Communication data processing system and method based on edge computing

Abstract

The invention discloses a communication data processing system and method based on edge computing, and belongs to the technical field of data processing.The method specifically comprises the steps that communication data on edge nodes are obtained, the obtained communication data are preprocessed, the preprocessed communication data are layered and filtered, and the data are obtained; the method comprises the following steps of: partitioning and compressing layered and filtered communication data, optimizing a transmission path and a transmission mode of the data by adopting an intelligent routing strategy to obtain an optimal transmission path, and cooperatively processing the data of a plurality of edge nodes by using distributed calculation among the edge nodes to obtain an optimal transmission path. Data processed by the edge nodes are uploaded to the center node for aggregation, and analysis results are generated and fed back to the edge nodes; according to the invention, the resource allocation is dynamically adjusted according to the actual computing power and the load condition of each edge node, and the waste of resources is avoided.

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and specifically to a communication data processing system and method based on edge computing. Background Art

[0002] With the rapid development of the Internet of Things (IoT), 5G communication technology, and artificial intelligence (AI), the amount of data generated is growing exponentially, especially in application scenarios such as video surveillance, intelligent transportation, and smart cities, where devices and sensors are deployed in large numbers and continuously generate massive amounts of data. These data often need to be processed and analyzed in real time, but the traditional centralized cloud computing model faces a series of challenges, mainly including the following aspects: latency issues, bandwidth bottlenecks, and network instability and reliability.

[0003] Edge computing is a distributed computing architecture that moves data processing and storage from the traditional centralized cloud to the edge of the network, close to where the data is generated. Edge computing reduces the distance and latency of data transmission by processing data locally, solving the problems of traditional cloud computing in terms of real-time, bandwidth, and latency. Edge computing can not only reduce network bandwidth pressure, but also provide higher response speed, which is especially suitable for scenarios that require real-time analysis and decision-making.

[0004] However, although edge computing has many advantages, in practical applications, the complexity and variability of the edge computing environment also brings new technical challenges, especially in communication data processing. How to effectively collect, transmit, process and analyze data from a large number of heterogeneous devices and sensors while maintaining performance indicators such as low latency, high bandwidth, high reliability and low energy consumption is a difficult problem that needs to be solved urgently. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention proposes a communication data processing system and method based on edge computing, which improves data processing efficiency and reduces the computing load of the central node and the delay of data transmission by moving operations such as preprocessing, filtering and distribution of communication data to edge nodes and combining them with optimized computing and data transmission strategies.

[0006] To achieve the above object, the present invention provides the following technical solutions: The communication data processing method based on edge computing includes the following specific steps: Acquire communication data on the edge node and preprocess the acquired communication data; Layering and filtering the pre-processed communication data; Chunking and compressing layered and filtered communication data; Adopt intelligent routing strategies to optimize data transmission paths and modes to obtain the optimal transmission path; Use distributed computing between edge nodes to collaboratively process data from multiple edge nodes; The data processed by each edge node is uploaded to the central node for aggregation, and the analysis results are generated and fed back to the edge nodes.

[0007] Specifically, the layering and filtering of the pre-processed communication data includes: Classify the pre-processed communication data into N categories according to data features, including data source, timestamp, and priority identification information; After the classification is completed, the importance of the communication data in each category is analyzed, and the importance score of the k-th category of communication data is calculated. The specific formula is: , Among them, d ij represents the jth communication data in the i-th communication data packet, Indicates communication data d ij Belonging to the kth category of communication data, represents the importance score of the k-th category of communication data, Indicates communication data d ij The weight of the pth feature, Indicates communication data d ij The pth eigenvalue of , ts represents the number of feature weights; Setting importance score thresholds , filter out the communication data that meets the importance requirements, the specific formula is: , D important,k Indicates the data that meets the importance requirement in the k-th category of communication data; The communication data that meets the requirements of importance are layered, and the specific formula of the layering function is: , in, represents the hierarchical function, , ... represents the importance score threshold of the first layer, the second layer, ... the Lth layer, and < <...< ; In a dynamic network environment, it is necessary to periodically recalculate the score of communication data and define a dynamic score function for the kth type of communication data. The specific formula is: , in, represents the dynamic score function of the kth type of communication data, t represents the current time, and t0 represents the communication data d ijThe generated initial time, e, represents an exponential function, which filters out data that does not meet the importance requirement by updating the hierarchical position of the communication data in real time.

