A data connector dynamic monitoring method and system based on artificial intelligence
Through the dynamic monitoring method based on artificial intelligence, the data transmission characteristics and integrity of the data connector are monitored in real time, which solves the problem of traditional static monitoring methods that cannot cope with data transmission in complex environments, and improves the stability and reliability of data transmission.
Patent Information
- Application Number
- CN202410377604.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-29
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-03-29
AI Technical Summary
Traditional static monitoring methods are difficult to fully understand the actual working conditions of data connectors in complex environments, and cannot promptly discover and deal with sudden problems during data transmission, resulting in reduced data transmission instability and reliability.
Using dynamic monitoring methods based on artificial intelligence, by obtaining data transmission formats, splitting test data, performing data transmission load tests, identifying data transmission characteristics, using outlier detection algorithms and fingerprint algorithms to evaluate data integrity, and monitoring data transmission stability in real time .
Real-time monitoring and analysis of data connectors is realized, the reliability and stability of data transmission is improved, and the information system needs for efficient data interaction.
Smart Images

Figure CN118170596B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data connector monitoring, and in particular to an artificial intelligence-based data connector dynamic monitoring method and system. Background Art
[0002] In today's digital age, data connectors play a vital role in information systems, and are used to achieve data interaction and communication between different systems. However, due to the complexity of data connectors and various uncertainties in the data transmission process, such as network delays and data loss, traditional static monitoring methods can no longer meet the requirements for data connector stability and reliability.
[0003] At present, some static monitoring methods only rely on one-time testing of connectors or inspections based on fixed rules, which makes it difficult to fully understand the actual working conditions of connectors in long-term and complex environments. In addition, traditional monitoring methods are usually unable to effectively deal with emergencies and changes in the data transmission process, and it is difficult to promptly discover and deal with possible problems with the connector, resulting in instability and reduced reliability of data transmission.
[0004] Therefore, a dynamic monitoring method and system based on artificial intelligence is needed to realize real-time monitoring and analysis of data connectors. This invention can combine data transmission characteristics and outlier detection algorithms to comprehensively identify the transmission characteristics of connectors and detect abnormalities in a timely manner. By evaluating data integrity and monitoring transmission impact characteristics, real-time monitoring of connector stability can be achieved, thereby improving the reliability and stability of data transmission and meeting the information system's needs for efficient data interaction. Summary of the invention
[0005] In order to solve at least one of the above technical problems, the present invention proposes a data connector dynamic monitoring method and system based on artificial intelligence.
[0006] A first aspect of the present invention provides a data connector dynamic monitoring method based on artificial intelligence, comprising:
[0007] Acquire a data transmission format of a target data connector, prepare a preset number of test data of the target data connector according to the data transmission format, and split the test data to obtain split data, wherein the split data includes split block test data and an assembly identifier of the block data;
[0008] Performing a data transmission load test on the target data connector according to the split data to identify data transmission characteristics, wherein the data transmission characteristics include data transmission rate characteristics, data concurrent connection characteristics, data transmission signal distortion characteristics, and data transmission delay characteristics;
[0009] Performing data outlier detection on the data transmission feature according to an outlier detection algorithm to obtain an outlier detection result;
[0010] Perform integrity assessment on the split data after the data transmission load test based on the fingerprint algorithm to obtain the integrity assessment result;
[0011] Determine the impact characteristics of data transmission by the target data connector according to the outlier detection result and the integrity assessment result;
[0012] The real-time data transmission of the target data connector is monitored according to the influencing characteristics, and the data transmission stability of the target data connector is analyzed in real time.
[0013] In this solution, the data transmission format of the target data connector is obtained, a preset number of test data of the target data connector is prepared according to the data transmission format, and the test data is split to obtain split data, wherein the split data includes the split block test data and the assembly identifier of the block data, specifically:
[0014] Acquire functional data of the target data connector, and determine the data transmission format of the target data connector according to the functional data, wherein the data transmission format includes data structure, data type, and transmission protocol;
[0015] Prepare data transmission test data of a preset number of target data connectors according to the data transmission format;
[0016] Building a distributed file system based on big data technology, uploading the test data to the distributed file system, and performing a split operation on the test data to obtain a plurality of block test data;
[0017] Read each block of test data, calculate a hash value of each block of data according to a hash function, and use the hash value as a unique identifier of each block of data;
[0018] Obtaining the starting offset and size of each block of test data according to the splitting record of the test data during the splitting operation, and obtaining an assembly identifier of the block of test data, wherein the assembly identifier includes a unique identifier of the block of data and a starting offset and size of the block of test data;
[0019] The split block test data and the assembly identifier of the block data are integrated to obtain split data of the test data.
[0020] In this solution, the data transmission load test is performed on the target data connector according to the split data to identify data transmission characteristics, which include data transmission rate characteristics, data concurrent connection characteristics, data transmission signal distortion characteristics, and data transmission delay characteristics, specifically:
[0021] Deploy a test environment for the target data connector, determine a data interaction device for the test environment, and import the split data into the test environment to perform a data maximum load transmission test;
[0022] Record the time and end time of the data transmission test, monitor the transmission rate change of the target data connector in real time according to the transmission time and data volume, and obtain the data transmission rate characteristics of each block data;
[0023] Monitor the changes in the number of concurrent transmissions of split data by the target data connector, determine the fluctuations and trends of the number of data block transmission connections, and obtain the data concurrent connection characteristics of the block data;
[0024] Comparing the size of each block data of the split data before and after the data transmission test to obtain block data size change data, determining the packet loss situation of the target data connector according to the block data size change data, and obtaining the data transmission signal distortion characteristics of each block data;
[0025] The data transmission delay time of the target data connector is calculated according to the transmission start time and data receiving time of each block data in the data transmission test, and the data transmission delay characteristics of each block data are obtained.
[0026] In this solution, the data transmission feature is subjected to data outlier detection according to the outlier detection algorithm to obtain an outlier detection result, which is specifically:
[0027] Performing outlier detection on each feature data in the data transmission feature in turn based on the LOF algorithm;
[0028] For the data transmission feature entering the outlier detection, the distance between each data point in the data transmission feature and other data points in the data transmission feature is calculated, and the K nearest neighbors of each data point are found according to the size of the distance to obtain the K-nearest neighbor data points;
[0029] Calculate the reachable distance between each data point and each data point in the K-nearest neighbor data points, and calculate the local reachable density of each data point based on the reachable distance;
[0030] The local outlier factor of each data point is calculated according to the local reachable density, and a marking operation is performed on the outlier factor to obtain an outlier detection result, wherein the outlier detection result includes the marked outlier block data and the outlier degree of the marked outlier block data for each feature in the data transmission feature.
