Computer intelligent service management system and method based on network big data

Abstract

The invention relates to the technical field of computers, and particularly discloses a computer intelligent service management system and method based on network big data, and the system comprises a data collection module which is used for collecting data of various sources through a self-adaptive data collection architecture, and the architecture carries out the dynamic data source management based on cloud and edge calculation, a multi-modal data fusion technology is combined to realize data docking and standardized processing among different sources; the intelligent analysis module is used for carrying out comprehensive mining and analysis on the collected data by adopting a deep learning algorithm and a big data analysis technology, identifying potential performance bottlenecks, service demand fluctuations and user behavior modes and generating an analysis report; according to the method, mass data can be processed and analyzed in real time, potential performance bottlenecks, service demand fluctuations and user behavior modes are identified, and automatic adjustment is performed according to real-time changes; through an adaptive scheduling engine and predictive analysis, resource allocation is accurately adjusted according to real-time feedback of user requirements and service performance.

Description

Technical Field

[0001] The present invention belongs to the field of computer technology, and particularly relates to a computer intelligent service management system and method based on network big data. Background Art

[0002] With the rapid development of information technology, especially the wide application of cloud computing, big data and artificial intelligence, the existing computer service management systems are facing increasing challenges. Due to the lack of effective processing capabilities for multiple data sources, the existing systems cannot accurately analyze and predict system performance, often failing to timely reflect the true state of the system, resulting in fluctuations in service quality and inefficient utilization of resources.

[0003] Currently, most resource scheduling in existing systems is based on static rules and cannot flexibly adjust resource allocation according to changes in system load. Especially when facing sudden high loads or demand fluctuations, the existing systems cannot make timely adaptive adjustments, easily leading to waste of resources or performance bottlenecks, thus affecting user experience and system operation efficiency. In addition, the decision-making process of existing service management systems often relies on empirical rules and lacks sufficient intelligent support. In practical applications, the systems can often only handle simple situations, and for complex and dynamically changing requirements, they often cannot provide efficient and optimized service decisions. In many service management systems, user feedback is often not fully utilized and cannot timely reflect changes in user behavior or actual user needs. The lack of a mechanism for dynamic adjustment and optimization makes it often impossible to improve service quality and system performance and continuously optimize them.

[0004] Therefore, it is necessary to propose a computer intelligent service management system and method based on network big data to solve the problem in the prior art of how to adjust resource allocation in real time in a complex and changeable environment and maintain high standards of service quality. Summary of the Invention

[0005] The purpose of the present invention is to provide a computer intelligent service management system and method based on network big data to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] A computer intelligent service management system based on network big data, comprising:

[0008] A data collection module, configured to collect data from multiple sources through an adaptive data acquisition architecture. The architecture is based on cloud and edge computing for dynamic data source management, and combines multi-modal data fusion technology to achieve data docking and standardization processing between different sources;

[0009] An intelligent analysis module, which is used to comprehensively mine and analyze the collected data by using deep learning algorithms and big data analysis techniques, identify potential performance bottlenecks, service demand fluctuations and user behavior patterns, and generate an analysis report;

[0010] A service quality monitoring module, which is used to adopt an adaptive monitoring strategy to monitor various service quality indicators in real time, automatically detect system anomalies or performance degradation according to the real-time monitoring data, and trigger an automatic adjustment mechanism;

[0011] An automated scheduling module, which is used to automatically schedule computer resources according to the analysis report and real-time monitoring data, dynamically adjust the allocation of service resources in combination with data changes, predict service demands by using deep learning algorithms, and achieve automatic optimal scheduling of service resources;

[0012] A service decision-making module, which is used to continuously optimize the scheduling strategy and service decision-making process based on a deep reinforcement learning algorithm through the analysis of historical data and user feedback, generate an optimal service decision-making plan, optimize long-term service decisions in combination with deep learning algorithms, and achieve multi-strategy integrated optimization;

[0013] A feedback optimization module, which is used to optimize the analysis algorithm and scheduling strategy by using an incremental learning algorithm according to the real-time monitoring data and user feedback, and adopt a multi-objective optimization algorithm to improve the efficiency of long-term service decisions.

