Trans-national office communication quality monitoring method, system, device and medium
Through the combination of deep neural network and support vector machine model, communication data is analyzed and predicted, early warning reports and adjustment suggestions are generated, and the frequent occurrence of communication failures in complex network environments is solved, and communication quality and efficiency are improved.
Patent Information
- Application Number
- CN202411054996.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-02
- Publication Date
- 2024-12-03
AI Technical Summary
The existing technology cannot effectively respond to the complex and changeable network environment and the need to refine communication quality monitoring, resulting in frequent communication failures and affecting the normal operation of the enterprise.
The deep neural network model is used to analyze communication data, extract network performance indicators, and use the support vector machine model to predict the next stage of network communication data, generate early warning reports and adjustment suggestions, locate faults and optimize the network.
It improves communication quality and efficiency, promptly discovers and solves potential problems, improves network stability and operational efficiency, and reduces the impact of failures on enterprise operations.
Smart Images

Figure CN119066440A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of communication quality, and in particular to a method, system, device and medium for monitoring the quality of cross-border internal office communications. Background Art
[0002] At present, with the development of enterprise globalization, the demand for internal office communications across countries is increasing, and the quality of communication directly affects the office efficiency and business operations of enterprises. At present, there are some cloud computing-based communication systems and quality monitoring technologies, but they are still insufficient in dealing with complex and changing network environments and finely monitoring communication quality. Traditional communication quality monitoring methods mainly rely on manual inspections and regular maintenance, which are not only inefficient, but also difficult to detect and solve problems in a timely manner. Although some existing automated monitoring systems can monitor communication quality in real time, they often lack fine management methods and optimized solutions.
[0003] The above-mentioned existing technical solutions have the following defects: the existing technology cannot effectively cope with the complex and changeable network environment and the need for refined monitoring of communication quality, resulting in frequent communication failures and affecting the normal operation of the enterprise. Therefore, there is room for improvement. Summary of the invention
[0004] In order to improve the stability and efficiency of communications, the present application provides a method, system, device and medium for monitoring the quality of cross-border internal office communications.
[0005] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A method for monitoring the quality of cross-border internal office communications, the method comprising: Obtain communication data of internal office networks of multinational companies; Analyzing the communication data using a trained deep neural network model to extract network performance indicators; According to the network performance indicators, the support vector machine model is used to predict the network communication data for the next stage; Matching the next-stage network communication data with preset communication data, and generating an early warning report when the matching result is that the communication data does not match; According to the early warning report, the fault is located and adjustment suggestion information is generated.
[0006] By adopting the above technical solution, the communication data of the internal office network of a multinational enterprise is first obtained, and the communication data is analyzed using a trained deep neural network model, and key network performance indicators are extracted from it. The deep neural network model can discover complex and nonlinear patterns in a large amount of data, which helps to obtain more accurate network performance indicators; then, the support vector machine model is used to predict the network communication data of the next stage based on the network performance indicators. By predicting the network performance indicator data of the next stage, fault warning of network performance is achieved, which helps to improve the quality and efficiency of communication; and these predicted data are matched with the preset communication data. If the matching result shows that the communication data does not match, an early warning report is generated. This report will detail which performance indicators have deviated and the degree of deviation. Finally, based on the early warning report, the possible causes of the network failure are further analyzed and located, and the failure is located according to the early warning report, and adjustment suggestion information is generated. By predicting and preventing potential network problems, the stability and operational efficiency of the network are improved.
[0007] In a preferred example, the present application may be further configured as follows: the communication data is analyzed using a trained deep neural network model, and the network performance index is extracted, including: Acquire historical network communication data, and preprocess the historical network communication data to obtain an initial training data set; Using the initial training data set to train the initial model to obtain the trained deep neural network model; The trained deep neural network model is used to read and analyze the communication data to obtain the network performance index.
