Data processing methods, devices, and storage media based on edge computing

Abstract

This invention relates to the field of data processing technology, and more particularly to a data processing method, apparatus, and storage medium based on edge computing. By analyzing pre-determined similar nodes, a timing synchronization coefficient, a data reception coefficient, and a spatial tolerance coefficient are obtained. These are used to calculate data transmission node anomaly values, analyze the data transmission anomaly tendencies of the similar nodes, and, for weak data transmission anomaly tendencies, calculate data transmission characteristic values ​​by combining a synchronization offset coefficient and data transmission node anomaly values ​​to determine the actual transmission node. The data to be transmitted is then processed and transmitted. This invention improves data transmission accuracy by analyzing and processing data and data nodes to determine the actual transmission node among several similar nodes, thus completing data transmission.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to data processing methods, apparatus and storage media based on edge computing. Background Technology

[0002] With the large-scale commercialization of 5G and 6G communications, the massive number of devices deployed in communication base stations, communication equipment rooms, and science and technology parks continuously generate heterogeneous and high-dimensional communication data. The traditional model of sending data back to the central network management or cloud for centralized processing faces problems such as bottlenecks in backhaul bandwidth and transmission latency, insufficient real-time response capabilities, underutilization of local computing resources at edge nodes, increased data privacy risks, and the failure of existing edge computing methods to adapt to the strong time sequence and spatial distribution characteristics of communication data, resulting in low processing accuracy and rigid resource scheduling. Therefore, there is an urgent need for an edge computing method that is oriented towards communication scenarios and can achieve efficient real-time collaborative processing near the data source side, so as to reduce dependence on the central cloud, improve network operation and maintenance automation and response speed, and ensure data security.

[0003] Chinese Patent Publication No. CN118377622A discloses a data processing method based on edge computing. This method collects raw data at an edge device, cleans the raw data to remove duplicate, erroneous, or irrelevant information, and then performs format conversion to unify the data format as needed. An encryption algorithm is selected and applied to encrypt the pre-processed data. The encrypted data is stored in a suitable storage medium or kept encrypted during transmission. A containerization tool is selected and used to create a container image of the application, enabling application deployment and updates. User feedback and data analysis results are collected to continuously optimize the computing distribution strategy. This invention integrates multiple technologies to achieve high efficiency, security, and a significant reduction in network latency in data processing, showing broad application prospects for large-scale data processing and real-time applications.

[0004] Chinese Patent Publication No. CN109714439A discloses a data processing method and system based on edge computing. The method includes: when a new data processing demand arises, a central node sends a data processing request to at least one distributed device associated with the data processing demand; the distributed device obtains the data resources required for the data processing request and loads the data resources into a preset data computing framework; the distributed device calls a pre-integrated data computing plugin in the data computing framework to perform data computing on the loaded data resources; the distributed device derives the data computing results from the data computing framework and feeds the data computing results back to the demand initiator. This invention provides a data processing method that decentralizes data processing, significantly reducing the load and pressure on the central node; it also improves the performance utilization of distributed devices; and during data processing, it reduces the amount of data transmitted, thus improving data processing efficiency.

[0005] However, the following problems still exist in the existing technology.

[0006] Communication base stations have several data chains that transmit data to different nodes. If the nodes are similar, data transmission errors are likely to occur. Existing technologies mostly use post-event full-domain scanning detection methods to deal with such errors. However, for data with high real-time requirements, this approach not only makes detection delayed but may even lead to invalid data. Summary of the Invention

[0007] To address the issue that existing technologies mostly employ post-event full-domain scanning detection methods for this type of error, which not only cause detection delays for data with high real-time requirements but may even lead to invalid data, this invention provides a data processing method based on edge computing, comprising:

[0008] Obtain the data to be transmitted, perform node matching on the data to be transmitted, and determine whether there are similar nodes;

[0009] For the existence of similar nodes, the data waiting status of the similar nodes is analyzed to determine the timing synchronization coefficient, the demand of the data to be transmitted and the similar nodes is analyzed to determine the data receiving coefficient, and the transmission space of the similar nodes is analyzed to determine the space tolerance coefficient.

[0010] Based on the timing synchronization coefficient, the data reception coefficient, and the spatial tolerance coefficient, abnormal values ​​of data transmission nodes are determined to analyze the abnormal data transmission tendency of similar nodes and determine the nodes to be transmitted.

[0011] To address the tendency of weak data transmission anomalies, the key synchronization lag of the data to be transmitted is analyzed to determine the synchronization offset coefficient. Combined with the abnormal values ​​of the data transmission nodes, data transmission characteristic values ​​are calculated to determine whether the node to be transmitted is an actual transmission node.

