility and efficiency of the network. This slicing method can effectively support the diversified business needs in the 5G network, and provide a refined communication data basis for subsequent data processing and interference source identification. According to the step of transmission simulation of the network slice transmission resource allocation data, the performance of different network slices in actual communication can be accurately simulated and predicted. Before the actual deployment of the network, the potential bottlenecks or deficiencies in resource allocation can be identified in advance, the configuration of network slice resources can be optimized, and communication quality problems caused by unreasonable resource allocation can be avoided. This is crucial for the realization of a large number of concurrent data transmission and low-latency communication in the 5G network. The step of calculating the performance error of the network slice communication transmission simulation data and the real-time 5G slice communication data helps to evaluate the performance stability of different network slices. This can timely discover the errors or performance deviations that may exist in the network slice during the actual communication process, thereby providing a basis for the subsequent optimization of communication strategies. Through accurate performance error analysis, problems that may affect communication quality can be effectively identified, providing strong decision support for network managers. Statistics of slices with high error amplitude based on slice communication performance error data can help quickly locate slices with serious interference or performance problems. Through statistical analysis of slices with high error amplitude, it can be clear which communication slices are interfered with or affected, providing a clear goal for subsequent identification of communication interference sources. Optimization of this process can improve the efficiency of network operation and maintenance and reduce the risk of network failure or poor user experience caused by interference or errors. The steps of identifying communication interference sources based on communication interference slice data can accurately identify the source of interference during communication. By identifying the interference source, not only can the network fault be quickly diagnosed, but also a basis can be provided for subsequent interference elimination or interference source control. This is crucial for the high reliability and low latency requirements of 5G networks, especially in complex wireless environments, and can effectively improve the service quality and user experience of the network. Through the communication network topology model, the interference source-affected nodes of real-time communication interference data can be identified, and it can be further determined which network nodes are most affected by the interference source. This process helps identify and locate key influencing nodes in the network, thereby optimizing the network structure or adjusting resource allocation, reducing the negative impact of interference on network performance, and improving overall communication efficiency.

[0057] Optionally, step S45 is specifically:

[0058] Step S451: extracting interference source network topology distribution features from real-time communication interference data, thereby obtaining interference source network topology distribution data;

[0059] Step S452: performing interference source associated topology structure matching on the interference source network topology allocation data through the communication network topology structure model, thereby obtaining interference source associated topology structure data;

[0060] Step S453: extracting performance characteristics of associated nodes from the interference source associated topology data based on the real-time network communication data, thereby obtaining associated node performance data;

[0061] Step S454: performing node performance change calculation according to the associated node performance data, thereby obtaining associated node performance change data;

[0062] Step S455: constructing an interference source signal attenuation model based on the associated node performance change data and the interference source associated topology structure data;

[0063] Step S456: Identify interference-affected nodes on the communication network topology model using the interference source signal attenuation model, thereby obtaining interference source-affected node data.

[0064] The present invention can obtain topological data that effectively characterizes the interference sources generated in real-time communication through the extraction of interference source network topology distribution features. This process makes it possible to accurately locate the interference source, thereby laying the foundation for the subsequent interference source associated topological structure matching. Based on the interference source associated topological structure matching of the communication network topological structure model, through the in-depth analysis of the interference source network topological distribution data, the correlation relationship between the interference source and the network environment in which it is located can be accurately identified, which helps to further understand the specific distribution and influence mode of the interference source in the network. Through the extraction of associated node performance features, the performance indicators of each node in the network can be extracted to help evaluate the working status of these nodes under the interference environment. The associated node performance data provides reliable data support for the subsequent node performance change calculation, so that the performance and change of the node under the influence of the interference source can be accurately predicted and judged, and the sudden decline of network performance can be prevented. With the acquisition of node performance change data, based on the combination of this data and the interference source associated topological structure, the interference source signal attenuation model is constructed, thereby realizing the quantitative analysis of the influence of interference source signal attenuation on each node in the communication network. By applying the interference source signal attenuation model, we can effectively identify the nodes that are most affected by the interference source, and further locate the scope and severity of the interference source. This process not only helps to improve the intelligence level of network operation and maintenance management, but also provides a scientific basis for network optimization and fault prediction, thereby improving the stability and reliability of the communication network.

[0065] Optionally, step S5 specifically includes:

[0066] Step S51: performing an impact node-network slice association on the interference source impact node data and the network slice transmission resource allocation data, thereby obtaining impact node-network slice association data;

[0067] Step S52: extracting the associated slice network load characteristics of the real-time network communication data according to the influencing node-network slice association data, thereby obtaining the associated slice network load data;

[0068] Step S53: quantifying the node interference of the interference source impact node data according to the interference source signal attenuation model, thereby obtaining the impact node interference data;

[0069] Step S54: estimating the interference impact factor based on the associated slice network load data and the interference data of the influencing node, thereby obtaining the interference impact factor;

[0070] Step S55: Reallocate the transmission resources of the network slice transmission resource allocation data to obtain the network slice transmission optimization resource allocation data, and upload it to the communication management platform to execute the data transmission task.

[0071] The present invention associates the interference source impact node data and the network slice transmission resource allocation data, which can ensure that the mutual influence of the interference source and the network slice is fully identified and considered, thereby providing accurate information support for subsequent network optimization. This association between the interference source and the network slice not only helps to timely discover potential load bottlenecks in the network, but also helps the network management system to better understand the working conditions of different slices, so as to more accurately allocate resources. By extracting the slice network load characteristics of real-time network communication data based on the impact node-network slice association data, real-time load monitoring and analysis can be achieved. This process can not only provide dynamic observation of the load status of different network slices, but also provide a scientific basis for subsequent load balancing and resource allocation, thereby effectively avoiding communication delays or disconnection caused by excessive load. When the interference source impact node data is quantified in combination with the interference source signal attenuation model, the actual impact of the interference source on the network performance can be more accurately quantified, especially in complex communication environments, where the interference source is often an important factor affecting network stability. Through accurate interference quantification, nodes that have a negative impact on network quality can be identified in a timely manner, thereby providing data support for subsequent interference suppression and optimization. Combining network slice load data and interference node interference data, the interference impact factor is estimated, providing quantitative indicators for network optimization. This process can not only evaluate the performance of existing network slices, but also predict the performance of the network under different interference environments, helping the communication management platform to make smarter resource adjustment decisions. Reallocating the transmission resources of network slices not only optimizes the efficiency of resource use, but also adapts to changes in network load and interference through dynamic adjustment, ensuring that communication quality is always in the best state. The optimized data uploaded to the communication management platform can effectively guide the execution of data transmission tasks and improve the overall performance and stability of the system.

[0072] Optionally, the present invention further provides a data transmission system applicable to 5G communication, which is used to execute the data transmission method applicable to 5G communication as described above, and the data transmission system applicable to 5G communication includes:

[0073] A topology analysis module is used to obtain network communication data, and perform communication network topology analysis based on the network communication data, thereby obtaining a communication network topology model; and perform communication demand analysis based on the communication network topology model, thereby obtaining regional communication demand data;

[0074] A behavior pattern classification module is used to classify user behavior patterns according to regional communication demand data, thereby obtaining regional user traffic behavior pattern data; and to allocate communication transmission resources according to the regional user traffic behavior pattern data, thereby obtaining communication transmission resource allocation data;

[0075] The slice resource allocation module is used to create an independent logical virtual network slice for the communication transmission resource allocation data, so as to obtain the virtual network slice data; perform network slice transmission resource allocation according to the virtual network slice data, so as to obtain the network slice transmission resource allocation data, and upload it to the communication management platform to perform the data transmission task;

[0076] The interference source impact node identification module is used to obtain real-time network communication data, and identify communication interference on the real-time network communication data according to the network slice transmission resource allocation data, so as to obtain real-time communication interference data; the interference source impact node identification is performed on the real-time communication interference data through the communication network topology structure model, so as to obtain the interference source impact node data;

[0077] The communication interference optimization module is used to optimize the communication interference of the network slice transmission resource allocation data according to the node data affected by the interference source, so as to obtain the network slice transmission optimization resource allocation data and upload it to the communication management platform to perform the data transmission task.