[0008] By adopting the above technical solution, the required data is first obtained from the historical network communication data, and then the data is preprocessed to meet the needs of model training, so as to improve the accuracy of model training and enable subsequent processing data to obtain more accurate processing results; after having the initial training data set, use these data to train the deep neural network model. During the training process, the model will continuously adjust its parameters to obtain the best performance on the training data set. Through a large amount of historical network communication data, a deep neural network model that can accurately extract network performance indicators can be trained; after having a trained model, it can be used to analyze new communication data and obtain network performance indicators from it, which is helpful for real-time monitoring of network performance. The model can analyze new communication data in real time and provide real-time feedback on network performance, so that operation and maintenance personnel can quickly respond to changes in network performance and adjust and optimize the network in time.
[0009] In a preferred example, the present application may be further configured as follows: the prediction of the next stage network communication data using the support vector machine model according to the network performance indicator includes: Obtain the network performance indicator data of the previous stage and the corresponding network performance indicator data; Training the initial data processing model according to the network performance indicator data of the previous stage and the corresponding network performance indicator data to obtain the support vector machine model; The network performance index is normalized, and the processed data is input into the support vector machine model for prediction to obtain the network communication data of the next stage.
[0010] By adopting the above technical solution, the network performance indicator data of the previous stage and the corresponding network performance indicator data during this period are first obtained, and then a support vector machine model is trained based on these historical data. By learning and predicting the historical network performance indicator data, possible network performance problems can be effectively predicted and solved; after the preprocessing step, the obtained network performance indicators are normalized, that is, the data is converted into a standard range, and then the processed data is used as input and input into the support vector machine model for prediction. The result is the network performance indicator of the next stage. The use of support vector machines makes the prediction results more accurate and more confident in the grasp of future network performance; at the same time, through normalization, input data of different ranges have the same proportion in the training and prediction process, which improves the robustness of the prediction model and helps to improve the accuracy and efficiency during communication.
[0011] In a preferred example, the present application may be further configured as follows: matching the next phase network communication data with the preset communication data, and when the matching result is that the communication data does not match, generating an early warning report includes: Comparing and matching the next-stage network communication data with preset communication data; When the matching result indicates that the communication data matches, generating a normal working message; When the matching result shows that the communication data does not match, an early warning mechanism is triggered to generate an early warning report including difference details and communication impact.
[0012] By adopting the above technical solution, the predicted network communication data of the next stage and the preset communication data are compared to see whether they match. If the predicted data of the network communication matches the preset data, that is, the network status develops as expected, then a normal working message will be generated, indicating that the network condition is good. If the predicted and preset data do not match, the early warning mechanism will be triggered to generate an early warning report. This report will include details of the difference between the predicted and actual data, as well as the impact on network communication that may be caused by such a difference. The network operation status is monitored in real time, and an early warning is generated in time when network performance degrades or failures occur, so that network administrators can take timely action to solve possible problems and reduce the impact and losses caused by network failures.
[0013] In a preferred example, the present application may be further configured as follows: locating the fault according to the early warning report and generating adjustment suggestion information includes: Analyze the difference data in the early warning report to obtain the cause of data anomaly and locate the existing network fault point; Analyze the network fault point and generate the corresponding adjustment suggestion information.
[0014] By adopting the above technical solution, first, the difference data in the early warning report will be deeply analyzed to find out the specific reasons for the data anomalies. After finding out the reasons for the anomalies, the fault points in the network can be further located; then, the located fault points are analyzed, and then based on the analysis results, corresponding adjustment suggestion information is generated to provide specific suggestions or solutions for repairing the faults. This helps to quickly find out the reasons for the anomalies and locate the fault points when anomalies in network communication data are detected, so as to respond quickly and reduce the impact of network failures on enterprise operations. At the same time, the analysis of the faults and specific adjustment suggestions can assist operation and maintenance personnel to repair faults more effectively and specifically, improve work efficiency, and also help prevent similar faults from happening again.
[0015] In a preferred example, the present application may be further configured as follows: the analyzing the network fault point and generating the corresponding adjustment suggestion information includes: Analyze the network fault point according to log analysis and traffic analysis to obtain the communication impact caused by the network fault point; According to the cause of the data anomaly and the degree of impact of the communication impact, corresponding adjustment strategies and suggestion information are generated.
