A data management method, apparatus, and storage medium for a power system

Abstract

This invention provides a data management method, apparatus, and storage medium for a power system. The method includes: classifying collected power data from a first power system to obtain structured data, semi-structured data, and unstructured data; constructing a first tree branch, a second tree branch, and a third tree branch, with the first power system as the root node and the structured data, semi-structured data, and unstructured data as child nodes; integrating the first tree branch, the second tree branch, and the third tree branch to construct a first data management tree for the first power system; matching a second power system based on system information of the first power system; and integrating the first data management tree with the second data management tree of the second power system to obtain a target data management tree for the first power system. This invention stores power system data using a tree structure, improving the storage flexibility and query efficiency of power system data.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a data management method, apparatus and storage medium for power systems. Background Technology

[0002] In modern power systems, with the rapid development of smart grid technology, power data has experienced explosive growth. This data covers multiple aspects such as the operating status of power equipment, grid topology, power load forecasting, fault diagnosis and recording, and has significant characteristics such as massive volume, multiple sources, and heterogeneity.

[0003] Traditional power system data storage methods often employ relational databases. For example, power grid equipment information is stored in two-dimensional tables, with foreign keys linking data in different tables to represent relationships between equipment and logical connections between data. However, relational databases require a predefined, fixed table structure; field types and lengths are determined during table creation. When a new data type is added to the power system or the data structure changes—for example, the introduction of new smart power equipment bringing new monitoring data indicators—the database table structure needs to be modified. This involves complex SQL operations and may affect existing data queries, stored procedures, and application programming interfaces, resulting in poor data storage flexibility. Furthermore, when performing complex join queries in relational databases, performance degrades drastically when the data volume is large and the relationships are complex, due to the table join operation. Summary of the Invention

[0004] This invention provides a data management method, apparatus, and storage medium for power systems, which improves the storage flexibility and query efficiency of power system data.

[0005] In a first aspect, the present invention provides a data management method for a power system, comprising:

[0006] The collected power data from the first power system is classified to obtain structured data, semi-structured data, and unstructured data.

[0007] With the first power system as the root node, and the structured data, the semi-structured data, and the unstructured data as child nodes, a first tree branch, a second tree branch, and a third tree branch are constructed respectively;

[0008] The first tree branch, the second tree branch, and the third tree branch are integrated to construct the first data management tree of the first power system;

[0009] The second power system is matched based on the system information of the first power system;

[0010] The first data management tree is integrated with the second data management tree of the second power system to obtain the target data management tree of the first power system.

[0011] In a second aspect, the present invention also provides a data management device for a power system, applied to the data management method for a power system as described in the first aspect; the data management device for the power system includes:

[0012] The data classification module is used to classify the collected power data of the first power system to obtain structured data, semi-structured data and unstructured data in the power data;

[0013] The tree branch construction module is used to construct a first tree branch, a second tree branch, and a third tree branch, respectively, with the first power system as the root node and the structured data, the semi-structured data, and the unstructured data as child nodes.

[0014] The tree branch integration module is used to integrate the first tree branch, the second tree branch, and the third tree branch to construct the first data management tree of the first power system;

[0015] The matching module is used to match the second power system based on the system information of the first power system;

[0016] The management tree integration module is used to integrate the first data management tree with the second data management tree of the second power system to obtain the target data management tree of the first power system.

[0017] Thirdly, the present invention also provides an electronic device, comprising: a memory for storing computer software programs; and a processor for reading and executing the computer software programs, thereby implementing the data management method of the power system as described above.

[0018] Fourthly, the present invention also provides a non-transitory computer-readable storage medium storing a computer software program, which, when executed by a processor, implements the data management method of the power system as described above.

[0019] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the data management method for the power system as described above.

[0020] The power system data management method provided in this invention, on the one hand, stores power system data in a tree structure. Therefore, its nodes and branches can be flexibly adjusted according to changes in the power system data. When new equipment or parameters are added, only new child nodes need to be added under the corresponding parent node, eliminating the need for large-scale modifications to the entire table structure as required by relational databases. This greatly improves the adaptability to changes in the power system data structure and enhances the storage flexibility of power system data. On the other hand, in the tree structure, data queries can quickly locate the target node and retrieve its data by traversing its child nodes and the data within those child nodes, with a time complexity of O(n) (where n is the number of child nodes). This avoids the need for multiple table joins and filtering operations required in relational databases, thereby improving the query efficiency of power system data. Attached Figure Description

[0021] Figure 1 This is a flowchart illustrating the data management method for a power system provided in an embodiment of the present invention;

[0022] Figure 2 This is a schematic diagram of the structure of the first tree branch provided in an embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of the structure of the second tree branch provided in an embodiment of the present invention;

[0024] Figure 4 This is a schematic diagram of the structure of the third tree branch provided in an embodiment of the present invention;

[0025] Figure 5 This is a schematic diagram of the target data management tree structure provided in an embodiment of the present invention;

[0026] Figure 6 This is a schematic diagram of the structure of a data management device for a power system provided in an embodiment of the present invention;

[0027] Figure 7 An embodiment diagram of the electronic device provided in this invention;

[0028] Figure 8 An embodiment diagram of a computer-readable storage medium provided in accordance with the present invention. Detailed Implementation

[0029] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0031] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0032] See Figure 1 , Figure 1 This is a flowchart illustrating the data management method for a power system provided by the present invention. In this embodiment, the executing entity of the data management method for a power system is a data management device. Therefore, the data management method for a power system includes:

[0033] Step 10: Classify the collected power data of the first power system to obtain structured data, semi-structured data and unstructured data in the power data.

[0034] Specifically, the data management device collects power data from any first power system, extracts features from the collected power data, and converts each data point in the power data into a corresponding feature vector, resulting in a feature vector set V = {v1, v2, ..., v...}. m} where m represents the number of data records. For example, for meter readings in structured data, the feature vector may include dimensions such as timestamp, reading value, and meter number; for equipment maintenance records in semi-structured data, the feature vector may include keyword frequency (such as fault type keywords, maintenance action keywords), text length, etc.; for infrared images in unstructured data, the feature vector may be dimensions such as image texture features, color features (converted to grayscale or other numerical representations), and shape features (such as the geometric features of the equipment outline).

[0035] Furthermore, the data management device calculates each feature vector v according to the density calculation formula. i density ρ i This yields the density vector set ρ = {ρ1, ρ2, ..., ρ...} m The density calculation formula is as follows:

[0036]

[0037] Where, ρ i Represents data point x i The density, indicated by data point x i Let be the number of data points in a neighborhood centered at x with radius r; n represents the total number of data points; χ(x) is an indicator function, where χ(x) = 1 when x ≥ 0, and χ(x) = 0 otherwise; ||x i -x j || represents the Euclidean distance between two eigenvectors.

[0038] Furthermore, for each feature vector v i The data management device calculates the minimum distance δ to the higher density eigenvectors. i This yields the distance vector set δ = {δ1, δ2, ..., δ}. m}, where for each data point x i If data point x i It is one of the points with the highest density, then otherwise, Simultaneously, the data management device determines the set of density peak points P = {p1, p2, ..., p...} k}, where k is the number of density peak points. Density peak points are points with high density and far distance from other high-density points. They can be determined by setting density thresholds and distance thresholds. The thresholds can be determined based on statistical analysis of the data and multiple experiments.

[0039] Furthermore, starting with the set P of density peak points, the data management device will associate each density peak point with a distance condition (such as δ). i Data points smaller than a preset distance threshold are grouped into the same category. Based on the typical characteristics of each data category, the resulting categories are labeled as structured data class C. s Semi-structured data class C ss Unstructured data class C ns .

