Service management and monitoring processing method and device based on intelligent data driving and terminal

Abstract

The invention discloses a service management and monitoring processing method and device based on intelligent data driving and a terminal. The method comprises the following steps: acquiring multi-source data in real time; dynamically adjusting a monitoring index threshold value of each type of data; key features are automatically extracted from the multi-source data; identifying a normal operation mode and an abnormal condition; based on the extracted key features and the identified normal operation mode and abnormal condition, automatically drawing a dependency relationship graph of the system architecture and the interactive service among the components, and generating a service link graph; and when the system architecture recorded by the generated service link diagram and the interaction service data of the interaction service among the components exceed the corresponding monitoring index threshold, automatically triggering the automatic repair response operation of the corresponding service threshold exceeding event. According to the method, the workload of manual configuration and debugging is remarkably reduced, manual intervention is reduced, and the operation and maintenance efficiency is improved; and service abnormity can be detected and responded in time, a time window for problem solving is shortened, and response efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of information data application technology, and in particular to a service management and monitoring processing method, device, intelligent terminal and storage medium based on intelligent data drive. Background Art

[0002] Existing technologies for service management and monitoring primarily rely on manually set preset rules and thresholds to detect and respond to system state changes. Administrators must manually set alert conditions based on historical experience and expected behavior, and manually adjust configurations to address environmental changes. This existing approach has limitations when dealing with complex and dynamic service environments, particularly when dealing with large-scale distributed systems and service link tracking. Frequent manual adjustments increase operational costs and slow response times.

[0003] Therefore, the existing technology still needs to be improved and developed. Summary of the Invention

[0004] The technical problem to be solved by the present invention is that, in view of the limitations of existing technologies in processing complex and dynamic service environments, especially in the face of large-scale distributed systems and service link tracking, frequent manual adjustments increase operation and maintenance costs and reduce response speed, a service management and monitoring processing method, device, intelligent terminal and storage medium based on intelligent data drive are provided.

[0005] The technical solutions adopted by the present invention to solve the problem are as follows: A service management and monitoring processing method based on intelligent data drive, which includes: A. Use real-time data stream processing technology to obtain multi-source data from various service components in real time; B. Preprocessing the multi-source data acquired in real time; dynamically adjusting the monitoring indicator thresholds of various types of data based on the preprocessed multi-source data and the historical trends of the multi-source data; C. Automatically extract key features from pre-processed multi-source data that are helpful for monitoring and service management using statistical methods and machine learning algorithms; identify normal operating modes and abnormal situations through the extracted key features; D. Based on the extracted key features and the identified normal operating modes and abnormal situations, the system architecture and the dependency diagram of the interactive services between components are automatically drawn, generating a service chain diagram. This is used to locate the source of problems, display the dependencies between services, and predict possible failures or performance bottlenecks in advance. E. Based on pre-configured automated operation rules, when the system architecture and interactive service data between components recorded in the generated service chain diagram exceed the corresponding monitoring indicator threshold, the automatic repair response operation of the corresponding service threshold-exceeding event is automatically triggered.

[0006] The intelligent data-driven service management and monitoring processing method, wherein the service components include: applications, databases and / or network devices; the multi-source data includes: log data, performance indicator data, user behavior data and / or network traffic data.

[0007] The intelligent data-driven service management and monitoring processing method, wherein the step of automatically drawing a dependency diagram of the system architecture and interactive services between components based on the extracted key features and the identified normal operation modes and abnormal conditions, and generating a service chain diagram further includes: According to the changes in service calls, the generated service link graph is automatically updated.

[0008] In the intelligent data-driven service management and monitoring processing method, the step of pre-processing the multi-source data acquired in real time includes: The multi-source data acquired in real time is cleaned to remove noise and invalid information; and the multi-source data from different sources is converted into standardized data in a specified format to obtain preprocessed multi-source data.

[0009] In the intelligent data-driven service management and monitoring processing method, the step of dynamically adjusting the monitoring indicator thresholds of various types of data based on pre-processed multi-source data and historical trends of the multi-source data further includes: Intelligently analyze the monitoring indicator thresholds of dynamically adjusted various types of data and verify the accuracy of alarms. The intelligent data-driven service management and monitoring processing method, wherein the steps of automatically triggering an automatic repair response operation for a corresponding service exceeding threshold event based on pre-configured automated operation rules when the system architecture and the interactive service data between components recorded in the generated service chain diagram exceed corresponding monitoring indicator thresholds include: Pre-configure automation operation rules; And pre-enter scripts that automatically trigger automatic repair response operations for corresponding service threshold-crossing events; Based on pre-configured automated operation rules, when the system architecture and interactive service data between components recorded in the generated service chain diagram exceed the corresponding monitoring indicator threshold, the script that controls the automatic repair response operation that triggers the corresponding service threshold-exceeding event is automatically executed to automatically perform the repair operation.

[0010] The intelligent data-driven service management and monitoring processing method further includes, before the step of using real-time data stream processing technology to obtain multi-source data from various service components in real time: Pre-acquire the configured monitoring indicator parameters of each multi-source data and the initial monitoring indicator threshold corresponding to each monitoring indicator parameter.

[0011] A service management and monitoring processing device based on intelligent data drive, wherein the device comprises: Multi-source data real-time acquisition module, used to acquire multi-source data from various service components in real time using real-time data stream processing technology; Data preprocessing module, used to preprocess multi-source data acquired in real time; An indicator threshold dynamic adjustment module, configured to dynamically adjust the monitoring indicator thresholds of various types of data based on pre-processed multi-source data and historical trends of the multi-source data; The feature extraction and recognition module uses statistical methods and machine learning algorithms to automatically extract key features from pre-processed multi-source data that are helpful for monitoring and service management. It also uses the extracted key features to identify normal operating modes and abnormal situations. The service chain visualization generation module is used to automatically draw the system architecture and the dependency diagram of the interactive services between components based on the extracted key features and the identified normal operation modes and abnormal situations, and generate a service chain diagram. It is used to locate the source of problems, display the dependency relationships between services, and predict possible failures or performance bottlenecks in advance. The automated response module is used to automatically trigger the automatic repair response operation of the corresponding service exceeding the threshold event based on pre-configured automated operation rules when the system architecture and the interactive service data between components recorded in the generated service chain diagram exceed the corresponding monitoring indicator threshold.

[0012] An intelligent terminal includes a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, including the method for executing any one of the methods described above.

[0013] A computer-readable storage medium, wherein when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform any one of the methods described above.

[0014] Beneficial effects of the present invention: The present invention provides a service management and monitoring processing method, device, intelligent terminal, and storage medium based on intelligent data drive. The present invention uses machine learning and big data analysis technologies to automatically extract features from massive amounts of service data and identify normal operating modes and abnormal situations. Furthermore, the present invention dynamically adjusts the thresholds of monitoring indicators based on real-time data streams and historical trends to ensure the accuracy and timeliness of alarms, significantly saving labor costs and improving work efficiency. Furthermore, the present invention has the following advantages: 1) Improved operation and maintenance efficiency and response efficiency: Through automated tools and intelligent algorithms, the workload of manual configuration and debugging is significantly reduced, human intervention is reduced, and operation and maintenance efficiency is improved; it can also detect and respond to service anomalies in a timely manner, shortening the time window for problem resolution and improving response efficiency.

