Power data asset consanguinity analysis method and system

Abstract

The invention belongs to the technical field of power dispatching automation, and particularly relates to a power data asset blood relationship analysis method and system. The method comprises the following steps: acquiring power data, and judging whether the type of the acquired power data is structured model data or unstructured operation data; performing blood relationship analysis on the unstructured operation data to obtain a data blood relationship; and inputting a data blood relationship obtained by blood relationship analysis of the unstructured operation data into a pre-trained self-trained recurrent neural network to obtain a data blood relationship influence factor under the data blood relationship of the unstructured operation data. According to the method, the data blood relationship can be automatically established for the unstructured operation data; by establishing a data blood relationship between structured data and unstructured operation data, dynamic tracking of a data relationship is realized, and upstream and downstream links of the data are updated in real time; the weight analysis of the change influence among the data is realized by acquiring the data blood relationship influence factor.

Description

Technical Field

[0001] The present invention belongs to the technical field of power dispatching automation, and particularly relates to a method and system for power data asset lineage analysis. Background Art

[0002] Data lineage technology is a technical system for tracking the flow relationship of data throughout its entire life cycle from generation to extinction. Its core lies in recording the origin, processing logic, and flow path of data, forming a visual network similar to a "family tree". This technology realizes fine-grained traceability at the field level or operator level by parsing data processing links such as the ETL process and SQL operations. For example, in Hive, the data conversion relationship can be captured through syntax parsing and Hook functions. The current technical architecture mostly adopts a five-layer system (acquisition, processing, storage, interface, application), uses a graph database to store complex lineage topologies, and uses a dynamic tracking mechanism to update the data link status in real time. Data lineage not only serves quality monitoring and compliance auditing in data governance but also can predict change risks through impact analysis. For example, this technology is used in scenarios such as repositioning sensitive data flow paths, data governance, and quality control.

[0003] Chinese Patent Application No. CN202510185428.6 discloses a power grid data lineage management system, which relates to the technical field of data management. The invention includes: a power grid data acquisition module, a power grid lineage data analysis module, a power grid lineage data processing module, and a local database. The invention integrates the historical data of each substation equipment belonging to the power grid, analyzes the lineage anomaly correlation coefficient of each data of the substation equipment belonging to the power grid, and dynamically adjusts the anomaly weight factor value of each data accordingly, thereby improving the early warning accuracy rate of substation equipment and reducing the failure rate of substation equipment. By analyzing the lineage similarity between each out-of-service substation equipment and each predicted fault substation equipment belonging to the power grid and each fault type, the predicted out-of-service reasons of each out-of-service substation equipment and the predicted fault reasons of each predicted fault substation equipment belonging to the power grid are quickly determined, thereby improving the maintenance efficiency of substation equipment and enhancing the operation efficiency of substation equipment.

[0004] The technical solution of this patent application is to extract the characteristic values of each data of each fault substation equipment belonging to the power grid and each data of each normal substation equipment at each historical monitoring time point, calculate the abnormal fluctuation coefficient of the equipment by calculating the average characteristic value of the normal substation equipment and the data characteristic value of each fault substation equipment, and then judge the equipment fault situation according to the set threshold. The disadvantage of such a judgment is that only by judging the abnormal fluctuation relationship through characteristic values, there will be a problem of data distortion when the equipment data sample is insufficient, and the state of equipment failure cannot be well directly characterized only by the difference between characteristic values.

[0005] The Chinese patent application with the application number CN202311465333.7 discloses a method for querying power data lineage, including: 1) counting the field information of database tables; 2) comparing the field names in different tables to obtain fields with high similarity in different tables; 3) if there are fields with high similarity, compare the data in the corresponding attribute columns of these two fields to determine whether there is a lineage relationship; 4) if there are no fields with high similarity between the two tables or the data corresponding to the fields with high similarity has no lineage relationship, compare each column of data in one table with one or more columns of data in the other table to determine whether there is a lineage relationship; 5) count the data lineage relationships found in the database and perform visual display on the front end. The invention can accurately and quickly find the associated fields between database tables, determine the lineage relationship between data tables, perform visual display on data lineage, increase the retrieval function for data lineage relationships, enabling relevant staff to have an overall and macroscopic understanding and control of the data.

[0006] When analyzing the data lineage relationship between data, this patent relies more on the similarity relationship between data storage tables and fields, that is, analyzing the logic of SQL statements and the structure of storage tables in the database to establish data lineage relationships; however, this method will result in the data lineage relationship only relying on structured data storage and being unable to perform automatic lineage analysis on unstructured running data. Summary of the Invention

[0007] The purpose of the present invention is to provide a method and system for analyzing the lineage of power data assets to solve the technical problem that the prior art cannot perform automatic lineage analysis on unstructured running data.

