Data monitoring and early warning platform in mobile office environment

Abstract

The invention provides a data monitoring and early warning platform in a mobile office environment, and relates to the technical field of data monitoring, and the platform comprises a data monitoring module which is used for monitoring and obtaining a plurality of pieces of office data currently operated by a user, and obtaining a plurality of pieces of data feature information and a plurality of operation types; the sensitivity analysis module is used for performing sensitivity analysis according to the multiple pieces of data feature information; the volatility analysis module is used for monitoring various network parameters and carrying out volatility analysis; and the risk early warning module is used for carrying out data risk analysis and calculation according to the data sensitivity parameters, the multiple pieces of network volatility information and the multiple operation types, and carrying out early warning according to the data risk parameters. According to the data transmission method and device, the technical problems of instability and risk of data transmission caused by influence on data security due to relatively large network condition fluctuation in the prior art can be solved, and the security and stability of data transmission in a mobile office scene are improved by dynamically monitoring network volatility and performing multi-dimensional comprehensive evaluation.

Description

Technical Field

[0001] The present application relates to the field of data monitoring technology, and in particular to a data monitoring and early warning platform in a mobile office environment. Background Art

[0002] With the rapid development of information technology, mobile office has become an important part of modern office. In the mobile office environment, users usually transmit data and collaborate remotely through public networks or mobile networks. However, the instability of the network environment, the security of data transmission, and the real-time requirements of operations have brought severe challenges to data management and information security. In mobile office, uploading and downloading sensitive data (such as financial statements, contract documents, and work reports) are core operations. Data transmission in public networks is extremely vulnerable to network security threats such as man-in-the-middle attacks and malicious traffic hijacking. Mobile office usually relies on public Wi-Fi and mobile 4G / 5G networks, which have performance fluctuations (such as decreased bandwidth and increased latency) and security risks (such as data theft). Existing data monitoring methods lack real-time monitoring of network parameters such as upload bandwidth, download bandwidth, and latency, especially in public network environments with large network fluctuations, and fail to quantify the impact of volatility on data transmission security.

[0003] In summary, the prior art has technical problems in that network fluctuations are often encountered in public networks or wireless network environments in mobile office scenarios, which affects data security and leads to unstable and risky data transmission. Summary of the invention

[0004] The purpose of this application is to provide a data monitoring and early warning platform in a mobile office environment to solve the technical problems in the prior art that network fluctuations are often encountered in public network or wireless network environments in mobile office scenarios, affecting data security and causing instability and risks in data transmission.

[0005] In view of the above problems, the present application provides a data monitoring and early warning platform in a mobile office environment, wherein the data monitoring and early warning platform in the mobile office environment includes: a data monitoring module, wherein the data monitoring module is used to monitor and obtain multiple office data currently operated by the user in the mobile office environment, and obtain multiple data feature information and multiple operation types of the multiple office data, wherein the operation type includes upload or download; a sensitivity analysis module, wherein the sensitivity analysis module is used to perform sensitivity analysis on the multiple office data according to the multiple data feature information, and obtain data sensitivity parameters; a volatility analysis module, wherein the volatility analysis module is used to monitor multiple network parameters of the network environment in the mobile office environment, obtain multiple network parameter sequences, perform volatility analysis respectively, and obtain multiple network volatility information, wherein the multiple network parameters include upload bandwidth, download bandwidth and delay; a risk warning module, wherein the risk warning module is used to perform data risk analysis and calculation according to the data sensitivity parameters, multiple network volatility information and multiple operation types, obtain data risk parameters, and issue warnings.

[0006] The technical solution provided in this application has at least the following technical effects or advantages:

[0007] By conducting sensitivity analysis on multiple characteristic information of office data, real-time monitoring of network parameters such as upload bandwidth, download bandwidth and latency, and analyzing their volatility, the stability and quality of the network environment are evaluated. By combining data sensitivity parameters, network volatility information and operation types, the risk of data operations is comprehensively evaluated and early warnings are issued accordingly to reduce the risk of data leakage or damage, thereby improving the security and stability of data transmission in mobile office scenarios.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0010] Figure 1This is a structural diagram of the data monitoring and early warning platform in the mobile office environment of this application;

[0011] Figure 2 This is a flow chart of risk warning in the data monitoring and early warning platform in the mobile office environment of this application.