[0015] 2) Enhanced reliability: Intelligent analysis and adaptive threshold setting ensure the accuracy and relevance of alarms, achieve precise monitoring, and reduce false alarms and missed alarms. The present invention can also implement preventive maintenance by predicting potential problems in advance and taking preventive measures, thereby reducing the risk of service interruptions and enhancing system stability.

[0016] 3) Data-driven decision-making can be achieved: The present invention makes full use of data, integrates and analyzes data from various service components, and provides a strong basis for optimizing resource allocation and service improvement; and the present invention continuously optimizes models and strategies based on feedback mechanisms, so that the system can self-improve and continuously optimize over time.

[0017] 4) It has strong flexibility and scalability; because the intelligent data-driven method of the present invention can flexibly respond to changes in the service environment, there is no need to frequently modify monitoring rules, and it has strong flexibility; and the present invention is easy to expand and supports multiple data sources and platforms, facilitating future expansion into new application scenarios and technology stacks.

[0018] 5) Improved security: The present invention combines AI technology to perform intelligent threat detection, which can identify atypical but potentially harmful behavior patterns and enhance the system's security protection capabilities. The present invention can also provide detailed audit records and reporting functions to help enterprises meet the requirements of industry regulations and standards. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] 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 description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 This is a flow chart of the service management and monitoring processing method based on intelligent data drive provided in Example 1 of the present invention.

[0021] Figure 2 This is a flow chart of the service management and monitoring processing method based on intelligent data drive provided in Example 2 of the present invention.

[0022] Figure 3 This is a service data workflow diagram of the service management and monitoring processing method based on intelligent data drive provided in Example 2 of the present invention.

[0023] Figure 4 This is a schematic diagram of the service data statistics process of the intelligent data-driven service management and monitoring processing method provided in Example 2 of the present invention.

[0024] Figure 5 A principle block diagram of an embodiment of a service management and monitoring processing device based on intelligent data drive provided by the present invention.

[0025] Figure 6 This is a block diagram of the internal structure of the smart terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the present invention more clear and distinct, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0027] Existing service management and monitoring technologies primarily rely on preset rules and thresholds to detect and respond to system status changes. Administrators must manually set alert conditions based on historical experience and expected behavior, and manually adjust configurations to address environmental changes. This existing approach presents the following problems: 1) Static rules lack flexibility: Preset monitoring rules cannot flexibly adapt to the rapidly changing service environment.

[0028] 2) Inefficient manual configuration: Frequent manual adjustments increase operation and maintenance costs and reduce response speed.

[0029] 3) Difficulty in capturing abnormal patterns: Monitoring methods based on fixed thresholds have difficulty identifying atypical but potential problems and are prone to missing early warning signals.

[0030] 4) Insufficient data utilization: Failure to fully utilize the large amount of logs and performance data generated during service operation for in-depth analysis and prediction.

[0031] like Figure 1As shown, a service management and monitoring processing method based on intelligent data drive in embodiment 1 of the present invention includes the following steps: Step S100: using real-time data stream processing technology to obtain multi-source data from various service components in real time; The service components include: applications, databases and / or network devices; the multi-source data include: log data, performance indicator data, user behavior data and / or network traffic data.

[0032] In this embodiment, multi-source data, including logs, performance metrics, and user behavior data, is collected from various service components (e.g., applications, databases, and network devices). This system supports multiple data formats and protocols to ensure comprehensive coverage. This system uses real-time data stream processing technologies, such as Apache Kafka or AWS Kinesis, for data collection to ensure immediacy and accuracy.

[0033] The real-time data stream processing technology used in the embodiments of the present invention is a method for processing and analyzing data streams, enabling data to be collected and processed immediately after it is generated, rather than waiting until the data is stored and then processed in batches. Real-time data collection and processing is achieved using stream processing frameworks such as Apache Kafka, Apache Flink, or Apache Spark Streaming.

[0034] In the embodiment of the present invention, each service component is specifically explained as follows: Among them, the application refers to software that implements specific functions and generates user behavior data and performance indicators.

[0035] The database stores and manages data and can provide accurate log data and performance indicators.

[0036] The network devices, such as routers and switches, can provide network traffic data and other related network performance indicators.

[0037] In the embodiment of the present invention, the collected multi-source data includes: The log data is used to record detailed information about system operation and user activities to assist in troubleshooting and system monitoring.

[0038] The performance indicators include application response time, CPU usage, etc., which reflect the health status of the system.

[0039] The user behavior data is used to record the user's operations in the application and analyze user preferences and behavior patterns.

[0040] The network traffic data provides information about network usage, such as packet flow and bandwidth usage, which helps monitor network performance and security.

[0041] In embodiments of the present invention, because data is processed in real time, rapid responses to market changes, user needs, or system anomalies are possible. Rapid data acquisition and analysis enable organizations to make more accurate and timely decisions. Furthermore, the present invention integrates data from diverse sources to identify issues and potential opportunities, thereby optimizing operational efficiency and improving effectiveness. Furthermore, by monitoring network traffic and log data in real time, the present invention enables timely detection and response to security threats.

[0042] In short, adopting this technology and multi-source data will bring greater flexibility and responsiveness, helping organizations maintain their advantage in a highly competitive market.

[0043] Of course, when the present invention is implemented, it can be expanded to support more data sources. For example, in addition to logs and performance data, user behavior data, network traffic data, etc. can also be integrated to provide more dimensional information for service management.

[0044] Step S200: pre-processing the multi-source data acquired in real time; dynamically adjusting the monitoring indicator thresholds of various types of data based on the pre-processed multi-source data and the historical trends of the multi-source data; In an embodiment of the present invention, multi-source data acquired in real time is cleaned to remove noise and invalid information; and multi-source data from different sources is converted into standardized data in a specified format to obtain preprocessed multi-source data. The preprocessing includes data cleaning, data conversion, data normalization, etc. Data cleaning involves removing duplicate, noisy, and incomplete data from the multi-source data acquired in real time. Data conversion unifies data in different formats or units into an analyzable format. Data normalization standardizes data values so that data from different sources can be directly compared. For example, temperature can be converted from Fahrenheit to Celsius.

[0045] In embodiments of the present invention, monitoring indicator thresholds are dynamically adjusted. After data preprocessing is complete, these thresholds are adjusted based on historical trends in multi-source data. Specifically, the present invention relies not only on current data but also analyzes trends in historical data to develop reasonable monitoring standards. Preprocessed data is used to analyze and monitor system operating status in real time. Indicator thresholds are then automatically and dynamically adjusted based on historical trends, such as seasonal variations and market fluctuations. For example, in power load monitoring, winter may lead to increased load, and the system can automatically adjust the overload alarm threshold.

[0046] For example, consider a smart city's traffic monitoring system, which acquires real-time data from various traffic sensors (such as cameras and ground sensors). Using the method presented in this paper, the multi-source data can be preprocessed to remove invalid or interfering signals and consolidated into a consistent data format. Furthermore, the present invention can dynamically adjust traffic flow monitoring thresholds based on daily peak hours (e.g., 8-9 a.m. and 5-6 p.m.). For example, the sensitivity of accident alerts can be increased during peak hours, prompting traffic management departments to take timely action. This approach enables more intelligent operations, reduces congestion and accidents, and improves the travel experience for citizens.