[0031] In this solution, the split data after the data transmission load test is subjected to integrity assessment based on the fingerprint algorithm to obtain the integrity assessment result, which is specifically:
[0032] A fingerprint algorithm is introduced to identify the hash function used when calculating the hash value of each block of data in the split data, and the hash value of the split data after the data transmission load test is calculated according to the hash function;
[0033] Generate a fingerprint of each block of data before and after the data transmission load test according to the hash value of each block of data before and after the data transmission load test, wherein the fingerprint includes reference fingerprint data of each block of data before the data transmission load test and fingerprint data to be evaluated of each block of data after the data transmission load test;
[0034] Comparing the reference fingerprint data with the fingerprint data to be evaluated, determining the similarity between the fingerprint data to be evaluated and the reference fingerprint data, and obtaining a similarity score for each block of data before and after the data transmission load test;
[0035] Determine a similarity score threshold according to a preset data integrity standard, mark the block data after the data transmission load test that is lower than the similarity score threshold, and obtain marked low-similarity block data;
[0036] Perform a data damage degree assessment on the marked low-similarity block data to obtain damage degree assessment data, calculate the proportion of the marked low-similarity block data, determine the integrity of the split data after the data transmission load test based on the proportion and the damage degree assessment data, and obtain an integrity assessment result.
[0037] In this solution, the influence characteristics of data transmission by the target data connector are determined according to the outlier detection result and the integrity assessment result, specifically:
[0038] According to the outlier detection result and the integrity assessment result, the same block data is identified for the marked outlier block data and the marked low-similarity block data to obtain the same block data;
[0039] Based on the information entropy weight method, a correlation analysis is performed on the outlier degree and the data damage degree of the same block data to determine the influence weight of the outlier degree of each feature in the data transmission feature of the block data on the data damage degree;
[0040] Determine the outlier value of the marked outlier block data and the data range of the non-outlier block data according to the outlier detection result, and obtain the outlier judgment standard data;
[0041] The impact characteristics of the target data connector for data transmission are determined based on the impact weight and outlier judgment standard data, wherein the impact characteristics include the impact weight characteristics of each data transmission feature of the target data connector on data damage during the data transmission process, the impact degree characteristics of the outlier degree of each data transmission feature on data damage, and the outlier standard judgment standard for block data.
[0042] In this solution, the real-time data transmission of the target data connector is monitored according to the influencing characteristics, and the data transmission stability of the target data connector is analyzed in real time, specifically:
[0043] The real-time data transmission process of the target data connector is monitored according to the influencing characteristics, and the data transmission characteristics of the target data connector during the real-time data transmission process are identified in real time;
[0044] Performing data transmission stability monitoring on the data transmission characteristics of the target data connector during real-time data transmission according to the influencing characteristics to obtain a data transmission stability monitoring result;
[0045] If the data transmission stability is lower than the preset value, an early warning operation will be performed on the real-time data transmission.
[0046] The second aspect of the present invention further provides a data connector dynamic monitoring system based on artificial intelligence, the system comprising: a memory, a processor, the memory comprising a data connector dynamic monitoring method program based on artificial intelligence, and when the data connector dynamic monitoring method program based on artificial intelligence is executed by the processor, the following steps are implemented:
[0047] Acquire a data transmission format of a target data connector, prepare a preset number of test data of the target data connector according to the data transmission format, and split the test data to obtain split data, wherein the split data includes split block test data and an assembly identifier of the block data;
[0048] Performing a data transmission load test on the target data connector according to the split data to identify data transmission characteristics, wherein the data transmission characteristics include data transmission rate characteristics, data concurrent connection characteristics, data transmission signal distortion characteristics, and data transmission delay characteristics;
[0049] Performing data outlier detection on the data transmission feature according to an outlier detection algorithm to obtain an outlier detection result;
[0050] Perform integrity assessment on the split data after the data transmission load test based on the fingerprint algorithm to obtain the integrity assessment result;
[0051] Determine the impact characteristics of data transmission by the target data connector according to the outlier detection result and the integrity assessment result;
[0052] The real-time data transmission of the target data connector is monitored according to the influencing characteristics, and the data transmission stability of the target data connector is analyzed in real time.
[0053] In this solution, the influence characteristics of data transmission by the target data connector are determined according to the outlier detection result and the integrity assessment result, specifically:
[0054] According to the outlier detection result and the integrity assessment result, the same block data is identified for the marked outlier block data and the marked low-similarity block data to obtain the same block data;
[0055] Based on the information entropy weight method, a correlation analysis is performed on the outlier degree and the data damage degree of the same block data to determine the influence weight of the outlier degree of each feature in the data transmission feature of the block data on the data damage degree;
[0056] Determine the outlier value of the marked outlier block data and the data range of the non-outlier block data according to the outlier detection result, and obtain the outlier judgment standard data;
[0057] The impact characteristics of the target data connector for data transmission are determined based on the impact weight and outlier judgment standard data, wherein the impact characteristics include the impact weight characteristics of each data transmission feature of the target data connector on data damage during the data transmission process, the impact degree characteristics of the outlier degree of each data transmission feature on data damage, and the outlier standard judgment standard for block data.
[0058] In this solution, the real-time data transmission of the target data connector is monitored according to the influencing characteristics, and the data transmission stability of the target data connector is analyzed in real time, specifically:
[0059] The real-time data transmission process of the target data connector is monitored according to the influencing characteristics, and the data transmission characteristics of the target data connector during the real-time data transmission process are identified in real time;
[0060] Performing data transmission stability monitoring on the data transmission characteristics of the target data connector during real-time data transmission according to the influencing characteristics to obtain a data transmission stability monitoring result;
[0061] If the data transmission stability is lower than the preset value, an early warning operation will be performed on the real-time data transmission.