[0014] Preferably, the intelligent analysis module is further used to establish a service quality prediction model by using deep learning algorithms and big data analysis techniques, realize dynamic prediction of service demands and performance bottlenecks, and generate prediction results;

[0015] Service quality prediction model:

[0016] h t =σ(W h x t +U h h t-1 +b h )

[0017] In the formula, h t is the hidden state at time t, x t represents the input, W h 、U h 、b h are trainable parameters, and σ is an activation function;

[0018] Based on an adaptive learning algorithm, dynamically adjust the service quality prediction model according to real-time data, and automatically adjust for short-term and long-term demand changes;

[0019] Optimize the processing speed of massive real-time data in combination with the cloud computing platform, and automatically adjust the resource configuration and service strategy based on the prediction results.

[0020] Preferably, the automated scheduling module is also used for the adaptive resource scheduling engine, and based on real-time load monitoring, fault detection, and performance evaluation, automatically expand or reduce the system resources elastically;

[0021] Introduce a scheduling strategy based on multiple optimization algorithms to achieve a globally optimal resource adjustment plan, and perform real-time switching of the optimization algorithms according to different scenarios.

[0022] Preferably, the service decision-making module is also used for the deep reinforcement learning algorithm, and through the analysis of historical data and user feedback, continuously optimize the service decision-making strategy;

[0023] Combined with the real-time changes of user behavior, network traffic, and system load, dynamically adjust the service decision-making strategy, and automatically generate an optimal service decision-making plan;

[0024] Based on the multi-agent system technology, achieve the collaborative scheduling of multiple nodes and multiple resources according to the service decision-making plan.

[0025] Preferably, the feedback optimization module is also used for the incremental learning algorithm, and perform adaptive optimization for each feedback to achieve continuous optimization of the scheduling strategy and algorithm configuration of the system in complex application scenarios;

[0026] Incremental update formula:

[0027] θ n =θ o +αΔθ

[0028] In the formula, θ n is the updated parameter, θ o is the original parameter, α is the learning rate, and Δθ is the updated value obtained by gradient descent;

[0029] Combine the Bayesian optimization method to adjust the model parameters, and use the graphics processing unit to accelerate data processing and model training;

[0030] Prior distribution in Bayesian optimization:

[0031] f(x)=μ(x)+κσ(x)

[0032] In the formula, μ(x) is the mean of the current prediction, σ(x) is the standard deviation, and κ is the trade-off parameter between exploration and exploitation;

[0033] Posterior distribution in Bayesian optimization:

[0034] P(f|D)∝P(D|f)·P(f)

[0035] Wherein, P(f|D) is the posterior distribution given data D, P(D|f) is the likelihood function, and P(f) is the prior distribution;

[0036] Automatically detect potential bottlenecks and propose correction plans based on the historical operation data of the system.

[0037] Preferably, the service quality monitoring module is further configured to integrate a multi-dimensional quality monitoring system, track various service quality indicators in real time, and dynamically adjust service quality standards and scheduling strategies through in-depth analysis of real-time monitoring data;

[0038] Introduce a service quality evaluation model based on time series analysis to optimize the accuracy and real-time response of multi-dimensional data analysis.

[0039] Preferably, the system is designed based on a microservices architecture, and each module exchanges data and communicates through a service bus, supporting flexible expansion and asynchronous processing of each module;

[0040] Each module adopts containerization technology and service mesh technology to achieve high availability and elastic scalability of the system, and supports independent deployment and version upgrade of each module.

[0041] A computer intelligent service management method based on network big data, including:

[0042] Adopt a distributed data acquisition architecture, collect real-time data from multiple heterogeneous data sources through multiple levels of automatic data acquisition points, and combine multi-modal data fusion technology to achieve data docking and standardized processing between different sources;

[0043] Based on deep learning algorithms and big data analysis technologies, establish a service quality prediction model, comprehensively analyze the collected data, identify potential performance bottlenecks, service demand fluctuations, and user behavior patterns, and predict the change trend of system service quality;

[0044] Integrate a multi-dimensional service quality monitoring system, track and monitor various service quality indicators in real time, combine with a time series analysis model, deeply analyze real-time monitoring data, and dynamically adjust service quality standards and scheduling strategies;

[0045] Based on predictive analysis and real-time monitoring data, through an adaptive resource scheduling engine, automatically schedule computer resources, dynamically adjust the allocation of service resources, and combine real-time load monitoring, fault detection, and performance evaluation to perform elastic resource expansion or contraction;

[0046] Based on deep reinforcement learning algorithms, through the analysis of historical data and user feedback, continuously optimize service decision-making strategies, and combine with real-time changes in user behavior, network traffic, and load to automatically generate the optimal service decision-making plan;

[0047] Based on the incremental learning algorithm, it adaptively optimizes for each feedback, continuously optimizes the scheduling strategy and algorithm configuration, adjusts the model parameters by combining the Bayesian optimization method, and accelerates data processing and model training through the graphics processing unit.