[0047] As can be seen, preprocessing in this step ensures data accuracy and reliability, reduces the impact of erroneous data on decision-making, and improves data quality. Furthermore, by dynamically adjusting the threshold, the system can more effectively respond to changes, improving response speed and accuracy.

[0048] In a further embodiment, step S200 specifically further includes: S201: Pre-acquire the configured monitoring indicator parameters of each multi-source data and the initial threshold value of the monitoring indicator corresponding to each monitoring indicator parameter; This step is to determine and obtain the relevant indicator parameters of the multi-source data to be monitored, including: Monitoring indicator parameters: These are specific parameters related to the data source, such as temperature, humidity, flow, pressure, etc., depending on the specific application scenario that needs to be monitored.

[0049] Initial thresholds: Set an initial threshold for each monitoring indicator for use in data monitoring and real-time analysis. These thresholds are typically based on industry standards, historical data, or expert advice.

[0050] By clearly defining monitoring indicators and their initial thresholds, we ensure that subsequent data processing and analysis have clear goals and standards. Furthermore, reasonable initial thresholds can reduce false positives and false negatives at system startup, improving the reliability of the monitoring system.

[0051] S202: Dynamically adjust monitoring indicator thresholds for various types of data based on pre-processed multi-source data and historical trends of the multi-source data; In this embodiment, the acquired, pre-processed multi-source data and its historical trends are analyzed to adjust the thresholds of the monitoring indicators. This process includes: historical data analysis: By analyzing the changing trends of historical data, normal fluctuations and potential anomalies are identified. Then, dynamic adjustment is performed: based on these analysis results, the thresholds are adjusted in real time or periodically to ensure that the monitoring system can operate effectively in different time periods and environmental conditions.

[0052] In this step, real-time threshold adjustments allow the system to adapt to changes in the environment and usage patterns, improving monitoring effectiveness. By taking historical data into account, the accuracy of monitoring indicators is improved, reducing the possibility of false positives and false negatives.

[0053] S203. Perform intelligent analysis on the monitoring indicator thresholds for dynamically adjusting various types of data and verify the accuracy of the alarm. In this embodiment, the acquired, pre-processed multi-source data and its historical trends are analyzed to adjust the thresholds of the monitoring indicators. Specifically, by analyzing the changing trends of historical data, normal fluctuations and potential anomalies are identified. Based on these analysis results, the thresholds are then adjusted in real time or periodically, achieving dynamic adjustment to ensure the effective operation of the monitoring system in different time periods and environmental conditions.

[0054] In this step, real-time threshold adjustments enable the system to adapt to changes in the environment and usage patterns, improving monitoring effectiveness. Furthermore, by considering historical data, the accuracy of monitoring indicators is improved, reducing the possibility of false positives and missed negatives.

[0055] S203: Perform intelligent analysis on the monitoring indicator thresholds for dynamically adjusting various types of data and verify the accuracy of the alarms; In this step, machine learning or other intelligent algorithms are also used to analyze the dynamically adjusted monitoring indicators. This involves pattern recognition of the current monitoring data to identify anomalies, trends, and potential issues. The effectiveness of the dynamically adjusted thresholds is verified by comparing actual monitoring results with pre-set alerts. The effectiveness of the new thresholds can be confirmed by backtesting historical data.

[0056] Thus, through intelligent analysis, the present invention can better identify potential problems and respond effectively, while also ensuring that the system reliably issues alarms by verifying the accuracy of thresholds, thereby improving the overall performance of the monitoring system.

[0057] Step S300: Utilize statistical methods and machine learning algorithms to automatically extract key features that are helpful for monitoring and service management from pre-processed multi-source data; and identify normal operating modes and abnormal situations through the extracted key features. In embodiments of the present invention, data feature extraction can utilize statistical methods (e.g., principal component analysis, feature selection) and machine learning algorithms (e.g., decision trees, random forests) to filter out the most representative and informative features from large amounts of data. These features can be numerical (e.g., product sales volume, production efficiency, etc.) or categorical (e.g., drug type, supplier classification, etc.).

[0058] Based on the extracted key features, a model is then built to identify normal operating patterns (i.e., data behavior under normal conditions) and anomalies (i.e., data points that deviate from normal patterns). This can be achieved using methods such as cluster analysis and time series analysis.

[0059] For example, a pharmaceutical company, using this invention in its data management and monitoring system, can extract data features: Application scenario: During the production process, the company monitors multiple indicators in real time, such as production line temperature, pressure, humidity, and raw material usage. Using principal component analysis, the company processes this multi-source data and extracts a few key features, such as "production efficiency" and "equipment failure rate," rather than processing hundreds of raw data points.

[0060] Then perform pattern recognition: Regarding normal patterns: Based on production data over the years, the pharmaceutical company can define a normal production efficiency range (such as producing X units of drug per hour).

[0061] Regarding abnormal situations: If the system monitoring detects that the production efficiency suddenly drops to half of the normal value, the system of the present invention can automatically identify this abnormality and remind the management personnel to take measures through the preset alarm mechanism, such as checking equipment failure or raw material problems.

[0062] Thus, the method of the present invention utilizes statistical methods and machine learning algorithms to efficiently extract key monitoring features from complex multi-source data and use these features to identify normal operating patterns and potential abnormalities. This approach not only accelerates data analysis but also improves the intelligence level of production management, ultimately achieving business optimization and risk management.

[0063] As can be seen in this step embodiment, by automatically extracting key features, the time required for manual selection and analysis is reduced, data processing efficiency is improved, and large-scale data analysis becomes feasible. Furthermore, identifying normal operating modes helps understand what is considered normal, while timely identification of abnormal conditions enables decision makers to take swift action to mitigate potential risks. Furthermore, the present invention utilizes statistical and machine learning methods to enhance understanding of complex data sets. Automated feature extraction and pattern recognition processes can reduce human bias, thereby improving the overall monitoring accuracy of the system.

[0064] Step S400: Based on the extracted key features and the identified normal operating modes and abnormal situations, a dependency diagram of the system architecture and the interactive services between components is automatically drawn to generate a service chain diagram. This diagram is used to locate the source of the problem, display the dependency relationships between services, and predict possible failures or performance bottlenecks in advance. In the embodiment of the present invention, the extracted key features and the identified normal operation modes and abnormal situations are used to automatically generate a system architecture diagram and a service interaction dependency diagram between components.

[0065] During this step, key characteristics and operating modes are applied. As data analysis results become more fully understood, key characteristics will serve as an important basis for constructing the system architecture diagram. Identifying operating modes helps clarify which components will behave predictably under normal operation, thereby forming dependencies between services.

[0066] When generating dependency graphs, visualization tools and graph algorithms can be used to automatically map the interactions and dependencies between service components, making complex service networks more intuitive and understandable. These graphs show the input and output relationships of each service and the interactions between them, forming a complete service chain diagram.

[0067] In embodiments of the present invention, once a service chain diagram is generated, it is easier to locate the source of potential problems. For example, if the performance of a service degrades, other services that depend on it may be affected. By monitoring these dependencies and changes in key characteristics, the present invention can predict potential failures or performance bottlenecks in advance, allowing timely intervention.

[0068] For example, taking the application of the present invention by a pharmaceutical company as an example, in its drug production and management system, the dependency graph of related services and components can bring significant benefits.