[0078] The data transmission system suitable for 5G communication of the present invention can implement any data transmission method suitable for 5G communication of the present invention, and is used to combine the operation and signal transmission medium between various modules to complete the data transmission method suitable for 5G communication. The internal modules of the system cooperate with each other, thereby improving the management efficiency and response speed of network resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0080] Figure 1 It is a schematic diagram of the steps of the data transmission method applicable to 5G communication of the present invention;

[0081] Figure 2 Detailed step flow diagram of step S1 in the present invention;

[0082] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0083] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0084] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0085] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0086] To achieve this, please refer to Figure 1 to Figure 2 , the present invention provides a data transmission method suitable for 5G communication, comprising the following steps:

[0087] Step S1: Acquire network communication data, and perform communication network topology analysis based on the network communication data, thereby obtaining a communication network topology model; perform communication demand analysis based on the communication network topology model, thereby obtaining regional communication demand data;

[0088] In this embodiment, in the communication network, communication data for a period of time is collected through network sensors, routers, switches and other devices, including information such as traffic, delay, and bandwidth utilization. Then, network topology analysis tools (such as GraphNeural Networks, GNN) are used to process these data to generate a communication network topology model. This topology model describes the connection relationship and performance indicators between various nodes (such as base stations, routers, switches, etc.). For example, in a wireless communication network in a city, the connection data and communication parameters of all base stations are first obtained. By analyzing these data, a graph structure can be established, in which the nodes of the graph represent base stations, the edges represent the communication links between base stations, and the bandwidth, delay and other information of the links are attached. According to this topology model, hot spots and communication bottlenecks in the network can be further identified. Then, by analyzing the topology model, the regional distribution of communication demand can be determined to obtain regional communication demand data. For example, some areas may have higher communication demands due to factors such as dense population and business activities, while other areas may have lower demands.

[0089] Step S2: classifying user behavior patterns according to regional communication demand data, thereby obtaining regional user traffic behavior pattern data; allocating communication transmission resources according to the regional user traffic behavior pattern data, thereby obtaining communication transmission resource allocation data;

[0090] In this embodiment, based on the obtained regional communication demand data, user behaviors are classified through machine learning algorithms (such as K-means clustering, decision trees, support vector machines, etc.). For example, by analyzing the traffic patterns of users in a commercial area, it is found that the traffic demand of users surges during peak hours, while the demand is lower during non-peak hours. Based on these behavior patterns, users are divided into different categories such as "peak-time active type", "all-weather stable type" and "off-peak period dependent type". Furthermore, by analyzing the traffic characteristics of each category (such as traffic size, volatility, etc.), a corresponding behavior model can be established. For example, the traffic of "peak-time active type" users usually reaches the highest value between 9 am and 12 pm, and there is a secondary peak between 4 pm and 6 pm. Based on these behavior pattern data, communication resources can be dynamically allocated to ensure that resources are prioritized during high-traffic periods to avoid network congestion.

[0091] Step S3: Create an independent logical virtual network slice for the communication transmission resource allocation data to obtain virtual network slice data; perform network slice transmission resource allocation according to the virtual network slice data to obtain network slice transmission resource allocation data, and upload it to the communication management platform to execute the data transmission task;

[0092] In this embodiment, virtual network slices are created based on regional user traffic behavior pattern data. Each virtual network slice corresponds to one or more user behavior patterns and has specific bandwidth, latency, and QoS (quality of service) requirements. Through network virtualization technologies (such as SDN and NFV), network resources are divided, and each slice can run independently on the physical network infrastructure as if they were independent networks. For example, for "peak-active" users, a high-priority virtual network slice can be created to allocate higher bandwidth and low-latency resources. For "off-peak-dependent" users, lower bandwidth and relaxed latency requirements may be allocated. Afterwards, the network slice resource management platform is used to allocate resources to these slices to ensure that each slice obtains sufficient resources when needed. The resource allocation strategy of the slice may consider factors such as traffic prediction, load balancing, and link redundancy.

[0093] Step S4: acquiring real-time network communication data, and performing communication interference identification on the real-time network communication data according to the network slice transmission resource allocation data, thereby obtaining real-time communication interference data; performing interference source impact node identification on the real-time communication interference data through the communication network topology structure model, thereby obtaining interference source impact node data;

[0094] In this embodiment, after collecting real-time network communication data through network sensors, routers, switches and other devices, an interference detection algorithm (for example, a statistical method based on indicators such as signal strength change, delay fluctuation, and signal-to-noise ratio) is used to identify the source of communication interference. Based on the resource allocation data of the network slice, the communication quality of each slice is monitored to detect whether there is interference, especially during high-load periods. For example, an abnormal increase in network traffic is detected near a base station because of interference caused by frequency overlap of neighboring base stations. Through real-time data monitoring, the affected nodes (such as base stations or routers) can be analyzed and the specific sources of interference can be identified. For example, if the interference source comes from a base station in a certain frequency band, it can be inferred that the interference in this frequency band affects the communication quality of multiple adjacent nodes. Using a machine learning-based prediction model, the interference source identification process can be tracked and optimized in real time to improve identification accuracy and response speed.

[0095] Step S5: Perform communication interference optimization on the network slice transmission resource allocation data according to the interference source impact node data, so as to obtain the network slice transmission optimization resource allocation data, and upload it to the communication management platform to execute the data transmission task.

[0096] In this embodiment, interference optimization is performed through the resource allocation management platform of the network slice according to the data of the node affected by the identified interference source. The optimization strategy includes adjusting the spectrum allocation of the interference source, modifying the transmission power, adjusting the bandwidth allocation of the network slice, etc. For example, when the interference source is a base station, the interference to the adjacent network slice can be reduced by reducing the power output of the base station or adjusting its communication frequency. In addition, additional auxiliary base stations can be deployed near the interference source or the traffic scheduling of the existing network can be changed to optimize resource allocation. For example, the traffic routing strategy is changed to guide high-traffic users to areas with less interference, or more resources are dynamically allocated to the affected areas. The optimized resource allocation data will be uploaded to the communication management platform to ensure that the communication network can run more efficiently after optimization while reducing the impact of interference. The communication management platform will adjust the resource allocation strategy of each slice according to the latest optimization data to ensure that the real-time data transmission task can be executed smoothly.

[0097] Optionally, step S1 specifically includes:

[0098] Step S11: acquiring network communication data, and performing data preprocessing on the network communication data, thereby obtaining communication data to be processed;

[0099] In this embodiment, network communication data is obtained from different data sources (such as communication base stations, routers, user equipment, etc.). These data may include but are not limited to network performance indicators such as user traffic information, data packets, signal strength, transmission rate, delay, packet loss rate, etc. In the data acquisition process, a distributed data collection method is adopted to ensure that a complete communication data set is collected from different locations and different time periods. When preprocessing these raw data, data cleaning is first performed to remove irrelevant or abnormal values ​​(for example, packet loss or erroneous signal data). Then, the data is formatted by standardization, normalization, etc. to ensure that it has a consistent structure and unit. Finally, the data is time-series calibrated to ensure that the data is arranged in chronological order for subsequent analysis.

[0100] Step S12: extracting communication connection features according to the communication data to be processed, thereby obtaining communication connection data, and identifying communication base stations based on the communication connection data, thereby obtaining regional communication base station connection data;

[0101] In this embodiment, effective connection information, such as connection duration, connection frequency, bandwidth requirements, signal strength, etc., is extracted from the communication data to be processed. These features can help determine the quality and stability of different communication connections. Next, based on these connection features, a machine learning algorithm (such as K-means clustering, support vector machine, etc.) is used to identify the communication base station. By clustering the user's connection data, it is possible to identify which base stations are responsible for the communication in which areas, and establish a connection relationship between the base stations. Finally, the connection data of the regional communication base station is obtained, including information such as the coverage range, connection load, and communication quality of each base station. Base station identification refers to identifying which base station the communication connection belongs to by analyzing the communication connection characteristics. This process usually requires a geographic information system (GIS) combined with a positioning algorithm, such as using the user's location information or the known location of the base station to match the base station. Assuming that a user is located in a certain area, the area contains multiple base stations. The spatial relationship between the communication connection quality data (such as signal strength) and the base station location can be used to identify the connected base station. Finally, the regional communication base station connection data is obtained, which contains the connection status between each base station and the user.