[0062] The present invention discloses a data connector dynamic monitoring method and system based on artificial intelligence. First, the transmission format of the target data connector is obtained and test data is prepared. Then, the test data is split and the connector is load tested to identify transmission characteristics such as rate, concurrent connections, signal distortion and delay. The outlier detection algorithm is used to detect the characteristics, and the data integrity is evaluated based on the fingerprint algorithm. According to the results, the transmission influencing characteristics of the connector are determined, and its stability is monitored in real time. The present invention combines artificial intelligence technology to comprehensively monitor data transmission, improve reliability, and has practical value. BRIEF DESCRIPTION OF THE DRAWINGS
[0063] Figure 1 A flow chart of a data connector dynamic monitoring method based on artificial intelligence of the present invention is shown;
[0064] Figure 2 A flow chart showing the outlier detection result obtained by the present invention is shown;
[0065] Figure 3 A flow chart showing real-time analysis of data transmission stability of a target data connector according to the present invention is shown;
[0066] Figure 4 A block diagram of a data connector dynamic monitoring system based on artificial intelligence of the present invention is shown. DETAILED DESCRIPTION
[0067] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.
[0068] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.
[0069] Figure 1 A flow chart of a data connector dynamic monitoring method based on artificial intelligence of the present invention is shown.
[0070] like Figure 1 As shown, the first aspect of the present invention provides a data connector dynamic monitoring method based on artificial intelligence, comprising:
[0071] S102, obtaining a data transmission format of a target data connector, preparing a preset number of test data of the target data connector according to the data transmission format, and performing a split operation on the test data to obtain split data, wherein the split data includes split block test data and an assembly identifier of the block data;
[0072] S104, performing a data transmission load test on the target data connector according to the split data, and identifying data transmission characteristics, wherein the data transmission characteristics include data transmission rate characteristics, data concurrent connection characteristics, data transmission signal distortion characteristics, and data transmission delay characteristics;
[0073] S106, performing data outlier detection on the data transmission feature according to an outlier detection algorithm to obtain an outlier detection result;
[0074] S108, performing integrity assessment on the split data after the data transmission load test based on the fingerprint algorithm to obtain an integrity assessment result;
[0075] S110, determining the influencing characteristics of data transmission by the target data connector according to the outlier detection result and the integrity assessment result;
[0076] S112, monitoring the real-time data transmission of the target data connector according to the influencing characteristics, and analyzing the data transmission stability of the target data connector in real time.
[0077] It should be noted that, by performing a data transmission load test on the target data connector, since the amount of data for the data transmission load test on the target data connector is massive, the test data needs to be split between the data transmission load tests to achieve load balancing during the data transmission process and avoid data performance degradation of the target data connector due to excessive data. According to the data transmission load test, data transmission characteristics are identified, outlier detection is performed on the data transmission characteristics, and integrity assessment is performed on the split data after the data transmission load test. According to the outlier detection results and the integrity assessment results, the influencing characteristics of the target data connector that have an impact on the data transmission during the data transmission process are determined, and the target data connector is evaluated according to the influencing characteristics. The real-time data transmission process of the target data connector is monitored, and the stability of data transmission is analyzed; the splitting operation can effectively simulate the data transmission load in the real world, ensuring the diversity and adequacy of the test data; the data transmission characteristics are analyzed by the outlier detection algorithm, so as to identify abnormal or unusual data transmission behaviors and improve the monitoring and diagnosis capabilities of the data transmission process; the data transmission stability of the target data connector is monitored in real time, so as to timely discover potential problems or anomalies, give early warnings and take corresponding measures; the target data connector refers to a physical connector or interface used to connect different devices or components, including a USB connector, an HDMI connector, an Ethernet connector, and a VGA connector.
[0078] According to an embodiment of the present invention, the data transmission format of the target data connector is obtained, a preset number of test data of the target data connector is prepared according to the data transmission format, and the test data is split to obtain split data, wherein the split data includes the split block test data and the assembly identifier of the block data, specifically:
[0079] Acquire functional data of the target data connector, and determine the data transmission format of the target data connector according to the functional data, wherein the data transmission format includes data structure, data type, and transmission protocol;
[0080] Prepare data transmission test data of a preset number of target data connectors according to the data transmission format;
[0081] Building a distributed file system based on big data technology, uploading the test data to the distributed file system, and performing a split operation on the test data to obtain a plurality of block test data;
[0082] Read each block of test data, calculate a hash value of each block of data according to a hash function, and use the hash value as a unique identifier of each block of data;
[0083] Obtaining the starting offset and size of each block of test data according to the splitting record of the test data during the splitting operation, and obtaining an assembly identifier of the block of test data, wherein the assembly identifier includes a unique identifier of the block of data and a starting offset and size of the block of test data;
[0084] The split block test data and the assembly identifier of the block data are integrated to obtain split data of the test data.
[0085] It should be noted that according to the data transmission format, data transmission test data of the target data connector of a preset number of levels is prepared to ensure the adequacy and representativeness of the test data, and a distributed file system is built using big data technology, and the test data is uploaded to it and split into multiple blocks of test data. This can improve the efficiency of data storage and management, and provide a basis for subsequent data processing and analysis; by using a hash function to calculate the hash value of each block of test data and obtain the starting offset and size of each block of test data, it helps to accurately assemble data blocks into complete data during data transmission and processing, and generate a unique identifier for each block of data. The identifier is unique and immutable, which can ensure that each data block can be accurately identified and located during data transmission and processing, which helps to track and manage data.
[0086] According to an embodiment of the present invention, the data transmission load test is performed on the target data connector according to the split data to identify data transmission characteristics, wherein the data transmission characteristics include data transmission rate characteristics, data concurrent connection characteristics, data transmission signal distortion characteristics, and data transmission delay characteristics, specifically:
[0087] Deploy a test environment for the target data connector, determine a data interaction device for the test environment, and import the split data into the test environment to perform a data maximum load transmission test;
[0088] Record the time and end time of the data transmission test, monitor the transmission rate change of the target data connector in real time according to the transmission time and data volume, and obtain the data transmission rate characteristics of each block data;
[0089] Monitor the changes in the number of concurrent transmissions of split data by the target data connector, determine the fluctuations and trends of the number of data block transmission connections, and obtain the data concurrent connection characteristics of the block data;
[0090] Comparing the size of each block data of the split data before and after the data transmission test to obtain block data size change data, determining the packet loss situation of the target data connector according to the block data size change data, and obtaining the data transmission signal distortion characteristics of each block data;
[0091] The data transmission delay time of the target data connector is calculated according to the transmission start time and data receiving time of each block data in the data transmission test, and the data transmission delay characteristics of each block data are obtained.
