Intelligent operation and maintenance method and system based on data assets

Abstract

This invention relates to the field of data information processing technology, and discloses an intelligent operation and maintenance method and system based on data assets. The method includes: collecting device status data through a distributed IoT sensor cluster; standardizing the raw data and optimizing the data transmission path based on a dynamic topology network; dynamically adjusting the data model structure according to real-time data streams; performing multi-dimensional detection based on user-configured data quality rules to generate a quality detection report; cleaning abnormal data in real time based on the detection results to generate an interactive decision view; predicting operation and maintenance risk events using a multi-algorithm fusion model; and dynamically adjusting the workflow task execution path according to the risk level. This method optimizes the data acquisition and transmission process, improves the real-time performance and accuracy of data quality monitoring, and enhances the intelligence of abnormal data processing and operation and maintenance risk prediction, making operation and maintenance management more flexible and efficient.

Description

Technical Field

[0001] This invention relates to the field of data information processing technology, and in particular to an intelligent operation and maintenance method and system based on data assets. Background Technology

[0002] With the rapid development of information technology, especially the maturity of technologies such as the Internet of Things (IoT), big data, and cloud computing, intelligent operation and maintenance (O&M) has gradually become an important part of modern enterprise management. Implementing intelligent O&M enables enterprises to achieve efficient resource management and optimization decisions through real-time monitoring of equipment status and operational data. The widespread application of IoT sensors makes equipment data collection more convenient and efficient; and through big data analytics, enterprises can predict faults, reduce costs, and improve equipment utilization efficiency. Furthermore, combined with artificial intelligence (AI) technology, intelligent O&M supports deep learning and analysis of massive amounts of data, helping to form adaptive and intelligent O&M strategies. This trend has already achieved significant results in various fields (such as manufacturing, power, and transportation), driving the intelligent transformation of equipment management.

[0003] While existing technologies have made some progress in intelligent operation and maintenance (O&M), several significant shortcomings remain. One major issue is the stability and efficiency of data transmission. In practical applications, IoT sensors often face difficulties such as communication latency and data packet loss, directly impacting data real-time performance and integrity. Furthermore, existing data models struggle to dynamically adjust to real-time data streams, often employing static models that cannot adapt to rapidly changing operating conditions. Simultaneously, the lack of effective data quality monitoring methods leads to delayed identification and processing of abnormal data, affecting the accuracy of O&M decisions. Moreover, existing methods typically rely on a single algorithm for risk prediction, failing to fully leverage the advantages of multiple algorithms, resulting in poor prediction performance. Therefore, to address these shortcomings, this invention proposes an intelligent O&M method based on data assets. This method aims to comprehensively improve the intelligence level of O&M by building a distributed IoT sensor cluster, optimizing data transmission paths, and utilizing dynamically adjusted data models and multi-algorithm fusion risk prediction models. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides an intelligent operation and maintenance method based on data assets, which can solve the problems of insufficient data reliability, lack of real-time performance, and inflexible handling of abnormal situations in traditional operation and maintenance management.

[0006] To address the aforementioned technical problems, this invention provides the following technical solution: an intelligent operation and maintenance method based on data assets, comprising: collecting device status data through a distributed IoT sensor cluster; standardizing the raw data and optimizing the data transmission path based on a dynamic topology network; dynamically adjusting the data model structure according to real-time data streams; performing multi-dimensional detection in conjunction with user-configured data quality rules to generate a quality detection report; cleaning abnormal data in real time based on the detection results to generate an interactive decision view; predicting operation and maintenance risk events using a multi-algorithm fusion model and dynamically adjusting the workflow task execution path according to the risk level.

[0007] As a preferred embodiment of the intelligent operation and maintenance method based on data assets described in this invention, the method includes: collecting device status data via an intelligent data sensing network through a distributed IoT sensor cluster; optimizing data transmission paths between sensor nodes based on a dynamic topology network; periodically broadcasting its own communication latency and packet loss rate to neighboring nodes; constructing a weighted graph structure network based on the received status data of neighboring nodes; dynamically selecting the current optimal transmission path based on Dijkstra's algorithm; and monitoring the link status in real time during data transmission. If the packet loss rate exceeds a threshold, path reselection is triggered.