[0102] Step S13: dividing the communication data to be processed into base station network cell communication data based on the regional communication base station connection data, thereby obtaining network cell communication data;

[0103] In this embodiment, the base station connection data is refined to the cell level to further analyze the network cells. Base stations usually cover multiple cells, so it is necessary to divide the regional communication base station connection data into cells. Each cell of the base station has its specific coverage area and communication characteristics, such as cell ID, frequency, signal quality, etc. For example, if a base station provides services in multiple cells, each connection can be classified according to the cell ID. For example, base station A covers cell 1, cell 2, and cell 3, and the received communication data will be divided according to the cell ID to ensure that the data of each cell is processed independently. The final network cell communication data contains the communication connection information in each cell, such as the number of users, data flow, signal quality, etc.

[0104] Step S14: performing a cell network topology analysis based on the network cell communication data to obtain a cell network topology model, and performing a communication topology merger on the cell network topology model according to the regional communication base station connection data to obtain a communication network topology model;

[0105] In this embodiment, based on the analysis of the cell communication data, a network topology model of the cell can be constructed. The topology model can reflect the connection relationship between each cell and the dependency relationship with the base station. Using a network topology analysis method, such as a graph theory algorithm, the communication links between each cell can be identified, and a graph model can be constructed, in which the nodes represent the cells and the edges represent the communication links between the cells. For example, in a communication network in a certain city, there may be high-quality connections between cells 1 and 2 covered by base station A, while base station B covers cells 3 and 4, and there may be weak connections between them. Through this network topology analysis, the communication path between the cells can be obtained. Next, the topology structure is merged based on the regional communication base station connection data, and the network connection information of the base station and the cell is merged to form a complete communication network topology model. This topology model will reflect the connection mode and communication quality between each base station and cell.

[0106] Step S15: Perform communication demand analysis based on the communication network topology model to obtain regional communication demand data.

[0107] In this embodiment, the communication demand analysis is performed using the constructed communication network topology model. The core of the communication demand analysis is to predict the communication demand in different areas and evaluate whether the network can meet these demands. During the analysis, various factors may need to be considered, such as the number of users, data traffic, signal coverage, base station load, etc. For example, suppose there is a shopping mall and a residential area in a certain area, the communication demand of the shopping mall is higher, while the demand of the residential area is lower. Based on the network topology model, it can be predicted that the shopping mall area may have a higher data traffic demand during peak hours. Through simulation and algorithm analysis, specific regional communication demand data is obtained. These data can not only reflect the current network status, but also provide a basis for future network expansion and optimization.

[0108] Optionally, step S14 is specifically:

[0109] Step S141: extracting cell communication signal strength features from network cell communication data, thereby obtaining cell communication signal strength data;

[0110] In this embodiment, information including but not limited to received signal strength indication (RSSI) value, signal-to-noise ratio (SNR) value, and multiple dimensions such as time, frequency, and space of each network cell contained in the network cell communication data is extracted to obtain cell communication signal strength data.

[0111] Step S142: performing signal strength gradient analysis according to the cell communication signal strength data, thereby obtaining cell signal strength gradient data, and determining adjacent cell boundaries according to the cell signal strength gradient data, thereby obtaining adjacent cell boundary data;

[0112] In this embodiment, the acquired cell signal strength data is subjected to gradient analysis to calculate the rate of change of the signal strength in spatial distribution. Usually, a gradient operator (such as the Sobel operator) or a differential method is used to process the two-dimensional signal strength map to extract the change trend of the signal strength. By analyzing the gradient change, the change area of ​​the signal strength can be accurately determined, and then the boundaries of each cell can be determined. Specifically, when the gradient of the signal strength reaches a certain threshold, it can be considered that the cell boundary position has appeared. In this way, the boundary data of adjacent cells is obtained, thereby providing a basis for subsequent topological relationship analysis.

[0113] Step S143: integrating cell connection relationships based on adjacent cell boundary data, thereby obtaining cell connection relationship data;

[0114] In this embodiment, based on the obtained cell boundary data, the connection relationship between adjacent cells can be integrated through geometric methods or graph theory algorithms. For example, the connection relationship between multiple adjacent cells can be visualized or mathematically modeled using Delaunay triangulation, Voronoi diagram or other space partitioning algorithms. Furthermore, a connected component algorithm (such as depth-first search DFS) or a shortest path algorithm (such as Dijkstra) can be used to analyze the connection between cells. Through these technical means, the connection relationship data between cells is finally obtained, that is, which cells are directly connected.

[0115] Step S144: performing cell connection mode identification on the network cell communication data according to the cell connection relationship data, thereby obtaining cell connection mode data;

[0116] In this embodiment, by analyzing the cell connection relationship, it is identified how the cells are connected through wireless links, thereby helping to build a more effective network topology. Specifically, this process involves identifying different cell clusters, coverage areas, signal strength distributions, etc. The identification process can be completed by data mining, pattern recognition algorithms (such as clustering algorithms, graph theory methods, etc.). Data mining technology can be used to analyze cell connection data, and the connection structure between cells can be identified by exploring patterns in the data. For example, clustering analysis methods (such as K-means, DBSCAN) can be applied to divide the cells into several clusters, and the connection patterns between cells in each cluster can be identified. Identify connection clusters between cells. For example, the cells are divided into multiple groups by clustering algorithms, and the cells in the groups are closely connected, while the cells between groups are weakly connected. Analyze the overlap of coverage areas between cells, identify which cells have a larger intersection of coverage areas, and can work together to optimize network performance. The cells are regarded as nodes in the graph, and the connections between them are regarded as edges in the graph. Through graph analysis methods (such as shortest path algorithms, minimum spanning tree algorithms, community detection algorithms, etc.), the cell connection patterns in the network can be further identified. For example, the connectivity graph algorithm can be used to identify which cells belong to the same coverage area and which cells have the strongest signal links. Suppose that in a city's 5G network, a large amount of cell connection relationship data is collected. These data include the signal strength (RSRP), SINR, connection success rate, etc. between each cell and the adjacent cells. The collected data includes the connection data between multiple cells and surrounding cells. For example, the RSRP between cell A and cell B is -90dBm, the RSRP between cell A and cell C is -85dBm, and the RSRP between cell B and cell C is -80dBm. These data are organized into a matrix form to represent the signal strength relationship between each cell and other cells. Through the K-means clustering algorithm, all cells are divided into several clusters according to signal strength and connection quality. For example, the K-means algorithm may divide these cells into three groups: one group is cells A, B, and C with better signal strength, another group is cells D and E with weaker signals, and the third group is cells F and G with intersections in signal coverage. By constructing a graph, nodes represent cells and edges represent the signal connection strength between cells. We can use the graph connectivity algorithm to detect which cells are closely connected. For example, by calculating the connected components of the graph, we can find that cells A, B, and C form a strongly connected subgraph, while cells D and E belong to another weakly connected subgraph.

[0117] Step S145: constructing a cell network topology structure according to the cell connection mode data and the cell connection relationship data, thereby obtaining a cell network topology structure model;

[0118] In this embodiment, based on the cell connection mode data obtained in step S144 and the cell connection relationship data in step S143, a network modeling technology (such as graph modeling) is used to construct the network topology of the cell. Specifically, each cell can be regarded as a node, and the connection relationship between adjacent cells can be regarded as the edge between nodes. Through these data, a topological graph reflecting the communication relationship between cells is constructed. For example, graph algorithms such as the shortest path algorithm and the minimum spanning tree algorithm are used to optimize the connection between cells, making network communication more efficient. Finally, a cell network topology structure model is formed, showing the connection relationship and communication flow direction of each cell in the network.

[0119] Step S146: merging the cell network topology structure model according to the regional communication base station connection data to obtain a communication network topology structure model.

[0120] In this embodiment, the data of regional communication base stations are used to further optimize and merge the cell network topology. The specific operation is to integrate the connection relationship between communication base stations in different cells into the existing topology model. For example, the physical connection data (such as optical fiber, microwave link, etc.) between base stations is used to determine which cells are connected through base stations. Distance- or capacity-based optimization methods can be used to weight the connections between cells to ensure that the communication network topology not only reflects the connection relationship between cells, but also takes into account factors such as communication quality, bandwidth, and delay between base stations. Finally, the merged communication network topology model facilitates the overall analysis, optimization, and adjustment of the communication network.

