Enterprise service platform intelligent management and control method and system based on function analysis

Abstract

The invention discloses an enterprise service platform intelligent management and control method and system based on function analysis, and relates to the technical field of platform intelligent management and control, and the method comprises the steps: collecting the calling frequency, resource occupancy rate, response time delay, user behavior track and abnormal event data of a function module, carrying out the standardization and time sequence verification, and constructing a multi-dimensional operation data flow. Constructing a functional behavior model based on a graph neural network, extracting module operation features and structural dependence, dynamically generating a functional thermodynamic scoring graph, and realizing visual display of module loads and abnormal hotspots; and constructing a functional twin copy for the key module, simulating a management and control strategy in an isolated simulation environment, and obtaining feedback. Constructing a multi-level management and control strategy generation matrix based on feedback, generating and optimizing candidate strategies, dynamically deploying, continuously monitoring and automatically adjusting; the system adopts a hierarchical rollback mechanism to realize strategy self-adaptive rollback in case of exception, so that stable and reliable operation of the platform is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of platform intelligent management and control, and particularly to a method and system for intelligent management and control of an enterprise service platform based on function analysis. Background Art

[0002] As enterprise service platforms continue to evolve, the number and complexity of their functional modules continues to increase. Each module generates a wide variety of operational data, including call frequency, resource utilization, response latency, user behavior patterns, and abnormal events. Accurately collecting and effectively utilizing this multi-dimensional operational data to build behavioral models that reflect functional activity, stability, and load characteristics has become a key challenge in intelligent platform management and control.

[0003] Furthermore, the current deployment of control policies lacks sufficient security verification, making it difficult to avoid system performance degradation and business interruptions caused by policy failure or unreasonable adjustments. Furthermore, the lack of real-time policy execution monitoring and automatic rollback mechanisms increases platform operational risks and makes it impossible to guarantee the continuity and stability of the enterprise service platform. Summary of the Invention

[0004] In order to solve the above technical problems, a method and system for intelligent management and control of enterprise service platforms based on functional analysis are provided. This technical solution solves the problems raised in the above background technology on how to accurately collect and effectively utilize these multi-dimensional operation data, and build a behavioral model that reflects functional activity, stability and load characteristics. In addition, the current deployment of management and control strategies lacks sufficient security verification means, real-time policy execution effect monitoring and automatic rollback mechanism.

[0005] In order to achieve the above objects, the technical solution adopted by the present invention is: An intelligent management and control method for an enterprise service platform based on functional analysis, specifically comprising: Acquire multi-dimensional operation data streams and construct functional behavior models through graph neural networks to comprehensively reflect the operation status and mutual relationships of functional modules and extract the operation characteristics of each functional module; Dynamically generate a function heat score map based on the operating characteristics of each function module, and use this heat score map to visualize the load distribution and abnormal hot spots of the function modules; Identify key functional modules based on the heat score graph, build functional twin copies for the identified key functional modules, and simulate the execution of the proposed control strategy in a simulation environment isolated from the production environment to obtain simulation feedback results. The control strategy refers to the control plan for key functional modules in terms of resource allocation, task scheduling, and access permission configuration; Based on the functional behavior model, heat score diagram, and functional twin replica simulation feedback results, a multi-level control strategy generation matrix is ​​constructed to generate candidate control strategy templates. Through the strategy optimization and deployment mechanism, a self-evolving control strategy set is formed and deployed to the enterprise service platform. By real-time monitoring of key operational features extracted from functional behavior models during the execution of enterprise service platform management and control strategies, and combining control flow charts with feedback indicators, we dynamically evaluate the effectiveness of strategy execution and drive a closed-loop feedback mechanism to achieve strategy self-adaptation. When the policy execution effect is abnormal, the hierarchical rollback mechanism is triggered according to the abnormality level and system feedback information. The system records the relevant rollback events and operation data and updates the rollback knowledge base.

[0006] In an optional embodiment, the multi-dimensional operation data stream is obtained, and a functional behavior model is constructed through a graph neural network to comprehensively reflect the operation status and mutual relationship of the functional modules and extract the operation characteristics of each functional module, specifically including: Based on the industrial communication protocol, the distributed control system (DCS), programmable logic controller (PLC), edge acquisition terminal, and user interaction log system connected to each functional module in the enterprise service platform are accessed. The call frequency, resource utilization, response latency, user behavior trajectory, and operation data corresponding to abnormal events generated by each functional module during operation are collected to obtain the original operation data set. The collected raw operating data is input into the data adaptation middleware deployed at the platform access layer, and the format is standardized and converted to obtain standardized operating data in a unified format. The data is then uploaded in batches to the data aggregation module of the enterprise service platform based on preset time intervals. The data aggregation module performs time synchronization, field regularization, and preliminary verification on the standardized operation data to obtain a multi-dimensional operation data stream; Based on the multi-dimensional operation data flow, the functional behavior modeling method of graph neural network is used to construct a functional behavior model, which integrates the interactive topological structure between functional modules with the dynamic indicator sequence related to resource utilization and behavioral response, and extracts the structural dependency and operation characteristics of each functional module.

[0007] In an optional embodiment, the function heat score map is dynamically generated according to the operating characteristics of each function module, and the heat score map is used to visualize the load distribution and abnormal hot spots of the function modules, specifically including: Based on call frequency, resource occupancy, and response latency, a local performance tensor is constructed to describe the module performance status. ,in, is the spatial coordinate of the module, For time, , corresponding to the three indicators of call frequency, resource occupancy and response delay; Combined with user behavior trajectory data, a deep clustering algorithm is used to model the user's access frequency and path pattern between different functional modules, construct a spatial activity distribution map, and extract the corresponding access heat intensity function. , represents the user activity mapping in space; From the constructed multi-dimensional operational data stream, feature dimensions related to system anomalies are extracted, including system error codes, retry behaviors, and interface response timeout logs, to construct a feature sequence of abnormal events. Based on the feature sequence of abnormal events, the time series feature extraction method is adopted, and the deep autoencoder is used to perform unsupervised learning on the propagation path, disturbance intensity and scope of abnormal events to generate an abnormal disturbance factor function that describes the abnormal evolution state. ; Through the time series modeling method, the temporal changes of local performance tensors, user activity and abnormal disturbance factors are integrated to generate the spatiotemporal thermal scoring function of the functional module: , in, Indicates spatial location No. The input feature vector at time is defined as:

[0008] Where, Respectively represent the modules in The calling frequency, resource utilization and response delay at each moment, Indicates that the position User access activity at all times, Indicates the Abnormal disturbance factor at the moment; Based on the thermal value output by the thermal scoring function, a three-dimensional functional thermal scoring map is constructed, and the module load and abnormal distribution dynamics are visualized in the form of a heat map.