[0040] Step 20: Using the first power system as the root node and structured data, semi-structured data, and unstructured data as child nodes, construct the first tree branch, the second tree branch, and the third tree branch respectively.

[0041] Furthermore, the data management device uses the first power system as the root node and the equipment hierarchy and data logic relationships within the power system as hierarchical constraints for structured data. For example, it uses power generation equipment, transmission equipment, substation equipment, power consumption equipment, and power users as upper-level nodes, and then further subdivides the lower-level nodes according to specific types and parameters. During node construction, the information entropy of each node is calculated to determine the node splitting and merging strategy, improving the rationality of the tree structure and query efficiency. When the information entropy is large, it indicates that the data distribution of the nodes is relatively scattered, requiring further node splitting; when the information entropy is small, it indicates that the data distribution of the nodes is relatively concentrated, considering merging nodes or stopping splitting, thus constructing the first tree branch, as described in steps 201 to 204.

[0042] Furthermore, the data management device constructs a tree structure based on the tags or markers in the semi-structured data (such as element names in XML or JSON) and the semantic relationships of the data.

[0043] For example, for equipment maintenance records, the maintenance event is taken as the upper-level node, and the maintenance date, maintenance personnel, maintenance equipment and other information are taken as the lower-level nodes. Then, a tree branch is constructed according to the degree of integration between the nodes in the lower-level nodes. That is, the nodes with higher degree of integration are used as parent and child nodes in the tree structure to obtain the second tree branch, as described in steps 205 to 208.

[0044] Furthermore, the data management device performs feature clustering on the unstructured data. First, it determines the initial value of the number of clusters, k, which can be estimated based on the data size and feature distribution, and adjusted subsequently. A density-adaptive clustering algorithm is used to group data with similar features into one class, thus dividing the unstructured data into k clusters. Starting from the root node "First Power System," the vector clustering results are added as the first-level child node set under the root node. For each cluster child node, key feature information is extracted from the data in the cluster to construct the second-level child node, resulting in the third tree branch, as described in steps 209 to 213. For example, for infrared images, images with similar temperature distributions and hotspot features are clustered into one class. A tree structure is constructed based on the vector clustering results. For example, the upper-level nodes are the cluster categories, and the lower-level nodes are key information extracted from image features, such as the location range of hotspots and temperature intervals.

[0045] Step 30: Integrate the first tree branch, the second tree branch, and the third tree branch to construct the first data management tree of the first power system.

[0046] Furthermore, the data management device takes the first power system as the root node and integrates the first tree branch, the second tree branch, and the third tree branch into a single tree to construct the first data management tree of the first power system.

[0047] Step 40: Match the second power system based on the system information of the first power system.

[0048] It should be noted that the system information in the embodiments of the present invention includes jurisdictional area information and power system information, which can be matched based on the distributed hash table (DHT) and semantic similarity.

[0049] Therefore, the data management device uses a preset hash function to convert the jurisdiction information and power system information of the first power system into corresponding hash values, and matches candidate power systems based on the hash values.

[0050] Furthermore, the data management device converts the jurisdiction area information and power system information of the first power system into corresponding semantic vectors through semantic encoding, and matches the second power system in the candidate power systems according to the semantic vectors, as described in steps 401 to 405.

[0051] Step 50: Integrate the first data management tree with the second data management tree of the second power system to obtain the target data management tree of the first power system.

[0052] Furthermore, the data management device traverses all nodes in the first data management tree and the second data management tree. For any first node in the first data management tree and any second node in the second data management tree, the first node and the second node are connected according to the correlation between the first node and the second node, and the positions of the first node and the second node in the first data management tree and the second data management tree, respectively, to obtain the target data management tree of the first power system, as described in steps 501 to 504.

[0053] This invention stores power system data in a tree structure. Therefore, the nodes and branches can be flexibly adjusted according to changes in the power system data. When new equipment or parameters are added, only new child nodes need to be added under the corresponding parent node, eliminating the need for large-scale modifications to the entire table structure as required by relational databases. This significantly improves the adaptability to changes in the power system data structure and enhances the storage flexibility of the power system data. Furthermore, in a tree structure, data queries can be performed by traversing the child nodes and their data to quickly locate the target node and retrieve the data within it, with a time complexity of O(n). This avoids the need for multiple table joins and filtering operations required in relational databases, thereby improving the query efficiency of power system data.

[0054] In one embodiment, steps 201 to 204 are described as follows:

[0055] Step 201: Input the structured data into the first data parsing model. Based on the first data parsing model, parse the structured data according to the device hierarchy and data logic relationship to obtain the first layer of structured data output by the first data parsing model.

[0056] It should be noted that the data management device in this embodiment of the invention embeds a pre-trained first data parsing model. This first data parsing model is trained on a pre-trained model based on the labels of sample structured data and its corresponding device hierarchy and data logic relationships. The pre-trained model can be a feedback-forward neural network, a feedback-backward neural network, etc. Therefore, the data management device inputs structured data into the first data parsing model. The first data parsing model parses the structured data according to the device hierarchy and data logic relationships, outputting the first layer of structured data. Thus, the first layer of structured data output by the first data parsing model is obtained. This first layer of structured data includes power generation equipment, transmission equipment, transformation equipment, power consumption equipment, and power users.

[0057] Step 202: The first-level child nodes are the power generation equipment, power transmission equipment, power transformation equipment, power consumption equipment, and power users as the root nodes.

[0058] Furthermore, the data management device sets the first power system as the root node r1, and the first-level child nodes L1 = {E} with the power generation equipment, transmission equipment, transformation equipment, power consumption equipment, and power users as the root nodes. 发电 E 输电 E 变电 E 用电设备 E 用电用户 This involves adding power generation equipment, transmission equipment, transformation equipment, power consumption equipment, and power users as child nodes under the root node.

[0059] Step 203: Traverse the second-level structured data of each node in the first-level child nodes, and use the second-level structured data of each node in the first-level child nodes as the child nodes of each node to construct the second-level child nodes of the first-level child nodes.

[0060] Furthermore, for each node E in the first-level child nodes i The data management device traverses nodes belonging to node E. i The structured data of the class is used to obtain each node E based on the specific data type and parameters. i The second layer of structured data, and each node E in the first layer of child nodes. i The second layer of structured data serves as the data for each node E. i The child nodes of the first-level child nodes are used to construct the second-level child nodes of the first-level child nodes.

[0061] Step 204: Split each node according to the information entropy of each node in the second layer of child nodes, construct the child nodes of each node in the second layer of child nodes, and obtain the first tree branch.

[0062] Furthermore, the data management device splits each node based on its information entropy in the second-level child nodes, constructing child nodes for each node in the second-level child nodes to obtain the first tree branch. The specific analysis is as follows: For each node in the second-level child nodes, if the information entropy of each node is greater than or equal to a preset threshold, the data management device splits each node to obtain the third-level child nodes of the second-level child nodes. Further, the data management device splits based on the information entropy of each node in the third-level child nodes until the information entropy of all nodes is less than the preset threshold, constructing the first tree branch. The preset threshold is set according to actual conditions, such as 1.5, 3, or 5. The formula for calculating the information entropy is:

[0063]

[0064] Where H(N) represents the information entropy of node N, n represents the number of child nodes belonging to node N, and p i This represents the probability that data belongs to each child node of node N. In one embodiment, the power generation equipment node E is used as an example. 发电 For example, we start by traversing the structured data belonging to the power generation equipment category in the power generation equipment database table. The power generation equipment database table contains parameter data for different types of generators (such as thermal generators, hydro generators, etc.), such as fields like generator number, rated power, rated voltage, and energy type.

