A method and system for identifying and diagnosing operation and maintenance function items based on big data

Abstract

The present invention relates to the technical field of big data analysis, and discloses a method and system for identifying and diagnosing operation and maintenance function items based on big data, comprising: constructing a life cycle evolution tree of the operation and maintenance function items to form nodes and branches; each node represents a functional state, and a branch represents the degradation of the state; by evolving the life cycle of the operation and maintenance function items, obtaining the functional state of the operation and maintenance function items at each node position in the life cycle evolution tree; calculating the matching degree using the current node position of the operation and maintenance function item and the actual data when the operation and maintenance function is triggered each time; updating the position of the node where the operation and maintenance function item is located according to the calculation result; generating a diagnosis result of the operation and maintenance function item according to the matching degree and the node position; the present invention has the characteristics of intelligence, adaptability and strong interpretability, can significantly improve operation and maintenance efficiency, reduce maintenance costs, and is suitable for operation and maintenance management needs in complex systems and high reliability scenarios.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and specifically to a method and system for identifying and diagnosing operation and maintenance function items based on big data. Background Art

[0002] Current information systems typically enter a long-term operation and maintenance phase after construction is completed. The quality and efficiency of operation and maintenance work directly affect the stability, availability, and affordability of the system. However, existing information projects generally face many problems in the management of operation and maintenance costs. On the one hand, there is a lack of a unified and scientific maintenance cost accounting system. There are large differences between different projects in budget preparation, cost sharing, and resource allocation, making it difficult to accurately assess the rationality of maintenance expenditures, which can easily lead to waste of resources or insufficient investment. On the other hand, the operation and maintenance process relies heavily on manual experience for problem identification and troubleshooting. Faced with multi-module and multi-dimensional data changes in complex systems, it is often difficult to detect potential risks in a timely manner, resulting in delayed responses, extended maintenance cycles, and reduced service quality.

[0003] In addition, existing operation and maintenance management technologies mainly focus on static monitoring and alarm rules, lack the ability to structured modeling and data-driven analysis of the system behavior evolution process, and are difficult to cover complex scenarios such as software and hardware collaboration, system state degradation, and operating parameter sensitivity. Especially when dealing with high-precision equipment, large-scale heterogeneous systems or real-time diagnosis needs, their adaptability and intelligence are obviously insufficient. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a method for identifying and diagnosing operation and maintenance function items based on big data, comprising:

[0006] Construct a lifecycle evolution tree for the operation and maintenance function items, forming nodes and branches; each node represents the function status, and the branch represents the degradation of the status;

[0007] By evolving the life cycle of the operation and maintenance function item, the functional state of each node position of the operation and maintenance function item in the life cycle evolution tree is obtained;

[0008] The matching degree is calculated using the current node position of the operation and maintenance function item and the actual data when the operation and maintenance function is triggered each time; based on the calculation result, the position of the node where the operation and maintenance function item is located is updated;

[0009] Generating a diagnosis result of an operation and maintenance function item according to the matching degree and the node position;

[0010] The location update includes utilizing the big data during operation to perform the matching analysis on the functional status of the node where the operation and maintenance function item is located and the actual data when the operation and maintenance function is triggered each time, so as to obtain the node to be assigned; performing a historical analysis based on the positional relationship between the nodes to be assigned, so as to determine the assigned node of the operation and maintenance function item, and updating the node position based on the assigned node.

[0011] As a preferred embodiment of the method for identifying and diagnosing operation and maintenance function items based on big data of the present invention, the operation and maintenance function items include functional modules that can respond to the perception of multiple parameters during operation; the functional modules can execute specific operation and maintenance actions based on the perception of the operating parameters when the operating parameters meet the trigger conditions;

[0012] Preset thresholds for the k operating parameters that each operation and maintenance function item can respond to, and use embedded trigger rules to determine whether the operating parameters can meet the trigger conditions;

[0013] Among them, k represents the number of operating parameters that can respond to the operation and maintenance function items in advance;

[0014] The preset threshold values of k operating parameters of the operation and maintenance function items are used as the functional states of the initial nodes of the lifecycle evolution tree; according to the degradation process of each operating parameter perceived by the operation and maintenance function, at the current node, the degradation of each operating parameter threshold is simulated separately to form a lower node after the degradation of each operating parameter threshold;

[0015] Each time the degradation process is simulated, only one operating parameter threshold is degraded, and the degraded operating parameter threshold and other operating parameter thresholds of the current node are used as a lower-level node functional state; after completing the degradation of each operating parameter threshold one by one, the functional state of all lower nodes of the current node is formed.