[0008] Specifically, the segmenting and compressing of the layered and filtered communication data includes: Assume that the communication data matrix after stratification and filtering is D filtered , according to the specified block rules, D filtered Divided into A blocks, the ath communication data block is represented as ; The ath communication data block is compressed and the data is converted from the time domain to the frequency domain. The specific compression formula is: , in, represents the ath communication data block after compression, Q represents the data length in the ath communication data block, represents the compression factor, q represents the frequency index, Indicates the specific index in the ath communication data block, represents the cosine basis function.

[0009] Specifically, the intelligent routing strategy is adopted to optimize the data transmission path and transmission mode to obtain the optimal transmission path, including: Assume that the set of edge nodes is E, and calculate the transmission efficiency of each edge node. The specific formula is: , in, represents the transmission efficiency of the edge node Ez, represents the available bandwidth of the edge node Ez, represents the network delay of the edge node Ez, represents the computational load of the edge node Ez, Indicates the amount of data sent or to be sent by the edge node Ez; Dynamically select the optimal transmission path of the edge node. The specific formula is: , Among them, Popt represents the optimal transmission path of the edge node, , and represents the weight coefficient, Ps represents the sth possible transmission path, represents the delay of the transmission path Ps, represents the congestion degree of the transmission path Ps, It represents the total load of all nodes on the transmission path Ps; Get feedback information in real time during the transmission process, and update the feedback according to the real-time feedback information. The specific formula is: , in, Indicates the latest feedback information of the transmission path Ps, represents the historical feedback information of the transmission path Ps, Indicates the feedback difference during the current transmission of the transmission path Ps, Represents the smoothing factor.

[0010] Specifically, the distributed computing among edge nodes is used to collaboratively process data of multiple edge nodes, including: Evaluate the computing power of each edge node and obtain the edge node E z Computing power ; Dynamic adjustment is made based on the computing power of each node and the current load situation. The specific load balancing formula is: , in, represents the load allocated to the edge node Ez, represents the sum of the computing power of all edge nodes, and Z represents the total number of edge nodes; Edge Node E z After the load is distributed, the edge nodes start to perform distributed computing in parallel. z Perform local data processing within its computing capabilities and provide feedback on the processing results for further collaborative processing; During the parallel computing process of edge nodes, version numbers are used to ensure data consistency and synchronization, and the load distribution strategy is adjusted in real time according to the real-time computing load, network status, and node response time.

[0011] Specifically, the preprocessing includes: data cleaning, clearing duplicate data and redundant data, supplementing missing values, and constructing a communication data matrix.

[0012] A communication data processing system based on edge computing, used to implement the communication data processing method based on edge computing, comprising: a data acquisition module, a layered filtering module, a block compression module, a transmission optimization module, a collaborative processing module and a result analysis unit; The data acquisition module is used to acquire communication data on the edge node and pre-process the acquired communication data; The layered filtering module is used to layer and filter the pre-processed communication data; The block compression module is used to block and compress the layered and filtered communication data; The transmission optimization module is used to optimize the data transmission path and transmission mode by adopting an intelligent routing strategy to obtain the optimal transmission path; The collaborative processing module is used to collaboratively process data of multiple edge nodes using distributed computing among edge nodes; The result analysis unit is used to upload the data processed by each edge node to the central node for aggregation, generate analysis results and feed them back to the edge node. Specifically, Specifically, the block compression module includes: a communication data block unit and a communication data compression unit; The communication data blocking unit is used to divide the layered and filtered communication data matrix into A blocks according to a specified blocking rule; The communication data compression unit is used to compress the communication data blocks and convert the data from the time domain to the frequency domain.

[0013] Specifically, the transmission optimization module includes: a transmission efficiency calculation unit, a dynamic edge node selection unit and a feedback update unit; The transmission efficiency calculation unit is used to calculate the transmission efficiency of each edge node; The dynamic edge node selection unit is used to dynamically select the optimal transmission path of the edge node; The feedback updating unit is used to obtain feedback information in the transmission process in real time and perform feedback update according to the real-time feedback information.