[0065] For E 发电 The second-level child nodes under a node are constructed by initially dividing them according to the generator type, such as creating a child node "Fire N" for "thermal generator". 火发 and the "hydraulic generator" sub-node water N 水发 Calculate N 火发 Node information entropy: In this embodiment of the invention, N 火发 There are m thermal power generator data records under the node. For each data record, its feature vector can be represented as v. i =(w i ,u i ,t i ), where w i Indicates the rated power value, u i Indicates the rated voltage value, t iThis represents the energy type, which is fixed as "thermal power" here. The probability of data belonging to different characteristic value ranges is calculated. For example, the rated power is divided into several intervals (such as low power interval [0, W1], medium power interval (W1, W2], high power interval (W2, +∞]), and the proportion of data in each interval to the total number of data m is counted, denoted as p1, p2, and p3 respectively (i.e., the probability of belonging to the low, medium, and high power intervals). Similarly, the rated voltage is divided in a similar way, and probabilities q1, q2, and q3 are calculated.

[0066] Furthermore, according to the information entropy formula Calculate N 火发 The information entropy of the node H(N) 火发 ), If H(N) 火发 If the value is greater than or equal to the preset threshold, then further splitting of N is required. 火发 node.

[0067] Furthermore, N is further divided according to the rated power range. 火发 Node. Create a child node N named "Low-power thermal generator". 低火发 Sub-node N of "medium-power thermal power generator" 中火发 and the sub-node N of "high-power thermal generator" 高火发 Recalculate the information entropy of these three new child nodes, for example, for N. 低火发 For each node, the probability distribution of its data across different ranges of rated voltage is recalculated, and H(N) is calculated using the aforementioned information entropy calculation formula. 低火发 If H(N) 低火发 If the value is less than a preset threshold, then stop processing N. 低火发 Node splitting; if H(N) 低火发 If the information entropy of all child nodes is still greater than or equal to the preset threshold, then continue splitting according to other features (such as generator manufacturers) until the information entropy of all child nodes is less than the preset threshold, then stop splitting.

[0068] For other first-level child nodes (such as E) 输电 E 变电 E 用电设备 E 用电用户 The first tree branch is constructed by performing the same process on the tree and its lower-level child nodes, including constructing, calculating information entropy, and splitting child nodes.

[0069] In one specific embodiment, some of the structured data of the first power system is as follows:

[0070]

[0071]

[0072] First, construct the root node "First Power System", and add the first-level child node "Power Generation Equipment" E. 发电 .

[0073] For E 发电 Node, construct the second-level child node "firepower generator" N 火发 And "hydroelectric generator" N 水发 Calculate N 火发 Node information entropy: The rated power is divided into a low power range [0,200], a medium power range (200,400], and a high power range (400,+∞]. There are 2 data points in the low power range. One data point is in the medium power range. There are 0 data points in the high power range (probability p3 = 0). Dividing the rated voltage into low voltage range [0, 150], medium voltage range (150, 250], and high voltage range (250, +∞), there is 1 data point in the low voltage range. Two data points are in the medium voltage range. Zero data points are in the high voltage range (probability q3 = 0).

[0074]

[0075] The preset threshold in this embodiment of the invention is T. s =1.5, because H(N) 火发 )>T s Then, according to the rated power range, it is further divided into N 火发 Node N is a "low-power thermal generator" 低火发 "Medium-power thermal power generator" N 中火发 and "high-power thermal generator" N 高火发 Calculate the information entropy of the new child node: N 低火发 There is one data point (number 003) under the node. Its rated voltage is in the low voltage range, so the probability p1 = 1, q1 = 1. The probability in other ranges is 0. Therefore, H(N) 低火发 )=-(1*1log2(1*1)+1*0log2(1*0)+0*1log2(0*1)+0*0log2(0*0))=0. Since H(N 火发 ) <T s Stop targeting N 低火发 Node splitting. Calculate N using the same method. 中火发 Nodes and N 高火发 The information entropy of the nodes is used to determine whether to continue splitting, and so on, to construct the tree branch structure of the entire power generation equipment section.

[0076] Furthermore, similar operations are performed on transmission equipment, transformer equipment, power-consuming equipment, and power users to ultimately complete the construction of the first tree branch, such as... Figure 2 As shown.

[0077] This invention stores the structured data of the power system in a tree structure. Therefore, during the storage process, it can be flexibly adjusted according to changes in the structured data. When new structured data is added, only a new child node needs to be added under the corresponding parent node, which greatly improves the adaptability to changes in the power system data structure and enhances the storage flexibility of power system data.

[0078] In one embodiment, steps 205 to 208 are described as follows:

[0079] Step 205: Input the semi-structured data into the second data parsing model, and parse the semi-structured data according to the semantic relationship of the data based on the second data parsing model to obtain the first layer of semi-structured data output by the second data parsing model.

[0080] It should be noted that the data management device in this embodiment of the invention embeds a pre-trained second data parsing model. This second data parsing model is trained based on sample semi-structured data and its corresponding data semantic relationship labels. Therefore, the data management device inputs semi-structured data into the second data parsing model, which then parses the semi-structured data according to the data semantic relationships, outputting first-layer semi-structured data. This first-layer semi-structured data includes equipment maintenance records, equipment inspection reports, and power system event logs.

[0081] Step 206: The first-level child nodes are the equipment maintenance records, equipment inspection reports, and power system event logs as the root nodes.

[0082] Furthermore, the data management device uses equipment maintenance records, equipment inspection reports, and power system event logs as the root nodes, with the first-level child nodes L2 = {S1, S2, S3}. Here, S1 represents the equipment maintenance record node, S2 represents the equipment inspection report node, and S3 represents the power system event log node. In other words, the equipment maintenance records, equipment inspection reports, and power system event logs are added to the root node.

[0083] Step 207: Perform semantic analysis on the text information of each node in the first-level child nodes, and construct the second-level child nodes for each node in the first-level child nodes.

[0084] Furthermore, the data management device performs semantic analysis on the text information of each node in the first-level child nodes to obtain the text of each node in the first-level child nodes, and constructs the second-level child nodes of each node in the first-level child nodes based on the text of each node in the first-level child nodes.

[0085] In one embodiment, the JSON text information of the equipment maintenance record node is: "record_id": "R001", "equipment_id": "EQ001", "date": "2024-05-10", "personnel": "JohnDoe", "description": "The transformer oil temperature was found to be too high during inspection. The cooling fan was replaced and the heat sink was cleaned."

[0086] Semantic analysis is performed on the JSON text information of the equipment maintenance record node, and the second-level child node of the equipment maintenance record node is constructed based on the obtained text as follows:

[0087] Maintenance Date Node: Node name is "date", node value is "2024-05-10". Maintenance Personnel Node: Node name is "personnel", node value is "JohnDoe". Maintenance Equipment Node: Node name is "equipment_id", node value is "EQ001". Maintenance Description Node: Node name is "description", fault type is "overheating oil", create a "fault type" sub-node with node value "overheating oil"; maintenance measure is "replace cooling fan, clean heatsink", create a "maintenance measure" sub-node with node value "replace cooling fan, clean heatsink".