[0009] In an optional embodiment, the identification of key functional modules based on the heat score map, the construction of functional twin copies for the identified key functional modules, and the simulation and execution of the proposed control strategy in a simulation environment isolated from the production environment to obtain simulation feedback results specifically include: Based on the spatial distribution characteristics and temporal evolution trend of thermal values ​​in the three-dimensional functional thermal score map, combined with the structural dependencies between modules, key functional modules with abnormally high thermal values ​​and persistently high thermal states are identified. For the identified key functional modules, in a simulation environment isolated from the enterprise service platform production environment, we construct corresponding functional twin copies based on the structural dependencies and operational characteristics extracted from the functional behavior model and the historical evolution trajectory of the modules during operation. In the functional twin copy, multiple candidate control strategies are formulated by combining resource allocation, task scheduling, and access permission configuration. These strategies are then pre-screened based on the system's historical control strategy execution feedback information to obtain multiple preliminary screening control strategy solutions. By deploying an interactive simulation sandbox with the ability to replay behavior trajectories and record intervention responses, the execution process of the initial screening control strategy plan in the functional twin copy is simulated, the performance of each candidate control strategy in the simulation environment and the mitigation effect on abnormal propagation are collected, and the simulation feedback results of the candidate control strategy are obtained.

[0010] In an optional embodiment, the multi-level control strategy generation matrix is ​​constructed based on the functional behavior model, heat score diagram, and functional twin replica simulation feedback results, candidate control strategy templates are generated, and a self-evolvable control strategy set is formed through a strategy optimization and deployment mechanism, and deployed to the enterprise service platform, specifically including: Based on the operating characteristics of key functional modules in the functional behavior model, the thermal distribution status and its evolution trend in the thermal score diagram, and the multi-dimensional simulation feedback results in the twin simulation environment, a multi-level control strategy generation matrix is ​​constructed. The generation matrix uses the functional module identifier as the index dimension and the resource intervention parameters, scheduling sequence parameters, and authority configuration parameters as the strategy dimensions. Multiple candidate control strategy templates are generated through multi-dimensional cross-combination. The candidate control strategy templates are input into the strategy optimization module. Based on the performance indicator response curve, abnormal propagation change trajectory and task execution offset recorded in the simulation feedback results, a feedback-driven strategy optimization mechanism is used to dynamically select the control strategy set with the best matching performance. Performing a structured expression on the control policy set to generate a policy deployment package, which includes a policy parameter mapping table, policy trigger conditions, policy scope, and policy effectiveness priority, and is mapped and bound to the system configuration interface of the enterprise service platform; Based on the structural dependencies between functional modules and their spatial location coordinates, the policy deployment package is injected into the running unit where the target module is located, and the policy is dynamically loaded through the platform's built-in policy mounting mechanism. The dynamic loading allows the policy version to be updated while the system is running; By constructing a policy execution control flow chart, marking the policy trigger node, policy intervention path and policy effectiveness module, the control flow chart is maintained synchronously with the functional behavior model to reflect the policy response path and the interaction relationship between modules; Based on the operating environment after policy deployment, the platform system continuously monitors the status of functional modules within the policy-effective area, and automatically adjusts the policy triggering frequency, action granularity and parameter weights based on the interaction between modules and resource competition dynamics.

[0011] In an optional embodiment, when the policy execution effect is abnormal, a hierarchical rollback mechanism is triggered according to the abnormality level and system feedback information, and the system records the relevant rollback events and operation data and updates the rollback knowledge base, specifically including: By real-time monitoring of key operational features extracted based on functional behavior models during the execution of enterprise service platform control strategies, and automatically evaluating the execution effect of control strategies using comprehensive evaluation indicators, it is determined whether a rollback should be triggered. Based on the assessment results, the abnormalities are graded and classified into mild abnormalities, moderate abnormalities, and severe abnormalities; When a minor anomaly is identified, key parameters in the control strategy are automatically adjusted to attempt to restore system stability without the need for an immediate rollback. When parameter fine-tuning fails to achieve the expected results and the degree of anomaly is determined to be moderate, the impact of the policy on some key functional modules is gradually revoked, and a partial rollback is implemented to control the spread of the anomaly; When the abnormality is severe and a partial rollback fails to effectively alleviate the system abnormality, a full system rollback is performed to restore the enterprise service platform to its stable state before the policy adjustment. Based on the rollback process, the intelligent anomaly diagnosis module continuously analyzes the root cause of the anomaly and dynamically adjusts the execution strength and scope of the rollback strategy based on the anomaly level and system feedback. The system records all rollback events and related key operating data in real time and builds a rollback knowledge base.

[0012] Furthermore, an intelligent management and control system for an enterprise service platform based on functional analysis is proposed, which is used to implement any of the above-mentioned intelligent management and control methods, specifically including: A raw data collection module, which is used to collect operational data of each functional module in the enterprise service platform, including call frequency, resource utilization, response latency, user behavior trajectory, and abnormal events; A data format standardization module is used to standardize the collected raw operating data, generate data in a unified format, and upload it to the data aggregation module; A multi-dimensional operation data flow construction module, which is used to perform time sequence alignment and field regularization on the standardized data and construct a multi-dimensional operation data flow; A functional behavior modeling module, which is used to establish a functional behavior model based on a graph neural network and extract the operating characteristics of each functional module; A thermal score generation module, which is used to fuse local performance tensors, user activity, and abnormal disturbance factors to construct a thermal score function and generate a three-dimensional thermal score map; Key module identification and simulation module, which is used to identify key functional modules based on the thermal score map, build corresponding functional twin copies, and test the control strategy in a simulation environment; A control strategy generation and deployment module, which is used to construct a multi-level strategy generation matrix, form candidate control strategy templates, and deploy them to the target module; The execution effect evaluation and rollback module is used to monitor the policy execution effect in real time, trigger hierarchical rollback when an anomaly occurs, and update the rollback knowledge base.

