Intelligent operation and maintenance terminal management and control method, device, equipment and storage medium

Abstract

The present invention relates to the field of operation and maintenance terminal management and control technology, and in particular to a management and control method, device, equipment and storage medium for intelligent operation and maintenance terminals. The method includes the following steps: obtaining historical terminal operation and maintenance logs and real-time terminal operation and maintenance status data; filtering outliers on the historical terminal operation and maintenance logs, and performing semantic feature analysis to generate operation and maintenance entity structure feature data; performing temporal logic association analysis on the operation and maintenance entity structure feature data to generate an entity dependency temporal logic diagram; constructing a terminal operation and maintenance logic map based on the entity dependency temporal logic diagram; performing multi-dimensional state feature analysis on the real-time terminal operation and maintenance status data, and performing temporal state transition fitting to construct an operation and maintenance state trend transition curve; performing stage trend feature mining on the operation and maintenance state trend transition curve to obtain multiple stage trend representation vectors. The present invention realizes efficient and safe operation and maintenance terminal management and control.

Description

Technical Field

[0001] The present invention relates to the field of operation and maintenance terminal management and control technology, and in particular to a management and control method, device, equipment and storage medium for an intelligent operation and maintenance terminal. Background Art

[0002] In the contemporary industrial environment, intelligent operation and maintenance terminals, as key equipment management tools, play an important role in monitoring, diagnosing and managing equipment status. With the continuous development of industrial Internet, Internet of Things and artificial intelligence technologies, intelligent operation and maintenance terminals are gradually becoming a key link in realizing intelligent equipment management and predictive maintenance. In the long-term operation process, intelligent operation and maintenance terminals face various challenges, such as equipment failure, performance degradation, safety hazards, etc., which will have a significant impact on production efficiency and equipment stability. Traditional operation and maintenance terminal management methods mainly rely on manual intervention and manual analysis, and there are problems such as low safety and low efficiency of operation and maintenance control. In order to meet the needs of modern industrial environments for intelligent operation and maintenance terminal management, an intelligent operation and maintenance terminal control method is urgently needed. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a management and control method, device, equipment and storage medium for an intelligent operation and maintenance terminal to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a method for controlling an intelligent operation and maintenance terminal, comprising the following steps:

[0005] Step S1: Obtain historical terminal operation and maintenance logs and real-time terminal operation and maintenance status data; filter outliers from historical terminal operation and maintenance logs, and perform semantic feature analysis to generate operation and maintenance entity structure feature data;

[0006] Step S2: Perform temporal logic association analysis on the operation and maintenance entity structure feature data to generate an entity dependency temporal logic diagram; construct a terminal operation and maintenance logic map based on the entity dependency temporal logic diagram;

[0007] Step S3: Perform multi-dimensional state feature analysis on the real-time terminal operation and maintenance state data, perform time series state transition fitting, and construct an operation and maintenance state trend transition curve;

[0008] Step S4: mining the stage trend features of the operation and maintenance status trend change curve to obtain multiple stage trend representation vectors; performing operation and maintenance situation prediction based on the multiple stage trend representation vectors to generate operation and maintenance status situation prediction data;

[0009] Step S5: Based on the terminal operation and maintenance logic map, the state transition deviation analysis is performed on the operation and maintenance status situation prediction data, and abnormal risk analysis is performed to obtain abnormal operation and maintenance risk data;

[0010] Step S6: Dynamically visualize the abnormal operation and maintenance risk data to generate a visualization view of the risk diffusion path; make adaptive risk management decisions on the visualization view of the risk diffusion path to build an operation and maintenance risk safety management strategy.

[0011] The present invention also provides a control device for an intelligent operation and maintenance terminal, comprising:

[0012] The semantic analysis module obtains historical terminal operation and maintenance logs and real-time terminal operation and maintenance status data; filters outliers from historical terminal operation and maintenance logs, and performs semantic feature analysis to generate operation and maintenance entity structure feature data;

[0013] The logic graph module performs temporal logic association analysis on the operation and maintenance entity structure feature data to generate an entity dependency temporal logic graph; and constructs a terminal operation and maintenance logic graph based on the entity dependency temporal logic graph;

[0014] The trend change module performs multi-dimensional status feature analysis on real-time terminal operation and maintenance status data, performs time series state change fitting, and constructs an operation and maintenance status trend change curve;

[0015] The situation prediction module mines the stage trend characteristics of the operation and maintenance status trend change curve to obtain multiple stage trend representation vectors; the operation and maintenance situation prediction is performed based on the multiple stage trend representation vectors to generate the operation and maintenance status situation prediction data;

[0016] The abnormal risk module performs state transition deviation analysis on the operation and maintenance status prediction data based on the terminal operation and maintenance logic map, and performs abnormal risk analysis to obtain abnormal operation and maintenance risk data;

[0017] The risk management and control module dynamically visualizes abnormal operation and maintenance risk data to generate a visualization of the risk diffusion path; it makes adaptive risk management and control decisions on the visualization of the risk diffusion path and builds an operation and maintenance risk safety management and control strategy.