[0012] The data to be transmitted is processed, and the processed data is transmitted to the actual transmission node.

[0013] Furthermore, the process of determining whether similar nodes exist includes,

[0014] Extract the feature identifier of the data to be transmitted, and calculate the similarity between the feature identifier and the node feature identifier in the preset node feature library;

[0015] If the similarity is greater than the baseline similarity, then the node corresponding to the node feature identifier is determined to be a similar node.

[0016] Furthermore, the process of determining the timing synchronization coefficients includes,

[0017] Send test matching packets to similar nodes and record the time taken from sending to receiving matching confirmation;

[0018] The ratio of the baseline time to the time consumed is determined as the timing synchronization coefficient.

[0019] Furthermore, the process of determining the data reception coefficient includes,

[0020] Extract the required features of the data to be transmitted and iterate through the required field library of historical data received by similar nodes.

[0021] The number of the same characteristics between the stated requirement feature and the requirement field library is counted, and the ratio of the number of such features to the total number of requirement features is determined as the data reception coefficient.

[0022] Furthermore, the process of determining the space tolerance coefficient includes,

[0023] Get the remaining storage capacity, current available cache space, and amount of data to be transferred for similar nodes;

[0024] The ratio of the remaining storage capacity to the amount of data to be transmitted is determined to be a first ratio.

[0025] The ratio of the current available cache space to the amount of data to be transmitted is determined as the second ratio.

[0026] The smaller of the first ratio and the second ratio is determined as the space tolerance coefficient.

[0027] Furthermore, the abnormal values ​​of the data transmission nodes are determined based on the timing synchronization index, the data reception index, and the spatial tolerance index, wherein,

[0028] The ratio of the timing synchronization coefficient to the reference timing synchronization coefficient is defined as the timing synchronization index;

[0029] The ratio of the data reception coefficient to the reference data reception coefficient is defined as the data reception index;

[0030] The ratio of the space tolerance factor to the baseline space tolerance factor is defined as the space tolerance index.

[0031] If the abnormal value of the data transmission node is greater than the abnormal value threshold of the data transmission node, then the data transmission abnormality tendency of the similar nodes is determined to be a weak data transmission abnormality tendency, and the similar nodes corresponding to the weak data transmission abnormality tendency are determined to be nodes to be transmitted;

[0032] If the abnormal value of the data transmission node is less than or equal to the abnormal value threshold of the data transmission node, then the data transmission abnormality tendency of similar nodes is determined to be a strong data transmission abnormality tendency.

[0033] Furthermore, the process of determining the synchronization offset coefficient includes,

[0034] Send a key synchronization probe packet to the node to be transmitted and record the number of key retries required for the node to return the correct decryption random number;

[0035] The ratio of the number of key retries to the number of base key retries is determined as the synchronization offset coefficient.

[0036] Furthermore, the data transmission characteristic value is determined based on the data transmission node anomaly index and the synchronization offset index, wherein,

[0037] The ratio of the abnormal value of a data transmission node to the baseline abnormal value of a data transmission node is defined as the data transmission node anomaly index.

[0038] The ratio of the synchronization offset coefficient to the reference synchronization offset coefficient is determined as the synchronization offset index;

[0039] If the data transmission characteristic value is greater than the data transmission characteristic value threshold, then the node to be transmitted is determined to be not the actual transmission node.

[0040] If the data transmission characteristic value is less than or equal to the data transmission characteristic value threshold, then the node to be transmitted is determined to be the actual transmission node.

[0041] Furthermore, an apparatus for a data processing method based on edge computing is also provided, comprising:

[0042] The node preprocessing module acquires the data to be transmitted, performs node matching on the data to be transmitted, and determines whether there are similar nodes.

[0043] The data processing module, for the existence of similar nodes, analyzes the data waiting status of the similar nodes to determine the timing synchronization coefficient, analyzes the demand of the data to be transmitted and the similar nodes to determine the data receiving coefficient, and analyzes the transmission space of the similar nodes to determine the space tolerance coefficient;

[0044] The anomaly analysis module determines the abnormal values ​​of data transmission nodes based on the timing synchronization coefficient, the data reception coefficient, and the spatial tolerance coefficient, in order to analyze the abnormal data transmission tendency of the similar nodes and determine the nodes to be transmitted.

[0045] The node determination module analyzes the key synchronization lag of the data to be transmitted to determine the synchronization offset coefficient, based on the abnormal tendency of weak data transmission, and calculates the data transmission characteristic value in combination with the abnormal value of the data transmission node to determine whether the node to be transmitted is the actual transmission node.