[0016] As a preferred embodiment of the big data-based operation and maintenance function item identification and diagnosis method of the present invention, the degradation process includes determining the degradation direction of each operating parameter based on the operating parameter threshold and the trigger rule, and each time degradation occurs, degrading the operating parameter threshold by one step according to the degradation direction;

[0017] The degradation direction includes: if the operation parameter is higher than the corresponding threshold when the operation and maintenance function is not triggered, then the degradation direction is judged to be reducing the operation parameter threshold; if the operation parameter is not higher than the corresponding threshold when the operation and maintenance function is not triggered, then the degradation direction is judged to be increasing the operation parameter threshold.

[0018] As a preferred embodiment of the big data-based operation and maintenance function item identification and diagnosis method of the present invention, the current node position of the operation and maintenance function item includes the result of updating the node position of the operation and maintenance function item in the life cycle evolution tree through each identification and diagnosis of the operation and maintenance function item, starting from the initial node of the life cycle evolution tree;

[0019] The actual data when the operation and maintenance function is triggered includes the operation parameter values when the operation and maintenance function is triggered during actual operation.

[0020] As a preferred solution of the big data-based operation and maintenance function item identification and diagnosis method described in the present invention, the matching degree includes: among all downstream nodes corresponding to the upper node adjacent to the current node, the vector representation of the function state of each node is , and the vector representation of the operating parameters when the operation and maintenance function is triggered for the last m times , perform weighted Euclidean distance calculation, add one to the result and take the reciprocal;

[0021] Where m represents the preset number of historical records to filter; represents the i-th node; is the vector representation of the functional state of the i-th node; Indicates the kth operating parameter threshold corresponding to the node functional status; Indicates the kth operating parameter value when the operating parameter triggers the operation and maintenance function; It is the vector representation of the operating parameters when the operation and maintenance function is triggered for the dth time.

[0022] As a preferred solution of the big data-based operation and maintenance function item identification and diagnosis method of the present invention, wherein: the node to be assigned includes a node whose matching degree is higher than a preset threshold;

[0023] Assume that: there is an adjacent relationship between adjacent nodes connected by the life cycle evolution tree, and the distance is one unit; there is an adjacent relationship between each node with the same adjacent upper node, and the distance is one unit;

[0024] The position relationship includes performing path calculation between nodes having an adjacent relationship to obtain the distance between each two nodes to be assigned;

[0025] The historical analysis includes calculating the average adjacent distance of each node to be assigned to all other nodes, and taking the node to be assigned with the minimum value as the node to be analyzed; tracing the node to be analyzed upstream to the upper node T adjacent to the current node; retrieving all the nodes to be assigned to calculated when node T updates its node position to form a set E; if the upstream node of the node to be analyzed is in set E, then the node to be analyzed is used as the assigned node;

[0026] If the upstream node of the node to be analyzed is not in the set E, the position of the node to be analyzed is corrected: clustering is performed among the downstream nodes of the set E to obtain cluster families and cluster centers;

[0027] The number of individuals in the cluster is used as the weight coefficient 1; the reciprocal of the distance between the individual in the cluster and the cluster center plus one is multiplied by the matching degree of the individual in the cluster as the weight coefficient 2; the weight coefficient 3 is allocated by the upstream node in the set E, and the evaluation coefficient is obtained by multiplying the weight coefficient 1, the weight coefficient 2 and the weight coefficient 3, and the node with the highest evaluation coefficient is selected as the home node;

[0028] The weight coefficient 3 includes a coefficient obtained by clustering the elements in the set E, multiplying the number of individuals in the cluster and the reciprocal of the distance between the individual in the cluster and the cluster center plus one.

[0029] As a preferred solution of the big data-based operation and maintenance function item identification and diagnosis method described in the present invention, the diagnosis result includes the functional status at the updated node position and the degradation trend of the current node; the degradation trend includes evaluating the uncertainty of the degradation process based on the calculation process of the belonging node. If the position of the node to be analyzed does not require position correction, the upstream path of the node to be analyzed is determined to be a historical trend of degradation; if the position of the node to be analyzed requires position correction, the upstream path updated each time is accumulated according to the number of upstream nodes, and the path with the largest accumulation result reaching the updated node is calculated as the historical trend of degradation.

[0030] A big data-based operation and maintenance function item identification and diagnosis system using any of the methods described in the present invention, wherein: an evolution unit constructs a life cycle evolution tree of the operation and maintenance function item to form nodes and branches; each node represents a functional state, and a branch represents the degradation of the state; an analysis unit obtains the functional state of the operation and maintenance function item at each node position in the life cycle evolution tree by evolving the life cycle of the operation and maintenance function item; an update unit calculates the matching degree using the current node position of the operation and maintenance function item and the actual data when the operation and maintenance function is triggered each time; and based on the calculation result, updates the position of the node where the operation and maintenance function item is located; and an output unit generates a diagnosis result of the operation and maintenance function item based on the matching degree and the node position.

