SCD file verification method and device, terminal equipment and storage medium
By parsing and comparing the virtual link information of SCD files, and using a preset model and database for automated verification, the problem of high error rate and low efficiency caused by manual verification is solved, and efficient and accurate SCD file verification is achieved.
Patent Information
- Application Number
- CN202511627377.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-07
- Publication Date
- 2026-02-10
Smart Images
Figure CN121503422A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of document verification technology, and in particular to an SCD document verification method, apparatus, terminal device, and storage medium. Background Technology
[0002] In the automation system of a smart substation, various intelligent electronic devices (IEDs), such as protection devices, measurement and control devices, and merging units, need to achieve data interaction and collaborative work through a network. The Substation Configuration Description (SCD) is the core carrier for realizing this collaboration. Through the SCD file, maintenance personnel can intuitively grasp the configuration logic and communication topology of all equipment in the substation. During equipment commissioning, there is no need to check the physical lines one by one; the correctness of the signal path can be verified simply by parsing the SCD file. When upgrading the system or replacing equipment, the connection relationships can be quickly adjusted by modifying the configuration information in the SCD file, significantly improving the flexibility and operational efficiency of the substation. Therefore, the completeness and accuracy of the SCD file directly determine the safe operation of the smart substation.
[0003] In existing technologies, SCD file verification mainly relies on manual reading to check the correctness and standardization of content such as virtual links in the SCD file. However, SCD files are often complex and contain a large amount of data. Therefore, existing technologies suffer from high error rates and slow efficiency when manually verifying SCD files. Summary of the Invention
[0004] This invention provides an SCD file verification method, apparatus, terminal device, and storage medium, which can solve the problem that the existing technology uses manual reading to verify SCD files with complex content and large data volume, resulting in a high error rate and slow efficiency.
[0005] An embodiment of the present invention provides an SCD file verification method, comprising:
[0006] Obtain the SCD file to be verified, and parse the SCD file to obtain virtual connection information and IED node information;
[0007] The above virtual link information is input into the preset file correctness verification model to obtain the correctness of the above SCD file to be verified.
[0008] If the SCD file to be verified is correct, extract the first virtual connection information of the first IED node that has the same function as the IED node information, and the second virtual connection information of the second IED node that has a dual configuration relationship with the IED node information from the preset file database.
[0009] The virtual link information of the SCD file to be verified is compared with the first virtual link information and the second virtual link information. If the comparison results are the same, the SCD file to be verified is determined to be complete.
[0010] Furthermore, the construction of the aforementioned preset file database includes:
[0011] Obtain several historical SCD files;
[0012] After parsing all historical SCD files, we obtain the historical virtual link information and historical IED node information for each historical SCD file.
[0013] Functional information and dual configuration information for obtaining information on each historical IED node;
[0014] Based on the aforementioned historical virtual connection information, historical IED node information, functional information of historical IED node information, and dual configuration information, the aforementioned preset file database is constructed.
[0015] Furthermore, the training of the aforementioned pre-defined document correctness verification model includes:
[0016] Obtain the real tags corresponding to each historical virtual link; wherein, the real tags are used to indicate the correctness of the historical SCD files corresponding to the historical virtual link information.
[0017] The aforementioned historical virtual connection information and the aforementioned real labels are input into the file correctness verification model to be trained for iterative training until the model evaluation index is greater than the preset index value, thereby generating the aforementioned preset file correctness verification model.
[0018] In each iteration of training, the current historical virtual connection information is input into the current file correctness verification model to obtain the correctness prediction result corresponding to each historical virtual connection information. Based on the current correctness prediction result and the corresponding true label, the current model evaluation index is calculated. If the current model evaluation index is greater than the preset index value, the current file correctness verification model is used as the preset file correctness verification model. Otherwise, the hyperparameters of the current file correctness verification model are adjusted, and the model is retrained.
[0019] Furthermore, based on the current accuracy prediction results and the corresponding true labels, the current model evaluation metrics are calculated, including:
[0020] Clustering the above historical virtual connection information yields several sub-virtual connection datasets;
[0021] Based on the current correctness prediction results and the corresponding true labels, a confusion matrix is constructed for each sub-virtual connection dataset.
[0022] After integrating the confusion matrices of each virtual connection dataset, the current integrated confusion matrix is obtained;
[0023] The current model evaluation index is calculated based on the current integration confusion matrix.