[0048] Preferably, in each feedback cycle, it analyzes the user requirements and service performance in real time, combines the feedback data with the historical behavior patterns, automatically adjusts the service quality and resource scheduling strategy, and forms a dynamic service management system based on the personalized needs of users.

[0049] Preferably, the method also combines the deep learning algorithm and natural language processing technology to realize the automatic analysis and response to user feedback and interaction;

[0050] In the process of service decision-making and resource scheduling, it dynamically adjusts the service strategy of user personalized needs based on the multi-dimensional data model.

[0051] Compared with the prior art, the beneficial effects of the present invention are:

[0052] The present invention can process and analyze massive data in real time, identify potential performance bottlenecks, service demand fluctuations and user behavior patterns, and automatically adjust according to real-time changes; through the adaptive scheduling engine and predictive analysis, according to the real-time feedback of user requirements and service performance, it accurately adjusts resource allocation to ensure the efficiency and stability of resource scheduling. In addition, based on the decision-making mechanism of deep reinforcement learning and the continuous optimization of the incremental learning algorithm, it continuously improves service decision-making in a changing environment and optimizes the resource scheduling strategy, so as to ensure that the service quality always maintains a high standard. This adaptive and intelligent scheduling and optimization ability can flexibly cope with various challenges in complex application scenarios and achieve efficient resource utilization and service quality assurance. Description of the Drawings

[0053] Figure 1 It is a framework diagram of the computer intelligent service management system based on network big data of the present invention;

[0054] Figure 2 It is a flowchart of the computer intelligent service management method based on network big data of the present invention. Detailed Embodiments

[0055] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0056] Example 1:

[0057] Please refer to Figure 1 as shown, a computer intelligent service management system based on network big data, including:

[0058] A data collection module, used to collect data from multiple sources through an adaptive data acquisition architecture. The architecture is based on cloud and edge computing for dynamic data source management, and combines multi-modal data fusion technology to achieve data docking and standardized processing between different sources;

[0059] An intelligent analysis module, used to comprehensively mine and analyze the collected data by using deep learning algorithms and big data analysis techniques, identify potential performance bottlenecks, service demand fluctuations and user behavior patterns, and generate analysis reports;

[0060] A service quality monitoring module, used to adopt an adaptive monitoring strategy to monitor various service quality indicators in real time, automatically detect system anomalies or performance degradation according to real-time monitoring data, and trigger an automatic adjustment mechanism;

[0061] An automated scheduling module, used to automatically schedule computer resources according to the analysis report and real-time monitoring data, dynamically adjust the allocation of service resources in combination with data changes, use deep learning algorithms for service demand prediction, and achieve automatic optimization scheduling of service resources;

[0062] A service decision-making module, used to continuously optimize the scheduling strategy and service decision-making process based on deep reinforcement learning algorithms through the analysis of historical data and user feedback, generate the optimal service decision-making plan, optimize long-term service decisions in combination with deep learning algorithms, and achieve multi-strategy integrated optimization;

[0063] A feedback optimization module, used to optimize the analysis algorithm and scheduling strategy according to real-time monitoring data and user feedback by using incremental learning algorithms, and adopt multi-objective optimization algorithms to improve the effectiveness of long-term service decisions.

[0064] The intelligent analysis module is also used to establish a service quality prediction model through deep learning algorithms and big data analysis techniques, realize dynamic prediction of service demand and performance bottlenecks, and generate prediction results;

[0065] Based on an adaptive learning algorithm, dynamically adjust the service quality prediction model according to real-time data, and automatically adjust for short-term and long-term demand changes;

[0066] Combine with the cloud computing platform to optimize the processing speed of massive real-time data, and automatically adjust resource configuration and service strategies based on the prediction results.

