Power transmission line defect evaluation method and system based on unmanned aerial vehicle image analysis

Abstract

The invention provides a power transmission line defect evaluation method and system based on unmanned aerial vehicle image analysis. A to-be-analyzed unmanned aerial vehicle image acquisition data set is analyzed to determine a power transmission line abnormal data set comprising a first power transmission line defect text from the unmanned aerial vehicle image acquisition data set, and abnormal event description of the first power transmission line defect text is acquired from the power transmission line abnormal data set; then event position determination is carried out on an unmanned aerial vehicle image acquisition data set, a first power transmission line defect text is selected to be ranked in a subsequent power transmission line abnormal data set, the power transmission line defect text can be completely captured through the ranking, and defect evaluation is carried out; therefore, the accuracy and reliability of defect evaluation of the power transmission line defect text are improved.

Description

Technical Field

[0001] The present application relates to the technical field of defect assessment, and in particular to a method and system for evaluating power transmission line defects based on drone image analysis. Background Art

[0002] With the continuous development and progress of UAV technology, the application fields of UAV have become more extensive. When UAV technology is combined with transmission line defect assessment technology, there may be problems such as unclear and inaccurate image capture leading to inaccurate defect assessment. How to improve the accuracy of the assessment is a technical problem that is difficult to solve at present. Summary of the invention

[0003] In view of this, the present application provides a method and system for evaluating power transmission line defects based on drone image analysis.

[0004] In a first aspect, a method for evaluating power transmission line defects based on drone image analysis is provided, which is applied to an illegal event identification system, and the method comprises at least the following steps: Analyze the drone image acquisition data set to be analyzed, and determine a first transmission line abnormality data set including a first transmission line defect text in the drone image acquisition data set, wherein the first transmission line defect text includes one or more transmission line defect texts; Based on the first transmission line abnormality data set, important description content of the first transmission line defect text is obtained, and the important description content at least includes an abnormal event description; based on the abnormal event description of the first transmission line defect text, the event location of the drone image acquisition data set is determined, and it is determined whether the first transmission line defect text is covered in the second transmission line abnormality data set of the drone image acquisition data set; On the premise that the first transmission line defect text is covered in the second transmission line abnormal data set, the first ranking of the first transmission line defect text in the second transmission line abnormal data set is determined; on the premise that the first transmission line defect text is not covered in the second transmission line abnormal data set, important attribute analysis is re-performed on the drone image acquisition data set to capture the second transmission line defect text and perform defect assessment.

[0005] In the present application, the drone image acquisition data set to be analyzed is analyzed to determine the first transmission line abnormality data set that includes the first transmission line defect text in the drone image acquisition data set, including: performing important attribute analysis on the drone image acquisition data set to be analyzed, and determining the first transmission line abnormality data set that includes the first transmission line defect text in the drone image acquisition data set.

[0006] In the present application, analyzing the drone image acquisition data set to be analyzed, and determining a first transmission line abnormality data set including a first transmission line defect text in the drone image acquisition data set, includes: determining an event location of the drone image acquisition data set to be analyzed, and determining a candidate transmission line defect text in the drone image acquisition data set; Determine the transmission line defect text that meets the specified requirements among the candidate transmission line defect texts as the first transmission line defect text; The power transmission line abnormal data set carrying the first power transmission line defect text is determined as the first power transmission line abnormal data set.

[0007] In the present application, the re-analysis of important attributes of the drone image acquisition data set, capturing the second transmission line defect text and performing defect assessment includes: On the premise that the second transmission line abnormality data set does not include the first transmission line defect text, re-analyze the important attributes of the drone image acquisition data set to determine a third transmission line abnormality data set of the drone image acquisition data set, wherein the third transmission line abnormality data set includes the captured second transmission line defect text; Based on the third power transmission line abnormality data set, obtaining important description content of the second power transmission line defect text, wherein the important description content at least includes an abnormal event description; Based on the abnormal event description of the second transmission line defect text, determine the event location of the drone image acquisition data set, and determine whether the fourth transmission line abnormal data set of the drone image acquisition data set covers the second transmission line defect text; On the premise that the second transmission line defect text is included in the fourth transmission line abnormality data set, a second ranking of the second transmission line defect text in the fourth transmission line abnormality data set is determined.

[0008] In the present application, the method further comprises: Performing important attribute analysis on the drone image acquisition data set to determine whether the first transmission line defect text is included in the fourth power transmission line abnormality data set of the drone image acquisition data set; On the premise that the first transmission line defect text is included in the fourth transmission line abnormality data set, a third ranking of the first transmission line defect text in the fourth transmission line abnormality data set is determined.

[0009] In the present application, the method further comprises: On the premise that the second power transmission line abnormality data set includes the first power transmission line defect text, obtaining an operation description of the first power transmission line defect text in the second power transmission line abnormality data set; Based on the description of the operation status of the first power transmission line defect text, a detection method for the first power transmission line defect text is triggered.

[0010] In the present application, the method further comprises: On the premise that the second transmission line defect text is included in the fourth transmission line abnormal data set, obtaining an operation description of the second transmission line defect text in the fourth transmission line abnormal data set; Based on the description of the operation condition of the second power transmission line defect text, a detection method for the second power transmission line defect text is triggered.

[0011] In the present application, the method further comprises: On the premise that the first transmission line defect text is included in the fourth transmission line abnormal data set, obtaining an operation description of the first transmission line defect text in the fourth transmission line abnormal data set; Based on the description of the operation status of the first power transmission line defect text, a detection method for the first power transmission line defect text is triggered.

[0012] In the present application, an important attribute analysis is performed on the drone image acquisition data set to be analyzed, and a first transmission line abnormality data set including a first transmission line defect text in the drone image acquisition data set is determined, including: Based on the first transmission line defect text set in advance, important attribute analysis is performed one by one on several transmission line abnormality data sets of the drone image acquisition data set, and a first transmission line abnormality data set including the first transmission line defect text is determined from the several transmission line abnormality data sets.