[0092] It should be noted that by identifying the characteristics of data transmission, the performance indicators of the target data connector can be effectively monitored and evaluated, which is conducive to providing a data basis for subsequent data monitoring.
[0093] Figure 2 A flow chart of obtaining outlier detection results according to the present invention is shown.
[0094] According to an embodiment of the present invention, the data outlier detection is performed on the data transmission feature according to the outlier detection algorithm to obtain the outlier detection result, specifically:
[0095] S202, performing outlier detection on each feature data in the data transmission feature in turn based on the LOF algorithm;
[0096] S204, for the data transmission feature entering the outlier detection, calculate the distance between each data point in the data transmission feature and other data points in the data transmission feature, find K nearest neighbors of each data point according to the size of the distance, and obtain K-nearest neighbor data points;
[0097] S206, calculating the reachable distance between each data point and each data point in the K-nearest neighbor data points, and calculating the local reachable density of each data point according to the reachable distance;
[0098] S208, calculating the local outlier factor of each data point according to the local reachable density, performing a marking operation on the outlier factor, and obtaining an outlier detection result, wherein the outlier detection result includes the marked outlier block data and the outlier degree of the marked outlier block data for each feature in the data transmission feature.
[0099] It should be noted that by performing outlier detection on the data transmission features through the LOF outlier detection algorithm, outlier data points in the data transmission features can be effectively identified, and outliers can be found more accurately by calculating the relationship between local density and neighbors; the LOF algorithm can consider the density relationship between data points and their neighboring points, and is more flexible and accurate than some distance threshold-based methods, which can reduce the false alarm rate and improve the accuracy and reliability of outlier detection; the data transmission features entering the outlier detection are the features contained in the data transmission features, which are detected outliers in turn.
[0100] According to an embodiment of the present invention, the split data after the data transmission load test is subjected to integrity assessment based on a fingerprint algorithm to obtain an integrity assessment result, specifically:
[0101] A fingerprint algorithm is introduced to identify the hash function used when calculating the hash value of each block of data in the split data, and the hash value of the split data after the data transmission load test is calculated according to the hash function;
[0102] Generate a fingerprint of each block of data before and after the data transmission load test according to the hash value of each block of data before and after the data transmission load test, wherein the fingerprint includes reference fingerprint data of each block of data before the data transmission load test and fingerprint data to be evaluated of each block of data after the data transmission load test;
[0103] Comparing the reference fingerprint data with the fingerprint data to be evaluated, determining the similarity between the fingerprint data to be evaluated and the reference fingerprint data, and obtaining a similarity score for each block of data before and after the data transmission load test;
[0104] Determine a similarity score threshold according to a preset data integrity standard, mark the block data after the data transmission load test that is lower than the similarity score threshold, and obtain marked low-similarity block data;
[0105] Perform a data damage degree assessment on the marked low-similarity block data to obtain damage degree assessment data, calculate the proportion of the marked low-similarity block data, determine the integrity of the split data after the data transmission load test based on the proportion and the damage degree assessment data, and obtain an integrity assessment result.
[0106] It should be noted that the fingerprint algorithm is used to generate fingerprints for the block data of the split data before and after the data transmission load test, and the fingerprint data is evaluated for similarity, and finally an integrity assessment report of the block data before and after the data transmission load test is obtained; the fingerprint algorithm can generate a unique identifier for the data, which is used to verify whether any changes have occurred to the data during the transmission process; the integrity assessment result provides detailed data integrity status, including which block data have problems and the specific nature of the problems; the integrity of the split data is the overall integrity assessment result of the block data after the data transmission load test.
[0107] According to an embodiment of the present invention, determining the influence characteristics of data transmission by the target data connector according to the outlier detection result and the integrity assessment result is specifically:
[0108] According to the outlier detection result and the integrity assessment result, the same block data is identified for the marked outlier block data and the marked low-similarity block data to obtain the same block data;
[0109] Based on the information entropy weight method, a correlation analysis is performed on the outlier degree and the data damage degree of the same block data to determine the influence weight of the outlier degree of each feature in the data transmission feature of the block data on the data damage degree;
[0110] Determine the outlier value of the marked outlier block data and the data range of the non-outlier block data according to the outlier detection result, and obtain the outlier judgment standard data;
[0111] The impact characteristics of the target data connector for data transmission are determined based on the impact weight and outlier judgment standard data, wherein the impact characteristics include the impact weight characteristics of each data transmission feature of the target data connector on data damage during the data transmission process, the impact degree characteristics of the outlier degree of each data transmission feature on data damage, and the outlier standard judgment standard for block data.
[0112] It should be noted that by conducting a correlation analysis between the degree of outliers and the degree of data corruption for the same block data based on the information entropy weight method, the influence weight of the degree of outliers of each data transmission feature on data corruption can be determined, which helps to determine which aspects of the data transmission features are more likely to cause data corruption; based on the outlier detection results, the outlier values of the marked outlier data and the data range of the non-outlier data are determined to obtain the outlier judgment standard data, which helps to provide standards and basis for subsequent outlier data identification and processing; the influencing features are the features that will affect the performance of data transmission during the data transmission process of the target data connector.
[0113] Figure 3 A flow chart of the present invention for analyzing the data transmission stability of a target data connector in real time is shown.
[0114] According to an embodiment of the present invention, the real-time data transmission of the target data connector is monitored according to the influencing feature, and the data transmission stability of the target data connector is analyzed in real time, specifically:
[0115] S302, monitoring the real-time data transmission process of the target data connector according to the influencing characteristics, and identifying in real time the data transmission characteristics of the target data connector during the real-time data transmission process;
[0116] S304, performing data transmission stability monitoring on the data transmission characteristics of the target data connector during the real-time data transmission process according to the influencing characteristics, and obtaining a data transmission stability monitoring result;
[0117] S306: If the data transmission stability is lower than a preset value, a warning operation is performed on the real-time data transmission.
