Host online environment monitoring method and device

Abstract

The invention discloses a host online environment monitoring method and device, and relates to the technical field of intelligent operation and maintenance, big data, finance or other technologies, and the method comprises the steps: executing a pre-deployed timing operation, and obtaining host online environment data; performing data preprocessing on the host online environment data according to a pre-trained data preprocessing model; generating a data table according to data categories according to the host online environment data after data preprocessing; inputting the host online environment data in the data table into the judgment model in sequence, and outputting a judgment result; according to the method, the complexity of host online environment monitoring can be simplified, the timeliness of monitoring and problem processing can be improved, the labor cost and the time cost of host online environment operation and maintenance can be saved, and the potential operation risk can be effectively reduced.

Description

Technical Field

[0001] The present invention relates to the fields of intelligent operation and maintenance, big data, finance or other technical fields, and in particular to a host online environment monitoring method and device. Background Art

[0002] This section is intended to provide a background or context for embodiments of the present invention. No description herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] Online business is of vital importance as the cornerstone of the normal operation of banking business. Therefore, it is required that the monitoring of the operating status of the host online environment and the handling of problems should be timely and effective. Since the bank's online business involves many types of channels, a large number of online address spaces that provide transaction loads at the same time, and a large number of bank test online environments, there are still a lot of repetitive and manual operations in the daily operation and maintenance monitoring and problem handling of the host online environment, which consumes a lot of energy and physical strength of the operation and maintenance personnel, easily leads to operational risks, and brings major hidden problems. In addition, the data volume is large, the types of channels involved are many, and the views provided are often not unified. The operation and maintenance personnel need to log in to the host environment one by one to check the online status information, which reduces the timeliness of monitoring and problem handling. The inspection operations of some inspection items are cumbersome, time-consuming, and prone to errors. Summary of the invention

[0004] The embodiment of the present invention provides a host online environment monitoring method, which is used to simplify the complexity of host online environment monitoring, improve the timeliness of monitoring and problem handling, save the manpower cost and time cost of host online environment operation and maintenance, and effectively reduce potential operation risks. The method includes:

[0005] Execute pre-deployed scheduled jobs to obtain host online environment data;

[0006] The host online environment data is preprocessed according to a pre-trained data preprocessing model; the data preprocessing model is obtained by training a naive Bayes model using a machine learning algorithm using historical host online environment data and corresponding preprocessing results;

[0007] Generate a data table according to the data category based on the host online environment data after data preprocessing;

[0008] Input the host online environment data in the data table into the judgment model in sequence, and output the judgment result; the judgment model is obtained by training the naive Bayes model through a machine learning algorithm using the historical host online environment data and the corresponding labels representing whether the data is abnormal; the judgment result represents whether the host online environment data is abnormal;

[0009] Display the data table and judgment results.

[0010] The embodiment of the present invention further provides a host online environment monitoring device, which is used to simplify the complexity of host online environment monitoring, improve the timeliness of monitoring and problem handling, save the manpower cost and time cost of host online environment operation and maintenance, and effectively reduce potential operation risks. The device includes:

[0011] The acquisition module is used to execute pre-deployed scheduled jobs and obtain host online environment data;

[0012] A preprocessing module is used to perform data preprocessing on the host online environment data according to a pre-trained data preprocessing model; the data preprocessing model is obtained by training a naive Bayes model through a machine learning algorithm using historical host online environment data and corresponding preprocessing results;

[0013] A data table generation module is used to generate a data table according to the data category based on the host online environment data after data preprocessing;

[0014] A judgment module is used to input the host online environment data in the data table into the judgment model in sequence and output a judgment result; the judgment model is obtained by training the naive Bayes model through a machine learning algorithm using the historical host online environment data and the corresponding labels representing whether the data is abnormal; the judgment result represents whether the host online environment data is abnormal;

[0015] The display module is used to display the data table and the judgment results.