[0013] In the present application, an important attribute analysis is performed on the drone image acquisition data set to be analyzed, and a first transmission line abnormality data set including a first transmission line defect text in the drone image acquisition data set is determined, including: Performing important attribute analysis on the power transmission line abnormality data set of the UAV image acquisition data set to determine candidate power transmission line defect texts in the power transmission line abnormality data set; Determine the transmission line defect text that meets the specified requirements among the candidate transmission line defect texts as the first transmission line defect text; The power transmission line abnormal data set carrying the first power transmission line defect text is determined as the first power transmission line abnormal data set.

[0014] In the present application, based on the abnormal event description of the first transmission line defect text, the event location of the drone image acquisition data set is determined, and it is judged whether the second transmission line abnormal data set of the drone image acquisition data set covers the first transmission line defect text, including: Determine the event location of a second power transmission line abnormality data set of the UAV image acquisition data set, and determine the abnormal event description of the candidate power transmission line defect text in the second power transmission line abnormality data set; When the abnormal event description matched with the abnormal event description of the first power transmission line defect text is included, it is determined that the first power transmission line defect text is included in the second power transmission line abnormality data set.

[0015] In the present application, the method is implemented by an artificial intelligence analysis network, and the artificial intelligence analysis network includes at least an important attribute analysis subnetwork, wherein an important attribute analysis is performed on the drone image acquisition data set to be analyzed, and a first transmission line abnormality data set including a first transmission line defect text in the drone image acquisition data set is determined, including: Loading each power transmission line abnormality data set of the UAV image acquisition data set into the important attribute analysis subnetwork for processing, and deriving important attribute descriptions of candidate power transmission line defect texts in each power transmission line abnormality data set; According to the important attribute description of the candidate power transmission line defect text, a first power transmission line abnormality data set including the first power transmission line defect text is determined.

[0016] In the present application, the artificial intelligence analysis network also includes an event location determination subnetwork, wherein the event location is determined for the second transmission line abnormality data set of the drone image acquisition data set, and the abnormal event description of the candidate transmission line defect text in the second transmission line abnormality data set is determined, including: The second transmission line abnormality data set is loaded into the event location determination subnetwork for processing, and abnormal event descriptions of candidate transmission line defect texts in the second transmission line abnormality data set are derived.

[0017] In the present application, the artificial intelligence analysis network also includes an operation description derivative subnetwork, wherein, on the premise that the first transmission line defect text is included in the second transmission line abnormal data set, obtaining the operation description of the first transmission line defect text in the second transmission line abnormal data set includes: The second transmission line abnormal data set is loaded into the operation condition description derivation subnetwork for processing, and the operation condition description of the first transmission line defect text in the second transmission line abnormal data set is derived.

[0018] In the present application, the drone image acquisition data set is a drone image acquisition data set within a specified scene acquired by a drone.

[0019] In a second aspect, a transmission line defect assessment system based on drone image analysis is provided, comprising a processor and a memory that communicate with each other, wherein the processor is used to read a computer program from the memory and execute it to implement the above method.

[0020] The embodiment of the present application provides a transmission line defect evaluation method and system based on drone image analysis. In the embodiment of the present application, the drone image acquisition data set to be analyzed can be analyzed to determine the transmission line abnormal data set including the first transmission line defect text from the drone image acquisition data set and obtain the abnormal event description of the first transmission line defect text from the transmission line abnormal data set, and then the event position is determined by the drone image acquisition data set, and the ranking of the first transmission line defect text in the subsequent transmission line abnormal data set is selected. The transmission line defect text can be completely captured through the ranking and defect evaluation can be performed, thereby improving the accuracy and reliability of the defect evaluation of the transmission line defect text. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A flow chart of a method for evaluating power transmission line defects based on drone image analysis provided in an embodiment of the present application.

[0023] Figure 2 A block diagram of a power transmission line defect assessment device based on drone image analysis provided in an embodiment of the present application.

[0024] Figure 3 An architectural diagram of a power transmission line defect assessment system based on drone image analysis provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to better understand the above technical scheme, the technical scheme of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0026] See also Figure 1 , shows a method for evaluating transmission line defects based on drone image analysis, which may include the technical solutions described in the following steps P11-step 13.

[0027] Step 11, analyzing the drone image acquisition data set to be analyzed, and determining a first transmission line abnormality data set including a first transmission line defect text in the drone image acquisition data set, wherein the first transmission line defect text includes one or more transmission line defect texts.

[0028] Step 12: Based on the first transmission line abnormality data set, obtain important description content of the first transmission line defect text, wherein the important description content at least includes an abnormal event description; based on the abnormal event description of the first transmission line defect text, determine the event location of the UAV image acquisition data set, and determine whether the first transmission line defect text is covered in the second transmission line abnormality data set of the UAV image acquisition data set.

[0029] Step 13: On the premise that the first transmission line defect text is included in the second transmission line abnormal data set, determine the first ranking of the first transmission line defect text in the second transmission line abnormal data set; on the premise that the first transmission line defect text is not included in the second transmission line abnormal data set, re-perform important attribute analysis on the drone image acquisition data set, capture the second transmission line defect text and perform defect assessment.

[0030] It can be understood that by analyzing the drone image acquisition data set to be analyzed, a transmission line abnormal data set including a first transmission line defect text can be determined from the drone image acquisition data set and the abnormal event description of the first transmission line defect text can be obtained from the transmission line abnormal data set. Then, by determining the event position of the drone image acquisition data set, the first transmission line defect text can be sorted in the subsequent transmission line abnormal data set. Through the sorting, the transmission line defect text can be completely captured and a defect assessment can be performed, thereby improving the accuracy and reliability of the defect assessment of the transmission line defect text.

[0031] STEP11, analyze the drone image acquisition data set to be analyzed, and determine the first transmission line abnormality data set including the first transmission line defect text in the drone image acquisition data set, wherein the first transmission line defect text includes one or more transmission line defect texts.