[0016] By adopting the above technical solution, based on system logs and network traffic data, we can understand the specific situation when the network fault point occurs, and by analyzing this information, we can derive the specific impact of the network fault point on communication; according to the cause of the data anomaly and the degree of communication impact caused by it, we will propose corresponding adjustment strategies and recommended information, so as to understand the cause and impact of the network failure more clearly, so as to take targeted and effective methods to repair the failure as soon as possible.
[0017] The second object of the invention is achieved by the following technical solutions: A transnational internal office communication quality monitoring system, the transnational internal office communication quality monitoring system comprising: The communication data acquisition module is used to acquire the communication data of the internal office network of a multinational enterprise; A feature extraction module is used to analyze the communication data using a trained deep neural network model to extract network performance indicators; A prediction module, used to predict the network communication data of the next stage using a support vector machine model according to the network performance indicators; An early warning module is used to match the next-stage network communication data with preset communication data, and generate an early warning report when the matching result is that the communication data does not match; The adjustment suggestion module is used to locate the fault according to the early warning report and generate adjustment suggestion information.
[0018] By adopting the above technical solution, the communication data of the internal office network of a multinational enterprise is first obtained, and the communication data is analyzed using a trained deep neural network model, and key network performance indicators are extracted from it. The deep neural network model can discover complex and nonlinear patterns in a large amount of data, which helps to obtain more accurate network performance indicators; then, the support vector machine model is used to predict the network communication data of the next stage based on the network performance indicators. By predicting the network performance indicator data of the next stage, fault warning of network performance is achieved, which helps to improve the quality and efficiency of communication; and these predicted data are matched with the preset communication data. If the matching result shows that the communication data does not match, an early warning report is generated. This report will detail which performance indicators have deviated and the degree of deviation. Finally, based on the early warning report, the possible causes of the network failure are further analyzed and located, and the failure is located according to the early warning report, and adjustment suggestion information is generated. By predicting and preventing potential network problems, the stability and operational efficiency of the network are improved.
[0019] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for monitoring the quality of cross-border internal office communications are implemented.
[0020] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for monitoring the quality of cross-border internal office communications are implemented.
[0021] In summary, the present application includes at least one of the following beneficial technical effects: 1. First, obtain the communication data of the internal office network of a multinational enterprise, use the trained deep neural network model to analyze the communication data, and extract key network performance indicators from it. The deep neural network model can find complex and nonlinear patterns in a large amount of data, which helps to obtain more accurate network performance indicators; then, use the support vector machine model to predict the network communication data of the next stage based on the network performance indicators. By predicting the network performance indicator data of the next stage, the fault warning of network performance is realized, which helps to improve the quality and efficiency of communication; and match these predicted data with the preset communication data. If the matching result shows that the communication data does not match, an early warning report is generated. This report will detail which performance indicators have deviated and the degree of deviation. Finally, based on the early warning report, further analyze and locate the possible causes of network failures, locate the failures based on the early warning report, and generate adjustment suggestion information. By predicting and preventing potential network problems, the stability and operational efficiency of the network can be improved; 2. First, the network performance index data of the previous stage and the corresponding network performance index data during this period are obtained. Then, a support vector machine model is trained based on these historical data. By learning and predicting the historical network performance index data, possible network performance problems can be effectively predicted and solved. After the preprocessing step, the obtained network performance index is normalized, that is, the data is converted into a standard range, and then the processed data is used as input and input into the support vector machine model for prediction. The result is the network performance index of the next stage. The use of support vector machines makes the prediction results more accurate and more confident in the grasp of future network performance. At the same time, through normalization, input data of different ranges have the same proportion in the training and prediction process, which improves the robustness of the prediction model and helps to improve the accuracy and efficiency of communication. 