[0118] It should be noted that the data transmission of the target data connector during the real-time data transmission process is monitored through the influencing characteristics. The data transmission rate characteristics, data concurrent connection characteristics, data transmission signal distortion characteristics, and data transmission delay characteristics of the target data connector during the real-time data transmission process are monitored to evaluate whether these characteristics are within the influencing characteristic range. If they are within the influencing characteristic range, it means that the transmission performance of the target data connector has declined. Finally, data transmission stability monitoring is performed to monitor changes in data transmission rate, changes in the number of concurrent data connections, changes in data transmission signal distortion, and changes in data transmission delay during the data transmission process, and then the data transmission stability of the target data connector is determined. If the stability is lower than the preset value, an early warning operation is performed to remind relevant personnel to replace the target data connector or change the data transmission channel, so as to avoid a reduction in data transmission efficiency due to a reduction in the stability of the data connector, and to avoid causing freezes or slow responses in applications with high real-time requirements, affecting user experience, and further avoiding data loss or damage due to unstable data transmission performance.
[0119] According to an embodiment of the present invention, it also includes:
[0120] Acquire data transmission stability monitoring result data within a preset time period, and plot the data transmission stability within the preset time period as a curve graph according to the data transmission stability monitoring result data;
[0121] Performing trend analysis on the curve graph based on a polynomial fitting method to obtain data transmission stability change trend data;
[0122] Obtain a historical data transmission stability curve chart of the target data connector under standard conditions;
[0123] A data transmission stability prediction model for the target data connector is constructed based on the LSTM algorithm, and the data transmission stability monitoring result data that changes with time in the curve graph is imported into the data transmission stability prediction model in a time series for training and learning;
[0124] The data transmission stability change trend data is used as the prediction basis of the LSTM model to obtain the real-time data transmission stability data of the target data connector in the current time period;
[0125] Importing the real-time data transmission stability data into a data transmission stability prediction model, predicting the data transmission stability of the target data connector within a future preset time period, and obtaining a data transmission stability prediction result;
[0126] Plotting the data transmission stability prediction result as a predicted stability change curve graph;
[0127] Compare the predicted stability change curve with the historical data transmission stability curve, mark and count the abnormal stability curve segments in the predicted stability change curve, and analyze the number and proportion of abnormal curve segments;
[0128] The life of the target connector in a future preset time period is evaluated according to the number and proportion of the abnormal curve segments to obtain a life prediction result of the target data connector.
[0129] It should be noted that, during the use of the target data connector, it is normal for the stability fluctuation to occur less than the preset number of times within a certain time range, but if the frequent stability fluctuation occurs more than the preset number of times within a certain time range, it can be determined that the target data connector has failed and the life of the target data connector has reached the end; by identifying the stability change trend of the target data connector within the preset time period and predicting the stability change in the future time period, by comparing the stability change curve of the future time period with the stability curve under the standard state, the abnormal stability curve segments of the stability change curve of the future time period are counted, and if the abnormal segments are greater than the preset number within the preset time period, it can be determined that the target data connector has failed; by predicting the life of the target data connector, managers can understand in advance the stability problems that may occur in the data connector in the future time period, which helps to take corresponding preventive measures or plan adjustments, which is crucial for data transmission of key businesses or applications, and can avoid data loss, delays and other problems, ensure the normal operation of the business, and perform maintenance in advance for upcoming stability problems to reduce unnecessary downtime and repair costs; the life prediction result includes the time point when the target data connector fails.
[0130] According to an embodiment of the present invention, it also includes:
[0131] Monitoring the volatility of the data transmission characteristics of the target data connector during the real-time data transmission process according to the data transmission characteristics of the target data connector during the real-time data transmission process, and obtaining the volatility monitoring data of the data transmission characteristics;
[0132] The volatility monitoring data is counted to obtain the number of fluctuations of each data transmission feature within a preset time period;
[0133] Determine a high-frequency fluctuation data transmission feature according to the fluctuation number, and mark the high-frequency fluctuation data transmission feature according to the high-frequency fluctuation data transmission feature to obtain a marking feature;
[0134] Acquire multiple target data connectors of the same type, and identify high-frequency fluctuation data transmission characteristics during data transmission of the multiple target data connectors of the same type;
[0135] Counting the number of target data connectors of the same type whose high-frequency fluctuation data transmission characteristics are used as marking characteristics during data transmission by the multiple target data connectors;
[0136] The proportion of the quantity is calculated. If the proportion is greater than a preset value, the marking feature is determined to be a native fluctuation feature, and the manufacturing process of the target data connector is adjusted.
[0137] It should be noted that the volatility of data transmission characteristics of multiple target data connectors within a preset time period is recorded to determine whether the high-frequency volatility is the same data transmission characteristic. If more than a preset number of target data connectors show the same high-frequency volatility of data transmission characteristics among multiple target data connectors, it can be determined that a manufacturing process problem occurred in the manufacturing process of the target data connector, resulting in a large number of data connectors showing volatility of the same data transmission characteristic. Ultimately, the manufacturing process is adjusted to avoid the degradation of data transmission performance due to the manufacturing process problems of the target data connector, thereby avoiding the performance degradation problem of the target data connector from the root.
[0138] Figure 4 A block diagram of a data connector dynamic monitoring system based on artificial intelligence of the present invention is shown.
[0139] The second aspect of the present invention further provides a data connector dynamic monitoring system 4 based on artificial intelligence, the system comprising: a memory 41, a processor 42, the memory comprising a data connector dynamic monitoring method program based on artificial intelligence, and when the data connector dynamic monitoring method program based on artificial intelligence is executed by the processor, the following steps are implemented:
[0140] Acquire a data transmission format of a target data connector, prepare a preset number of test data of the target data connector according to the data transmission format, and split the test data to obtain split data, wherein the split data includes split block test data and an assembly identifier of the block data;
[0141] Performing a data transmission load test on the target data connector according to the split data to identify data transmission characteristics, wherein the data transmission characteristics include data transmission rate characteristics, data concurrent connection characteristics, data transmission signal distortion characteristics, and data transmission delay characteristics;
[0142] Performing data outlier detection on the data transmission feature according to an outlier detection algorithm to obtain an outlier detection result;
[0143] Perform integrity assessment on the split data after the data transmission load test based on the fingerprint algorithm to obtain the integrity assessment result;
[0144] Determine the impact characteristics of data transmission by the target data connector according to the outlier detection result and the integrity assessment result;
[0145] The real-time data transmission of the target data connector is monitored according to the influencing characteristics, and the data transmission stability of the target data connector is analyzed in real time.