[0067] Furthermore, this module uses deep learning algorithms and big data analysis techniques to establish a service quality prediction model, predicting service demand, performance bottlenecks, user behavior patterns, etc. This strategy enables the system to make dynamic adjustments and optimizations based on real-time data and prediction results, improving service quality and resource utilization efficiency.

[0068] The automated scheduling module is also used for the adaptive resource scheduling engine to automatically expand or reduce system resources elastically based on real-time load monitoring, fault detection, and performance evaluation;

[0069] Introduce a scheduling strategy based on multiple optimization algorithms to achieve a globally optimal resource adjustment plan and perform real-time switching of optimization algorithms according to different scenarios.

[0070] The service decision-making module is also used to continuously optimize service decision-making strategies based on deep reinforcement learning algorithms through the analysis of historical data and user feedback;

[0071] Combined with the real-time changes in user behavior, network traffic, and system load, dynamically adjust service decision-making strategies and automatically generate optimal service decision-making plans;

[0072] Based on multi-agent system technology, achieve collaborative scheduling of multiple nodes and multiple resources according to the service decision-making plan.

[0073] Furthermore, adaptively schedule resources based on information such as real-time monitoring data, load, fault detection, and performance evaluation to achieve elastic expansion and reduction of computer resources. At the same time, combine deep reinforcement learning algorithms with multiple optimization algorithms to automatically optimize resource allocation and service scheduling plans, achieve globally optimal resource allocation, and ensure the efficient operation of the system.

[0074] The feedback optimization module is also used to perform adaptive optimization for each feedback based on incremental learning algorithms, achieving continuous optimization of scheduling strategies and algorithm configurations in complex application scenarios;

[0075] Combine Bayesian optimization methods to adjust model parameters and use graphics processing units to accelerate data processing and model training;

[0076] Based on the historical operation data of the system, automatically detect potential bottlenecks and propose correction plans.

[0077] The service quality monitoring module is also used to integrate a multi-dimensional quality monitoring system, track various service quality indicators in real time, and dynamically adjust service quality standards and scheduling strategies through in-depth analysis of real-time monitoring data;

[0078] Introduce a service quality assessment model based on time series analysis to optimize the accuracy and real-time response of multi-dimensional data analysis.

[0079] Furthermore, the service decision-making module and the feedback optimization module can continuously optimize the service decision-making strategy and scheduling algorithm through deep reinforcement learning and incremental learning algorithms. Combining a multi-dimensional quality monitoring system, they dynamically adjust the service quality standard and scheduling strategy through real-time data monitoring and in-depth analysis, and optimize the system performance through an automatic feedback mechanism, so as to adapt to changing user needs and service strategies, forming a continuously improving intelligent optimization process.

[0080] The system is designed based on a microservices architecture, and each module exchanges and communicates data through a service bus, supporting flexible expansion and asynchronous processing of modules;

[0081] Each module adopts containerization technology and service mesh technology to achieve high availability and elastic scalability of the system, supporting independent deployment and version upgrade of modules.

[0082] Embodiment 2:

[0083] Please refer to Figure 2 As shown, a computer intelligent service management method based on network big data includes:

[0084] Adopt a distributed data acquisition architecture, collect real-time data from multiple heterogeneous data sources through multiple levels of automatic data acquisition points, and combine multi-modal data fusion technology to achieve data docking and standardized processing between different sources;

[0085] Based on deep learning algorithms and big data analysis techniques, establish a service quality prediction model, comprehensively analyze the collected data, identify potential performance bottlenecks, service demand fluctuations, and user behavior patterns, and predict the changing trend of system service quality;

[0086] Integrate a multi-dimensional service quality monitoring system, real-time track and monitor various service quality indicators, combine time series analysis models, deeply analyze real-time monitoring data, and dynamically adjust service quality standards and scheduling strategies;

[0087] Based on predictive analysis and real-time monitoring data, through an adaptive resource scheduling engine, automatically schedule computer resources, dynamically adjust the allocation of service resources, and combine real-time load monitoring, fault detection, and performance evaluation to perform elastic resource expansion or contraction;

[0088] Based on deep reinforcement learning algorithms, through the analysis of historical data and user feedback, continuously optimize the service decision-making strategy, and combine the real-time changes in user behavior, network traffic, and load to automatically generate the optimal service decision-making plan;

[0089] Based on incremental learning algorithms, perform adaptive optimization for each feedback, continuously optimize the scheduling strategy and algorithm configuration, adjust model parameters in combination with Bayesian optimization methods, and accelerate data processing and model training through a graphics processing unit.