3. Conduct in-depth analysis of the difference data in the early warning report to find out the specific reasons for the data anomaly. After finding out the reasons for the anomaly, the fault points in the network can be further located. Then, analyze the located fault points, and then generate corresponding adjustment suggestion information based on the analysis results to provide specific suggestions or solutions for repairing the faults. This helps to quickly find out the reasons for the anomalies and locate the fault points when abnormalities in network communication data are detected, so as to respond quickly and reduce the impact of network failures on enterprise operations. At the same time, the analysis of the faults and specific adjustment suggestions can assist operation and maintenance personnel to repair faults more effectively and specifically, improve work efficiency, and also help prevent similar faults from happening again. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] Figure 1 is a flow chart of a method for monitoring the quality of cross-border internal office communications in one embodiment of the present application; Figure 2 This is a flowchart for implementing step S20 in a method for monitoring the quality of cross-border internal office communications in one embodiment of the present application; Figure 3 This is a flowchart for implementing step S30 in a method for monitoring the quality of cross-border internal office communications in one embodiment of the present application; Figure 4 This is a flowchart for implementing step S40 in a method for monitoring the quality of cross-border internal office communications in one embodiment of the present application; Figure 5 This is a flowchart for implementing step S50 in a method for monitoring the quality of cross-border internal office communications in one embodiment of the present application; Figure 6 This is a flowchart for implementing step S52 in a method for monitoring the quality of cross-border internal office communications in one embodiment of the present application; Figure 7 This is a principle block diagram of a transnational internal office communication quality monitoring system in one embodiment of the present application; Figure 8 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION
[0023] The present application is further described in detail below in conjunction with the accompanying drawings.
[0024] In one embodiment, if Figure 1 As shown, the present application discloses a method for monitoring the quality of cross-border internal office communications, which specifically includes the following steps: S10: Obtain communication data of the internal office network of a multinational enterprise.
[0025] Specifically, data packets on the network are captured through specific tools and technologies, such as network monitoring tools, packet sniffers, log servers, etc. to collect network communication data. These data include various information, such as network traffic, latency, packet loss rate, etc. The collected data will be stored and analyzed to identify network usage patterns, performance bottlenecks, security threats, etc., and then take corresponding optimization or protection measures.
[0026] S20: Use the trained deep neural network model to analyze the communication data and extract network performance indicators.
[0027] In this embodiment, the network performance index refers to a series of quantitative parameters used to evaluate the performance of a computer network.
[0028] Specifically, a labeled data set is used to train the model to identify network performance indicators. A deep neural network model that has learned the specific characteristics of network communications through a large amount of data is used to analyze the currently acquired communication data. The communication data is input into the model to allow the model to identify and process the communication data. By analyzing and extracting performance indicators, the network's operating status can be predicted, potential problems can be diagnosed, or the network configuration can be optimized, which helps to improve the efficiency of network management and help to promptly discover and resolve network problems.
[0029] S30: Based on the network performance indicators, the support vector machine model is used to predict the network communication data for the next stage.
[0030] Specifically, the support vector machine model is used to input current or historical network performance indicators as features to predict network communication data in the next period of time, such as the size of network traffic, possible delays, etc. Through prediction, potential network problems can be discovered in advance, such as congestion caused by traffic peaks or increased packet loss caused by hardware failures. The prediction results can help network administrators reasonably allocate network resources, such as bandwidth and storage, to cope with upcoming data transmission needs. Through accurate prediction, resource waste can be avoided. For example, the use of network equipment can be reduced during low-traffic periods, thereby saving energy and reducing maintenance costs.
[0031] S40: Match the next phase network communication data with the preset communication data, and generate an early warning report when the matching result is that the communication data does not match.
[0032] Specifically, the next stage of network communication data predicted by the support vector machine model is compared with a set of preset communication data standards. The preset communication data is set based on historical data, industry standards or the best performance indicators of the network. If the predicted communication data matches the preset data or is within an acceptable deviation range, then the network may be considered to be operating normally. When there is a significant difference between the predicted communication data and the preset communication data, the matching result is considered to be a communication data mismatch, which indicates that the network is about to or has encountered problems. Once a communication data mismatch is detected, the system will automatically generate an early warning report. This report will detail which performance indicators are beyond the preset range and the degree of deviation, which will help improve the stability and reliability of the network.
