IT service management platform based on artificial intelligence

Abstract

The invention discloses an IT service management platform based on artificial intelligence, and the platform comprises the steps: collecting the network time when a system answers n groups of basic questions, building a network time-question group number curve, obtaining a corresponding feature value, building an analysis model, obtaining a prediction abnormality rate of the IT system, and judging whether the IT system is abnormal or not based on the prediction abnormality rate. According to the method, the predicted abnormal rate of each IT system is obtained, a comprehensive analysis model is established, the comprehensive abnormal rate is obtained, whether the IT system is abnormal or not is judged based on the comprehensive abnormal rate, and when the IT system is judged to be abnormal, the early warning operation is carried out, and the service management is completed. Single-layer and double-layer synchronous management realizes anomaly monitoring of a single system and an overall local area network, a proposed specific corresponding analysis model improves the judgment accuracy of an abnormal condition, and the efficiency and quality of IT service management are improved by utilizing an artificial intelligence technology.

Description

Technical Field

[0001] The present invention relates to the technical field of computer science and information, and in particular to an IT service management platform based on artificial intelligence. Background Art

[0002] With the rapid development of information technology, enterprises are increasingly dependent on IT services.

[0003] Existing IT service management platforms often rely on manual service monitoring, fault handling, and resource management, which is inefficient and error-prone. The rapid development of artificial intelligence technology provides new solutions for IT service management. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above problems existing in the existing IT service management platform, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is to solve the problem that the existing IT service management platform relies on manual service monitoring, fault handling and resource management, which is inefficient and prone to errors.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: an IT service management platform based on artificial intelligence, wherein each IT system forms a local area network, and the IT service management platform specifically includes the following components: a data acquisition module, which is used to collect data from any IT system, and the collected data is specifically the network time of each IT system answering n groups of basic questions; a data processing module, which is wirelessly connected to the data acquisition module, and establishes a curve of network time-question group number after obtaining each network time; a data analysis module, which is data connected to the data processing module, obtains corresponding characteristic values ​​based on the curve of network time-question group number, establishes an analysis model, and obtains the predicted abnormality rate of the IT system; an abnormal service determination module, which is data connected to the data analysis module, determines whether the IT system is abnormal based on the predicted abnormality rate, and performs an early warning operation when it is determined to be abnormal, thereby completing service management.

[0008] As a preferred solution of the IT service management platform based on artificial intelligence described in the present invention, when the data collection module collects data, the AI ​​asks n groups of basic questions step by step in chronological order.

[0009] As a preferred solution of the artificial intelligence-based IT service management platform described in the present invention, the data acquisition module is also embedded with a data preprocessing unit, which performs data preprocessing after acquiring the collected data; wherein the data preprocessing steps are specifically: extraction, conversion and loading.

[0010] As a preferred solution of the artificial intelligence-based IT service management platform described in the present invention, the data processing module establishes a curve of network time-question group number, which specifically includes the following steps: S1: obtaining the network time corresponding to each of n groups of basic questions; S2: using the order of asking the n groups of questions as the X-axis and the network time as the Y-axis to obtain the corresponding reference points; S3: connecting each reference point in turn with a smooth curve to form a curve of network time-question group number.

[0011] As a preferred solution of the IT service management platform based on artificial intelligence described in the present invention, the analysis model established by the data analysis module is specifically:

[0012]

[0013] Where η is the predicted anomaly rate; T1 is the network time of the first reference point, ms; T n is the network time of the nth reference point, in ms; T max is the maximum network time of the reference point, ms; T min is the minimum network time of the reference point, in ms; n is the number of reference points, i.e. the number of problem groups; d min The minimum derivative of the curve of network time-problem group number; d max is the maximum derivative of the curve of network time-problem group number; 1.65 and 1.09 are adjustment constants; dx is the integral operation.

