Power grid fault response detection method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a power grid fault response detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring first equipment information of a plurality of associated power grid equipment corresponding to target power grid equipment from a preset knowledge graph; according to each piece of first equipment information and second equipment information corresponding to the target power grid equipment, detecting equipment correlation between the target power grid equipment and each piece of associated power grid equipment to obtain a correlation detection result; detecting a coupling marshalling equipment set corresponding to the target power grid equipment from the associated power grid equipment according to the correlation detection result; and according to the coupling marshalling equipment set, carrying out equipment fault response detection based on N-1 calculation on the target power grid equipment. By adopting the method, the accuracy of power grid fault response detection can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of power grid fault response detection, and in particular to a power grid fault response detection method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the development of power grid fault response detection technology, power grid fault response detection technology has emerged. Power grid fault response detection technology can be used to detect the impact of power grid equipment failures on power grid operation.

[0003] In traditional technology, grid equipment data is usually collected first, and then grid fault response detection is performed based on the grid equipment data.

[0004] However, power grid equipment data is usually massive, and it is usually difficult to filter out effective data from the massive data for power grid fault response detection, which results in low accuracy of power grid fault response detection. Summary of the invention

[0005] Based on this, it is necessary to provide a power grid fault response detection method, device, computer equipment, computer readable storage medium and computer program product that can improve the accuracy of power grid fault response detection in order to address the above technical problems.

[0006] In a first aspect, the present application provides a power grid fault response detection method, comprising:

[0007] Acquire first device information of multiple associated power grid devices corresponding to the target power grid device from a preset knowledge graph;

[0008] According to each of the first device information and the second device information corresponding to the target power grid device, detecting the device correlation between the target power grid device and each of the associated power grid devices, and obtaining a correlation detection result;

[0009] According to the correlation detection result, detecting a coupling grouping device set corresponding to the target power grid device from each of the associated power grid devices;

[0010] According to the coupled marshaling device set, device fault response detection based on N-1 calculation is performed on the target power grid device.

[0011] In one embodiment, the coupled grouping device set includes a plurality of coupled grouping power grid devices; and performing device fault response detection based on N-1 calculation on the target power grid device according to the coupled grouping device set includes:

[0012] Acquire the marshaling device information of each of the coupled marshaling power grid devices from a preset knowledge graph;

[0013] Extracting features from each of the marshaling equipment information to obtain a plurality of marshaling equipment features;

[0014] According to the characteristics of each of the marshaling devices, detecting the type of the N-1 calculation model for the target power grid device to perform the N-1 calculation;

[0015] According to the target N-1 calculation model corresponding to the N-1 calculation model type, the target power grid equipment is subjected to N-1 calculation-based equipment fault response detection.

[0016] In one embodiment, the detecting, according to the characteristics of each of the marshaling devices, the type of the N-1 calculation model for the target power grid device to perform the N-1 calculation includes:

[0017] Detecting device association relationship information between each of the coupled grouping power grid devices and the target power grid device from the preset knowledge graph;

[0018] According to the equipment association relationship information, a corresponding feature weight is matched for each of the marshaling equipment features;

[0019] According to the feature weight corresponding to each of the marshalling equipment features, weighted fusion is performed on the features of each marshalling equipment to obtain a fused equipment feature;

[0020] According to the fusion device feature and the second device feature corresponding to the second device information, the N-1 calculation model type of the target power grid device for performing the N-1 calculation is detected.

[0021] In one embodiment, detecting the device correlation between the target power grid device and each of the associated power grid devices according to each of the first device information and the second device information corresponding to the target power grid device includes:

[0022] Extracting device features from the first device information to obtain first device features corresponding to the associated power grid device;

[0023] Extracting device features from the second device information of the target power grid device to obtain a second device feature corresponding to the target power grid device;

[0024] According to the feature similarity between the first device feature and the second device feature, the device correlation between the target power grid device and the associated power grid device is detected.

[0025] In one embodiment, the correlation detection result includes a device correlation value; and detecting the coupling grouping device set corresponding to the target power grid device from each of the associated power grid devices according to the correlation detection result includes:

[0026] If the device correlation value is greater than a preset correlation threshold, marking the associated power grid device corresponding to the device correlation value as an associated power grid device of the first type;

[0027] If the device correlation value is not greater than a preset correlation threshold, marking the associated power grid device corresponding to the device correlation value as an associated power grid device of the second type;

[0028] All the first-type associated power grid devices are collectively set as a coupling grouping device set corresponding to the target power grid device.

[0029] In one embodiment, the method further comprises:

[0030] Acquire power grid data text, wherein the power grid data text includes device parameter texts of a plurality of basic power grid devices;

[0031] According to the device parameter texts of the plurality of basic power grid devices, detecting association relationships between the plurality of basic power grid devices in pairs, and obtaining an association relationship detection result;

[0032] A preset knowledge graph is constructed based on the association relationship detection results and the equipment parameter texts of the multiple basic power grid equipment.

[0033] In a second aspect, the present application further provides a power grid fault response detection device, comprising:

[0034] An acquisition module, used to acquire first device information of multiple associated power grid devices corresponding to the target power grid device from a preset knowledge graph;

[0035] A first detection module, configured to detect the device correlation between the target power grid device and each of the associated power grid devices according to each of the first device information and the second device information corresponding to the target power grid device, and obtain a correlation detection result;

[0036] A second detection module, configured to detect a coupling grouping device set corresponding to the target power grid device from each of the associated power grid devices according to the correlation detection result;

[0037] The device fault response detection module is used to perform device fault response detection based on N-1 calculation on the target power grid device according to the coupled marshaling device set.