[0024] Furthermore, after determining that the SCD file to be verified is complete, the process also includes:
[0025] All historical virtual link information is extracted from the aforementioned preset file database;
[0026] An SVG file is generated based on all historical virtual link information and the virtual link information of the SCD file to be verified, for the visualization of virtual links.
[0027] Based on the above method embodiments, the present invention provides corresponding apparatus embodiments;
[0028] This invention provides an SCD file verification device, comprising:
[0029] The module includes a file parsing module, a file correctness verification module, a data extraction module, and a file integrity verification module.
[0030] The aforementioned file parsing module is used to obtain the SCD file to be verified and parse the SCD file to obtain virtual link information and IED node information.
[0031] The above-mentioned file correctness verification module is used to input the above-mentioned virtual link information into the preset file correctness verification model to obtain the correctness of the above-mentioned SCD file to be verified.
[0032] The aforementioned data extraction module is used to extract, when the aforementioned SCD file to be verified is correct, the first virtual connection information of the first IED node that has the same function as the aforementioned IED node information, and the second virtual connection information of the second IED node that has a dual configuration relationship with the aforementioned IED node information from the preset file database.
[0033] The aforementioned file integrity verification module is used to compare the virtual link information of the SCD file to be verified with the first virtual link information and the second virtual link information, respectively. If the comparison results are the same, the SCD file to be verified is determined to be complete.
[0034] Furthermore, the aforementioned data extraction module includes:
[0035] The system includes a historical file acquisition unit, a historical file parsing unit, a file information acquisition unit, and a database construction unit.
[0036] The aforementioned historical file acquisition unit is used to acquire several historical SCD files;
[0037] The aforementioned historical file parsing unit is used to parse all historical SCD files to obtain the historical virtual link information and historical IED node information of each historical SCD file.
[0038] The aforementioned file information acquisition unit is used to acquire functional information and dual configuration information of each historical IED node;
[0039] The aforementioned database construction unit is used to construct the aforementioned preset file database based on the aforementioned historical virtual connection information, historical IED node information, functional information of historical IED node information, and dual configuration information.
[0040] Furthermore, the aforementioned document correctness verification module includes:
[0041] Label acquisition unit and model training unit;
[0042] The aforementioned tag acquisition unit is used to acquire the real tags corresponding to each historical virtual link information; wherein, the aforementioned real tags are used to indicate the correctness of the historical SCD files corresponding to the aforementioned historical virtual link information.
[0043] The aforementioned model training unit is used to input the aforementioned historical virtual connection information and the aforementioned real labels into the file correctness verification model to be trained for iterative training until the model evaluation index is greater than the preset index value, thereby generating the aforementioned preset file correctness verification model. Specifically, during each iteration of training, the current historical virtual connection information is input into the current file correctness verification model to obtain the correctness prediction result corresponding to each historical virtual connection information. Based on the current correctness prediction result and the corresponding real label, the current model evaluation index is calculated. If the current model evaluation index is greater than the preset index value, then the current file correctness verification model is used as the preset file correctness verification model; otherwise, the hyperparameters of the current file correctness verification model are adjusted, and the model is retrained.
[0044] Based on the above method embodiments, the present invention provides a corresponding terminal device embodiment;
[0045] The present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements an SCD file verification method described in any embodiment of the present invention.
[0046] Based on the above method embodiments, the present invention provides a corresponding storage medium embodiment;
[0047] The present invention provides a storage medium including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements an SCD file verification method according to any embodiment of the present invention.
[0048] The embodiments of the present invention have the following beneficial effects:
[0049] This invention provides an SCD file verification method, apparatus, terminal device, and storage medium. The method includes: acquiring an SCD file to be verified and parsing it to obtain virtual link information and IED node information; then inputting the virtual link information into a preset file correctness verification model to obtain the correctness of the SCD file; if the SCD file is correct, extracting first virtual link information of a first IED node with the same function as the IED node information, and second virtual link information of a second IED node with a dual configuration relationship with the IED node information from a preset file database; finally, comparing the virtual link information of the SCD file to be verified with the first virtual link information and the second virtual link information respectively; if the comparison results are the same, the SCD file to be verified is determined to be complete. Therefore, this invention verifies the correctness of SCD files through a preset file correctness verification model, compares it with virtual link information with the same function and a dual configuration relationship, and determines the integrity of the SCD file based on the comparison results to obtain the verification result. The entire process does not require manual verification, thus greatly reducing the error rate and slow efficiency problems caused by manual verification. Attached Figure Description
[0050] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0051] Figure 1 This is a flowchart illustrating an SCD file verification method provided in an embodiment of the present invention.