[0016] Compared with the host online environment monitoring technical solution in the prior art, the embodiment of the present invention obtains host online environment data by executing a pre-deployed scheduled job; performs data preprocessing on the host online environment data according to a pre-trained data preprocessing model; the data preprocessing model is obtained by training a naive Bayesian model through a machine learning algorithm using historical host online environment data and corresponding preprocessing results; a data table is generated according to data categories based on the host online environment data after data preprocessing; the host online environment data in the data table is input into the judgment model in sequence, and a judgment result is output; the judgment model is obtained by training a naive Bayesian model through a machine learning algorithm using historical host online environment data and corresponding labels representing whether the data is abnormal; the judgment result represents whether the host online environment data is abnormal; displaying the data table and the judgment result can simplify the complexity of host online environment monitoring, improve the timeliness of monitoring and problem handling, save the manpower cost and time cost of host online environment operation and maintenance, and effectively reduce potential operational risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0018] Figure 1 is a flow chart of a host online environment monitoring method according to an embodiment of the present invention;

[0019] Figure 2 It is a flowchart of a specific example of the host online environment monitoring method in an embodiment of the present invention;

[0020] Figure 3 It is a flowchart of a specific example of the host online environment monitoring method in an embodiment of the present invention;

[0021] Figure 4 Schematic diagram of a host online environment monitoring device according to an embodiment of the present invention;

[0022] Figure 5 Schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0024] The embodiments of the present invention relate to the field of large-scale, centralized, multi-channel large-scale mainframe online environment monitoring and maintenance, and specifically relate to a mainframe online environment operation and maintenance method and technology based on an API (Application Programming Interface) interface and FTP (File Transfer Protocol), and introducing intelligent data collection and big data model technology to construct a unified view of the host online environment status information, and realize intelligent diagnosis and processing of abnormal status.

[0025] The embodiments of the present invention overcome the shortcomings of the prior art and provide an intelligent host online environment monitoring method and device. The intelligent collection of system operation and maintenance indicator data is realized by calling the API interface regularly on the host side, and a transmission channel for the collected data is established based on the FTP file transfer protocol, so that the platform side can display the host online environment status information in the form of a unified view, and introduce big data model technology and algorithms to realize intelligent diagnosis and processing of online abnormal problem information, thereby improving the efficiency of host online environment operation and maintenance and problem handling, greatly reducing the cost of manual operation and maintenance, and potential operational risks.

[0026] The embodiment of the present invention provides a host online environment monitoring method. Figure 1 FIG. 1 is a flow chart of a host online environment monitoring method according to an embodiment of the present invention. Figure 1 As shown, the host online environment monitoring method may include:

[0027] Step 101, executing a pre-deployed scheduled job to obtain host online environment data;

[0028] Step 102, performing data preprocessing on the host online environment data according to a pre-trained data preprocessing model; the data preprocessing model is obtained by training a naive Bayes model using historical host online environment data and corresponding preprocessing results through a machine learning algorithm;

[0029] Step 103, generating a data table according to the host online environment data after data preprocessing according to the data category;

[0030] Step 104, input the host online environment data in the data table into the judgment model in sequence, and output the judgment result; the judgment model is obtained by training the naive Bayes model through a machine learning algorithm using the historical host online environment data and the corresponding label representing whether the data is abnormal; the judgment result represents whether the host online environment data is abnormal;

[0031] Step 105: display the data table and the judgment result.

[0032] Figure 2 FIG. 1 is a flowchart of a specific example of a host online environment monitoring method according to an embodiment of the present invention. Figure 2As shown, in the embodiment of the present invention, the host online environment monitoring method can be based on the host side and the platform side. The host side is used to run the banking business online, and the platform side is an online monitoring platform, which is used to provide data processing services for the host online environment monitoring method. The host side can include a business system, a pre-deployed scheduled job, an API interface or an intelligent data acquisition module, a database, etc. The scheduled job can call the API interface or the intelligent data acquisition module to enable them to collect host data according to demand, and the database is used to store data. The platform side may include a database, an intelligent analysis and processing module, a unified view, etc., which are respectively used to obtain and store data from the host-side database through the FTP data transmission protocol, analyze and process the data, and provide a unified view for users to view.