[0146] According to an embodiment of the present invention, the data transmission format of the target data connector is obtained, a preset number of test data of the target data connector is prepared according to the data transmission format, and the test data is split to obtain split data, wherein the split data includes the split block test data and the assembly identifier of the block data, specifically:
[0147] Acquire functional data of the target data connector, and determine the data transmission format of the target data connector according to the functional data, wherein the data transmission format includes data structure, data type, and transmission protocol;
[0148] Prepare data transmission test data of a preset number of target data connectors according to the data transmission format;
[0149] Building a distributed file system based on big data technology, uploading the test data to the distributed file system, and performing a split operation on the test data to obtain a plurality of block test data;
[0150] Read each block of test data, calculate a hash value of each block of data according to a hash function, and use the hash value as a unique identifier of each block of data;
[0151] Obtaining the starting offset and size of each block of test data according to the splitting record of the test data during the splitting operation, and obtaining an assembly identifier of the block of test data, wherein the assembly identifier includes a unique identifier of the block of data and a starting offset and size of the block of test data;
[0152] The split block test data and the assembly identifier of the block data are integrated to obtain split data of the test data.
[0153] According to an embodiment of the present invention, the data transmission load test is performed on the target data connector according to the split data to identify data transmission characteristics, wherein the data transmission characteristics include data transmission rate characteristics, data concurrent connection characteristics, data transmission signal distortion characteristics, and data transmission delay characteristics, specifically:
[0154] Deploy a test environment for the target data connector, determine a data interaction device for the test environment, and import the split data into the test environment to perform a data maximum load transmission test;
[0155] Record the time and end time of the data transmission test, monitor the transmission rate change of the target data connector in real time according to the transmission time and data volume, and obtain the data transmission rate characteristics of each block data;
[0156] Monitor the changes in the number of concurrent transmissions of split data by the target data connector, determine the fluctuations and trends of the number of data block transmission connections, and obtain the data concurrent connection characteristics of the block data;
[0157] Comparing the size of each block data of the split data before and after the data transmission test to obtain block data size change data, determining the packet loss situation of the target data connector according to the block data size change data, and obtaining the data transmission signal distortion characteristics of each block data;
[0158] The data transmission delay time of the target data connector is calculated according to the transmission start time and data receiving time of each block data in the data transmission test, and the data transmission delay characteristics of each block data are obtained.
[0159] According to an embodiment of the present invention, the data outlier detection is performed on the data transmission feature according to the outlier detection algorithm to obtain the outlier detection result, specifically:
[0160] Performing outlier detection on each feature data in the data transmission feature in turn based on the LOF algorithm;
[0161] For the data transmission feature entering the outlier detection, the distance between each data point in the data transmission feature and other data points in the data transmission feature is calculated, and the K nearest neighbors of each data point are found according to the size of the distance to obtain the K-nearest neighbor data points;
[0162] Calculate the reachable distance between each data point and each data point in the K-nearest neighbor data points, and calculate the local reachable density of each data point based on the reachable distance;
[0163] The local outlier factor of each data point is calculated according to the local reachable density, and a marking operation is performed on the outlier factor to obtain an outlier detection result, wherein the outlier detection result includes the marked outlier block data and the outlier degree of the marked outlier block data for each feature in the data transmission feature.
[0164] According to an embodiment of the present invention, the split data after the data transmission load test is subjected to integrity assessment based on a fingerprint algorithm to obtain an integrity assessment result, specifically:
[0165] A fingerprint algorithm is introduced to identify the hash function used when calculating the hash value of each block of data in the split data, and the hash value of the split data after the data transmission load test is calculated according to the hash function;
[0166] Generate a fingerprint of each block of data before and after the data transmission load test according to the hash value of each block of data before and after the data transmission load test, wherein the fingerprint includes reference fingerprint data of each block of data before the data transmission load test and fingerprint data to be evaluated of each block of data after the data transmission load test;
[0167] Comparing the reference fingerprint data with the fingerprint data to be evaluated, determining the similarity between the fingerprint data to be evaluated and the reference fingerprint data, and obtaining a similarity score for each block of data before and after the data transmission load test;
[0168] Determine a similarity score threshold according to a preset data integrity standard, mark the block data after the data transmission load test that is lower than the similarity score threshold, and obtain marked low-similarity block data;
[0169] Perform a data damage degree assessment on the marked low-similarity block data to obtain damage degree assessment data, calculate the proportion of the marked low-similarity block data, determine the integrity of the split data after the data transmission load test based on the proportion and the damage degree assessment data, and obtain an integrity assessment result.
[0170] According to an embodiment of the present invention, determining the influence characteristics of data transmission by the target data connector according to the outlier detection result and the integrity assessment result is specifically:
[0171] According to the outlier detection result and the integrity assessment result, the same block data is identified for the marked outlier block data and the marked low-similarity block data to obtain the same block data;
[0172] Based on the information entropy weight method, a correlation analysis is performed on the outlier degree and the data damage degree of the same block data to determine the influence weight of the outlier degree of each feature in the data transmission feature of the block data on the data damage degree;
[0173] Determine the outlier value of the marked outlier block data and the data range of the non-outlier block data according to the outlier detection result, and obtain the outlier judgment standard data;
[0174] The impact characteristics of the target data connector for data transmission are determined based on the impact weight and outlier judgment standard data, wherein the impact characteristics include the impact weight characteristics of each data transmission feature of the target data connector on data damage during the data transmission process, the impact degree characteristics of the outlier degree of each data transmission feature on data damage, and the outlier standard judgment standard for block data.
[0175] According to an embodiment of the present invention, the real-time data transmission of the target data connector is monitored according to the influencing feature, and the data transmission stability of the target data connector is analyzed in real time, specifically:
[0176] The real-time data transmission process of the target data connector is monitored according to the influencing characteristics, and the data transmission characteristics of the target data connector during the real-time data transmission process are identified in real time;
[0177] Performing data transmission stability monitoring on the data transmission characteristics of the target data connector during real-time data transmission according to the influencing characteristics to obtain a data transmission stability monitoring result;
[0178] If the data transmission stability is lower than the preset value, an early warning operation will be performed on the real-time data transmission.