[0032] STEP 12: Based on the first power transmission line abnormality data set, obtain important description content of the first power transmission line defect text, wherein the important description content at least includes an abnormal event description.

[0033] STEP13, based on the abnormal event description of the first transmission line defect text, determine the event location of the UAV image acquisition data set, and determine whether the second transmission line abnormal data set of the UAV image acquisition data set covers the first transmission line defect text.

[0034] STEP 14: On the premise that the second power transmission line abnormality data set includes the first power transmission line defect text, determine a first ranking of the first power transmission line defect text in the second power transmission line abnormality data set.

[0035] In an embodiment of the present application, it is possible to analyze the drone image acquisition data set to be analyzed, determine the transmission line abnormal data set including the first transmission line defect text from the drone image acquisition data set, and obtain the abnormal event description of the first transmission line defect text from the transmission line abnormal data set, and then determine the event position of the drone image acquisition data set, and select the ranking of the first transmission line defect text in the subsequent transmission line abnormal data set, thereby improving the accuracy and reliability of the defect assessment of the transmission line defect text.

[0036] In an independent embodiment, the drone image acquisition data set to be analyzed may be a drone image acquisition data set in a specified scene acquired by a drone. The specified scene may be a specified subject for the drone to acquire the drone image acquisition data set, and in the specified scene, one or more drone image acquisition data sets of transmission line defect texts may be acquired.

[0037] In one possible implementation, the drone image acquisition data set can be analyzed in STEP11, and a first transmission line abnormality data set including a first transmission line defect text can be determined from the drone image acquisition data set. Analyzing the drone image acquisition data set can include performing important attribute analysis on the drone image acquisition data set, and capturing the first transmission line defect text through the important attribute analysis; it can also include determining the event location of the drone image acquisition data set, and capturing the first transmission line defect text through the event location determination. This application does not explain the analysis methods of the drone image acquisition data set one by one.

[0038] In a possible embodiment, the first transmission line defect text may include one transmission line defect text or may include several transmission line defect texts, which may be set according to actual operation steps. The present application does not limit the number of the first transmission line defect texts.

[0039] In an independent embodiment, STEP11 may include: performing important attribute analysis on the drone image acquisition data set to be analyzed, and determining a first transmission line abnormal data set including a first transmission line defect text in the drone image acquisition data set. Among them, the first transmission line defect text may be a pre-set abnormal standard. The important attributes of the illegal event may be pre-stored in the business client or system, and the first transmission line abnormal data set including the first transmission line defect text may be determined by analyzing and comparing each transmission line abnormal data set of the drone image acquisition data set. In addition, the first transmission line defect text may also be a transmission line defect text analyzed from each transmission line abnormal data set of the drone image acquisition data set. For example, a specified scene may include one or more transmission line defect texts, and the first transmission line defect text may be automatically determined from these transmission line defect texts.

[0040] In a possible embodiment, performing important attribute analysis on the drone image acquisition data set to be analyzed and determining a first transmission line abnormality data set including a first transmission line defect text in the drone image acquisition data set may include: based on a pre-set first transmission line defect text, performing important attribute analysis on several transmission line abnormality data sets of the drone image acquisition data set one by one, and determining a first transmission line abnormality data set including the first transmission line defect text from the several transmission line abnormality data sets.

[0041] For example, a first power transmission line defect text may be set in advance, such as: pre-specified relevant data that may cause big data errors or disorder can be used to derive important attribute descriptions of the first power transmission line defect text based on the content attributes of the first power transmission line defect text, so as to analyze the first power transmission line defect text in the drone image acquisition data set. The description of the important attributes of the derived first power transmission line defect text is not described in detail in this application.

[0042] In one possible implementation, important attribute analysis can be performed one by one on several power transmission line abnormality data sets of the drone image acquisition data set, and the analyzed important attribute descriptions can be compared with the important attribute descriptions of the first power transmission line defect text, and the first power transmission line abnormality data set including the first power transmission line defect text can be determined from the several power transmission line abnormality data sets. It is understandable that the important attribute analysis can be implemented by using AI intelligent learning models and other methods, and the present application will not elaborate on the important attribute analysis one by one.

[0043] Through the above technical solution, it is possible to accurately analyze the pre-specified transmission line defect text and determine the transmission line abnormal data set including the pre-specified transmission line defect text, thereby improving the accuracy of the transmission line defect text defect assessment.

[0044] In an independent embodiment, performing important attribute analysis on the drone image acquisition data set to be analyzed to determine a first transmission line abnormality data set including a first transmission line defect text in the drone image acquisition data set may include: performing important attribute analysis on the transmission line abnormality data set of the drone image acquisition data set to determine candidate transmission line defect texts in the transmission line abnormality data set; determining the transmission line defect text that meets specified requirements in the candidate transmission line defect texts as the first transmission line defect text; and determining the transmission line abnormality data set carrying the first transmission line defect text as the first transmission line abnormality data set.

[0045] For example, an important attribute analysis can be performed on the transmission line abnormal data set of the UAV image acquisition data set to determine the candidate transmission line defect texts in the transmission line abnormal data set, and then the candidate transmission line defect texts in the transmission line abnormal data set are judged according to the specified requirements, and the transmission line defect text that meets the specified requirements is determined as the first transmission line defect text, and the transmission line abnormal data set including the first transmission line defect text is determined as the first transmission line abnormal data set. Among them, the specified requirements can be one or more conditions set in advance. For example, the specified requirements can be understood as the transmission line defect text with the largest abnormal ranking in the candidate transmission line defect text, and can also be understood as the transmission line defect text with the best description of important attributes in the candidate transmission line defect text. Those skilled in the art can configure the specified requirements according to the actual operating conditions, and this application will not go into details one by one.

[0046] Through the above technical solution, it is possible to determine in real time the transmission line defect text that meets the requirements and determine the corresponding transmission line abnormal data set, thereby improving the accuracy and reliability of the transmission line defect text defect assessment.