[0121] Optionally, step S15 is specifically:

[0122] Step S151: extracting cell data throughput features from the communication network topology model, thereby obtaining cell data throughput data;

[0123] In this embodiment, the network traffic information of each network cell is obtained from the network topology model. The specific implementation method can be to monitor the traffic of the base station equipment of each cell and collect the uplink and downlink data traffic of each cell. The metering equipment of the base station (such as a traffic counter, a real-time data analysis system, etc.) can be used to extract the throughput characteristics. During implementation, the system will collect and summarize the data by time period (such as hours, days) to generate a throughput data set for each cell. For example, suppose there is a cell A in the network, and its base station has a traffic counter. By measuring the uplink and downlink throughput of the cell every hour and storing it in the database, the throughput data set of cell A is finally obtained. Other cells are also monitored and data recorded in a similar manner.

[0124] Step S152: performing time series statistics of cell data throughput according to the cell data throughput data, thereby obtaining cell high throughput time data and cell low throughput time data;

[0125] In this embodiment, a time series analysis is performed on the throughput data of each cell, and the throughput change trend is counted by time period (such as every hour, every day, etc.). Based on the statistical throughput value, a high throughput time period and a low throughput time period are determined. In specific implementation, a throughput threshold is set (for example, if it exceeds the threshold, it is a high throughput time period, and if it is below the threshold, it is a low throughput time period). For example, if the throughput of cell A exceeds 10Gbps from 9 to 10 pm, this time period can be marked as a "high throughput time period". If the throughput is less than 2Gbps from 5 to 6 in the morning, it is marked as a "low throughput time period". Such statistical data helps to identify which time periods have higher network bandwidth requirements and which time periods have lower requirements.

[0126] Step S153: Calculate the cell throughput time ratio based on the cell high throughput time data and the cell low throughput time data, thereby obtaining the cell throughput time ratio data;

[0127] In this embodiment, the throughput time ratio is calculated based on the high throughput and low throughput time data. The specific method is to calculate the ratio of the duration of the high throughput period to the duration of the low throughput period. For example, if the high throughput period of a cell is 20 hours long and the low throughput period is 4 hours long, then the throughput time ratio is 20:4 or 5:1. The duration of the high throughput and low throughput periods of each cell is counted and the ratio is calculated to obtain the throughput time ratio data of each cell. Such ratio data helps to measure the throughput fluctuation of each cell, and then perform reasonable network optimization and resource allocation.

[0128] Step S154: dividing the communication network topology model into communication cells according to the cell throughput time ratio data, thereby obtaining high-throughput and high-ratio cell data and low-throughput and high-ratio cell data;

[0129] In this embodiment, the cells are divided according to the throughput time ratio data. Specifically, the cells with higher high throughput time ratio (for example, the ratio is greater than a preset threshold) are divided into "high throughput and high proportion cells", and the cells with lower high throughput time ratio are divided into "low throughput and high proportion cells". This helps to optimize network resources according to throughput requirements and time proportion. For example, assuming that the ratio of high throughput time to low throughput time in cell B is 10:1, which is much higher than other cells, then the cell can be divided into a "high throughput and high proportion cell". If the ratio of cell C is 1:5, it can be divided into a "low throughput and high proportion cell". Through this division, the network management system can dynamically allocate resources according to the needs of different cells.

[0130] Step S155: integrating cell communication demands according to the high-throughput and high-ratio cell data, thereby obtaining high-communication demand cell data; integrating cell communication demands according to the low-throughput and high-ratio cell data, thereby obtaining low-communication demand cell data;

[0131] In this embodiment, the data of high-throughput and high-proportion cells and low-throughput and high-proportion cells are further analyzed to integrate the communication demand data of each cell. The integration method can be to count the total bandwidth demand and the number of users of each cell during the high-throughput period and the low-throughput period, so as to obtain the communication demand of each cell. For high-throughput and high-proportion cells, their communication demand is usually high, while low-throughput and high-proportion cells may have a lower demand for bandwidth. For example, the communication demands of multiple cells can be summarized by region to obtain the total demand data in a certain area. This helps network planners to effectively allocate resources to cells in different regions. Cells with high communication demand need to add base stations or expand bandwidth, while cells with low communication demand may not require too much resource investment.

[0132] Step S156: regional spatial merging of the high communication demand cell data and the low communication demand cell data to obtain regional communication demand data.

[0133] In this embodiment, the cell data with different high communication demands and low communication demands are spatially merged to generate the overall communication demand data of the region. The total communication demand data of a region is integrated according to the geographical location, throughput demand and time proportion of the cell. For example, the demand data of multiple cells can be superimposed on a regional map through GIS (Geographic Information System) to calculate the total bandwidth demand, total number of users and other data in the region. Through spatial merging, a heat map of communication demand in a certain area is obtained, thereby providing a basis for network optimization.

[0134] Optionally, step S2 specifically includes:

[0135] Step S21: Divide the regional communication demand data into time windows, thereby obtaining regional communication demand window data;

[0136] In this embodiment, the communication demand data of the region is divided into windows according to preset time intervals (such as hours, half an hour or shorter time periods). The communication demand data in each time window can be analyzed and processed independently. For example, if the collected data is the user's uplink and downlink traffic, these data can be aggregated and processed according to time periods such as every hour and every 15 minutes to generate traffic demand data in each window. In this way, a regional communication demand window data set will eventually be obtained, in which each time window corresponds to the communication demand situation within a period of time.

[0137] Step S22: extracting regional user connection features according to the regional communication demand window data, thereby obtaining regional user connection time period data and regional user flow window data;

[0138] In this embodiment, the connection feature data in each time window is extracted using the obtained regional communication demand window data. For example, by analyzing the number of communication connections, connection duration, user activity and other information in each time window, the "regional user connection time period data" can be obtained. This can be done by statistically analyzing the number of active users in the region in each time period and the communication load in each time period. At the same time, based on the changing trend of the traffic data, the "regional user traffic window data" is extracted. For example, based on the fluctuations in the uplink and downlink traffic in the time window, the traffic peak period, traffic trough period, etc. are calculated to reflect the user's traffic demand in the period.

[0139] Step S23: performing regional user connection period distribution analysis based on the regional user connection period data, thereby obtaining regional user connection period distribution data, and performing connected user mobility pattern recognition based on the user connection period distribution data, thereby obtaining user mobility pattern data;

[0140] In this embodiment, the regional user connection time period data is analyzed to understand the user's connection status in different time periods. Through statistical analysis, a connection time period distribution data can be obtained, for example, in which time periods the number of user connections is the largest, and in which time periods the number of user connections is less. This time period distribution data can be presented in the form of heat maps, time period frequency maps, etc. Then, based on these connection time period distribution data, combined with GPS or other location information, the user's movement pattern is identified through machine learning or rule modeling. For example, in certain time periods, if the user moves frequently between fixed areas, it indicates that the user has a specific travel mode, such as commuting mode, shopping mode, etc. Finally, "user movement pattern data" can be obtained, which describes the user's activity trajectory and behavior pattern in different time periods.

[0141] Step S24: performing regional user traffic periodicity analysis according to the regional user traffic window data, thereby obtaining regional user traffic periodicity data, and performing user traffic behavior pattern recognition based on the regional user traffic periodicity data, thereby obtaining a user traffic behavior pattern;

[0142] In this embodiment, by performing periodic analysis on the regional user traffic window data (for example, using Fourier transform, periodic analysis algorithm, etc.), the periodic pattern of traffic changes in different time periods can be identified. For example, the traffic in certain areas fluctuates regularly every day during certain time periods, such as rush hour, or the traffic changes significantly on specific days (such as weekends). Through periodic analysis, "regional user traffic periodic data" can be obtained. Subsequently, based on these periodic data, traffic behavior pattern recognition can be performed, and clustering algorithms or pattern recognition algorithms, such as K-means, decision trees, etc., can be used to analyze the user's traffic behavior pattern, such as the concentration of user traffic peaks in certain time periods and low user traffic in certain time periods. These traffic behavior patterns can help operators understand users' traffic demands and usage habits in different time periods, and thus optimize network resource allocation.

[0143] Step S25: integrating the user behavior patterns based on the user mobility pattern data and the user traffic behavior patterns, thereby obtaining regional user traffic behavior pattern data;

[0144] In this embodiment, the obtained user mobility pattern data is integrated with the user traffic behavior pattern data to fully understand the traffic demand characteristics and behavior trends of regional users. Specifically, multidimensional data fusion technology can be used to combine the user's traffic demand in different time periods with their mobility behavior to generate "regional user traffic behavior pattern data". For example, by combining travel patterns with traffic usage patterns, the traffic demand of certain specific groups (such as commuting users) during rush hours and their correlation with location changes can be obtained. This process may involve the application of data mining and machine learning models (such as collaborative filtering, cluster analysis, etc.) to help discover potential user behavior patterns, and then conduct accurate traffic prediction and resource optimization.