[0046] The processing and transmission module processes the data to be transmitted and transmits the processed data to the actual transmission node.

[0047] Furthermore, a storage medium is provided that stores a computer program, which, when executed by a processor, can be used to perform a data processing method based on edge computing.

[0048] Compared with existing technologies, this invention analyzes and obtains timing synchronization coefficients, data reception coefficients, and spatial tolerance coefficients from pre-determined similar nodes. These coefficients are then used to calculate data transmission node anomalies and analyze the data transmission anomaly tendencies of the similar nodes. For weak data transmission anomalies, data transmission characteristic values ​​are calculated by combining synchronization offset coefficients and data transmission node anomalies to determine the actual transmission node. The data to be transmitted is then processed and transmitted. This invention analyzes and processes data and data nodes to determine the actual transmission node from several similar nodes, completing the data transmission. This is particularly beneficial for data with high real-time requirements, improving data transmission accuracy.

[0049] In particular, by analyzing data waiting conditions, demand, and transmission space, the timing synchronization coefficient, data reception coefficient, and space tolerance coefficient are determined, providing a data foundation for subsequent calculation of data transmission node anomalies. In practice, the timing synchronization coefficient reflects the responsiveness of similar nodes to the arrival time of data packets. If a node has a timing synchronization defect, even if its basic attributes are similar, timing errors and verification failures will occur after receiving data, leading to data retransmission or packet loss. The data reception coefficient quantifies the node's actual demand for receiving transmitted data. If nodes are highly similar in appearance, address, and tag but do not have the corresponding firmware pre-installed or have not established a dedicated session for this transmission, it is considered a latent reception defect. Conventional demand matching cannot identify this, and direct transmission will result in unparseable data. The space tolerance coefficient, by comparing the ratio of remaining storage capacity, available cache space, and data volume, reflects whether the node has the physical space to accommodate the data, avoiding transmission interruptions due to insufficient resources. Based on this, the present invention considers the problem of multiple similar nodes that may appear in the data transmission process from a multi-source perspective. It performs quantitative analysis on several similar nodes to classify them, providing a data-based theoretical basis for subsequently determining the actual transmission nodes, thereby improving the transmission accuracy and efficiency of real-time transmission tasks.

[0050] In particular, by comprehensively considering the timing synchronization coefficient, data reception coefficient, and spatial tolerance coefficient, outlier values ​​of data transmission nodes are calculated to identify nodes to be transmitted. In practice, data processing and transmission are mostly based on post-transmission verification, lacking pre-transmission analysis. Furthermore, the timing synchronization coefficient, data reception coefficient, and spatial tolerance coefficient determine a node's synchronization capability, reception willingness, and available space. Insufficient timing synchronization can lead to data verification failures due to timing discrepancies, even if the node has the demand and space. A low data reception coefficient means that although the node is synchronized and has sufficient space, it cannot parse the data. A small spatial tolerance coefficient means that although the node is synchronized and has the demand, it still discards data due to resource overflow. It is understandable that considering only a single factor, such as focusing solely on spatial tolerance while ignoring timing synchronization, could lead to misclassifying out-of-sync nodes as available nodes, causing frequent retransmissions in subsequent transmissions. Focusing solely on demand while ignoring space could result in sending data to fully loaded nodes, leading to packet loss. Based on this, the present invention considers a comprehensive analysis of the data waiting status, demand and transmission space of the data to be processed and the data nodes, and calculates the abnormal values ​​of the data transmission nodes to identify the nodes to be transmitted among similar nodes. This provides data and theoretical basis for targeted analysis in subsequent calculations, thereby improving the transmission accuracy and efficiency of real-time transmission tasks.

[0051] In particular, to address the tendency for weak data transmission anomalies, the key synchronization lag of the data to be transmitted is analyzed to determine the synchronization offset coefficient, which is used to calculate data transmission characteristic values ​​and identify the actual transmission node for transmitting the processed data. In practice, data transmission is mostly evaluated based on node similarity matching or a single resource dimension, neglecting the hidden layer of key synchronization. Key synchronization lag can cause the node to receive data but fail to correctly decrypt or verify the data packet, leading to decryption failure, data corruption, or data discarding triggered by security mechanisms. It is understandable that even if a node appears normal, has sufficient resources, and is timely, a key activation time offset can render the data completely unrecoverable at the application layer. Without analyzing this lag, selecting nodes solely based on outlier values ​​can misclassify these pseudo-usable nodes as actual transmission nodes, resulting in invalid transmission. Furthermore, data transmission node anomalies reflect a comprehensive anomaly tendency of nodes across three dimensions: timing, demand, and space. However, these anomalies cannot cover synchronization issues at the key level, thus leading to data transmission failure. Based on this, the present invention considers introducing a key synchronization lag, combined with the abnormal values ​​of data transmission nodes, to conduct targeted analysis on similar nodes, and to determine the actual transmission node among the nodes to be transmitted, so as to improve the transmission accuracy and transmission efficiency of real-time transmission tasks. Attached Figure Description