[0090] In each feedback cycle, the user requirements and service performance are analyzed in real time. Combining the feedback data with the historical behavior patterns, the service quality and resource scheduling strategy are automatically adjusted to form a dynamic service management system based on the personalized needs of users.

[0091] This method also combines deep learning algorithms with natural language processing technologies to achieve automated analysis and response to user feedback and interactions;

[0092] In the process of service decision-making and resource scheduling, the service strategy for the personalized needs of users is dynamically adjusted based on a multi-dimensional data model.

[0093] Application example: Intelligent resource management and optimization of a cloud computing service platform

[0094] I. Application background

[0095] A large cloud computing service platform provides virtual machines, storage, and computing resources to customers in different industries. The requirements of these customers are variable, and the system load fluctuates greatly. In particular, the performance of large customers and important services during peak traffic periods is crucial. The existing resource scheduling and service quality monitoring systems are mainly based on static rules, unable to flexibly respond to real-time load changes and lacking intelligent service decision-making. The platform often faces resource waste or performance bottlenecks, resulting in a decline in customer satisfaction. Especially during high loads, the service quality will fluctuate significantly.

[0096] II. Application implementation

[0097] Use an adaptive data acquisition architecture to collect data in real time from multiple data sources (including customer usage, traffic, network load, hardware performance, etc.).

[0098] The data sources include various hardware devices within the cloud platform, the CPU and memory utilization of servers, network bandwidth usage, service request logs of customers, etc.

[0099] Combined with multi-modal data fusion technology, the data from different sources is standardized for further analysis.

[0100] Adopt deep learning and big data analysis technologies to mine the collected data and analyze potential bottlenecks and service demand fluctuations.

[0101] Based on historical data, establish a service quality prediction model to identify trends of peak traffic periods and sudden increases in load, and predict system performance changes.

[0102] According to the changes in real-time data, dynamically adjust the service quality prediction, and optimize resource allocation based on the prediction results.

[0103] Integrate a multi-dimensional service quality monitoring system to track key metrics in real time, such as response time, throughput, service availability, etc.

[0104] Through an adaptive monitoring strategy, detect system anomalies or performance degradation in real time and trigger an automatic adjustment mechanism to elastically expand computing resources.

[0105] According to the analysis report and real-time data, automatically adjust the resource allocation to ensure rapid resource expansion during peak periods and automatic resource reduction during low loads, avoiding waste.

[0106] Based on deep reinforcement learning algorithms, continuously optimize service decision-making strategies, and dynamically generate optimal resource scheduling plans by combining user behavior, network traffic, and load conditions in real time.

[0107] After each service delivery, analyze user feedback through incremental learning algorithms and automatically optimize algorithm configurations and scheduling strategies to ensure that the service always meets user needs.

[0108] Use Bayesian optimization methods to adjust model parameters to ensure the efficiency and robustness of the model in complex application scenarios.

[0109] Adopt deep reinforcement learning techniques to continuously optimize scheduling strategies and optimize resource allocation plans based on historical data and user feedback.

[0110] Based on multi-agent system technology, achieve collaborative scheduling among multiple data centers and multiple nodes to ensure the efficiency of resource scheduling across regions and nodes.

[0111] II. Application Scenarios

[0112] During peak periods of e-commerce promotion activities (such as Double 11) or the financial industry, identify the trend of sudden traffic surges in advance and adjust resource allocation in a timely manner through a prediction model to prevent performance bottlenecks and ensure that users can obtain stable and efficient services.

[0113] For the personalized needs of different enterprise customers, dynamically adjust the resource allocation strategy according to the customer's historical behavior and demand patterns to ensure that each customer can obtain high-quality services during their demand peaks.

[0114] As user needs change and data is continuously updated, continuously improve service quality and resource utilization efficiency in the long-term operation through a continuously optimized service decision-making mechanism (combining incremental learning and reinforcement learning).