[0031] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein: when the processor executes the computer program, the steps of any one of the methods of the present invention are implemented.

[0032] A computer-readable storage medium stores a computer program, wherein: when the computer program is executed by a processor, the steps of any one of the methods of the present invention are implemented.

[0033] Beneficial effects of the present invention: The big data-based operation and maintenance function item identification and diagnosis method provided by the present invention realizes the dynamic evolution expression of complex operation and maintenance function status by constructing a life cycle evolution tree of the operation and maintenance function items and adopting a path modeling method based on parameter-aware degradation. By utilizing big data analysis and matching degree calculation mechanism, the accuracy of node status attribution and the real-time update are effectively improved. Especially when there are multiple candidate nodes, the robustness and intelligence of attribution judgment are enhanced through a comprehensive analysis strategy of structural distance, clustering weight and path tracing. In addition, a degradation trend assessment mechanism is introduced to identify the most representative operation and maintenance status change path in the historical evolution trajectory, providing a basis for fault prediction and maintenance decision-making. Compared with the existing operation and maintenance methods based on static rules, the present invention has the characteristics of intelligence, adaptability and strong interpretability, can significantly improve operation and maintenance efficiency, reduce maintenance costs, and is suitable for operation and maintenance management needs in complex systems and high reliability scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0035] Figure 1 An overall flow chart of a method for identifying and diagnosing operation and maintenance function items based on big data is provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0036] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0037] Reference Figure 1 , as one embodiment of the present invention, provides a method for identifying and diagnosing operation and maintenance function items based on big data, comprising:

[0038] S1: Construct a lifecycle evolution tree for the operation and maintenance function item, forming nodes and branches. Each node represents a function state, and a branch represents the degradation of that state. By evolving the lifecycle of the operation and maintenance function item, the function state at each node in the lifecycle evolution tree is obtained.

[0039] It should be noted that by constructing a lifecycle evolution tree for operation and maintenance functional items, structured modeling of the state change process of operation and maintenance functional items is achieved. Since the operation and maintenance function will be affected by a variety of operating parameters during the operation of the system, its functional state will exhibit complex behavioral characteristics such as gradual change, degradation, and fluctuation. The traditional static threshold judgment method is difficult to accurately reflect the evolution trend of the functional state. By abstracting the states of functional items at different stages as "nodes" and defining the state migration relationships caused by changes in operating parameters or perceived degradation as "branches", a complete functional lifecycle evolution path can be constructed. In this structure, the functional state represented by each node not only has clear response characteristics, but also has contextual evolution logic, which is helpful for subsequent state identification, matching calculation and node attribution judgment based on actual operation data. This structure provides a data-driven support foundation for systematically identifying operation and maintenance status, predicting functional degradation trends and improving diagnostic accuracy.

[0040] Furthermore, the operation and maintenance function items include functional modules that can respond to the perception of multiple parameters during operation; the functional modules can perform specific operation and maintenance actions based on the perception status of the operating parameters when the operating parameters reach the trigger conditions.

[0041] A threshold value is preset for the k operating parameters that each operation and maintenance function item can respond to. Through the embedded trigger rules (when any operating parameter among the k operating parameters reaches the threshold, or the preset operating parameter combination reaches the threshold at the same time), it is judged whether the operating parameters can meet the trigger conditions.

[0042] Here, k represents the number of pre-screened operating parameters that can respond to the operation and maintenance function item, and is an integer greater than 0. The number of data dimensions for each operation and maintenance function item is different.

[0043] The preset thresholds of k operating parameters of the operation and maintenance function items are used as the functional states of the initial nodes of the lifecycle evolution tree; according to the degradation process of each operating parameter perceived by the operation and maintenance function, at the current node, the degradation of each operating parameter threshold is simulated separately to form lower nodes for each operating parameter threshold after degradation, and there is one node for each group of degraded parameter combinations.

[0044] Each time the degradation process is simulated, only one operating parameter threshold is degraded, and the degraded operating parameter threshold and other operating parameter thresholds of the current node are used as a lower-level node functional state; after completing the degradation of each operating parameter threshold one by one, the functional state of all lower nodes of the current node is formed.