[0052] Figure 2 This is a schematic diagram of the structure of an SCD file verification device provided in an embodiment of the present invention. Detailed Implementation
[0053] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.
[0055] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.
[0056] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0057] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.
[0058] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).
[0059] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.
[0060] See Figure 1 To address the problem that existing technologies rely on manual reading to verify complex and large-volume SCD files, resulting in high error rates and slow efficiency, an embodiment of the present invention provides an SCD file verification method, comprising:
[0061] Step S101: Obtain the SCD file to be verified, and parse the SCD file to be verified to obtain virtual connection information and IED node information;
[0062] Specifically, the SAX parsing method is used to parse the SCD file to be verified. The IED node information mentioned above includes: "IED", "AccessPoint", "LD", "LN", "DO", "DA", "Input" and their corresponding name and desc attribute values. The SAX parsing method is as follows: First, a SAXHandeltoSCDFile class is created to implement the SAX parsing method. Then, the startDocument method to start traversing the document and the endDocument method to end the document are added to the class. The startElement and endElement methods are used to obtain the attribute values of each node in the SCD file, such as the name and desc attribute values. Finally, the characters method is used to obtain the Value values of the "IED", "AccessPoint", "LD", "LN", "DO", "DA", and "Input" nodes.
[0063] Preferably, using the SAX parsing method to parse the file to obtain relevant data information of the SCD file can improve the data extraction efficiency of the SCD file.
[0064] Step S102: Input the above virtual link information into the preset file correctness verification model to obtain the correctness of the above SCD file to be verified;
[0065] Specifically, the above-mentioned preset file correctness verification model is built based on the KNN model.
[0066] In a preferred embodiment, training the aforementioned preset document correctness verification model includes:
[0067] Obtain the real tags corresponding to each historical virtual link; wherein, the real tags are used to indicate the correctness of the historical SCD files corresponding to the historical virtual link information.
[0068] The aforementioned historical virtual connection information and the aforementioned real labels are input into the file correctness verification model to be trained for iterative training until the model evaluation index is greater than the preset index value, thereby generating the aforementioned preset file correctness verification model.
[0069] Specifically, the evaluation metrics for the aforementioned models are accuracy, precision, and recall. Accuracy refers to the percentage of results predicted correctly by the model out of the total results; precision is the probability of a result whose true label is "correct" and whose model prediction is also "correct" among all results predicted correctly by the model; and recall is the probability of a result whose true label is "correct" and whose model prediction is also "correct" among all predicted results corresponding to "correct" true labels.
[0070] In each iteration of training, the current historical virtual connection information is input into the current file correctness verification model to obtain the correctness prediction result corresponding to each historical virtual connection information. Based on the current correctness prediction result and the corresponding true label, the current model evaluation index is calculated. If the current model evaluation index is greater than the preset index value, the current file correctness verification model is used as the preset file correctness verification model. Otherwise, the hyperparameters of the current file correctness verification model are adjusted, and the model is retrained.
[0071] Specifically, the hyperparameters mentioned above include the K value within the model.
[0072] Specifically, the precision, accuracy, and recall metrics are calculated using the following formulas:
[0073]
[0074]
[0075] In the formula, Precision represents the precision metric, ACC represents the accuracy metric, Recall represents the recall metric, TP represents true positives (the number of documents predicted as "correct" by the document correctness verification model and whose true label is also "correct"), FP represents false positives (the number of documents predicted as "correct" by the document correctness verification model but whose true label is "incorrect"), TN represents true negatives (the number of documents predicted as "incorrect" by the document correctness verification model and whose true label is also "incorrect"), and FN represents false negatives (the number of documents predicted as "incorrect" by the document correctness verification model but whose true label is "correct"), which is also false negatives.
[0076] In this preferred embodiment, the training of the preset file correctness verification model is completed using historical virtual connection information and corresponding real tags.
[0077] In another preferred embodiment, the current model evaluation metric is calculated based on the current correctness prediction result and the corresponding true label, including:
[0078] Clustering the above historical virtual connection information yields several sub-virtual connection datasets;
[0079] Specifically, the k-means clustering algorithm is used for clustering.
[0080] Based on the current correctness prediction results and the corresponding true labels, a confusion matrix is constructed for each sub-virtual connection dataset.
[0081] After integrating the confusion matrices of each virtual connection dataset, the current integrated confusion matrix is obtained;
[0082] The current model evaluation index is calculated based on the current integration confusion matrix.