[0038] In one embodiment, the coupled grouping device set includes a plurality of coupled grouping power grid devices; the device fault response detection module is further used for:

[0039] Acquire the marshaling device information of each of the coupled marshaling power grid devices from a preset knowledge graph;

[0040] Extracting features from each of the marshaling equipment information to obtain a plurality of marshaling equipment features;

[0041] According to the characteristics of each of the marshaling devices, detecting the type of the N-1 calculation model for the target power grid device to perform the N-1 calculation;

[0042] According to the target N-1 calculation model corresponding to the N-1 calculation model type, the target power grid equipment is subjected to N-1 calculation-based equipment fault response detection.

[0043] In one embodiment, the device fault response detection module is further used to:

[0044] Detecting device association relationship information between each of the coupled grouping power grid devices and the target power grid device from the preset knowledge graph;

[0045] According to the equipment association relationship information, a corresponding feature weight is matched for each of the marshaling equipment features;

[0046] According to the feature weight corresponding to each of the marshalling equipment features, weighted fusion is performed on the features of each marshalling equipment to obtain a fused equipment feature;

[0047] According to the fusion device feature and the second device feature corresponding to the second device information, the N-1 calculation model type of the target power grid device for performing the N-1 calculation is detected.

[0048] In one embodiment, the first detection module is further used for:

[0049] Extracting device features from the first device information to obtain first device features corresponding to the associated power grid device;

[0050] Extracting device features from the second device information of the target power grid device to obtain a second device feature corresponding to the target power grid device;

[0051] According to the feature similarity between the first device feature and the second device feature, the device correlation between the target power grid device and the associated power grid device is detected.

[0052] In one embodiment, the correlation detection result includes a device correlation value; and the second detection module is further configured to:

[0053] If the device correlation value is greater than a preset correlation threshold, marking the associated power grid device corresponding to the device correlation value as an associated power grid device of the first type;

[0054] If the device correlation value is not greater than a preset correlation threshold, marking the associated power grid device corresponding to the device correlation value as an associated power grid device of the second type;

[0055] All the first-type associated power grid devices are collectively set as a coupling grouping device set corresponding to the target power grid device.

[0056] In one embodiment, the device further comprises:

[0057] A knowledge graph construction module, used to obtain power grid data text, wherein the power grid data text includes device parameter texts of multiple basic power grid devices;

[0058] According to the device parameter texts of the plurality of basic power grid devices, detecting association relationships between the plurality of basic power grid devices in pairs, and obtaining an association relationship detection result;

[0059] A preset knowledge graph is constructed based on the association relationship detection results and the equipment parameter texts of the multiple basic power grid equipment.

[0060] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0061] Acquire first device information of multiple associated power grid devices corresponding to the target power grid device from a preset knowledge graph; detect the device correlation between the target power grid device and each of the associated power grid devices based on each of the first device information and the second device information corresponding to the target power grid device to obtain a correlation detection result; detect a coupled grouping device set corresponding to the target power grid device from each of the associated power grid devices based on the correlation detection result; and perform device fault response detection on the target power grid device based on N-1 calculation based on the coupled grouping device set.

[0062] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0063] Acquire first device information of multiple associated power grid devices corresponding to the target power grid device from a preset knowledge graph; detect the device correlation between the target power grid device and each of the associated power grid devices based on each of the first device information and the second device information corresponding to the target power grid device to obtain a correlation detection result; detect a coupled grouping device set corresponding to the target power grid device from each of the associated power grid devices based on the correlation detection result; and perform device fault response detection on the target power grid device based on N-1 calculation based on the coupled grouping device set.

[0064] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0065] Acquire first device information of multiple associated power grid devices corresponding to the target power grid device from a preset knowledge graph; detect the device correlation between the target power grid device and each of the associated power grid devices based on each of the first device information and the second device information corresponding to the target power grid device to obtain a correlation detection result; detect a coupled grouping device set corresponding to the target power grid device from each of the associated power grid devices based on the correlation detection result; and perform device fault response detection on the target power grid device based on N-1 calculation based on the coupled grouping device set.

[0066] The above-mentioned power grid fault response detection method, device, computer equipment, computer-readable storage medium and computer program product first obtain the first device information of multiple associated power grid devices corresponding to the target power grid device from the preset knowledge graph; according to each first device information and the second device information corresponding to the target power grid device, detect the device correlation between the target power grid device and each associated power grid device to obtain the correlation detection result, so as to use the correlation detection result to detect the coupling grouping device set corresponding to the target power grid device from each associated power grid device, so as to achieve the search for the coupling grouping device set related to the power grid fault response detection of the target power grid device from the massive power grid equipment, so as to use the effective device information of the coupling grouping device set to perform equipment fault response detection based on N-1 calculation on the target power grid equipment, thereby achieving the purpose of obtaining effective data from massive power grid equipment data for equipment fault response detection, and thus the accuracy of equipment fault response detection can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0068] Figure 1 A schematic diagram of a flow chart of a power grid fault response detection method in one embodiment of the present application;

[0069] Figure 2 A schematic diagram of a process of performing device fault response detection based on N-1 calculation on a target power grid device in one embodiment of the present application;

[0070] Figure 3 This is a structural block diagram of a power grid fault response detection device in one embodiment of the present application;

[0071] Figure 4 This is a diagram of the internal structure of a computer device in one embodiment of the present application. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0073] In an exemplary embodiment, Figure 1 As shown, a method for detecting a power grid fault response is provided, comprising the following steps 202 to 208. Among them:

[0074] Step 202: Obtain first device information of multiple associated power grid devices corresponding to the target power grid device from a preset knowledge graph.

[0075] Among them, in this embodiment, a preset knowledge graph is set for the target power grid, and the preset knowledge graph includes multiple entities, each entity corresponds to a power grid device in the target power grid; the entity information contained in the entity can be the power grid equipment parameter information of the power grid device.