[0047] In an independent embodiment, the above method can be implemented by an artificial intelligence analysis network, which includes at least an important attribute analysis subnetwork. The important attribute analysis subnetwork is used to perform important attribute analysis on the transmission line defect text in the transmission line abnormal data set. The important attribute analysis subnetwork may, for example, include an AI artificial intelligence analysis network, etc., and the present application does not describe the types of important attribute analysis subnetworks one by one.

[0048] In a possible implementation embodiment, an important attribute analysis is performed on the drone image acquisition data set to be analyzed to determine a first transmission line abnormality data set including a first transmission line defect text in the drone image acquisition data set, which may include: loading each transmission line abnormality data set of the drone image acquisition data set into the important attribute analysis subnetwork for processing one by one, and deriving important attribute descriptions of candidate transmission line defect texts in each transmission line abnormality data set; and determining the first transmission line abnormality data set including the first transmission line defect text based on the important attribute descriptions of the candidate transmission line defect texts.

[0049] For example, important attribute analysis can be performed through an important attribute analysis subnetwork. Each transmission line abnormality data set of the drone image acquisition data set can be loaded into the important attribute analysis subnetwork for processing one by one, and important attribute descriptions of candidate transmission line defect texts can be derived from each transmission line abnormality data set; based on the important attribute descriptions of the candidate transmission line defect texts, a first transmission line abnormality data set including a first transmission line defect text specified in advance can be determined, or a transmission line defect text that meets specified requirements can be determined, and the transmission line defect text is used as the first transmission line defect text, and the transmission line abnormality data set including the first transmission line defect text is determined as the first transmission line abnormality data set.

[0050] Through the above technical solution, the accuracy of defect assessment of transmission line defects can be improved.

[0051] In a possible implementation embodiment, STEP11 may include: determining the event location of the drone image acquisition data set to be analyzed, and determining the candidate transmission line defect texts in the drone image acquisition data set; determining the transmission line defect text that meets the specified requirements in the candidate transmission line defect texts as the first transmission line defect text; and determining the transmission line abnormality data set carrying the first transmission line defect text as the first transmission line abnormality data set.

[0052] For example, the event location of the transmission line abnormal data set of the drone image acquisition data set can be determined (for example, it can be a defect assessment abnormal key feature), and the candidate transmission line defect text in the transmission line abnormal data set can be determined. Then, the candidate transmission line defect text in the transmission line abnormal data set can be judged according to the specified requirements, and the transmission line defect text that meets the specified requirements can be determined as the first transmission line defect text, and the transmission line abnormal data set including the first transmission line defect text can be determined as the first transmission line abnormal data set. Among them, the specified requirements can be one or more conditions set in advance. For example, the specified requirements can be that the abnormal key features of the candidate transmission line defect text are fully presented, or that the accuracy and reliability of each abnormal key feature of the candidate transmission line defect text is the highest.

[0053] Through the above implementation scheme, it is possible to determine in real time the transmission line defect text that meets the requirements and determine the corresponding transmission line abnormal data set, thereby improving the accuracy and reliability of the transmission line defect text defect assessment.

[0054] In a possible implementation, after determining the first transmission line abnormal data set through the event location, an important attribute description of the first transmission line defect text can be obtained. According to the important attribute description, an important attribute analysis can be performed when the first transmission line defect text is lost. It is understandable that the important attribute description of the first transmission line defect text can be obtained in different ways, and the present application will not repeat the methods for obtaining the important attribute description one by one.

[0055] In a possible implementation, after determining the first transmission line abnormal data set, the important description content of the first transmission line defect text can be obtained in STEP12, and the important description content at least includes the abnormal event description (such as the subject of the abnormal key feature in the transmission line abnormal data set). Among them, there can be multiple important description contents of the first transmission line defect text, such as important attribute description, abnormal event description, operation situation description, etc. In the first transmission line abnormal data set, the first transmission line defect text can be obtained, which at least includes the important description content of the abnormal event description. It can be understood that the abnormal event description of the first transmission line defect text can be obtained in a variety of ways, and the present application will not repeat the methods of obtaining the abnormal event description one by one.

[0056] In an independent embodiment, the abnormal event description of the first transmission line defect text can be described by the subject of the abnormal key features in the transmission line abnormal data set. Further, the abnormal event description of the first transmission line defect text can be determined by the position of each abnormal key feature of the first transmission line defect text in the first transmission line abnormal data set. For example, the first transmission line defect text can be set to have 10 abnormal key features, and the abnormal event description of the first transmission line defect text can be determined according to the subject of the 10 abnormal key features in the first transmission line abnormal data set. The number of abnormal key features can be set according to the actual operation situation, and the specific number of abnormal key features will not be described one by one in this application.

[0057] In a possible implementation example, according to the abnormal event description of the first transmission line defect text, the event location of the drone image acquisition data set can be determined in STEP13, and it can be determined whether the first transmission line defect text is included in the second transmission line abnormal data set of the drone image acquisition data set. That is, the first transmission line defect text is attribute-selected within the specified scene (analysis topic). If the first transmission line defect text is selected, it can be considered that the first transmission line defect text is within the specified scene, and the order of the first transmission line defect text in the transmission line abnormal data set can be determined in STEP14; if the first transmission line defect text is not selected, it can be considered that the first transmission line defect text meets the specified scene.

[0058] In an independent embodiment, STEP13 may include: determining the event location of the second transmission line abnormal data set of the drone image acquisition data set, and determining the abnormal event description of the candidate transmission line defect text in the second transmission line abnormal data set; when covering the abnormal event description paired with the abnormal event description of the first transmission line defect text, determining that the first transmission line defect text is covered in the second transmission line abnormal data set.