[0018] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the management and control method of the intelligent operation and maintenance terminal described in any one of the above items are implemented.

[0019] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for controlling the intelligent operation and maintenance terminal described in any one of the above items are implemented.

[0020] The intelligent operation and maintenance terminal management and control method, device, equipment and storage medium provided by the present invention have the following beneficial effects: outlier filtering and semantic feature analysis are used to identify and process abnormal situations in data, improve data quality, generate operation and maintenance entity structure feature data to provide a basis for subsequent analysis, help understand the relationship and characteristics between operation and maintenance entities, build a terminal operation and maintenance logic map to show the correlation between terminal operation and maintenance entities, deepen the understanding of the overall structure of the system, fit the time series state change to reveal the law of state change, provide data support for subsequent prediction, build an operation and maintenance state trend change curve to monitor the changing trend of the system state, help predict the future state, stage trend feature mining discovers the law and trend of state change, and provides a more accurate basis for prediction, generates operation and maintenance state situation prediction data to help predict the future system state, take corresponding measures in advance, extract abnormal risk data to identify potential problems and risks, and improve the safety and stability of the system, and intuitively understand and analyze the risk propagation path through dynamic visualization processing and risk diffusion path visualization view generation, provide a basis for decision-making, and build an operation and maintenance risk safety management and control strategy to help respond to risk events in a timely manner, so as to ensure the operation and maintenance safety and stability of intelligent terminals. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic diagram of the steps of a method for controlling an intelligent operation and maintenance terminal according to the present invention;

[0022] Figure 2 Detailed implementation flow chart of step S1;

[0023] Figure 3 is a schematic diagram of a detailed implementation process of step S3;

[0024] Figure 4 It is a schematic diagram of the detailed implementation steps of step S4. DETAILED DESCRIPTION

[0025] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0026] The example of this application provides a method, device, equipment and storage medium for the management and control of an intelligent operation and maintenance terminal. The execution subjects of the method, device, equipment and storage medium for the management and control of the intelligent operation and maintenance terminal include but are not limited to: mechanical equipment, data processing platform, cloud server node, network upload equipment, etc. equipped with the system can be regarded as the general computing node of this application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0027] In the embodiment of the present invention, refer to Figure 1, is a schematic flow chart of the steps of a method for controlling a smart operation and maintenance terminal of the present invention. In this example, the steps of the method for controlling a smart operation and maintenance terminal include:

[0028] Step S1: Obtain historical terminal operation and maintenance logs and real-time terminal operation and maintenance status data; filter outliers from historical terminal operation and maintenance logs, and perform semantic feature analysis to generate operation and maintenance entity structure feature data;

[0029] In this embodiment, historical terminal operation and maintenance log data, including fault logs, maintenance records, etc., are obtained from the enterprise's terminal management system. The terminal device status monitoring system collects the terminal device's operating status data in real time, such as CPU usage, memory usage, hard disk usage, etc. The historical log data is cleaned and formatted to remove invalid information and abnormal characters. The log data is classified and aggregated according to key information such as timestamps and terminal IDs in the logs. For real-time monitoring data, data sampling and aggregation are performed regularly to generate a time series of status indicators for each terminal device. An outlier detection algorithm is applied to the historical log data, such as outlier detection based on statistical distribution and machine learning-based detection. Anomaly detection, etc., identify problematic operation and maintenance events, set threshold rules for real-time monitoring data, monitor in real time whether various indicators are beyond the normal range, discover abnormal conditions in a timely manner, perform natural language processing on abnormal log events, extract key entity information, such as fault type, impact range, solution, etc., build an operation and maintenance knowledge base, associate the extracted semantic features with historical operation and maintenance data, form operation and maintenance entity structure feature data, organize the processed operation and maintenance entity structure feature data into visual reports or dashboards for operation and maintenance personnel to query and analyze, and push abnormal events of real-time monitoring data to relevant operation and maintenance personnel for processing in a timely manner through API or message queue.