[0033] S50: According to the early warning report, the fault is located and adjustment suggestion information is generated.
[0034] Specifically, when the system generates an early warning report, the network administrator or automated fault management system will analyze the report content. The early warning report usually contains abnormal data of network performance indicators, such as sudden high latency, low throughput, high packet loss rate, etc. Through detailed analysis of the early warning report, the possible location of the fault can be determined. This may involve identifying the specific network device with the problem. After determining the fault location, further analysis of the possible causes of these anomalies, such as hardware failure, software configuration errors, network congestion, security attacks or other network problems, based on the results of fault location and cause inference, the system will generate a series of adjustment suggestions, which will help to quickly locate the fault and generate adjustment suggestions.
[0035] By adopting the above technical solution, the communication data of the internal office network of a multinational enterprise is first obtained, and the communication data is analyzed using a trained deep neural network model, and key network performance indicators are extracted from it. The deep neural network model can discover complex and nonlinear patterns in a large amount of data, which helps to obtain more accurate network performance indicators; then, the support vector machine model is used to predict the network communication data of the next stage based on the network performance indicators. By predicting the network performance indicator data of the next stage, fault warning of network performance is achieved, which helps to improve the quality and efficiency of communication; and these predicted data are matched with the preset communication data. If the matching result shows that the communication data does not match, an early warning report is generated. This report will detail which performance indicators have deviated and the degree of deviation. Finally, based on the early warning report, the possible causes of the network failure are further analyzed and located, and the failure is located according to the early warning report, and adjustment suggestion information is generated. By predicting and preventing potential network problems, the stability and operational efficiency of the network are improved.
[0036] In one embodiment, if Figure 2As shown, in step S20, the communication data is analyzed using the trained deep neural network model to extract network performance indicators, specifically including: S21: Acquire historical network communication data, pre-process the historical network communication data, and obtain an initial training data set.
[0037] Specifically, collect past network communication data, such as transmission rate, network delay, packet loss rate and other network performance-related parameters. After collecting the historical network communication data, clean the raw data so that the data can be input into the model, such as removing noise and outliers in the historical network communication data, filling missing values, etc. This helps to improve the efficiency and accuracy of model training, so that network performance can be more effectively monitored and predicted.
[0038] S22: Use the initial training data set to train the initial model to obtain a trained deep neural network model.
[0039] Specifically, the initial form of the deep neural network model is trained with the prepared initial training data set. By inputting data into the model and adjusting the model's parameters, such as the weights and biases in the neural network, the error between the model's prediction results and the label values in the initial training data set is made as small as possible. Through training, the deep neural network model will continuously optimize and adjust its parameters, and the performance of the model will gradually improve.
[0040] S23: Use the trained deep neural network model to read and analyze the communication data to obtain network performance indicators.
[0041] Specifically, by using a trained deep neural network model to read and analyze the collected communication data, we can obtain network performance indicators, such as data transmission speed, network latency, data packet loss rate, etc. These network performance indicators can help us understand the operation status of the network and locate and solve possible problems.
[0042] In one embodiment, if Figure 3 As shown, in step S30, the network communication data of the next stage is predicted by using the support vector machine model according to the network performance index, which specifically includes: S31: Obtain the network performance indicator data of the previous stage and the corresponding network performance indicator data.
[0043] Specifically, collect network performance indicator data from the previous stage, such as the previous day, previous hour or previous minute. These indicators include network traffic, transmission speed, delay, and packet loss rate. It is also necessary to obtain the actual network performance data corresponding to these indicator data, that is, what really happened to the network at that stage. Associate the indicator data with the actual network performance data to more accurately understand the changes in network performance and provide useful input information for subsequent predictions or analysis.
[0044] S32: Training the initial data processing model according to the network performance indicator data of the previous stage and the corresponding network performance indicator data to obtain a support vector machine model.
[0045] Specifically, the network performance indicator data of the previous stage and the corresponding actual network performance result data are used as the training set to train the initial model. When the model is trained with this data set, the final result is a trained and optimized support vector machine model. By predicting future network performance indicators, possible network problems can be discovered in advance and corresponding measures can be taken to solve them.