[0059] For example, the abnormal event description can be represented by an abnormal key feature. The event location is determined for the second transmission line abnormal data set of the drone image acquisition data set, and the subject of each abnormal key feature of the candidate transmission line defect text in the second transmission line abnormal data set can be obtained. The subject of the abnormal key feature of the candidate transmission line defect text obtained from the second transmission line abnormal data set is compared with the subject of the abnormal key feature of the first transmission line defect text one by one to determine the similarity between the subject of the abnormal key feature of each transmission line defect text and the subject of the abnormal key feature of the first transmission line defect text. If the subject of the abnormal key feature with a similarity greater than or equal to the specified standard value of the similarity is covered, it can be considered that the second transmission line abnormal data set covers the abnormal event description matched with the abnormal event description of the first transmission line defect text, and it can be determined that the second transmission line abnormal data set covers the first transmission line defect text.

[0060] By associating the descriptions of abnormal events, it is determined that the second transmission line abnormal data set includes the first transmission line defect text, which can improve the accuracy and reliability of the defect assessment of the transmission line defect text.

[0061] In an independent embodiment, when a transmission line defect assessment method based on drone image analysis is implemented through an artificial intelligence analysis network, the artificial intelligence analysis network may include at least an event location determination subnetwork. The event location determination subnetwork may be used to determine the event location of a transmission line abnormal data set. It is understandable that the event location determination subnetwork may, for example, include an AI artificial intelligence analysis network.

[0062] In the present application, the event location of the second transmission line abnormality data set of the drone image acquisition data set is determined, and the abnormal event description of the candidate transmission line defect text in the second transmission line abnormality data set is determined, which may include: loading the second transmission line abnormality data set into the event location determination subnetwork for processing, and deriving the abnormal event description of the candidate transmission line defect text in the second transmission line abnormality data set.

[0063] By determining the event location of the second transmission line abnormal data set through the event location determination subnetwork, the accuracy of event location determination can be improved, thereby improving the accuracy and reliability of the transmission line defect text defect assessment.

[0064] In the present application, in STEP 14, on the premise that the first transmission line defect text is included in the second transmission line abnormal data set, the first ranking of the first transmission line defect text in the second transmission line abnormal data set can be determined. By determining the first ranking of the first transmission line defect text in the second transmission line abnormal data set, the accuracy of the transmission line defect text defect assessment can be improved.

[0065] In a possible implementation embodiment, the method may also include: on the premise that the first transmission line defect text is covered in the second transmission line abnormal data set, an operation description of the first transmission line defect text in the second transmission line abnormal data set can be obtained; according to the operation description of the first transmission line defect text, a detection method for the first transmission line defect text is triggered.

[0066] For example, when the second transmission line abnormal data set includes the first transmission line defect text, the operation description of the first transmission line defect text in the second transmission line abnormal data set can be obtained, and the operation description can be used to characterize the subject content of the first transmission line defect text in the second transmission line abnormal data set, which can be represented by the mutual correlation relationship of abnormal key features. According to the operation description of the first transmission line defect text, the detection method for the first transmission line defect text can be triggered. For example, the first transmission line defect text can be visualized according to the content of the transmission line defect text specified in advance. Further, the detection method for the first transmission line defect text can be to determine whether the operation description of the first transmission line defect text (the mutual correlation relationship of abnormal key features) is associated with the operation description of the transmission line defect text specified in advance (the mutual correlation relationship of abnormal key features), and give scoring information according to the correlation, wherein the higher the correlation, the higher the score. The operational description of the first transmission line defect text may also be a dimensional attribute when the first transmission line defect text interacts with a pre-specified transmission line defect text. Accordingly, the detection method for the first transmission line defect text may also be to implement corresponding countermeasures based on the operational description of the first transmission line defect text.

[0067] It can be understood that, based on the operational description of the first transmission line defect text, a variety of contents can be determined, for example, abnormal classification rules, etc.; based on the operational description, there can also be a variety of detection methods for triggering the first transmission line defect text, which can be to evaluate the correlation between the operational description of the first transmission line defect text and the operational description of a pre-specified transmission line defect text and provide scoring information, or to implement corresponding countermeasures based on the operational description of the first transmission line defect text, or to use other operations.

[0068] By obtaining an operation description of the first transmission line defect text and triggering a detection method for the first transmission line defect text according to the operation description, the accuracy and reliability of defect assessment and selection of the first transmission line defect text can be improved.

[0069] In an independent embodiment, when a transmission line defect evaluation method based on drone image analysis is implemented through an artificial intelligence analysis network, the artificial intelligence analysis network may include at least an operation description derivative subnetwork. The operation description derivative subnetwork may be used to derive the operation description of the first transmission line defect text in the transmission line abnormal data set. It is understandable that the operation description derivative subnetwork may, for example, include an AI artificial intelligence analysis network, and the present application will not repeat the types of the operation description derivative subnetworks one by one.

[0070] In a possible implementation, on the premise that the first transmission line defect text is included in the second transmission line abnormal data set, obtaining the operation description of the first transmission line defect text in the second transmission line abnormal data set may include: loading the second transmission line abnormal data set into the operation description derivation subnetwork for processing, and deriving the operation description of the first transmission line defect text in the second transmission line abnormal data set.

[0071] By obtaining the operation description of the first transmission line defect text through the operation description derivative subnetwork, the accuracy and reliability of the operation description of the first transmission line defect text can be improved, thereby improving the accuracy and reliability of defect evaluation and selection of the first transmission line defect text.

[0072] According to the process of a transmission line defect evaluation method based on drone image analysis according to an embodiment of the present application, in an independent embodiment, the transmission line defect evaluation method based on drone image analysis may also include the following contents.

[0073] STEP15. On the premise that the second transmission line abnormality data set does not include the first transmission line defect text, re-analyze the important attributes of the UAV image acquisition data set to determine the third transmission line abnormality data set of the UAV image acquisition data set, and the third transmission line abnormality data set includes the captured second transmission line defect text.

[0074] STEP 16: Based on the third power transmission line abnormality data set, obtain important description content of the second power transmission line defect text, wherein the important description content at least includes an abnormal event description.

[0075] STEP17, based on the abnormal event description of the second transmission line defect text, determine the event location of the UAV image acquisition data set, and determine whether the fourth transmission line abnormal data set of the UAV image acquisition data set covers the second transmission line defect text.