[0145] Step S26: performing communication transmission resource allocation according to the regional user traffic behavior pattern data, thereby obtaining communication transmission resource allocation data.

[0146] In this embodiment, communication transmission resources are dynamically allocated based on the obtained regional user traffic behavior pattern data and the actual load of the communication network in the region. This can be achieved through resource optimization algorithms (such as genetic algorithms, reinforcement learning, etc.), and the bandwidth, spectrum resources and base station access strategies in the region are intelligently adjusted according to different time periods and user behavior patterns. For example, if it is found that the user traffic in the region surges during certain time periods (such as rush hour), the resource allocation of the base station can be automatically adjusted to give priority to the traffic needs of commuting users. At this time, the communication transmission resource allocation data may include the load of each base station, the bandwidth allocation, etc. Through this strategy, the utilization efficiency of the communication network can be improved, resource waste can be reduced, and the communication experience of users during high traffic periods can be ensured.

[0147] Optionally, step S3 specifically includes:

[0148] Step S31: integrating the regional communication resource demand model according to the regional communication demand data, thereby obtaining the regional communication resource demand data;

[0149] In this embodiment, according to the regional communication demand data, machine learning or data clustering methods are used to perform pattern recognition on the communication demand. For example, the K-means algorithm or Gaussian mixture model can be used to cluster different types of communication demands to find out the communication demand patterns of each region. This model not only takes into account the changes in the number of users, but also includes different requirements of geographical location, user active time, and application scenarios (such as high-definition video, AR / VR, etc.). The regional communication resource demand data after final integration can accurately describe the future resource demand distribution in the region and provide a basis for subsequent resource pool division and network slice creation. Assume that during the peak hours of a certain area, the user traffic demand in some areas is large, while that in other areas is relatively small. Through this integrated analysis, the communication resource demand pattern in different time periods and different regions can be accurately predicted. The "regional communication resource demand data" finally generated will include specific time, area, and traffic requirements to help subsequent resource allocation and network planning.

[0150] Step S32: dividing the slice resource pool based on the communication transmission resource allocation data, thereby obtaining slice resource pool data;

[0151] In this embodiment, the network slice resource pool is divided based on the regional needs and available resources using communication transmission resource allocation data (such as bandwidth, latency, reliability and other indicators). By analyzing the capacity of communication resources in each region, the slice resource pool can be dynamically divided on demand. Assuming that the bandwidth resource in the network resource pool is 10Gbps, by calculating and allocating the demand for each virtual slice, slices are made according to the specific needs of regional services (such as large-scale IoT device connections or high-definition video streaming). The division of resource pools can be optimized according to the priority of different communication needs, quality of service (QoS) requirements, and network available bandwidth. For example, a higher priority resource pool is allocated for delay-sensitive services (such as autonomous driving and telemedicine), while a lower priority resource pool is provided for regular Internet access. Different resource pools can be divided according to the diversity of communication needs (such as low latency, high bandwidth, and high reliability). Assuming that the industrial Internet demand in a certain area has high requirements for low latency and high reliability, the network resource pool in the area may be divided into a low-latency and high-priority resource pool, while the data traffic for ordinary users can be divided into a standard bandwidth resource pool.

[0152] Step S33: dividing the network topology structure according to the communication network topology structure model, thereby obtaining network topology structure data;

[0153] In this embodiment, the existing communication network is divided by a network topology model. The communication network topology model includes a detailed layout of all nodes (such as base stations, switches, routers, etc.) and links (such as optical fibers, microwave links, wireless links, etc.) in the network. Specifically, the network topology can be modeled using a graph theory method. By inputting existing network topology data (such as base station location, link bandwidth, network delay, coverage, etc.), the network is divided using a graph cutting algorithm (such as a K-means clustering algorithm) to generate multiple sub-network topologies, representing different business demand areas. For example, considering the different needs of the core network, edge network, and access network, multiple topology sub-networks can be divided, and each sub-network can serve different application scenarios (such as smart cities, industrial automation, etc.). In the process of topology division, the capabilities and locations of network devices must also be considered to ensure efficient allocation of resources. The deployment density and user distribution of base stations in the region can also be considered, and the network can be divided into multiple sub-areas through optimization algorithms (such as K-means clustering, shortest path algorithm, etc.) to reduce network congestion and improve resource utilization. Assuming that the user traffic in the core area of ​​a city is large, while the user density in the suburban area is low, the core area and suburban area of ​​the city can be divided into different topological sub-areas.

[0154] Step S34: Creating a virtual network slice according to the network topology data, the slice resource pool data, and the regional communication resource demand data, thereby obtaining virtual network slice data, and performing slice priority division on the virtual network slice data, thereby obtaining virtual network slice priority data;

[0155] In this embodiment, virtual network slices are created based on the previously obtained network topology data, slice resource pool data, and regional communication resource demand data. Each virtual network slice is allocated corresponding resources from the resource pool according to its specific requirements (such as bandwidth, latency, reliability, etc.). The creation of virtual network slices involves dividing physical network resources into multiple logically independent slices. The dynamic configuration of virtual network slices is achieved through SDN (Software Defined Network) and NFV (Network Function Virtualization) technologies. During the creation process, a priority division strategy is adopted to prioritize virtual slices of different service types. For example, low-latency slices (such as telemedicine and autonomous driving) are given higher priorities, while high-bandwidth video stream slices may have lower priorities. Virtual network slice priority data is determined based on the urgency of business needs and service quality requirements. Assume that in a certain area, the demand for industrial automation has low network latency requirements, while the demand for high-definition video streams has high bandwidth requirements. In this case, a low-latency virtual slice is created for industrial automation control, and a high-bandwidth priority virtual slice is created for high-definition video streams. The priority of each virtual slice is divided according to the type of service it serves.

[0156] Step S35: extracting the priority slice configuration of the virtual network slice priority data to obtain the priority slice configuration data, and estimating the slice resource demand according to the priority slice configuration data to obtain the priority slice resource demand data;

[0157] In this embodiment, slice configuration extraction is performed according to the priority data of the virtual network slice. Priority slice configuration data is generated by dynamically analyzing the resource requirements and priorities of different slices. For each virtual network slice, a resource requirement estimation model (such as a regression analysis model based on load prediction) is used to estimate its resource requirements. For example, a high-priority slice (such as an autonomous driving slice) has a large bandwidth requirement and an extremely low latency requirement, so the resource requirement of the slice will be allocated with a higher priority in the estimation. The priority slice resource requirement data includes estimates of bandwidth, latency, computing power, storage, and other aspects. Through this data, the resource allocation of the network slice can be dynamically adjusted to ensure that high-priority services obtain sufficient resources. Based on the obtained virtual network slice priority data, the resource requirements of each virtual network slice are further estimated. For example, it is assumed that a high-priority slice (such as an industrial automation slice) requires lower latency and higher reliability, while a low-priority slice (such as ordinary web browsing) has a higher bandwidth requirement. In the resource requirement estimation process, a machine learning-based prediction model (such as regression analysis, decision tree, etc.) can be used for accurate calculation to estimate the bandwidth, latency, computing power, and other resources required for each slice.

[0158] Step S36: Allocate transmission resources for virtual network slice data according to the priority slice resource demand data, thereby obtaining network slice transmission resource allocation data, and upload it to the communication management platform to execute the data transmission task.

[0159] In this embodiment, transmission resources are allocated to virtual network slices according to the generated priority slice resource demand data. Transmission resource allocation involves factors such as bandwidth, routing selection, and network topology path optimization. The transmission resources of different virtual slices can be dynamically adjusted through a network resource scheduling platform (for example, a resource scheduling mechanism based on an SDN controller). Network transmission resources can also be dynamically allocated using a resource scheduling algorithm (such as a fair sharing algorithm or a priority scheduling algorithm) according to the priority and demand characteristics of each virtual slice (such as bandwidth, latency, reliability, etc.). In actual applications, high-priority virtual slices may have priority in obtaining bandwidth and computing resources, while low-priority slices will be allocated according to the remaining resources. In addition, it is necessary to monitor the resource usage of the network in real time and adjust the slice resource allocation strategy in a timely manner. For example, during the peak period of network load, the network path will be adjusted according to the priority data to ensure the bandwidth and latency requirements of high-priority slices. After completing resource allocation, all transmission resource data will be uploaded to the communication management platform, and the platform will execute the data transmission task through the corresponding control interface. In this process, the resource allocation data includes the bandwidth, path, congestion control strategy, etc. of each slice.