[0012] Explanation of the accompanying drawings: data monitoring module 11, sensitivity analysis module 12, volatility analysis module 13, risk warning module 14. DETAILED DESCRIPTION

[0013] This application solves the technical problem in the prior art that network fluctuations often occur in public networks or wireless network environments in mobile office scenarios, which affects data security and leads to instability and risk of data transmission by providing a data monitoring and early warning platform in a mobile office environment. Through sensitivity analysis of multiple characteristic information of office data, real-time monitoring of network parameters such as upload bandwidth, download bandwidth and delay, and analysis of their volatility, the stability and quality of the network environment are evaluated, and the risk of data operation is comprehensively evaluated by combining data sensitivity parameters, network volatility information and operation types, and early warning is issued accordingly, reducing the risk of data leakage or damage, and improving the security and stability of data transmission in mobile office scenarios.

[0014] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0015] For examples, please see the attached Figure 1 The present application provides a data monitoring and early warning platform in a mobile office environment, wherein the data monitoring and early warning platform in the mobile office environment includes:

[0016] The data monitoring module 11 is used to monitor and obtain multiple office data currently operated by the user in a mobile office environment, and obtain multiple data feature information and multiple operation types of the multiple office data, wherein the operation type includes upload or download.

[0017] Specifically, a mobile office environment refers to a scenario where users use mobile devices (such as laptops, tablets, and mobile phones) to complete work tasks in non-traditional workplaces (such as home, cafes, and travel) through various network methods (such as Wi-Fi, mobile data, and VPN). For example, employees access the company's internal system through remote desktops and upload contract documents using public Wi-Fi in hotels. Use data monitoring tools (such as Windows API, cloud storage SDK, and file system monitoring tools) to track all user operations in a mobile office environment in real time, such as editing documents, sending emails, uploading or downloading files, etc. For example, use traffic analysis tools to capture upload or download data flows.

[0018] Extract the core features of each monitored data, including data path, data object and data subject. Data path refers to the storage location or access path of data, that is, the storage location in the local or remote system; data object is the customer or subject associated with the data determined by file content analysis, such as determining that the file belongs to customer A; data subject refers to important business indicators in the data (such as contract amount or project budget), such as the total amount of the associated project.

[0019] Get the specific operations that users are currently performing on multiple office data, including upload and download. Multiple operation types refer to the classification of user behaviors on data. Common operation types include upload (transferring local files to the server or cloud) and download (obtaining files from remote resources to the local). By collecting the office data characteristics and operation types of users in a mobile office environment, we can understand the data flow dynamics and user behavior patterns.

[0020] The sensitivity analysis module 12 is used to perform sensitivity analysis on the plurality of office data according to the plurality of data feature information to obtain data sensitivity parameters.

[0021] Specifically, multiple data feature information is multidimensional information describing the characteristics of office data, including data path, data object and data subject. Based on the data feature information, the sensitivity parameters of office data are calculated to quantify its potential risks. An office data sensitivity classifier is constructed based on historical data to classify office data into different sensitivity levels (such as low sensitivity, medium sensitivity and high sensitivity). Multiple data feature information is input into the office data sensitivity classifier, different weights are assigned to the path, customer and amount according to the importance of the feature, multiple features are integrated into a sensitivity parameter, the sensitivity of each data is calculated, and multiple sensitivity levels of multiple office data are obtained. The average of multiple sensitivity levels is calculated to obtain the data sensitivity parameter. The higher the total amount, the more important the customer, the more confidential the path, and the higher the sensitivity parameter. Sensitivity analysis is a process of evaluating and determining data sensitivity, which involves in-depth analysis of data feature information to identify possible risks and sensitivities in the data. Through quantitative analysis of data features and calculation of sensitivity parameters, not only accurate sensitivity assessment of office data is achieved, but also which data has higher sensitivity can be identified, so as to better protect these data.

[0022] The volatility analysis module 13 is used to monitor various network parameters of the network environment in the mobile office environment, obtain multiple network parameter sequences, perform volatility analysis on each sequence, and obtain multiple network volatility information, wherein the multiple network parameters include upload bandwidth, download bandwidth, and delay.