[0008] To achieve the above purpose, the present invention adopts the following technical solutions: In the first aspect, the present invention provides a method for analyzing the lineage of power data assets, including: Obtain power data and determine whether the obtained power data type is structured model data or unstructured running data; Perform lineage analysis on unstructured running data to obtain data lineage relationships; Input the data lineage relationships obtained by performing lineage analysis on unstructured running data into a pre-trained self-trained recurrent neural network to obtain data lineage impact factors under the data lineage relationships of unstructured running data.

[0009] A further improvement of the present invention is that in the step of performing lineage analysis on unstructured running data to obtain data lineage relationships, it includes data lineage analysis between native data and data lineage analysis between derivative data and native data.

[0010] A further improvement of the present invention lies in that the step of analyzing the data lineage between the native data specifically includes: identifying the ID field in the device model table, confirming the device type according to the ID coding rule, combining the maintained device connection relationship situation, then reading the connection relationship between devices, automatically identifying and associating the native data of the same type, and establishing the data lineage relationship.

[0011] A further improvement of the present invention lies in that the step of analyzing the data lineage between the derivative data and the native data specifically includes: calculating the logic according to the model data name, the running data name, and the logical relationship formula; extracting the relationship between the associated derivative data, the native data, and the static parameters of the device model used in the calculation logic, and establishing the data lineage relationship.

[0012] A further improvement of the present invention lies in that the step of inputting the data lineage relationship obtained by analyzing the data lineage of the unstructured running data into a pre-trained self-trained recurrent neural network to obtain the data lineage influence factor under the data lineage relationship of the unstructured running data specifically includes: Inputting the data lineage relationship of the unstructured running data, the time-series native data, or the time-series derivative data into a pre-trained self-trained recurrent neural network, and calculating the associated influence factor reward through an activation function in the input layer: reward = k1 * cal_logic + k2* data_dif + k3 * response_dif Wherein, cal_logic is the calculation logic influence factor, data_dif is the input data change factor, response_dif is the output data influence factor, and k1, k2, and k3 are respectively dynamically adjusted weight coefficients; Returning the obtained associated influence factor reward to the input layer, continuously looping until the gradient converges to a set threshold, outputting this associated influence factor reward, and setting it as the data lineage influence factor under the data lineage relationship of the input unstructured running data.

[0013] A further improvement of the present invention lies in that the pre-trained self-trained recurrent neural network is a GRU.

[0014] A further improvement of the present invention further includes the following steps: for the structured model data, identifying the ID field in the device model table, confirming the device type according to the ID coding rule, combining the maintained device ownership relationship situation, identifying the associated device management ledger information, and establishing the data lineage relationship between the device ID and the institutional ID field; combining the maintained device connection relationship situation, identifying the associated device static parameter information, and establishing the data lineage relationship between each device model table and the static parameter fields between each device.

[0015] In a second aspect, the present invention provides a power data asset lineage analysis system, comprising: A data analysis module, configured to obtain power data and determine whether the obtained power data type is structured model data or unstructured operation data; A lineage analysis module, configured to perform lineage analysis on the unstructured operation data to obtain data lineage relationships; An impact factor extraction module, configured to input the data lineage relationships obtained by performing lineage analysis on the unstructured operation data into a pre-trained self-trained recurrent neural network to obtain data lineage impact factors under the data lineage relationships of the unstructured operation data.

[0016] In a third aspect, the present invention provides an electronic device, comprising a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the power data asset lineage analysis method.

[0017] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the power data asset lineage analysis method is implemented.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a power data asset lineage analysis method, comprising: obtaining power data and determining whether the obtained power data type is structured model data or unstructured operation data; performing lineage analysis on the unstructured operation data to obtain data lineage relationships; inputting the data lineage relationships obtained by performing lineage analysis on the unstructured operation data into a pre-trained self-trained recurrent neural network to obtain data lineage impact factors under the data lineage relationships of the unstructured operation data. The present invention can automatically establish data lineage relationships for unstructured operation data; by establishing data lineage relationships for structured data and unstructured operation data, dynamic tracking of data relationships is realized, and the upstream and downstream data links are updated in real time. By obtaining data lineage impact factors, weight analysis of the change impacts between data is realized. When data anomalies occur, troubleshooting can start from the data with large impacts, realizing fast positioning and tracing of data anomalies. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The specification drawings forming a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings: Figure 1 It is a schematic diagram of the structured model data lineage analysis process; Figure 2Schematic diagram of the unstructured operation data lineage analysis process; Figure 3 Schematic diagram of the unstructured operation data factor analysis process; Figure 4 Schematic diagram of the process of a power data asset lineage analysis method according to an embodiment of the present invention; Figure 5 Block diagram of the structure of a power data asset lineage analysis system according to an embodiment of the present invention; Figure 6 Block diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed implementation manners

[0020] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments may be combined with each other.