[0008] As a preferred embodiment of the intelligent operation and maintenance method based on data assets described in this invention, the dynamic adjustment of the data model structure includes: receiving standardized data streams transmitted from a distributed IoT sensor cluster in real time; dividing the data into batches according to a preset time window; extracting statistical features for each data batch and comparing the feature similarity with the previous batch; when the feature similarity is lower than a set threshold, triggering model parameter adjustment and updating the model weights through incremental learning; expanding or shrinking the model input feature dimensions; and having the adjusted model version coexist with historical versions for comparison by visualization analysis tools.

[0009] As a preferred embodiment of the intelligent operation and maintenance method based on data assets described in this invention, the multi-dimensional detection includes configuring data quality rules using a self-service data quality monitoring platform and performing multi-dimensional data quality detection. The field integrity threshold calculation for data quality rules uses an improved dynamic integrity formula: ; in, The threshold for field integrity. for, The weight of the k-th field. This represents the total number of samples. The time decay factor, It is a non-empty index function. When field The value is 1 if the value is not empty, and 0 otherwise. The system generates a visual decision view through multi-dimensional data visualization and analysis tools. Users can select fields from the data quality inspection results as analysis dimensions by dragging and dropping. The system automatically associates with the historical operation and maintenance database, aggregates data by time dimension, and generates comparison curves. It supports selecting abnormal data areas in the visualization view and triggers data cleaning to locate the corresponding original data.

[0010] As a preferred embodiment of the intelligent operation and maintenance method based on data assets described in this invention, the real-time cleaning of abnormal data includes correcting the abnormal data, and the semantic conflict detection of the real-time data cleaning engine adopts an improved similarity calculation formula: ; in, For semantic similarity, Let i be the term frequency-inverse document frequency of the i-th feature. For feature weights, For predefined data schema templates, For word similarity calculation based on the Jaccard coefficient, The variance of the current data stream, The number of features.

[0011] As a preferred embodiment of the intelligent operation and maintenance method based on data assets described in this invention, the multi-algorithm fusion model includes: a decision tree module that prioritizes screening the top N fields in terms of feature importance; a time series analysis module that periodically detects the screened fields and marks data points that deviate from the historical fluctuation range; a clustering analysis module that performs density clustering on the marked data points to generate a set of candidate risk events; and users can adjust the input parameter weights of each module and view intermediate calculation results through a visual interface.

[0012] As a preferred embodiment of the intelligent operation and maintenance method based on data assets described in this invention, the dynamic adjustment of the workflow task execution path includes classifying risk events based on the prediction results of a multi-algorithm fusion model and formulating corresponding control strategies for each level. When the detection is low risk, continue the normal process and monitor regularly; when the detection is medium risk, increase the frequency of reviews and tests, and trigger additional review steps; when the detection is high risk, pause the current workflow and initiate emergency response procedures.

[0013] As a preferred embodiment of the intelligent operation and maintenance system based on data assets described in this invention, it includes: a data acquisition and transmission optimization module, a data quality monitoring and adjustment module, an abnormal data cleaning and decision support module, a risk prediction and assessment module, and a dynamic workflow management module. The data acquisition and transmission optimization module uses a distributed IoT sensor cluster to collect device status data in real time. The data quality monitoring and adjustment module performs multi-dimensional data quality detection on the received real-time data stream according to the quality rules configured by the user. The abnormal data cleaning and decision support module cleans the detected abnormal data in real time, including correction and semantic conflict detection. The risk prediction and assessment module uses a multi-algorithm fusion model to predict operation and maintenance risk events, and generates a set of candidate risk events by ranking the importance of features and marking data points that deviate from historical fluctuations. The dynamic workflow management module dynamically adjusts the execution path of workflow tasks based on risk prediction results.

[0014] A computer device includes a memory and a processor, the memory storing a computer program, characterized in that the processor executes the computer program to implement the steps of an intelligent operation and maintenance method based on data assets.

[0015] A computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of an intelligent operation and maintenance method based on data assets.

[0016] The beneficial effects of this invention are as follows: By constructing a distributed IoT sensor network and a dynamic topology data transmission path, real-time and efficient data acquisition is achieved, significantly reducing data latency and packet loss rate. The dynamic data model adjustment mechanism enables the operation and maintenance system to adapt to rapidly changing operating environments, effectively improving the model's accuracy and adaptability. Self-service data quality monitoring allows for real-time identification and cleaning of abnormal data, supporting high-quality data-driven decision-making. Combining multi-algorithm fusion models for risk assessment not only improves the prediction accuracy of risk events but also effectively formulates corresponding control strategies, thereby significantly enhancing the intelligence level of the entire operation and maintenance process and effectively addressing many limitations of traditional intelligent operation and maintenance technologies. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of an intelligent operation and maintenance method based on data assets, provided as an embodiment of the present invention.