[0088] The XML text information for the equipment inspection report node is as follows:<inspection_report>

[0089] <report_id> I001< / report_id>

[0090] <equipment> EQ002< / equipment>

[0091] <inspector> Alice Smith< / inspector>

[0092] <date> 2024-06-05< / date>

[0093] <result> The equipment has no abnormalities in appearance, the insulators are clean, and the connections are secure.< / result>

[0094] < / inspection_report>

[0095] Semantic analysis is performed on the XML text information of the equipment inspection report node, and the second-level child nodes of the equipment inspection report node are constructed based on the obtained text as follows: Inspection Date Node: Node name is "date", node value is "2024-06-05". Inspection Personnel Node: Node name is "inspector", node value is "AliceSmith". Inspected Equipment Node: Node name is "equipment", node value is "EQ002". Inspection Result Node: Node name is "result", creating a "Equipment Appearance Status" child node with a node value of "No Abnormalities"; creating a "Insulator Status" child node with a node value of "Clean"; creating a "Connection Part Status" child node with a node value of "Firm".

[0096] The text information of the power system event log node is: "2024-07-15-10:30:00, a voltage dip occurred on the 10kV bus of substation B, lasting for 5 seconds. The cause is suspected to be an external line fault."

[0097] Semantic analysis is performed on the text information of the power system event log nodes, and the second-level sub-nodes of the power system event log nodes are constructed based on the obtained text as follows: Event Date and Time Node: Node name is "datetime", node value is "2024-07-15-10:30:00". Event Location Node: Node name is "location", node value is "Substation B". Event Type Node: Node name is "event_type", node value is "Voltage Sag". Event Duration Node: Node name is "duration", node value is "5 seconds". Event Cause Node: Node name is "reason", node value is "External Line Fault".

[0098] Step 208: Based on the fusion degree between the second-level child nodes of each node in the first-level child nodes, construct the node relationship between the second-level child nodes of each node in the first-level child nodes to obtain the second tree branch.

[0099] Furthermore, the data management device determines the degree of fusion between the second-level child nodes of each node in the first-level child nodes, and constructs the node relationship between the second-level child nodes of each node in the first-level child nodes based on the degree of fusion between the second-level child nodes of each node in the first-level child nodes, thereby obtaining the second tree branch, as described in steps 2081 to 2085.

[0100] This invention stores the semi-structured data of the power system in a tree structure. Therefore, during the storage process, it can be flexibly adjusted according to the changes in the semi-structured data. When new semi-structured data is added, only a new child node needs to be added under the corresponding parent node, which greatly improves the adaptability to changes in the power system data structure and enhances the storage flexibility of the power system data.

[0101] In one embodiment, steps 2081 to 2085 are described as follows:

[0102] Step 2081: Convert each word in the text of each node in the second-level child nodes into a vector representation using a preset word vector model.

[0103] Optionally, the data management device uses a pre-defined word vector model trained with natural language processing technology, such as Word2Vec or GloVe, to convert each word in the text of each node in the second-level child nodes into a vector representation.

[0104] In one embodiment, for the equipment maintenance record node, for nodes A and B in its second-level child nodes, the text corresponding to node A, after being transformed by a word vector model, can be represented as a = {a1, a2, ..., a...} m The text corresponding to node B, after being transformed by the word vector model, can be represented as a vector set b = {b1, b2, ..., b}. n}

[0105] Step 2082: Determine the semantic association degree between any two nodes in the second-level child nodes based on the vector representation of any two nodes in the second-level child nodes.

[0106] Furthermore, the data management device determines the semantic association degree between any two nodes in the second-level child nodes based on the vector representation of any two nodes in the second-level child nodes. In one embodiment, continuing the above embodiment, for node A and node B in the second-level child nodes of the equipment maintenance record node, the specific calculation formula for the semantic association degree between node A and node B is as follows:

[0107]

[0108] Where S(A,B) represents the semantic association degree between node A and node B, a i Let b represent the i-th vector representation of node A. j Represents the j-th vector of node B; cos(a i ,b j ) represents a vector. i The vector representation of b jThe cosine similarity between the two vector representations indicates the degree of similarity between them in the semantic space; m represents the number of vector representations of node A, and n represents the number of vector representations of node B.

[0109] Step 2083: Determine the data dependency between any two nodes in the second-level child nodes based on the event probabilities of any two nodes in the second-level child nodes.

[0110] Furthermore, the data management device analyzes the dependency relationship between any two nodes in the second-layer child nodes based on the event probability of any two nodes in the second-layer child nodes, and determines the data dependency degree between any two nodes in the second-layer child nodes. The specific analysis is as follows: Continuing the above embodiment, in the equipment maintenance record node, the type of maintenance equipment may determine the range of fault types and the possible types of maintenance measures. Let D(A,B) represent the data dependency degree between node A and node B.

[0111] Therefore, for discrete data, data dependency is determined by calculating conditional probabilities. In one embodiment, if the probability of a specific fault type B occurring under a certain equipment type A is known to be P(B|A), and the probability of fault type B occurring under all equipment types is known to be P(B), then the data dependency between node A and node B is D(A,B) = P(B|A) / P(B). If D(A,B)>1, it indicates that node B has a strong dependency on node A; if D(A,B)=1, it indicates that node B and node A are independent; if D(A,B)<1, it indicates that node A has a certain inhibitory effect on node B or a weak dependency.

[0112] Furthermore, for continuous data (such as the changes in certain equipment operating parameters in maintenance records), linear regression or other correlation analysis methods can be used to calculate the dependence.

[0113] For example, equipment operating time A and equipment wear parameter B can be used to obtain the regression equation B = αA + β through linear regression. Based on the regression coefficient α and the goodness of fit R... 2 The degree of data dependence is determined by a combination of indicators.

[0114] Step 2084: Determine the degree of fusion between any two nodes in the second-layer child nodes based on the semantic association degree and data dependency degree between any two nodes in the second-layer child nodes.

[0115] Furthermore, the data management device determines the fusion degree F(A,B) between any two nodes in the second-layer child nodes based on the semantic association and data dependency between them. The specific formula for calculating the fusion degree F(A,B) is as follows:

[0116] F(A,B)=ωS(A,B)+(1-ω)D(A,B);

[0117] Wherein, ω represents the preset weight coefficient, which can be determined according to the characteristics of the actual data and the focus of the analysis. For example, if more emphasis is placed on the impact of semantic information on the tree structure, ω can be set to a larger value; if more emphasis is placed on the inherent dependencies between data, (1-ω) can be set to a larger value.

[0118] Step 2085: If the fusion degree between any two nodes in the second-level child nodes is greater than or equal to the preset fusion degree threshold, then construct the parent-child node relationship between any two nodes in the second-level child nodes to obtain the second tree branch.

[0119] Furthermore, the data management device determines whether the fusion degree between any two nodes in the second-level child nodes is greater than or equal to a preset fusion degree threshold. This preset fusion degree threshold is set according to actual conditions, such as 0.7, 0.8, or 0.9. If the fusion degree between any two nodes in the second-level child nodes is greater than or equal to the preset fusion degree threshold, the data management device constructs a parent-child relationship between these two nodes, thus obtaining a second tree branch.

[0120] In a specific embodiment, taking the equipment maintenance record node S1 of the first-level child node in the above embodiment as an example, the parent-child node relationship between any two nodes in the second-level child node of the equipment maintenance record node S1 is constructed as follows: The semantic correlation degree between the "Equipment Maintenance Type" node and the "Fault Type" node is calculated. For the word vector sets of "Transformer" (transformer equipment type) and "oil temperature was too high" (oil temperature too high fault type), the semantic correlation degree is calculated using the semantic correlation degree formula. After word vector model transformation, the vector for "Transformer" is t, the vector for "oil" is o, the vector for "temperature" is p, the vector for "too" is q, and the vector for "high" is h. Then, the semantic correlation degree S(Equipment Maintenance Type, Fault Type) = 0.57 is obtained by summing and averaging the cosine similarities of cos(t,o), cos(t,p), cos(t,q), and cos(t,h).