[0069] Regarding generating a service chain diagram: During the drug production process, the pharmaceutical company uses multiple service components, such as "raw material management," "production scheduling," "quality inspection," and "shipping system." By extracting the key business features of these components (such as production cycle, inspection standards, etc.), a dependency diagram between services can be automatically drawn. Then, regarding locating the source of the problem, it can be assumed that quality issues occurred in a certain production batch. Through the service chain diagram, the team can quickly view the dependency relationship between the "quality inspection" service and the "production scheduling" service, and find that the "production scheduling" service caused problems in the production process due to delays in raw materials.

[0070] Regarding fault prediction applications, let's assume the system detects a continuous increase in the response time of the "Quality Inspection" service. This can be clearly identified through a dependency graph to the related "Production Scheduling" service. The system can then issue an early warning, alerting managers to the potential impact on production line efficiency, allowing them to proactively adjust raw material supply plans.

[0071] By automatically generating a service dependency graph based on extracted key features and identified operational patterns and anomalies, the pharmaceutical company can effectively locate the source of problems, visualize interactions between services, and predict potential system failures in advance. This not only improves production management efficiency but also provides a crucial guarantee for the company's operational stability and quality control.

[0072] In embodiments of the present invention, by generating a dependency graph, the relationships between various components can be clearly displayed. In the event of a failure, the affected services can be quickly identified, reducing troubleshooting time. Furthermore, through the intuitive service link map, administrators can quickly understand the system architecture and its operation, and measure the contribution of each component to the overall service. Preemptively identifying potential bottlenecks and failure areas in the system allows enterprises to implement preventative measures, thereby improving system reliability and stability and reducing maintenance costs. By drawing a dependency graph between services, the present invention helps administrators intuitively understand the system architecture and the interactions between components.

[0073] Furthermore, in an embodiment of the present invention, the method further includes: automatically updating the generated service link diagram according to changes in service calls. That is, in an embodiment of the present invention, the link diagram is automatically updated as service calls change to maintain its timeliness.

[0074] Step S500: Based on the pre-configured automated operation rules, when the system architecture and the interactive service data between components recorded in the generated service chain diagram exceed the corresponding monitoring indicator threshold, the automatic repair response operation of the corresponding service exceeding the threshold event is automatically triggered.

[0075] In embodiments of the present invention, preconfigured automated operating rules may be predefined and configured to monitor and respond to the performance and health of various components in the system. These rules may include threshold settings that specify tolerance ranges for certain performance indicators (e.g., response time, error rate, etc.).

[0076] The service link diagram automatically generated in the previous step of the present invention maps out the system architecture and the interdependencies between components, which can help administrators understand how various services interact with each other.

[0077] Specifically, when the service data collected by the monitoring system exceeds a predefined threshold (for example, the service response time exceeds the set 2 seconds), a potential problem will be identified.

[0078] Regarding the automatic triggering of cross-threshold events, in embodiments of the present invention, once a service metric is found to have exceeded a threshold, an cross-threshold event is automatically identified and triggered, indicating that a service or component may be experiencing a failure or performance degradation. Upon confirming the cross-threshold event, the present invention executes predefined repair actions and performs automatic repair response operations, such as automatically restarting the service, adjusting resource allocation, or switching to a backup server to restore service performance.

[0079] For example, taking an e-commerce platform as an example, there are multiple components in the service architecture of the e-commerce platform, including user interface, payment service, inventory management, etc. After using the present invention, monitoring indicators are configured on the platform, including: the response time of the payment service cannot exceed 2 seconds, and the error rate of inventory management cannot exceed 1%. In specific implementation, if the monitoring system finds that the response time of the payment service reaches 3 seconds, which exceeds the set threshold, the system will automatically: trigger an over-threshold event: record this event, and notify relevant personnel. And perform automatic repair operations: for example, it will control the automatic restart of the payment service; and control the increase of processor resources for the payment service or switch traffic to a backup payment service instance. It can be seen that through this automation mechanism, the e-commerce platform can quickly respond to potential failures, thereby ensuring the continuity of user experience and the stability of the service.

[0080] It can be seen that the present invention can quickly respond to events that exceed the threshold and repair problems before or immediately, thereby reducing downtime and user impact. Automated operations also reduce reliance on manual monitoring and response, reduce the risk of human error, and free up the time of the operations team, allowing them to focus on other strategic tasks. Furthermore, the present invention can monitor service status in real time, report and handle problems in a timely manner, and improve the ability to respond to failures. Furthermore, the present invention can optimize resource utilization: automated repair operations can dynamically adjust resource allocation based on system load, improving overall resource utilization.

[0081] In a further embodiment, step S500 specifically includes: S501, pre-configure automated operation rules; In this embodiment of the present invention, automated operation rules are pre-configured. These rules define how to monitor and manage various components in the system. These rules include performance thresholds, service dependencies, trigger conditions, and more. This ensures that the system can monitor service status in real time and automatically respond based on the defined criteria.

[0082] S502, and pre-entering a script for automatically triggering an automatic repair response operation corresponding to a service exceeding a threshold event; In this step, specific automated scripts are entered into the system. These scripts are designed to execute remediation actions when monitored service metrics exceed predefined thresholds. For example, these scripts might automatically restart services, scale resources, or send alert notifications, thereby achieving a higher level of automation by combining multiple operational steps. The present invention provides specific operational instructions to ensure that remediation measures are automatically implemented when problems arise, reducing manual intervention and response time.

[0083] S503. Based on pre-configured automated operation rules, when the system architecture and the interactive service data between components recorded in the generated service chain diagram exceed the corresponding monitoring indicator threshold, the script that controls the automatic repair response operation that triggers the corresponding service threshold-exceeding event is automatically executed to automatically perform the repair operation.

[0084] During the monitoring process, this invention automatically triggers a related over-threshold event when the interaction data for each component recorded in the generated service chain diagram exceeds the set monitoring indicator threshold. This mechanism invokes the previously entered automatic repair operation script and executes the corresponding repair steps. This is intended to automate the repair operation, ensure rapid restoration of normal system operation, reduce the need for manual intervention, and thus improve system stability and availability.

[0085] Through these three steps, the present invention enables automated operations and maintenance management. When service performance exceeds a preset threshold, not only is the issue promptly detected and recorded, but appropriate remedial measures can also be quickly and accurately implemented, ensuring efficient and stable system operation. This automated approach is crucial for improving an enterprise's service quality and responsiveness.

[0086] As can be seen from the above, the present invention also has the following advantages: 1) Specifically, there is an intelligent data analysis engine: it uses machine learning and big data analysis technologies to automatically extract features from massive service data and identify normal operating modes and abnormal situations.

[0087] 2) Dynamic setting of adaptive thresholds can be achieved: based on real-time data streams and historical trends, the thresholds of monitoring indicators can be dynamically adjusted to ensure the accuracy and timeliness of alarms.

[0088] 3) Predictive maintenance can be achieved: through continuous monitoring and analysis of service performance, possible failures or performance bottlenecks can be predicted in advance and preventive measures can be taken.

[0089] 4) It can realize service chain visualization: providing an intuitive service chain diagram to help administrators quickly locate the source of the problem and understand the dependencies between services.