[0019] Figure 2 This is a schematic diagram of the working modules of an intelligent operation and maintenance system based on data assets, provided as an embodiment of the present invention. Detailed Implementation

[0020] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0021] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0023] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0024] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0025] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0026] Example 1, referring to Figure 1 This is the first embodiment of the present invention, which provides an intelligent operation and maintenance method based on data assets, including: S1: Collect device status data through a distributed IoT sensor cluster, standardize the raw data, and optimize the data transmission path based on a dynamic topology network.

[0027] Furthermore, the intelligent data sensing network collects data through a distributed IoT sensor cluster. Data transmission paths between sensor nodes are optimized based on a dynamic topology network. Each sensor node periodically broadcasts its communication latency and packet loss rate to neighboring nodes. Based on the received state data from neighboring nodes, a weighted graph structure network is constructed. The weights are calculated as follows: ; in, Let i be the weight from node i to node j. The coefficients configured for the user. Let be the delay time from node i to node j. Let be the packet loss rate from node i to node j; The system dynamically selects the current optimal transmission path based on Dijkstra's algorithm and monitors the link status in real time during data transmission. If the packet loss rate exceeds the threshold, path reselection is triggered.

[0028] It should be noted that the raw data includes, but is not limited to, support for manual single-entry data entry, batch entry, and template import; automatic and real-time data collection; and the formulation, execution, and monitoring of data collection plans.

[0029] This system assists users in entering data assets by defining templates and automatically verifies the legality of the entered data. It supports uploading and importing data in the common Excel format and automatically verifies template files. It also embeds a web-based spreadsheet, providing batch data operations and real-time verification. This solves the problem of timely data validity and accuracy verification in Excel operations under normal circumstances, improving the user experience while significantly increasing the efficiency and quality of data submission.

[0030] It integrates with business systems to acquire master data in full or incremental form through data collection, and initializes the data through data cleaning, integration, and transformation. It uses various common databases as data sources for data extraction, including but not limited to MySQL, Oracle, SQL Server, and DM. When submitting application forms, it supports online deduplication and similarity matching checks based on the defined rules of the data model. It provides automatic prompts for system data verification during the data creation application process, and supports attachment uploads such as PDF, JPG, WORD, and EXCEL, with online viewing support.

[0031] S2: Dynamically adjust the data model structure based on real-time data streams, perform multi-dimensional detection in conjunction with user-configured data quality rules, and generate a quality detection report.

[0032] Furthermore, it receives standardized data streams transmitted from a distributed IoT sensor cluster in real time, divides the data into batches according to a preset time window, extracts statistical features for each data batch, and compares the feature similarity with the previous batch. When the feature similarity is lower than a set threshold, it triggers model parameter adjustment and updates the model weights through incremental learning. It expands or shrinks the model input feature dimension. The adjusted model version coexists with the historical version for comparison by visualization analysis tools.

[0033] It should be noted that data quality rules are configured using a self-service data quality monitoring platform to perform multi-dimensional data quality checks. The field integrity threshold calculation for data quality rules uses an improved dynamic integrity formula: ; in, The threshold for field integrity. for, The weight of the k-th field. This represents the total number of samples. The time decay factor, It is a non-empty index function. When field The value is 1 if the value is not empty, and 0 otherwise. The system generates a visual decision view through multi-dimensional data visualization and analysis tools. Users can select fields from the data quality inspection results as analysis dimensions by dragging and dropping. The system automatically associates with the historical operation and maintenance database, aggregates data by time dimension, and generates comparison curves. It supports selecting abnormal data areas in the visualization view and triggers data cleaning to locate the corresponding original data.

[0034] Furthermore, it supports defining verification rules for data assets, maximizing the uniqueness and standardization of data assets. The system's verification functions include, but are not limited to, configurable verification rules. The system intelligently verifies the input format and accuracy of data assets based on configuration, customization, or the code repository, and supports cascading attribute verification. The system's verification functions support the specifications and standards used during data creation, ensuring the uniqueness, integrity, consistency, and validity of user-entered data.