[0013] In an optional embodiment, the heat score generation module specifically includes: A performance tensor construction unit, which extracts call frequency, resource occupancy, and response latency, and constructs a local performance tensor according to spatial coordinates and time series; A user behavior modeling unit, which extracts user behavior trajectories and forms a user activity function; An abnormal disturbance learning unit, which uses a deep autoencoder to perform unsupervised learning of abnormal propagation and disturbance based on the abnormal event feature sequence to form an abnormal disturbance factor; The time series scoring modeling unit takes the performance tensor, activity, and abnormal disturbance as input, performs joint time series modeling through LSTM, and outputs a thermal scoring function.

[0014] In an optional embodiment, the key module identification and simulation module specifically includes: A key module identification unit, which uses the spatial distribution and temporal evolution trend of the thermal score map in combination with the functional behavior model to automatically identify key functional modules with abnormally increased thermal values ​​or those that are continuously in a high-temperature state; A functional twin construction unit, which builds corresponding functional twin copies based on the structural dependencies and operational characteristics of key modules to implement a simulation model isolated from the production environment; A strategy simulation test unit deploys control strategies in a simulation environment, executes strategy behavior trajectory playback, and collects strategy performance and anomaly mitigation effect feedback data.

[0015] In an optional embodiment, the execution effect evaluation and rollback module specifically includes: An execution effect evaluation unit, which monitors the execution effect of the strategy in real time and evaluates the execution status based on feedback indicators; An abnormality level determination unit, wherein the abnormality level determination unit classifies abnormality levels according to comprehensive evaluation indicators; A rollback policy scheduling unit, which performs parameter adjustment, local rollback, or full system rollback according to the abnormality level; The rollback knowledge base construction unit records rollback events and key operation data to construct a rollback knowledge base.

[0016] Compared with the prior art, the present invention has the following beneficial effects: This solution proposes an intelligent management and control method and system for enterprise service platforms based on functional analysis. By collecting and standardizing the multi-dimensional operating data of each functional module, constructing a multi-dimensional operating data stream, and establishing a functional behavior model based on a graph neural network, it accurately reflects the operating status and associated characteristics of the module, effectively solving the problems of insufficient multi-dimensional data utilization and inaccurate behavior modeling. By dynamically generating functional heat score graphs and identifying key modules, combined with functional twin replica simulation feedback, multi-level generation and self-evolution optimization of management and control strategies are achieved, making up for the problem of insufficient security verification of management and control strategies in existing technologies. At the same time, the system supports dynamic strategy effect evaluation based on real-time operating characteristics and feedback indicators, and cooperates with hierarchical rollback mechanisms and intelligent anomaly diagnosis to ensure the stable operation and business continuity of the enterprise service platform, effectively reducing the risks caused by strategy failure, and improving the platform's intelligent management and control capabilities and operational reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of an enterprise service platform intelligent management and control method based on function analysis proposed by the present invention; Figure 2 A flowchart for constructing the functional behavior model and identifying key modules in the present invention; Figure 3 This is a flow chart of the control strategy generation, deployment and rollback mechanism in the present invention; Figure 4 This is a system framework diagram of the enterprise service platform intelligent management and control system based on functional analysis proposed by the present invention. DETAILED DESCRIPTION

[0018] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0019] Reference Figure 1 - Figure 4 As shown, an intelligent management and control method for an enterprise service platform based on functional analysis specifically includes: Acquire multi-dimensional operation data streams and construct functional behavior models through graph neural networks to comprehensively reflect the operation status and mutual relationships of functional modules and extract the operation characteristics of each functional module; Dynamically generate a function heat score map based on the operating characteristics of each function module, and use this heat score map to visualize the load distribution and abnormal hot spots of the function modules; Identify key functional modules based on the heat score graph, build functional twin copies for the identified key functional modules, and simulate and execute the proposed control strategy in a simulation environment isolated from the production environment to obtain simulation feedback results. The control strategy refers to the control plan for key functional modules in terms of resource allocation, task scheduling, and access permission configuration; Based on the functional behavior model, heat score diagram, and functional twin replica simulation feedback results, a multi-level control strategy generation matrix is ​​constructed to generate candidate control strategy templates. Through the strategy optimization and deployment mechanism, a self-evolving control strategy set is formed and deployed to the enterprise service platform. By real-time monitoring of key operational features extracted from functional behavior models during the execution of enterprise service platform management and control strategies, and combining control flow charts with feedback indicators, we dynamically evaluate the effectiveness of strategy execution and drive a closed-loop feedback mechanism to achieve strategy self-adaptation. When the policy execution effect is abnormal, the hierarchical rollback mechanism is triggered according to the abnormality level and system feedback information. The system records the relevant rollback events and operation data and updates the rollback knowledge base.

[0020] Furthermore, we acquire multi-dimensional operation data streams and construct functional behavior models through graph neural networks to comprehensively reflect the operation status and mutual relationships of functional modules and extract the operation characteristics of each functional module, including: Based on the industrial communication protocol, the distributed control system (DCS), programmable logic controller (PLC), edge acquisition terminal, and user interaction log system connected to each functional module in the enterprise service platform are accessed. The call frequency, resource utilization, response latency, user behavior trajectory, and operation data corresponding to abnormal events generated by each functional module during operation are collected to obtain the original operation data set. The collected raw operating data is input into the data adaptation middleware deployed at the platform access layer, and the format is standardized and converted to obtain standardized operating data in a unified format. The data is then uploaded in batches to the data aggregation module of the enterprise service platform based on preset time intervals. The data aggregation module performs time synchronization, field regularization, and preliminary verification on the standardized operation data to obtain a multi-dimensional operation data stream; Based on the multi-dimensional operation data flow, the functional behavior modeling method of graph neural network is used to construct a functional behavior model, which integrates the interactive topological structure between functional modules with the dynamic indicator sequence related to resource utilization and behavioral response, and extracts the structural dependency and operation characteristics of each functional module.