[0115] III. Application Results

[0116] Improve service quality: By monitoring in real time and dynamically adjusting resources, the service availability and response time of the platform have been significantly improved. Especially during peak traffic periods, the platform can respond flexibly to avoid service interruptions or performance degradation caused by insufficient resources.

[0117] Optimize resource utilization: The adaptive scheduling engine ensures the flexibility of resource allocation, enabling the platform to achieve the optimal resource utilization efficiency under different load conditions and reducing unnecessary resource waste.

[0118] Enhance customer satisfaction: By deeply analyzing the changes in customer behavior and needs, the platform can provide more personalized and efficient services to customers, greatly improving the customer experience.

[0119] Example 3:

[0120] The embodiment of the present invention also provides a computer-readable storage medium. A program of the computer intelligent service management system based on network big data as described in any one of the above is stored on the computer-readable storage medium. When the program is executed by a processor, it implements each process of the above service management system embodiment and can achieve the same technical effects. To avoid repetition, it will not be elaborated here. Among them, the computer-readable storage medium, such as a read-only memory (ROM for short), a random access memory (RAM for short), a magnetic disk, or an optical disc, etc.

[0121] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without conflict, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0122] In the attached drawings of the disclosed embodiments of the present invention, only the structures related to the disclosed embodiments of the present invention are involved. Other structures can refer to the general design. Without conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0123] The flowcharts shown in the drawings are only illustrative examples, and do not necessarily include all the contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged. Therefore, the actual execution order may change according to the actual situation.

[0124] Although embodiments of the present invention have been shown and described, those of ordinary skill in the art will appreciate that various changes, modifications, substitutions and permutations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A computer intelligent service management system based on network big data, characterized in that: include: A data collection module is used to collect data from multiple sources through an adaptive data collection architecture. The architecture is based on cloud and edge computing to perform dynamic data source management and combine multimodal data fusion technology to achieve data docking and standardized processing between different sources; Intelligent analysis module, which uses deep learning algorithms and big data analysis technology to comprehensively mine and analyze the collected data, identify potential performance bottlenecks, service demand fluctuations and user behavior patterns, and generate analysis reports; The service quality monitoring module is used to adopt an adaptive monitoring strategy to monitor various service quality indicators in real time, automatically detect system anomalies or performance degradation based on real-time monitoring data, and trigger an automatic adjustment mechanism; An automated scheduling module, for automatically scheduling computer resources according to the analysis report and the real-time monitoring data, dynamically adjusting the allocation of service resources in combination with data changes, using a deep learning algorithm to predict service demand, and realizing automatic optimization and scheduling of service resources; The service decision module is used to continuously optimize the scheduling strategy and service decision process based on the deep reinforcement learning algorithm, analyze historical data and user feedback, generate the best service decision plan, optimize long-term service decisions in combination with the deep learning algorithm, and realize multi-strategy integrated optimization; The feedback optimization module is used to optimize the analysis algorithm and scheduling strategy based on the real-time monitoring data and the user feedback using an incremental learning algorithm, and to improve the efficiency of the long-term service decision-making using a multi-objective optimization algorithm.

2. According to claim 1, a computer intelligent service management system based on network big data is characterized in that: The intelligent analysis module is also used for: Through deep learning algorithms and big data analysis technology, a service quality prediction model is established to achieve dynamic prediction of the service demand and the performance bottleneck, and generate prediction results; Service quality prediction model: h t =σ(W h x t +U h h t-1 +b h ) In the formula, h t is the hidden state at time t, x t represents input, W h , U h 、b h is a trainable parameter, σ is an activation function; Based on an adaptive learning algorithm, dynamically adjust the service quality prediction model according to the real-time data to automatically adjust to short-term and long-term demand changes; The processing speed of the massive real-time data is optimized in combination with the cloud computing platform, and resource allocation and service strategies are automatically adjusted based on the prediction results.

3. A computer intelligent service management system based on network big data according to claim 2, characterized in that: The automated scheduling module is also used for: Adaptive resource scheduling engine, which automatically and elastically expands or reduces system resources based on real-time load monitoring, fault detection and performance evaluation; A scheduling strategy based on multiple optimization algorithms is introduced to implement a global optimal resource adjustment solution, and the optimization algorithms are switched in real time according to different scenarios.