[0090] 5) Automated response mechanism: Integrated automation tools can automatically perform repair operations after detecting specific events, reducing manual intervention.

[0091] The present invention is further described in detail below through another specific application embodiment. This specific application embodiment provides a service management and monitoring processing method based on intelligent data drive, such as Figure 2 As shown, without increasing the workload of developers, the data script publishing process, algorithm annotation, data set training process, and service publishing process can be connected to the Ai Platform (a platform for artificial intelligence and machine learning services) data presentation to complete the seamless connection of the R&D process and realize automatic data connection. Figure 2 As shown, data development (local development) publishes data table structures through the operations and maintenance release platform, which then undergoes automatic data synchronization and connects to the Ai Platform (a platform for artificial intelligence and machine learning services) for data presentation. Data annotation and data training on the data annotation platform also involve publishing datasets through the operations and maintenance release platform, which then undergoes automatic data synchronization and connects to the Ai Platform (a platform for artificial intelligence and machine learning services) for data presentation. Software development (local development) also publishes algorithms through the operations and maintenance release platform, which then undergoes automatic data synchronization and connects to the Ai Platform (a platform for artificial intelligence and machine learning services) for data presentation. Service development (GitLab management) also publishes services through the operations and maintenance release platform, which then undergoes automatic data synchronization and connects to the AiPlatform (a platform for artificial intelligence and machine learning services) for data presentation.

[0092] In an embodiment of the present invention, a data monitoring and early warning capability is provided. When data changes exceeding preset values occur, messages are proactively pushed to designated personnel, and a real-time monitoring dashboard is provided to allow attention to abnormal or substandard data situations and to follow up and improve related work in a timely manner.

[0093] In the embodiment of the present invention, a data view can be implemented. Under the data view, changes in association tables and association algorithms can be observed, and details of associated contents can be viewed through the data view.

[0094] A data view is a visual interface or tool that aggregates and displays information from various data sources. This view allows users to more intuitively understand the relationships and structures between data. Regarding observing changes in association tables: Association tables display relationships between data, potentially including correlations, dependencies, or other statistical relationships between different variables. In a data view, users can observe changes in these association tables in real time, such as data updates, pattern recognition, or trend analysis, to understand how individual variables influence each other.

[0095] Regarding observing changes in association algorithms: Association algorithms are used to analyze patterns and relationships in datasets. Common examples include association rule learning (such as the Apriori algorithm and the FP-Growth algorithm). Data views allow users to monitor the performance and results of these algorithms, understanding which algorithms perform better on specific datasets or how parameter adjustments affect results.

[0096] Drill-down allows users to drill down to more detailed information within a data view. This means users can click or select a data point or relationship to view detailed information, such as the specific value, calculation method, or related data context. This in-depth analysis helps users gain a more comprehensive understanding of the data.

[0097] As can be seen, the steps in this embodiment describe a feature-rich data view that not only provides an overall view of data relationships but also allows users to delve into the details of the data. This is crucial for data analysis, decision support, and discovering potential insights. In this way, users can better understand and utilize data, leading to more informed decisions.

[0098] The embodiment of the present invention can also implement an algorithm view. Under the algorithm view, changes in the data tables used by the algorithm and the services to which the algorithm is applied can be observed, and details of related content can be viewed through it.

[0099] The algorithm view is a visual interface designed to display data and services related to a specific algorithm. This view can help users better understand the application effect of the algorithm and its performance in actual business.

[0100] Regarding observing the data tables used by an algorithm, in the algorithm view, users can view the data tables associated with the algorithm. This includes the source, structure, and content of the data used. For example, a data table might include the features processed by the algorithm, the distribution of data samples, and real-time data changes. By observing these data tables, users can understand the data upon which the algorithm is basing its modeling and predictions.

[0101] In this embodiment, the algorithm view can also display changes in the services that use the algorithm. For example, an online recommendation system may use a new recommendation algorithm. The algorithm view can show the impact of the algorithm on metrics such as recommendation results, user click-through rate, and conversion rate. Monitoring these changes can help evaluate the effectiveness of the algorithm and identify optimization directions.

[0102] Penetration viewing allows users to delve deeper into the details of a specific data point or service within the algorithm view. For example, clicking on a service change reveals more information about how the algorithm impacted the service's specific metrics, the underlying calculation logic, and the data supporting the change. This in-depth analysis allows users to more fully understand the actual application and impact of the algorithm.

[0103] It can be seen that this step embodiment describes an integrated algorithm view that can help users: observe and analyze data tables related to the algorithm, monitor performance changes of services that apply the algorithm, and gain in-depth understanding of detailed information on related content.

[0104] Furthermore, the embodiment of the present invention can also implement a service view. Under the service view, changes in the algorithms used by the service and the interfaces referenced by the service can be observed, and details of the associated content can be viewed through it.

[0105] In this embodiment, the service view is a visual interface that displays key information such as the running status of a specific service, the algorithms used, and the referenced interfaces. This view can help users quickly understand the overall situation of the service and its relationship with other components.

[0106] In this embodiment, the service view allows users to view the algorithms associated with a service. This includes the algorithm type and version used by the service, as well as the algorithm's performance metrics. For example, if a service uses a machine learning algorithm for data processing, the service view can display information such as the algorithm's name, training status, and accuracy, helping users understand the algorithm's role and impact within the service.

[0107] In this embodiment, services typically call interfaces of other services or systems during runtime. In the service view, users can observe changes in these referenced interfaces, such as their response time, availability, and call frequency. This information helps users monitor the interaction between services and external systems and identify potential performance bottlenecks or interface failures.

[0108] Regarding drill-down viewing of associated content, drill-down viewing allows users to drill down into the details of a specific algorithm or interface within the service view. This means users can click or select an algorithm or interface to obtain more detailed information, such as specific call parameters, algorithm input and output data, and key steps in its processing. This in-depth analysis enables users to fully understand the internal mechanisms and operational processes of the service, thereby optimizing service performance.

[0109] In this embodiment, a comprehensive service view is described, which can help users observe and analyze the algorithms used by services, monitor the called interfaces and their changes, and gain in-depth understanding of the specific details of related content.

[0110] Through this service view, users can better understand the service implementation process, algorithm effects and interface health, providing important insights for optimizing services and improving the overall performance of the system.

[0111] like Figure 3 As shown, the service data workflow of a service management and monitoring processing method based on intelligent data drive in this specific application embodiment includes the following steps: S10, start configuration and go to step S11; In this embodiment, this step is the starting point of the entire service data workflow. At this point, the user or system is ready to configure data, including setting goals and confirming the type and scope of data to be configured. This step ensures that the user is clear about the direction and goals of the configuration, laying the foundation for the smooth progress of subsequent steps.

[0112] S11: Data source configuration, and proceeds to step S12; In this step, the user selects and configures a data source. Data sources can be various databases, file systems, or online APIs, providing the data needed by the service. For example, the user might configure data extraction from a relational database or specify information acquisition from an external service. This ensures the system knows where to obtain the required data, preparing it for subsequent data processing and analysis.

[0113] S12: Data table configuration and enter S13; In this embodiment, this step involves the specific configuration of data tables. Here, the user defines which data tables will be used, including their structure, field names, data types, and other information. The user can also configure the relationships between data tables. By setting the structure and properties of the data tables, this step ensures that the data is stored in a logically reasonable format within the database, facilitating subsequent access and analysis.