[0179] According to an embodiment of the present invention, it also includes:
[0180] Acquire data transmission stability monitoring result data within a preset time period, and plot the data transmission stability within the preset time period as a curve graph according to the data transmission stability monitoring result data;
[0181] Performing trend analysis on the curve graph based on a polynomial fitting method to obtain data transmission stability change trend data;
[0182] Obtain a historical data transmission stability curve chart of the target data connector under standard conditions;
[0183] A data transmission stability prediction model for the target data connector is constructed based on the LSTM algorithm, and the data transmission stability monitoring result data that changes with time in the curve graph is imported into the data transmission stability prediction model in a time series for training and learning;
[0184] The data transmission stability change trend data is used as the prediction basis of the LSTM model to obtain the real-time data transmission stability data of the target data connector in the current time period;
[0185] Importing the real-time data transmission stability data into a data transmission stability prediction model, predicting the data transmission stability of the target data connector within a future preset time period, and obtaining a data transmission stability prediction result;
[0186] Plotting the data transmission stability prediction result as a predicted stability change curve graph;
[0187] Compare the predicted stability change curve with the historical data transmission stability curve, mark and count the abnormal stability curve segments in the predicted stability change curve, and analyze the number and proportion of abnormal curve segments;
[0188] The life of the target connector in a future preset time period is evaluated according to the number and proportion of the abnormal curve segments to obtain a life prediction result of the target data connector.
[0189] According to an embodiment of the present invention, it also includes:
[0190] Monitoring the volatility of the data transmission characteristics of the target data connector during the real-time data transmission process according to the data transmission characteristics of the target data connector during the real-time data transmission process, and obtaining the volatility monitoring data of the data transmission characteristics;
[0191] The volatility monitoring data is counted to obtain the number of fluctuations of each data transmission feature within a preset time period;
[0192] Determine a high-frequency fluctuation data transmission feature according to the fluctuation number, and mark the high-frequency fluctuation data transmission feature according to the high-frequency fluctuation data transmission feature to obtain a marking feature;
[0193] Acquire multiple target data connectors of the same type, and identify high-frequency fluctuation data transmission characteristics during data transmission of the multiple target data connectors of the same type;
[0194] Counting the number of target data connectors of the same type whose high-frequency fluctuation data transmission characteristics are used as marking characteristics during data transmission by the multiple target data connectors;
[0195] The proportion of the quantity is calculated. If the proportion is greater than a preset value, the marking feature is determined to be a native fluctuation feature, and the manufacturing process of the target data connector is adjusted.
[0196] The present invention discloses a data connector dynamic monitoring method and system based on artificial intelligence. First, the transmission format of the target data connector is obtained and test data is prepared. Then, the test data is split and the connector is load tested to identify transmission characteristics such as rate, concurrent connections, signal distortion and delay. The outlier detection algorithm is used to detect the characteristics, and the data integrity is evaluated based on the fingerprint algorithm. According to the results, the transmission influencing characteristics of the connector are determined, and its stability is monitored in real time. The present invention combines artificial intelligence technology to comprehensively monitor data transmission, improve reliability, and has practical value.
[0197] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
[0198] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0199] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0200] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.
[0201] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.
[0202] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
Claims
1. A dynamic monitoring method for data connectors based on artificial intelligence, It is characterized in that The following steps are involved: Acquire a data transmission format of a target data connector, prepare a preset number of test data of the target data connector according to the data transmission format, and split the test data to obtain split data, wherein the split data includes split block test data and assembly identifiers of the block test data; Performing a data transmission load test on the target data connector according to the split data to identify data transmission characteristics, wherein the data transmission characteristics include data transmission rate characteristics, data concurrent connection characteristics, data transmission signal distortion characteristics, and data transmission delay characteristics; Performing data outlier detection on the data transmission feature according to an outlier detection algorithm to obtain an outlier detection result; Perform integrity assessment on the split data after the data transmission load test based on the fingerprint algorithm to obtain the integrity assessment result; Determine the impact characteristics of data transmission by the target data connector according to the outlier detection result and the integrity assessment result; The real-time data transmission of the target data connector is monitored according to the influencing characteristics, and the data transmission stability of the target data connector is analyzed in real time.
2. According to claim 1, a data connector dynamic monitoring method based on artificial intelligence, It is characterized in that The data transmission format of the target data connector is obtained, a preset number of test data of the target data connector is prepared according to the data transmission format, and the test data is split to obtain split data, wherein the split data includes the split block test data and the assembly identifier of the block test data, specifically: Acquire functional data of the target data connector, and determine the data transmission format of the target data connector according to the functional data, wherein the data transmission format includes data structure, data type, and transmission protocol; Prepare data transmission test data of a preset number of target data connectors according to the data transmission format; Building a distributed file system based on big data technology, uploading the test data to the distributed file system, and performing a split operation on the test data to obtain a plurality of block test data; Read each block of test data, calculate a hash value of each block of test data according to a hash function, and use the hash value as a unique identifier of each block of test data; Acquire the starting offset and size of each block test data according to the splitting record of the test data during the splitting operation, and obtain an assembly identifier of the block test data, wherein the assembly identifier includes a unique identifier of the block test data and a starting offset and size of the block test data; The split block test data and the assembly identifier of the block test data are integrated to obtain split data of the test data.
3. According to the artificial intelligence-based data connector dynamic monitoring method of claim 1, It is characterized in that The data transmission load test is performed on the target data connector according to the split data to identify data transmission characteristics, wherein the data transmission characteristics include data transmission rate characteristics, data concurrent connection characteristics, data transmission signal distortion characteristics, and data transmission delay characteristics, specifically: Deploy a test environment for the target data connector, determine a data interaction device for the test environment, and import the split data into the test environment to perform a data maximum load transmission test; Record the time and end time of the data transmission test, monitor the transmission rate change of the target data connector in real time according to the transmission time and data volume, and obtain the data transmission rate characteristics of each block test data; Monitor the changes in the number of concurrent transmissions of split data by the target data connector, determine the fluctuations and trends in the number of data block transmission connections, and obtain the data concurrent connection characteristics of the block test data; Comparing the size of each block test data of the split data before and after the data transmission test to obtain block test data size change data, determining the packet loss situation of the target data connector according to the block test data size change data, and obtaining the data transmission signal distortion characteristics of each block test data; The data transmission delay time of the target data connector is calculated according to the transmission start time and data receiving time of each block test data in the data transmission test, and the data transmission delay characteristics of each block test data are obtained.