[0014] As a preferred solution of the artificial intelligence-based IT service management platform described in the present invention, when the abnormal service determination module determines an abnormality, when the predicted abnormality rate is higher than a threshold, it is determined to be abnormal, and an early warning operation is performed to complete service management.

[0015] As a preferred solution of the artificial intelligence-based IT service management platform described in the present invention, the threshold is set to 2.94 or 2.939.

[0016] As a preferred solution of the artificial intelligence-based IT service management platform described in the present invention, it also includes a local area network IT service comprehensive judgment module, which is wirelessly connected to the data analysis module, obtains the predicted abnormality rate of each IT system, establishes a comprehensive analysis model, obtains the comprehensive abnormality rate, determines whether it is abnormal based on the comprehensive abnormality rate, and performs early warning operations when it is determined to be abnormal, thereby completing service management.

[0017] As a preferred solution of the IT service management platform based on artificial intelligence described in the present invention, the comprehensive analysis model is specifically:

[0018]

[0019] Among them, δ is the comprehensive abnormality rate; η1 is the predicted abnormality rate of the first IT system; η m is the predicted abnormal rate of the mth IT system; m is the number of IT systems; -1.62 is the adjustment constant; dx is the integral operation.

[0020] As a preferred solution of the artificial intelligence-based IT service management platform described in the present invention, when the comprehensive abnormality rate is higher than the comprehensive threshold, the local area network is determined to be abnormal; wherein the comprehensive threshold is set to 1.13.

[0021] Beneficial effects of the present invention: The present invention provides an IT service management platform based on artificial intelligence, collects the network time of each system answering n groups of basic questions, establishes a curve of network time-question group number, obtains corresponding characteristic values ​​based on the curve of network time-question group number, establishes an analysis model, obtains the predicted abnormality rate of the IT system, determines whether the IT system is abnormal based on the predicted abnormality rate, and performs an early warning operation after determining the abnormality to complete service management. The present invention also obtains the predicted abnormality rate of each IT system through a local area network IT service comprehensive judgment module, establishes a comprehensive analysis model, obtains the comprehensive abnormality rate, determines whether it is abnormal based on the comprehensive abnormality rate, and performs an early warning operation after determining the abnormality to complete service management. The single-layer and double-layer synchronous management realizes the abnormal monitoring of a single system and the entire local area network. The specific corresponding analysis model proposed improves the accuracy of the judgment of abnormal situations. By using artificial intelligence technology, automated IT service monitoring, fault prediction, resource optimization and service process automation are realized, thereby improving the efficiency and quality of IT service management. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 labor. Among them:

[0023] Figure 1 This is a system module diagram of the artificial intelligence-based IT service management platform provided by the present invention.

[0024] Figure 2 A flow chart of a method for establishing a network time-question group number curve for a data processing module provided by the present invention. DETAILED DESCRIPTION

[0025] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0026] Existing IT service management platforms often rely on manual service monitoring, fault handling, and resource management, which is inefficient and error-prone. The rapid development of artificial intelligence technology provides new solutions for IT service management.

[0027] Therefore, please refer to Figure 1 The present invention provides an IT service management platform based on artificial intelligence. Each IT system forms a local area network. The IT service management platform specifically includes the following components:

[0028] The data collection module 100 is used to collect data from any IT system, and the collected data is specifically the network time of the IT system answering n groups of basic questions;

[0029] The data processing module 200 is wirelessly connected to the data acquisition module 100, and after acquiring each network time, a curve of network time-problem group number is established;

[0030] The data analysis module 300 is connected to the data processing module 200, obtains corresponding characteristic values ​​based on the curve of network time-problem group number, establishes an analysis model, and obtains the predicted abnormality rate of the IT system;

[0031] The abnormal service determination module 400 is data-connected to the data analysis module 300, determines whether the IT system is abnormal based on the predicted abnormality rate, and performs early warning operations when abnormality is determined to complete service management.

[0032] Specifically, when the data collection module 100 collects data, the AI ​​asks n groups of basic questions step by step in chronological order.