[0114] S13: indicator configuration and enter S14; In this step, users configure metrics for measuring and evaluating data. This includes defining key performance indicators (KPIs) and data analysis metrics (such as average, maximum, and minimum values). These metrics will be used to monitor data performance and ensure that the service achieves its intended business objectives. This step, through clear metric configuration, helps users effectively track and measure service performance during data analysis and decision-making.

[0115] S14: Configuration completed; This step indicates that all configuration steps have been successfully completed. At this point, you can save the configuration, and the system will begin running the data service according to the configuration, officially entering the data processing and analysis phase. This step ensures that the entire configuration process is complete and prepares for subsequent operations (such as data processing and report generation).

[0116] The service data workflow described in the preceding steps can help users step through the configuration process, from data source selection to indicator settings. By clarifying the purpose of each step, you can ensure that the final service can successfully acquire, process, and analyze data, thereby achieving the established business goals.

[0117] S20: Timing start and enter S21; This step marks the beginning of the entire scheduled workflow. At the scheduled time, the system automatically initiates the data processing process, preparing to execute subsequent tasks. This scheduled initiation can be based on a specific time interval (e.g., daily, hourly) or a specific event (e.g., after a system reboot). This ensures that data processing automatically begins at the scheduled time, reducing manual intervention, improving system automation, and ensuring the continuity of business processes.

[0118] S21: Scan indicator configuration and enter S22; In this step, the system scans and checks previously configured metrics; that is, it assesses which metrics need to be calculated, monitored, or updated to ensure their applicability within the current dataset. This phase involves a quick check of the data source to confirm data integrity and accuracy. This step ensures that all monitoring metrics are correctly captured before data processing, preventing errors and ensuring that subsequent data analysis accurately reflects the real-world situation.

[0119] S22: Statistics are stored in the database and the process goes to S23; In this step, statistical analysis is performed on previously scanned metrics and the results are stored in a database. This includes data processing, calculations, and summaries, such as calculating averages, finding maximum and minimum values, or generating other key performance indicators (KPIs). The final statistical results are stored as a new record in the database, facilitating subsequent query and analysis. This step ensures that all key metric data is updated and stored in a timely manner, providing accurate data support for subsequent analysis, report generation, and decision-making.

[0120] S23: Timing ends; This step concludes the entire scheduled data processing process. After the statistics storage operation is complete, the present invention stops the current processing task and enters the next cycle. At this point, the user may receive a notification of the completion of the operation, or the system will automatically prepare for the next scheduled start. This step marks the end of scheduled data processing, preparing for the next scheduled task or manual operation, and ensuring the rational use of system resources.

[0121] The above-described scheduled data processing and statistics workflow achieves automated data monitoring and statistical analysis through a series of orderly steps. Through scheduled startup, indicator scanning, data statistics storage, and scheduled termination, the system ensures efficient operation and helps enterprises acquire and analyze data in real time, thereby supporting better decision-making and business optimization.

[0122] S30: observe data and enter S31; In this step, the system or user begins observing and monitoring data. This can include viewing real-time data streams, monitoring data trends, or checking the health of specific datasets. This step ensures timely access to required information, preparing for subsequent indicator review and data analysis.

[0123] S31: Check the indicators and enter S32; In this step, users will begin reviewing previously defined key performance indicators (KPIs) or other relevant metrics. These metrics are used to assess the current state of data, system performance, or business performance. Users can access data for these metrics using charts or other visualization tools. By reviewing these metrics in this step, users can identify potential issues or trends and make timely decisions and adjustments.

[0124] S32: View the data table, and enter S33 and S34; This step involves viewing a specific data table to obtain more detailed information. Users may use specific queries to retrieve data records from the database and analyze the content of each field, as well as the integrity and consistency of the data. Viewing the data table in this step can help users obtain more in-depth and detailed data, assisting in data analysis and data-based decision-making.

[0125] S33: Observation completed; In this step, after the observation and analysis are completed, the end of the observation process will be marked, indicating that the user has obtained the required information and all relevant data and indicators have been checked. This step ensures that the user can confirm the end of the observation process and prepare for further operations.

[0126] S34: DBA opens the communication, table change record is recorded; end; Content: During this phase, the DBA (database administrator) needs to record and communicate changes to the data tables. This may involve keeping a change log, recording modifications to the table structure, data entry operations, field updates, and more. This log will be used to track subsequent data updates and version management. Maintaining change records in this step ensures more standardized data management, facilitating subsequent auditing, analysis, and troubleshooting.

[0127] As can be seen, the data observation and monitoring workflow described above ensures effective data tracking and analysis through a series of orderly steps. This process involves real-time data monitoring, indicator analysis, data table review, and record-keeping by the database administrator. Ultimately, it ensures data reliability and traceability, supporting enterprises in making more informed decisions based on data.

[0128] like Figure 4 As shown, the service data statistics process of a service management and monitoring processing method based on intelligent data drive in this specific application embodiment includes the following steps: S40: Add indicators and enter S41; In this example, the user decides to add new metrics to an existing monitoring or analysis system. These metrics may be designed to assess new business requirements, performance standards, or data analysis objectives. This step, by adding new metrics, helps more comprehensively monitor system performance, business progress, or other key data points, ensuring timely responses to important changes.

[0129] S41: record the indicator configuration and proceed to S42; In this example, this step involves documenting the specific configuration of the newly added metric; this includes the metric's name, type, calculation method, threshold, and other relevant information. Recording this information ensures that team members can reference and use these metrics in the future. This step ensures that the newly added metric is clearly documented for subsequent maintenance, review, and use, increasing transparency.

[0130] S42: Create an XXL-Job task and enter S43; In this step, a new XXL-Job task is created based on user instructions to schedule or automate operations related to the new metric. For example, this task might periodically calculate the value of the new metric and update the results to a data warehouse or report. XXL-Job is a popular distributed task scheduling platform for managing microservices and backend tasks. This step automates the processing of the new metric by creating a scheduled task, reducing manual intervention and improving work efficiency. It also ensures that the new metric is updated on time and remains up-to-date.

[0131] S43: End; This step completes the creation and configuration of all tasks. Users can confirm that all new metrics and corresponding scheduled tasks have been correctly configured and are ready to move on to the next phase of work. This ensures a smooth completion of the entire process, paving the way for subsequent data monitoring and analysis, and provides a clear understanding of the next steps.

[0132] The above workflow for adding metrics and creating tasks follows a series of clear steps, helping users effectively add new monitoring metrics and integrate them into existing systems. By recording metric configurations and creating automated scheduling tasks, new metrics can be monitored and analyzed promptly and accurately, supporting more scientific and data-driven decision-making.

[0133] S50: Add state change and enter S51; In this step, we decided to introduce new state changes. These are specific events within a system component, task, or business process. State changes can include "Start," "Pause," "Complete," or "Error," which identify the current state of the process or task. Adding state changes in this step can help teams better track and manage the system's operational status, making the progress of each step clearer and providing a basis for subsequent analysis and decision-making.

[0134] S51: record the indication status and proceed to S52; This step involves documenting newly introduced status changes in detail. This may include the status name, specific meaning, change timestamp, responsible personnel, and other information. This record ensures convenient status tracing and troubleshooting. By documenting status changes in detail, this step ensures transparency and traceability, providing the necessary documentation so that the team can quickly identify issues and analyze the causes of status changes during subsequent work.

