AIOps intelligent operation and maintenance method and system based on artificial intelligence technology

Abstract

The invention discloses an AIOps intelligent operation and maintenance method and system based on an artificial intelligence technology, and relates to the technical field of artificial intelligence operation and maintenance, and the method comprises the steps: carrying out the real-time monitoring and data processing of a system state through a first algorithm; analyzing association among the components through a knowledge graph and predicting faults; and optimizing the resource allocation and fault processing flow based on a first algorithm. According to the AIOps intelligent operation and maintenance method based on the artificial intelligence technology provided by the invention, each component of the system is monitored in real time, the time and complexity of manual intervention are reduced, the automatic management capability of the system is improved, the dependency relationship among the micro-service components in the system is analyzed, and the system reliability is improved. According to the method, the fault location accuracy and efficiency are improved, the stability and availability of the system are improved through fault prediction, the overall performance and the resource utilization rate of the system are improved through automatic resource allocation, and better effects are achieved in the aspects of execution cost, load balance and completion time.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence operation and maintenance technology, and specifically to an AIOps intelligent operation and maintenance method based on artificial intelligence technology. Background Art

[0002] With the continuous development of information technology, AIOps (artificial intelligence operation and maintenance) has gradually become a core technology in IT system management. AIOps integrates big data analysis, artificial intelligence and automation technology to achieve real-time monitoring, fault detection, problem prediction and intelligent decision-making of complex IT infrastructure. Compared with traditional manual operation and maintenance, AIOps can automatically process large amounts of log data, system indicators and alarm information, significantly improving the system's operation and maintenance efficiency and reliability. In recent years, with the widespread application of microservice architecture and cloud computing, enterprises have an increasing demand for intelligent operation and maintenance, which has also prompted the rapid development of AIOps technology. Through AI-driven operation and maintenance methods, enterprises can manage their complex IT environment more proactively and accurately, and avoid huge losses caused by system failures.

[0003] Although AIOps technology has improved the management level of IT systems in many aspects, the existing technology still has some shortcomings. Existing AIOps solutions often face the problem of insufficient real-time performance in data processing, resulting in the timeliness of system status monitoring and fault detection unable to meet the business needs under high concurrency and complex architectures. The existing system has weak multi-component correlation analysis capabilities for microservice architectures and is unable to fully grasp the dependencies between services in the system, resulting in insufficient accuracy and efficiency in fault prediction. The intelligence level of resource allocation optimization is low, and resources cannot be dynamically adjusted according to real-time load changes, which easily leads to resource waste or system overload. In addition, the existing technology is relatively limited in the automation of fault handling, and the fault repair process often relies on manual intervention, and cannot achieve fully automated repair and optimization. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: the existing AIOps intelligent operation and maintenance methods have insufficient real-time data processing, inaccurate microservice correlation analysis, weak dynamic resource allocation capabilities, and the optimization problem of how to achieve automatic repair of faults.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: an AIOps intelligent operation and maintenance method based on artificial intelligence technology, comprising real-time monitoring and data processing of system status through a first algorithm; analyzing the relationship between components and predicting faults through a knowledge graph; and optimizing resource allocation and fault handling processes based on the first algorithm.

[0007] As a preferred solution of the AIOps intelligent operation and maintenance method based on artificial intelligence technology described in the present invention, the real-time monitoring and data processing of the system status through the first algorithm includes continuously tracking the system operation status and collecting system data through the first algorithm.

[0008] As a preferred solution of the AIOps intelligent operation and maintenance method based on artificial intelligence technology described in the present invention, the real-time monitoring and data processing of the system status through the first algorithm also includes aggregating, filtering and standardizing the collected real-time data and historical data.

[0009] As a preferred solution of the AIOps intelligent operation and maintenance method based on artificial intelligence technology described in the present invention, wherein: the analysis of the association between components and prediction of faults through knowledge graph includes analyzing the association relationship between components and establishing a global view of system components.

[0010] As a preferred solution of the AIOps intelligent operation and maintenance method based on artificial intelligence technology described in the present invention, wherein: the analysis of the relationship between components through knowledge graph and prediction of failures also includes combining historical operation and maintenance data with real-time operation and maintenance data to predict system failures and potential performance bottlenecks.

[0011] As a preferred solution of the AIOps intelligent operation and maintenance method based on artificial intelligence technology described in the present invention, wherein: the optimization of resource allocation and fault handling process based on the first algorithm includes optimizing the dynamic allocation of system resources based on the analysis results.