[0033] In order to simplify the complexity of host online environment monitoring and improve the timeliness of monitoring and problem handling, in one embodiment, before executing the pre-deployed scheduled job and obtaining the host online environment data, it can also include: receiving an instruction to deploy a scheduled job on the host; the scheduled job is used to regularly obtain the host online environment data; and deploying the scheduled job on the host according to the instruction. For example, the scheduled job can be a scheduled trigger to call the online API interface, and the API interface has a module with an intelligent data collection function embedded in it to collect all the current host online environment data.

[0034] In one embodiment, the host online environment data may include one or any combination of host online workload status data, routing status data, communication connection status data, database connection status data, peripheral gateway connection status data, and online address space data. For example, the specific collected information content may involve host online workload status, routing status, communication connection status, database connection status, peripheral gateway connection status, number of online address spaces, etc.

[0035] In one embodiment, the principles and steps for determining the index items of the specific host online environment data may be as follows:

[0036] 1) Prioritize the normal status of the entire WORKLOAD (workload) of the host environment to avoid large-scale business transaction abnormalities. Therefore, the API interface first obtains the WORKLOAD status value through online management. Under normal circumstances, the normal status value is ACTIVE;

[0037] 2) On the basis of the normal status of the entire WORKLOAD (workload), further ensure the normal status of the routing of the transaction sent to the host online, avoid abnormal transaction requests from the terminal, and abnormal problems in routing to the corresponding channel online processing. Therefore, the API interface again obtains the status value and number information of TRAGET REGION (target routing connection) and ROUTING REGION (routing connection) through the management connection. Under normal circumstances, the normal status value is ACTIVE, and the normal number value is formulated in combination with actual business operation and maintenance needs and configured in the verification file;

[0038] 3) In addition, the communication connection status between lines will also affect the transaction routing status, so the API interface also needs to obtain the communication status information between each transaction processing line to ensure that the entire business transaction routing link is normal. Under normal circumstances, the normal status value is ACTIVE;

[0039] 4) During the business transaction processing, it is necessary to interact with the database to process related data. Therefore, the API interface needs to obtain the number of connections and status information with the database to ensure the normal data processing process. Under normal circumstances, the normal value of the status is CONECTED, and the normal value of the number is formulated in combination with the actual business operation and maintenance requirements and configured in the verification file;

[0040] 5) During the business testing process, in order to meet the specific business volume and transaction load, a sufficient number of connections need to be started under normal circumstances to support its business load. Therefore, the API interface must also obtain accurate information on the number of online startups in real time to ensure that the expected business load requirements are met. The normal value of the number is formulated in combination with the actual business operation and maintenance needs and configured in the verification file.

[0041] In summary, the index items included in the host online environment data can fully reflect the host online environment status information, so they are monitored and inspected as key operation and maintenance index items.

[0042] Since there is a large amount of invalid junk information in the fully collected information that cannot accurately display the actual status of the system, it is necessary to further filter and classify the data through pre-deployed data collection rules to generate effective data information that can truly reflect the current system status for analytical decision-making. In one embodiment, the host online environment monitoring method can also include: obtaining historical host online environment data and pre-processed historical host online environment data; according to the historical host online environment data and the processed historical host online environment data, training the naive Bayes model through a machine learning algorithm to generate a data preprocessing model. The data preprocessing model can be generated through machine learning training based on the naive Bayes algorithm model, and the specific algorithm principle will not be repeated here.

[0043] In order to improve the accuracy of abnormal judgment of host online environment data, in one embodiment, the host online environment monitoring method may also include: obtaining historical host online environment data; adding labels to the historical host online environment data; the labels characterize the abnormal conditions of the historical host online environment data; and training the naive Bayes model through a machine learning algorithm based on the historical host online environment data and the added labels to generate a judgment model.