[0021] Specifically, based on the multi-dimensional operation data flow, in order to accurately model the operation behavior and interdependence of each functional module in the enterprise service platform, this embodiment adopts a functional behavior modeling method based on a graph neural network (GNN) to construct a functional behavior model and clearly extract the structural dependencies and dynamic operation characteristics of each functional module; First, based on the five core indicators of call frequency, resource utilization, response latency, user behavior trajectory, and abnormal events contained in the multi-dimensional operation data stream, an interaction topology diagram between functional modules is constructed. In this diagram, each node represents a functional module, and the edges reflect the interaction and dependency relationships between modules. The edge weights comprehensively consider factors such as the coordinated changes between indicators, resource conflicts, and the propagation of abnormal events. They are automatically obtained through training with the historical operation data collected from the platform to form a structural dependency weight matrix that reflects real business dependencies. Next, the model uses a dependency-aware feature aggregation mechanism as the information propagation unit of the graph neural network. In this mechanism, the influence weights of neighboring nodes on the central node are dynamically adjusted based on the strength of the dependencies between modules, accurately capturing the structural dependencies between modules. For example, if the frequent occurrence of abnormal events in module A is directly affected by the call of module B, the model will increase the feature transfer weight from module B to ensure that the structural dependencies are effectively reflected. To extract the operational characteristics of each module, the module's timing indicators (such as response latency fluctuations and resource usage changes) are encoded as dynamic feature sequences, which serve as node input features. Through iterative calculations using a multi-layer graph convolutional network, the model aggregates the state information of neighboring nodes and combines it with changes in its own timing characteristics to form an operational feature vector for each module, comprehensively reflecting the module's current state and evolutionary trends. Ultimately, the trained functional behavior model not only clearly depicts the structural dependencies between modules, but also accurately extracts the dynamic operation characteristics of each module, providing a solid data foundation for subsequent thermal score map generation, key module identification, and functional twin copy construction.

[0022] Furthermore, a function heat score map is dynamically generated based on the operating characteristics of each function module. This heat score map allows for a visual display of the function module load distribution and abnormal hot spots, specifically including: Based on call frequency, resource occupancy, and response latency, a local performance tensor is constructed to describe the module performance status. ,in, is the spatial coordinate of the module, For time, , corresponding to the three indicators of call frequency, resource occupancy and response delay; Combined with user behavior trajectory data, a deep clustering algorithm is used to model the user's access frequency and path pattern between different functional modules, construct a spatial activity distribution map, and extract the corresponding access heat intensity function. , represents the user activity mapping in space; From the constructed multi-dimensional operational data stream, feature dimensions related to system anomalies are extracted, including system error codes, retry behaviors, and interface response timeout logs, to construct a feature sequence of abnormal events. Based on the feature sequence of abnormal events, the time series feature extraction method is adopted, and the deep autoencoder is used to perform unsupervised learning on the propagation path, disturbance intensity and scope of abnormal events to generate an abnormal disturbance factor function that describes the abnormal evolution state. ; Through the time series modeling method, the temporal changes of local performance tensors, user activity and abnormal disturbance factors are integrated to generate the spatiotemporal thermal scoring function of the functional module: , in, Indicates spatial location No. The input feature vector at time is defined as:

[0023] Where, Respectively represent the modules in The calling frequency, resource utilization and response delay at each moment, Indicates that the position User access activity at all times, Indicates the Abnormal disturbance factor at the moment; Based on the thermal value output by the thermal scoring function, a three-dimensional functional thermal scoring map is constructed, and the module load and abnormal distribution dynamics are visualized in the form of a heat map.

[0024] Furthermore, key functional modules are identified based on the heat score graph, functional twin copies are built for the identified key functional modules, and the proposed control strategies are simulated and executed in a simulation environment isolated from the production environment to obtain simulation feedback results, including: Based on the spatial distribution characteristics and temporal evolution trend of thermal values ​​in the three-dimensional functional thermal score map, combined with the structural dependencies between modules, key functional modules with abnormally high thermal values ​​and persistently high thermal states are identified. Specifically, after constructing the three-dimensional functional thermal score map, the system first performs a statistical analysis of the thermal values ​​of each functional module in space, identifying abnormal hotspot modules whose thermal values ​​are significantly higher than the overall level. Subsequently, for the thermal value changes of each module, the system uses a sliding time window statistical method to calculate the mean and variance of the thermal values ​​within each window, and uses a change point detection algorithm to automatically identify the time points when the module's thermal value changes significantly. By detecting situations where the thermal value remains at a high level in multiple consecutive windows, the system determines that the module is in a state of continuous high heat, thereby distinguishing between short-term and long-term anomalies. Finally, combining the structural dependencies between modules in the functional behavior model, the system performs a weighted propagation analysis on the impact paths of abnormal modules, identifying key functional modules that not only have abnormal thermal values ​​but also have a significant impact on other modules. This analytical approach, which integrates spatial distribution, dynamic changes, and network structure, effectively improves the accuracy of identifying key modules. For the identified key functional modules, in a simulation environment isolated from the enterprise service platform production environment, we construct corresponding functional twin copies based on the structural dependencies and operational characteristics extracted from the functional behavior model and the historical evolution trajectory of the modules during operation. In the functional twin copy, multiple candidate control strategies are formulated by combining resource allocation, task scheduling, and access permission configuration. These strategies are then pre-screened based on the system's historical control strategy execution feedback information to obtain multiple preliminary screening control strategy solutions. By deploying an interactive simulation sandbox with the ability to replay behavior trajectories and record intervention responses, we simulate the execution process of the initial screening control strategy plan in the functional twin replica, collect the performance of each candidate control strategy in the simulation environment and its effect on mitigating abnormal propagation, and obtain simulation feedback results of the candidate control strategy; Specifically, to improve the efficiency and accuracy of control strategy generation and screening, the platform system first formulates multiple candidate control strategies in the functional twin replica, focusing on the three intervention dimensions of resource allocation, task scheduling, and access rights configuration. Each candidate strategy combines the operational bottlenecks and dependency structure differences of key functional modules, and constructs a representative control solution through parameter perturbation and strategy permutation. After the candidate control strategies are formulated, they are preliminarily screened based on the system's historical control strategy execution feedback information, eliminating those that are obviously incompatible with the existing operating scenarios or have poor historical feedback effects, and obtaining multiple preliminary screening control strategy solutions; historical control strategies are policy instances that have been actually deployed and executed by the enterprise service platform at different operating stages, usually including intervention elements such as resource allocation parameters, task scheduling logic, and access permission configuration, and are bound to corresponding functional modules, trigger conditions, and target states. Each historical strategy has a clear applicable context, strategy structure, and expected goals; this feedback information comes from the strategy execution logs, module performance evaluation results, and exception response process data recorded by the enterprise service platform during actual operation. The system forms a historical strategy feedback database through structured archiving and dynamic updates, supporting data-driven evaluation of the expected performance of candidate strategies in similar scenarios; The system then screens the control strategies and deploys them one by one into an interactive simulation sandbox environment capable of replaying behavioral trajectories and recording intervention responses. The simulation sandbox, relying on the functional twin replica built by the platform, accurately reproduces the current system operating status and module interaction logic, ensuring that the strategies' performance during simulation fully reflects their practical feasibility. During the simulation process, the system tracks the intervention behavior of each strategy throughout the entire process, collects key performance indicators (such as changes in response delay, resource utilization fluctuations, task delay offset, etc.) and changes in abnormal propagation paths, and evaluates its effect on improving system performance and its ability to suppress the spread of abnormalities; all simulation feedback data will serve as the decision-making basis for subsequent strategy optimization modules to ensure that the selected strategy has good controllability and adaptability.