[0052] Figure 1 This is a schematic diagram of the data processing method based on edge computing according to an embodiment of the present invention;

[0053] Figure 2 This is a logic block diagram for determining the node to be transmitted according to an embodiment of the present invention;

[0054] Figure 3 A logic block diagram for determining whether the node to be transmitted is an actual transmission node according to an embodiment of the present invention;

[0055] Figure 4 This is a structural block diagram of a data processing device based on edge computing according to an embodiment of the present invention. Detailed Implementation

[0056] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0057] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0058] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0059] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0060] Please see Figure 1 The diagram illustrates the steps of a data processing method based on edge computing according to an embodiment of the present invention. The present invention provides a data processing method based on edge computing, comprising:

[0061] Step S1: Obtain the data to be transmitted, perform node matching on the data to be transmitted, and determine whether there are similar nodes;

[0062] Specifically, there is no limitation on the method of acquiring the data to be transmitted. For example, in this embodiment of the invention, the protocol data unit to be sent is captured in real time by the MAC layer scheduler of the base station. Of course, those skilled in the art can also use other methods, as long as the required data is obtained, which will not be elaborated here.

[0063] Specifically, the process of determining whether similar nodes exist includes,

[0064] Extract the feature identifier of the data to be transmitted, and calculate the similarity between the feature identifier and the node feature identifier in the preset node feature library;

[0065] If the similarity is greater than the baseline similarity, then the node corresponding to the node feature identifier is determined to be a similar node.

[0066] Specifically, there is no limitation on the method of extracting feature identifiers. In this embodiment of the invention, the target node identifier field is extracted by performing deep packet inspection on the data to be transmitted. For example, for user plane data, the TEID in the GTP-U header and the target IP address in the outer IP header are extracted. Of course, those skilled in the art can also use other methods, as long as the required data is obtained, which will not be elaborated here.

[0067] Specifically, the feature identifier includes one or more combinations of the target node's base station identifier, IP address, tunnel endpoint identifier, and service set identifier.

[0068] Specifically, there is no limitation on the method for determining the preset node feature library. For example, in the embodiments of the present invention, it can be an existing open-source feature library, or it can be a feature library constructed by pre-entering the configuration information of each node during the network planning stage. Of course, those skilled in the art can also use other methods, which will not be elaborated here.

[0069] Specifically, the specific method of similarity calculation is not limited. For example, in the embodiments of the present invention, cosine similarity is used for calculation. Of course, those skilled in the art can also use other methods, as long as the required data is obtained. This will not be elaborated further.

[0070] Specifically, the baseline similarity is calculated in advance by obtaining the historical similarities of several nodes that complete data transmission in one go, and determining the average of each historical similarity as the baseline similarity.

[0071] Step S2: For the existence of similar nodes, analyze the data waiting status of the similar nodes to determine the timing synchronization coefficient, analyze the demand of the data to be transmitted and the similar nodes to determine the data receiving coefficient, and analyze the transmission space of the similar nodes to determine the space tolerance coefficient.

[0072] Specifically, the process of determining timing synchronization coefficients includes,

[0073] Send test matching packets to similar nodes and record the time taken from sending to receiving matching confirmation;

[0074] The ratio of the baseline time to the time consumed is determined as the timing synchronization coefficient.

[0075] Specifically, the test match packet is a custom OAM probe frame that carries no payload to ensure minimal transmission latency and deterministic processing time. Upon receiving it, the receiver immediately timestamps the reception at the physical layer and replies with an acknowledgment frame in the same format.

[0076] Specifically, the baseline time is calculated in advance. The historical time corresponding to several nodes that complete data transmission in one go is obtained in advance, and the average of each historical time is determined as the baseline time.

[0077] Specifically, the timing synchronization coefficient characterizes the relative time synchronization accuracy or link response efficiency between the node and the transmitter. It reflects whether the node can complete data reception and processing within the expected time window. A larger timing synchronization coefficient indicates a longer actual measurement time, suggesting faster node processing speed, less clock drift, lower link load, and a higher degree of time synchronization with the transmitter, making it more suitable as a target for receiving high-real-time data.