[0021] The following detailed descriptions are all exemplary descriptions, aiming to provide further detailed descriptions of the present invention. Unless otherwise specified, all technical terms adopted by the present invention have the same meaning as commonly understood by those of ordinary skill in the art to which the present invention belongs. The terms used in the present invention are only for describing specific implementation manners, and are not intended to limit the exemplary embodiments according to the present invention.

[0022] Definition of technical terms: Native data: The original data collected by the acquisition device and sent to the data platform.

[0023] Derived data: Data obtained through mathematical calculations based on some device static parameters in the native data and model data.

[0024] Structured model data: Information such as device ledgers and device parameters stored in a structured manner.

[0025] Unstructured operation data: Data collected by the acquisition device stored in an unstructured manner, such as device electrical quantities and signal quantities, which have the characteristic of time series.

[0026] In view of the multi-source heterogeneous data collected by the current power big data platform, and there are many data storage components and types in the big data platform, in order to trace the data source and transfer path, quickly locate the root cause of data anomalies, it is necessary to analyze the association relationship and the degree of association impact between data according to the characteristics of different types of data storage structures, evaluate the impact of data changes on downstream systems, and ensure the integrity and traceability of the data supporting the decision-making basis of each business application. The present invention provides a power data asset lineage analysis method for solving the above technical problems.

[0027] A method for analyzing the lineage of electric power data assets according to the present invention performs data lineage analysis based on multi-source structured data and unstructured data collected by an electric power big data platform. For structured model data, data lineage analysis of the structured model data is realized through automatic identification and association of data tables and fields. For unstructured operation data, a neural network is trained to determine the calculation formula logic between the original data and the derivative data and the influence results of past historical data changes, and the neural network is trained to determine the data lineage influence factors between the original data and the derivative data, and the data lineage influence factors are dynamically adjusted.

[0028] Currently, the big data platform has collected a large amount of multi-source heterogeneous electric power data generated by various automation dispatching systems such as SCADA, OMS, EMS, and D5000. These data are of various types, with complex data relationships and strong interaction effects between data. In the embodiments of the present invention, data lineage analysis is performed on electric power models and operation data to realize automatic identification of the association relationships between data and tracing of the full-life cycle flow paths of data, accurately locate the data flow directions, support cross-system and full-scenario data transparency management and data governance, and thus provide full-chain and dynamic data governance support for the digital transformation of the power grid.

[0029] The embodiments of the present invention provide a method for analyzing the lineage of electric power data assets, including the following steps: Obtain the electric power data of the big data platform, and determine whether the obtained data type is structured model data or unstructured operation data; Please refer to Figure 1 As shown, for structured model data, the structured model data is generally stored in the form of a device model table; generally, a type of device is stored in the same device model table; first, identify the ID field in the device model table, confirm the device type according to the ID coding rule, and combine the maintained device ownership relationship to identify the associated device management ledger information (the management ledger information between each device and the management agency), and establish the data lineage relationship between the device ID and the agency ID field; combine the maintained device connection relationship to identify the associated device static parameter information, and establish the data lineage relationship between the static parameter fields of each device model table and each device.

[0030] Please refer to Figure 2As shown in the figure, for unstructured operation data, data lineage analysis is divided into two parts. For the data lineage analysis between native data, first identify the ID field in the device model table, confirm the device type according to the ID coding rule, and combine the maintained device connection relationship. Then read the connection relationship between devices, automatically identify and associate the native data of the same type, and establish the data lineage relationship. For the data lineage analysis between derived data and native data, calculate the logic according to the model data name, operation data name, and logical relationship formula stored in the big data operation platform; extract the relationship between the associated derived data, native data, and static parameters of the device model when calculating the logic, and establish the data lineage relationship.