[0012] As a preferred solution of the AIOps intelligent operation and maintenance method based on artificial intelligence technology described in the present invention, wherein: the optimization of resource allocation and fault handling process based on the first algorithm also includes generating a plan based on the predicted fault situation, and repairing it through scripts or artificial intelligence.

[0013] Another object of the present invention is to provide an AIOps intelligent operation and maintenance system based on artificial intelligence technology, which can analyze the relationship between components through a knowledge graph through an analysis and prediction module, and predict system failures, thereby solving the current problem of instability of robots when driving on ground with water marks.

[0014] As a preferred solution of the AIOps intelligent operation and maintenance system based on artificial intelligence technology described in the present invention, it includes: a monitoring and processing module, an analysis and prediction module, and a process optimization module; the monitoring and processing module is used to perform real-time monitoring and data processing on the system status through a first algorithm; the analysis and prediction module is used to analyze the relationship between components through a knowledge graph and predict faults; the process optimization module is used to optimize resource allocation and fault handling processes based on the first algorithm.

[0015] A computer device includes a memory and a processor, wherein the memory stores a computer program, and wherein the processor executes the computer program to implement an AIOps intelligent operation and maintenance method based on artificial intelligence technology.

[0016] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of an AIOps intelligent operation and maintenance method based on artificial intelligence technology are implemented.

[0017] Beneficial effects of the present invention: The present invention provides an AIOps intelligent operation and maintenance method based on artificial intelligence technology, which monitors each component of the system in real time, dynamically collects various data during system operation, reduces the time and complexity of manual intervention, and improves the system's automated management capabilities. By analyzing the dependencies between microservice components in the system, the accuracy and efficiency of fault location are improved, and fault prediction improves the stability and availability of the system. Through automated resource allocation, the overall performance and resource utilization of the system are improved. The present invention achieves better results in execution cost, load balancing and completion time. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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:

[0019] Figure 1 An overall flow chart of an AIOps intelligent operation and maintenance method based on artificial intelligence technology provided for the first and second embodiments of the present invention.

[0020] Figure 2 An overall module diagram of an AIOps intelligent operation and maintenance system based on artificial intelligence technology provided for the fourth embodiment of the present invention. DETAILED DESCRIPTION

[0021] 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.

[0022] Example 1

[0023] Reference Figure 1 , is an embodiment of the present invention, and provides an AIOps intelligent operation and maintenance method based on artificial intelligence technology, including:

[0024] S1: Real-time monitoring and data processing of system status is performed through the first algorithm.

[0025] Furthermore, real-time monitoring and data processing of the system status by the first algorithm includes continuously tracking the system operation status and collecting system data by the first algorithm.

[0026] In the embodiment of the present application, the first algorithm is a machine learning algorithm. The machine learning algorithm is a data-based algorithm that generates predictions and decisions by extracting information from historical and real-time data. The core principle is to use statistical and computer science pattern recognition methods to analyze data and ultimately generate a model so that accurate judgments can be made on similar data or situations in the future. Machine learning algorithms are usually data collection. The system obtains a large amount of historical and real-time data from multiple sources (such as sensors, user activity logs, network indicators, etc.). Subsequently, the algorithm preprocesses the data to ensure consistency and noise-freeness of the data, such as by removing outliers and performing standardization. This The process is particularly important because the quality of the data directly affects the performance of the model. After preprocessing, the data is used to train the model. The model training process generally uses a set of data sets with known results to optimize the parameters of the algorithm to minimize the prediction error. After the training is completed, the model will continue to accept new data for prediction and continuously update through incremental training to improve the accuracy and adaptability of the model. Ultimately, this machine learning algorithm can make predictions based on observed patterns, such as system load changes or potential failure trends. Compared with traditional rule-based algorithms, machine learning algorithms can adapt to complex and diverse system environments, especially in data-driven scenarios, showing higher accuracy and robustness;

[0027] The system collects performance data from multiple microservice components through distributed proxy nodes, such as CPU usage, memory usage, network latency, response time, etc. The proxy nodes send data streams to the data center periodically (for example, every second or every minute);

[0028] In the implementation of machine learning models, data collection is not limited to the current system state, but also includes the playback of historical data to enable incremental training of the model. Real-time data collection is combined with historical data at appropriate points in time to ensure the continuity and consistency of the data flow;