[0076] STEP 18: On the premise that the second transmission line defect text is included in the fourth transmission line abnormality data set, determine a second ranking of the second transmission line defect text in the fourth transmission line abnormality data set.

[0077] In the above embodiment, under the premise that the first transmission line defect text is not included in the second transmission line abnormal data set, the important attribute analysis can be re-performed on the drone image acquisition data set to determine the third transmission line abnormal data set including the second transmission line defect text, and obtain the abnormal event description of the second transmission line defect text in the third transmission line abnormal data set; according to the abnormal event description of the second transmission line defect text, the event position of the drone image acquisition data set can be determined to determine whether the second transmission line defect text is included in the fourth transmission line abnormal data set of the drone image acquisition data set; under the premise that the second transmission line defect text is included in the fourth transmission line abnormal data set, the second ranking of the second transmission line defect text in the fourth transmission line abnormal data set is determined.

[0078] By re-performing important attribute analysis on the UAV image acquisition data set on the premise that the first transmission line defect text is not covered in the second transmission line abnormal data set, capturing the second transmission line defect text and performing defect assessment and selection, the reliability of the transmission line defect text defect assessment and selection can be improved.

[0079] In an independent embodiment, the method also includes: on the premise that the second transmission line defect text is covered in the fourth transmission line abnormal data set, obtaining an operation description of the second transmission line defect text in the fourth transmission line abnormal data set; based on the operation description of the second transmission line defect text, triggering a detection method for the second transmission line defect text.

[0080] For example, when the fourth transmission line abnormal data set includes the second transmission line defect text, the operation description of the second transmission line defect text in the fourth transmission line abnormal data set can be obtained, and the operation description can be used to represent the subject content of the second transmission line defect text in the fourth transmission line abnormal data set, which can be represented by the mutual correlation relationship of the abnormal key features. According to the operation description of the second transmission line defect text, the detection method for the second transmission line defect text can be triggered. Accordingly, the detection method for the second transmission line defect text can be to determine whether the operation description of the second transmission line defect text (the mutual correlation relationship of the abnormal key features) is associated with the operation description of the pre-specified transmission line defect text (the mutual correlation relationship of the abnormal key features), and give scoring information according to the correlation, wherein the higher the correlation, the higher the scoring information. The operation description of the second transmission line defect text can also be a dimensional attribute when the second transmission line defect text interacts with the pre-specified transmission line defect text. Accordingly, the detection method for the second transmission line defect text can also be to implement corresponding countermeasures according to the operation description of the second transmission line defect text.

[0081] It is understandable that, according to the description of the operation situation of the second transmission line defect text, a variety of contents can be determined, and according to the description of the operation situation, there can also be a variety of detection methods for triggering the second transmission line defect text. The present application will not describe the description of the operation situation of the second transmission line defect text and the detection method for the second transmission line defect text executed according to the description of the operation situation one by one.

[0082] By obtaining the operation description of the second transmission line defect text and triggering the detection method for the second transmission line defect text according to the operation description, the accuracy and reliability of defect assessment and selection of the second transmission line defect text can be improved.

[0083] In an independent embodiment, on the premise that the first transmission line defect text is not included in the second transmission line abnormality data set (the first transmission line defect text is lost) and the second transmission line defect text is started to be selected, the method also includes: performing important attribute analysis on the drone image acquisition data set to determine whether the first transmission line defect text is included in the fourth transmission line abnormality data set of the drone image acquisition data set; on the premise that the first transmission line defect text is included in the fourth transmission line abnormality data set, determining the third ranking of the first transmission line defect text in the fourth transmission line abnormality data set.

[0084] For example, under the premise that the first transmission line defect text is not included in the second transmission line abnormal data set, when performing defect assessment on the second transmission line defect text, the important attribute analysis can be performed again on the drone image acquisition data set to determine whether the first transmission line defect text is included in the fourth transmission line abnormal data set of the drone image acquisition data set. Among them, the method of performing important attribute analysis on the drone image acquisition data set can be to continuously perform important attribute analysis on the drone image acquisition data set, or to perform important attribute analysis intermittently (for example, 6 seconds) or at intervals of several transmission line abnormal data sets. The method of important attribute analysis will not be described in detail in this application.

[0085] In an independent embodiment, on the premise that the first transmission line defect text is included in the fourth transmission line abnormal data set, the third ranking of the first transmission line defect text in the fourth transmission line abnormal data set can be determined, that is, defect assessment of the first transmission line defect text starts here.

[0086] Through the above technical solution, the accuracy of defect assessment and selection of the first transmission line defect text can be increased.

[0087] In an independent embodiment, the method further includes: obtaining an operation description of the first transmission line defect text in the fourth transmission line abnormal data set, on the premise that the first transmission line defect text is covered in the fourth transmission line abnormal data set; and triggering a detection method for the first transmission line defect text based on the operation description of the first transmission line defect text.

[0088] For example, when the fourth transmission line abnormal data set includes the first transmission line defect text, the operation description of the first transmission line defect text in the fourth transmission line abnormal data set can be obtained, and the operation description can be used to represent the subject content of the first transmission line defect text in the fourth transmission line abnormal data set, which can be represented by the mutual correlation of abnormal key features. According to the operation description of the first transmission line defect text, the detection method for the first transmission line defect text can be triggered. Accordingly, the detection method for the first transmission line defect text can be to determine whether the operation description of the first transmission line defect text (the mutual correlation of abnormal key features) matches the operation description of the pre-specified transmission line defect text (the mutual correlation of abnormal key features), and give scoring information according to the correlation, wherein the higher the correlation, the higher the scoring information. The operation description of the first transmission line defect text can also be a dimensional attribute when the first transmission line defect text interacts with the pre-specified transmission line defect text. Accordingly, the detection method for the first transmission line defect text can also be to implement corresponding countermeasures according to the operation description of the first transmission line defect text.