[0025] Furthermore, based on the functional behavior model, heat score diagram, and the simulation feedback results of the functional twin replica, a multi-level control strategy generation matrix is ​​constructed to generate candidate control strategy templates. Through the strategy optimization and deployment mechanism, a self-evolving control strategy set is formed and deployed to the enterprise service platform. Specifically, it includes: Based on the operating characteristics of key functional modules in the functional behavior model, the thermal distribution status and its evolution trend in the thermal score diagram, and the multi-dimensional simulation feedback results in the twin simulation environment, a multi-level control strategy generation matrix is ​​constructed. The generation matrix uses the functional module identifier as the index dimension and the resource intervention parameters, scheduling sequence parameters, and authority configuration parameters as the strategy dimensions. Multiple candidate control strategy templates are generated through multi-dimensional cross-combination. This strategy generation matrix uses the unique identifier of a functional module as the index dimension to define the corresponding strategy action unit. Within the strategy dimension, resource intervention parameters (such as CPU and memory limit thresholds), task scheduling sequence parameters (such as scheduling priority and execution timing), and access permission configuration parameters (such as call permission level and data isolation strategy) are set. By cross-combining these multiple dimension parameters, the system automatically generates a set of candidate control strategy templates covering different strategy combination scenarios, providing input for subsequent strategy optimization and deployment. The candidate control strategy templates are input into the strategy optimization module. Based on the performance indicator response curve, abnormal propagation change trajectory and task execution offset recorded in the simulation feedback results, a feedback-driven strategy optimization mechanism is used to dynamically select the control strategy set with the best matching performance. Structurally express the control policy set and generate a policy deployment package. The deployment package includes a policy parameter mapping table, policy trigger conditions, policy scope, and policy effectiveness priority, and is mapped and bound to the system configuration interface of the enterprise service platform. Specifically, the generated candidate control policy templates will be input into the platform's built-in policy optimization module. Based on the feedback results of the candidate policies in the functional twin simulation environment, this module extracts multi-dimensional information such as key performance indicator response curves (such as changes in system response delays and resource utilization fluctuations), abnormal propagation change trajectories (such as the impact range of fault nodes and the degree of shortening of propagation paths), and task execution offsets (such as the delay or advancement of task completion time). It uses a feedback-driven policy optimization mechanism to dynamically screen candidate policy templates. Finally, several control policies with the highest matching degree, the most controllable risks, and the most obvious performance improvement effects are selected to form a control policy set. The system then structures the control policy set and generates a policy deployment package for deployment. The deployment package includes a parameter mapping table for each policy (indicating the correspondence between each policy parameter and module operating parameters), policy trigger conditions (such as thermal value reaching a threshold or resource usage exceeding a limit), policy scope (specifying the set of affected functional modules), and policy priority (determining the execution order in case of conflicting decisions). The deployment package is also bound to the system configuration interface of the enterprise service platform to ensure that policy parameters can be injected into the target module on demand and can be automatically loaded at the module level. Based on the structural dependencies between functional modules and their spatial location coordinates, the policy deployment package is injected into the running unit where the target module is located, and the policy is dynamically loaded through the platform's built-in policy mounting mechanism. Dynamic loading allows the policy version to be updated while the system is running. By constructing a policy execution control flow chart, marking the policy trigger nodes, policy intervention paths and policy effectiveness modules, the control flow chart and the functional behavior model are maintained synchronously to reflect the policy response paths and the interaction between modules; Based on the operational environment after policy deployment, the platform system continuously monitors the status of functional modules within the policy's effective area, and automatically adjusts the policy's trigger frequency, action granularity, and parameter weights based on the interaction between modules and resource competition dynamics. On the one hand, after completing policy optimization and structured expression, the system locates the target module and its corresponding operating unit for each policy based on the structural dependencies between functional modules and their spatial location coordinates in the enterprise service platform. The system automatically injects the policy deployment package into the corresponding operating unit and dynamically loads the policy through the platform's built-in policy mounting mechanism. This dynamic loading process supports online hot deployment, which allows policy updates and version switching without stopping system operation, ensuring the continuity of policy effectiveness and minimal disruption to deployment. On the other hand, to ensure visual tracking and full-process control of the policy execution process, the system simultaneously constructs a policy execution control flow chart. This flow chart uses the policy trigger node as the starting point, clearly defines the policy intervention path (such as the resource adjustment path and the permission change link) and the policy action module, forming a complete policy response chain. The control flow chart is kept updated with the functional behavior model to depict the interaction evolution and dependency adjustment between platform functional modules after policy intervention, supporting the system to track and analyze operational behavior evolution at the policy level. After the policy is formally deployed and enters the running state, the system will continuously monitor the operating status of functional modules in the policy's effective area, and collect key indicators such as call frequency, response delay and resource usage changes; at the same time, the platform combines the dependencies between modules and the dynamics of resource competition to analyze in real time the impact of policy execution on the overall system stability; based on the monitoring results, the system can automatically adjust the policy triggering frequency (such as reducing the frequency of policy activation to alleviate system load), the granularity of action (such as refining module-level intervention to the interface level), and the weight configuration of policy parameters, so as to achieve adaptive dynamic adjustment and effect enhancement during the policy operation process.

[0026] Furthermore, when the policy execution effect is abnormal, a hierarchical rollback mechanism is triggered based on the abnormality level and system feedback information. The system records the relevant rollback events and operation data and updates the rollback knowledge base, including: By real-time monitoring of key operational features extracted based on functional behavior models during the execution of enterprise service platform control strategies, and automatically evaluating the execution effect of control strategies using comprehensive evaluation indicators, it is determined whether a rollback should be triggered. Based on the assessment results, the abnormalities are graded and classified into mild abnormalities, moderate abnormalities, and severe abnormalities; When a minor anomaly is identified, key parameters in the control strategy are automatically adjusted to attempt to restore system stability without the need for an immediate rollback. When parameter fine-tuning fails to achieve the expected results and the degree of anomaly is determined to be moderate, the impact of the policy on some key functional modules is gradually revoked, and a partial rollback is implemented to control the spread of the anomaly; When the abnormality is severe and a partial rollback fails to effectively alleviate the system abnormality, a full system rollback is performed to restore the enterprise service platform to its stable state before the policy adjustment. Based on the rollback process, the intelligent anomaly diagnosis module continuously analyzes the root cause of the anomaly and dynamically adjusts the execution strength and scope of the rollback strategy based on the anomaly level and system feedback. The system records all rollback events and related key operating data in real time and builds a rollback knowledge base.