[0160] Optionally, step S4 is specifically:

[0161] Step S41: acquiring real-time network communication data, and dividing the real-time network communication data into slice communication data, thereby obtaining real-time 5G slice communication data;

[0162] In this embodiment, a dedicated network data capture device or software tool is used to monitor network traffic in real time at the core network, access network, or wireless access network level. Network protocol analysis tools (such as Wireshark or a dedicated 5G network slicing monitoring platform) can be used to obtain real-time network communication data packets. Next, these data packets are sliced ​​and divided, and the communication data is sliced ​​according to its business needs according to the preset network slicing configuration (such as eMBB, URLLC, mMTC, etc.). Specifically, by analyzing the traffic characteristics of the data packets, different business flows are divided into different network slices and saved as independent slice data. These slice communication data will contain information such as bandwidth, delay, data flow, etc. of each slice as the basis for subsequent analysis.

[0163] Step S42: Performing network slice communication transmission simulation according to the network slice transmission resource allocation data, thereby obtaining network slice communication transmission simulation data;

[0164] In this embodiment, based on the acquired real-time 5G slice communication data, combined with the resource allocation strategy of the network slice (such as bandwidth allocation on demand, priority scheduling, etc.), the transmission simulation of the network slice is performed. This simulation process can be completed by using a network simulation platform (such as NS3 or OMNeT++). During the simulation process, it is necessary to allocate resources according to the configurations such as the priority, bandwidth limit, and latency requirements of each slice, and simulate the resource contention and scheduling between network slices. The output data of the transmission simulation includes indicators such as the actual throughput, latency, and packet loss rate of each network slice. These simulation data can be used to evaluate the performance of the network slice and provide a basis for subsequent optimization.

[0165] Step S43: Calculate the slice communication performance error of the network slice communication transmission simulation data and the real-time 5G slice communication data, so as to obtain slice communication performance error data;

[0166] In this embodiment, the obtained network slice transmission simulation data is compared and analyzed with the real-time 5G slice communication data obtained in step S41. Specifically, by calculating the difference between the network slice transmission simulation data and the actual communication data (such as the error of indicators such as throughput, delay, and packet loss rate), an error analysis model (such as mean square error MSE, mean absolute error MAE, etc.) is used to quantify the performance error. The calculated error data helps to reveal the gap between the simulation and the actual network conditions and provide feedback for network optimization. This step is crucial to identifying the performance bottleneck of the network slice, and can reveal hidden dangers such as resource configuration problems of the slice and unbalanced network load.

[0167] Step S44: performing high error amplitude slice statistics according to the slice communication performance error data, thereby obtaining communication interference slice data, and identifying communication interference sources based on the communication interference slice data, thereby obtaining real-time communication interference data;

[0168] In this embodiment, according to the calculated slice communication performance error data, communication slices with high error margins are identified through statistical analysis of the error data. These errors may be caused by factors such as communication interference, network congestion, and insufficient spectrum resources. Slices with high error margins are manifested as large delays, packet loss rates, or insufficient throughput. Furthermore, based on these slice data with high error margins, signal processing and machine learning algorithms (such as clustering analysis, anomaly detection, etc.) are used to identify possible sources of communication interference. Interference source identification can be accomplished by analyzing factors such as the change pattern of network traffic, the load of base stations, and the network topology. The identified interference sources may be spectrum interference between adjacent base stations, wireless signal shielding, and other problems, forming real-time communication interference data.

[0169] Step S45: using the communication network topology model to identify interference source impact nodes on the real-time communication interference data, thereby obtaining interference source impact node data.

[0170] In this embodiment, by establishing a topological structure model of the communication network (such as the distribution of base station locations, access points, user equipment, etc.), the identified communication interference data is combined with the network topology for analysis. At this time, network topology analysis tools (such as Gephi, Graph-tool, etc.) can be used to simulate the impact of interference sources on different network nodes. For example, the network topology model is used to analyze the impact of a certain interference source (such as an overly strong signal or spectrum interference of a specific base station) on surrounding base stations or user equipment. By modeling data such as the signal interference propagation path and signal strength between nodes, the network nodes that are most severely interfered are identified. These interfered nodes are "interference source affected nodes", and their data can be used for further network optimization and interference management.

[0171] Optionally, step S45 is specifically:

[0172] Step S451: extracting interference source network topology distribution features from real-time communication interference data, thereby obtaining interference source network topology distribution data;

[0173] In this embodiment, a graph theory or topology analysis method is used to calculate the distribution of interference sources in the network topology based on the interference data. For example, a positioning algorithm (such as location-based interference source positioning) can be used to determine the specific location of the interference source and map it to the network topology. These data are extracted and form interference source network topology distribution data, including the relationship between the interference source and each node in the network. For example, in a 5G communication network, wireless signal interference data near each base station (BS) is collected, and the topological relationship between the interference source and each base station is extracted through positioning technology and interference intensity analysis, thereby obtaining an interference source distribution map. According to the spatial distribution characteristics of the interference source, the interference source network topology distribution data is constructed, such as the area corresponding to each interference source, the signal strength distribution, and the affected network equipment (such as base stations, routers, access points, etc.).

[0174] Step S452: performing interference source associated topology structure matching on the interference source network topology allocation data through the communication network topology structure model, thereby obtaining interference source associated topology structure data;

[0175] In this embodiment, the interference source network topology allocation data is matched with the communication network topology. For example, the location of the interference source is matched with the network node based on a similarity metric (such as Euclidean distance, Manhattan distance, etc.). According to the matching results, the association information between the interference source and the network topology structure is obtained, such as which network nodes the interference source affects, the degree of influence, etc. It is assumed that the communication network uses a traditional cellular network structure, in which the connection relationship between the base station, the core router and the terminal is known. By comparing the interference source data with the nodes (such as base stations, routers) and their connection relationships in the network topology model, it is identified which nodes in the network are associated with each interference source. For example, the signal interference of a base station may affect multiple access terminals. The matching results can identify the location of these terminals in the topology map and the degree of their impact, thereby obtaining the interference source associated topology structure data.

[0176] Step S453: extracting performance characteristics of associated nodes from the interference source associated topology data based on the real-time network communication data, thereby obtaining associated node performance data;

[0177] In this embodiment, based on the obtained interference source associated topology data, performance characteristics of each node involved in the network (such as base stations, routers, and user terminals) are extracted. These performance characteristics include network performance indicators such as signal strength, throughput, delay, and packet loss rate. For example, if the throughput of a user terminal is reduced due to interference from a certain base station, parameters such as the throughput, signal strength, and delay of the terminal can be extracted from the real-time network communication data, and the network performance degradation of the terminal can be evaluated through these data. Finally, the performance data of each associated node is obtained, such as "Terminal B in the area affected by base station A has a throughput reduction of 30% and a delay increase of 5ms."

[0178] Step S454: performing node performance change calculation according to the associated node performance data, thereby obtaining associated node performance change data;

[0179] In this embodiment, the extracted node performance data is subjected to time series analysis or change rate calculation. For example, assuming that the signal strength of a base station continues to decrease over a period of time, this will cause the user terminals in its service area to show a trend of decreasing throughput. By comparing data at different time points, the changing trend of node performance can be calculated. For example, the signal strength of base station A has decreased by 10% in the past hour, resulting in a 5% decrease in the average throughput of terminals in its coverage area. Finally, associated node performance change data is generated, which helps to further evaluate the impact of interference sources.

[0180] Step S455: constructing an interference source signal attenuation model based on the associated node performance change data and the interference source associated topology structure data;

[0181] In this embodiment, after obtaining the performance change data of the associated nodes, these data are used to construct a signal attenuation model of the interference source. The model takes into account factors such as the spatial distance between the interference source and the node, the signal attenuation factor (for example, attenuation caused by buildings, weather, etc.), and the transmission power of the interference source. By fitting the performance changes of different nodes (such as decreased throughput or increased delay) with the associated data of the interference source, a mathematical model is constructed to describe the signal attenuation of the interference source. For example, assuming that the signal strength attenuation of a base station is positively correlated with the signal interference of interference source A, a formula or algorithm can be derived through multiple experiments and data fitting to predict the signal attenuation degree of a node under a given interference source strength and distance.