[0089] It is understandable that a variety of contents may be determined based on the description of the operation condition of the first power transmission line defect text, and a variety of detection methods may be triggered for the first power transmission line defect text based on the description of the operation condition.

[0090] By obtaining an operation description of the first transmission line defect text and triggering a detection method for the first transmission line defect text according to the operation description, the accuracy of defect assessment and selection of the first transmission line defect text can be improved.

[0091] Under the above premise, please refer to Figure 2 , a transmission line defect assessment device 200 based on drone image analysis is provided, which is applied to a transmission line defect assessment system based on drone image analysis, and the device comprises: The data set determination module 210 is used to analyze the drone image acquisition data set to be analyzed, and determine a first transmission line abnormality data set including a first transmission line defect text in the drone image acquisition data set, wherein the first transmission line defect text includes one or more transmission line defect texts; The description content acquisition module 220 is used to acquire important description content of the first transmission line defect text based on the first transmission line abnormality data set, wherein the important description content at least includes an abnormal event description; based on the abnormal event description of the first transmission line defect text, determine the event location of the drone image acquisition data set, and determine whether the first transmission line defect text is covered in the second transmission line abnormality data set of the drone image acquisition data set; The defect assessment module 230 is used to determine the first ranking of the first transmission line defect text in the second transmission line abnormal data set, on the premise that the first transmission line defect text is covered in the second transmission line abnormal data set; and to re-perform important attribute analysis on the drone image acquisition data set, capture the second transmission line defect text and perform defect assessment, on the premise that the first transmission line defect text is not covered in the second transmission line abnormal data set.

[0092] Under the above premise, please refer to Figure 3 , shows a transmission line defect assessment system 300 based on drone image analysis, including a processor 310 and a memory 320 that communicate with each other, and the processor 310 is used to read and execute a computer program from the memory 320 to implement the above method.

[0093] Under the above premise, a computer-readable storage medium is also provided, on which a computer program stored implements the above method when running.

[0094] In summary, based on the above scheme, in an embodiment of the present application, it is possible to determine the transmission line abnormal data set including the first transmission line defect text from the drone image acquisition data set by analyzing the drone image acquisition data set to be analyzed, and obtain the abnormal event description of the first transmission line defect text from the transmission line abnormal data set, and then determine the event position of the drone image acquisition data set, and select the sorting of the first transmission line defect text in the subsequent transmission line abnormal data set. Through sorting, the transmission line defect text can be completely captured and defect assessment can be performed, thereby improving the accuracy and reliability of the defect assessment of the transmission line defect text.

[0095] It should be understood that the system and its modules shown above can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above methods and systems can be implemented using computer executable instructions and / or included in processor control codes, such as on a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided. The system and its modules of the present application can not only be implemented by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but can also be implemented by software such as executed by various types of processors, and can also be implemented by a combination of the above hardware circuits and software (e.g., firmware).

[0096] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or may be any other beneficial effects that may be obtained.

[0097] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.

[0098] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0099] In addition, it will be appreciated by those skilled in the art that various aspects of the present application may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may all be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present application may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0100] Computer storage media may include a propagated data signal containing computer program code, such as in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination of forms. Computer storage media can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or equipment to communicate, propagate or transmit the program for use. The program code on the computer storage medium can be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0101] The computer program codes required for the operation of each part of the present application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages, etc. The program code can be run entirely on the user's computer, or run on the user's computer as an independent software package, or run partially on the user's computer and partially on a remote computer, or run entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0102] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that meet the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0103] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more embodiments of the invention, in the above description of the embodiments of the application, multiple features are sometimes combined into one embodiment, drawing or description thereof. However, this disclosure method does not mean that the subject matter of the application requires more features than those mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0104] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used for the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers allow adaptive changes. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which can be changed according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of the present application are approximate values, in specific embodiments, the designation of such numerical values ​​is as accurate as possible within the feasible range.

[0105] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, instructions, publications, documents, etc., cited in this application are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the content of this application, documents that limit the broadest scope of the claims of this application (currently or later attached to this application) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the attached materials of this application are inconsistent or conflicting with the content described in this application, the descriptions, definitions, and / or use of terms in this application shall prevail.

[0106] Finally, it should be understood that the embodiments described in this application are only used to illustrate the principles of the embodiments of the present application. Other variations may also fall within the scope of the present application. Therefore, as an example and not a limitation, the alternative configurations of the embodiments of the present application may be considered to be consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to the embodiments explicitly introduced and described in the present application.

[0107] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for evaluating power transmission line defects based on drone image analysis, characterized in that: The method comprises at least the following steps: Analyze the drone image acquisition data set to be analyzed, and determine a first transmission line abnormality data set including a first transmission line defect text in the drone image acquisition data set, wherein the first transmission line defect text includes one or more transmission line defect texts; Based on the first transmission line abnormality data set, important description content of the first transmission line defect text is obtained, and the important description content at least includes an abnormal event description; based on the abnormal event description of the first transmission line defect text, the event location of the drone image acquisition data set is determined, and it is determined whether the first transmission line defect text is covered in the second transmission line abnormality data set of the drone image acquisition data set; On the premise that the first transmission line defect text is covered in the second transmission line abnormal data set, the first ranking of the first transmission line defect text in the second transmission line abnormal data set is determined; on the premise that the first transmission line defect text is not covered in the second transmission line abnormal data set, important attribute analysis is re-performed on the drone image acquisition data set to capture the second transmission line defect text and perform defect assessment.

2. The method according to claim 1, characterized in that Analyze the drone image acquisition data set to be analyzed, and determine the first transmission line abnormality data set that includes the first transmission line defect text in the drone image acquisition data set, including: perform important attribute analysis on the drone image acquisition data set to be analyzed, and determine the first transmission line abnormality data set that includes the first transmission line defect text in the drone image acquisition data set.