[0076] It should be noted that as the grid equipment parameter information of the grid equipment is continuously collected in real time, the entity information in the preset knowledge graph will also be dynamically updated in real time.

[0077] As an example, the power grid equipment parameter information may be transformer information, terminal equipment information, switch information, and power grid statistical information, among which the transformer information may be the transformer model, rated power, connection method, and transformer type, among which the terminal equipment information may be the terminal equipment type and the terminal equipment installation location, among which the switch information may be the switch equipment model, installation location, and switch status, among which the power grid statistical information may be the total load and load peak of the power grid substation, among which

[0078] As an example, step 202 includes: locating the target entity corresponding to the target power grid equipment from the preset knowledge graph according to the equipment number of the target power grid equipment; detecting multiple associated entities that have a connection relationship with the target entity in the preset knowledge graph, and taking the power grid equipment corresponding to the associated entity as the associated power grid equipment; extracting the power grid equipment parameter information corresponding to each associated power grid equipment from the preset graph as the first equipment information.

[0079] Step 204 , detecting the device correlation between the target power grid device and each associated power grid device according to each first device information and the second device information corresponding to the target power grid device, and obtaining a correlation detection result.

[0080] As an example, step 204 includes: extracting grid equipment parameter information of the target grid equipment as the second equipment information from a preset knowledge graph; detecting the equipment correlation between the target grid equipment and each associated grid equipment based on the information correlation between each first equipment information and the second equipment information, and obtaining a correlation detection result.

[0081] As an example, detecting the device correlation between the target power grid device and each associated power grid device according to each first device information and the second device information corresponding to the target power grid device includes:

[0082] Perform device feature extraction on the first device information to obtain the first device feature corresponding to the associated power grid device; perform device feature extraction on the second device information of the target power grid device to obtain the second device feature corresponding to the target power grid device; and detect the device correlation between the target power grid device and the associated power grid device based on the feature similarity between the first device feature and the second device feature.

[0083] Specifically, the first device information is one-hot encoded to obtain a first one-hot encoded feature, and the first one-hot encoded feature is reduced in dimension to obtain a first device feature corresponding to the associated power grid device; the second device information of the target power grid device is one-hot encoded to obtain a second one-hot encoded feature of the target power grid device, and the second one-hot encoded feature is reduced in dimension to obtain a second device feature of the target power grid device; the feature distance between the first device feature and the second device feature is calculated; the feature distance is mapped to a device correlation value between the target power grid device and the associated power grid device, wherein the feature distance is used to characterize the feature similarity between the first device feature and the second device feature, the larger the feature distance, the lower the feature similarity, the smaller the device correlation value, the lower the device correlation, the smaller the feature distance, the higher the feature similarity, the larger the device correlation value, and the higher the device correlation.

[0084] Step 206: According to the correlation detection result, the coupling grouping device set corresponding to the target power grid device is detected from each associated power grid device.

[0085] Among them, the correlation detection result includes a device correlation value, which is used to characterize the correlation between the target power grid device and the associated power grid device. The larger the device correlation value, the higher the correlation between the target power grid device and the associated power grid device. The smaller the device correlation value, the lower the correlation between the target power grid device and the associated power grid device.

[0086] As an example, the correlation detection result includes a device correlation value; according to the correlation detection result, a coupling grouping device set corresponding to the target power grid device is detected from each associated power grid device, including:

[0087] If the device correlation value is greater than the preset correlation threshold, the associated power grid device corresponding to the device correlation value is marked as the first type of associated power grid device; if the device correlation value is not greater than the preset correlation threshold, the associated power grid device corresponding to the device correlation value is marked as the second type of associated power grid device; all the first type of associated power grid devices are collectively set as the coupling grouping device set corresponding to the target power grid device.

[0088] Specifically, if the device correlation value is greater than the preset correlation threshold, it means that after the target power grid device fails, the probability that the associated power grid device corresponding to the device correlation value is affected by the association is high, and therefore the associated power grid device corresponding to the device correlation value is marked as the first type of associated power grid device; if the device correlation value is not greater than the preset correlation threshold, it means that after the target power grid device fails, the probability that the associated power grid device corresponding to the device correlation value is affected by the association is low, and therefore the associated power grid device corresponding to the device correlation value is marked as the second type of associated power grid device; all the first type of associated power grid devices are collectively set as the coupling grouping device set corresponding to the target power grid device.

[0089] Step 208: Perform device fault response detection based on N-1 calculation on the target power grid device according to the coupled marshaling device set.

[0090] In this embodiment, N-1 calculation is performed on the target power grid device to achieve detection of fault response in the power grid after the target power grid device sends a fault signal; the above-mentioned coupled grouping device set includes multiple coupled grouping power grid devices.

[0091] It should be noted that the purpose of N-1 calculation is that in a power grid under normal operating mode, when any component (such as lines, generators, transformers, etc.) is fault-free or disconnected due to a fault, the power grid should be able to maintain stable operation and normal power supply, other components are not overloaded, and the voltage and frequency are within the allowable range, that is, the power grid responds normally and can operate normally.

[0092] As an example, step 208 includes: obtaining grid equipment parameter information corresponding to each coupled grouping grid equipment from a preset knowledge graph as coupling equipment information; and performing equipment fault response detection based on N-1 calculation on the target grid equipment according to each coupling equipment information.