[0035] Field validation rules include, but are not limited to: required fields, uniqueness, value range, default value, length, pure characters, pure numbers, regular expressions, and complex logic validation.

[0036] S3: Clean abnormal data in real time based on the detection results and generate an interactive decision view.

[0037] Furthermore, to correct abnormal data, the real-time data cleaning engine uses an improved similarity calculation formula for semantic conflict detection: ; in, For semantic similarity, Let i be the term frequency-inverse document frequency of the i-th feature. For feature weights, For predefined data schema templates, For word similarity calculation based on the Jaccard coefficient, The variance of the current data stream, The number of features.

[0038] It should be noted that data management through an interactive decision view consists of three parts: metadata management, master data management, and data quality management. Metadata management collects and manages metadata from database tables, maintaining data lineage. The master data system provides the definition of master data standards, enabling business process management based on these standards. Data quality management checks data quality from dimensions such as integrity, standardization, and consistency, providing end-to-end monitoring of problematic data discovery, analysis, and resolution. Users can conveniently and efficiently manage data visually through data management functions, clearly understanding information related to databases, tables, data lineage, and data quality within the data warehouse. It also enables comprehensive screening and precise location of data quality issues, assisting managers in managing data quality through a visual interface.

[0039] S4: Utilize a multi-algorithm fusion model to predict operational risk events and dynamically adjust workflow task execution paths based on risk levels.

[0040] Furthermore, the multi-algorithm fusion model includes: a decision tree module that prioritizes the N fields with the highest feature importance; a time series analysis module that performs periodic checks on the selected fields and marks data points that deviate from the historical fluctuation range; and a cluster analysis module that performs density clustering on the marked data points to generate a set of candidate risk events. Users can adjust the input parameter weights of each module and view intermediate calculation results through a visual interface.

[0041] Furthermore, based on the prediction results of the multi-algorithm fusion model, risk events are classified and corresponding control strategies are formulated for each level; When the detection is low risk, continue the normal process and monitor regularly; when the detection is medium risk, increase the frequency of reviews and tests, and trigger additional review steps; when the detection is high risk, pause the current workflow and initiate emergency response procedures.

[0042] It should be noted that comprehensive process management functions are provided, supporting system administrators to customize processes at different levels. This includes adding, editing, deleting, publishing, and deactivating process instances, configuring process forms, and configuring flowcharts. Process forms need to support WYSIWYG drag-and-drop controls; approval steps in the flowchart can be drawn by dragging and dropping; nodes in the process can be associated with approvers / roles, and nodes can be associated with multiple approvers / roles simultaneously. Processes can be exported as independent files with one click, and process files can be imported, enabling rapid online process publishing, which is ready to use immediately after publishing.

[0043] Example 2, the second embodiment of the present invention, differs from the previous embodiment in that: If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0044] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0045] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0046] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0047] Example 3, referring to Figure 2 As an embodiment of the present invention, an intelligent operation and maintenance system based on data assets is provided, characterized in that it includes a data acquisition and transmission optimization module, a data quality monitoring and adjustment module, an abnormal data cleaning and decision support module, a risk prediction and assessment module, and a dynamic workflow management module. The data acquisition and transmission optimization module utilizes a distributed IoT sensor cluster to collect device status data in real time. The data quality monitoring and adjustment module performs multi-dimensional data quality checks on the received real-time data stream according to the quality rules configured by the user. The abnormal data cleaning and decision support module cleans the detected abnormal data in real time, including correction and semantic conflict detection. The risk prediction and assessment module uses a multi-algorithm fusion model to predict operational risk events. By ranking the importance of features, it marks data points that deviate from historical fluctuations and generates a set of candidate risk events. The dynamic workflow management module dynamically adjusts the execution path of workflow tasks based on risk prediction results.

[0048] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A smart operation and maintenance method based on data assets, characterized in that: include, Device status data is collected through a distributed IoT sensor cluster, the raw data is standardized, and the data transmission path is optimized based on a dynamic topology network. The data model structure is dynamically adjusted based on real-time data streams, and multi-dimensional detection is performed in conjunction with user-configured data quality rules to generate a quality detection report. Based on the detection results, abnormal data is cleaned in real time to generate an interactive decision view; A multi-algorithm fusion model is used to predict operational risk events, and the workflow task execution path is dynamically adjusted according to the risk level.