[0182] Step S456: Identify interference-affected nodes on the communication network topology model using the interference source signal attenuation model, thereby obtaining interference source-affected node data.

[0183] In this embodiment, the constructed interference source signal attenuation model is used to identify interference-affected nodes on the communication network topology. According to the output of the model, it is identified which nodes (such as base stations, routers, terminals, etc.) are affected by the interference source, and the degree of impact is significant enough to cause network performance to degrade. Assuming that multiple base stations in a certain area are affected by the same interference source, their signals are greatly attenuated, resulting in a decrease in the communication quality of a large number of terminals. The attenuation model can identify these affected base stations and their associated terminals, and then obtain the interference source impact node data. These impact node data can help operators optimize the network layout, eliminate or weaken the interference source, and improve the overall performance of the communication network.

[0184] Optionally, step S5 specifically includes:

[0185] Step S51: performing an impact node-network slice association on the interference source impact node data and the network slice transmission resource allocation data, thereby obtaining impact node-network slice association data;

[0186] In this embodiment, the interference source impact node data is associated with the network slice transmission resource allocation data. Specifically, each slice in the network slice corresponds to a certain resource allocation, such as bandwidth, latency, etc., and each slice also transmits data on different physical nodes. By associating the data of the interference source impact node and the network slice resource allocation data, it is possible to identify which nodes and which network slices are most susceptible to interference. In specific implementation, a database or association analysis algorithm (such as a graph-based data association model) can be used to generate "affecting node-network slice association data", and the subsequent steps can be planned based on these data.

[0187] Step S52: extracting the associated slice network load characteristics of the real-time network communication data according to the influencing node-network slice association data, thereby obtaining the associated slice network load data;

[0188] In this embodiment, the slice network load characteristics are extracted to reflect the load status of each network slice. According to the obtained "influencing node-network slice association data", these real-time network communication data are associated with the network slice. For example, for the nodes in each network slice, according to the traffic load of the nodes (such as the comparison between high-load nodes and low-load nodes), the network load characteristics of each slice (such as the number of bytes transmitted per second, response time, etc.) are calculated. Then, these data will reflect the real-time load of each slice under the current conditions.

[0189] Step S53: quantifying the node interference of the interference source impact node data according to the interference source signal attenuation model, thereby obtaining the impact node interference data;

[0190] In this embodiment, the interference source signal attenuation model is used to quantify the influence of the interference source on the node. Specifically, the classical propagation loss model (such as free space loss, Hata model, etc.) can be used to simulate the propagation attenuation process of the interference source signal. According to the specific location of the network node, the power and frequency of the interference source and other parameters, the interference intensity of each affected node is calculated. For example, if the interference source is close to the node and the signal strength is large, the interference quantization value of the node will be high. In order to achieve this process, GIS data and radio environment simulation tools can be combined to dynamically calculate the interference effects of different interference sources on different nodes. Ultimately, the output "interference data affecting nodes" will include information such as the interference intensity, impact range, and duration of the node.

[0191] Step S54: estimating the interference impact factor based on the associated slice network load data and the interference data of the influencing node, thereby obtaining the interference impact factor;

[0192] In this embodiment, based on the obtained associated slice network load data and the interference data of the affected nodes, the interference impact factor can be estimated by weighted summation or other mathematical modeling methods. Specifically, the estimation of the interference impact factor can calculate the relationship between the current load (such as traffic, delay, etc.) and the interference (such as signal strength, interference time, etc.) of each node. Then, these data are combined to evaluate the performance degradation of each network slice when the interference source exists. Common evaluation methods include weighted average method, regression analysis method, etc., which can adjust the weight according to the severity of the load, the intensity of the interference and the priority of the network slice to obtain the final interference impact factor.

[0193] Step S55: Reallocate the network slice transmission resource allocation data according to the interference influencing factor to obtain the network slice transmission optimization resource allocation data, and upload it to the communication management platform to execute the data transmission task.

[0194] In this embodiment, the transmission resources of the network slice are reallocated according to the estimated interference impact factor. For example, an optimization algorithm (such as linear programming, genetic algorithm, particle swarm optimization, etc.) can be used to reallocate the bandwidth, delay, spectrum and other resources of the network slice. Through the optimization algorithm, the resource allocation of the network slice can be dynamically adjusted to give priority to the resources of the slices with lighter load and less interference, while limiting the resources of the slices with greater interference impact, or migrating their traffic to nodes with lower load. Finally, the reallocated resource data will be uploaded through the communication management platform to perform the corresponding data transmission tasks.

[0195] Optionally, the present invention further provides a data transmission system applicable to 5G communication, which is used to execute the data transmission method applicable to 5G communication as described above, and the data transmission system applicable to 5G communication includes:

[0196] A topology analysis module is used to obtain network communication data, and perform communication network topology analysis based on the network communication data, thereby obtaining a communication network topology model; and perform communication demand analysis based on the communication network topology model, thereby obtaining regional communication demand data;

[0197] A behavior pattern classification module is used to classify user behavior patterns according to regional communication demand data, thereby obtaining regional user traffic behavior pattern data; and to allocate communication transmission resources according to the regional user traffic behavior pattern data, thereby obtaining communication transmission resource allocation data;

[0198] The slice resource allocation module is used to create an independent logical virtual network slice for the communication transmission resource allocation data, so as to obtain the virtual network slice data; perform network slice transmission resource allocation according to the virtual network slice data, so as to obtain the network slice transmission resource allocation data, and upload it to the communication management platform to perform the data transmission task;

[0199] The interference source impact node identification module is used to obtain real-time network communication data, and identify communication interference on the real-time network communication data according to the network slice transmission resource allocation data, so as to obtain real-time communication interference data; the interference source impact node identification is performed on the real-time communication interference data through the communication network topology structure model, so as to obtain the interference source impact node data;

[0200] The communication interference optimization module is used to optimize the communication interference of the network slice transmission resource allocation data according to the node data affected by the interference source, so as to obtain the network slice transmission optimization resource allocation data and upload it to the communication management platform to perform the data transmission task.

[0201] The data transmission system suitable for 5G communication of the present invention can implement any data transmission method suitable for 5G communication of the present invention, and is used to combine the operation and signal transmission medium between various modules to complete the data transmission method suitable for 5G communication. The internal modules of the system cooperate with each other, thereby improving the management efficiency and response speed of network resources.

Claims

1. A data transmission method suitable for 5G communication, characterized in that: The following steps are involved: Step S1: Acquire network communication data, and perform communication network topology analysis based on the network communication data, thereby obtaining a communication network topology model; perform communication demand analysis based on the communication network topology model, thereby obtaining regional communication demand data; Step S2: classifying user behavior patterns according to regional communication demand data, thereby obtaining regional user traffic behavior pattern data; allocating communication transmission resources according to the regional user traffic behavior pattern data, thereby obtaining communication transmission resource allocation data; Step S3: Create an independent logical virtual network slice for the communication transmission resource allocation data to obtain virtual network slice data; perform network slice transmission resource allocation according to the virtual network slice data to obtain network slice transmission resource allocation data, and upload it to the communication management platform to execute the data transmission task; Step S4: acquiring real-time network communication data, and performing communication interference identification on the real-time network communication data according to the network slice transmission resource allocation data, thereby obtaining real-time communication interference data; performing interference source impact node identification on the real-time communication interference data through the communication network topology structure model, thereby obtaining interference source impact node data; Step S5: Perform communication interference optimization on the network slice transmission resource allocation data according to the interference source impact node data, so as to obtain the network slice transmission optimization resource allocation data, and upload it to the communication management platform to execute the data transmission task.

2. The data transmission method suitable for 5G communication according to claim 1, characterized in that: Step S1 is specifically as follows: Step S11: acquiring network communication data, and performing data preprocessing on the network communication data, thereby obtaining communication data to be processed; Step S12: extracting communication connection features according to the communication data to be processed, thereby obtaining communication connection data, and identifying communication base stations based on the communication connection data, thereby obtaining regional communication base station connection data; Step S13: dividing the communication data to be processed into base station network cell communication data based on the regional communication base station connection data, thereby obtaining network cell communication data; Step S14: performing a cell network topology analysis based on the network cell communication data to obtain a cell network topology model, and performing a communication topology merger on the cell network topology model according to the regional communication base station connection data to obtain a communication network topology model; Step S15: Perform communication demand analysis based on the communication network topology model to obtain regional communication demand data.