[0029] In an optional embodiment, the first algorithm can also be implemented in other ways, such as an algorithm based on a rule engine. The algorithm based on a rule engine is an algorithm that makes decisions through a preset rule set. Its working method is to make judgments based on the real-time status of the system and the defined threshold. Once the conditions are met, a specific operation is triggered. This type of algorithm does not rely on the accumulation of historical data. All judgment bases are executed on the data snapshot at the current moment. Therefore, it is very suitable for scenarios that require rapid response. The algorithm of the rule engine usually includes a rule set, and the decision conditions set by the operation and maintenance personnel according to the specific needs of the system and past experience, and data collection. This type of algorithm usually collects the current status information of the system at a high frequency, such as CPU usage and network latency once per second, to ensure that the instantaneous state of the system can be accurately monitored. Then, the rule execution engine judges in real time whether the collected data meets the rule conditions. Once the conditions are met, the corresponding operation will be triggered immediately without the need for complex data analysis. Compared with machine learning algorithms, algorithms based on rule engines are less dependent on data and pay more attention to real-time and simple conditional judgments. Therefore, they are suitable for single and easy-to-define decision scenarios. The design of the rule engine enables it to respond quickly even when resource requirements are low. Although it cannot make deep predictions like machine learning, it has advantages in the speed of response to the current system status.

[0030] In the rule engine implementation, data collection still involves collecting real-time performance data from microservice components through proxy nodes, but the difference is that the data is limited to the data snapshot at the current moment and does not include the playback of historical data;

[0031] The rule engine does not require complex historical data for analysis, so the frequency of data collection can be higher, which is more suitable for quickly judging the system status at a single moment. The rule engine collects the current CPU usage, memory usage and other data once a second and transmits it directly to the rule engine unit for judgment.

[0032] Furthermore, real-time monitoring and data processing of the system status by the first algorithm also includes aggregating, filtering and standardizing the collected real-time data and historical data.

[0033] In the embodiment of the present application, since the machine learning model has high requirements on data quality, the preprocessing process is more complicated, and the steps include interpolating or filling in the missing data to ensure the integrity of the data;

[0034] Identify and remove obvious outliers in the data using statistical methods or simple rules;

[0035] Standardize performance metrics with different units and ranges, such as converting CPU utilization from a percentage to a range between 0 and 1, or converting network latency to standard milliseconds, to ensure that all data has a consistent scale when it is input into the model;

[0036] To adapt to machine learning algorithms, preprocessing will sort the data by timestamp to form time series data, which is convenient for the model to learn the dynamic changes of the system;

[0037] The data preprocessing of machine learning algorithms is more complex, ensuring that the data input into the machine learning model is noise-free, anomaly-free, standardized and continuous, ensuring that the algorithm can accurately monitor the system behavior.

[0038] In an optional embodiment, the data preprocessing process is relatively simple, the purpose is to ensure that the collected data meets the basic judgment requirements, and does not involve complex time series analysis. The preprocessing step includes making all collected performance data have a consistent format, such as converting CPU usage and memory usage into the same unit format;

[0039] Remove redundant or invalid data so that the data processed by the rule engine are all relevant to the current monitoring purpose. For temporarily useless data, discard it directly to ensure processing efficiency.

[0040] Simple outlier detection and processing. When invalid data is detected, the value will be ignored immediately to avoid misleading the rule engine.

[0041] Since the rule engine relies on predefined rule sets, data preprocessing only needs to meet basic formatting and cleaning requirements and does not require standardization or complex continuity analysis. The preprocessing process is faster and supports the rule engine's efficient processing of real-time data.

[0042] Example 2

[0043] Reference Figure 1 , is an embodiment of the present invention, and provides an AIOps intelligent operation and maintenance method based on artificial intelligence technology, including:

[0044] S2: Analyze the associations between components and predict failures through knowledge graphs.

[0045] Furthermore, the knowledge graph is used to analyze the associations between components and predict faults, including analyzing the associations between components and establishing a global view of system components.

[0046] It should be noted that the knowledge graph helps system administrators and operation and maintenance personnel to intuitively understand the internal operating mechanism of the microservice architecture by building and maintaining the complex associations between components in the system, and provides support for the system's operation and maintenance decisions;

[0047] In the microservice architecture, each microservice has a complex dependency relationship. The knowledge graph builds a global view based on the interaction data, call chain and dependency relationship between microservices through semantic analysis. This global view is not only a simple service call chain, but also combines the context information of each component, such as the communication mode between services, the usage of the database, the interaction frequency of the message queue, etc. This enables the system to provide more accurate fault analysis and prediction capabilities;

[0048] Through the knowledge graph, the system can identify critical paths and dependencies, and generate a dynamic association graph to display the real-time dependencies between microservices. For operation and maintenance personnel, it improves the efficiency of troubleshooting and can quickly locate the root cause of the problem. If a microservice fails, the knowledge graph can quickly display other components associated with the service and analyze its potential impact range, helping operation and maintenance personnel make accurate repair decisions.