[0023] Specifically, the network environment in the mobile office environment is monitored through network monitoring tools, and various network parameters at different time points are collected, including upload bandwidth, download bandwidth and latency, to obtain multiple network parameter sequences, which include a collection of network parameter values ​​collected at multiple time points, reflecting the trend of network performance over time. Public networks are usually used in mobile office environments, that is, network environments accessed through public Wi-Fi or shared networks. Since they are not fully controlled by individuals or enterprises, they are vulnerable to external threats (such as network intrusions and data theft). When someone invades the network, the upload bandwidth, download bandwidth and latency of the public network will fluctuate.

[0024] By using statistical methods to analyze the variation of the network parameter sequence, volatility analysis is performed to evaluate the stability of network performance. The quantitative volatility analysis results are usually expressed as standard deviation or rate of change. The greater the volatility, the more unstable the network performance. Abnormal network volatility (such as drastic changes in upload bandwidth and large fluctuations in latency) may indicate network intrusion, data corruption or other security threats. In a public Wi-Fi environment, attackers may cause abnormal network performance through man-in-the-middle attacks or hijacking of traffic, which manifests as reduced bandwidth or increased latency.

[0025] The volatility analysis is performed on multiple network parameter sequences, that is, the upload bandwidth sequence, download bandwidth sequence and delay sequence are analyzed respectively. The instability of the network is identified by analyzing the fluctuations in the network parameter sequence, and the upload volatility information, download volatility information and delay volatility information are obtained as multiple network volatility information. Through the volatility analysis, the abnormal fluctuations of upload, download and delay can be accurately identified, and the judgment of whether there is a security threat can be assisted, which helps to reduce the risk of data leakage and network intrusion in the public network.

[0026] The risk warning module 14 is used to perform data risk analysis and calculation according to the data sensitivity parameters, multiple network volatility information and multiple operation types, obtain data risk parameters, and issue warnings.

[0027] Specifically, the data sensitivity parameter is calculated based on data characteristics (such as path confidentiality, customer importance, and amount sensitivity), and the higher the value, the more sensitive the data. Multiple network volatility information refers to the instability indicators that comprehensively reflect network performance, including upload volatility information, download volatility information, and delay volatility information.

[0028] According to multiple operation types, i.e., specific operation behaviors of users on data, such as uploading (such as transferring files to cloud storage) and downloading (such as obtaining data from a server), a preset delay weight is configured for the delay volatility information, and the upload weight and download weight of the upload volatility information and the download volatility information are configured accordingly. The preset delay weight, upload weight and download weight are used to perform weighted calculation on the upload volatility information, download volatility information and delay volatility information, and the upload volatility information, download volatility information and delay volatility information are multiplied by the corresponding weights, and all are added together to obtain the network volatility information.

[0029] Multiply the network volatility information and the data sensitivity parameter to obtain the data risk parameter. When the risk parameter exceeds the preset threshold, the alarm mechanism is triggered to issue a warning, reminding you to pay attention to potential risks or take security measures (such as pausing operations or switching networks). Otherwise, no warning is triggered. Data risk analysis calculation refers to calculating the risk level of data transmission in the current network environment by comprehensively considering data sensitivity parameters, network volatility information, and operation types. The data risk parameters are used to evaluate the transmission risk of data in a mobile office environment, so that corresponding security measures can be taken. Understanding the risk level of data can help formulate more effective security strategies, such as encrypting high-risk data or using more secure transmission channels.

[0030] Furthermore, the data monitoring module 11 in the data monitoring and early warning platform in the mobile office environment is also used for:

[0031] In a mobile office environment, multiple office data currently operated by a user are monitored and acquired; data paths, data objects and data targets of the multiple office data are acquired respectively, and combined into multiple data feature information; and multiple operation types currently operated on the multiple office data are acquired.