[0030] Step S2: Perform temporal logic association analysis on the operation and maintenance entity structure feature data to generate an entity dependency temporal logic diagram; construct a terminal operation and maintenance logic map based on the entity dependency temporal logic diagram;

[0031] In this embodiment, the time series associations between entities are analyzed, and the causal logic and temporal dependencies between entities are identified by using time series analysis, event association mining and other methods to construct an entity dependency temporal logic diagram to represent the temporal sequence dependencies between operation and maintenance entities. The entity nodes in the entity dependency temporal logic diagram are mapped to operation and maintenance knowledge fields such as terminal equipment, fault types, and solutions. The semantic associations between entities are improved by combining domain knowledge and expert experience, and the interpretability of the graph is improved. The graph database technology is used to construct a terminal operation and maintenance logic graph to support complex graph queries and reasoning analysis.

[0032] Step S3: Perform multi-dimensional state feature analysis on the real-time terminal operation and maintenance state data, perform time series state transition fitting, and construct an operation and maintenance state trend transition curve;

[0033] In this embodiment, the real-time terminal operation and maintenance status data obtained includes indicators such as CPU usage, memory usage, and hard disk usage. These status indicator data are statistically analyzed to calculate basic features such as mean, variance, and peak. In combination with domain knowledge, the normal range and abnormal threshold of each status indicator are defined. The real-time value of each indicator is compared with the normal range to identify abnormal states with problems. The time series data of the status indicators of each terminal device are smoothed and interpolated to eliminate noise and fill in missing values. Time series analysis methods, such as autoregressive moving average (ARIMA) models, neural networks, etc., are used to perform trend prediction on the status indicator data. According to the prediction results, the change trend curve of each status indicator in the future period is drawn.

[0034] Step S4: mining the stage trend features of the operation and maintenance status trend change curve to obtain multiple stage trend representation vectors; performing operation and maintenance situation prediction based on the multiple stage trend representation vectors to generate operation and maintenance status situation prediction data;

[0035] In this embodiment, the curve data is segmented and analyzed to identify key turning points and change stages in the curve. For each change stage, corresponding statistical features, such as mean, slope, variance, etc., are extracted as the trend characterization vector of that stage. The trend characterization vectors of each terminal device at different stages are organized into a sample data set. Based on the sample data set, machine learning models, such as time series prediction models and anomaly detection models, are trained. The trained prediction models are used to perform situation prediction on the operation and maintenance status in the future.

[0036] Step S5: Based on the terminal operation and maintenance logic map, the state transition deviation analysis is performed on the operation and maintenance status situation prediction data, and abnormal risk analysis is performed to obtain abnormal operation and maintenance risk data;

[0037] In this embodiment, the generated operation and maintenance status situation prediction data is collected, including the status prediction of each terminal device in the future time period. Combined with the terminal operation and maintenance logic map, analyze whether there is a deviation between the predicted state and the normal state transfer logic defined in the map. For the prediction results that deviate from the normal state transfer, identify the abnormal state transition that occurs. According to the severity of the abnormal state transition, combined with the scope of fault impact and difficulty of resolution recorded in the map, evaluate and score its risk. For abnormal states with higher evaluation scores, further analyze the root causes and chain reactions, and evaluate the risk level of the overall operation and maintenance system. Detailed information on high-risk abnormal states, such as fault type, scope of impact, solution, etc., is organized into a report.

[0038] Step S6: Dynamically visualize the abnormal operation and maintenance risk data to generate a visualization view of the risk diffusion path; make adaptive risk management decisions on the visualization view of the risk diffusion path to build an operation and maintenance risk safety management strategy.

[0039] In this embodiment, dynamic visualization technology is used, such as an interactive topology map based on D3.js, to generate a visualization view of the risk diffusion path, highlighting the occurrence point of the risk event, the transmission path, and the affected key entities in the view. For the visualization view of the risk diffusion path, combined with the formulated risk management and control strategy, the feasibility and effectiveness of various response measures are analyzed, and domain knowledge and expert experience are used to formulate corresponding management and control decisions for each risk event, such as isolating the affected equipment, launching emergency plans, etc., to establish a risk management and control knowledge base based on the graph, to associate the management and control decisions with the entities and relationships in the graph, to form a closed-loop risk management mechanism, to monitor real-time operation and maintenance data, to identify abnormal risk events in real time, to automatically generate targeted management and control strategies in combination with the risk management and control knowledge base, and to push them to the operation and maintenance personnel for execution in a timely manner, to track and evaluate the execution of the management and control strategies, and to continuously optimize the management and control decisions in the knowledge base.