[0093] In the above-mentioned power grid fault response detection method, first, the first device information of multiple associated power grid devices corresponding to the target power grid device is obtained from the preset knowledge graph; according to each first device information and the second device information corresponding to the target power grid device, the device correlation between the target power grid device and each associated power grid device is detected to obtain the correlation detection result, and then the correlation detection result is used to detect the coupling grouping device set corresponding to the target power grid device from each associated power grid device, so that it is possible to find the coupling grouping device set related to the power grid fault response detection of the target power grid device from the massive power grid equipment, and then use the effective device information of the coupling grouping device set to perform equipment fault response detection on the target power grid equipment based on N-1 calculation, thereby achieving the purpose of obtaining effective data from massive power grid equipment data for equipment fault response detection, and thus the accuracy of equipment fault response detection can be improved.

[0094] It should be noted that power grid equipment data is usually massive. On the one hand, it is usually difficult to filter out effective data from the massive data for power grid fault response detection, which leads to low accuracy of power grid fault response detection. On the other hand, it is usually difficult to provide a matching computing model for massive data for power grid fault response detection, which further leads to low accuracy of power grid fault response detection.

[0095] In an exemplary embodiment, Figure 2 As shown, the coupled marshaling device set includes a plurality of coupled marshaling power grid devices; according to the coupled marshaling device set, device fault response detection based on N-1 calculation is performed on the target power grid device, including:

[0096] Step 302, obtaining marshaling device information of each coupled marshaling power grid device from a preset knowledge graph;

[0097] As an example, the grid equipment parameter information corresponding to each coupled grouped grid equipment can be obtained from the preset knowledge graph as the coupling equipment information.

[0098] Step 304, extracting features from each marshaling device information to obtain multiple marshaling device features;

[0099] As an example, step 304 includes: for each marshaling device information, performing one-hot encoding on the marshaling device information to obtain one-hot encoding features; inputting the one-hot encoding features into the feature extraction model to perform feature dimension reduction, and outputting the marshaling device features. The marshaling device features can be embedded feature vectors, that is, vector.

[0100] Step 306, detecting the type of N-1 calculation model for the target power grid equipment to perform N-1 calculation according to the characteristics of each marshaling device;

[0101] As an example, step 306 includes: splicing the features of each marshalling device to obtain the marshalling device splicing features; mapping the marshalling device splicing features into corresponding feature classification identifiers according to a preset classifier; and using the calculation model type corresponding to the feature classification identifier as the target power grid device to perform N-1 calculations on the N-1 calculation model type.

[0102] As an example, according to the characteristics of each marshaling device, the type of N-1 calculation model for detecting the target power grid device to perform N-1 calculation includes:

[0103] Detect the equipment association relationship information between each coupled marshaling power grid equipment and the target power grid equipment from the preset knowledge graph; match the corresponding feature weight for each marshaling equipment feature according to the equipment association relationship information; perform weighted fusion on the features of each marshaling equipment according to the corresponding feature weight for each marshaling equipment feature match to obtain a fused equipment feature; detect the N-1 calculation model type for the target power grid equipment to perform N-1 calculation according to the fused equipment feature and the second equipment feature corresponding to the second equipment information.

[0104] Among them, the connection edges between entities in the preset knowledge graph can describe the association relationship information between different entities, that is, can describe the association relationship information between different power grid equipment.

[0105] Specifically, the device association relationship information between each coupled marshaling power grid device and the target power grid device is obtained from the preset knowledge graph; feature extraction is performed on each device association relationship information to obtain the device association relationship feature corresponding to each coupled marshaling power grid device, and the feature weight of the marshaling device feature matching corresponding to each coupled marshaling power grid device is obtained by normalizing each device association relationship feature; according to the feature weight of each marshaling device feature matching, each marshaling device feature is weighted respectively to obtain the weighted marshaling device feature; the weighted marshaling device features are feature fused to obtain the fused device feature, wherein the feature fusion method may be splicing or summing, etc.; feature extraction is performed on the second device information of the target power grid device to obtain the second device feature; the fused device feature and the second device feature are spliced ​​to obtain the target splicing feature; according to the preset classifier, the target splicing feature is mapped to the corresponding feature classification identifier; the calculation model type corresponding to the feature classification identifier is used as the target power grid device to perform N-1 calculation N-1 calculation model type. In this embodiment, the target power grid equipment is evaluated for N-1 calculation and N-1 calculation model type based on the association relationship information between the target power grid equipment and each coupled grouping power grid equipment in the preset knowledge graph. The evaluation basis is richer, which can improve the evaluation accuracy of the target power grid equipment for N-1 calculation and N-1 calculation model type.

[0106] It should be noted that there are usually multiple types of N-1 computing models, and different types of N-1 computing models are adapted to different N-1 computing scenarios. For example, the above-mentioned N-1 computing model can be an N-1 computing module with no complementary relationship or an N-1 computing model with a complementary relationship greater than 2, etc.

[0107] Step 308: Perform N-1 calculation-based device fault response detection on the target power grid device according to the target N-1 calculation model corresponding to the N-1 calculation model type.

[0108] As an example, step 308 includes: obtaining a target N-1 calculation model under the N-1 calculation model type; performing N-1 calculation on the target power grid device by inputting the second device information of the target power grid device and the grouping device information of each coupled power grid device into the target N-1 calculation model, and performing device fault response detection based on the N-1 calculation on the target power grid device.

[0109] In this embodiment, first, the marshaling equipment information of each coupled marshaling power grid equipment is obtained from the preset knowledge graph, and then the feature extraction is performed on each marshaling equipment information to obtain multiple marshaling equipment features, so that the N-1 calculation model type for the target power grid equipment to perform N-1 calculation can be detected according to the characteristics of each marshaling equipment, so that the corresponding target N-1 calculation model can be accurately matched for the target power grid equipment according to the N-1 calculation model type for the target power grid equipment to perform N-1 calculation, so that according to the target N-1 calculation model corresponding to the N-1 calculation model type, the second equipment information of the target power grid equipment and the marshaling equipment information of each coupled marshaling power grid equipment, the target power grid equipment is subjected to the device fault response detection based on the N-1 calculation, which, on the one hand, realizes the screening of valid data (second equipment information and marshaling equipment information) from massive data for power grid fault response detection, and on the other hand, realizes the provision of a matching target N-1 calculation model for valid data for power grid fault response detection, thereby improving the accuracy of power grid fault response detection.