[0046] S33: normalize the network performance indicators, and input the processed data into the support vector machine model for prediction to obtain the network communication data for the next stage.
[0047] Specifically, the various indicators of the data are unified to the same scale, which can eliminate the dimensional effects between different indicators and enable the model to view all features fairly. This processing is usually suitable for situations where the ranges of the data variables vary greatly. The normalized network performance indicators are input into the trained support vector machine model. The support vector machine model will make predictions based on the input data to obtain the network communication data label for the next stage, which helps to understand possible network problems in advance and prepare for them in advance.
[0048] In one embodiment, if Figure 4 As shown, in step S40, the next phase network communication data is matched with the preset communication data, and when the matching result is that the communication data does not match, an early warning report is generated, which specifically includes: S41: Compare and match the next phase network communication data with the preset communication data.
[0049] Specifically, the predicted network communication data of the next stage is compared and matched with the preset communication data. The purpose of comparison and matching is to confirm whether the actual performance of the network meets expectations or predictions. If the actual performance of the network is consistent with expectations, it means that the network is operating normally; if not, there may be some network problems that require further inspection and processing. Such a comparison and matching process is a very important part of network performance management and helps to promptly discover and deal with network problems.
[0050] S42: When the matching result shows that the communication data matches, a normal working message is generated.
[0051] Specifically, after comparing the expected and actual communication data, if the data matches, that is, the actual communication data is consistent with the expected, the system will generate a message indicating that the network is working normally as feedback on the network operation status.
[0052] S43: When the matching result shows that the communication data does not match, the warning mechanism is triggered to generate a warning report including the difference details and the communication impact.
[0053] Specifically, when there is a difference between the predicted network communication data and the actual standard network communication data, that is, the actual performance of the network does not match expectations, the system will activate the early warning mechanism, issue a warning signal or notification to attract the attention of the network administrator, and generate an early warning report detailing the difference between expectations and reality, and the impact that this difference may have on communications, which helps to quickly understand and solve the problem.
[0054] In one embodiment, if Figure 5 As shown, in step S50, the fault is located according to the early warning report, and adjustment suggestion information is generated, which specifically includes: S51: Analyze the difference data in the early warning report, obtain the cause of the data anomaly, and locate the existing network fault point.
[0055] Specifically, after receiving the early warning report, the process of analyzing the difference data in the report is to find out the cause of the data anomaly, so as to locate the possible fault points in the network. The early warning report will contain the difference data between the actual communication data and the expected communication data. A detailed analysis of these difference data can reveal the possible causes of the situation. When network data anomalies are found, the specific cause of the anomaly and the fault location need to be analyzed and located in detail in order to take effective remedial measures.
[0056] S52: Analyze network fault points and generate corresponding adjustment suggestion information.
[0057] Specifically, when the network fault point is located, further in-depth analysis is performed on the network fault point, and then some corresponding adjustment suggestions are output or proposed based on the analysis results to help solve the network fault and improve network performance.
[0058] In one embodiment, if Figure 6 As shown, in step S52, the network fault point is analyzed and corresponding adjustment suggestion information is generated, which specifically includes: S521: Analyze the network fault point according to the log analysis and traffic analysis to obtain the communication impact caused by the network fault point.
[0059] Specifically, the behavior of the network is understood by studying the logs generated during the operation of the network. Traffic analysis is to understand the behavior of the network by studying the amount and characteristics of data flows in the network. The specific location or link where the failure occurs in the network is studied to better understand where the problem lies, such as the specific extent of the impact, the scope of the impact, etc., and use this information to deduce the impact of network failures on communications.
[0060] S522: Generate corresponding adjustment strategies and suggestion information according to the cause of the data anomaly and the degree of impact of the communication impact.