[0033] For example, n sets of basic questions are set as follows: start collecting with the current day as the measurement node, select the search keywords that rank first on the popular search engine every day, collect them in chronological order, and form a data set for n sets of questions. When AI asks n sets of basic questions, it asks them step by step in chronological order, synchronizes, and obtains the network time of the IT system answering n sets of basic questions. At this time, each question corresponds to an answer time. Since n sets of data are collected evenly in chronological order, the reference points obtained are also evenly distributed points in chronological order.

[0034] Furthermore, a data preprocessing unit is also embedded in the data acquisition module 100 to perform data preprocessing after acquiring the collected data;

[0035] Among them, the data preprocessing steps are specifically: extraction, conversion and loading.

[0036] It should be noted that the data preprocessing unit embedded in the data acquisition module 100 usually follows the process of extraction, transformation, and loading, referred to as ETL. The following are the specific steps and descriptions of this process:

[0037] 1. Extraction:

[0038] Data extraction: Extract the required data from the original data source (such as database, file system, API, etc.).

[0039] Source data identification: Determine what data is needed and where and in what format it is stored.

[0040] Data extraction strategy: Decide whether to extract the entire data or extract incremental data based on the frequency of data updates and business needs.

[0041] 2. Transform:

[0042] Data cleaning: including removing duplications, correcting errors, filling missing values, etc. to ensure data quality.

[0043] Data standardization: converting data into a unified format or standard to facilitate subsequent processing and analysis.

[0044] Data validation: ensuring that data meets specific business rules and quality requirements.

[0045] Data conversion: Perform necessary conversions on data, such as data type conversion, unit conversion, encoding conversion, etc.

[0046] Feature engineering: creating new data features or indicators based on analysis requirements.

[0047] Data aggregation: Summarize data, such as aggregating by time period, category, etc.

[0048] 3. Load:

[0049] Data loading: Loading the transformed and preprocessed data into a target data storage system such as a data warehouse, database, or data lake.

[0050] Data indexing: Create indexes for loaded data to optimize query performance.

[0051] Data synchronization: Ensure that the loaded data remains consistent with the source data, especially when the data is incrementally updated.

[0052] The entire data preprocessing process aims to improve the quality, availability and efficiency of data, ensuring that subsequent data analysis and business decisions can be made based on accurate and complete data sets.

[0053] For further information, see Figure 2 The data processing module 200 establishes a curve of network time-problem group number, which specifically includes the following steps:

[0054] S1: Get the network time corresponding to each of n groups of basic questions;

[0055] S2: Take the order of asking n groups of questions as the X-axis and the network time as the Y-axis to obtain the corresponding reference points;

[0056] S3: Connect each reference point in sequence with a smooth curve to form a curve of network time-problem group number.

[0057] Furthermore, the analysis model established by the data analysis module 300 is specifically:

[0058]

[0059] Where η is the predicted anomaly rate; T1 is the network time of the first reference point, ms; T n is the network time of the nth reference point, in ms; T max is the maximum network time of the reference point, ms; T min is the minimum network time of the reference point, in ms; n is the number of reference points, i.e. the number of problem groups; d min The minimum derivative of the curve of network time-problem group number; d max is the maximum derivative of the curve of network time-problem group number; 1.65 and 1.09 are adjustment constants; dx is the integral operation.

[0060] Specifically, when the abnormal service determination module 400 determines an abnormality, when the predicted abnormality rate is higher than a threshold, it is determined to be abnormal, and an early warning operation is performed to complete service management.

[0061] Specifically, the threshold is set to 2.94 or 2.939.

[0062] Furthermore, it also includes a local area network IT service comprehensive judgment module 500, which is wirelessly connected to the data analysis module 300, obtains the predicted abnormality rate of each IT system, establishes a comprehensive analysis model, obtains the comprehensive abnormality rate, determines whether it is abnormal based on the comprehensive abnormality rate, and performs early warning operations when it is determined to be abnormal, thereby completing service management.