[0032] Specifically, the mobile office environment refers to the scenario where users use portable devices (such as laptops and smartphones) to perform office activities in non-fixed workplaces (such as at home, in a cafe, or on the go). Use data monitoring tools (such as Windows API, cloud storage SDK, and file system monitoring tools) to capture the user's current operations in real time from the user's mobile device or the application used, record the files or data being operated, and obtain multiple office data, including document content, email communication records, meeting participation, file transfer logs, etc. Extract the data path (file storage location), data object (data ownership or business relevance, such as the relationship between data and specific customers), and data target (content goal or core value, usually related to the financial or functional characteristics of the business) of multiple office data, and integrate the path, object, and target into a unified feature description to form data feature information.

[0033] Obtain the user's current operation behavior on multiple office data, that is, multiple operation types, including upload or download. The upload operation refers to the process of the user sending local data to the server or cloud storage. For example, the user uploads the edited document to the company server. The download operation refers to the process of the user obtaining data from the server or cloud storage to the local device. For example, the user downloads the latest market report from the company server. By real-time monitoring and detailed recording of user data operations in a mobile office environment, extracting key data feature information, and identifying operation types, basic data support is provided for subsequent data sensitivity analysis, network volatility monitoring, and data risk analysis, thereby ensuring data security and compliance.

[0034] Furthermore, the sensitivity analysis module 12 in the data monitoring and early warning platform in the mobile office environment is also used for:

[0035] Construct an office data sensitivity classifier; input the plurality of data feature information into the office data sensitivity classifier, classify and obtain a plurality of sensitivity levels of the plurality of office data; calculate the mean of the plurality of sensitivity levels to obtain a data sensitivity parameter.

[0036] Specifically, based on the office data processing records in the past period of time, data paths, data objects and data targets are extracted as sample data feature information sets, and the sample data feature information sets are preprocessed, including removing missing values, standardizing or normalizing data, encoding categorical variables, etc. The preprocessed data are divided into training data sets and test data sets. The training data sets are used to train the classifier, while the test data sets are used to evaluate the performance of the classifier. According to the characteristics of the data and the complexity of the problem, a suitable machine learning algorithm is selected, including decision trees, random forests, support vector machines (SVMs), neural networks, etc. The selected machine learning algorithm is trained using the training data set. During the training process, the algorithm learns how to predict the sensitivity level of the data based on the data feature information. Sample features and sensitivity level labels are input, and the relationship between features and sensitivity levels is fitted through supervised learning. The performance of the classifier is evaluated using the test data set, including accuracy, recall rate, F1 score, etc. According to the performance of the model on the test data set, the parameters of the algorithm are adjusted to improve the performance of the classifier. When the model meets the convergence requirements, the training is stopped and it is used as the office data sensitivity classifier.

[0037] Input multiple data feature information into the office data sensitivity classifier, predict the sensitivity level corresponding to the multiple office data currently being operated, and obtain multiple sensitivity levels, such as low sensitivity, medium sensitivity, and high sensitivity. For each piece of data, the classifier will make a judgment based on the distance of the feature vector at the classification boundary and output the sensitivity level. Convert the sensitivity level to a numerical value (for example, low = 1, medium = 2, high = 3), then calculate the average of the sensitivity levels of all office data, quantify the sensitivity risk of the overall data, and obtain the data sensitivity parameter, which represents the sensitivity risk of the entire data set and is used to quantify the overall security requirements. By constructing an office data sensitivity classifier and calculating the data sensitivity parameter, the sensitivity of office data can be quantified, potential sensitive data leakage risks can be identified and handled, and the security and compliance of data in a mobile office environment can be ensured.

[0038] Furthermore, the sensitivity analysis module 12 in the data monitoring and early warning platform in the mobile office environment is also used for:

[0039] According to the office data processing records in the historical time, a set of sample data feature information is collected, and the sample sensitivity level is labeled for each sample data feature information to obtain a sample sensitivity level set; a random forest is used to construct an office data sensitive classifier; the sample data feature information set and the sample sensitivity level set are divided to obtain a training set and a test set; the training set is used to perform supervised training on the office data sensitive classifier, and the test set is used to perform testing to determine whether it converges; if so, the training is completed and the office data sensitive classifier is obtained, if not, supervised training is continued until the office data sensitive classifier converges.