[0014] Specifically, the collaborative processing module includes: a capacity calculation unit, a load balancing unit, a collaborative processing unit and a real-time adjustment unit; The capability calculation unit is used to evaluate the computing capability of each edge node; The load balancing unit is used to dynamically adjust based on the computing capacity and current load situation of each node; The collaborative processing unit is used to perform local data processing within the computing capacity of the edge node and to feed back the processing results for further collaborative processing; The real-time adjustment unit is used to adjust the load distribution strategy in real time according to the real-time computing load, network status and node response time.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention proposes a communication data processing method based on edge computing, which significantly reduces the data transmission distance, reduces communication delay, and improves the response speed of the system by moving data processing to the edge node close to the data source.

[0016] 2. The present invention proposes a communication data processing method based on edge computing. Through edge computing, data is transmitted to the cloud or other remote nodes only when needed. This can not only effectively reduce network bandwidth requirements, but also avoid excessive congestion in cloud data centers and optimize the utilization efficiency of network resources. In addition, edge computing can also use local storage and computing resources to process data, thereby reducing dependence on the core network and improving the overall throughput of the network.

[0017] 3. The present invention proposes a communication data processing method based on edge computing. Edge nodes are usually deployed in a local environment and rely on the computing power of edge devices to perform data processing, which can effectively reduce the computing load and improve the computing efficiency of the entire system. At the same time, the distributed characteristics of edge computing can also dynamically adjust resource allocation according to the actual computing power and load conditions of each node, thereby avoiding waste of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flow chart of the communication data processing method based on edge computing provided by the present invention; Figure 2 A flow chart of communication data transmission optimization provided by the present invention; Figure 3 A flow chart of collaborative processing of communication data provided by the present invention; Figure 4 This is an architecture diagram of the communication data processing system based on edge computing provided by the present invention. DETAILED DESCRIPTION

[0019] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, in the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside" and the like indicate the orientation or position relationship based on the orientation or position relationship shown in the accompanying drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "No. 1", "No. 2" and "No. 3" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. The present invention is further explained below in conjunction with specific embodiments.

[0020] Example 1 See also Figure 1-3 , an embodiment of the present invention provides: a communication data processing method based on edge computing, comprising the following specific steps: Step S1: Acquire communication data on the edge node and pre-process the acquired communication data; The preprocessing in step S1 includes: data cleaning, clearing duplicate and redundant data, supplementing missing values, and constructing the communication data matrix D raw ; , where d nm Indicates the mth item of data in the nth data packet in the communication data; Step S2: layering and filtering the preprocessed communication data; The specific steps of step S2 are: Step S201: Classify the pre-processed communication data into N categories according to data features, including data source, timestamp, priority identifier and other information; In step S201, each data is classified by a preset classification function, and a classification function, i.e., a classification rule, is automatically determined by machine learning or a statistical model to adapt to different types of communication data requirements; Step S202: After the classification is completed, the importance of the communication data in each category is analyzed, and the importance score of the k-th category of communication data is calculated. The specific formula is: , Among them, d ij represents the jth communication data in the i-th communication data packet, Indicates communication data d ij Belonging to the kth category of communication data, represents the importance score of the k-th category of communication data, Indicates communication data d ij The weight of the pth feature, Indicates communication data d ij The pth eigenvalue of , ts represents the number of feature weights, which is also the number of data in the kth type of communication data; Communication data ij The pth characteristic value of the communication data, such as the time sensitivity of the data, the amount of data, or the priority of the data packet, etc. ij The weight of the pth feature is used to calculate the weight score of each data packet through the feature weight and importance function; Importance score formula (scoring formula): This formula uses feature weights to evaluate data to ensure that key data is processed first. The idea of ​​the scoring formula is derived from the concept of weighted average, which determines the importance of data by assigning different weights to different features; Step S203: Setting importance score threshold , filter out the communication data that meets the importance requirements, the specific formula is: , D important,k Indicates the data that meets the importance requirement in the k-th category of communication data; Step S204: stratify the communication data that meet the importance requirements. The specific formula of the stratification function is: , in, represents the hierarchical function, , ... represents the importance score threshold of the first layer, the second layer, ... the Lth layer, and < <...< ; Tiered storage formula: The tiered formula allocates data to different storage layers based on the scoring value. By setting multiple layers of thresholds, edge nodes can flexibly process data of different priorities. Step S205: In a dynamic network environment, it is necessary to periodically recalculate the score of the communication data and define a dynamic score function for the k-th type of communication data. The specific formula is: , in, represents the dynamic score function of the kth type of communication data, t represents the current time, and t0 represents the communication data d ij The generated initial time, e, represents an exponential function, which filters out data that does not meet the importance requirement by updating the hierarchical position of the communication data in real time.