[0110] As an example, the power grid fault response detection method further includes:

[0111] Obtain power grid data text, wherein the power grid data text includes equipment parameter texts of multiple power grid basic equipment; detect associations between the multiple power grid basic equipment based on the equipment parameter texts of the multiple power grid basic equipment to obtain association detection results; and construct a preset knowledge graph based on the association detection results and the equipment parameter texts of the multiple power grid basic equipment.

[0112] Among them, the power grid equipment data collected in this embodiment usually exists in the form of power grid data text, so a preset knowledge graph can be constructed by performing some text processing on the power grid data text.

[0113] Specifically, a power grid data text is obtained, wherein the power grid data text includes equipment parameter texts of multiple power grid devices; for each equipment parameter text, text processing is performed on the equipment parameter text to obtain a processed text, wherein the text processing method may be text segmentation, synonym replacement, and text classification, etc.; text feature extraction is performed on each processed text to obtain multiple text features; based on the multiple first text features, the association relationship between each power grid equipment is detected to obtain an association relationship detection result; based on the multiple processed texts, multiple entities of a preset knowledge graph are respectively constructed, wherein each entity corresponds to a power grid device, and the entity information contained in each entity is the processed text; based on the association relationship detection result, a connection edge of each entity is constructed to obtain a preset knowledge graph, wherein the connection edge between entities is used to characterize the association relationship between entities.

[0114] In this embodiment, the construction of a preset knowledge graph corresponding to each power grid device can be realized, laying a foundation for power grid fault response detection of the target power grid device.

[0115] In a complete embodiment, first, according to the device number of the target power grid device, the target entity corresponding to the target power grid device is located from the preset knowledge graph; multiple associated entities that have a connection relationship with the target entity are detected in the preset knowledge graph, and the power grid devices corresponding to the associated entities are taken as associated power grid devices; and the power grid device parameter information corresponding to each associated power grid device is extracted from the preset graph as the first device information.

[0116] Furthermore, the first device information is one-hot encoded to obtain a first one-hot encoded feature, and the first one-hot encoded feature is reduced in dimension to obtain a first device feature corresponding to the associated power grid device; the second device information of the target power grid device is one-hot encoded to obtain a second one-hot encoded feature of the target power grid device, and the second one-hot encoded feature is reduced in dimension to obtain a second device feature of the target power grid device; the feature distance between the first device feature and the second device feature is calculated; the feature distance is mapped to a device correlation value between the target power grid device and the associated power grid device, wherein the feature distance is used to characterize the feature similarity between the first device feature and the second device feature, the larger the feature distance, the lower the feature similarity, the smaller the device correlation value, the lower the device correlation, the smaller the feature distance, the higher the feature similarity, the larger the device correlation value, and the higher the device correlation.

[0117] Furthermore, if the device correlation value is greater than the preset correlation threshold, it means that after the target power grid device fails, the probability that the associated power grid device corresponding to the device correlation value is affected by the association is high, and therefore the associated power grid device corresponding to the device correlation value is marked as the first type of associated power grid device; if the device correlation value is not greater than the preset correlation threshold, it means that after the target power grid device fails, the probability that the associated power grid device corresponding to the device correlation value is affected by the association is low, and therefore the associated power grid device corresponding to the device correlation value is marked as the second type of associated power grid device; all the first type of associated power grid devices are collectively set as the coupling grouping device set corresponding to the target power grid device.

[0118] Further, the marshaling equipment information of each coupled marshaling power grid equipment is obtained from the preset knowledge graph; for each marshaling equipment information, the marshaling equipment information is one-hot encoded to obtain the one-hot encoded feature; the one-hot encoded feature is input into the feature extraction model to perform feature dimensionality reduction, and the marshaling equipment feature is output. Among them, the marshaling equipment feature can be an embedded feature vector, that is, vector; obtain the device association relationship information between each coupled marshaling power grid device and the target power grid device from the preset knowledge graph; perform feature extraction on each device association relationship information to obtain the device association relationship feature corresponding to each coupled marshaling power grid device, and obtain the feature weight of the marshaling device feature matching corresponding to each coupled marshaling power grid device by normalizing each device association relationship feature; weight each marshaling device feature according to the feature weight of each marshaling device feature matching to obtain the weighted marshaling device feature; perform feature fusion on each weighted marshaling device feature to obtain a fused device feature, wherein the feature fusion method can be splicing or summing, etc.; perform feature extraction on the second device information of the target power grid device to obtain the second device feature; splice the fused device feature and the second device feature to obtain the target splicing feature; map the target splicing feature to the corresponding feature classification identifier according to the preset classifier; perform N-1 calculation on the N-1 calculation model type corresponding to the feature classification identifier as the target power grid device.

[0119] Furthermore, a target N-1 calculation model under the N-1 calculation model type is obtained; by inputting the second device information of the target power grid device and the grouping device information of each coupled grouping power grid device into the target N-1 calculation model for N-1 calculation, the target power grid device is subjected to equipment fault response detection based on the N-1 calculation.

[0120] In this embodiment, on the one hand, it is possible to filter out valid data (second device information and marshalling device information) from massive data for power grid fault response detection, and on the other hand, it is possible to provide a matching target N-1 calculation model for valid data for power grid fault response detection, thereby improving the accuracy of power grid fault response detection.