[0121] In historical maintenance data, it was found that the probability of oil temperature overheating fault in transformer-type equipment is P(oil temperature overheating, Transformer) = 0.3, and the probability of oil temperature overheating fault in all equipment types is P(oil temperature overheating) = 0.1. Therefore, the data dependency D(maintained equipment type, fault type) = 0.3 / 0.1 = 3.

[0122] In this embodiment of the invention, the preset fusion threshold is 2, and the preset weight coefficient is 0.4. Therefore, F(Equipment type under maintenance, Fault type) = 0.57 * 0.4 + 0.6 * 3 = 2.028. Since 2.028 > 2, the "Equipment type under maintenance" node is taken as the parent node, and the "Fault type" node is taken as the child node of the "Equipment type under maintenance" node. Similarly, the fusion degree between other nodes is calculated, such as the fusion degree between "Fault type" and "Maintenance measures". Based on the results, a complete tree structure relationship between the second-level child nodes is constructed, and then a complete second tree branch is constructed. For example, if a certain fault type is found to have a high fusion degree with a specific maintenance measure, the maintenance measure node is taken as a child node of the fault type node so that relevant maintenance measure information can be quickly obtained when querying a specific fault. Specifically, as shown below... Figure 3 As shown.

[0123] This invention stores the semi-structured data of the power system in a tree structure. Therefore, during the storage process, it can be flexibly adjusted according to the changes in the semi-structured data. When new semi-structured data is added, only a new child node needs to be added under the corresponding parent node, which greatly improves the adaptability to changes in the power system data structure and enhances the storage flexibility of the power system data.

[0124] In one embodiment, steps 209 to 213 are described as follows:

[0125] Step 209: Input the unstructured data into the feature extraction model, extract features from the unstructured data based on the feature extraction model, and output the feature vector of the unstructured data.

[0126] It should be noted that the data management device in this embodiment of the invention embeds a pre-trained feature extraction model. This feature extraction model is trained based on unstructured sample data and its corresponding feature vector labels. Therefore, the data management device inputs unstructured data into the feature extraction model, which extracts features from the unstructured data to obtain feature vectors. This allows the model to output the feature vectors of the unstructured data.

[0127] In one embodiment, the unstructured data includes N infrared images. For each infrared image, the feature extraction model uses the temperature value of each pixel in the image as the basic data to construct a temperature matrix of the image and calculate the statistical features of the image, such as the average temperature. Temperature variance Number of hotspot pixels n h Statistical features such as the number of pixels whose temperature exceeds a certain threshold are combined into a feature vector. i = 1, 2, ..., N represents the i-th infrared image.

[0128] Step 210: Determine the local density of each feature vector in the unstructured data and the minimum distance between each feature vector in the unstructured data and the target feature vector based on the local density.

[0129] Furthermore, for each feature vector F i The data management device determines each feature vector F in the unstructured data based on the local density algorithm. i Local density f i Each feature vector F i Local density f i Indicates each feature vector F i radius d c The number of feature vectors in the neighborhood is calculated using the following formula:

[0130]

[0131] Where n represents the total number of eigenvectors; χ(x) represents the indicator function, which is 1 when x≥0, and 0 otherwise; d ij Represents the eigenvector F i Other eigenvectors F j The distance between them.

[0132] In one embodiment, when calculating the local density of eigenvector F1, all other eigenvectors F1 are traversed. j For j = 2, 3, ..., N, calculate the eigenvector F1 and other eigenvectors F1 and F2. j The Euclidean distance d between them 1j If d 1j ≤d c Then f1 is incremented by 1. The local density f of all image feature vectors is calculated sequentially. i ,i=1,2,..,N.

[0133] Furthermore, the data management device traverses the local density ratio eigenvector F i The local density of all target feature vectors F j The eigenvector set S is obtained. i ={F j |f j >f i}, calculate the eigenvector F i To the eigenvector set S i Each target feature vector F j distance d ij The minimum value among them is taken as the feature vector F. i With the target feature vector Fj minimum distance It should be noted that for the feature vector with the highest local density, its minimum distance is... Set to the maximum distance to all other feature vectors.

[0134] Step 211: Based on the local density and minimum distance of each feature vector in the unstructured data, determine the vector clustering result of each feature vector in the unstructured data.

[0135] Furthermore, the data management device determines the local density f of each feature vector. i and minimum distance Plot the decision graph using the values ​​of local density f. i x-axis represents the minimum distance (The vertical axis is used as the coordinate).

[0136] In the decision graph, the local density f i and minimum distance Larger eigenvectors are usually candidate eigenvectors for cluster centers. By observing the distribution of eigenvectors in the decision graph, and combining the actual operation knowledge of the power system and the characteristics of the data, the initial value of the number of clusters k is initially determined. For example, k=3 is determined, and the three cluster center eigenvectors C1, C2, and C3 corresponding to each eigenvector are determined.

[0137] Furthermore, the data management device starts with the cluster center feature vector of each feature vector and assigns density-connected feature vectors in its neighborhood to the corresponding clusters. For example, for the cluster center feature vector C1, the semi-structured data corresponding to the density-connected (i.e., there is a path) feature vectors in its neighborhood are first assigned to cluster C1. This process is repeated until all feature vectors of the semi-structured data have been assigned to a cluster, resulting in three cluster sets C. cluster1 C cluster2 C cluster3 .

[0138] Step 212: The first-level child node of the root node is the vector clustering result of each feature vector in the unstructured data.

[0139] Furthermore, the data management device uses the vector clustering result of each feature vector in the unstructured data as the first-level child node of the root node. In one embodiment, for the feature vectors of infrared images in semi-structured data, the three clustering sets C of the feature vectors of the infrared images are... cluster1 C cluster2 C cluster3 They are added as first-level child nodes under the root node and named "Cluster 1 Infrared Image Data", "Cluster 2 Infrared Image Data", and "Cluster 3 Infrared Image Data" respectively.

[0140] Step 213: Extract the key feature information of each node in the first layer of child nodes, and use the key feature information of each node in the first layer of child nodes as the child nodes of each node in the first layer of child nodes to construct the second layer of child nodes of each node in the first layer of child nodes, thus obtaining the third tree branch.

[0141] Furthermore, the data management device extracts the key feature information of each node in the first-layer child nodes, and uses the key feature information of each node in the first-layer child nodes as the child nodes of each node in the first-layer child nodes, constructing the second-layer child nodes of each node in the first-layer child nodes, thus obtaining the third tree branch. Continuing the above embodiment, for the infrared image data in the "Cluster 1 Infrared Image Data" child node, key feature information is extracted to construct the second-layer child nodes. For example, the hotspot location range of all images in the cluster is calculated, each infrared image in the cluster is traversed, the coordinate range of all hotspot pixels is found, and the x-coordinate range of the hotspot is obtained through statistical calculation as [x min ,x max The y-coordinate range is [y min ,y max Create a child node named "Hotspot Location Range" with the attribute value "x-coordinate range: [x]". min ,x max ], y-coordinate range: [y min ,y max ]”. Calculate the temperature range of the images within the cluster, and count the highest and lowest temperatures of all images in the cluster to obtain the temperature range [T]. min ,T max Create a child node named "Temperature Range" with the attribute value "[T min ,T max It can also calculate other key feature information, such as average hotspot area (the average of the hotspot areas of all images within a cluster), create an "average hotspot area" sub-node and set the corresponding attribute values.