[0135] S52: Change the XXL-Job task status and enter S53; In this step, user commands are received to change the status of the associated XXL-Job task. This can include changing a task's status to "Failed," "Completed," or "Pending" to reflect its latest status. XXL-Job is a platform for distributed task scheduling, so timely task status updates ensure the accuracy of the task scheduling system and the proper functioning of its related functions. By promptly updating task status, this step ensures that all relevant personnel are aware of the current task's progress, avoiding potential misunderstandings or process stalls, thereby improving work efficiency.

[0136] S53: End; This step completes the process of adding, recording, and changing task statuses. Users can confirm that all changes have been recorded and updated, and are ready to move on to the next phase. This ensures a smooth workflow completion, provides the necessary data foundation for subsequent operations or analysis, and allows users to easily carry out subsequent tasks.

[0137] As you can see, the above state change management workflow helps users effectively manage and record system state changes through a series of clear steps. By adding state changes, recording detailed indications, and updating the status of related tasks, the system improves traceability and transparency, ensuring that teams can make timely and reasonable decisions based on accurate data when addressing issues and optimizing processes.

[0138] S60: Scheduled task execution and enter S61; In this embodiment, this step marks the automated start of a scheduled task; triggered at a predetermined time or when specific conditions are met, the task is scheduled for execution without manual intervention. Executing a scheduled task primarily involves retrieving the task to be run from a task list. This step automates scheduled task execution to improve work efficiency, ensuring that tasks are executed accurately at the designated time, and supporting the continued operation of the system and the smooth flow of business processes.

[0139] S61: The executor executes and enters S62; The executor (Task Executor or similar component) in this embodiment of the present invention begins processing the scheduled timed task. The executor is responsible for managing the execution of the task, including handling its status, monitoring the execution progress, and managing callbacks for task failure or success. This ensures that the task is effectively managed during execution and that its status is monitored in a timely manner to prepare for subsequent script execution.

[0140] S62: Execute the script and enter S63; This step is the core of task execution. The executor begins executing the specific script or program associated with the task. This involves database operations, data processing, data analysis, or other automated operations. The execution script is typically a set of predefined commands or functions that implement specific business logic. This step completes the intended operations by executing the script, ensuring that the task achieves its intended objectives and obtains the desired results or data.

[0141] S63: End.

[0142] This step indicates that the scheduled task has completed execution. Users can verify the results of the task by inspecting output, viewing logs, or monitoring task status. This step marks the successful conclusion of the workflow, ensuring that all tasks and subsequent processing have been successfully completed, providing a basis for possible subsequent actions or analysis.

[0143] As can be seen above, the scheduled task execution workflow in the specific embodiment of the present invention helps users automate task processing through a series of clear steps. Through scheduled task execution, executor management, and script execution, tasks are ensured to be completed successfully within the scheduled time, thereby improving the efficiency and effectiveness of business processing. This process has wide application in many automated systems and business scenarios.

[0144] Exemplary devices like Figure 5 As shown, an embodiment of the present invention provides a service management and monitoring processing device based on intelligent data drive, which includes: A multi-source data real-time acquisition module 310 is used to acquire multi-source data from various service components in real time using real-time data stream processing technology; The data preprocessing module 320 is used to preprocess the multi-source data acquired in real time; An indicator threshold dynamic adjustment module 330 is used to dynamically adjust the monitoring indicator thresholds of various types of data based on pre-processed multi-source data and historical trends of the multi-source data; Feature extraction and identification module 340 is used to automatically extract key features that are helpful for monitoring and service management from pre-processed multi-source data using statistical methods and machine learning algorithms; and identify normal operating modes and abnormal situations based on the extracted key features; The service chain visualization generation module 350 is used to automatically draw a dependency diagram of the system architecture and the interactive services between components based on the extracted key features and the identified normal operation modes and abnormal situations, and generate a service chain diagram. This is used to locate the source of problems, display the dependencies between services, and predict possible failures or performance bottlenecks in advance. The automated response module 360 is used to automatically trigger the automatic repair response operation of the corresponding service exceeding the threshold event based on pre-configured automated operation rules when the system architecture and the interactive service data between components recorded in the generated service chain diagram exceed the corresponding monitoring indicator threshold, as described above.

[0145] Based on the above embodiment, the present invention also provides an intelligent terminal, whose principle block diagram can be shown as follows: Figure 6As shown. The intelligent terminal includes a processor, a memory, a network interface, a display screen, and a database connected via a system bus. The processor of the intelligent terminal is used to provide computing and control capabilities. The memory of the intelligent terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the intelligent terminal is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a service management and monitoring processing method based on intelligent data driving is implemented. The database of the intelligent terminal is used to store a service management and monitoring processing program based on intelligent data driving.

[0146] Those skilled in the art will understand that Figure 6 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the solution of the present invention and does not constitute a limitation on the smart terminal to which the solution of the present invention is applied. The specific smart terminal may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0147] In one embodiment, a smart terminal is provided, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations: Adopt real-time data stream processing technology to obtain multi-source data from various service components in real time; Preprocessing multi-source data acquired in real time; dynamically adjusting monitoring indicator thresholds for various types of data based on the preprocessed multi-source data and historical trends of the multi-source data; Utilize statistical methods and machine learning algorithms to automatically extract key features from pre-processed multi-source data that are helpful for monitoring and service management. Identify normal operating patterns and abnormal situations through the extracted key features. Based on the extracted key features and the identified normal operating modes and abnormal situations, the system architecture and the dependency diagram of the interactive services between components are automatically drawn to generate a service chain diagram. This is used to locate the source of problems, display the dependencies between services, and predict possible failures or performance bottlenecks in advance. Based on pre-configured automated operation rules, when the system architecture and interactive service data between components recorded in the generated service chain diagram exceed the corresponding monitoring indicator threshold, the automatic repair response operation of the corresponding service exceeding the threshold event is automatically triggered.

[0148] The service components include: applications, databases and / or network devices; the multi-source data include: log data, performance indicator data, user behavior data and / or network traffic data.

[0149] The intelligent data-driven service management and monitoring processing method, wherein the step of automatically drawing a dependency diagram of the system architecture and interactive services between components based on the extracted key features and the identified normal operation modes and abnormal conditions, and generating a service chain diagram further includes: According to the changes in service calls, the generated service link graph is automatically updated.

[0150] In the intelligent data-driven service management and monitoring processing method, the step of pre-processing the multi-source data acquired in real time includes: The multi-source data acquired in real time is cleaned to remove noise and invalid information; and the multi-source data from different sources is converted into standardized data in a specified format to obtain preprocessed multi-source data.

[0151] In the intelligent data-driven service management and monitoring processing method, the step of dynamically adjusting the monitoring indicator thresholds of various types of data based on pre-processed multi-source data and historical trends of the multi-source data further includes: Intelligently analyze the monitoring indicator thresholds of dynamically adjusted various types of data and verify the accuracy of alarms. The intelligent data-driven service management and monitoring processing method, wherein the steps of automatically triggering an automatic repair response operation for a corresponding service exceeding threshold event based on pre-configured automated operation rules when the system architecture and the interactive service data between components recorded in the generated service chain diagram exceed corresponding monitoring indicator thresholds include: Pre-configure automation operation rules; And pre-enter scripts that automatically trigger automatic repair response operations for corresponding service threshold-crossing events; Based on pre-configured automated operation rules, when the system architecture and interactive service data between components recorded in the generated service chain diagram exceed the corresponding monitoring indicator threshold, the script that controls the automatic repair response operation that triggers the corresponding service threshold-exceeding event is automatically executed to automatically perform the repair operation.