[0031] Please refer to Figure 3 As shown in the figure, for the lineage relationship of the aforementioned unstructured operation data, input the data lineage relationship, time-series native data, or time-series derived data of the unstructured operation data into a pre-trained self-trained recurrent neural network (in a specific embodiment of the present invention, the recurrent neural network used is GRU (Gated Recurrent Unit); pre-trained in advance using historical data), and calculate the correlation influence factor reward through the activation function in the input layer: reward = k1 * cal_logic + k2* data_dif + k3 * response_dif Where cal_logic is the calculation logic influence factor (a fixed value obtained through pre-training), data_dif is the input data change factor, response_dif is the output data influence factor, and k1, k2, and k3 are the weight coefficients adjusted dynamically.

[0032] Calculate the correlation influence factor reward through the above activation function, return the obtained correlation influence factor reward to the input layer, and this loop continues until the gradient converges to the set threshold, and output this correlation influence factor reward, which is set as the data lineage influence factor under the data lineage relationship of the input unstructured operation data.

[0033] Please refer to Figure 4 As shown in the figure, an embodiment of the present invention provides a method for power data asset lineage analysis, including: S1. Obtain power data and determine whether the obtained power data type is structured model data or unstructured operation data; S2. Conduct lineage analysis on the unstructured operation data to obtain the data lineage relationship; S3. Input the data lineage relationship obtained by performing lineage analysis on the unstructured operation data into a pre-trained self-trained recurrent neural network to obtain the data lineage impact factor under the data lineage relationship of the unstructured operation data.

[0034] In a specific embodiment, in the step of performing lineage analysis on the unstructured operation data to obtain the data lineage relationship, it includes the data lineage analysis between the native data and the data lineage analysis between the derived data and the native data.

[0035] In a specific embodiment, the step of the data lineage analysis between the native data specifically includes: identifying the ID field in the device model table, confirming the device type according to the ID coding rule, combining the maintained device connection relationship, then reading the connection relationship between the devices, automatically identifying and associating the native data of the same type, and establishing the data lineage relationship.

[0036] In a specific embodiment, the step of the data lineage analysis between the derived data and the native data specifically includes: calculating the logic according to the model data name, the operation data name and the logical relationship formula; extracting the relationship between the associated derived data, the native data and the static parameters of the device model used in the calculation logic, and establishing the data lineage relationship.

[0037] In a specific embodiment, the step of inputting the data lineage relationship obtained by performing lineage analysis on the unstructured operation data into a pre-trained self-trained recurrent neural network to obtain the data lineage impact factor under the data lineage relationship of the unstructured operation data specifically includes: Input the data lineage relationship of the unstructured operation data, the time-series native data or the time-series derived data into a pre-trained self-trained recurrent neural network, and calculate the associated impact factor reward through the activation function in the input layer: reward = k1 * cal_logic + k2* data_dif + k3 * response_dif where cal_logic is the calculation logic impact factor, data_dif is the input data change factor, response_dif is the output data impact factor, and k1, k2, and k3 are the dynamically adjusted weight coefficients respectively; Return the obtained associated impact factor reward to the input layer, and loop continuously until the gradient converges to the set threshold, output this associated impact factor reward, and set it as the data lineage impact factor under the data lineage relationship of the input unstructured operation data.

[0038] In a specific embodiment, the pre-trained self-trained recurrent neural network is GRU.

[0039] In a specific embodiment, the following steps are further included: for the structured model data, identify the ID field in the device model table, confirm the device type according to the ID coding rule, combine the maintained device ownership relationship, identify the associated device management ledger information, and establish the data lineage relationship between the device ID and the organization ID field; combine the maintained device connection relationship, identify the static parameter information of the associated devices, and establish the data lineage relationship between the static parameter fields of each device model table and each device.

[0040] Please refer to Figure 5 As shown, the embodiment of the present invention further provides a power data asset lineage analysis system, including: A data analysis module, configured to obtain power data and determine whether the obtained power data type is structured model data or unstructured operation data; A lineage analysis module, configured to perform lineage analysis on the unstructured operation data to obtain a data lineage relationship; An influence factor extraction module, configured to input the data lineage relationship obtained by performing lineage analysis on the unstructured operation data into a pre-trained self-trained recurrent neural network to obtain a data lineage influence factor under the data lineage relationship of the unstructured operation data.

[0041] Please refer to Figure 6 As shown, the embodiment of the present invention provides an electronic device 100 for implementing a power data asset lineage analysis method; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0042] The memory 101 can be used to store the computer program 103. The processor 102 realizes the steps of a power data asset lineage analysis method described in the embodiment by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created according to the use of the electronic device 100 (such as audio data, etc.). In addition, the memory 101 may include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (FlashCard), at least one magnetic disk storage device, a flash device, or other non-volatile solid-state storage devices.