[0040] Specifically, the office data processing records in the historical time include the log information of the user's operation of office data in the past historical time, including the records of the access, editing, uploading, downloading and other behaviors of files or data. The sample data feature information set is extracted from the historical office data processing records, including data path, data object and data target, etc. Based on the feature information of office data and actual business needs, the labeling standards of sensitivity levels are defined. For example, experts or rules assign sensitivity level labels to each sample (such as low sensitivity, medium sensitivity, and high sensitivity). According to the labeling standards, the sensitivity level of each sample data feature information is labeled to form a sample sensitivity level set, that is, the result set obtained after labeling all sample data feature information sets, which includes the sensitivity level of each sample.

[0041] Combine the sample data feature information set and the sample sensitivity level set into supervised training data, and preprocess the data, including data cleaning (removing invalid data) and data normalization (eliminating the dimensions between data). The numerical vector representation of paths, objects, and targets is used as input features, and the sample sensitivity level is used as the corresponding output label. Select a suitable model (such as logistic regression, random forest, or deep learning model) for training, build an office data sensitivity classifier, and predict the sensitivity level of the data based on the data feature information. Select a suitable model type based on the amount of data and task complexity, such as logistic regression, random forest, support vector machine (SVM), deep neural network (such as multi-layer perceptron MLP), etc.

[0042] Taking random forest as an example, by constructing multiple decision trees and combining the prediction results of each tree, higher classification accuracy and robustness can be achieved. Random forest has good performance in handling classification problems and can handle a large number of features. Quantify the sample data feature information set into numerical form to form an input feature vector, such as mapping the path to the interval of 0-1 through keyword scoring, assigning values ​​according to customer type, etc. Divide the data set into a training set and a test set (such as 70% training set and 30% test set), and stratified sampling is usually used to ensure that the sensitivity level is evenly distributed in the two sets. Set the key parameters of random forest to initialize the model, including the number of decision trees, the maximum depth of a single tree, and the weights of different categories. Input the training set into the random forest model for training, and the model will learn how to predict the sensitivity level of the data based on the features. Evaluate the model performance through the test set, compare the predicted value with the true value, calculate the loss function (such as mean square error), and update the model parameters accordingly. Set the convergence conditions of the model, such as the validation set loss change is less than 0.01 for 5 consecutive rounds or the training set accuracy reaches 95%. Iterate the training of the office data sensitivity classifier until the convergence condition is met, then stop the training; otherwise, continue to adjust the parameters or optimize the data processing process until the office data sensitivity classifier reaches the convergence condition. Apply the trained model to achieve automatic sensitivity level classification. By using historical data records to build and train the office data sensitivity classifier, learn how to judge the sensitivity of data based on data feature information, and improve the ability to predict the sensitivity of unknown data.

[0043] Furthermore, the volatility analysis module 13 in the data monitoring and early warning platform in the mobile office environment is also used for:

[0044] Monitor the upload bandwidth, download bandwidth and delay of the network environment in the mobile office environment at multiple timestamps to obtain an upload bandwidth sequence, a download bandwidth sequence and a delay sequence as multiple network parameter sequences; perform volatility analysis on the upload bandwidth sequence, the download bandwidth sequence and the delay sequence respectively to obtain upload volatility information, download volatility information and delay volatility information as multiple network volatility information.

[0045] Specifically, the upload bandwidth, download bandwidth and latency of the network environment in the mobile office environment at different times are monitored. Upload bandwidth refers to the maximum rate at which data is transmitted from the local device to the network per unit time, measured in Mbps (megabits per second); download bandwidth refers to the maximum rate at which data is received from the network to the local device per unit time, measured in Mbps; latency refers to the time required for data to reach the target device from the source device in the network, measured in milliseconds (ms). Multiple timestamps are recorded at different time points. By recording network parameters at multiple timestamps, the stability and performance of the network are analyzed. The upload bandwidth, download bandwidth and latency at multiple timestamps are sorted by time to obtain the upload bandwidth sequence, download bandwidth sequence and latency sequence, which are used as multiple network parameter sequences to analyze trends and patterns in network performance.