[0044] In step 103, after generating a data table according to the data category based on the host online environment data after data preprocessing, the generated status information data can be inserted into the data table on the host side. The data in the table can be used for iterative development of data acquisition algorithms and data preprocessing models to further improve the intelligence level of data acquisition and processing.

[0045] The data stored in the database on the host side can also be summarized in the data table on the platform side through the transmission channel established by the FTP file transfer protocol. The data in the data table on the platform side can be used to display the operation and maintenance indicator item categories of information collection in the front-end view of the platform. At the same time, the data is also used as the input of the intelligent analysis and processing module. The module uses the big data model to make a decision analysis on each input data status instance information according to the judgment model determined by machine learning. Specifically, the host online environment data is traversed and matched through the judgment model to judge the normality of the host online status. The judgment model can be generated through machine learning training based on the naive Bayes algorithm model, and the specific algorithm principle will not be repeated here.

[0046] In order to further improve the intelligence level and accuracy of data collection and processing, in one embodiment, after preprocessing the host online environment data according to the pre-trained data preprocessing model, it also includes: using the preprocessed host online environment data to update the historical host online environment data; using the updated historical host online environment data to train the data preprocessing model to generate an updated data preprocessing model. Since the accuracy of the model generated by the machine learning algorithm depends on the data in the training set and the test set, the training set and the test set can be updated using the preprocessed host online environment data, and the updated data can be used for training to ensure the accuracy of the model.

[0047] In order to improve the timeliness of problem handling, in one embodiment, the host online environment monitoring method may also include: using a pre-configured data exception handling script to process the host online environment data with an abnormal judgment result, and generate an exception handling result; the data exception handling script includes multiple sub-scripts corresponding to the category of the host online environment data; displaying the exception handling result; receiving and storing feedback information input by the user according to the exception handling result. Multiple sub-scripts corresponding to the category of the host online environment data can be pre-configured, and the sub-scripts are used to automatically process abnormal data of different categories, improve the level of automation, and save the labor cost of problem handling. For abnormal data, corresponding intelligent processing operations are taken according to the dimensions of the operation and maintenance indicator items of information collection, and the processing results are synchronously output to the platform front-end view. The user can perform intervention processing again according to the online status information and related abnormal problem processing results displayed on the view page, feedback the processing results on the front-end interface, and then upload the feedback processing information to the host side database synchronously through the FTP transmission protocol, which is convenient for subsequent backtracking and further iterative development of the data collection rules and the normal standard rule algorithms of the operation and maintenance indicators.

[0048] Figure 3 FIG. 1 is a flowchart of a specific example of a host online environment monitoring method according to an embodiment of the present invention. Figure 3 As shown, the process of the host online environment monitoring method can be as follows:

[0049] Triggering automated scheduled jobs can be triggered by users through the interactive platform or can be continuously triggered. The API interface is called according to the scheduled job. The API interface uses the embedded collection module to intelligently collect the host online environment data, filter and classify the data, and can use the pre-trained data preprocessing model for filtering. The processed information is written to the database on the host side. It can be determined whether the FTP transmission protocol has been established. If not, an FTP transmission protocol is established to form a channel between the host-side database and the platform-side database, and the host-side data is written to the platform-side database. The data in the platform-side database is displayed in a visual manner on the one hand, and abnormal problems are identified and intelligently processed on the other hand, and the processing results are also displayed.