[0043] The at least one processor 102 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or the processor 102 may also be any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and connects various parts of the entire electronic device 100 through various interfaces and lines.

[0044] The memory 101 in the electronic device 100 stores multiple instructions to implement a method for analyzing the lineage of power data assets. The processor 102 can execute the multiple instructions to implement: Obtain power data and determine whether the obtained power data type is structured model data or unstructured operation data; Perform lineage analysis on the unstructured operation data to obtain data lineage relationships; Input the data lineage relationships obtained by performing lineage analysis on the unstructured operation data into a pre-trained self-trained recurrent neural network to obtain data lineage influence factors under the data lineage relationships of the unstructured operation data.

[0045] If the modules / units integrated in the electronic device 100 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, and read-only memory (ROM, Read-Only Memory).

[0046] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0047] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0048] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0049] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, such that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable devices provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0050] 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 above embodiments, those of ordinary skill in the art should understand that: still can modify the specific implementation manners of the present invention or make equivalent substitutions, and any modification or equivalent substitution within the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. A method for analyzing the lineage of power data assets, characterized in that, Including: Obtain power data and determine whether the obtained power data type is structured model data or unstructured operation data; Conduct lineage analysis on the unstructured operation data to obtain data lineage relationships; Input the data lineage relationships obtained from the lineage analysis of the unstructured operation data into a pre-trained self-training recurrent neural network to obtain data lineage impact factors under the data lineage relationships of the unstructured operation data.

2. The method for analyzing the lineage of power data assets according to claim 1, wherein In the step of conducting lineage analysis on the unstructured operation data to obtain data lineage relationships, it includes the lineage analysis between native data and the lineage analysis between derivative data and native data.

3. The method for power data asset lineage analysis according to claim 2, characterized in that The step of the lineage analysis between native data specifically includes: identifying the ID field in the device model table, confirming the device type according to the ID coding rule, combining the maintained device connection relationship situation, then reading the connection relationship between devices, automatically identifying and associating the native data of the same type, and establishing data lineage relationships.

4. The method for analyzing the lineage of power data assets according to claim 2, characterized in that, The step of the lineage analysis between derivative data and native data specifically includes: calculating the logic according to the model data name, operation data name and logical relationship formula; extracting the relationships among the associated derivative data, native data and static parameters of the device model used in the calculation logic, and establishing data lineage relationships.

5. The method for analyzing the lineage of power data assets according to claim 1, wherein The step of inputting the data lineage relationships obtained from the lineage analysis of the unstructured operation data into a pre-trained self-training recurrent neural network to obtain data lineage impact factors under the data lineage relationships of the unstructured operation data specifically includes: Input the data lineage relationships, time-series native data or time-series derivative data of the unstructured operation data into a pre-trained self-training recurrent neural network, and calculate the associated impact factor reward through an activation function in the input layer: reward = k1 * cal_logic + k2* data_dif + k3 * response_dif Where cal_logic is the calculation logic impact factor, data_dif is the input data change factor, response_dif is the output data impact factor, and k1, k2, and k3 are weight coefficients dynamically adjusted respectively; Return the obtained associated impact factor reward to the input layer, continuously loop until the gradient converges to a set threshold, output this associated impact factor reward, and set it as the data lineage impact factor under the data lineage relationships of the input unstructured operation data.

6. The method for analyzing the lineage of power data assets according to claim 5, wherein The pre-trained self-training recurrent neural network is GRU.

7. A method for analyzing the lineage of power data assets according to claim 1, characterized in that It also includes the following steps: For the structured model data, identify the ID field in the device model table, confirm the device type according to the ID coding rule, combine the maintained device ownership relationship situation, identify the associated device management ledger information, and establish the data lineage relationship between the device ID and the institutional ID field; combine the maintained device connection relationship situation, identify the associated device static parameter information, and establish the data lineage relationship between each device model table and the static parameter fields between devices.

8. A power data asset lineage analysis system, characterized in that, Including: A data analysis module, configured to obtain power data and determine whether the obtained power data type is structured model data or unstructured operation data; A lineage analysis module, configured to perform lineage analysis on unstructured operation data to obtain data lineage relationships; An impact factor extraction module, configured to input the data lineage relationships obtained by performing lineage analysis on unstructured operation data into a pre-trained self-trained recurrent neural network to obtain data lineage impact factors under the data lineage relationships of unstructured operation data.

9. An electronic device, characterized in that, It includes a processor and a memory. The processor is configured to execute a computer program stored in the memory to implement a method for power data asset lineage analysis according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, a method for power data asset lineage analysis according to any one of claims 1 to 7 is implemented.

Images