[0078] Specifically, the process of determining the data reception coefficient includes,

[0079] Extract the required features of the data to be transmitted and iterate through the required field library of historical data received by similar nodes.

[0080] The number of the same characteristics between the stated requirement feature and the requirement field library is counted, and the ratio of the number of such features to the total number of requirement features is determined as the data reception coefficient.

[0081] Specifically, there is no limitation on the method of obtaining the required characteristics. For example, in the embodiments of the present invention, the information elements in the control plane signaling can be obtained by performing deep packet inspection on the protocol header of the data to be transmitted. Of course, those skilled in the art can also use other methods, as long as the required data is obtained, which will not be elaborated here.

[0082] Specifically, the requirement field library can be an open-source requirement field library that can be obtained directly, or it can be a requirement field library that is constructed by extracting all requirement features from the data after the node has successfully received and processed the data once.

[0083] Specifically, the data reception coefficient characterizes whether a node currently possesses the ability to correctly receive, decrypt, and submit data to be transmitted to the upper layer. It reflects the completeness of the node in key dimensions such as decryption keys, session context, and buffer availability. The larger the data reception coefficient, the more complete the receiving conditions the node has, and the higher the probability of successfully processing the data, making it suitable as the final target node.

[0084] Specifically, the process of determining the space tolerance factor includes,

[0085] Get the remaining storage capacity, current available cache space, and amount of data to be transferred for similar nodes;

[0086] The ratio of the remaining storage capacity to the amount of data to be transmitted is determined to be a first ratio.

[0087] The ratio of the current available cache space to the amount of data to be transmitted is determined as the second ratio.

[0088] The smaller of the first ratio and the second ratio is determined as the space tolerance coefficient.

[0089] Specifically, there is no limitation on the method of obtaining the remaining storage capacity. For example, in this embodiment of the invention, a storage status query request can be sent to similar nodes, and the nodes respond with the number of remaining bytes of their total storage space. Of course, those skilled in the art can also use other methods, as long as the required data is obtained, which will not be elaborated here.

[0090] Specifically, there is no limitation on the method of obtaining the current available cache space. For example, in this embodiment of the invention, the current available cache space can be obtained by sending a buffer status query command to similar nodes. Of course, those skilled in the art can also use other methods, as long as the required data is obtained, which will not be elaborated here.

[0091] Specifically, there is no limitation on the method of obtaining the amount of data to be transmitted. For example, in the embodiments of the present invention, the amount of data to be transmitted can be obtained by directly performing statistics, which will not be elaborated further.

[0092] Specifically, the spatial tolerance coefficient characterizes the degree of matching tolerance between a node and a transmitter in terms of physical spatial features. It reflects whether the node is located in the expected physical location or channel environment, and the degree of influence of environmental changes on spatial features. The larger the spatial tolerance coefficient, the closer the actual measured spatial features are to the reference features, indicating that the node is highly matched to the expected target in space, the signal propagation path is stable and reliable, and it is suitable as a transmission target for high-reliability data.

[0093] Step S3: Determine the abnormal values ​​of data transmission nodes based on the timing synchronization coefficient, the data reception coefficient, and the spatial tolerance coefficient, in order to analyze the abnormal data transmission tendency of the similar nodes and determine the nodes to be transmitted.

[0094] Specifically, outlier values ​​for data transmission nodes are determined based on timing synchronization index, data reception index, and spatial tolerance index, among which...

[0095] The ratio of the timing synchronization coefficient to the reference timing synchronization coefficient is defined as the timing synchronization index;

[0096] Specifically, the baseline timing synchronization coefficient is calculated in advance. The historical timing synchronization coefficients corresponding to several nodes that complete data transmission in one go are obtained in advance, and the average value of each historical timing synchronization coefficient is determined as the baseline timing synchronization coefficient.

[0097] The ratio of the data reception coefficient to the reference data reception coefficient is defined as the data reception index;

[0098] Specifically, the baseline data reception coefficient is calculated in advance. The historical data reception coefficients corresponding to several nodes that complete data transmission in one go are obtained in advance, and the average of each historical data reception coefficient is determined as the baseline data reception coefficient.

[0099] The ratio of the space tolerance factor to the baseline space tolerance factor is defined as the space tolerance index.

[0100] Specifically, the baseline spatial tolerance coefficient is calculated in advance. The historical spatial tolerance coefficients corresponding to several nodes that complete data transmission in one go are obtained in advance, and the average of each historical spatial tolerance coefficient is determined as the baseline spatial tolerance coefficient.