[0050] In summary, compared with the host online environment monitoring technical solution in the prior art, the embodiment of the present invention obtains host online environment data by executing a pre-deployed scheduled job; performs data preprocessing on the host online environment data according to a pre-trained data preprocessing model; the data preprocessing model is obtained by training a naive Bayes model through a machine learning algorithm using historical host online environment data and corresponding preprocessing results; a data table is generated according to data categories based on the host online environment data after data preprocessing; the host online environment data in the data table is input into the judgment model in sequence, and a judgment result is output; the judgment model is obtained by training a naive Bayes model through a machine learning algorithm using historical host online environment data and corresponding labels representing whether the data is abnormal; the judgment result represents whether the host online environment data is abnormal; displaying the data table and the judgment result can simplify the complexity of host online environment monitoring, improve the timeliness of monitoring and problem handling, save the manpower cost and time cost of host online environment operation and maintenance, and effectively reduce potential operational risks.

[0051] The present invention also provides a host online environment monitoring device, as described in the following embodiments. Since the principle of the device to solve the problem is similar to that of the host online environment monitoring method, the implementation of the device can refer to the implementation of the host online environment monitoring method, and the repeated parts will not be repeated.

[0052] Figure 4 This is a schematic diagram of a host online environment monitoring device according to an embodiment of the present invention, comprising:

[0053] The acquisition module 401 is used to execute the pre-deployed scheduled job and acquire the host online environment data;

[0054] A preprocessing module 402 is used to perform data preprocessing on the host online environment data according to a pre-trained data preprocessing model; the data preprocessing model is obtained by training a naive Bayes model using the historical host online environment data and the corresponding preprocessing results through a machine learning algorithm;

[0055] A data table generating module 403 is used to generate a data table according to the data type based on the host online environment data after data preprocessing;

[0056] The judgment module 404 is used to input the host online environment data in the data table into the judgment model in sequence and output the judgment result; the judgment model is obtained by training the naive Bayes model through a machine learning algorithm using the historical host online environment data and the corresponding labels representing whether the data is abnormal; the judgment result represents whether the host online environment data is abnormal;

[0057] The display module 405 is used to display the data table and the judgment result.

[0058] In one embodiment, the host online environment monitoring device may further include: a scheduled job deployment module, which is used to:

[0059] Receiving an instruction to deploy a scheduled job on a host; the scheduled job is used to obtain host online environment data at a scheduled time;

[0060] Deploy scheduled jobs on the host according to the instructions.

[0061] In one embodiment, the host online environment monitoring device may further include: a data preprocessing model generation module, which is used to:

[0062] Obtain historical host online environment data and pre-processed historical host online environment data;

[0063] According to the historical host online environment data and the processed historical host online environment data, the naive Bayes model is trained through the machine learning algorithm to generate a data preprocessing model.

[0064] In one embodiment, the host online environment monitoring device may further include: a judgment model generation module, which is used to:

[0065] Get historical host online environment data;

[0066] Adding a label to the historical host online environment data; the label represents an abnormal situation of the historical host online environment data;

[0067] Based on the historical host online environment data and the added labels, the naive Bayes model is trained through a machine learning algorithm to generate a judgment model.

[0068] In one embodiment, the host online environment monitoring device may further include: an update module, which is used to:

[0069] Using the host online environment data after data preprocessing to update the historical host online environment data;

[0070] The data preprocessing model is trained using the updated historical host online environment data to generate an updated data preprocessing model.

[0071] In one embodiment, the host online environment monitoring device may further include: an exception handling module, which is used to:

[0072] Using a pre-configured data exception processing script, the host online environment data with a judgment result of abnormality is processed to generate an exception processing result; the data exception processing script includes a plurality of sub-scripts corresponding to the categories of the host online environment data;

[0073] Display the results of exception handling;

[0074] Receive and store feedback information entered by the user based on the exception handling results.

[0075] In one embodiment, the host online environment data includes one or any combination of host online workload status data, routing status data, communication connection status data, database connection status data, peripheral gateway connection status data, and online address space data.

[0076] An embodiment of the present invention further provides a computer device, Figure 5 This is a schematic diagram of a computer device in an embodiment of the present invention. The computer device 500 includes a memory 510, a processor 520, and a computer program 530 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 530, the host online environment monitoring method is implemented.