[0049] Furthermore, analyzing the associations between components and predicting failures through knowledge graphs also includes combining historical operation and maintenance data with real-time operation and maintenance data to predict system failures and potential performance bottlenecks.

[0050] It should be noted that in the enterprise microservice architecture, system components and dependencies change over time. The knowledge graph can continuously learn from real-time and historical data and dynamically adjust the system's dependency graph. When new microservices are launched or existing services are upgraded, the knowledge graph automatically updates its associations to ensure that the system can reflect the current actual operating status in real time.

[0051] By combining historical data, the knowledge graph can identify current anomalies and predict possible future failures by analyzing past failure patterns. If the performance indicators of a microservice in the system begin to show a pattern similar to a historical failure, the knowledge graph will issue an early warning based on this data, prompting operation and maintenance personnel to take appropriate measures. This predictive capability can avoid potential risks in advance and reduce the possibility of system downtime.

[0052] S3: Optimize resource allocation and fault handling process based on the first algorithm.

[0053] Furthermore, optimizing resource allocation and fault handling process based on the first algorithm includes optimizing dynamic allocation of system resources based on the analysis result.

[0054] In the embodiment of the present application, resource allocation is dynamically optimized through a machine learning algorithm. The machine learning model predicts future loads by analyzing historical data and current status. The model can make accurate predictions about upcoming high-load periods based on current system behavior (e.g., high concurrent requests during certain hours of the day or seasonal user access peaks).

[0055] Based on the prediction results of the model, the system dynamically adjusts the resource allocation strategy before high load is about to occur. For example, when the system load is expected to increase in the next hour, the system allocates more resources to the CPU, memory, and network bandwidth in advance to ensure that the system can continue to run stably during high load and avoid performance bottlenecks caused by insufficient resources.

[0056] When the load actually occurs, the system adjusts resource allocation in real time to ensure efficient use of existing resources. If the resource demand of a microservice decreases, the system automatically releases some resources to avoid resource waste.

[0057] In an optional embodiment, dynamic resource allocation optimization is performed through a rule engine. The operation and maintenance team defines a set of resource allocation rules based on the historical performance data of the system. For example, it defines that when the CPU usage rate exceeds 80%, the computing resources of the microservice are increased, and when the memory usage rate is less than 50%, the memory allocation is reduced.

[0058] When the performance indicator of a microservice exceeds the preset threshold, the rule engine automatically triggers the corresponding resource adjustment operation. For example, the system automatically increases the number of CPU cores for services with excessive load, or allocates additional network resources for services that occupy too much bandwidth.

[0059] If the system detects that resource usage is below a certain threshold, the rule engine automatically reclaims some resources and allocates them to other microservices in need, thereby improving the overall resource utilization of the system;

[0060] The rule engine can quickly make decisions on resource adjustments to ensure that the system can use resources efficiently when faced with load fluctuations, avoiding system overload or resource waste.

[0061] Furthermore, optimizing resource allocation and fault handling processes based on the first algorithm also includes generating solutions based on predicted fault conditions and performing repairs through scripts or artificial intelligence.

[0062] In the embodiment of the present application, the machine learning algorithm automatically generates a repair plan for the current potential fault based on the repair records of historical faults. If the network delay suddenly increases, the system recommends adjusting the routing settings or increasing the network bandwidth;

[0063] When a fault response plan is generated, the system automatically performs related repair operations. For serious faults, the system can also perform restart operations through automated scripts, or switch to backup microservice instances to ensure rapid recovery of the system.

[0064] In an optional embodiment, when the system detects an anomaly, the system generates corresponding repair suggestions according to the rule set, and executes the repair plan through an automated process. The system automatically triggers the operation of restarting the service or adding resources to ensure that the fault is quickly handled;

[0065] When the rule is triggered, the system automatically executes repair measures and restores services. After discovering that the performance of a service has degraded, the system automatically adjusts the load balancing and switches to other healthy service instances.

[0066] Example 3

[0067] One embodiment of the present invention provides an AIOps intelligent operation and maintenance method based on artificial intelligence technology. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0068] The experimental environment is a system with a distributed microservice architecture, which includes 50 microservice nodes. Each node runs different business logic. The experiment is carried out under load changes and different failure scenarios. The key performance indicators of the system include CPU utilization, memory usage, network latency, and response time. The goal of the experiment is to verify the performance of the present invention in dealing with system anomalies, optimizing resource utilization, and improving system stability.