[0045] A functional state expression model based on an operational parameter perception mechanism is constructed to provide a logical basis for node generation and path expansion in the lifecycle evolution tree. Due to the varying sensitivities of different operational and maintenance functional items to the operational environment, the associated operational parameter dimensions vary, and these parameters often have nonlinear or combined influence relationships. By presetting k key operational parameters and their corresponding thresholds that trigger each functional item's operational response, combined with multiple triggering rules (such as single-parameter triggering and parameter combination triggering), a more precise characterization of the functional item's perception of system state changes can be achieved.

[0046] Using these preset thresholds as the initial node states of the evolution tree, we can systematically generate the possible states of functional items under different parameter perception paths by simulating parameter degradation without relying on manual experience. Each degradation process modifies the threshold of only one parameter, helping to construct a "single-parameter-driven functional state change path," thereby making the node evolution logic traceable and explainable. By mapping the degradation of each parameter one by one, we can fully restore the potential degradation path of the operation and maintenance functional item in the multidimensional parameter space, providing reliable structural support for subsequent node attribution judgment and state prediction.

[0047] Furthermore, the degradation process includes determining the degradation direction of each operating parameter based on the operating parameter threshold and the triggering rule. Each time degradation occurs, the operating parameter threshold is degraded by one step according to the degradation direction. The degradation direction includes: if the operating parameter is above the corresponding threshold when the operation and maintenance function is not triggered, then the degradation direction is determined to be decreasing the operating parameter threshold; if the operating parameter is not above the corresponding threshold when the operation and maintenance function is not triggered, then the degradation direction is determined to be increasing the operating parameter threshold.

[0048] The degradation process aims to dynamically model the sensitivity of operational parameters to maintenance functions and, through a parameter threshold adjustment mechanism with controllable step sizes, promote the refined construction of the lifecycle evolution tree structure. Because the triggering of maintenance functions is often influenced by the combined effects of multiple operational parameter states, simulating the evolution of these parameters during system operation is crucial for accurately modeling the functional state evolution path.

[0049] By introducing "degradation direction" judgment logic, the parameter threshold adjustment process is no longer static or preset. Instead, the parameter's degradation direction is automatically deduced based on the relationship between the actual parameter value and the trigger threshold, thereby more closely matching the state evolution trends in real-world operational scenarios. For example, if a parameter remains consistently above its threshold without triggering the operation and maintenance function, the system should determine that the threshold setting is too wide and requires downward adjustment; otherwise, it should be adjusted upward. This directional adjustment based on actual operational data ensures that the branch nodes in the evolution tree more closely align with the evolutionary patterns of the real system.

[0050] Furthermore, by adjusting only one parameter at a time by a single step, a single-dimensional progressive state migration path can be formed in the parameter space, thereby constructing a clear, traceable, and comprehensive state evolution tree structure. This design enhances the controllability and interpretability of the evolution path, supporting the accuracy improvement of subsequent matching evaluation, node updates, and diagnostic output, while avoiding the complexity of mapping caused by the explosion of parameter combinations, resulting in significant modeling efficiency and engineering practicality.

[0051] S2: Calculate the matching degree using the current node position of the operation and maintenance function item and the actual data when the operation and maintenance function is triggered each time; and update the position of the node where the operation and maintenance function item is located based on the calculation result.

[0052] Furthermore, the location update includes utilizing big data during operation to perform matching analysis on the functional status of the node where the operation and maintenance function item is located and the actual data when the operation and maintenance function is triggered each time, so as to obtain the node to be assigned; performing historical analysis based on the positional relationship between the nodes to be assigned, so as to determine the assigned node of the operation and maintenance function item, and updating the node position based on the assigned node.

[0053] Specifically, the current node position of the operation and maintenance function item includes the result of updating the node position of the operation and maintenance function item in the lifecycle evolution tree through each identification and diagnosis of the operation and maintenance function item, starting from the initial node of the lifecycle evolution tree. The actual data when the operation and maintenance function is triggered includes the operating parameter values when the operation and maintenance function is triggered during actual operation.

[0054] By clarifying the definition of "the current node position of the operation and maintenance function item", that is, starting from the initial node of the life cycle evolution tree, combined with each identification and diagnosis result triggered by actual data, the node attribution of the function item in the tree structure is dynamically adjusted, so that the system can continuously and logically track the changes in the functional status on the evolution path.

[0055] Furthermore, by introducing a standardized input format for "actual data"—operational parameter values collected each time an operation and maintenance function is triggered—we ensure that the matching calculation is based on real-time, specific, and quantifiable input information. This operational parameter data reflects the actual performance of the function item in the system's operating environment, thus serving as an important basis for determining the function's status.