[0121] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0122] Based on the same inventive concept, the embodiment of the present application also provides a power grid fault response detection device for implementing the power grid fault response detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more power grid fault response detection device embodiments provided below can refer to the limitations of the power grid fault response detection method above, and will not be repeated here.

[0123] In an exemplary embodiment, Figure 3 As shown, a power grid fault response detection device is provided, including: an acquisition module 402, a first detection module 404, a second detection module 406 and an equipment fault response detection module 408, wherein:

[0124] The acquisition module 402 is used to obtain the first device information of multiple associated power grid devices corresponding to the target power grid device from the preset knowledge graph.

[0125] The first detection module 404 is used to detect the device correlation between the target power grid device and each of the associated power grid devices according to each of the first device information and the second device information corresponding to the target power grid device, and obtain a correlation detection result.

[0126] The second detection module 406 is used to detect the coupling grouping device set corresponding to the target power grid device from each of the associated power grid devices according to the correlation detection result.

[0127] The device fault response detection module 408 is used to perform device fault response detection based on N-1 calculation on the target power grid device according to the coupled marshaling device set.

[0128] In one embodiment, the coupled grouping device set includes a plurality of coupled grouping power grid devices; the device fault response detection module is further used for:

[0129] Acquire the marshaling device information of each of the coupled marshaling power grid devices from a preset knowledge graph;

[0130] Extracting features from each of the marshaling equipment information to obtain a plurality of marshaling equipment features;

[0131] According to the characteristics of each of the marshaling devices, detecting the type of the N-1 calculation model for the target power grid device to perform the N-1 calculation;

[0132] According to the target N-1 calculation model corresponding to the N-1 calculation model type, the target power grid equipment is subjected to N-1 calculation-based equipment fault response detection.

[0133] In one embodiment, the device fault response detection module is further used to:

[0134] Detecting device association relationship information between each of the coupled grouping power grid devices and the target power grid device from the preset knowledge graph;

[0135] According to the equipment association relationship information, a corresponding feature weight is matched for each of the marshaling equipment features;

[0136] According to the feature weight corresponding to each of the marshalling equipment features, weighted fusion is performed on the features of each marshalling equipment to obtain a fused equipment feature;

[0137] According to the fusion device feature and the second device feature corresponding to the second device information, the N-1 calculation model type of the target power grid device for performing the N-1 calculation is detected.

[0138] In one embodiment, the first detection module is further used for:

[0139] Extracting device features from the first device information to obtain first device features corresponding to the associated power grid device;

[0140] Extracting device features from the second device information of the target power grid device to obtain a second device feature corresponding to the target power grid device;

[0141] According to the feature similarity between the first device feature and the second device feature, the device correlation between the target power grid device and the associated power grid device is detected.

[0142] In one embodiment, the correlation detection result includes a device correlation value; and the second detection module is further configured to:

[0143] If the device correlation value is greater than a preset correlation threshold, marking the associated power grid device corresponding to the device correlation value as an associated power grid device of the first type;

[0144] If the device correlation value is not greater than a preset correlation threshold, marking the associated power grid device corresponding to the device correlation value as an associated power grid device of the second type;

[0145] All the first-type associated power grid devices are collectively set as a coupling grouping device set corresponding to the target power grid device.

[0146] In one embodiment, the device further comprises:

[0147] A knowledge graph construction module, used to obtain power grid data text, wherein the power grid data text includes device parameter texts of multiple basic power grid devices;

[0148] According to the device parameter texts of the plurality of basic power grid devices, detecting association relationships between the plurality of basic power grid devices in pairs, and obtaining an association relationship detection result;

[0149] A preset knowledge graph is constructed based on the association relationship detection results and the equipment parameter texts of the multiple basic power grid equipment.

[0150] Each module in the above-mentioned power grid fault response detection device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0151] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a power grid fault response detection method is implemented.

[0152] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0153] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0154] Acquire first device information of multiple associated power grid devices corresponding to the target power grid device from a preset knowledge graph;

[0155] According to each of the first device information and the second device information corresponding to the target power grid device, detecting the device correlation between the target power grid device and each of the associated power grid devices, and obtaining a correlation detection result;

[0156] According to the correlation detection result, detecting a coupling grouping device set corresponding to the target power grid device from each of the associated power grid devices;

[0157] According to the coupled marshaling device set, device fault response detection based on N-1 calculation is performed on the target power grid device.

[0158] In one embodiment, the coupling grouping device set includes a plurality of coupling grouping power grid devices; when the processor executes the computer program, the following steps are also implemented:

[0159] Acquire the marshaling device information of each of the coupled marshaling power grid devices from a preset knowledge graph;

[0160] Extracting features from each of the marshaling equipment information to obtain a plurality of marshaling equipment features;

[0161] According to the characteristics of each of the marshaling devices, detecting the type of the N-1 calculation model for the target power grid device to perform the N-1 calculation;

[0162] According to the target N-1 calculation model corresponding to the N-1 calculation model type, the target power grid equipment is subjected to N-1 calculation-based equipment fault response detection.

[0163] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0164] Detecting device association relationship information between each of the coupled grouping power grid devices and the target power grid device from the preset knowledge graph;

[0165] According to the equipment association relationship information, a corresponding feature weight is matched for each of the marshaling equipment features;

[0166] According to the feature weight corresponding to each of the marshalling equipment features, weighted fusion is performed on the features of each marshalling equipment to obtain a fused equipment feature;

[0167] According to the fusion device feature and the second device feature corresponding to the second device information, the N-1 calculation model type of the target power grid device for performing the N-1 calculation is detected.