[0040] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0041] Step S11: Obtain historical terminal operation and maintenance logs and real-time terminal operation and maintenance status data;

[0042] Step S12: Calculate the mean of operation and maintenance parameters for the historical terminal operation and maintenance logs to obtain the mean range of the operation and maintenance parameters;

[0043] Step S13: filtering the historical terminal operation and maintenance logs for outliers according to the mean range of the operation and maintenance parameters to generate filtered terminal operation and maintenance logs;

[0044] Step S14: performing semantic feature analysis on the filtered terminal operation and maintenance logs to extract multiple key operation and maintenance entities;

[0045] Step S15: Perform deep structural feature mining on multiple key operation and maintenance entities to generate operation and maintenance entity structural feature data.

[0046] In this embodiment, after obtaining the terminal device authorization, the real-time terminal operation and maintenance status data is obtained from the log file, database, monitoring system, etc. of the terminal device. The real-time terminal operation and maintenance status data is obtained from the monitoring system, sensor, etc. of the terminal device. The historical terminal operation and maintenance log and the real-time terminal operation and maintenance status data are in multiple formats, such as text files, database records, JSON format, etc. Relevant operation and maintenance parameters are extracted from the historical terminal operation and maintenance log, such as CPU usage, memory usage, disk space usage, network traffic, etc. The extracted operation and maintenance parameters are averaged to obtain the average value of each parameter. According to statistical indicators such as the mean and standard deviation, the mean range of each operation and maintenance parameter is determined. It is determined whether there are abnormal values ​​in the historical terminal operation and maintenance log. Multiple methods are used to filter the abnormal values, such as the 3σ rule, the box plot method, cluster analysis, etc., to generate a filtered terminal operation and maintenance log, which contains normal values ​​and existing abnormal values. Natural language processing (NLP) is used The technology performs semantic analysis on the filtered terminal operation and maintenance logs. For example, part-of-speech tagging, named entity recognition, dependency syntax analysis and other technologies are used to extract multiple key operation and maintenance entities from the analysis results, such as terminal device name, fault type, timestamp, operator, etc., and analyze the relationship between key entities, such as the association between terminal device name and fault type. Machine learning, deep learning and other technologies are used to perform deep structural feature mining on multiple key operation and maintenance entities. For example, cluster analysis, association rule mining, neural network and other technologies are used to generate operation and maintenance entity structure feature data based on the mining results, such as the characteristics of different fault types, the characteristics of different terminal devices, etc. The generated operation and maintenance entity structure feature data is used for applications such as fault prediction, anomaly detection, and operation and maintenance optimization.

[0047] In this embodiment, the specific steps of step S2 are:

[0048] Step S21: performing dependency evolution analysis between entities on the operation and maintenance entity structure feature data, thereby obtaining dependency relationships between multiple entities;

[0049] Step S22: performing temporal logic association analysis on dependency relationships among multiple entities to generate an entity dependency temporal logic diagram;

[0050] Step S23: performing entity interaction frequency statistics on the operation and maintenance entity structure feature data, thereby generating operation and maintenance entity interaction frequency data;

[0051] Step S24: implicitly structure the operation and maintenance entity interaction frequency data based on the entity dependency time sequence logic diagram to construct a terminal operation and maintenance logic graph;

[0052] The temporal logic association analysis is specifically as follows:

[0053] Extract entity dependency timestamps based on dependency relationships between multiple entities;

[0054] Calculate the semantic similarity of the operation and maintenance entity structure feature data to generate entity semantic similarity;

[0055] Based on the entity dependency timestamp, the dependency relationships between multiple entities are analyzed for temporal logic association, thereby obtaining the dependency temporal logic;

[0056] Analyze entity interaction paths based on entity semantic similarity to generate association links between entities;

[0057] According to the dependency timing logic, the associated links between entities are globally logically linked to generate an entity dependency timing logic diagram.

[0058] In this embodiment, machine learning or deep learning models are used to analyze the operation and maintenance entity structure feature data, for example, using models such as Bayesian networks, Markov chains, and neural networks. Analyze different types of dependencies, such as causal relationships, correlation relationships, and time dependencies. Analyze the strength of different dependencies, such as strong dependencies, weak dependencies, etc. Use a temporal logic analysis method to analyze the dependencies between multiple entities, for example, using methods such as temporal logic reasoning and timing diagrams. According to the analysis results, an entity dependency timing logic diagram is generated, for example, using a graphical tool or programming language. The entity dependency timing logic diagram contains information such as multiple entities, dependencies between entities, and the time sequence of dependency occurrence. Count the number of interactions between different entities, such as the number of interactions between different terminal devices, the number of interactions between different fault types, etc. Calculate the interaction frequency between different entities based on the number of interactions and time period. Generate operation and maintenance entity interaction frequency data, for example, using tables, charts, etc. Integrate the entity dependency timing logic diagram and the operation and maintenance entity interaction frequency data, and use graph theory, network analysis, and other technologies for implicit structured processing. Build a terminal operation and maintenance logic map, which includes information such as multiple entities, dependencies between entities, and interaction frequencies between entities.