[0046] Volatility analysis is a method for evaluating the stability of network performance. It identifies network instability by analyzing the fluctuations in the network parameter sequence, usually including calculating the range of changes in parameter values, standard deviations, or other statistical indicators. A high volatility of upload bandwidth indicates that the upload rate fluctuates frequently, which may affect the stability of large file transmission. Volatility analysis is performed on each data sequence separately. Any two upload bandwidths in the upload bandwidth sequence are randomly selected multiple times, and the deviation ratio of the two upload bandwidths is calculated to obtain multiple upload bandwidth volatility information. The mean of multiple upload bandwidth volatility information is calculated to obtain upload volatility information. Similarly, the download volatility information and delay volatility information of the download bandwidth sequence and delay sequence are calculated as multiple network volatility information. By calculating the upload volatility information, download volatility information, and delay volatility information, the stability of the network is comprehensively evaluated. High volatility indicates that there is a high probability of network security problems.

[0047] Furthermore, the volatility analysis module 13 in the data monitoring and early warning platform in the mobile office environment is also used for:

[0048] Randomly extract two upload bandwidths from the upload bandwidth sequence, and calculate the deviation ratio of the two upload bandwidths as the first upload bandwidth volatility information; continue to randomly extract multiple groups of upload bandwidths, calculate to obtain multiple upload bandwidth volatility information, and calculate the average to obtain the upload volatility information; continue to calculate according to the download bandwidth sequence and delay sequence to obtain the download volatility information and delay volatility information.

[0049] Specifically, each timestamp in the upload bandwidth sequence corresponds to an upload bandwidth value, which reflects the network's ability to upload data at different times. Randomly selecting two upload bandwidths in the upload bandwidth sequence helps avoid deviations and more comprehensively evaluate the volatility of the network. Calculate the deviation ratio of the two upload bandwidths, that is, the ratio of the deviation between the two bandwidth values ​​relative to their mean, to obtain the first upload bandwidth volatility information. Similarly, repeat the process of randomly selecting two upload bandwidth values ​​multiple times to obtain multiple groups of upload bandwidth values. For each group of randomly selected upload bandwidth values, calculate the deviation ratio to obtain multiple upload bandwidth volatility information. Calculate the average of multiple upload bandwidth volatility information, add all calculated upload bandwidth volatility information values, and then divide by the total number of volatility information values ​​to obtain the upload volatility information, which represents the overall upload bandwidth volatility.

[0050] Similarly, the above steps are performed on the download bandwidth sequence and delay sequence. By calculating the deviation ratio of multiple randomly selected bandwidth value pairs and the deviation ratio of multiple randomly selected delay value pairs, the download volatility information and delay volatility information are obtained. Through random sampling and mean calculation, the overall volatility characteristics of upload, download and delay are accurately quantified to avoid the influence of instantaneous outliers on the results. The volatility information of upload, download bandwidth and delay evaluates the overall stability of the network.

[0051] Further, as attached Figure 2 As shown, the risk warning module 14 in the data monitoring and warning platform in the mobile office environment is also used for:

[0052] According to the multiple operation types, the upload weight and download weight of the upload volatility information and the download volatility information in the multiple network volatility information are configured, wherein the delay volatility information is configured with a preset delay weight; the preset delay weight, upload weight and download weight are used to perform weighted calculation on the upload volatility information, download volatility information and delay volatility information to obtain network volatility information; the network volatility information is multiplied by the data sensitivity parameter to obtain a data risk parameter; it is determined whether the data risk parameter is greater than or equal to a data risk parameter threshold, and if so, an early warning is issued, and if not, no early warning is issued.

[0053] Specifically, according to multiple operation types of multiple office data, that is, the specific operation behaviors of users on data in the office environment, including uploading (such as transferring files to cloud storage) and downloading (such as obtaining files from a remote server). The delay volatility information is configured with a preset delay weight, which is a predefined setting used to indicate the importance of delay volatility information in the overall performance evaluation. According to the preset delay weight, the upload weight and download weight of the upload volatility information and the download volatility information are calculated. The weights dynamically calculated according to the preset delay weights based on the upload and download ratios of the operation types are used to configure the impact of the upload and download volatility information in the overall network volatility. The upload, download and delay volatility information are comprehensively considered, and the upload volatility information, download volatility information and delay volatility information are multiplied by the corresponding weights respectively, and then summed to obtain a comprehensive network volatility information value.