[0142] Using the same method, corresponding second-level child nodes are constructed for the child nodes of "cluster 2 infrared image data" and "cluster 3 infrared image data", thereby completing the construction of the third tree branch, as follows: Figure 4 As shown.

[0143] This invention stores unstructured power system data in a tree structure. Therefore, during storage, the data can be flexibly adjusted according to changes in the unstructured data. When new unstructured data is added, only a new child node needs to be added under the corresponding parent node, which greatly improves the adaptability to changes in the power system data structure and enhances the storage flexibility of power system data.

[0144] In one embodiment, steps 401 to 405 are described as follows:

[0145] Step 401: Integrate the jurisdiction information and power system information of the first power system to obtain the information string of the first power system.

[0146] Specifically, for the first power system Z1, the data management device transmits its jurisdictional area information I 1r (such as geographical location information expressed in latitude and longitude ranges, voltage level coverage areas, etc.) and power system information I 1s (Such as power generation capacity, total length of transmission lines, number of substations, etc.) are integrated. In one embodiment, the jurisdiction area information I 1r Represented as [lon] 1min ,lon 1max ,lat 1min ,lat 1max V 1min V 1max (Longitude range, latitude range, voltage level range), Power System Information I 1s Represented as [P] 1s ,L 1s N 1s (Power generation capacity, transmission line length, number of substations), connect the information elements in a specific order to form a specific formatted information string Str1 = concat(I 1r ,I 1s ).

[0147] Step 402: Perform hash calculation on the information string based on the hash function to obtain the first hash value.

[0148] Furthermore, the data management device performs a hash calculation on the information string Str1 using the SHA-256 hash function H to obtain the hash value h1 = H(Str1) of the first power system Z1.

[0149] Step 403: Match the first hash value in a preset hash table to obtain candidate power systems.

[0150] In the pre-defined hash table, the hash value h2 = H(Str2) of each power system Z2 is also processed according to the process of the first power system, which includes the jurisdiction information I. 2r =[lon 2min ,lon 2max ,lat 2min ,lat 2max V 2min V 2max ] and power system information I 2s =[P 2s ,L 2sN 2s ] Combine into a message string Str2 = concat(I 2r ,I 2s Then, the hash value h2 = H(Str2) of the information string Str2 is calculated using the SHA-256 hash function H.

[0151] Furthermore, the data management device performs a lookup operation on hash values ​​h1 and h2, along with their corresponding power system identifiers (such as Z1 and Z2), in a preset hash table, and calculates the difference value Diff between hash values ​​h1 and h2. h =hammingdistance(h1,h2) (Hamming distance and other difference measurement methods). If the difference value Diff h Less than or equal to the hash difference threshold T h If the power system Z2 is selected as a candidate power system for the first power system Z1, it will proceed to the next step of semantic similarity matching analysis; otherwise, the matching degree between the power system Z2 and the first power system Z1 is determined to be low, and integration will not be considered. Therefore, it can be understood that the difference between the second hash value h2 and the first hash value h1 of the candidate power system is less than or equal to the hash difference threshold.

[0152] Step 404: Semantically encode the jurisdiction information and power system information of the first power system to obtain the first comprehensive semantic vector of the first power system.

[0153] Furthermore, regarding the jurisdictional information I of the first power system Z1 1r The data management device uses a semantic encoding method from a Geographic Information System (GIS) to construct semantic vectors. For example, it maps latitude and longitude ranges to a two-dimensional semantic space, mapping longitude ranges to the x-axis coordinate range and latitude ranges to the y-axis coordinate range, resulting in vector V. 1r =[x 1rmin ,x 1rmax ,y 1rmin ,y 1rmax For voltage level range [V] 1min V 1max Based on the voltage level semantic classification table in the power sector, it can be converted into a discrete semantic encoding vector V. 1v (For example, the encoding corresponding to low voltage, medium voltage, high voltage, etc.). Further, the vector V... 1r and semantic encoding vector V 1v The jurisdictional information I of the first power system Z1 is combined. 1r semantic vectors SV 1r =combine(V 1r V 1v ).

[0154] Furthermore, for the power system information I of the first power system Z1 1s Semantic vectors are constructed based on the ontology of the power industry. For example, power generation capacity P 1s The power system can be classified according to its size (small, medium, large, etc.) and converted into semantic codes; transmission line length L 1s and the number of substations N 1s It is also converted into code according to the corresponding semantic rules of the power field, and combined to form the power system information I of the first power system Z1. 1s semantic vectors SV 1s Finally, the comprehensive semantic vector SV1 = concat(SV1) of the first power system Z1 is obtained. 1r ,SV 1s ).

[0155] It should be noted that the comprehensive semantic vector SV2 of each power system in the candidate power system is also obtained according to the above process.

[0156] Step 405: Match the candidate power systems based on the first comprehensive semantic vector to obtain the second power system in the candidate power systems.

[0157] Furthermore, the data management device calculates the semantic similarity score S of the comprehensive semantic vector SV1 and the comprehensive semantic vector SV2 using the cosine similarity formula. s The specific calculation formula is as follows:

[0158]

[0159] Among them, a i and b i These represent the corresponding dimension elements of the comprehensive semantic vector SV1 and the comprehensive semantic vector SV2, respectively, where n represents the vector dimension.

[0160] Furthermore, if the semantic similarity score S is determined... s If the semantic similarity score is greater than or equal to the preset semantic similarity threshold, it is determined that the power system in the candidate power system has a high semantic compatibility with the first power system Z1, thereby obtaining the second power system of the first power system Z1. Therefore, it can be understood that the semantic similarity score between the first comprehensive semantic vector of the first power system and the second comprehensive semantic vector of the second power system is greater than or equal to the preset semantic similarity threshold.

[0161] This invention identifies a second power system with a high correlation to the first power system by matching jurisdictional information and power system information. After integrating the first and second power systems, better power dispatch coordination can be achieved. At the same time, the power system in the region can be evaluated from a more macro perspective, which helps to analyze the power supply and demand balance of the entire region and provides comprehensive data support for future planning of power generation facilities construction and power grid upgrading.

[0162] In one embodiment, steps 501 to 504 are described as follows:

[0163] Step 501: Traverse all nodes in the first data management tree and the second data management tree. For any first node in the first data management tree and any second node in the second data management tree, determine the degree of association between the first node and the second node.

[0164] Optionally, the data management device traverses all nodes in the first and second data management trees. For node pairs in the first data management tree (Tree1) and the second data management tree (Tree2) of the first power system (i.e., for any first node in the first data management tree and any second node in the second data management tree), it calculates the correlation degree between the first and second nodes. The correlation degree is used to consider cross-system semantic compatibility and functional complementarity. For example, for the generator node E in the first data management tree (Tree1)... 1g The power transmission equipment node E in the second data management tree Tree2 2t In terms of semantic compatibility, we check whether the voltage output range of the power generation equipment matches the voltage receiving range of the transmission equipment (based on semantic knowledge in the power field). In terms of functional complementarity, we consider whether the power generation capacity of the power generation equipment can be matched with the power transmission capacity of the transmission equipment (based on the power system operation logic).

[0165] Therefore, the data management device determines the cross-system data type matching score T between the first node X and the second node Y according to the power sector equipment type matching rules. XY (XY), determine the cross-system semantic association score S between the first node X and the second node Y based on semantic compatibility checks. XY (XY), the cross-system functional correlation score F between the first node X and the second node Y is determined based on the functional complementarity analysis. XY (X,Y), determine the correlation degree R(X,Y) between the first node X and the second node Y according to the correlation degree calculation formula, and obtain the correlation degree matrix M. R Among them, the correlation matrix M R The matrix element m ij =R(N) i N j), N i and N j The formula for calculating the correlation between nodes in different data management trees is as follows:

[0166] R(X,Y)=αT XY (XY)+βS XY (XY)+γF XY (XY);

[0167] Wherein, α, β, and γ represent weighting coefficients, which are determined based on expert knowledge.