[0059] Furthermore, the specific implementation steps of the temporal logic association analysis are as follows: extracting the timestamp of each dependency from the dependencies between multiple entities. The timestamp is in date and time format, for example, "2024-08-22 10:00:00", which is also in timestamp format. The extracted entity dependency timestamp is stored in a data structure, and the semantic similarity of the operation and maintenance entity structure feature data is calculated using natural language processing (NLP) technology, for example, using word vectors, semantic networks, deep learning models and other methods. Different similarity indicators are used, for example, cosine similarity, Jaccard similarity, edit distance and the like. The calculated entity semantic similarity is stored in a similarity matrix, and the rows and columns of the matrix represent different entities respectively. The entity dependency timestamp is analyzed using a temporal logic analysis method, for example, using temporal logic reasoning, a temporal diagram and other methods. The temporal logic relationship of the dependency between different entities is extracted from the analysis results, for example, entity A depends on entity B, entity B depends on entity C, entity C depends on entity D, etc. Use different ways to express temporal logic relationships, for example, text descriptions, graphical displays, logical expressions, etc. Use graph theory, network analysis and other technologies to analyze the entity semantic similarity matrix, for example, using shortest path algorithms, centrality analysis and other methods. Based on the analysis results, generate inter-entity association links, for example, the association link between entity A and entity B, the association link between entity B and entity C, etc. Weight the association links according to the entity semantic similarity, for example, the higher the semantic similarity of the entity, the higher the weight of its association link. Integrate the entity dependency temporal logic and the association links between entities, and use graph theory, network analysis and other technologies to perform global logical link processing. Generate an entity dependency temporal logic diagram, which contains information such as multiple entities, dependency relationships between entities, association links between entities, and the time order in which dependency relationships occur.

[0060] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0061] Step S31: performing multi-dimensional status feature analysis on the real-time terminal operation and maintenance status data to obtain multi-dimensional operation and maintenance status features;

[0062] Step S32: Analyze the time series changes of the multi-dimensional operation and maintenance status characteristics to generate operation and maintenance status time series change data;

[0063] Step S33: performing periodic state fluctuation trend evolution on the operation and maintenance state time series change data to generate periodic state trend data;

[0064] Step S34: Perform time series state transition fitting on the periodic state trend data to construct an operation and maintenance state trend transition curve.

[0065] In this embodiment, a time series analysis method is used to analyze the multi-dimensional operation and maintenance status characteristics, for example, a moving average method, an exponential smoothing method, an autoregressive model (AR), a moving average model (MA), an autoregressive moving average model (ARMA), etc. are used to analyze the temporal change trend of each state feature, for example, an upward trend, a downward trend, a stable trend, etc., and generate operation and maintenance status time series change data, for example, using charts, tables, etc. to display, and a periodic analysis method is used to analyze the operation and maintenance status time series change data, for example, using Fourier transform, autocorrelation function, etc. methods, to identify the periodic change trend of each state feature, for example, daily, weekly, monthly and other periods, to generate periodic state trend data, for example, using charts, tables, etc. to display, and a curve fitting method is used to fit the periodic state trend data, for example, using linear regression, polynomial regression, exponential regression, etc. methods, to select a suitable curve type, for example, a linear curve, an exponential curve, a sine curve, etc., to reflect the time series change trend of the state characteristics, and to construct an operation and maintenance state trend change curve, for example, using a graphical tool or a programming language to generate.

[0066] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S4. In this embodiment, the detailed implementation steps of step S4 include:

[0067] Step S41: performing dynamic sliding window decomposition on the operation and maintenance status trend change curve to obtain operation and maintenance status trend samples at multiple time points;

[0068] Step S42: mining stage trend features for operation and maintenance status trend samples at multiple time points, thereby obtaining multiple stage trend representation vectors;

[0069] Step S43: predicting the future operation and maintenance situation of the operation and maintenance state trend change curve according to the multiple stage trend characterization vectors, and generating operation and maintenance state situation prediction data.