3. The method according to claim 1, characterized in that Analyzing the drone image acquisition data set to be analyzed, and determining a first transmission line abnormality data set including a first transmission line defect text in the drone image acquisition data set, including: determining an event location of the drone image acquisition data set to be analyzed, and determining a candidate transmission line defect text in the drone image acquisition data set; Determine the transmission line defect text that meets the specified requirements among the candidate transmission line defect texts as the first transmission line defect text; The power transmission line abnormal data set carrying the first power transmission line defect text is determined as the first power transmission line abnormal data set.

4. The method according to claim 1, characterized in that: The re-performing important attribute analysis on the drone image acquisition data set, capturing the second transmission line defect text and performing defect assessment, includes: On the premise that the second transmission line abnormality data set does not include the first transmission line defect text, re-analyze the important attributes of the drone image acquisition data set to determine a third transmission line abnormality data set of the drone image acquisition data set, wherein the third transmission line abnormality data set includes the captured second transmission line defect text; Based on the third power transmission line abnormality data set, obtaining important description content of the second power transmission line defect text, wherein the important description content at least includes an abnormal event description; Based on the abnormal event description of the second transmission line defect text, determine the event location of the drone image acquisition data set, and determine whether the fourth transmission line abnormal data set of the drone image acquisition data set covers the second transmission line defect text; On the premise that the second transmission line defect text is included in the fourth transmission line abnormality data set, determining a second ranking of the second transmission line defect text in the fourth transmission line abnormality data set; Wherein, the method further comprises: Performing important attribute analysis on the drone image acquisition data set to determine whether the first transmission line defect text is included in the fourth power transmission line abnormality data set of the drone image acquisition data set; On the premise that the first transmission line defect text is included in the fourth transmission line abnormality data set, a third ranking of the first transmission line defect text in the fourth transmission line abnormality data set is determined.

5. The method according to claim 1, characterized in that The method further comprises: On the premise that the second power transmission line abnormality data set includes the first power transmission line defect text, obtaining an operation description of the first power transmission line defect text in the second power transmission line abnormality data set; Based on the description of the operation status of the first power transmission line defect text, a detection method for the first power transmission line defect text is triggered.

6. The method according to claim 4, characterized in that The method further comprises: On the premise that the second transmission line defect text is included in the fourth transmission line abnormal data set, obtaining an operation description of the second transmission line defect text in the fourth transmission line abnormal data set; Based on the description of the operation condition of the second power transmission line defect text, a detection method for the second power transmission line defect text is triggered.

7. The method according to claim 4, characterized in that The method further comprises: On the premise that the first transmission line defect text is included in the fourth transmission line abnormal data set, obtaining an operation description of the first transmission line defect text in the fourth transmission line abnormal data set; Based on the description of the operation status of the first power transmission line defect text, a detection method for the first power transmission line defect text is triggered.

8. The method according to claim 2, characterized in that: Performing important attribute analysis on the drone image acquisition data set to be analyzed, determining a first transmission line abnormality data set including a first transmission line defect text in the drone image acquisition data set, including: Based on the first transmission line defect text set in advance, important attribute analysis is performed one by one on several transmission line abnormal data sets of the UAV image acquisition data set, and a first transmission line abnormal data set including the first transmission line defect text is determined from the several transmission line abnormal data sets; Among them, the important attribute analysis is performed on the drone image acquisition data set to be analyzed, and the first transmission line abnormality data set including the first transmission line defect text in the drone image acquisition data set is determined, including: Performing important attribute analysis on the power transmission line abnormality data set of the UAV image acquisition data set to determine candidate power transmission line defect texts in the power transmission line abnormality data set; Determine the transmission line defect text that meets the specified requirements among the candidate transmission line defect texts as the first transmission line defect text; The power transmission line abnormal data set carrying the first power transmission line defect text is determined as the first power transmission line abnormal data set.

9. The method according to claim 1, characterized in that: Based on the abnormal event description of the first transmission line defect text, determining the event location of the drone image acquisition data set, and judging whether the second transmission line abnormal data set of the drone image acquisition data set covers the first transmission line defect text, including: Determine the event location of a second power transmission line abnormality data set of the UAV image acquisition data set, and determine the abnormal event description of the candidate power transmission line defect text in the second power transmission line abnormality data set; When the abnormal event description matched with the abnormal event description of the first power transmission line defect text is included, determining that the first power transmission line defect text is included in the second power transmission line abnormal data set; The method is implemented by an artificial intelligence analysis network, and the artificial intelligence analysis network includes at least an important attribute analysis subnetwork, wherein an important attribute analysis is performed on the drone image acquisition data set to be analyzed, and a first transmission line abnormality data set including a first transmission line defect text in the drone image acquisition data set is determined, including: Loading each power transmission line abnormality data set of the UAV image acquisition data set into the important attribute analysis subnetwork for processing, and deriving important attribute descriptions of candidate power transmission line defect texts in each power transmission line abnormality data set; Determining a first transmission line abnormality data set including a first transmission line defect text according to an important attribute description of the candidate transmission line defect text; The artificial intelligence analysis network further includes an event location determination subnetwork, wherein the event location is determined for the second transmission line abnormality data set of the drone image acquisition data set, and the abnormal event description of the candidate transmission line defect text in the second transmission line abnormality data set is determined, including: Loading the second transmission line abnormality data set into the event location determination subnetwork for processing, and deriving abnormal event descriptions of candidate transmission line defect texts in the second transmission line abnormality data set; The artificial intelligence analysis network further includes an operation description derivative subnetwork, wherein, on the premise that the second transmission line abnormality data set includes the first transmission line defect text, obtaining an operation description of the first transmission line defect text in the second transmission line abnormality data set includes: Loading the second transmission line abnormal data set into the operation description derivation subnetwork for processing, and deriving the operation description of the first transmission line defect text in the second transmission line abnormal data set; The drone image acquisition data set is a drone image acquisition data set within a specified scene acquired by a drone.

10. A power transmission line defect assessment system based on drone image analysis, characterized in that: The invention comprises a processor and a memory communicating with each other, wherein the processor is used to read a computer program from the memory and execute the computer program to implement the method according to any one of claims 1 to 9.

Images