[0021] In this embodiment, the dynamic screening formula: a time-based weight decay formula ensures that the importance of data is updated over time, thereby achieving dynamic management. The formula uses the concept of exponential decay to simulate the decreasing importance of data as time decreases, ensuring that the system can be automatically adjusted under time evolution; The above steps and formulas constitute a complete communication data stratification and filtering method. By combining importance scoring, multi-layer storage and time decay mechanism, it effectively improves the efficiency of data processing and management in the edge computing environment.

[0022] Step S3: Blocking and compressing the layered and filtered communication data; The specific steps of step S3 are: Step S301: Set the communication data matrix after stratification and filtering as D filtered , according to the specified block rules, D filtered Divided into A blocks, the ath communication data block is represented as ; The size of the block can be adjusted adaptively according to the priority of the data packet and the characteristics of the data. The size of each block depends on the network conditions, the importance of the data, and the compression performance requirements. Blocking can not only improve the compression efficiency, but also improve the system's tolerance to data packet loss. Step S302: compress the ath communication data block and convert the data from the time domain to the frequency domain. The specific compression formula is: , in, represents the ath communication data block after compression, Q represents the data length in the ath communication data block, that is, the number of elements contained in each data block, represents the compression coefficient, which controls the amplitude of each frequency component. These coefficients are used to weight different frequency components and determine the proportion of each frequency in the transformed data. q represents the frequency index. Indicates the specific index (row number or data position) in the ath communication data block, with a value range of 0 to Q-1. Corresponding to a time domain data point, Represents the cosine basis function, which is used to convert data from the time domain to the frequency domain. Its function is to perform a weighted transformation on the data through the cosine wave to obtain each frequency component.

[0023] The compression formula uses the cosine function to perform weighted averaging on the signal, so that the energy of the signal is concentrated on a few low-frequency components. In this way, most of the redundancy of the data can be removed, while the important part of the signal is retained, and the coefficient of the low-frequency part is The coefficients of the high-frequency part will remain large, while the coefficients of the high-frequency part will be relatively small. Therefore, the key to data compression is to retain only the coefficients of the low-frequency part and discard or quantize the high-frequency part, so as to reduce the amount of data.

[0024] Step S4: Adopting intelligent routing strategy to optimize the data transmission path and transmission mode to obtain the optimal transmission path; The specific steps of step S4 are: Step S401: Set the edge node set to E, and calculate the transmission efficiency of each edge node. The specific formula is: , in, represents the transmission efficiency of the edge node Ez, represents the available bandwidth of the edge node Ez, Indicates the network delay of the edge node Ez (may be affected by factors such as network load and distance between nodes), represents the computational load of the edge node Ez (i.e., the amount of data currently processed by the node and the computational complexity), Indicates the amount of data sent or to be sent by the edge node Ez; Transmission efficiency It measures the transmission capacity of each node under given network delay and load. The larger the bandwidth, the smaller the delay and the lower the load, the higher the transmission efficiency. This formula calculates the transmission efficiency of each node at the current moment by considering multiple factors such as bandwidth, network delay and node load, and helps decide whether to transmit data. The node will dynamically adjust the timing of data transmission according to the transmission efficiency, so as to avoid network congestion or node overload during transmission, and ensure that the asynchronous transmission of the system can be carried out efficiently. Step S402: Dynamically select the optimal transmission path of the edge node. The specific formula is: , Among them, Popt represents the optimal transmission path of the edge node, , and represents the weight coefficient, which is used to control the priority of different transmission performance indicators. Ps represents the sth possible transmission path. represents the delay of the transmission path Ps, taking into account the distance between nodes and the response time of the network, It represents the congestion degree of the transmission path Ps and describes the load of nodes and links on the path. It represents the sum of the loads of all nodes on the transmission path Ps, reflecting the resource consumption of the nodes on the path; The path selection strategy is based on the idea of ​​weighted sum. By adjusting the weight coefficients, the system can flexibly balance various transmission performance indicators (such as delay, bandwidth utilization, load balancing, etc.). By dynamically adjusting these weight coefficients, the system can automatically select the optimal path according to the real-time network environment and node load, avoiding the shortcomings of traditional static routing methods. Step S403: Acquire feedback information in the transmission process in real time, and perform feedback update according to the real-time feedback information. The specific formula is: , in, Indicates the latest feedback information of the transmission path Ps, represents the historical feedback information of the transmission path Ps, Indicates the feedback difference during the current transmission of the transmission path Ps (such as bandwidth change, delay change, etc.), Represents a smoothing factor that controls the importance of history and current feedback.