[0101] Specifically, in this embodiment of the invention, the weighted sum of the timing synchronization index, data reception index, and spatial tolerance index is determined to be an anomaly value for the data transmission node. The weight coefficients of the timing synchronization index, data reception index, and spatial tolerance index are all 1. When configuring the weights, considering that the node location is fixed and the channel environment is relatively stable in the communication base station scenario, while data reception conditions and buffer space are more likely to become bottlenecks for real-time transmission, the weight coefficient of the timing synchronization index is determined to be 0.3, and the weight coefficients of the data reception index and the spatial tolerance index are both 0.35.

[0102] Please see Figure 2 This is a logical block diagram illustrating the determination of the node to be transmitted according to an embodiment of the present invention. If the abnormal value of the data transmission node is greater than the abnormal value threshold of the data transmission node, then the data transmission abnormality tendency of the similar node is determined to be a weak data transmission abnormality tendency, and the similar node corresponding to the weak data transmission abnormality tendency is determined to be the node to be transmitted;

[0103] If the abnormal value of the data transmission node is less than or equal to the abnormal value threshold of the data transmission node, then the data transmission abnormality tendency of similar nodes is determined to be a strong data transmission abnormality tendency.

[0104] Specifically, the data transmission node anomaly threshold is calculated in advance. In this embodiment of the invention, the historical data transmission node anomaly values ​​corresponding to several nodes that complete data transmission in one go are obtained in advance, and the data transmission node anomaly threshold is determined based on the average of the historical data transmission node anomaly values.

[0105] Please continue reading. Figure 1 As shown, in step S4, in response to the tendency of weak data transmission anomalies, the key synchronization lag of the data to be transmitted is analyzed to determine the synchronization offset coefficient, and the data transmission characteristic value is calculated in combination with the abnormal value of the data transmission node to determine whether the node to be transmitted is the actual transmission node.

[0106] Specifically, the process of determining the synchronization offset coefficient includes,

[0107] Send a key synchronization probe packet to the node to be transmitted and record the number of key retries required for the node to return the correct decryption random number;

[0108] The ratio of the number of key retries to the number of base key retries is determined as the synchronization offset coefficient.

[0109] Specifically, the synchronization probe packet is a custom security probe frame used to send encrypted random numbers to the node to be transmitted and require the node to decrypt and return the verification result, thereby measuring the number of key retries required for the node to correctly decrypt.

[0110] Specifically, the baseline key retry count is calculated in advance. The average number of retries for the key probe packet processed by the node to be transmitted under normal historical conditions is obtained in advance, and the average number of retries is used as the baseline key retry count.

[0111] Specifically, the synchronization offset coefficient characterizes the degree of deviation of the current key synchronization state of the node to be transmitted relative to its historical normal state. It reflects the probability that the node cannot decrypt correctly due to key synchronization failure, clock drift, or security context failure. The larger the synchronization offset coefficient, the more the actual number of key retries is than the historical normal level, indicating a large deviation in key synchronization between the node and the sender. In this case, sending data to the node may lead to decryption failure or data loss, resulting in a serious decrease in transmission reliability.

[0112] Specifically, the data transmission characteristic values ​​are determined based on the data transmission node anomaly index and the synchronization offset index, where...

[0113] The ratio of the abnormal value of a data transmission node to the baseline abnormal value of a data transmission node is defined as the data transmission node anomaly index.

[0114] Specifically, the abnormal values ​​of the data transmission nodes corresponding to the reference timing synchronization coefficient, the reference data reception coefficient, and the reference spatial tolerance coefficient are determined to be the abnormal values ​​of the reference data transmission nodes.

[0115] The ratio of the synchronization offset coefficient to the reference synchronization offset coefficient is determined as the synchronization offset index;

[0116] Specifically, the baseline synchronization offset coefficient is calculated in advance. The historical synchronization offset coefficients corresponding to several nodes that complete data transmission in one go are obtained in advance, and the average value of each historical synchronization offset coefficient is determined as the baseline synchronization offset coefficient.

[0117] Specifically, in this embodiment of the invention, the weighted sum of the data transmission node anomaly index and the synchronization offset index is determined to be the data transmission characteristic value. The sum of the weight coefficients of the data transmission node anomaly index and the synchronization offset index is 1. When configuring the weights, considering their independent and equally important impact on the transmission success rate, the weight coefficients of both the data transmission node anomaly index and the synchronization offset index are determined to be 0.5.