[0152] The intelligent data-driven service management and monitoring processing method further includes, before the step of using real-time data stream processing technology to obtain multi-source data from various service components in real time: The configured monitoring indicator parameters of each multi-source data and the initial monitoring indicator threshold corresponding to each monitoring indicator parameter are obtained in advance, as described above.

[0153] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0154] In summary, the present invention provides a service management and monitoring processing method, device, intelligent terminal, and storage medium driven by intelligent data. It utilizes machine learning and big data analysis techniques to automatically extract features from massive amounts of service data and identify normal operating modes and abnormal situations. Furthermore, the present invention dynamically adjusts monitoring indicator thresholds based on real-time data streams and historical trends, ensuring the accuracy and timeliness of alerts, significantly saving labor costs and improving work efficiency. Furthermore, the present invention has the following advantages: 1) Improved operation and maintenance efficiency and response efficiency: Through automated tools and intelligent algorithms, the workload of manual configuration and debugging is significantly reduced, human intervention is reduced, and operation and maintenance efficiency is improved; it can also detect and respond to service anomalies in a timely manner, shortening the time window for problem resolution and improving response efficiency.

[0155] 2) Enhanced reliability: Intelligent analysis and adaptive threshold setting ensure the accuracy and relevance of alarms, achieve precise monitoring, and reduce false alarms and missed alarms. The present invention can also implement preventive maintenance by predicting potential problems in advance and taking preventive measures, thereby reducing the risk of service interruptions and enhancing system stability.

[0156] 3) Data-driven decision-making can be achieved: The present invention makes full use of data, integrates and analyzes data from various service components, and provides a strong basis for optimizing resource allocation and service improvement; and the present invention continuously optimizes models and strategies based on feedback mechanisms, so that the system can self-improve and continuously optimize over time.

[0157] 4) It has strong flexibility and scalability; because the intelligent data-driven method of the present invention can flexibly respond to changes in the service environment, there is no need to frequently modify monitoring rules, and it has strong flexibility; and the present invention is easy to expand and supports multiple data sources and platforms, facilitating future expansion into new application scenarios and technology stacks.

[0158] 5) Improved security: The present invention combines AI technology to perform intelligent threat detection, which can identify atypical but potentially harmful behavior patterns and enhance the system's security protection capabilities. The present invention can also provide detailed audit records and reporting functions to help enterprises meet the requirements of industry regulations and standards.

Claims

1. A service management and monitoring processing method based on intelligent data drive, characterized in that: include: Adopt real-time data stream processing technology to obtain multi-source data from various service components in real time; Preprocess multi-source data acquired in real time; Dynamically adjust monitoring indicator thresholds for various types of data based on pre-processed multi-source data and historical trends of the multi-source data; Automatically extract key features that are helpful for monitoring and service management from pre-processed multi-source data using statistical methods and machine learning algorithms; Identify normal operating modes and abnormal situations through extracted key features; Based on the extracted key features and the identified normal operating modes and abnormal situations, the system architecture and the dependency diagram of the interactive services between components are automatically drawn to generate a service chain diagram. This is used to locate the source of problems, display the dependencies between services, and predict possible failures or performance bottlenecks in advance. Based on pre-configured automated operation rules, when the system architecture and interactive service data between components recorded in the generated service chain diagram exceed the corresponding monitoring indicator threshold, the automatic repair response operation of the corresponding service exceeding the threshold event is automatically triggered.

2. The service management and monitoring processing method based on intelligent data drive according to claim 1 is characterized in that: in, The service components include: applications, databases and / or network devices; the multi-source data include: log data, performance indicator data, user behavior data and / or network traffic data.

3. The service management and monitoring processing method based on intelligent data drive according to claim 1 is characterized in that: The step of automatically drawing a dependency diagram of the system architecture and interactive services between components based on the extracted key features and the identified normal operation modes and abnormal situations, and generating a service chain diagram further includes: According to the changes in service calls, the generated service link graph is automatically updated.

4. The service management and monitoring processing method based on intelligent data drive according to claim 1 is characterized in that: The step of preprocessing the multi-source data acquired in real time includes: The multi-source data acquired in real time is cleaned to remove noise and invalid information; and the multi-source data from different sources is converted into standardized data in a specified format to obtain preprocessed multi-source data.

5. The service management and monitoring processing method based on intelligent data drive according to claim 1 is characterized in that: The step of dynamically adjusting the monitoring indicator thresholds of various types of data based on the pre-processed multi-source data and the historical trends of the multi-source data further includes: Intelligently analyze the monitoring indicator thresholds of dynamically adjusted various types of data and verify the accuracy of alarms.

6. The service management and monitoring processing method based on intelligent data drive according to claim 1 is characterized in that: The steps of automatically triggering an automatic repair response operation for a corresponding service exceeding threshold event based on pre-configured automated operation rules include: Pre-configure automation operation rules; And pre-enter scripts that automatically trigger automatic repair response operations for corresponding service threshold-crossing events; Based on pre-configured automated operation rules, when the system architecture and interactive service data between components recorded in the generated service chain diagram exceed the corresponding monitoring indicator threshold, the script that controls the automatic repair response operation that triggers the corresponding service threshold-exceeding event is automatically executed to automatically perform the repair operation.

7. The service management and monitoring processing method based on intelligent data drive according to claim 1 is characterized in that: The step of using real-time data stream processing technology to obtain multi-source data from various service components in real time also includes: Pre-acquire the configured monitoring indicator parameters of each multi-source data and the initial monitoring indicator threshold corresponding to each monitoring indicator parameter.

8. A service management and monitoring processing device based on intelligent data drive, characterized in that: The device comprises: Multi-source data real-time acquisition module, used to acquire multi-source data from various service components in real time using real-time data stream processing technology; Data preprocessing module, used to preprocess multi-source data acquired in real time; An indicator threshold dynamic adjustment module, configured to dynamically adjust the monitoring indicator thresholds of various types of data based on pre-processed multi-source data and historical trends of the multi-source data; The feature extraction and recognition module uses statistical methods and machine learning algorithms to automatically extract key features from pre-processed multi-source data that are helpful for monitoring and service management. It also uses the extracted key features to identify normal operating modes and abnormal situations. The service chain visualization generation module is used to automatically draw the system architecture and the dependency diagram of the interactive services between components based on the extracted key features and the identified normal operation modes and abnormal situations, and generate a service chain diagram. It is used to locate the source of problems, display the dependency relationships between services, and predict possible failures or performance bottlenecks in advance. The automated response module is used to automatically trigger the automatic repair response operation of the corresponding service exceeding the threshold event based on pre-configured automated operation rules when the system architecture and the interactive service data between components recorded in the generated service chain diagram exceed the corresponding monitoring indicator threshold.

9. An intelligent terminal, characterized in that: The device comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, and the one or more programs include being used to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 7.

Images