[0070] In this embodiment, the dynamic sliding window technology is used to decompose the operation and maintenance status trend change curve, for example, a sliding window of fixed size or a sliding window of adaptive size is used. The appropriate window size is selected according to the data characteristics and prediction requirements, for example, according to factors such as time period and data change frequency. Each sliding window corresponds to an operation and maintenance status trend sample, which contains the status data of all time points in the window. The stage trend characteristics are extracted from each operation and maintenance status trend sample, and the characteristics of the operation and maintenance status trend samples in each time window are analyzed, such as the average value, fluctuation degree, change rate, etc., and multi-dimensional indicators that can represent the trend characteristics of different stages are extracted to form stage trend characterization vectors. These characterization vectors can be used to describe and distinguish the operation and maintenance status change trends in different time periods. The aforementioned extracted multiple stage trend characterization vectors are input into the prediction model for learning and training. The trained prediction model is used to predict the development of the operation and maintenance status situation in a certain period of time in the future according to the current operation and maintenance status trend change, and generate situation prediction data reflecting the future operation and maintenance status prediction results.

[0071] In this embodiment, the specific steps of step S5 are:

[0072] Step S51: performing situation trajectory evolution on the operation and maintenance status situation prediction data, thereby obtaining an operation and maintenance situation prediction trajectory;

[0073] Step S52: performing state transition deviation analysis on the operation and maintenance situation prediction trajectory based on the terminal operation and maintenance logic map, and extracting the situation prediction deviation trajectory;

[0074] Step S53: performing deviation change logic identification on the situation prediction deviation trajectory, thereby generating deviation trajectory change logic data;

[0075] Step S54: performing abnormal risk analysis on the operation and maintenance status situation prediction data according to the deviation trajectory change logic data, thereby obtaining abnormal operation and maintenance risk data.

[0076] In this embodiment, the operation and maintenance status situation prediction data are arranged in chronological order to form a continuous prediction trajectory. The operation and maintenance situation prediction trajectory contains the prediction status information at each time point, such as CPU usage, memory usage, network traffic, etc. The prediction trajectory reflects the change trend of the operation and maintenance state in a certain period of time in the future. The operation and maintenance situation prediction trajectory is compared with the terminal operation and maintenance logic map to analyze the deviation between the predicted state and the actual state. The deviation is a positive deviation, a negative deviation, no deviation, etc. All deviation information is arranged in chronological order to form a situation prediction deviation trajectory. The situation prediction deviation trajectory is analyzed using a time series analysis method, for example, using a moving average method, an exponential smoothing method, an autoregressive model (AR), a moving average model (MA), an autoregressive moving average model (ARMA), etc. Identify the law and logic of the deviation change, for example, the deviation gradually increases, the deviation changes periodically, the deviation suddenly jumps, etc. Generate the deviation trajectory change logic data, for example, using a table, a chart, etc. to display it. According to the logic data of deviation trajectory changes, analyze the abnormal risk of operation and maintenance status situation prediction data, and evaluate the level of abnormal operation and maintenance risks according to the deviation change logic and risk impact, such as low risk, medium risk, high risk, etc.

[0077] In this embodiment, the specific steps of step S6 are:

[0078] Step S61: Identify the risk diffusion evolution of abnormal operation and maintenance risk data to obtain potential risk diffusion paths;

[0079] Step S62: dynamically visualize the potential risk diffusion path to generate a risk diffusion path visualization view;

[0080] Step S63: Perform comprehensive risk diagnosis and evaluation on the risk diffusion path visualization view to obtain an operation and maintenance risk evaluation value;

[0081] Step S64: Make adaptive risk management decisions on abnormal operation and maintenance risk data based on the operation and maintenance risk assessment value, and build an operation and maintenance risk safety management strategy.

[0082] In this embodiment, the correlation and propagation characteristics of abnormal operation and maintenance risk data are analyzed, and the risk diffusion path and propagation mode are predicted by using methods such as graph algorithms or system modeling. The identified risk diffusion path is displayed in a visual way, such as a network diagram, a tree diagram, etc., and interactive visualization methods are used to intuitively reflect the dynamic process of risk diffusion. According to the characteristics of the risk diffusion path, combined with the risk propagation model, the probability of occurrence and potential impact of various risk events are evaluated, and the overall operation and maintenance risk assessment value is obtained through comprehensive analysis. According to the risk assessment results, targeted risk control measures are taken, such as emergency plans, resource allocation, etc., to build a dynamically adjustable operation and maintenance risk safety control strategy, realize adaptive risk control, and build an operation and maintenance risk safety control strategy according to decision rules. For example, use automated scripts, rule engines, artificial intelligence and other technologies to realize risk control. Dynamically adjust and optimize the risk control strategy according to actual conditions, for example, according to risk change trends, environmental factors, etc.