[0118] Please see Figure 3The diagram shown is a logical block diagram illustrating how to determine whether the node to be transmitted is an actual transmission node according to an embodiment of the present invention. If the data transmission characteristic value is greater than the data transmission characteristic value threshold, then it is determined that the node to be transmitted is not an actual transmission node.

[0119] If the data transmission characteristic value is less than or equal to the data transmission characteristic value threshold, then the node to be transmitted is determined to be the actual transmission node.

[0120] Specifically, the data transmission feature value threshold is calculated in advance. In this embodiment of the invention, the historical data transmission feature values ​​corresponding to several nodes that complete data transmission in one go are obtained in advance, and the data transmission feature value threshold is determined based on the average of each historical data transmission feature value.

[0121] Specifically, if there are several nodes to be transmitted that are less than or equal to the data transmission characteristic value threshold, the node with the smallest data transmission characteristic value is determined as the actual transmission node.

[0122] Please continue reading. Figure 1 As shown, in step S5, the data to be transmitted is processed, and the processed data to be transmitted is transmitted to the actual transmission node.

[0123] Specifically, the specific processing method for processing the data to be transmitted is not limited. For example, in the embodiments of the present invention, the data can be processed by any one or a combination of the following methods:

[0124] Based on the key synchronization status of the actual transmission node, the data to be transmitted is encrypted or re-encrypted to match the node's current valid key; based on the space tolerance coefficient and available buffer space of the actual transmission node, the data to be transmitted is segmented or compressed to fit the node's receiving window; based on the timing synchronization coefficient of the actual transmission node, a timestamp is added to the data to be transmitted or the transmission time is adjusted to reduce receiving window misalignment caused by clock skew; or based on the data receiving coefficient of the actual transmission node, necessary protocol header fields are supplemented to ensure that the node can correctly identify it.

[0125] Please see Figure 4 The diagram shown is a structural block diagram of a data processing apparatus based on edge computing according to an embodiment of the present invention. Specifically, an apparatus for a data processing method based on edge computing is also provided, comprising:

[0126] The node preprocessing module acquires the data to be transmitted, performs node matching on the data to be transmitted, and determines whether there are similar nodes.

[0127] The data processing module, which is connected to the node preprocessing module, is used to analyze the data waiting status of similar nodes to determine the timing synchronization coefficient, analyze the demand of the data to be transmitted and the similar nodes to determine the data receiving coefficient, and analyze the transmission space of the similar nodes to determine the space tolerance coefficient.

[0128] An anomaly analysis module, connected to the data processing module, is used to determine anomaly values ​​of data transmission nodes based on the timing synchronization coefficient, the data reception coefficient, and the spatial tolerance coefficient, and to analyze the data transmission anomaly tendency of similar nodes and determine the nodes to be transmitted.

[0129] The node determination module, which is connected to the anomaly analysis module, is used to analyze the key synchronization lag of the data to be transmitted to determine the synchronization offset coefficient in response to the tendency of weak data transmission anomalies. Combined with the abnormal values ​​of the data transmission node, the data transmission characteristic value is calculated to determine whether the node to be transmitted is the actual transmission node.

[0130] The processing and transmission module is connected to the node determination module to process the data to be transmitted and transmit the processed data to the actual transmission node.

[0131] Specifically, a storage medium is also provided, which stores a computer program that, when executed by a processor, can be used to perform a data processing method based on edge computing.

[0132] Specifically, storage media include, but are not limited to, non-volatile storage media such as ROM, RAM, hard disks, solid-state drives, USB flash drives, CD-ROMs, and SD cards.

[0133] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A data processing method based on edge computing, characterized in that, include: Obtain the data to be transmitted, perform node matching on the data to be transmitted, and determine whether there are similar nodes; For the existence of similar nodes, the data waiting status of the similar nodes is analyzed to determine the timing synchronization coefficient, the demand of the data to be transmitted and the similar nodes is analyzed to determine the data receiving coefficient, and the transmission space of the similar nodes is analyzed to determine the space tolerance coefficient. Based on the timing synchronization coefficient, the data reception coefficient, and the spatial tolerance coefficient, abnormal values ​​of data transmission nodes are determined to analyze the abnormal data transmission tendency of similar nodes and determine the nodes to be transmitted. To address the tendency of weak data transmission anomalies, the key synchronization lag of the data to be transmitted is analyzed to determine the synchronization offset coefficient. Combined with the abnormal values ​​of the data transmission nodes, data transmission characteristic values ​​are calculated to determine whether the node to be transmitted is an actual transmission node. The data to be transmitted is processed, and the processed data is transmitted to the actual transmission node.