[0061] Specifically, analyze the reasons behind the discovered data anomalies to determine what caused these anomalies. At the same time, evaluate the impact of these anomalies on network communications, such as how large a range of network services it affects and how long the impact lasts. Based on the understanding of the causes and impact of the anomalies, formulate corresponding adjustment strategies. These strategies may be to fix current problems, prevent similar problems in the future, improve network performance, etc. At the same time, these strategies are formed into recommendation information and provided to network administrators or other relevant personnel so that they can take action.
[0062] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0063] In one embodiment, a system for monitoring the quality of cross-border internal office communications is provided, and the system for monitoring the quality of cross-border internal office communications corresponds one-to-one to the method for monitoring the quality of cross-border internal office communications in the above embodiment. Figure 7 As shown, the transnational internal office communication quality monitoring system includes a communication acquisition module, a feature extraction module, a prediction module, an early warning module and an adjustment suggestion module. The detailed description of each functional module is as follows: The communication data acquisition module is used to acquire the communication data of the internal office network of a multinational enterprise; The feature extraction module is used to analyze the communication data using the trained deep neural network model and extract network performance indicators; The prediction module is used to predict the network communication data of the next stage based on the network performance indicators using the support vector machine model; An early warning module is used to match the next phase of network communication data with the preset communication data, and generate an early warning report when the matching result is that the communication data does not match; The adjustment suggestion module is used to locate the fault according to the early warning report and generate adjustment suggestion information.
[0064] Optionally, the feature extraction module includes: The initial training set acquisition submodule is used to acquire historical network communication data, pre-process the historical network communication data, and obtain an initial training data set; A deep neural network training submodule is used to train the initial model using the initial training data set to obtain a trained deep neural network model; The communication analysis submodule is used to read and analyze communication data using the trained deep neural network model to obtain network performance indicators.
[0065] Optionally, the prediction module includes: The performance indicator data acquisition submodule is used to acquire the network performance indicator data of the previous stage and the corresponding network performance indicator data; The training support vector machine model submodule is used to train the initial data processing model according to the network performance indicator data of the previous stage and the corresponding network performance indicator data to obtain a support vector machine model; The prediction performance index submodule is used to normalize the network performance index and input the processed data into the support vector machine model for prediction to obtain the network performance index for the next stage.
[0066] Optionally, the early warning module includes: The data matching submodule is used to compare and match the next phase network communication data with the preset communication data; A normal working submodule, used for generating a normal working message when the matching result shows that the communication data matches; The early warning report generation submodule is used to trigger the early warning mechanism when the matching result shows that the communication data does not match, and generate an early warning report containing the difference details and the communication impact.
[0067] Optionally, the adjustment suggestion module includes: The positioning submodule is used to analyze the difference data in the early warning report, obtain the cause of data anomaly, and locate the existing network fault point; The fault point analysis submodule is used to analyze network fault points and generate corresponding adjustment suggestion information.
[0068] Optionally, the fault point analysis submodule includes: Obtaining a communication impact data unit, which is used to analyze the network fault point based on log analysis and traffic analysis, and obtain the communication impact caused by the network fault point; The adjustment suggestion generating unit is used to generate corresponding adjustment strategies and suggestion information according to the cause of data anomaly and the degree of influence of communication impact.
[0069] For the specific definition of a transnational internal office communication quality monitoring system, please refer to the definition of a transnational internal office communication quality monitoring method mentioned above, which will not be repeated here. Each module in the above-mentioned transnational internal office communication quality monitoring system can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0070] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to obtain historical communication data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for monitoring the quality of cross-border internal office communications is implemented.
[0071] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Obtain communication data of internal office networks of multinational companies; Use the trained deep neural network model to analyze the communication data and extract network performance indicators; According to the network performance indicators, the support vector machine model is used to predict the network communication data for the next stage; Match the next phase network communication data with the preset communication data, and generate an early warning report when the matching result is that the communication data does not match; Based on the early warning report, the fault is located and adjustment suggestion information is generated.
[0072] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Obtain communication data of internal office networks of multinational companies; Use the trained deep neural network model to analyze the communication data and extract network performance indicators; According to the network performance indicators, the support vector machine model is used to predict the network communication data for the next stage; Match the next phase network communication data with the preset communication data, and generate an early warning report when the matching result is that the communication data does not match; Based on the early warning report, the fault is located and adjustment suggestion information is generated.