[0168] Step 502: Determine a first path from the root node of the first data management tree to the first node based on the first data management tree, and determine a second path from the root node of the second data management tree to the second node based on the second data management tree.

[0169] Furthermore, the data management device determines the path from the root node of the first data management tree to the first node X based on the first data management tree. X = [r1,n1,n2,...,X], and the path Path, which is the second path Y from the root node of the second data management tree to the second node, determined according to the second data management tree. Y = [r2,m1,m2,...,Y], where r1 represents the root node of the first data management tree Tree1, n1,n2,... represent the intermediate nodes of the first data management tree Tree1, r2 represents the root node of the second data management tree Tree2, and m1,m2,... represent the intermediate nodes of the second data management tree Tree2.

[0170] Step 503: Determine the path weight between the first node and the second node based on the first path and the second path.

[0171] Furthermore, the data management device follows the first path. X Second Path Y Calculate the path weight W(X,Y) between the first node and the second node to obtain the path weight matrix M. W , where the path weight matrix M W The matrix element m ij =W(N) i N j ), where the path weight W(X,Y) represents the combined influence of the importance of nodes and the path length on the path from their respective root nodes to the two associated nodes. The calculation formula for the path weight W(X,Y) is as follows:

[0172]

[0173] Among them, l X and lY These represent paths. X and Path Y Length (number of nodes); and These represent the importance weights of nodes on the path, determined based on the node's level and functional importance in its respective power system's data management tree. For example, the root node and critical equipment nodes have higher weights; λ represents the path length difference penalty coefficient.

[0174] Step 504: Connect the first node and the second node based on the correlation degree and path weight to obtain the target data management tree of the first power system.

[0175] Furthermore, the data management device connects the first node and the second node in the correlation matrix where the correlation degree is greater than or equal to a preset correlation degree threshold, and the path weight in the path weight matrix is ​​less than or equal to a preset path weight threshold. The preset correlation degree threshold and the preset path weight threshold are set according to actual conditions. This process is repeated until all node pairs meeting the conditions have been processed, resulting in the target data management tree of the first power system, as shown in the figure. Figure 5 As shown.

[0176] This invention integrates the data management trees of the first power system and the second power system. Therefore, the integrated target data management tree can provide a more comprehensive perspective. Considering the mutual influence between multiple systems, data integration can better predict the possibility and scope of cross-system fault propagation, formulate countermeasures in advance, and ensure the safe and stable operation of the regional power system.

[0177] Furthermore, the data management device for a power system provided by the present invention will be described below. The data management device for a power system described below can be referred to in correspondence with the data management method for a power system described above. Optionally, referencing... Figure 6 , Figure 6 This is a schematic diagram of the structure of the power system data management device provided by the present invention. The power system data management device includes...

[0178] The data classification module 610 is used to classify the collected power data of the first power system to obtain structured data, semi-structured data and unstructured data in the power data;

[0179] The tree branch construction module 620 is used to construct the first tree branch, the second tree branch, and the third tree branch, with the first power system as the root node and structured data, semi-structured data, and unstructured data as child nodes, respectively.

[0180] The tree branch integration module 630 is used to integrate the first tree branch, the second tree branch and the third tree branch to construct the first data management tree of the first power system;

[0181] Matching module 640 is used to match the second power system based on the system information of the first power system;

[0182] The management tree integration module 650 is used to integrate the first data management tree with the second data management tree of the second power system to obtain the target data management tree of the first power system.

[0183] This invention stores power system data in a tree structure. Therefore, the nodes and branches can be flexibly adjusted according to changes in the power system data. When new equipment or parameters are added, only new child nodes need to be added under the corresponding parent node, eliminating the need for large-scale modifications to the entire table structure as required by relational databases. This significantly improves the adaptability to changes in the power system data structure and enhances the storage flexibility of the power system data. Furthermore, in a tree structure, data queries can be performed by traversing the child nodes and their data to quickly locate the target node and retrieve the data within it, with a time complexity of O(n). This avoids the need for multiple table joins and filtering operations required in relational databases, thereby improving the query efficiency of power system data.

[0184] Please see Figure 7 , Figure 7 An embodiment diagram of an electronic device provided in accordance with the present invention. For example... Figure 7 As shown, an embodiment of the present invention provides an electronic device 700, including a memory 710, a processor 720, and a computer program 711 stored in the memory 710 and executable on the processor 720. When the processor 720 executes the computer program 711, it performs the following steps:

[0185] The collected power data from the first power system is classified to obtain structured data, semi-structured data, and unstructured data.

[0186] With the first power system as the root node and structured data, semi-structured data, and unstructured data as child nodes, construct the first tree branch, the second tree branch, and the third tree branch respectively;

[0187] Integrate the first tree branch, the second tree branch, and the third tree branch to construct the first data management tree of the first power system;

[0188] The second power system is matched based on the system information of the first power system;

[0189] The first data management tree is integrated with the second data management tree of the second power system to obtain the target data management tree of the first power system.

[0190] Please see Figure 8 , Figure 8 An embodiment diagram of a computer-readable storage medium provided in accordance with an embodiment of the present invention is shown. Figure 8 As shown, this embodiment provides a computer-readable storage medium 800, on which a computer program 711 is stored. When the computer program 711 is executed by a processor, it performs the following steps:

[0191] The collected power data from the first power system is classified to obtain structured data, semi-structured data, and unstructured data.

[0192] With the first power system as the root node and structured data, semi-structured data, and unstructured data as child nodes, construct the first tree branch, the second tree branch, and the third tree branch respectively;

[0193] Integrate the first tree branch, the second tree branch, and the third tree branch to construct the first data management tree of the first power system;

[0194] The second power system is matched based on the system information of the first power system;

[0195] The first data management tree is integrated with the second data management tree of the second power system to obtain the target data management tree of the first power system.

[0196] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the power system data management method provided by the above methods, the method including:

[0197] The collected power data from the first power system is classified to obtain structured data, semi-structured data, and unstructured data.

[0198] With the first power system as the root node and structured data, semi-structured data, and unstructured data as child nodes, construct the first tree branch, the second tree branch, and the third tree branch respectively;

[0199] Integrate the first tree branch, the second tree branch, and the third tree branch to construct the first data management tree of the first power system;

[0200] The second power system is matched based on the system information of the first power system;

[0201] The first data management tree is integrated with the second data management tree of the second power system to obtain the target data management tree of the first power system.

[0202] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0203] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0204] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data management method for a power system, characterized in that, include: The collected power data from the first power system is classified to obtain structured data, semi-structured data, and unstructured data. With the first power system as the root node, and the structured data, the semi-structured data, and the unstructured data as child nodes, a first tree branch, a second tree branch, and a third tree branch are constructed respectively; The first tree branch, the second tree branch, and the third tree branch are integrated to construct the first data management tree of the first power system; The second power system is matched based on the system information of the first power system; The first data management tree is integrated with the second data management tree of the second power system to obtain the target data management tree of the first power system; The system information includes jurisdictional area information and power system information; the step of matching the second power system based on the system information of the first power system includes: The jurisdictional information and power system information of the first power system are integrated to obtain the information string of the first power system; The information string is hashed based on a preset hash function to obtain a first hash value; Based on the first hash value, a candidate power system is obtained by matching it in a preset hash table; the difference between the second hash value of the candidate power system and the first hash value is less than or equal to the hash difference threshold. The jurisdiction information and power system information of the first power system are semantically encoded to obtain the first comprehensive semantic vector of the first power system. Based on the first comprehensive semantic vector, a second power system is obtained from the candidate power system by matching the first comprehensive semantic vector with the second comprehensive semantic vector of the second power system; the semantic similarity score between the first comprehensive semantic vector and the second comprehensive semantic vector of the second power system is greater than or equal to a preset semantic similarity threshold.