[0056] Overall, through the continuous tracking of node positions, the temporal and continuous expression of functional state evolution can be achieved; on the other hand, through the standardized input of actual parameter data, the data dependence and judgment accuracy of the state recognition process are enhanced, providing a reliable input source for the diagnostic results and a supporting basis for the interpretability of the functional state.

[0057] Furthermore, the matching degree includes, among all downstream nodes (a large category including lower nodes and lower nodes of lower nodes, etc.) corresponding to the upper node adjacent to the current node (referring to the first upper node along the evolutionary tree path), the vector representation of the functional state of each node , and the vector representation of the operating parameters when the operation and maintenance function is triggered for the last m times , perform weighted Euclidean distance calculation, add one to the result and take the reciprocal to get it.

[0058] Matching calculation function (weighted Euclidean distance) uses weighted Euclidean distance as the preferred matching algorithm:

[0059]

[0060] in, The actual data Dimension value; The corresponding dimension value representing the node response feature (each dimension represents an operating parameter); Indicates the weight of each dimension, which is preset based on the parameter's impact on diagnosis (e.g. response time > ambient temperature). express and similarity.

[0061] Map distance to matching degree:

[0062]

[0063] The closer the matching degree is to 1, the more consistent the node is with the current actual state.

[0064] Where m represents the preset number of historical records to filter; represents the i-th node; is the vector representation of the functional state of the i-th node; Indicates the kth operating parameter threshold corresponding to the node functional status; Indicates the kth operating parameter value when the operating parameter triggers the operation and maintenance function; It is the vector representation of the operating parameters when the operation and maintenance function is triggered for the dth time.

[0065] The node to be assigned includes a node whose matching degree is higher than a preset threshold.

[0066] Through the topological relationship between nodes in the life cycle evolution tree, a state discrimination basis with spatial constraints and path correlation is constructed to provide structural support for attribution node screening, state update judgment and degradation trend analysis. Taking into account that the state evolution of operation and maintenance function items often presents certain path dependence and structural aggregation characteristics, if attribution judgment is only based on feature similarity, it is easy to ignore the actual topological relationship between nodes in the evolution path, resulting in inconsistency between the attribution judgment result and the system evolution logic, reducing the accuracy and credibility of the diagnosis. Assume: there is an adjacent relationship between adjacent nodes connected by the life cycle evolution tree, and the distance is one unit; there is an adjacent relationship between each node with the same adjacent upper node, and the distance is one unit. The position relationship includes performing path calculation between nodes with adjacent relationships to obtain the distance between each two nodes to be attributed.

[0067] The introduction of the structural assumption that "the distance between adjacent nodes is one unit" not only defines the basic evolutionary distance between directly upstream and downstream nodes, but also stipulates that sibling nodes with the same parent node have a structurally equal relationship. By performing path calculations between nodes with adjacent relationships, the minimum structural distance between any two nodes to be assigned can be determined, thus forming a quantifiable spatial positional relationship.

[0068] This structural distance information can be used in the subsequent node selection process to determine whether candidate nodes exhibit clustering trends and follow similar evolutionary paths. Through structural density analysis and centrality assessment, the rationality and continuity of the final node selection can be improved. Compared to identification methods that rely solely on feature similarity, this method introduces a structural consistency criterion, enhancing the stability of operation and maintenance status identification and its ability to interpret evolution.

[0069] The historical analysis includes calculating, for each node to be assigned (there can be multiple nodes to be assigned at the same location, and the number of nodes to be assigned is equal to m), the average adjacent distance to all other nodes, and taking the node to be assigned corresponding to the minimum value as the node to be analyzed; tracing the node to be analyzed upstream to the upper-level node T adjacent to the current node; and retrieving all the nodes to be assigned calculated when node T updates its node position to form a set E.

[0070] Continuity constraints on historical evolution paths are introduced during the node attribution process to enhance the logical consistency and recognition stability of attribution judgments. The functional state change path described by the lifecycle evolution tree has clear directionality and structural dependencies. Operational and maintenance functions in a system typically evolve gradually along a specific degradation path. Therefore, if the upstream node of the current node to be analyzed already appears in set E (the set of nodes participating in attribution judgments in historical records), it indicates that the node to be analyzed has a direct structural connection with the historically identified path and is a natural continuation of the original degradation chain. By directly confirming the node to be analyzed as the current attribution node, overcorrection or unnecessary correction of reasonable states within a clear path is avoided, ensuring the stability, consistency, and traceability of the recognition results. This design effectively reduces the risk of jumpy judgments caused by occasional data anomalies, local perturbations, or parameter jitter. While maintaining recognition sensitivity, it also enhances the system's "fault tolerance" and "path memory" for evolutionary trends.