[0073] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0074] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.
[0075] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A method for monitoring the quality of cross-border internal office communications, characterized in that: The method for monitoring the quality of transnational internal office communications comprises: Obtain communication data of internal office networks of multinational companies; Analyzing the communication data using a trained deep neural network model to extract network performance indicators; According to the network performance indicators, the support vector machine model is used to predict the network communication data for the next stage; Matching the next-stage network communication data with preset communication data, and generating an early warning report when the matching result is that the communication data does not match; According to the early warning report, the fault is located and adjustment suggestion information is generated.
2. A method for monitoring the quality of cross-border internal office communications according to claim 1, characterized in that: The analyzing the communication data using the trained deep neural network model to extract network performance indicators includes: Acquire historical network communication data, and preprocess the historical network communication data to obtain an initial training data set; Using the initial training data set to train the initial model to obtain the trained deep neural network model; The trained deep neural network model is used to read and analyze the communication data to obtain the network performance index.
3. A method for monitoring the quality of cross-border internal office communications according to claim 2, characterized in that: The method of using a support vector machine model to predict the network communication data for the next stage according to the network performance indicator includes: Obtain the network performance indicator data of the previous stage and the corresponding network performance indicator data; Training the initial data processing model according to the network performance indicator data of the previous stage and the corresponding network performance indicator data to obtain the support vector machine model; The network performance index is normalized, and the processed data is input into the support vector machine model for prediction to obtain the network communication data of the next stage.
4. A method for monitoring the quality of transnational internal office communications according to claim 3, characterized in that: The step of matching the next-stage network communication data with preset communication data and generating an early warning report when the matching result is that the communication data does not match includes: Comparing and matching the next-stage network communication data with preset communication data; When the matching result indicates that the communication data matches, generating a normal working message; When the matching result shows that the communication data does not match, an early warning mechanism is triggered to generate an early warning report including difference details and communication impact.
5. A method for monitoring the quality of cross-border internal office communications according to claim 4, characterized in that: The locating of the fault according to the early warning report and generating adjustment suggestion information includes: Analyze the difference data in the early warning report to obtain the cause of data anomaly and locate the existing network fault point; Analyze the network fault point and generate the corresponding adjustment suggestion information.
6. A method for monitoring the quality of cross-border internal office communications according to claim 5, characterized in that: The analyzing the network fault point and generating the corresponding adjustment suggestion information comprises: Analyze the network fault point according to log analysis and traffic analysis to obtain the communication impact caused by the network fault point; According to the cause of the data anomaly and the degree of impact of the communication impact, corresponding adjustment strategies and suggestion information are generated.
7. A transnational internal office communication quality monitoring system, characterized in that: The transnational internal office communication quality monitoring system comprises: The communication data acquisition module is used to acquire the communication data of the internal office network of a multinational enterprise; A feature extraction module is used to analyze the communication data using a trained deep neural network model to extract network performance indicators; A prediction module, used to predict the network communication data of the next stage using a support vector machine model according to the network performance indicators; An early warning module is used to match the next-stage network communication data with preset communication data, and generate an early warning report when the matching result is that the communication data does not match; The adjustment suggestion module is used to locate the fault according to the early warning report and generate adjustment suggestion information.
8. A transnational internal office communication quality monitoring system according to claim 7, characterized in that: The feature extraction module comprises: The submodule for obtaining an initial training data set is used to obtain historical network communication data, preprocess the historical network communication data, and obtain an initial training data set; A deep neural network model training submodule is used to train the initial model using the initial training data set to obtain the trained deep neural network model; The reading and analysis submodule is used to use the trained deep neural network model to read and analyze the communication data to obtain the network performance index.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for monitoring the quality of cross-border internal office communications as claimed in any one of claims 1 to 6 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a method for monitoring the quality of cross-border intra-office communications as claimed in any one of claims 1 to 6 are implemented.