2. The intelligent operation and maintenance method based on data assets as described in claim 1, characterized in that: The acquired device status data includes data collected by the intelligent data sensing network through a distributed IoT sensor cluster. Data transmission paths are optimized between sensor nodes based on a dynamic topology network. Each sensor node periodically broadcasts its own communication latency and packet loss rate to neighboring nodes. Based on the received status data of neighboring nodes, a weighted graph structure network is constructed. The optimal transmission path is dynamically selected based on Dijkstra's algorithm. The link status is monitored in real time during data transmission. If the packet loss rate exceeds a threshold, path reselection is triggered.

3. The intelligent operation and maintenance method based on data assets as described in claim 2, characterized in that: The dynamic adjustment of the data model structure includes receiving the standardized data stream transmitted by the distributed IoT sensor cluster in real time, dividing the data into batches according to a preset time window, extracting statistical features for each data batch, and comparing the feature similarity with the previous batch. When the feature similarity is lower than a set threshold, the model parameters are adjusted, and the model weights are updated through incremental learning; the model input feature dimensions are expanded or contracted; the adjusted model version coexists with the historical version for comparison by visualization analysis tools.

4. The intelligent operation and maintenance method based on data assets as described in claim 3, characterized in that: The multi-dimensional detection includes configuring data quality rules using a self-service data quality monitoring platform and performing multi-dimensional data quality detection. The field integrity threshold calculation for data quality rules uses an improved dynamic integrity formula: ； in, The threshold for field integrity. for, The weight of the k-th field. This represents the total number of samples. The time decay factor, It is a non-empty index function. When field The value is 1 if the value is not empty, and 0 otherwise. The system generates a visual decision view through multi-dimensional data visualization and analysis tools. Users can select fields from the data quality inspection results as analysis dimensions by dragging and dropping. The system automatically associates with the historical operation and maintenance database, aggregates data by time dimension, and generates comparison curves. It supports selecting abnormal data areas in the visualization view and triggers data cleaning to locate the corresponding original data.

5. The intelligent operation and maintenance method based on data assets as described in claim 4, characterized in that: The real-time cleaning of abnormal data includes correcting the abnormal data, and the semantic conflict detection of the real-time data cleaning engine adopts an improved similarity calculation formula: ； in, For semantic similarity, Let i be the term frequency-inverse document frequency of the i-th feature. For feature weights, For predefined data schema templates, For word similarity calculation based on the Jaccard coefficient, The variance of the current data stream, The number of features.

6. The intelligent operation and maintenance method based on data assets as described in claim 5, characterized in that: The multi-algorithm fusion model includes a decision tree module that prioritizes filtering the top N fields based on feature importance. The time series analysis module performs periodic checks on the filtered fields and marks data points that deviate from the historical fluctuation range; The clustering analysis module performs density clustering on the labeled data points to generate a set of candidate risk events; Users can adjust the input parameter weights of each module through a visual interface and view intermediate calculation results.

7. The intelligent operation and maintenance method based on data assets as described in claim 6, characterized in that: The dynamic adjustment of workflow task execution paths includes classifying risk events based on the prediction results of a multi-algorithm fusion model and formulating corresponding control strategies for each level. When the detection is low risk, continue the normal process and monitor regularly; when the detection is medium risk, increase the frequency of reviews and tests, and trigger additional review steps; when the detection is high risk, pause the current workflow and initiate emergency response procedures.

8. A system employing an intelligent operation and maintenance method based on data assets as described in any one of claims 1 to 7, characterized in that: It includes a data acquisition and transmission optimization module, a data quality monitoring and adjustment module, an abnormal data cleaning and decision support module, a risk prediction and assessment module, and a dynamic workflow management module; The data acquisition and transmission optimization module uses a distributed IoT sensor cluster to collect device status data in real time. The data quality monitoring and adjustment module performs multi-dimensional data quality detection on the received real-time data stream according to the quality rules configured by the user. The abnormal data cleaning and decision support module cleans the detected abnormal data in real time, including correction and semantic conflict detection. The risk prediction and assessment module uses a multi-algorithm fusion model to predict operation and maintenance risk events, and generates a set of candidate risk events by ranking the importance of features and marking data points that deviate from historical fluctuations. The dynamic workflow management module dynamically adjusts the execution path of workflow tasks based on risk prediction results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images