[0071] To address the issue of unstable state identification caused by operational data fluctuations, structural path breaks, or short-term anomalies, the decision on the node to which the operation and maintenance function items belong in the lifecycle evolution tree is ensured to be more robust, reasonable, and interpretable. In a multi-node candidate state, relying solely on matching or current observation data can lead to incorrect attribution. This is especially true when the node to be analyzed is structurally disconnected from the existing attribution record (set E), which can easily lead to state jumps and discontinuities. If the upstream node of the node to be analyzed is not in set E, the position of the node to be analyzed is corrected: clustering is performed on the downstream nodes of set E to obtain clusters and cluster centers; the number of individuals in the cluster is used as the weight coefficient 1; the reciprocal of the distance between an individual in the cluster and the cluster center plus one is multiplied by the matching degree of the individuals in the cluster as the weight coefficient 2; a weight coefficient 3 is assigned using the upstream nodes in set E. Weight coefficients 1, 2, and 3 are multiplied together to obtain an evaluation coefficient, and the node with the highest evaluation coefficient is selected as the attribution node.

[0072] The weight coefficient 3 includes a coefficient obtained by clustering the elements in the set E, multiplying the number of individuals in the cluster and the reciprocal of the distance between the individual in the cluster and the cluster center plus one.

[0073] In practical systems, changes in operating parameters are often affected by a variety of disturbances, potentially leading to temporary functional state shifts or identification errors. To prevent such transient anomalies from misleading attribution judgments, this paper introduces a position correction mechanism when determining that the analyzed node is disconnected from the historical path (set E). Through methods such as downstream node clustering, historical path structure analysis, and matching guidance, a multi-source information fusion attribution scoring system is formed.

[0074] The scoring system is composed of the following three core weights, each with independent functions and synergistic advantages:

[0075] The weight coefficient 1 (number of individuals in a cluster) reflects whether the current area is a high-incidence, high-density area of abnormal conditions. The higher the density, the stronger the abnormal clustering of the cluster, and the higher the credibility of the attribution.

[0076] The weight factor 2 (a fusion of cluster center distance and matching degree) incorporates the structural centrality and state matching accuracy of individual nodes. By adding one to each node's distance from the cluster center, taking the inverse of the distance, and multiplying it by the node's matching degree, we can simultaneously measure whether the node is an anomalous "structural center" and its "semantic closeness" to the current state.

[0077] Weight coefficient 3 (the fusion of historical path structure and current clustering trends) evaluates the structural distribution trend by re-clustering the upstream nodes in set E. This considers that truly credible attribution nodes should not only be unusually concentrated in the current data but also consistent with the historical path evolution trend. Therefore, a cluster analysis is performed again on the historical upstream nodes in set E. If a cluster family exhibits clear structural clustering characteristics (i.e., a large number of individuals and a concentrated structure), this direction represents the main trend of past abnormal evolution. The method of "number of individuals × the inverse of the distance to the center plus one" is used to quantify the structural consistency and degree of evolutionary convergence, thus forming the basis for path credibility in attribution judgment.

[0078] Finally, the three weights are multiplied together to form a comprehensive evaluation coefficient, enabling comprehensive localization of the nodes to be analyzed from the three dimensions of "spatial density," "matching semantics," and "structural trends." This method not only overcomes the instability of traditional single-feature matching in abnormal fluctuation scenarios, but also, through a combination of data-driven, structural constraints, and path evolution laws, enables adaptive adjustment and strong interpretability in attribution judgment, significantly improving the recognition accuracy and fault tolerance of this invention in complex operation and maintenance environments.

[0079] S3: Generate a diagnosis result of the operation and maintenance function item according to the matching degree and the node position.

[0080] The diagnostic result includes the functional status of the updated node position and the degradation trend of the current node. The degradation trend includes evaluating the uncertainty of the degradation process based on the calculation process of the home node. If the position of the node to be analyzed does not require position correction, the upstream path of the node to be analyzed is determined to be a historical trend of degradation. If the position of the node to be analyzed requires position correction, the upstream path of each update is accumulated according to the number of upstream nodes, and the path with the largest accumulated result reaching the updated node is calculated as the historical trend of degradation.

[0081] By introducing a degradation trend identification mechanism based on path weight accumulation, we achieve dynamic modeling and uncertainty identification of the state evolution trends of operation and maintenance function items in the lifecycle evolution tree. Because operating parameters in complex systems often exhibit nonlinear perturbations and local anomalies, functional state identification must not only consider the functional state of the current node but also the continuity and rationality of its evolution path.