4. According to claim 3, a computer intelligent service management system based on network big data is characterized in that: The service decision module is also used to: Based on the deep reinforcement learning algorithm, the service decision strategy is continuously optimized by analyzing the historical data and the user feedback; Combined with the real-time changes in user behavior, network traffic and system load, the service decision strategy is dynamically adjusted to automatically generate the optimal service decision solution; Based on multi-agent system technology, the coordinated scheduling of multiple nodes and multiple resources is achieved according to the service decision-making solution.

5. A computer intelligent service management system based on network big data according to claim 4, characterized in that: The feedback optimization module is also used for: Based on the incremental learning algorithm, adaptive optimization is performed for each feedback, so that the system can continuously optimize the scheduling strategy and algorithm configuration in complex application scenarios; Incremental update formula: i n =θ o +αΔθ In the formula, θ n is the updated parameter, θ o is the original parameter, α is the learning rate, and Δθ is the updated value obtained by gradient descent; Combine Bayesian optimization methods to adjust model parameters, and use graphics processing units to accelerate data processing and model training; Prior distribution in Bayesian optimization: f(x)=μ(x)+κσ(x) Where μ(x) is the mean of the current prediction, σ(x) is the standard deviation, and κ is the trade-off parameter between exploration and exploitation; Posterior distribution in Bayesian optimization: P(f|D)∝P(D|f)·P(f) Where P(f|D) is the posterior distribution of the given data D, P(D|f) is the likelihood function, and P(f) is the prior distribution; Automatically detect potential bottlenecks and propose correction plans based on the system's historical operation data.

6. A computer intelligent service management system based on network big data according to claim 5, characterized in that: The service quality monitoring module is also used for: Integrate a multi-dimensional quality monitoring system to track various service quality indicators in real time, and dynamically adjust service quality standards and scheduling strategies through in-depth analysis of the real-time monitoring data; Introduce a service quality evaluation model based on time series analysis to optimize the accuracy and real-time response of multi-dimensional data analysis.

7. A computer intelligent service management system based on network big data according to claim 6, characterized in that: The system is designed based on microservice architecture, and each module exchanges data and communicates through the service bus, supporting flexible expansion and asynchronous processing of each module; Each module uses containerization technology and service mesh technology to achieve high availability and elastic scalability of the system, and supports independent deployment and version upgrades of each module.

8. A computer intelligent service management method based on network big data, characterized in that: include: Adopting a distributed data collection architecture, it collects real-time data from multiple heterogeneous data sources through multiple levels of automatic data collection points, and combines multimodal data fusion technology to achieve data connection and standardized processing between different sources; Based on deep learning algorithms and big data analysis technology, a service quality prediction model is established to comprehensively analyze the collected data, identify potential performance bottlenecks, service demand fluctuations and user behavior patterns, and predict the changing trend of system service quality; Integrate a multi-dimensional service quality monitoring system to track and monitor various service quality indicators in real time. Combined with the time series analysis model, deeply analyze the real-time monitoring data and dynamically adjust the service quality standards and scheduling strategies. Based on predictive analysis and the real-time monitoring data, the adaptive resource scheduling engine automatically schedules computer resources, dynamically adjusts the allocation of service resources, and elastically expands or reduces resources in combination with real-time load monitoring, fault detection and performance evaluation; Based on deep reinforcement learning algorithms, the service decision strategy is continuously optimized through analysis of historical data and user feedback, and the optimal service decision plan is automatically generated based on real-time changes in user behavior, network traffic, and load. Based on the incremental learning algorithm, adaptive optimization is performed for each feedback, the scheduling strategy and algorithm configuration are continuously optimized, the model parameters are adjusted in combination with the Bayesian optimization method, and data processing and model training are accelerated through the graphics processing unit.

9. A computer intelligent service management method based on network big data according to claim 8, characterized in that: In each feedback cycle, the user needs and service performance are analyzed in real time, and the feedback data and historical behavior patterns are combined to automatically adjust the service quality and resource scheduling strategy to form a dynamic service management system based on user personalized needs.

10. A computer intelligent service management method based on network big data according to claim 9, characterized in that: The method also combines deep learning algorithms with natural language processing technology to achieve automated analysis and response to the user feedback and interactions; In the process of service decision-making and resource scheduling, the service strategy for the user's personalized needs is dynamically adjusted based on the multi-dimensional data model.

Images