[0069] The system uses the method of the present invention to perform real-time monitoring and collect the operating data of each microservice. In order to ensure the scientific nature of the experiment, the data collection frequency is set to once every 10 seconds, and the experiment lasts for 24 hours, simulating the peak load and trough periods in the actual operating environment.

[0070] As shown in Table 1, the CPU utilization rates of microservice 1, microservice 3, and microservice 6 reached 85%, 92%, and 78%, respectively. The resource requirements of these nodes are significantly higher. Traditional methods can only respond through preset rules after the load exceeds the threshold, and it is difficult to respond in time. When the method of the present invention detects that the node load is higher than the preset threshold, it timely predicts the further growth of the future load, increases the number of CPU cores in advance, ensures the stability of the system, effectively controls the growth of the load, and avoids the degradation of system performance.

[0071] In terms of memory usage, through the method of the present invention, the system releases excess resources when memory resources are not needed and reallocates them to required services. The memory usage of microservice 2 and microservice 5 are 2.0GB and 1.8GB respectively. The system determines that no additional resources are needed, so no excessive adjustments are made. For microservice 3, its memory usage is higher, and the system ensures its smooth operation by allocating resources in advance.

[0072] In the scenario where the network bottleneck problem is introduced, the network delay of microservice 3 reaches 300ms. The method of the present invention identifies this problem in advance and controls the delay within a reasonable range through route optimization and resource adjustment, ultimately avoiding system crash.

[0073] Table 1 Experimental data table

[0074]

[0075] Example 4

[0076] Reference Figure 2 , as an embodiment of the present invention, provides an AIOps intelligent operation and maintenance system based on artificial intelligence technology, including: a monitoring and processing module, an analysis and prediction module, and a process optimization module.

[0077] The monitoring and processing module is used to monitor the system status in real time and process data through the first algorithm; the analysis and prediction module is used to analyze the relationship between components and predict faults through the knowledge graph; and the process optimization module is used to optimize resource allocation and fault handling processes based on the first algorithm.

[0078] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0079] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0080] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0081] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0082] 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 AIOps intelligent operation and maintenance method based on artificial intelligence technology, characterized in that: include: Real-time monitoring and data processing of system status through a first algorithm; Analyze the associations between components and predict failures through knowledge graphs; The resource allocation and fault handling process are optimized based on the first algorithm.

2. The AIOps intelligent operation and maintenance method based on artificial intelligence technology according to claim 1, characterized in that: The real-time monitoring and data processing of the system status by the first algorithm includes continuously tracking the system operation status and collecting system data by the first algorithm.

3. The AIOps intelligent operation and maintenance method based on artificial intelligence technology as claimed in claim 2, characterized in that: The real-time monitoring and data processing of the system status by the first algorithm also includes aggregating, filtering and standardizing the collected real-time data and historical data.

4. The AIOps intelligent operation and maintenance method based on artificial intelligence technology as claimed in claim 3, characterized in that: Analyzing the associations between components and predicting faults through a knowledge graph includes analyzing the associations between components and establishing a global view of system components.

5. The AIOps intelligent operation and maintenance method based on artificial intelligence technology as claimed in claim 4, characterized in that: The method of analyzing the associations between components and predicting failures through a knowledge graph also includes combining historical operation and maintenance data with real-time operation and maintenance data to predict system failures and potential performance bottlenecks.

6. The AIOps intelligent operation and maintenance method based on artificial intelligence technology according to claim 5, characterized in that: The process of optimizing resource allocation and fault handling based on the first algorithm includes optimizing dynamic allocation of system resources based on analysis results.

7. The AIOps intelligent operation and maintenance method based on artificial intelligence technology according to claim 6, characterized in that: The process of optimizing resource allocation and fault handling based on the first algorithm also includes generating a solution according to the predicted fault condition and performing repairs through scripts or artificial intelligence.

8. A system using an AIOps intelligent operation and maintenance method based on artificial intelligence technology as described in any one of claims 1 to 7, characterized in that: Including monitoring and processing module, analysis and prediction module, and process optimization module; The monitoring and processing module is used to perform real-time monitoring and data processing on the system status through a first algorithm; The analysis and prediction module is used to analyze the association between components and predict faults through the knowledge graph; The process optimization module is used to optimize resource allocation and fault handling processes based on a first algorithm.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of an AIOps intelligent operation and maintenance method based on artificial intelligence technology described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of an AIOps intelligent operation and maintenance method based on artificial intelligence technology described in any one of claims 1 to 7 are implemented.

Images