[0025] The feedback information of the path is updated by the weighted average method, so that the historical and current feedback information can be smoothly integrated, thereby effectively capturing the changing trend of transmission performance. This feedback mechanism optimizes data transmission decisions in real time by continuously adjusting the path feedback information, ensuring that the system can flexibly respond to network conditions and load changes, and further improving the efficiency and reliability of asynchronous data transmission.

[0026] Step S5: using distributed computing among edge nodes to collaboratively process data from multiple edge nodes; The specific steps of step S5 are: Step S501: Evaluate the computing power of each edge node. The specific formula is: , in, represents the computing power of the edge node Ez, g() represents a comprehensive metric function, which usually adopts a weighted average method to consider the contribution of various factors, CPU represents the computing power of the edge node Ez, which is usually determined by factors such as the computing speed and core number of the processor, memory represents the memory capacity of the edge node Ez, which affects its ability to process data, storage represents the storage capacity of the edge node Ez, which determines its storage capacity for processing data, and network represents the network bandwidth of the edge node Ez, which affects the speed and delay of data transmission; Step S502: Dynamically adjust based on the computing capacity of each node and the current load situation. The specific load balancing formula is: , in, Indicates the load assigned to the edge node Ez, that is, the amount of data that the node needs to process. represents the sum of the computing power of all edge nodes, and Z represents the total number of edge nodes; This formula determines the load that should be allocated to each node by calculating the proportion of each node's computing power to the total computing power. The stronger the node's computing power, the greater the load allocated to it, ensuring that resources are used reasonably. This load balancing strategy is based on the proportional allocation method, allocating data processing tasks to nodes with more computing resources, thereby maximizing data processing efficiency. In this way, the system can dynamically balance the load of each node to avoid a node being overloaded and affecting overall performance. Step S503: Edge node E z After the load is distributed, the edge nodes start to perform distributed computing in parallel. z Perform local data processing within its computing capabilities and provide feedback on the processing results for further collaborative processing; Step S504: During the parallel computing process of the edge nodes, the version number is used to ensure data consistency and synchronization, and the load distribution strategy is adjusted in real time according to the real-time computing load, network status and node response time.

[0027] Controlling data synchronization through version numbers ensures that each node can perform calculations based on the latest data during parallel processing, avoiding errors caused by data lag or conflict, effectively reducing data conflicts and improving system data consistency. By adjusting the balance between load and latency, the system can dynamically adjust the load distribution strategy of each node to maximize the computing efficiency of the entire edge computing network and avoid node overload or computing bottlenecks.

[0028] Step S6: The data processed by each edge node is uploaded to the central node for aggregation, and the analysis results are generated and fed back to the edge nodes.

[0029] Example 2 See also Figure 4 , another embodiment provided by the present invention: a communication data processing system based on edge computing, comprising: a data acquisition module, a layered filtering module, a block compression module, a transmission optimization module, a collaborative processing module and a result analysis unit; The data acquisition module is used to acquire communication data on the edge node and pre-process the acquired communication data; The layered filtering module is used to layer and filter the pre-processed communication data; The block compression module is used to block and compress the layered and filtered communication data; The transmission optimization module is used to optimize the data transmission path and transmission mode by adopting an intelligent routing strategy to obtain the optimal transmission path; The collaborative processing module is used to collaboratively process data of multiple edge nodes using distributed computing among edge nodes; The result analysis unit is used to upload the data processed by each edge node to the central node for aggregation, generate analysis results and feed them back to the edge node.