[0083] Specifically, a confusion matrix can be constructed based on the true positives, false positives, true negatives, and false negatives corresponding to each virtual connection dataset.
[0084] In this preferred embodiment, the current model evaluation index is calculated using the current correctness prediction results and the corresponding true labels.
[0085] Step S103: If the SCD file to be verified is correct, extract the first virtual connection information of the first IED node that has the same function as the IED node information, and the second virtual connection information of the second IED node that has a dual configuration relationship with the IED node information from the preset file database.
[0086] For illustrative purposes, if IED nodes "A" and "B" are both line protection devices of the same type, and both function as overcurrent protection and reclosing control for 110kV lines, then they are considered to have the same function. If IED nodes "A" and "B" are dual-configuration IEDs in the same bay (such as set A and set B equipment), then they are considered to have a dual configuration relationship.
[0087] In a preferred embodiment, the construction of the aforementioned preset file database includes:
[0088] Obtain several historical SCD files;
[0089] After parsing all historical SCD files, we obtain the historical virtual link information and historical IED node information for each historical SCD file.
[0090] Functional information and dual configuration information for obtaining information on each historical IED node;
[0091] Based on the aforementioned historical virtual connection information, historical IED node information, functional information of historical IED node information, and dual configuration information, the aforementioned preset file database is constructed.
[0092] Specifically, after parsing the historical SCD files, a CRC checksum is obtained. Therefore, when constructing the preset file database, this CRC checksum is used as the unique identification attribute to identify the corresponding historical SCD file.
[0093] Specifically, when constructing the preset file database, for each historical SCD file, its corresponding historical virtual connection information, historical IED node information, historical IED node information function information, and dual configuration information are placed into an array to construct a MySQL database.
[0094] Preferably, when constructing the preset file database, a CRC checksum is used as the unique identification attribute of the SCD file, which reduces the reading time and achieves efficient reading when reading historical SCD files again.
[0095] In this preferred embodiment, a preset file database is constructed by parsing and extracting data from historical SCD files.
[0096] Step S104: Compare the virtual link information of the SCD file to be verified with the first virtual link information and the second virtual link information respectively. If the comparison results are the same, the SCD file to be verified is determined to be complete.
[0097] Specifically, through similar IED verification, IEDs "P_L2201A" and "P_L2202A" have the same function, so their configurations should be highly similar. Through dual configuration checks, theoretically, if IEDs "P_L2201A" and "P_L2201B" are in a dual configuration relationship, their overall structure and the data connections between the two groups, including topology and virtual terminal connections, should be basically similar. Therefore, based on the above two comparison results, it can be determined whether the SCD file to be verified has missing virtual link information, and thus its integrity can be judged.
[0098] Preferably, if the comparison results are found to be different, it is necessary to further determine whether the difference is due to the difference caused by different manufacturers, and then the comparison process can be further improved.
[0099] In a preferred embodiment, after determining that the SCD file to be verified is complete, the method further includes:
[0100] All historical virtual link information is extracted from the aforementioned preset file database;
[0101] An SVG file is generated based on all historical virtual link information and the virtual link information of the SCD file to be verified, for the visualization of virtual links.
[0102] Specifically, the above SVG file is generated using elements such as rectangle (rect), circle (circl), ellipse (ellipse), line (line), and text (text), forming a visual display of virtual links, which can then be displayed in a browser.
[0103] Preferably, after visualizing the virtual connections, the details of the virtual connections of a specific device can be displayed from different viewing angles through interactive graphical design. Furthermore, the relationship between the IED and the transmitting and receiving devices can be intuitively displayed through macro diagrams, making the virtual connection display of the SCD file clearer.
[0104] Preferably, visualization is used to intuitively analyze the virtual connection information of the SCD file, realizing the optimized analysis of information interaction logic in smart substations and further ensuring the accuracy of SCD file verification.
[0105] In this preferred embodiment, the virtual links of the SCD file are visualized by generating an SVG file.
[0106] Based on the above method embodiments, the present invention provides corresponding apparatus embodiments.
[0107] like Figure 2 As shown, an embodiment of the present invention provides an SCD file verification device, comprising:
[0108] The module includes a file parsing module, a file correctness verification module, a data extraction module, and a file integrity verification module.
[0109] The aforementioned file parsing module is used to obtain the SCD file to be verified and parse the SCD file to obtain virtual link information and IED node information.
[0110] The above-mentioned file correctness verification module is used to input the above-mentioned virtual link information into the preset file correctness verification model to obtain the correctness of the above-mentioned SCD file to be verified.