[0083] In this embodiment, the present invention further provides a control device for an intelligent operation and maintenance terminal, including:

[0084] The semantic analysis module obtains historical terminal operation and maintenance logs and real-time terminal operation and maintenance status data; filters outliers from historical terminal operation and maintenance logs, and performs semantic feature analysis to generate operation and maintenance entity structure feature data;

[0085] The logic graph module performs temporal logic association analysis on the operation and maintenance entity structure feature data to generate an entity dependency temporal logic graph; and constructs a terminal operation and maintenance logic graph based on the entity dependency temporal logic graph;

[0086] The trend change module performs multi-dimensional status feature analysis on real-time terminal operation and maintenance status data, performs time series state change fitting, and constructs an operation and maintenance status trend change curve;

[0087] The situation prediction module mines the stage trend characteristics of the operation and maintenance status trend change curve to obtain multiple stage trend representation vectors; the operation and maintenance situation prediction is performed based on the multiple stage trend representation vectors to generate the operation and maintenance status situation prediction data;

[0088] The abnormal risk module performs state transition deviation analysis on the operation and maintenance status prediction data based on the terminal operation and maintenance logic map, and performs abnormal risk analysis to obtain abnormal operation and maintenance risk data;

[0089] The risk management and control module dynamically visualizes abnormal operation and maintenance risk data to generate a visualization of the risk diffusion path; it makes adaptive risk management and control decisions on the visualization of the risk diffusion path and builds an operation and maintenance risk safety management and control strategy.

[0090] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the management and control method of the intelligent operation and maintenance terminal described in any one of the above items are implemented.

[0091] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for controlling the intelligent operation and maintenance terminal described in any one of the above items are implemented.

[0092] Those skilled in the art clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0093] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it is stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or partly or all or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media for storing program codes such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks or optical disks.

[0094] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0095] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for controlling an intelligent operation and maintenance terminal, characterized in that: The following steps are involved: Step S1: Obtain historical terminal operation and maintenance logs and real-time terminal operation and maintenance status data; filter outliers from historical terminal operation and maintenance logs, and perform semantic feature analysis to generate operation and maintenance entity structure feature data; Step S2: Perform temporal logic association analysis on the operation and maintenance entity structure feature data to generate an entity dependency temporal logic diagram; construct a terminal operation and maintenance logic map based on the entity dependency temporal logic diagram; The specific steps of step S2 are: Step S21: performing dependency evolution analysis between entities on the operation and maintenance entity structure feature data, thereby obtaining dependency relationships between multiple entities; Step S22: performing temporal logic association analysis on dependency relationships among multiple entities to generate an entity dependency temporal logic diagram; Step S23: performing entity interaction frequency statistics on the operation and maintenance entity structure feature data, thereby generating operation and maintenance entity interaction frequency data; Step S24: implicitly structure the operation and maintenance entity interaction frequency data based on the entity dependency time sequence logic diagram to construct a terminal operation and maintenance logic graph; The temporal logic association analysis is specifically as follows: Extract entity dependency timestamps based on dependency relationships between multiple entities; Calculate the semantic similarity of the operation and maintenance entity structure feature data to generate entity semantic similarity; Based on the entity dependency timestamp, the dependency relationships between multiple entities are analyzed for temporal logic association, thereby obtaining the dependency temporal logic; Analyze entity interaction paths based on entity semantic similarity to generate association links between entities; Perform global logical link processing on the association links between entities according to the dependency temporal logic to generate an entity dependency temporal logic diagram; Step S3: Perform multi-dimensional state feature analysis on the real-time terminal operation and maintenance state data, perform time series state transition fitting, and construct an operation and maintenance state trend transition curve; Step S4: mining the stage trend features of the operation and maintenance status trend change curve to obtain multiple stage trend representation vectors; performing operation and maintenance situation prediction based on the multiple stage trend representation vectors to generate operation and maintenance status situation prediction data; The specific steps of step S4 are: Step S41: performing dynamic sliding window decomposition on the operation and maintenance status trend change curve to obtain operation and maintenance status trend samples at multiple time points; Step S42: mining stage trend features for the multi-time point operation and maintenance status trend samples, thereby obtaining multiple stage trend representation vectors; Step S43: predicting the future operation and maintenance situation of the operation and maintenance state trend change curve according to the multiple stage trend characterization vectors, and generating operation and maintenance state situation prediction data; Step S5: Based on the terminal operation and maintenance logic map, the state transition deviation analysis is performed on the operation and maintenance status situation prediction data, and abnormal risk analysis is performed to obtain abnormal operation and maintenance risk data; Step S6: Dynamically visualize the abnormal operation and maintenance risk data to generate a visualization view of the risk diffusion path; Make adaptive risk management decisions based on the visualization of risk diffusion paths and build an operation and maintenance risk safety management strategy.