[0030] The block compression module includes: a communication data block unit and a communication data compression unit; The communication data blocking unit is used to divide the layered and filtered communication data matrix into A blocks according to a specified blocking rule; The communication data compression unit is used to compress the communication data blocks and convert the data from the time domain to the frequency domain.

[0031] A transmission optimization module, including: a transmission efficiency calculation unit, a dynamic edge node selection unit and a feedback update unit; The transmission efficiency calculation unit is used to calculate the transmission efficiency of each edge node; The dynamic edge node selection unit is used to dynamically select the optimal transmission path of the edge node; The feedback updating unit is used to obtain feedback information in the transmission process in real time and perform feedback update according to the real-time feedback information.

[0032] The collaborative processing module includes: a capacity calculation unit, a load balancing unit, a collaborative processing unit and a real-time adjustment unit; The capability calculation unit is used to evaluate the computing capability of each edge node; The load balancing unit is used to dynamically adjust based on the computing capacity and current load situation of each node; The collaborative processing unit is used to perform local data processing within the computing capacity of the edge node and to feed back the processing results for further collaborative processing; The real-time adjustment unit is used to adjust the load distribution strategy in real time according to the real-time computing load, network status and node response time.

[0033] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0034] The specific implementation modes described above further describe the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0035] The above preset parameters or preset thresholds are all set by technicians in this field according to actual conditions or obtained through large-scale data simulation.

[0036] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A communication data processing method based on edge computing, characterized in that: include: Acquire communication data on the edge node and preprocess the acquired communication data; Layering and filtering the pre-processed communication data; Chunking and compressing layered and filtered communication data; Adopt intelligent routing strategies to optimize data transmission paths and modes to obtain the optimal transmission path; Use distributed computing between edge nodes to collaboratively process data from multiple edge nodes; The data processed by each edge node is uploaded to the central node for aggregation, and the analysis results are generated and fed back to the edge nodes.

2. The communication data processing method based on edge computing according to claim 1, characterized in that: The layering and filtering of the pre-processed communication data includes: Classify the pre-processed communication data into N categories according to data features, including data source, timestamp, and priority identification information; After the classification is completed, the importance of the communication data in each category is analyzed, and the importance score of the k-th category of communication data is calculated. The specific formula is: ， Among them, d ij represents the jth communication data in the i-th communication data packet, Indicates communication data d ij Belonging to the kth category of communication data, represents the importance score of the k-th category of communication data, Indicates communication data d ij The weight of the pth feature, Indicates communication data d ij The pth eigenvalue of , ts represents the number of feature weights; Setting importance score thresholds , filter out the communication data that meets the importance requirements, the specific formula is: , D important,k Indicates the data that meets the importance requirement in the k-th category of communication data; The communication data that meets the requirements of importance are layered, and the specific formula of the layering function is: ， in, represents the hierarchical function, , ... represents the importance score threshold of the first layer, the second layer, ... the Lth layer, and < <...< ; In a dynamic network environment, it is necessary to periodically recalculate the score of communication data and define a dynamic score function for the kth type of communication data. The specific formula is: ， in, represents the dynamic score function of the kth type of communication data, t represents the current time, and t0 represents the communication data d ij The generated initial time, e, represents an exponential function, which filters out data that does not meet the importance requirement by updating the hierarchical position of the communication data in real time.

3. The communication data processing method based on edge computing according to claim 1, characterized in that: The step of dividing and compressing the layered and filtered communication data includes: Assume that the communication data matrix after stratification and filtering is D filtered , according to the specified block rules, D filtered Divided into A blocks, the ath communication data block is represented as ; The ath communication data block is compressed and the data is converted from the time domain to the frequency domain. The specific compression formula is: ， in, represents the ath communication data block after compression, Q represents the data length in the ath communication data block, represents the compression factor, q represents the frequency index, Indicates the specific index in the ath communication data block, represents the cosine basis function.