2. The data processing method based on edge computing according to claim 1, characterized in that, The process of determining whether similar nodes exist includes... Extract the feature identifier of the data to be transmitted, and calculate the similarity between the feature identifier and the node feature identifier in the preset node feature library; If the similarity is greater than the baseline similarity, then the node corresponding to the node feature identifier is determined to be a similar node.

3. The data processing method based on edge computing according to claim 1, characterized in that, The process of determining the timing synchronization coefficients includes: Send test matching packets to similar nodes and record the time taken from sending to receiving matching confirmation; The ratio of the baseline time to the time consumed is determined as the timing synchronization coefficient.

4. The data processing method based on edge computing according to claim 1, characterized in that, The process of determining the data reception coefficient includes, Extract the required features of the data to be transmitted and iterate through the required field library of historical data received by similar nodes. The number of the same characteristics between the stated requirement feature and the requirement field library is counted, and the ratio of the number of such features to the total number of requirement features is determined as the data reception coefficient.

5. The data processing method based on edge computing according to claim 1, characterized in that, The process of determining the space tolerance coefficient includes: Get the remaining storage capacity, current available cache space, and amount of data to be transferred for similar nodes; The ratio of the remaining storage capacity to the amount of data to be transmitted is determined to be a first ratio. The ratio of the current available cache space to the amount of data to be transmitted is determined as the second ratio. The smaller of the first ratio and the second ratio is determined as the space tolerance coefficient.

6. The data processing method based on edge computing according to claim 1, characterized in that, The abnormal values ​​of the data transmission nodes are determined based on the timing synchronization index, the data reception index, and the spatial tolerance index, wherein... The ratio of the timing synchronization coefficient to the reference timing synchronization coefficient is defined as the timing synchronization index; The ratio of the data reception coefficient to the reference data reception coefficient is defined as the data reception index; The ratio of the space tolerance factor to the baseline space tolerance factor is defined as the space tolerance index. If the abnormal value of the data transmission node is greater than the abnormal value threshold of the data transmission node, then the data transmission abnormality tendency of the similar nodes is determined to be a weak data transmission abnormality tendency, and the similar nodes corresponding to the weak data transmission abnormality tendency are determined to be nodes to be transmitted; If the abnormal value of the data transmission node is less than or equal to the abnormal value threshold of the data transmission node, then the data transmission abnormality tendency of similar nodes is determined to be a strong data transmission abnormality tendency.

7. The data processing method based on edge computing according to claim 1, characterized in that, The process of determining the synchronization offset coefficient includes: Send a key synchronization probe packet to the node to be transmitted and record the number of key retries required for the node to return the correct decryption random number; The ratio of the number of key retries to the number of base key retries is determined as the synchronization offset coefficient.

8. The data processing method based on edge computing according to claim 1, characterized in that, The data transmission characteristic values ​​are determined based on the data transmission node anomaly index and the synchronization offset index, wherein, The ratio of the abnormal value of a data transmission node to the baseline abnormal value of a data transmission node is defined as the data transmission node anomaly index. The ratio of the synchronization offset coefficient to the reference synchronization offset coefficient is determined as the synchronization offset index; If the data transmission characteristic value is greater than the data transmission characteristic value threshold, then the node to be transmitted is determined to be not the actual transmission node. If the data transmission characteristic value is less than or equal to the data transmission characteristic value threshold, then the node to be transmitted is determined to be the actual transmission node.

9. An apparatus for applying the edge computing-based data processing method according to any one of claims 1-8, characterized in that, include, The node preprocessing module acquires the data to be transmitted, performs node matching on the data to be transmitted, and determines whether there are similar nodes. The data processing module, for the existence of similar nodes, analyzes the data waiting status of the similar nodes to determine the timing synchronization coefficient, analyzes the demand of the data to be transmitted and the similar nodes to determine the data receiving coefficient, and analyzes the transmission space of the similar nodes to determine the space tolerance coefficient; The anomaly analysis module determines the abnormal values ​​of data transmission nodes based on the timing synchronization coefficient, the data reception coefficient, and the spatial tolerance coefficient, in order to analyze the abnormal data transmission tendency of the similar nodes and determine the nodes to be transmitted. The node determination module analyzes the key synchronization lag of the data to be transmitted to determine the synchronization offset coefficient, based on the abnormal tendency of weak data transmission, and calculates the data transmission characteristic value in combination with the abnormal value of the data transmission node to determine whether the node to be transmitted is the actual transmission node. The processing and transmission module processes the data to be transmitted and transmits the processed data to the actual transmission node.

10. A storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it can be used to perform a data processing method based on edge computing.

Images