[0168] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0169] Extracting device features from the first device information to obtain first device features corresponding to the associated power grid device;

[0170] Extracting device features from the second device information of the target power grid device to obtain a second device feature corresponding to the target power grid device;

[0171] According to the feature similarity between the first device feature and the second device feature, the device correlation between the target power grid device and the associated power grid device is detected.

[0172] In one embodiment, the correlation detection result includes a device correlation value; when the processor executes the computer program, the following steps are also implemented:

[0173] If the device correlation value is greater than a preset correlation threshold, marking the associated power grid device corresponding to the device correlation value as an associated power grid device of the first type;

[0174] If the device correlation value is not greater than a preset correlation threshold, marking the associated power grid device corresponding to the device correlation value as an associated power grid device of the second type;

[0175] All the first-type associated power grid devices are collectively set as a coupling grouping device set corresponding to the target power grid device.

[0176] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0177] Acquire power grid data text, wherein the power grid data text includes device parameter texts of a plurality of basic power grid devices;

[0178] According to the device parameter texts of the plurality of basic power grid devices, detecting association relationships between the plurality of basic power grid devices in pairs, and obtaining an association relationship detection result;

[0179] A preset knowledge graph is constructed based on the association relationship detection results and the equipment parameter texts of the multiple basic power grid equipment.

[0180] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0181] Acquire first device information of multiple associated power grid devices corresponding to the target power grid device from a preset knowledge graph;

[0182] According to each of the first device information and the second device information corresponding to the target power grid device, detecting the device correlation between the target power grid device and each of the associated power grid devices, and obtaining a correlation detection result;

[0183] According to the correlation detection result, detecting a coupling grouping device set corresponding to the target power grid device from each of the associated power grid devices;

[0184] According to the coupled marshaling device set, device fault response detection based on N-1 calculation is performed on the target power grid device.

[0185] In one embodiment, the coupled grouping device set includes a plurality of coupled grouping power grid devices; when the computer program is executed by the processor, the following steps are also implemented:

[0186] Acquire the marshaling device information of each of the coupled marshaling power grid devices from a preset knowledge graph;

[0187] Extracting features from each of the marshaling equipment information to obtain a plurality of marshaling equipment features;

[0188] According to the characteristics of each of the marshaling devices, detecting the type of the N-1 calculation model for the target power grid device to perform the N-1 calculation;

[0189] According to the target N-1 calculation model corresponding to the N-1 calculation model type, the target power grid equipment is subjected to N-1 calculation-based equipment fault response detection.

[0190] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0191] Detecting device association relationship information between each of the coupled grouping power grid devices and the target power grid device from the preset knowledge graph;

[0192] According to the equipment association relationship information, a corresponding feature weight is matched for each of the marshaling equipment features;

[0193] According to the feature weight corresponding to each of the marshalling equipment features, weighted fusion is performed on the features of each marshalling equipment to obtain a fused equipment feature;

[0194] According to the fusion device feature and the second device feature corresponding to the second device information, the N-1 calculation model type of the target power grid device for performing the N-1 calculation is detected.

[0195] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0196] Extracting device features from the first device information to obtain first device features corresponding to the associated power grid device;

[0197] Extracting device features from the second device information of the target power grid device to obtain a second device feature corresponding to the target power grid device;

[0198] According to the feature similarity between the first device feature and the second device feature, the device correlation between the target power grid device and the associated power grid device is detected.

[0199] In one embodiment, the correlation detection result includes a device correlation value; when the computer program is executed by a processor, the following steps are further implemented:

[0200] If the device correlation value is greater than a preset correlation threshold, marking the associated power grid device corresponding to the device correlation value as an associated power grid device of the first type;

[0201] If the device correlation value is not greater than a preset correlation threshold, marking the associated power grid device corresponding to the device correlation value as an associated power grid device of the second type;

[0202] All the first-type associated power grid devices are collectively set as a coupling grouping device set corresponding to the target power grid device.

[0203] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0204] Acquire power grid data text, wherein the power grid data text includes device parameter texts of a plurality of basic power grid devices;

[0205] According to the device parameter texts of the plurality of basic power grid devices, detecting association relationships between the plurality of basic power grid devices in pairs, and obtaining an association relationship detection result;

[0206] A preset knowledge graph is constructed based on the association relationship detection results and the equipment parameter texts of the multiple basic power grid equipment.

[0207] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0208] Acquire first device information of multiple associated power grid devices corresponding to the target power grid device from a preset knowledge graph;

[0209] According to each of the first device information and the second device information corresponding to the target power grid device, detecting the device correlation between the target power grid device and each of the associated power grid devices, and obtaining a correlation detection result;

[0210] According to the correlation detection result, detecting a coupling grouping device set corresponding to the target power grid device from each of the associated power grid devices;

[0211] According to the coupled marshaling device set, device fault response detection based on N-1 calculation is performed on the target power grid device.

[0212] In one embodiment, the coupled grouping device set includes a plurality of coupled grouping power grid devices; when the computer program is executed by the processor, the following steps are also implemented:

[0213] Acquire the marshaling device information of each of the coupled marshaling power grid devices from a preset knowledge graph;

[0214] Extracting features from each of the marshaling equipment information to obtain a plurality of marshaling equipment features;

[0215] According to the characteristics of each of the marshaling devices, detecting the type of the N-1 calculation model for the target power grid device to perform the N-1 calculation;

[0216] According to the target N-1 calculation model corresponding to the N-1 calculation model type, the target power grid equipment is subjected to N-1 calculation-based equipment fault response detection.