4. The communication data processing method based on edge computing according to claim 1, characterized in that: The intelligent routing strategy is used to optimize the data transmission path and transmission mode to obtain the optimal transmission path, including: Assume that the set of edge nodes is E, and calculate the transmission efficiency of each edge node. The specific formula is: ， in, represents the transmission efficiency of the edge node Ez, represents the available bandwidth of the edge node Ez, represents the network delay of the edge node Ez, represents the computational load of the edge node Ez, Indicates the amount of data sent or to be sent by the edge node Ez; Dynamically select the optimal transmission path of the edge node. The specific formula is: ， Among them, Popt represents the optimal transmission path of the edge node, , and represents the weight coefficient, Ps represents the sth possible transmission path, represents the delay of the transmission path Ps, represents the congestion degree of the transmission path Ps, represents the total load of all nodes on the transmission path Ps; Get feedback information in real time during the transmission process, and update the feedback according to the real-time feedback information. The specific formula is: ， in, Indicates the latest feedback information of the transmission path Ps, represents the historical feedback information of the transmission path Ps, Indicates the feedback difference during the current transmission of the transmission path Ps, Represents the smoothing factor.

5. The communication data processing method based on edge computing according to claim 1, characterized in that: The method uses distributed computing among edge nodes to collaboratively process data of multiple edge nodes, including: Evaluate the computing power of each edge node and obtain the edge node E z Computing power ; Dynamic adjustment is made based on the computing power of each node and the current load situation. The specific load balancing formula is: ， in, represents the load allocated to the edge node Ez, represents the sum of the computing power of all edge nodes, and Z represents the total number of edge nodes; Edge Node E z After the load is distributed, the edge nodes start to perform distributed computing in parallel. z Perform local data processing within its computing capabilities and provide feedback on the processing results for further collaborative processing; During the parallel computing process of edge nodes, version numbers are used to ensure data consistency and synchronization, and the load distribution strategy is adjusted in real time according to the real-time computing load, network status, and node response time.

6. The communication data processing method based on edge computing according to claim 1, characterized in that: The preprocessing includes: data cleaning, clearing duplicate data and redundant data, supplementing missing values, and constructing a communication data matrix.

7. A communication data processing system based on edge computing, used to implement the communication data processing method based on edge computing according to any one of claims 1 to 6, characterized in that: include: Data acquisition module, layered filtering module, block compression module, transmission optimization module, collaborative processing module and result analysis unit; The data acquisition module is used to acquire communication data on the edge node and pre-process the acquired communication data; The layered filtering module is used to layer and filter the pre-processed communication data; The block compression module is used to block and compress the layered and filtered communication data; The transmission optimization module is used to optimize the data transmission path and transmission mode by adopting an intelligent routing strategy to obtain the optimal transmission path; The collaborative processing module is used to collaboratively process data of multiple edge nodes using distributed computing among edge nodes; The result analysis unit is used to upload the data processed by each edge node to the central node for aggregation, generate analysis results and feed them back to the edge node.

8. The communication data processing system based on edge computing according to claim 7, characterized in that: The block compression module includes: a communication data block unit and a communication data compression unit; The communication data blocking unit is used to divide the layered and filtered communication data matrix into A blocks according to a specified blocking rule; The communication data compression unit is used to compress the communication data blocks and convert the data from the time domain to the frequency domain.

9. The communication data processing system based on edge computing according to claim 8, characterized in that: The transmission optimization module includes: a transmission efficiency calculation unit, a dynamic edge node selection unit and a feedback update unit; The transmission efficiency calculation unit is used to calculate the transmission efficiency of each edge node; The dynamic edge node selection unit is used to dynamically select the optimal transmission path of the edge node; The feedback updating unit is used to obtain feedback information in the transmission process in real time and perform feedback update according to the real-time feedback information.

10. The communication data processing system based on edge computing according to claim 9, characterized in that: The collaborative processing module includes: a capacity calculation unit, a load balancing unit, a collaborative processing unit and a real-time adjustment unit; The capability calculation unit is used to evaluate the computing capability of each edge node; The load balancing unit is used to dynamically adjust based on the computing capacity and current load situation of each node; The collaborative processing unit is used to perform local data processing within the computing capacity of the edge node and to feed back the processing results for further collaborative processing; The real-time adjustment unit is used to adjust the load distribution strategy in real time according to the real-time computing load, network status and node response time.

Images