2. The data management method for a power system according to claim 1, characterized in that, The steps for constructing the first tree branch, with the first power system as the root node and structured data as child nodes, include: The structured data is input into a first data parsing model. Based on the first data parsing model, the structured data is parsed according to the equipment hierarchy and data logic relationship to obtain the first layer of structured data output by the first data parsing model. The first layer of structured data includes power generation equipment, power transmission equipment, power transformation equipment, power consumption equipment, and power users. The first data parsing model is trained based on the sample structured data and its corresponding equipment hierarchy and data logic relationship labels. The power generation equipment, the power transmission equipment, the power transformation equipment, the power consumption equipment, and the power users are the first-level child nodes of the root node; Traverse the second-level structured data of each node in the first-level child nodes, and use the second-level structured data of each node in the first-level child nodes as the child nodes of each node to construct the second-level child nodes of the first-level child nodes; Based on the information entropy of each node in the second layer of child nodes, split each node and construct the child nodes of each node in the second layer of child nodes to obtain the first tree branch.

3. The data management method for a power system according to claim 2, characterized in that, The step of splitting each node based on the information entropy of each node in the second layer of child nodes to construct child nodes for each node in the second layer of child nodes, thereby obtaining the first tree branch, includes: For each node in the second layer of child nodes, if the information entropy of each node is greater than or equal to a preset threshold, then each node is split to obtain the third layer of child nodes in the second layer; the splitting is performed according to the information entropy of each node in the third layer of child nodes until the information entropy of all nodes is less than the preset threshold, thus constructing the first tree branch; the formula for calculating the information entropy is: Where H(N) represents the information entropy of node N, n represents the number of child nodes belonging to node N, and p i This represents the probability that the data belongs to each child node of node N.

4. The data management method for a power system according to claim 1, characterized in that, The steps for constructing the second tree branch, with the first power system as the root node and semi-structured data as child nodes, include: The semi-structured data is input into the second data parsing model. Based on the second data parsing model, the semi-structured data is parsed according to the data semantic relationships to obtain the first layer of semi-structured data output by the second data parsing model. The first layer of semi-structured data includes equipment maintenance records, equipment inspection reports, and power system event logs. The second data parsing model is trained based on sample semi-structured data and its corresponding data semantic relationship labels. The equipment maintenance record, the equipment inspection report, and the power system event log are the first-level child nodes of the root node; Semantic analysis is performed on the text information of each node in the first layer of child nodes to construct the second layer of child nodes for each node in the first layer of child nodes; Based on the degree of fusion between the second-level child nodes of each node in the first-level child nodes, the node relationships between the second-level child nodes of each node in the first-level child nodes are constructed to obtain the second tree branch.

5. The data management method for a power system according to claim 4, characterized in that, The step of constructing the node relationships between the second-level child nodes of each node in the first-level child nodes based on the fusion degree between the second-level child nodes of each node in the first-level child nodes, to obtain the second tree branch, includes: The text of each node in the second-layer child nodes is converted into a vector representation using a preset word vector model. Based on the vector representations of any two nodes in the second layer of child nodes, determine the semantic association degree between any two nodes in the second layer of child nodes; Based on the event probabilities of any two nodes in the second layer of child nodes, determine the data dependency between any two nodes in the second layer of child nodes; Based on the semantic association and data dependency between any two nodes in the second layer of child nodes, determine the degree of fusion between any two nodes in the second layer of child nodes; If the fusion degree between any two nodes in the second layer of child nodes is greater than or equal to the preset fusion degree threshold, then the parent-child relationship between any two nodes in the second layer of child nodes is constructed to obtain the second tree branch.

6. The data management method for a power system according to claim 1, characterized in that, The steps to construct the third tree branch, with the first power system as the root node and unstructured data as child nodes, include: The unstructured data is input into a feature extraction model, and features are extracted from the unstructured data based on the feature extraction model to output the feature vector of the unstructured data; the feature extraction model is trained based on the sample unstructured data and its corresponding feature vector label results; The local density of each feature vector in the unstructured data is determined based on the local density, and the minimum distance between each feature vector in the unstructured data and the target feature vector is determined based on the local density. Based on the local density and minimum distance of each feature vector in the unstructured data, the vector clustering result of each feature vector in the unstructured data is determined; The vector clustering result of each feature vector in the unstructured data is taken as the first-level child node of the root node; Extract the key feature information of each node in the first layer of child nodes, and use the key feature information of each node in the first layer of child nodes as the child node of each node in the first layer of child nodes to construct the second layer of child nodes of each node in the first layer of child nodes, thereby obtaining the third tree branch.

7. The data management method for a power system according to claim 1, characterized in that, The step of integrating the first data management tree with the second data management tree of the second power system to obtain the target data management tree of the first power system includes: Traverse all nodes in the first data management tree and the second data management tree. For any first node in the first data management tree and any second node in the second data management tree, determine the degree of association between the first node and the second node. Based on the first data management tree, a first path from the root node of the first data management tree to the first node is determined, and based on the second data management tree, a second path from the root node of the second data management tree to the second node is determined; Based on the first path and the second path, determine the path weight between the first node and the second node; The first node and the second node are connected based on the correlation degree and path weight to obtain the target data management tree of the first power system.

8. A data management device for a power system, characterized in that, A data management method applied to a power system as described in any one of claims 1 to 7; The data management device for the power system includes: The data classification module is used to classify the collected power data of the first power system to obtain structured data, semi-structured data and unstructured data in the power data; The tree branch construction module is used to construct a first tree branch, a second tree branch, and a third tree branch, respectively, with the first power system as the root node and the structured data, the semi-structured data, and the unstructured data as child nodes. The tree branch integration module is used to integrate the first tree branch, the second tree branch, and the third tree branch to construct the first data management tree of the first power system; The matching module is used to match the second power system based on the system information of the first power system; The management tree integration module is used to integrate the first data management tree with the second data management tree of the second power system to obtain the target data management tree of the first power system; The system information includes jurisdictional area information and power system information; the step of matching the second power system based on the system information of the first power system includes: The jurisdictional information and power system information of the first power system are integrated to obtain the information string of the first power system; The information string is hashed based on a preset hash function to obtain a first hash value; Based on the first hash value, a candidate power system is obtained by matching it in a preset hash table; the difference between the second hash value of the candidate power system and the first hash value is less than or equal to the hash difference threshold. The jurisdiction information and power system information of the first power system are semantically encoded to obtain the first comprehensive semantic vector of the first power system. Based on the first comprehensive semantic vector, a second power system is obtained from the candidate power system by matching the first comprehensive semantic vector with the second comprehensive semantic vector of the second power system; the semantic similarity score between the first comprehensive semantic vector and the second comprehensive semantic vector of the second power system is greater than or equal to a preset semantic similarity threshold.

9. A non-transitory computer-readable storage medium, wherein a computer software program is stored therein, characterized in that, When the computer software program is executed by the processor, it implements the data management method for the power system as described in any one of claims 1 to 7.

Images