[0027] Specifically, after a control strategy is deployed, the enterprise service platform system continuously monitors its performance during execution, constructing a set of operational characteristic indicators based on functional behavior models, such as the response latency of functional modules, the magnitude of resource utilization changes, and the frequency of abnormal event triggering. Key characteristic values ​​are extracted and recorded at fixed time intervals. The system uses a built-in comprehensive evaluation algorithm and combines these characteristic parameters to construct a multi-dimensional execution effect scoring model, forming a complete control strategy execution performance evaluation system. In actual implementation, the platform sets multi-level assessment thresholds. For example, the full score for the comprehensive score is 100 points. A score below 85 is considered a minor anomaly, a score below 70 is considered a moderate anomaly, and a score below 50 is considered a major anomaly. When the system score falls below the minor anomaly threshold (e.g., 85 points), the platform automatically triggers the anomaly determination process. When a minor anomaly is detected, the system first optimizes the policy through a parameter fine-tuning mechanism, such as adjusting key parameters such as resource allocation ratios, task scheduling intervals, or access permission granularity, in an attempt to restore the stability of the platform's operation without reversing the policy. If the execution effect still does not meet expectations after the parameter adjustment, and the score drops to the moderate anomaly range (e.g., below 70 points), the system will trigger a local rollback mechanism; the local rollback is based on the current functional behavior model and module dependency graph, locating the key modules within the affected range, revoking the policy's intervention configuration, and limiting the further spread of the anomaly; If the anomaly score further drops to a severe level (e.g., below 50 points) and the partial rollback fails to significantly alleviate the anomaly, the platform will initiate a full system rollback process, withdraw all deployed policies, and restore the platform to its pre-policy stable state based on the system operation status snapshot. During the entire policy exception handling process, the platform also dispatches the intelligent exception diagnosis module to conduct real-time analysis of multi-dimensional factors such as the exception triggering cause, propagation path, and intervention response. It also dynamically adjusts the rollback scope and execution rhythm to ensure that the rollback operation is targeted and controllable. The system simultaneously records policy version information, anomaly level determination results, triggering time, key parameter changes, and operational characteristic indicators related to all rollback events. This data is then stored in a rollback knowledge base, serving as decision support and strategy optimization for subsequent anomaly handling in similar scenarios. Through the continuous expansion and updating of the knowledge base, the platform system possesses a continuously evolving rollback response capability.

[0028] Furthermore, an intelligent management and control system for an enterprise service platform based on functional analysis is proposed, which is used to implement any of the above-mentioned intelligent management and control methods, specifically including: The raw data collection module is used to collect the operating data of each functional module in the enterprise service platform, including call frequency, resource utilization, response delay, user behavior trajectory and abnormal events; Data format standardization module: The data format standardization module is used to standardize the collected original operation data, generate data in a unified format and upload it to the data aggregation module; A multi-dimensional operation data flow construction module, which is used to perform time sequence alignment and field regularization on the standardized data and construct a multi-dimensional operation data flow; Functional behavior modeling module, which is used to establish a functional behavior model based on graph neural network and extract the operating characteristics of each functional module; Thermal score generation module: The thermal score generation module is used to fuse local performance tensors, user activity and abnormal disturbance factors to construct a thermal score function and generate a three-dimensional thermal score map; Key module identification and simulation module: This module is used to identify key functional modules based on the thermal score map, build corresponding functional twin copies, and test control strategies in a simulation environment. The control strategy generation and deployment module is used to build a multi-level strategy generation matrix, form candidate control strategy templates and deploy them to the target module; The execution effect evaluation and rollback module is used to monitor the policy execution effect in real time, trigger hierarchical rollback when an anomaly occurs, and update the rollback knowledge base.

[0029] Furthermore, the heat score generation module specifically includes: Performance tensor construction unit,The performance tensor construction unit extracts call frequency, resource occupancy, and response latency, and constructs a local performance tensor based on spatial coordinates and time series; User behavior modeling unit, which extracts user behavior trajectories and forms a user activity function; Abnormal perturbation learning unit: Based on the abnormal event feature sequence, the abnormal perturbation learning unit uses a deep autoencoder to unsupervisedly learn abnormal propagation and perturbation to form an abnormal perturbation factor; The time series scoring modeling unit takes the performance tensor, activity, and abnormal disturbance as input, performs joint time series modeling through LSTM, and outputs a thermal scoring function.

[0030] Furthermore, the key module identification and simulation module specifically includes: Key module identification unit: The key module identification unit uses the spatial distribution and temporal evolution trend of the thermal score map, combined with the functional behavior model, to automatically identify key functional modules with abnormal sudden increases in thermal values ​​and those that are continuously in a high-temperature state; Functional twin construction unit: This unit builds corresponding functional twin copies based on the structural dependencies and operational characteristics of key modules, thus realizing a simulation model isolated from the production environment. The strategy simulation test unit deploys control strategies in a simulation environment, replays the execution of strategy behavior trajectories, and collects feedback data on strategy performance and anomaly mitigation effects.

[0031] Furthermore, the execution effect evaluation and rollback module specifically includes: Execution effect evaluation unit: The execution effect evaluation unit monitors the execution effect of the strategy in real time and evaluates the execution status based on feedback indicators; Anomaly level determination unit, which classifies abnormality levels according to comprehensive evaluation indicators; Rollback strategy scheduling unit, which takes parameter adjustments, local rollbacks, or full system rollbacks based on the abnormality level; The rollback knowledge base construction unit records rollback events and key operation data and constructs a rollback knowledge base.

[0032] To sum up, the advantages of the present invention are: through the standardized collection and fusion of multi-dimensional operation data, combined with the graph neural network to build a functional behavior model, accurate state perception and dynamic feature extraction of the functional modules of the enterprise service platform can be achieved; based on the functional thermal score diagram and functional twin simulation copy, key modules can be effectively identified and management strategies can be optimized, supporting multi-level generation and adaptive evolution of strategies; in addition, the integration of real-time execution effect evaluation and hierarchical rollback mechanism, combined with intelligent anomaly diagnosis, can quickly respond to abnormal situations, ensure system stability and reliability, and comprehensively improve the platform's intelligent management level and operation efficiency.