[0082] In the actual state update process, when a node does not need position correction, its upstream path can be directly regarded as the current evolution trend; however, when the node attribution result depends on cluster correction or path deviation judgment, it is necessary to use the "historical path frequency + node level weighting" method to identify trends and perform preference scoring on all possible evolution paths. Specifically:

[0083] If, after an update, a node is at the uth node in the evolutionary tree, then the value u is accumulated for this path. During the next update, if the updated node is a subordinate of the uth node, then the value u+1 is accumulated for this path (adding the previous accumulated value equals 2u+1). If the updated node is not a subordinate of the uth node, then the value u+1 is accumulated for the evolutionary path of the updated node, and so on. The current node position can differ from the evolutionary path; they are the results of two parameter evaluations.

[0084] This embodiment dynamically constructs a weighted scoring system for multiple candidate evolution paths during multiple rounds of state updates. Ultimately, the path with the largest cumulative value identifies the "main degradation trend path," or the system evolution trajectory that is most reliable, frequent, and consistent with natural evolutionary logic. This path not only reflects the continuity of system state changes but also helps distinguish between the "corrected position" and the "natural evolution path," significantly improving the system's ability to model sudden state changes and uncertain evolutionary behavior.

[0085] On the other hand, this embodiment also provides an operation and maintenance function item identification and diagnosis system based on big data, which includes:

[0086] Evolution unit, constructs the life cycle evolution tree of operation and maintenance function items, forming nodes and branches; each node represents the functional state, and the branch represents the degradation of the state.

[0087] The analyzing unit obtains the functional status of the operation and maintenance function item at each node position in the life cycle evolution tree by evolving the life cycle of the operation and maintenance function item.

[0088] The updating unit calculates the matching degree using the current node position of the operation and maintenance function item and the actual data when the operation and maintenance function is triggered each time; updates the position of the node where the operation and maintenance function item is located based on the calculation result; and the output unit generates a diagnostic result of the operation and maintenance function item based on the matching degree and the node position.

[0089] If the above 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 the present invention, or the portion 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 for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0090] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the 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 (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0091] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, and then editing, interpreting, or processing in another suitable manner as necessary, and then storing it in a computer memory.

[0092] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0093] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for identifying and diagnosing operation and maintenance function items based on big data, characterized in that: include: Construct a lifecycle evolution tree for operation and maintenance function items to form nodes and branches; Each node represents a functional state, and branches represent the degradation of the state; By evolving the life cycle of the operation and maintenance function item, the functional state of each node position of the operation and maintenance function item in the life cycle evolution tree is obtained; The matching degree is calculated using the current node position of the operation and maintenance function item and the actual data when the operation and maintenance function is triggered each time; Based on the calculation results, the location of the node where the operation and maintenance function item is located is updated; Generating a diagnosis result of an operation and maintenance function item according to the matching degree and the node position; The location update includes utilizing the big data during operation to perform the matching analysis on the functional status of the node where the operation and maintenance function item is located and the actual data when the operation and maintenance function is triggered each time, so as to obtain the node to be assigned; performing a historical analysis based on the positional relationship between the nodes to be assigned, so as to determine the assigned node of the operation and maintenance function item, and updating the node position based on the assigned node.

2. The method for identifying and diagnosing operation and maintenance function items based on big data according to claim 1, characterized in that: The operation and maintenance function items include functional modules that can respond to the perception of multiple parameters during operation; the functional modules can perform specific operation and maintenance actions based on the perception status of the operating parameters when the operating parameters meet the trigger conditions; Preset thresholds for the k operating parameters that each operation and maintenance function item can respond to, and use embedded trigger rules to determine whether the operating parameters can meet the trigger conditions; Among them, k represents the number of operating parameters that can respond to the operation and maintenance function items in advance; The preset threshold values of k operating parameters of the operation and maintenance function items are used as the functional states of the initial nodes of the lifecycle evolution tree; according to the degradation process of each operating parameter perceived by the operation and maintenance function, at the current node, the degradation of each operating parameter threshold is simulated separately to form a lower node after the degradation of each operating parameter threshold; Each time the degradation process is simulated, only one operating parameter threshold is degraded, and the degraded operating parameter threshold and other operating parameter thresholds of the current node are used as a lower-level node functional state; after completing the degradation of each operating parameter threshold one by one, the functional state of all lower nodes of the current node is formed.