[0111] The aforementioned data extraction module is used to extract, when the aforementioned SCD file to be verified is correct, the first virtual connection information of the first IED node that has the same function as the aforementioned IED node information, and the second virtual connection information of the second IED node that has a dual configuration relationship with the aforementioned IED node information from the preset file database.
[0112] The aforementioned file integrity verification module is used to compare the virtual link information of the SCD file to be verified with the first virtual link information and the second virtual link information, respectively. If the comparison results are the same, the SCD file to be verified is determined to be complete.
[0113] In a preferred embodiment, the data extraction module includes:
[0114] The system includes a historical file acquisition unit, a historical file parsing unit, a file information acquisition unit, and a database construction unit.
[0115] The aforementioned historical file acquisition unit is used to acquire several historical SCD files;
[0116] The aforementioned historical file parsing unit is used to parse all historical SCD files to obtain the historical virtual link information and historical IED node information of each historical SCD file.
[0117] The aforementioned file information acquisition unit is used to acquire functional information and dual configuration information of each historical IED node;
[0118] The aforementioned database construction unit is used to construct the aforementioned preset file database based on the aforementioned historical virtual connection information, historical IED node information, functional information of historical IED node information, and dual configuration information.
[0119] In another preferred embodiment, the above-mentioned file correctness verification module includes:
[0120] Label acquisition unit and model training unit;
[0121] The aforementioned tag acquisition unit is used to acquire the real tags corresponding to each historical virtual link information; wherein, the aforementioned real tags are used to indicate the correctness of the historical SCD files corresponding to the aforementioned historical virtual link information.
[0122] The aforementioned model training unit is used to input the aforementioned historical virtual connection information and the aforementioned real labels into the file correctness verification model to be trained for iterative training until the model evaluation index is greater than the preset index value, thereby generating the aforementioned preset file correctness verification model. Specifically, during each iteration of training, the current historical virtual connection information is input into the current file correctness verification model to obtain the correctness prediction result corresponding to each historical virtual connection information. Based on the current correctness prediction result and the corresponding real label, the current model evaluation index is calculated. If the current model evaluation index is greater than the preset index value, then the current file correctness verification model is used as the preset file correctness verification model; otherwise, the hyperparameters of the current file correctness verification model are adjusted, and the model is retrained.
[0123] It should be noted that the device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; 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. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without creative effort. The above schematic diagrams are merely examples of an SCD file verification device and do not constitute a limitation on an SCD file verification device. It may include more or fewer components than illustrated, or combine certain components, or use different components.
[0124] Based on the above method embodiments, the present invention provides corresponding terminal device embodiments.
[0125] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements an SCD file verification method described in any embodiment of the present invention.
[0126] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the device.
[0127] The aforementioned terminal devices may be computing devices such as desktop computers, laptops, handheld computers, and cloud servers. These devices may include, but are not limited to, processors and memory.
[0128] The processor can be a Central Processing Unit (CPU), or 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. A general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the device, connecting various parts of the device via various interfaces and lines.
[0129] The aforementioned memory can be used to store the aforementioned computer programs and / or modules. The aforementioned processor implements various functions of the aforementioned device by running or executing the computer programs and / or modules stored in the aforementioned memory, and by calling data stored in the memory. The aforementioned memory may mainly include a program storage area and a data storage area, wherein the program storage area may store the operating system, at least one application program required for a function, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.
[0130] Based on the above method embodiments, the present invention provides corresponding storage medium embodiments.
[0131] Another embodiment of the present invention provides a storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the storage medium is located to execute an SCD file verification method as described in any embodiment of the present invention.
[0132] In this embodiment, the storage medium is a computer-readable storage medium, and the computer program includes computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.
[0133] The above are preferred embodiments of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.
Claims
1. A method for verifying SCD files, characterized in that, include: Obtain the SCD file to be verified, and parse the SCD file to obtain virtual connection information and IED node information; The virtual connection information is input into a preset file correctness verification model to obtain the correctness of the SCD file to be verified. If the SCD file to be verified is correct, extract the first virtual connection information of the first IED node that has the same function as the IED node information, and the second virtual connection information of the second IED node that has a dual configuration relationship with the IED node information from the preset file database. The virtual link information of the SCD file to be verified is compared with the first virtual link information and the second virtual link information respectively. If the comparison results are the same, the SCD file to be verified is determined to be complete.