[0063] Furthermore, the comprehensive analysis model is as follows:

[0064]

[0065] Among them, δ is the comprehensive abnormality rate; η1 is the predicted abnormality rate of the first IT system; η m is the predicted abnormal rate of the mth IT system; m is the number of IT systems; -1.62 is the adjustment constant; dx is the integral operation.

[0066] Specifically, when the comprehensive abnormality rate is higher than the comprehensive threshold, the local area network is determined to be abnormal;

[0067] Among them, the comprehensive threshold is set to 1.13.

[0068] In order to verify the technical effect of the present invention, the following simulation experiment is now carried out:

[0069] Purpose of the test

[0070] Verify the performance of AI-based IT service management platform in improving service monitoring efficiency, reducing fault handling time, and optimizing resource management.

[0071] Experimental design

[0072] Experimental environment construction: Build a simulated enterprise IT system LAN, including multiple IT systems, each system can answer basic questions and provide corresponding network time data.

[0073] Data Collection: Use the data collection module to collect network time from various IT systems to answer basic questions.

[0074] Data processing: The collected data is transferred to the data processing module for processing, including data preprocessing, establishing network time-problem group number curve, etc.

[0075] Data analysis: Based on the processed data, use the data analysis module to build an analysis model and calculate the predicted anomaly rate.

[0076] Abnormality determination and early warning: abnormality determination is performed based on the predicted abnormality rate, and an early warning operation is triggered when an abnormality is determined.

[0077] Data collection and processing

[0078] Suppose we collect data from a local area network that contains five IT systems. The following is part of the collected data:

[0079] Table 1

[0080]

[0081] Table 2

[0082] IT System Number Prediction abnormality rate (%) IT1 2.1 IT2 3.7 IT3 1.5 IT4 4.2 IT5 2.8

[0083] Test verification process

[0084] Data preprocessing: Data preprocessing is performed based on the data in the data collection form, including extraction, conversion and loading.

[0085] Curve establishment: Using the results of data preprocessing, establish the network time-problem group number curve and extract the corresponding eigenvalues.

[0086] Model building: Using the extracted feature values, an analysis model is built to calculate the predicted anomaly rate of each IT system.

[0087] Abnormality determination: Based on the predicted abnormality rate, determine whether each IT system is abnormal and record the determination results.

[0088] Warning triggering: For IT systems judged to be abnormal, the warning operation is triggered and the warning log is recorded.

[0089] Test results

[0090] After analyzing the data collected and the results recorded during the test, the following are some of the test results:

[0091] Table 3

[0092] IT System Number Actual abnormal state Predict abnormal conditions Warning Operation IT1 normal normal Not triggered IT2 abnormal abnormal Triggered ... ... ... ... IT5 abnormal abnormal Triggered

[0093] in conclusion

[0094] Through the above test verification process, the performance improvement of the solution of the present invention in IT service management can be specifically evaluated, including the performance in monitoring efficiency, fault handling time and resource management optimization. The actual technical effect of the solution of the present invention can be intuitively demonstrated through the specific data in the table.

[0095] The present invention provides an IT service management platform based on artificial intelligence, collects the network time of each system answering n groups of basic questions, establishes a curve of network time-question group number, obtains corresponding characteristic values ​​based on the curve of network time-question group number, establishes an analysis model, obtains the predicted abnormality rate of the IT system, determines whether the IT system is abnormal based on the predicted abnormality rate, and performs an early warning operation after determining abnormality to complete service management. The present invention also obtains the predicted abnormality rate of each IT system through a local area network IT service comprehensive judgment module, establishes a comprehensive analysis model, obtains the comprehensive abnormality rate, determines whether it is abnormal based on the comprehensive abnormality rate, and performs an early warning operation after determining abnormality to complete service management. The single-layer and double-layer synchronous management realizes the abnormal monitoring of a single system and the entire local area network. The specific corresponding analysis model proposed improves the judgment accuracy of abnormal situations. By using artificial intelligence technology, automated IT service monitoring, fault prediction, resource optimization and service process automation are realized, thereby improving the efficiency and quality of IT service management.