[0033] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions merely illustrate the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent management and control method for an enterprise service platform based on functional analysis, characterized in that: include: Acquire multi-dimensional operation data streams and build functional behavior models through graph neural networks to comprehensively reflect the operation status and mutual relationships of functional modules and extract the operation characteristics of each functional module; Dynamically generate a function heat score map based on the operating characteristics of each function module, and use this heat score map to visualize the load distribution and abnormal hot spots of the function modules; Identify key functional modules based on the heat score graph, build functional twin copies for the identified key functional modules, and simulate the execution of the proposed control strategy in a simulation environment isolated from the production environment to obtain simulation feedback results. The control strategy refers to the control plan for key functional modules in terms of resource allocation, task scheduling, and access permission configuration; Based on the functional behavior model, heat score diagram, and functional twin replica simulation feedback results, a multi-level control strategy generation matrix is ​​constructed to generate candidate control strategy templates. Through the strategy optimization and deployment mechanism, a self-evolving control strategy set is formed and deployed to the enterprise service platform. By real-time monitoring of key operational features extracted from functional behavior models during the execution of enterprise service platform management and control strategies, and combining control flow charts with feedback indicators, we dynamically evaluate the effectiveness of strategy execution and drive a closed-loop feedback mechanism to achieve strategy self-adaptation. When the policy execution effect is abnormal, the hierarchical rollback mechanism is triggered according to the abnormality level and system feedback information. The system records the relevant rollback events and operation data and updates the rollback knowledge base.

2. The method for intelligent management and control of an enterprise service platform based on functional analysis according to claim 1, characterized in that: The multi-dimensional operation data stream is obtained, and a functional behavior model is constructed through a graph neural network to comprehensively reflect the operation status and mutual relationship of the functional modules and extract the operation characteristics of each functional module. Specifically, the following steps are involved: Based on the industrial communication protocol, the distributed control system (DCS), programmable logic controller (PLC), edge acquisition terminal, and user interaction log system connected to each functional module in the enterprise service platform are accessed. The call frequency, resource utilization, response latency, user behavior trajectory, and operation data corresponding to abnormal events generated by each functional module during operation are collected to obtain the original operation data set. The collected raw operating data is input into the data adaptation middleware deployed at the platform access layer, and the format is standardized and converted to obtain standardized operating data in a unified format. The data is then uploaded in batches to the data aggregation module of the enterprise service platform based on preset time intervals. The data aggregation module performs time synchronization, field regularization, and preliminary verification on the standardized operation data to obtain a multi-dimensional operation data stream; Based on the multi-dimensional operation data flow, the functional behavior modeling method of graph neural network is used to construct a functional behavior model, which integrates the interactive topological structure between functional modules with the dynamic indicator sequence related to resource utilization and behavioral response, and extracts the structural dependency and operation characteristics of each functional module.

3. The intelligent management and control method of an enterprise service platform based on functional analysis according to claim 1 is characterized in that: The function heat score map is dynamically generated based on the operating characteristics of each function module, and the heat score map is used to visualize the load distribution and abnormal hot spots of the function modules, specifically including: Based on call frequency, resource occupancy, and response latency, a local performance tensor is constructed to describe the module performance status. ,in, is the spatial coordinate of the module, For time, , corresponding to the three indicators of call frequency, resource occupancy and response delay; Combined with user behavior trajectory data, a deep clustering algorithm is used to model the user's access frequency and path pattern between different functional modules, construct a spatial activity distribution map, and extract the corresponding access heat intensity function. , represents the user activity mapping in space; From the constructed multi-dimensional operational data stream, feature dimensions related to system anomalies are extracted, including system error codes, retry behaviors, and interface response timeout logs, to construct a feature sequence of abnormal events. Based on the feature sequence of abnormal events, the time series feature extraction method is adopted, and the deep autoencoder is used to perform unsupervised learning on the propagation path, disturbance intensity and scope of abnormal events to generate an abnormal disturbance factor function that describes the abnormal evolution state. ; Through the time series modeling method, the temporal changes of local performance tensors, user activity and abnormal disturbance factors are integrated to generate the spatiotemporal thermal scoring function of the functional module: , in, Indicates spatial location No. The input feature vector at time is defined as: ； Where, Respectively represent the modules in Call frequency, resource utilization, and response latency at each moment; Indicates that the position User access activity at all times, Indicates the Abnormal disturbance factor at the moment; Based on the thermal value output by the thermal scoring function, a three-dimensional functional thermal scoring map is constructed, and the module load and abnormal distribution dynamics are visualized in the form of a heat map.

4. The method for intelligent management and control of an enterprise service platform based on functional analysis according to claim 1, characterized in that: The process involves identifying key functional modules based on the heat score graph, building functional twin copies for the identified key functional modules, and simulating the execution of the proposed control strategies in a simulation environment isolated from the production environment to obtain simulation feedback results, specifically including: Based on the spatial distribution characteristics and temporal evolution trend of thermal values ​​in the three-dimensional functional thermal score map, combined with the structural dependencies between modules, key functional modules with abnormally high thermal values ​​and persistently high thermal states are identified. For the identified key functional modules, in a simulation environment isolated from the enterprise service platform production environment, we construct corresponding functional twin copies based on the structural dependencies and operational characteristics extracted from the functional behavior model and the historical evolution trajectory of the modules during operation. In the functional twin copy, multiple candidate control strategies are formulated by combining resource allocation, task scheduling, and access permission configuration. These strategies are then pre-screened based on the system's historical control strategy execution feedback information to obtain multiple preliminary screening control strategy solutions. By deploying an interactive simulation sandbox with the ability to replay behavior trajectories and record intervention responses, the execution process of the initial screening control strategy plan in the functional twin copy is simulated, the performance of each candidate control strategy in the simulation environment and the mitigation effect on abnormal propagation are collected, and the simulation feedback results of the candidate control strategy are obtained.