2. The SCD file verification method according to claim 1, characterized in that, The construction of the preset file database includes: Obtain several historical SCD files; After parsing all historical SCD files, we obtain the historical virtual link information and historical IED node information for each historical SCD file. Functional information and dual configuration information for obtaining information on each historical IED node; The preset file database is constructed based on the historical virtual connection information, historical IED node information, functional information of historical IED node information, and dual configuration information.
3. The SCD file verification method according to claim 2, characterized in that, The training of the preset file correctness verification model includes: Obtain the real tags corresponding to each historical virtual link information; wherein, the real tags are used to indicate the correctness of the historical SCD files corresponding to the historical virtual link information; The historical virtual connection information and the real labels are input into the file correctness verification model to be trained for iterative training until the model evaluation index is greater than the preset index value, and the preset file correctness verification model is generated. In each iteration of training, the current historical virtual connection information is input into the current file correctness verification model to obtain the correctness prediction result corresponding to each historical virtual connection information. Based on the current correctness prediction result and the corresponding true label, the current model evaluation index is calculated. If the current model evaluation index is greater than the preset index value, the current file correctness verification model is used as the preset file correctness verification model. Otherwise, the hyperparameters of the current file correctness verification model are adjusted, and the model is retrained.
4. The SCD file verification method according to claim 3, characterized in that, The current model evaluation metric is calculated based on the current correctness prediction results and the corresponding true labels, including: Clustering the historical virtual connection information yields several sub-virtual connection datasets; Based on the current correctness prediction results and the corresponding true labels, a confusion matrix is constructed for each sub-virtual connection dataset. After integrating the confusion matrices of each virtual connection dataset, the current integrated confusion matrix is obtained; The current model evaluation index is calculated based on the current integration confusion matrix.
5. The SCD file verification method according to claim 4, characterized in that, After determining that the SCD file to be verified is complete, the process also includes: All historical virtual connection information is extracted from the preset file database; An SVG file is generated based on all historical virtual link information and the virtual link information of the SCD file to be verified, for the visualization of virtual links.
6. An SCD file verification device, characterized in that, include: The module includes a file parsing module, a file correctness verification module, a data extraction module, and a file integrity verification module. The file parsing module is used to obtain the SCD file to be verified and parse the SCD file to obtain virtual connection information and IED node information. The file correctness verification module is used to input the virtual link information into a preset file correctness verification model to obtain the correctness of the SCD file to be verified. The data extraction module is used to extract, when the SCD file to be verified is correct, the first virtual connection information of the first IED node that has the same function as the IED node information, and the second virtual connection information of the second IED node that has a dual configuration relationship with the IED node information from the preset file database. The file integrity verification module is used to compare the virtual link information of the SCD file to be verified with the first virtual link information and the second virtual link information respectively. If the comparison results are the same, the SCD file to be verified is determined to be complete.
7. The SCD file verification device according to claim 6, characterized in that, The data extraction module includes: The system includes a historical file acquisition unit, a historical file parsing unit, a file information acquisition unit, and a database construction unit. The historical file acquisition unit is used to acquire several historical SCD files; The historical file parsing unit is used to parse all historical SCD files to obtain the historical virtual link information and historical IED node information of each historical SCD file. The file information acquisition unit is used to acquire functional information and dual configuration information of each historical IED node; The database construction unit is used to construct the preset file database based on the historical virtual connection information, historical IED node information, functional information of historical IED node information, and dual configuration information.
8. The SCD file verification device according to claim 7, characterized in that, The file integrity verification module includes: Label acquisition unit and model training unit; The tag acquisition unit is used to acquire the real tags corresponding to each historical virtual link information; wherein, the real tags are used to indicate the correctness of the historical SCD file corresponding to the historical virtual link information; The model training unit is used to input the historical virtual connection information and the real labels into the file correctness verification model to be trained for iterative training until the model evaluation index is greater than a preset index value, thereby generating the preset file correctness verification model. Specifically, during each iteration, the current historical virtual connection information is input into the current file correctness verification model to obtain the correctness prediction result corresponding to each historical virtual connection information. Based on the current correctness prediction result and the corresponding real label, the current model evaluation index is calculated. If the current model evaluation index is greater than the preset index value, the current file correctness verification model is used as the preset file correctness verification model; otherwise, the hyperparameters of the current file correctness verification model are adjusted, and the model is retrained.
9. A terminal device, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements an SCD file verification method as described in any one of claims 1 to 5.
10. A storage medium, characterized in that, The storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device where the storage medium is located to perform an SCD file verification method as described in any one of claims 1 to 5.