[0096] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An AI-based IT service management platform, where each IT system forms a local area network, characterized by: The IT service management platform specifically includes the following components: A data collection module (100) is used to collect data from any IT system, wherein the collected data specifically refers to the network time of the IT system answering n groups of basic questions; A data processing module (200) is wirelessly connected to the data acquisition module (100) to acquire each network time and then establish a curve of network time-question group number; A data analysis module (300) is connected to the data processing module (200) and acquires corresponding characteristic values ​​based on a curve of network time-problem group number, establishes an analysis model, and acquires a predicted abnormality rate of the IT system; The abnormal service determination module (400) is data-connected to the data analysis module (300), determines whether the IT system is abnormal based on the predicted abnormality rate, and performs an early warning operation when an abnormality is determined, thereby completing service management.

2. The AI-based IT service management platform according to claim 1, characterized in that: When the data collection module (100) collects data, the AI ​​asks n groups of basic questions step by step in chronological order.

3. The AI-based IT service management platform according to claim 2, characterized in that: The data acquisition module (100) is also embedded with a data preprocessing unit, which performs data preprocessing after acquiring the collected data; Among them, the data preprocessing steps are specifically: extraction, conversion and loading.

4. The AI-based IT service management platform according to claim 3, characterized in that: The data processing module (200) establishes a curve of network time-question group number, which specifically comprises the following steps: S1: Get the network time corresponding to each of n groups of basic questions; S2: Take the order of asking n groups of questions as the X-axis and the network time as the Y-axis to obtain the corresponding reference points; S3: Connect each reference point in sequence with a smooth curve to form a curve of network time-problem group number.

5. The AI-based IT service management platform according to claim 4, characterized in that: The analysis model established by the data analysis module (300) is specifically: Where η is the predicted anomaly rate; T1 is the network time of the first reference point, ms; T n is the network time of the nth reference point, in ms; T max is the maximum network time of the reference point, ms; T min is the minimum network time of the reference point, in ms; n is the number of reference points, i.e. the number of problem groups; d min The minimum derivative of the curve of network time-problem group number; d max is the maximum derivative of the curve of network time-problem group number; 1.65 and 1.09 are adjustment constants; dx is the integral operation.

6. The artificial intelligence-based IT service management platform according to claim 5, characterized in that: When the abnormal service determination module (400) determines an abnormality, when the predicted abnormality rate is higher than a threshold, it is determined to be abnormal, and an early warning operation is performed to complete service management.

7. The artificial intelligence-based IT service management platform according to claim 6, characterized in that: The threshold was set to 2.94 or 2.

939.

8. The artificial intelligence-based IT service management platform according to claim 7, characterized in that: It also includes a local area network IT service comprehensive determination module (500), which is wirelessly connected to the data analysis module (300) to obtain the predicted abnormality rate of each IT system, establish a comprehensive analysis model, obtain the comprehensive abnormality rate, determine whether it is abnormal based on the comprehensive abnormality rate, and perform early warning operations when it is determined to be abnormal, thereby completing service management.

9. The artificial intelligence-based IT service management platform according to claim 8, characterized in that: The comprehensive analysis model is specifically: Among them, δ is the comprehensive abnormality rate; η1 is the predicted abnormality rate of the first IT system; η m is the predicted abnormal rate of the mth IT system; m is the number of IT systems; -1.62 is the adjustment constant; dx is the integral operation.

10. The artificial intelligence-based IT service management platform according to claim 9, characterized in that: When the comprehensive abnormality rate is higher than the comprehensive threshold, the local area network is determined to be abnormal; Wherein, the comprehensive threshold is set to 1.13.

Images