2. The method for controlling the intelligent operation and maintenance terminal according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: Obtain historical terminal operation and maintenance logs and real-time terminal operation and maintenance status data; Step S12: Calculate the mean of operation and maintenance parameters for the historical terminal operation and maintenance logs to obtain the mean range of the operation and maintenance parameters; Step S13: filtering the historical terminal operation and maintenance logs for outliers according to the mean range of the operation and maintenance parameters to generate filtered terminal operation and maintenance logs; Step S14: performing semantic feature analysis on the filtered terminal operation and maintenance logs to extract multiple key operation and maintenance entities; Step S15: Perform deep structural feature mining on multiple key operation and maintenance entities to generate operation and maintenance entity structural feature data.

3. The method for controlling the intelligent operation and maintenance terminal according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: performing multi-dimensional status feature analysis on the real-time terminal operation and maintenance status data to obtain multi-dimensional operation and maintenance status features; Step S32: Analyze the time series changes of the multi-dimensional operation and maintenance status characteristics to generate operation and maintenance status time series change data; Step S33: performing periodic state fluctuation trend evolution on the operation and maintenance state time series change data to generate periodic state trend data; Step S34: Perform time series state transition fitting on the periodic state trend data to construct an operation and maintenance state trend transition curve.

4. The method for controlling the intelligent operation and maintenance terminal according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: performing situation trajectory evolution on the operation and maintenance status situation prediction data, thereby obtaining an operation and maintenance situation prediction trajectory; Step S52: performing state transition deviation analysis on the operation and maintenance situation prediction trajectory based on the terminal operation and maintenance logic map, and extracting the situation prediction deviation trajectory; Step S53: performing deviation change logic identification on the situation prediction deviation trajectory, thereby generating deviation trajectory change logic data; Step S54: performing abnormal risk analysis on the operation and maintenance status situation prediction data according to the deviation trajectory change logic data, thereby obtaining abnormal operation and maintenance risk data.

5. The method for controlling the intelligent operation and maintenance terminal according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: Identify the risk diffusion evolution of abnormal operation and maintenance risk data to obtain potential risk diffusion paths; Step S62: dynamically visualize the potential risk diffusion path to generate a risk diffusion path visualization view; Step S63: Perform comprehensive risk diagnosis and evaluation on the risk diffusion path visualization view to obtain an operation and maintenance risk evaluation value; Step S64: Make adaptive risk management decisions on abnormal operation and maintenance risk data based on the operation and maintenance risk assessment value, and build an operation and maintenance risk safety management strategy.

6. A control device for an intelligent operation and maintenance terminal, characterized in that: The method for executing the management and control of the intelligent operation and maintenance terminal according to claim 1 comprises: The semantic analysis module obtains historical terminal operation and maintenance logs and real-time terminal operation and maintenance status data; filters outliers from historical terminal operation and maintenance logs, and performs semantic feature analysis to generate operation and maintenance entity structure feature data; The logic graph module performs temporal logic association analysis on the operation and maintenance entity structure feature data to generate an entity dependency temporal logic graph; and constructs a terminal operation and maintenance logic graph based on the entity dependency temporal logic graph; The trend change module performs multi-dimensional status feature analysis on real-time terminal operation and maintenance status data, performs time series state change fitting, and constructs an operation and maintenance status trend change curve; The situation prediction module mines the stage trend characteristics of the operation and maintenance status trend change curve to obtain multiple stage trend representation vectors; the operation and maintenance situation prediction is performed based on the multiple stage trend representation vectors to generate the operation and maintenance status situation prediction data; The abnormal risk module performs state transition deviation analysis on the operation and maintenance status prediction data based on the terminal operation and maintenance logic map, and performs abnormal risk analysis to obtain abnormal operation and maintenance risk data; The risk management and control module dynamically visualizes abnormal operation and maintenance risk data to generate a visualization of the risk diffusion path; it makes adaptive risk management and control decisions on the visualization of the risk diffusion path and builds an operation and maintenance risk safety management and control strategy.

7. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method for controlling the intelligent operation and maintenance terminal according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for controlling the intelligent operation and maintenance terminal according to any one of claims 1 to 5 are implemented.

Images