5. The method for intelligent management and control of an enterprise service platform based on functional analysis according to claim 1, characterized in that: Based on the functional behavior model, heat score diagram, and the simulation feedback results of the functional twin replica, a multi-level control strategy generation matrix is ​​constructed to generate candidate control strategy templates. A self-evolving control strategy set is formed through the strategy optimization and deployment mechanism and deployed to the enterprise service platform. Specifically, it includes: Based on the operating characteristics of key functional modules in the functional behavior model, the thermal distribution status and its evolution trend in the thermal score diagram, and the multi-dimensional simulation feedback results in the twin simulation environment, a multi-level control strategy generation matrix is ​​constructed. The generation matrix uses the functional module identifier as the index dimension and the resource intervention parameters, scheduling sequence parameters, and authority configuration parameters as the strategy dimensions. Multiple candidate control strategy templates are generated through multi-dimensional cross-combination. The candidate control strategy templates are input into the strategy optimization module. Based on the performance indicator response curve, abnormal propagation change trajectory and task execution offset recorded in the simulation feedback results, a feedback-driven strategy optimization mechanism is used to dynamically select the control strategy set with the best matching performance. Performing a structured expression on the control policy set to generate a policy deployment package, which includes a policy parameter mapping table, policy trigger conditions, policy scope, and policy effectiveness priority, and is mapped and bound to the system configuration interface of the enterprise service platform; Based on the structural dependencies between functional modules and their spatial location coordinates, the policy deployment package is injected into the running unit where the target module is located, and the policy is dynamically loaded through the platform's built-in policy mounting mechanism. The dynamic loading allows the policy version to be updated while the system is running; By constructing a policy execution control flow chart, marking the policy trigger node, policy intervention path and policy effectiveness module, the control flow chart is maintained synchronously with the functional behavior model to reflect the policy response path and the interaction relationship between modules; Based on the operating environment after policy deployment, the platform system continuously monitors the status of functional modules within the policy-effective area, and automatically adjusts the policy triggering frequency, action granularity and parameter weights based on the interaction between modules and resource competition dynamics.

6. The method for intelligent management and control of an enterprise service platform based on functional analysis according to claim 1, characterized in that: When the policy execution effect is abnormal, the hierarchical rollback mechanism is triggered according to the abnormality level and system feedback information, and the system records the relevant rollback events and operation data and updates the rollback knowledge base, specifically including: By real-time monitoring of key operational features extracted based on functional behavior models during the execution of enterprise service platform control strategies, and automatically evaluating the execution effect of control strategies using comprehensive evaluation indicators, it is determined whether a rollback should be triggered. Based on the assessment results, the abnormalities are graded and classified into mild abnormalities, moderate abnormalities, and severe abnormalities; When a minor anomaly is identified, key parameters in the control strategy are automatically adjusted to attempt to restore system stability without the need for an immediate rollback. When parameter fine-tuning fails to achieve the expected results and the abnormality is judged to be moderate, the impact of the policy on some key functional modules will be gradually revoked, and a partial rollback will be implemented to control the spread of the abnormality; When the abnormality is severe and a partial rollback fails to effectively alleviate the system abnormality, a full system rollback is performed to restore the enterprise service platform to its stable state before the policy adjustment. Based on the rollback process, the intelligent anomaly diagnosis module continuously analyzes the root cause of the anomaly and dynamically adjusts the execution strength and scope of the rollback strategy based on the anomaly level and system feedback. The system records all rollback events and related key operating data in real time and builds a rollback knowledge base.

7. An intelligent management and control system for an enterprise service platform based on functional analysis, for implementing the intelligent management and control method according to any one of claims 1 to 6, specifically comprising: A raw data collection module, which is used to collect operational data of each functional module in the enterprise service platform, including call frequency, resource utilization, response latency, user behavior trajectory, and abnormal events; A data format standardization module is used to standardize the collected raw operating data, generate data in a unified format, and upload it to the data aggregation module; A multi-dimensional operation data flow construction module, which is used to perform time sequence alignment and field regularization on the standardized data and construct a multi-dimensional operation data flow; A functional behavior modeling module, which is used to establish a functional behavior model based on a graph neural network and extract the operating characteristics of each functional module; A thermal score generation module, which is used to fuse local performance tensors, user activity, and abnormal disturbance factors to construct a thermal score function and generate a three-dimensional thermal score map; Key module identification and simulation module, which is used to identify key functional modules based on the thermal score map, build corresponding functional twin copies, and test the control strategy in a simulation environment; A control strategy generation and deployment module, which is used to construct a multi-level strategy generation matrix, form candidate control strategy templates, and deploy them to the target module; The execution effect evaluation and rollback module is used to monitor the policy execution effect in real time, trigger hierarchical rollback when an anomaly occurs, and update the rollback knowledge base.

8. The enterprise service platform intelligent management and control system based on function analysis according to claim 7 is characterized in that: The thermal score generation module specifically includes: A performance tensor construction unit, which extracts call frequency, resource occupancy, and response latency, and constructs a local performance tensor according to spatial coordinates and time series; A user behavior modeling unit, which extracts user behavior trajectories and forms a user activity function; An abnormal disturbance learning unit, which uses a deep autoencoder to perform unsupervised learning of abnormal propagation and disturbance based on the abnormal event feature sequence to form an abnormal disturbance factor; The time series scoring modeling unit takes the performance tensor, activity, and abnormal disturbance as input, performs joint time series modeling through LSTM, and outputs a thermal scoring function.

9. The enterprise service platform intelligent management and control system based on function analysis according to claim 7 is characterized in that: The key module identification and simulation module specifically includes: A key module identification unit, which uses the spatial distribution and temporal evolution trend of the thermal score map in combination with the functional behavior model to automatically identify key functional modules with abnormally increased thermal values ​​or those that are continuously in a high-temperature state; A functional twin construction unit, which builds corresponding functional twin copies based on the structural dependencies and operational characteristics of key modules to implement a simulation model isolated from the production environment; A strategy simulation test unit deploys control strategies in a simulation environment, executes strategy behavior trajectory playback, and collects strategy performance and anomaly mitigation effect feedback data.

10. The enterprise service platform intelligent management and control system based on function analysis according to claim 7, characterized in that: The execution effect evaluation and rollback module specifically includes: An execution effect evaluation unit, which monitors the execution effect of the strategy in real time and evaluates the execution status based on feedback indicators; An abnormality level determination unit, wherein the abnormality level determination unit classifies abnormality levels according to comprehensive evaluation indicators; A rollback policy scheduling unit, which performs parameter adjustment, local rollback, or full system rollback according to the abnormality level; The rollback knowledge base construction unit records rollback events and key operation data to construct a rollback knowledge base.

Images