[0217] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0218] Detecting device association relationship information between each of the coupled grouping power grid devices and the target power grid device from the preset knowledge graph;

[0219] According to the equipment association relationship information, a corresponding feature weight is matched for each of the marshaling equipment features;

[0220] According to the feature weight corresponding to each of the marshalling equipment features, weighted fusion is performed on the features of each marshalling equipment to obtain a fused equipment feature;

[0221] According to the fusion device feature and the second device feature corresponding to the second device information, the N-1 calculation model type of the target power grid device for performing the N-1 calculation is detected.

[0222] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0223] Extracting device features from the first device information to obtain first device features corresponding to the associated power grid device;

[0224] Extracting device features from the second device information of the target power grid device to obtain a second device feature corresponding to the target power grid device;

[0225] According to the feature similarity between the first device feature and the second device feature, the device correlation between the target power grid device and the associated power grid device is detected.

[0226] In one embodiment, the correlation detection result includes a device correlation value; when the computer program is executed by a processor, the following steps are further implemented:

[0227] If the device correlation value is greater than a preset correlation threshold, marking the associated power grid device corresponding to the device correlation value as an associated power grid device of the first type;

[0228] If the device correlation value is not greater than a preset correlation threshold, marking the associated power grid device corresponding to the device correlation value as an associated power grid device of the second type;

[0229] All the first-type associated power grid devices are collectively set as a coupling grouping device set corresponding to the target power grid device.

[0230] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0231] Acquire power grid data text, wherein the power grid data text includes device parameter texts of a plurality of basic power grid devices;

[0232] According to the device parameter texts of the plurality of basic power grid devices, detecting association relationships between the plurality of basic power grid devices in pairs, and obtaining an association relationship detection result;

[0233] A preset knowledge graph is constructed based on the association relationship detection results and the equipment parameter texts of the multiple basic power grid equipment.

[0234] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0235] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0236] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A power grid fault response detection method, characterized in that: The method comprises: Acquire first device information of multiple associated power grid devices corresponding to the target power grid device from a preset knowledge graph; According to each of the first device information and the second device information corresponding to the target power grid device, detecting the device correlation between the target power grid device and each of the associated power grid devices, and obtaining a correlation detection result; According to the correlation detection result, detecting a coupling grouping device set corresponding to the target power grid device from each of the associated power grid devices; According to the coupled marshaling device set, device fault response detection based on N-1 calculation is performed on the target power grid device.

2. The method according to claim 1, characterized in that The coupled grouping device set includes a plurality of coupled grouping power grid devices; and performing device fault response detection based on N-1 calculation on the target power grid device according to the coupled grouping device set includes: Acquire the marshaling device information of each of the coupled marshaling power grid devices from a preset knowledge graph; Extracting features from each of the marshaling equipment information to obtain a plurality of marshaling equipment features; According to the characteristics of each of the marshaling devices, detecting the type of the N-1 calculation model for the target power grid device to perform the N-1 calculation; According to the target N-1 calculation model corresponding to the N-1 calculation model type, the target power grid equipment is subjected to N-1 calculation-based equipment fault response detection.

3. The method according to claim 2, characterized in that The detecting, according to the characteristics of each of the marshaling devices, the type of the N-1 calculation model for the target power grid device to perform the N-1 calculation comprises: Detecting device association relationship information between each of the coupled grouping power grid devices and the target power grid device from the preset knowledge graph; According to the equipment association relationship information, a corresponding feature weight is matched for each of the marshaling equipment features; According to the feature weight corresponding to each of the marshalling equipment features, weighted fusion is performed on the features of each marshalling equipment to obtain a fused equipment feature; According to the fusion device feature and the second device feature corresponding to the second device information, the N-1 calculation model type of the target power grid device for performing the N-1 calculation is detected.

4. The method according to claim 1, characterized in that The detecting, according to each of the first device information and the second device information corresponding to the target power grid device, the device correlation between the target power grid device and each of the associated power grid devices includes: Extracting device features from the first device information to obtain first device features corresponding to the associated power grid device; Extracting device features from the second device information of the target power grid device to obtain a second device feature corresponding to the target power grid device; According to the feature similarity between the first device feature and the second device feature, the device correlation between the target power grid device and the associated power grid device is detected.

5. The method according to claim 1, characterized in that The correlation detection result includes a device correlation value; and detecting a coupling grouping device set corresponding to the target power grid device from each of the associated power grid devices according to the correlation detection result includes: If the device correlation value is greater than a preset correlation threshold, marking the associated power grid device corresponding to the device correlation value as an associated power grid device of the first type; If the device correlation value is not greater than a preset correlation threshold, marking the associated power grid device corresponding to the device correlation value as an associated power grid device of the second type; All the first-type associated power grid devices are collectively set as a coupling grouping device set corresponding to the target power grid device.

6. The method according to claim 1, characterized in that The method further comprises: Acquire power grid data text, wherein the power grid data text includes device parameter texts of a plurality of basic power grid devices; According to the device parameter texts of the plurality of basic power grid devices, detecting association relationships between the plurality of basic power grid devices in pairs, and obtaining an association relationship detection result; A preset knowledge graph is constructed based on the association relationship detection results and the equipment parameter texts of the multiple basic power grid equipment.

7. A power grid fault response detection device, characterized in that: The device comprises: An acquisition module, used to acquire first device information of multiple associated power grid devices corresponding to the target power grid device from a preset knowledge graph; A first detection module, configured to detect the device correlation between the target power grid device and each of the associated power grid devices according to each of the first device information and the second device information corresponding to the target power grid device, and obtain a correlation detection result; A second detection module, configured to detect a coupling grouping device set corresponding to the target power grid device from each of the associated power grid devices according to the correlation detection result; The device fault response detection module is used to perform device fault response detection based on N-1 calculation on the target power grid device according to the coupled marshaling device set.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images