3. The data transmission method suitable for 5G communication according to claim 2, characterized in that: Step S14 is specifically as follows: Step S141: extracting cell communication signal strength features from network cell communication data, thereby obtaining cell communication signal strength data; Step S142: performing signal strength gradient analysis according to the cell communication signal strength data, thereby obtaining cell signal strength gradient data, and determining adjacent cell boundaries according to the cell signal strength gradient data, thereby obtaining adjacent cell boundary data; Step S143: integrating cell connection relationships based on adjacent cell boundary data, thereby obtaining cell connection relationship data; Step S144: performing cell connection mode identification on the network cell communication data according to the cell connection relationship data, thereby obtaining cell connection mode data; Step S145: constructing a cell network topology structure according to the cell connection mode data and the cell connection relationship data, thereby obtaining a cell network topology structure model; Step S146: merging the cell network topology structure model according to the regional communication base station connection data to obtain a communication network topology structure model.

4. The data transmission method suitable for 5G communication according to claim 2, characterized in that: Step S15 is specifically as follows: Step S151: extracting cell data throughput features from the communication network topology model, thereby obtaining cell data throughput data; Step S152: performing time series statistics of cell data throughput according to the cell data throughput data, thereby obtaining cell high throughput time data and cell low throughput time data; Step S153: Calculate the cell throughput time ratio based on the cell high throughput time data and the cell low throughput time data, thereby obtaining the cell throughput time ratio data; Step S154: dividing the communication network topology model into communication cells according to the cell throughput time ratio data, thereby obtaining high-throughput and high-ratio cell data and low-throughput and high-ratio cell data; Step S155: integrating cell communication demands according to the high-throughput and high-ratio cell data, thereby obtaining high-communication demand cell data; integrating cell communication demands according to the low-throughput and high-ratio cell data, thereby obtaining low-communication demand cell data; Step S156: regional spatial merging of the high communication demand cell data and the low communication demand cell data to obtain regional communication demand data.

5. The data transmission method suitable for 5G communication according to claim 1, characterized in that: Step S2 is specifically as follows: Step S21: Divide the regional communication demand data into time windows, thereby obtaining regional communication demand window data; Step S22: extracting regional user connection features according to the regional communication demand window data, thereby obtaining regional user connection time period data and regional user flow window data; Step S23: performing regional user connection period distribution analysis based on the regional user connection period data, thereby obtaining regional user connection period distribution data, and performing connected user mobility pattern recognition based on the user connection period distribution data, thereby obtaining user mobility pattern data; Step S24: performing regional user traffic periodicity analysis according to the regional user traffic window data, thereby obtaining regional user traffic periodicity data, and performing user traffic behavior pattern recognition based on the regional user traffic periodicity data, thereby obtaining a user traffic behavior pattern; Step S25: integrating the user behavior patterns based on the user mobility pattern data and the user traffic behavior patterns, thereby obtaining regional user traffic behavior pattern data; Step S26: performing communication transmission resource allocation according to the regional user traffic behavior pattern data, thereby obtaining communication transmission resource allocation data.

6. The data transmission method suitable for 5G communication according to claim 1, characterized in that: Step S3 is specifically as follows: Step S31: integrating the regional communication resource demand model according to the regional communication demand data, thereby obtaining the regional communication resource demand data; Step S32: dividing the slice resource pool based on the communication transmission resource allocation data, thereby obtaining slice resource pool data; Step S33: dividing the network topology structure according to the communication network topology structure model, thereby obtaining network topology structure data; Step S34: Creating a virtual network slice according to the network topology data, the slice resource pool data, and the regional communication resource demand data, thereby obtaining virtual network slice data, and performing slice priority division on the virtual network slice data, thereby obtaining virtual network slice priority data; Step S35: extracting the priority slice configuration of the virtual network slice priority data to obtain the priority slice configuration data, and estimating the slice resource demand according to the priority slice configuration data to obtain the priority slice resource demand data; Step S36: Allocate transmission resources for virtual network slice data according to the priority slice resource demand data, thereby obtaining network slice transmission resource allocation data, and upload it to the communication management platform to execute the data transmission task.

7. The data transmission method suitable for 5G communication according to claim 1, characterized in that: Step S4 is specifically as follows: Step S41: acquiring real-time network communication data, and dividing the real-time network communication data into slice communication data, thereby obtaining real-time 5G slice communication data; Step S42: Performing network slice communication transmission simulation according to the network slice transmission resource allocation data, thereby obtaining network slice communication transmission simulation data; Step S43: Calculate the slice communication performance error of the network slice communication transmission simulation data and the real-time 5G slice communication data, so as to obtain slice communication performance error data; Step S44: performing high error amplitude slice statistics according to the slice communication performance error data, thereby obtaining communication interference slice data, and identifying communication interference sources based on the communication interference slice data, thereby obtaining real-time communication interference data; Step S45: using the communication network topology model to identify interference source impact nodes on the real-time communication interference data, thereby obtaining interference source impact node data.

8. The data transmission method suitable for 5G communication according to claim 7, characterized in that: Step S45 is specifically as follows: Step S451: extracting interference source network topology distribution features from real-time communication interference data, thereby obtaining interference source network topology distribution data; Step S452: performing interference source associated topology structure matching on the interference source network topology allocation data through the communication network topology structure model, thereby obtaining interference source associated topology structure data; Step S453: extracting performance characteristics of associated nodes from the interference source associated topology data based on the real-time network communication data, thereby obtaining associated node performance data; Step S454: performing node performance change calculation according to the associated node performance data, thereby obtaining associated node performance change data; Step S455: constructing an interference source signal attenuation model based on the associated node performance change data and the interference source associated topology structure data; Step S456: using the interference source signal attenuation model to identify interference-affected nodes in the communication network topology model, thereby obtaining interference source-affected node data.

9. The data transmission method suitable for 5G communication according to claim 1, characterized in that: Step S5 is specifically as follows: Step S51: performing an impact node-network slice association on the interference source impact node data and the network slice transmission resource allocation data, thereby obtaining impact node-network slice association data; Step S52: extracting the associated slice network load characteristics of the real-time network communication data according to the influencing node-network slice association data, thereby obtaining the associated slice network load data; Step S53: quantifying the node interference of the interference source impact node data according to the interference source signal attenuation model, thereby obtaining the impact node interference data; Step S54: estimating the interference impact factor based on the associated slice network load data and the interference data of the influencing node, thereby obtaining the interference impact factor; Step S55: Reallocate the transmission resources of the network slice transmission resource allocation data to obtain the network slice transmission optimization resource allocation data, and upload it to the communication management platform to execute the data transmission task.

10. A data transmission system suitable for 5G communication, characterized in that: Used to execute the data transmission method applicable to 5G communication as claimed in claim 1, the data transmission system applicable to 5G communication comprises: A topology analysis module is used to obtain network communication data, and perform communication network topology analysis based on the network communication data, thereby obtaining a communication network topology model; and perform communication demand analysis based on the communication network topology model, thereby obtaining regional communication demand data; A behavior pattern classification module is used to classify user behavior patterns according to regional communication demand data, thereby obtaining regional user traffic behavior pattern data; and to allocate communication transmission resources according to the regional user traffic behavior pattern data, thereby obtaining communication transmission resource allocation data; The slice resource allocation module is used to create an independent logical virtual network slice for the communication transmission resource allocation data, so as to obtain the virtual network slice data; perform network slice transmission resource allocation according to the virtual network slice data, so as to obtain the network slice transmission resource allocation data, and upload it to the communication management platform to perform the data transmission task; The interference source impact node identification module is used to obtain real-time network communication data, and identify communication interference on the real-time network communication data according to the network slice transmission resource allocation data, so as to obtain real-time communication interference data; the interference source impact node identification is performed on the real-time communication interference data through the communication network topology structure model, so as to obtain the interference source impact node data; The communication interference optimization module is used to optimize the communication interference of the network slice transmission resource allocation data according to the node data affected by the interference source, so as to obtain the network slice transmission optimization resource allocation data and upload it to the communication management platform to perform the data transmission task.

Images