[0054] Multiply the network volatility information by the data sensitivity parameter to obtain the data risk parameter, which comprehensively reflects the impact of the network environment and data sensitivity on operational risks. The data risk parameter threshold is the benchmark value for judging data risk. If it exceeds this value, an early warning will be triggered. By comparing the data risk parameter and the data risk parameter threshold, it is decided whether to trigger an early warning. If the data risk parameter is greater than or equal to the threshold, an early warning is triggered, indicating that there may be a security risk; if the data risk parameter is less than the threshold, the risk is considered to be within an acceptable range and no early warning is triggered. By adjusting the weights and thresholds, the early warning conditions can be flexibly set according to different business needs and network environments, and combined with network volatility and data sensitivity, data risks can be more comprehensively assessed, making early warnings more accurate and reducing the possibility of false positives and missed reports.

[0055] Furthermore, the risk warning module 14 in the data monitoring and warning platform in the mobile office environment is also used for:

[0056] Subtract the preset delay weight from 1 to obtain the weight to be configured; obtain the proportion of upload operation types and download operation types in the multiple operation types, and multiply them by the weight to be configured respectively to obtain the upload weight and download weight of the upload volatility information and download volatility information.

[0057] Specifically, a delay weight is predefined to indicate the importance or degree of influence of delay in the overall network performance evaluation. The preset delay weight is usually a value between 0 and 1, where 0 indicates that the delay has no effect on the overall performance, and 1 indicates that the delay has a complete impact on the overall performance. The weight to be configured is obtained by subtracting the preset delay weight from 1, which is used for the weight allocation of upload and download volatility information, indicating the relative importance of other network parameters (such as upload bandwidth and download bandwidth) in the overall performance evaluation in addition to delay.

[0058] Get the proportion of upload operation types and download operation types in multiple operation types of multiple office data, that is, the proportion of upload operations and download operations in all operations. For example, in a certain period of time, the user uploaded 4 files and downloaded 6 files, then the upload proportion is 0.4, and the download proportion is 0.6. Count the number of user upload and download operations in a period of time, and calculate their respective proportions. The operation proportion will be used to allocate the weight of upload and download volatility information.

[0059] The proportion of upload operation types is multiplied by the weight to be configured to obtain the upload weight of the upload volatility information, and the proportion of download operation types is multiplied by the weight to be configured to obtain the download volatility information and download weight. For example, if the preset delay weight is 0.2, the weight to be configured is 0.8. If the upload proportion is 0.4 and the download proportion is 0.6, the upload weight is 0.32 and the download weight is 0.48. By dynamically calculating the upload and download weights, the impact of different operation types in the network volatility analysis can be flexibly adjusted to make the evaluation more in line with the actual network usage scenario. Through the combination of operation proportion and delay weight, the dynamic allocation of network volatility analysis weights is realized, which improves the adaptability of the model. Different operation types (upload or download) have different sensitivities to network stability, and the weight configuration method can accurately reflect user behavior characteristics.

[0060] In summary, the data monitoring and early warning platform in the mobile office environment provided by this application has the following technical effects:

[0061] By conducting sensitivity analysis on multiple characteristic information of office data, real-time monitoring of network parameters such as upload bandwidth, download bandwidth and latency, and analyzing their volatility, the stability and quality of the network environment are evaluated. By combining data sensitivity parameters, network volatility information and operation types, the risk of data operations is comprehensively evaluated and early warnings are issued accordingly to reduce the risk of data leakage or damage, thereby improving the security and stability of data transmission in mobile office scenarios.