4. According to claim 1, a data connector dynamic monitoring method based on artificial intelligence, It is characterized in that The outlier detection is performed on the data transmission feature according to the outlier detection algorithm to obtain an outlier detection result, specifically: Performing outlier detection on each feature data in the data transmission feature in turn based on the LOF algorithm; For the data transmission feature entering the outlier detection, the distance between each data point in the data transmission feature and other data points in the data transmission feature is calculated, and the K nearest neighbors of each data point are found according to the size of the distance to obtain the K-nearest neighbor data points; Calculate the reachable distance between each data point and each data point in the K-nearest neighbor data points, and calculate the local reachable density of each data point based on the reachable distance; The local outlier factor of each data point is calculated according to the local reachable density, and the outlier factor is marked to obtain an outlier detection result, which includes the marked outlier block test data and the outlier degree of the marked outlier block test data for each feature in the data transmission feature.
5. According to claim 2, a data connector dynamic monitoring method based on artificial intelligence, It is characterized in that The split data after the data transmission load test is subjected to integrity assessment based on the fingerprint algorithm to obtain the integrity assessment result, which is specifically: A fingerprint algorithm is introduced to identify the hash function used when calculating the hash value of each block test data in the split data, and the hash value of the split data after the data transmission load test is calculated according to the hash function; Generate a fingerprint of each block test data before and after the data transmission load test according to the hash value of each block test data before and after the data transmission load test, wherein the fingerprint includes reference fingerprint data of each block test data before the data transmission load test and fingerprint data to be evaluated of each block test data after the data transmission load test; Comparing the reference fingerprint data with the fingerprint data to be evaluated, determining the similarity between the fingerprint data to be evaluated and the reference fingerprint data, and obtaining a similarity score of each block test data before and after the data transmission load test; Determine a similarity score threshold according to a preset data integrity standard, mark the block test data after the data transmission load test that is lower than the similarity score threshold, and obtain marked low-similarity block test data; Perform a data damage degree assessment on the marked low-similarity block test data to obtain damage degree assessment data, calculate the proportion of the marked low-similarity block test data, determine the integrity of the split data after the data transmission load test based on the proportion and the damage degree assessment data, and obtain an integrity assessment result.
6. According to claim 1, a data connector dynamic monitoring method based on artificial intelligence, It is characterized in that The determining of the impact characteristics of data transmission by the target data connector according to the outlier detection result and the integrity assessment result is specifically: According to the outlier detection result and the integrity assessment result, the marked outlier block test data and the marked low-similarity block test data are identified as the same block test data to obtain the same block test data; Based on the information entropy weight method, a correlation analysis is performed on the outlier degree and the data damage degree of the same block test data to determine the influence weight of the outlier degree of each feature in the data transmission feature of the block test data on the data damage degree; Determine the outlier value of the marked outlier block test data and the data range of the non-outlier block test data according to the outlier detection result, and obtain the outlier judgment standard data; The impact characteristics of the target data connector for data transmission are determined based on the impact weight and outlier judgment standard data, wherein the impact characteristics include the impact weight characteristics of each data transmission characteristic of the target data connector on data damage during the data transmission process, the impact degree characteristics of the outlier degree of each data transmission characteristic on data damage, and the outlier standard judgment standard of the block test data.
7. According to claim 1, a data connector dynamic monitoring method based on artificial intelligence, It is characterized in that The real-time data transmission of the target data connector is monitored according to the influencing characteristics, and the data transmission stability of the target data connector is analyzed in real time, specifically: The real-time data transmission process of the target data connector is monitored according to the influencing characteristics, and the data transmission characteristics of the target data connector during the real-time data transmission process are identified in real time; Performing data transmission stability monitoring on the data transmission characteristics of the target data connector during real-time data transmission according to the influencing characteristics to obtain a data transmission stability monitoring result; If the data transmission stability is lower than the preset value, an early warning operation will be performed on the real-time data transmission.
8. A data connector dynamic monitoring system based on artificial intelligence, It is characterized in that The data connector dynamic monitoring system based on artificial intelligence includes a storage and a processor, wherein the storage includes a data connector dynamic monitoring method program based on artificial intelligence, and when the data connector dynamic monitoring method program based on artificial intelligence is executed by the processor, the following steps are implemented: Acquire a data transmission format of a target data connector, prepare a preset number of test data of the target data connector according to the data transmission format, and split the test data to obtain split data, wherein the split data includes split block test data and assembly identifiers of the block test data; Performing a data transmission load test on the target data connector according to the split data to identify data transmission characteristics, wherein the data transmission characteristics include data transmission rate characteristics, data concurrent connection characteristics, data transmission signal distortion characteristics, and data transmission delay characteristics; Performing data outlier detection on the data transmission feature according to an outlier detection algorithm to obtain an outlier detection result; Perform integrity assessment on the split data after the data transmission load test based on the fingerprint algorithm to obtain the integrity assessment result; Determine the impact characteristics of data transmission by the target data connector according to the outlier detection result and the integrity assessment result; The real-time data transmission of the target data connector is monitored according to the influencing characteristics, and the data transmission stability of the target data connector is analyzed in real time.
9. The data connector dynamic monitoring system based on artificial intelligence according to claim 8, It is characterized in that The determining of the impact characteristics of data transmission by the target data connector according to the outlier detection result and the integrity assessment result is specifically: According to the outlier detection result and the integrity assessment result, the marked outlier block test data and the marked low-similarity block test data are identified as the same block test data to obtain the same block test data; Based on the information entropy weight method, a correlation analysis is performed on the outlier degree and the data damage degree of the same block test data to determine the influence weight of the outlier degree of each feature in the data transmission feature of the block test data on the data damage degree; Determine the outlier value of the marked outlier block test data and the data range of the non-outlier block test data according to the outlier detection result, and obtain the outlier judgment standard data; The impact characteristics of the target data connector for data transmission are determined based on the impact weight and outlier judgment standard data, wherein the impact characteristics include the impact weight characteristics of each data transmission characteristic of the target data connector on data damage during the data transmission process, the impact degree characteristics of the outlier degree of each data transmission characteristic on data damage, and the outlier standard judgment standard of the block test data.
10. The data connector dynamic monitoring system based on artificial intelligence according to claim 8, It is characterized in that The real-time data transmission of the target data connector is monitored according to the influencing characteristics, and the data transmission stability of the target data connector is analyzed in real time, specifically: The real-time data transmission process of the target data connector is monitored according to the influencing characteristics, and the data transmission characteristics of the target data connector during the real-time data transmission process are identified in real time; Performing data transmission stability monitoring on the data transmission characteristics of the target data connector during real-time data transmission according to the influencing characteristics to obtain a data transmission stability monitoring result; If the data transmission stability is lower than the preset value, an early warning operation will be performed on the real-time data transmission.