3. The method for identifying and diagnosing operation and maintenance function items based on big data according to claim 2, characterized in that: The degradation process includes determining the degradation direction of each operating parameter according to the threshold of the operating parameter and the trigger rule, and degrading the threshold of the operating parameter by one step according to the degradation direction each time the degradation occurs; The degradation direction includes, if the operation parameter is higher than the corresponding threshold when the operation and maintenance function is not triggered, then the degradation direction is determined to be reducing the operation parameter threshold; If the operation parameter is not higher than the corresponding threshold when the operation and maintenance function is not triggered, it is judged that the degradation direction is to increase the operation parameter threshold.

4. The method for identifying and diagnosing operation and maintenance function items based on big data according to claim 3, characterized in that: The current node position of the operation and maintenance function item includes the result of updating the node position of the operation and maintenance function item in the life cycle evolution tree through each identification and diagnosis of the operation and maintenance function item, starting from the initial node of the life cycle evolution tree; The actual data when the operation and maintenance function is triggered includes the operation parameter values when the operation and maintenance function is triggered during actual operation.

5. The method for identifying and diagnosing operation and maintenance function items based on big data according to claim 4, characterized in that: The matching degree includes the vector representation of the functional state of each node in all downstream nodes corresponding to the upper node adjacent to the current node. , and the vector representation of the operating parameters when the operation and maintenance function is triggered for the last m times , perform weighted Euclidean distance calculation, add one to the result and take the reciprocal; Where m represents the preset number of historical records to filter; represents the i-th node; is the vector representation of the functional state of the i-th node; Indicates the kth operating parameter threshold corresponding to the node functional status; Indicates the kth operating parameter value when the operating parameter triggers the operation and maintenance function; It is the vector representation of the operating parameters when the operation and maintenance function is triggered for the dth time.

6. The method for identifying and diagnosing operation and maintenance function items based on big data according to claim 5, characterized in that: The node to be assigned includes a node whose matching degree is higher than a preset threshold; Assume that there is an adjacent relationship between adjacent nodes connected by the life cycle evolution tree, and the distance is one unit; There is an adjacent relationship between each node with the same adjacent upper node, and the distance is one unit; The position relationship includes performing path calculation between nodes having an adjacent relationship to obtain the distance between each two nodes to be assigned; The historical analysis includes calculating, for each node to be assigned, the average adjacent distance to all other nodes, and taking the node to be assigned corresponding to the minimum value as the node to be analyzed; The node to be analyzed is traced upstream until it reaches the upper node T adjacent to the current node; all nodes to be assigned calculated by node T when the node position is updated are retrieved to form a set E; If the upstream node of the node to be analyzed is in the set E, the node to be analyzed is used as the home node; If the upstream node of the node to be analyzed is not in the set E, the position of the node to be analyzed is corrected: clustering is performed among the downstream nodes of the set E to obtain cluster families and cluster centers; The number of individuals in the cluster is used as the weight coefficient 1; the reciprocal of the distance between the individual in the cluster and the cluster center plus one is multiplied by the matching degree of the individual in the cluster as the weight coefficient 2; the weight coefficient 3 is allocated by the upstream node in the set E, and the evaluation coefficient is obtained by multiplying the weight coefficient 1, the weight coefficient 2 and the weight coefficient 3, and the node with the highest evaluation coefficient is selected as the home node; The weight coefficient 3 includes a coefficient obtained by clustering the elements in the set E, multiplying the number of individuals in the cluster and the reciprocal of the distance between the individual in the cluster and the cluster center plus one.

7. The method for identifying and diagnosing operation and maintenance function items based on big data according to claim 6, characterized in that: The diagnosis result includes the functional status of the node position after the update and the degradation trend of the current node; The degradation trend includes evaluating the uncertainty of the degradation process based on the calculation process of the home node. If the position of the node to be analyzed does not require position correction, the upstream path of the node to be analyzed is determined to be a degraded historical trend. If the position of the node to be analyzed requires position correction, the upstream paths updated each time are accumulated according to the number of upstream nodes, and the path with the largest accumulated result reaching the updated node is calculated as the degraded historical trend.

8. A big data-based operation and maintenance function item identification and diagnosis system using the method according to any one of claims 1 to 7, characterized in that: The evolution unit constructs a lifecycle evolution tree of the operation and maintenance function item, forming nodes and branches; each node represents a functional state, and a branch represents the degradation of the state; the analysis unit obtains the functional state of the operation and maintenance function item at each node position in the lifecycle evolution tree by evolving the lifecycle of the operation and maintenance function item; The update unit calculates the matching degree using the current node position of the operation and maintenance function item and the actual data when the operation and maintenance function is triggered each time; Based on the calculation results, the location of the node where the operation and maintenance function item is located is updated; The output unit generates a diagnosis result of the operation and maintenance function item according to the matching degree and the node position.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.

10. 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 according to any one of claims 1 to 7 are implemented.

Images