[0062] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0063] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. Data monitoring and early warning platform in mobile office environment, characterized by: include: A data monitoring module, the data monitoring module is used to monitor and obtain multiple office data currently operated by the user in a mobile office environment, and obtain multiple data feature information and multiple operation types of the multiple office data, wherein the operation type includes upload or download; A sensitivity analysis module, wherein the sensitivity analysis module is used to perform sensitivity analysis on the plurality of office data according to the plurality of data feature information to obtain data sensitivity parameters; A volatility analysis module, the volatility analysis module is used to monitor multiple network parameters of the network environment in the mobile office environment, obtain multiple network parameter sequences, perform volatility analysis on each sequence, and obtain multiple network volatility information, wherein the multiple network parameters include upload bandwidth, download bandwidth, and delay; A risk warning module, wherein the risk warning module is used to perform data risk analysis and calculation according to the data sensitivity parameters, multiple network volatility information and multiple operation types, obtain data risk parameters, and issue warnings; Wherein, the volatility analysis module further includes: Monitor the upload bandwidth, download bandwidth and delay of the network environment in the mobile office environment at multiple time stamps, and obtain an upload bandwidth sequence, a download bandwidth sequence and a delay sequence as multiple network parameter sequences; Performing volatility analysis on the upload bandwidth sequence, the download bandwidth sequence, and the delay sequence respectively to obtain upload volatility information, download volatility information, and delay volatility information as multiple network volatility information; Randomly extracting two upload bandwidths from the upload bandwidth sequence, and calculating a deviation ratio between the two upload bandwidths as first upload bandwidth volatility information, wherein the deviation ratio is obtained by calculating a ratio of a deviation value between the two upload bandwidths and a mean value between the two upload bandwidths; Continue to randomly extract multiple groups of upload bandwidths, calculate and obtain multiple upload bandwidth volatility information, and calculate the average to obtain the upload volatility information; The download volatility information and the delay volatility information are continuously calculated based on the download bandwidth sequence and the delay sequence.

2. The data monitoring and early warning platform in a mobile office environment according to claim 1 is characterized in that: In a mobile office environment, multiple office data currently operated by a user are monitored and acquired, and multiple data feature information and multiple operation types of the multiple office data are acquired, including: In a mobile office environment, monitor and obtain multiple office data currently operated by the user; Respectively obtain data paths, data objects and data targets of the plurality of office data, and combine them into a plurality of data feature information; A plurality of operation types currently operating on the plurality of office data are obtained.

3. The data monitoring and early warning platform in a mobile office environment according to claim 1 is characterized in that: According to the plurality of data feature information, sensitivity analysis of the plurality of office data is performed to obtain data sensitivity parameters, including: Build a sensitive classifier for office data; Inputting the plurality of data feature information into the office data sensitivity classifier, and classifying and obtaining a plurality of sensitivity levels of the plurality of office data; Calculating the average of the multiple sensitivity levels to obtain a data sensitivity parameter; Among them, building an office data sensitive classifier includes: According to the office data processing records in the historical period, a set of sample data feature information is collected, and each sample data feature information is labeled with a sample sensitivity level to obtain a set of sample sensitivity levels; Use random forest to build office data sensitive classifier; Dividing the sample data feature information set and the sample sensitivity level set to obtain a training set and a test set; Using the training set to perform supervised training on the office data sensitive classifier, and using the test set to perform testing to determine whether convergence occurs; If yes, the training is completed and the office data sensitive classifier is obtained. If no, the supervised training is continued until the office data sensitive classifier converges.

4. The data monitoring and early warning platform in a mobile office environment according to claim 1 is characterized in that: According to the data sensitivity parameters, multiple network volatility information and multiple operation types, data risk analysis and calculation are performed to obtain data risk parameters and issue early warnings, including: According to the multiple operation types, configure the upload weight and download weight of the upload volatility information and the download volatility information in the multiple network volatility information, wherein the delay volatility information is configured with a preset delay weight; The preset delay weight, upload weight and download weight are used to perform weighted calculation on the upload volatility information, download volatility information and delay volatility information to obtain network volatility information; Multiplying the network volatility information by the data sensitivity parameter to obtain a data risk parameter; Determine whether the data risk parameter is greater than or equal to the data risk parameter threshold, if so, issue a warning, if not, do not issue a warning.

5. The data monitoring and early warning platform in a mobile office environment according to claim 4 is characterized in that: Configuring, according to the multiple operation types, an upload weight and a download weight of the upload volatility information and the download volatility information in the multiple network volatility information, including: Subtract the preset delay weight from 1 to obtain a weight to be configured; The proportions of the upload operation type and the download operation type in the multiple operation types are obtained, and the proportions are multiplied by the weights to be configured respectively to obtain the upload weight and the download weight of the upload volatility information and the download volatility information.

Images