[0077] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the host online environment monitoring method is implemented.

[0078] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the host online environment monitoring method is implemented.

[0079] Before the present invention is used, the operation and maintenance personnel need to log in to each set of host environment to check the online status information. The operation of some inspection items is cumbersome, time-consuming and error-prone. After the present invention is used, the operation and maintenance personnel do not need to log in to each set of environment for manual inspection. They can log in to the online operation and maintenance platform to obtain the host online status information in real time and realize intelligent diagnosis and processing of online abnormal problems. The invention simplifies the complexity of the operation and maintenance of the host online environment, improves the effectiveness of monitoring and problem handling, saves the manpower cost and time cost required for the operation and maintenance of the host online environment, and effectively reduces the potential operation risks.

[0080] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0081] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0082] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0083] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0084] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A host online environment monitoring method, characterized in that: include: Execute pre-deployed scheduled jobs to obtain host online environment data; The host online environment data is preprocessed according to a pre-trained data preprocessing model; the data preprocessing model is obtained by training a naive Bayes model using a machine learning algorithm using historical host online environment data and corresponding preprocessing results; Generate a data table according to the data category based on the host online environment data after data preprocessing; Input the host online environment data in the data table into the judgment model in sequence, and output the judgment result; The judgment model is obtained by training the naive Bayes model through a machine learning algorithm using historical host online environment data and corresponding labels representing whether the data is abnormal; the judgment result represents whether the host online environment data is abnormal; Display the data table and judgment results.

2. The method according to claim 1, characterized in that Before executing the pre-deployed scheduled job to obtain the host online environment data, it also includes: Receiving an instruction to deploy a scheduled job on a host; the scheduled job is used to obtain host online environment data at a scheduled time; Deploy scheduled jobs on the host according to the instructions.

3. The method according to claim 1, characterized in that Also includes: Obtain historical host online environment data and pre-processed historical host online environment data; According to the historical host online environment data and the processed historical host online environment data, the naive Bayes model is trained through the machine learning algorithm to generate a data preprocessing model.

4. The method according to claim 1, characterized in that Also includes: Get historical host online environment data; Add tags to historical host online environment data; The tag represents the abnormal situation of the historical host online environment data; Based on the historical host online environment data and the added labels, the naive Bayes model is trained through a machine learning algorithm to generate a judgment model.

5. The method according to claim 1, characterized in that After preprocessing the host online environment data according to the pre-trained data preprocessing model, it also includes: Using the host online environment data after data preprocessing to update the historical host online environment data; The data preprocessing model is trained using the updated historical host online environment data to generate an updated data preprocessing model.

6. The method according to claim 1, characterized in that Also includes: Use the pre-configured data exception processing script to process the host online environment data that is judged to be abnormal and generate an exception processing result; The data exception processing script includes a plurality of sub-scripts corresponding to the categories of the host online environment data; Display the results of exception handling; Receive and store feedback information entered by the user based on the exception handling results.

7. The method according to claim 1, characterized in that The host online environment data includes one or any combination of host online workload status data, routing status data, communication connection status data, database connection status data, peripheral gateway connection status data, and online address space data.

8. A host online environment monitoring device, characterized in that: include: The acquisition module is used to execute pre-deployed scheduled jobs and obtain host online environment data; A preprocessing module is used to perform data preprocessing on the host online environment data according to a pre-trained data preprocessing model; the data preprocessing model is obtained by training a naive Bayes model through a machine learning algorithm using historical host online environment data and corresponding preprocessing results; A data table generation module is used to generate a data table according to the data category based on the host online environment data after data preprocessing; A judgment module, used to input the host online environment data in the data table into the judgment model in sequence and output the judgment result; The judgment model is obtained by training the naive Bayes model through a machine learning algorithm using historical host online environment data and corresponding labels representing whether the data is abnormal; the judgment result represents whether the host online environment data is abnormal; The display module is used to display the data table and the judgment results.

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 method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images