Substation alarm method and system based on primitive monitoring, computer equipment, readable storage medium and program product

Abstract

The invention relates to a substation alarm method and system based on primitive monitoring, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring monitoring video data of a transformer substation; performing primitive recognition processing on the monitoring video data to obtain structured primitive data; inputting the structured primitive data into a preset exception recognition model to obtain an exception detection result corresponding to the monitoring video data; generating monitoring alarm information according to the monitoring abnormal data under the condition that the structured primitive data is determined to contain the monitoring abnormal data based on the abnormal detection result; and pushing the monitoring alarm information. According to the method, the monitoring efficiency, the real-time performance and the data processing capability of video monitoring in the transformer substation can be effectively improved through primitive embedding, the real-time performance and the accuracy of a monitoring system are comprehensively improved, a user can be informed of the abnormal condition in time through alarm, and the alarm efficiency of the abnormal condition of the transformer substation is comprehensively improved.

Description

Technical Field

[0001] The present application relates to the technical field of substation monitoring, and in particular to a substation alarm method, system, computer equipment, readable storage medium and program product based on graphic element monitoring. Background Art

[0002] With the development of computer technology and power technology, the number and scale of substations are increasing, which puts forward higher requirements for substation monitoring and management. Traditional substation monitoring systems usually adopt text-based and graphic-based monitoring methods, which have problems such as non-intuitive information and poor real-time performance. In order to solve these problems, video monitoring technology has gradually been applied to substation monitoring systems.

[0003] Video surveillance technology can obtain video images in substations. By analyzing and processing video images, it can realize real-time monitoring and management of the operating status of substation equipment and personnel's operating behaviors. However, the current substation monitoring system mainly relies on manual inspection and video monitoring, but there are problems such as low monitoring efficiency, poor real-time performance, and weak data processing capabilities, which affect the alarm efficiency of abnormal substation conditions. Summary of the invention

[0004] Based on this, it is necessary to provide a substation alarm method, system, computer equipment, computer-readable storage medium and computer program product based on graphic element monitoring that can improve the substation alarm efficiency in response to the above technical problems.

[0005] In a first aspect, the present application provides a substation alarm method applied to image element monitoring, the method comprising:

[0006] Obtain monitoring video data of the substation;

[0007] Performing image element recognition processing on the surveillance video data to obtain structured image element data;

[0008] Inputting the structured graph metadata into a preset anomaly recognition model to obtain an anomaly detection result corresponding to the monitoring video data, wherein the preset anomaly recognition model is trained based on the structured graph metadata in the historical data;

[0009] In a case where it is determined based on the abnormality detection result that the structured graph metadata contains monitoring abnormality data, generating monitoring alarm information according to the monitoring abnormality data;

[0010] Push the monitoring alarm information.

[0011] In one embodiment, performing primitive recognition processing on the surveillance video data to obtain structured primitive metadata includes:

[0012] Performing image element recognition processing on the surveillance video data to identify target key image elements in the surveillance video data;

[0013] Determine the primitive type corresponding to the target key primitive;

[0014] Based on the primitive type, the corresponding target key primitive is converted into structured primitive data.

[0015] In one embodiment, the method further comprises:

[0016] Get the display mode of the graphic element information;

[0017] Performing page generation processing based on the structured graphic element metadata and the graphic element information display mode to obtain a graphic element display information page;

[0018] Pushing the graphic element display information page;

[0019] Obtaining alarm threshold information based on feedback from the graphic element display information page;

[0020] In the case where it is determined based on the abnormality detection result that the structured graph metadata includes monitoring abnormality data, generating monitoring alarm information according to the monitoring abnormality data includes:

[0021] When it is determined based on the anomaly detection result and the alarm threshold information that the structured graph metadata includes monitoring anomaly data, monitoring alarm information is generated according to the monitoring anomaly data.

[0022] In one embodiment, the pushing of the graphic element display information page includes:

[0023] Compressing and encrypting the graphic element display information page to obtain display information encrypted data;

[0024] The graphic element display information page is pushed based on the display information encrypted data.

[0025] In one embodiment, the method further comprises:

[0026] Obtain historical surveillance video data;

[0027] Performing image element recognition processing on the historical monitoring video data to obtain training image element data;

[0028] Perform abnormal category labeling processing on the training graph metadata to obtain model training data;

[0029] Model training is performed on the initial abnormality recognition model based on the model training data to obtain a preset abnormality recognition model.

[0030] In one embodiment, generating monitoring alarm information according to the monitoring abnormal data includes:

[0031] Extracting the abnormality type and abnormality occurrence time corresponding to the monitoring abnormality data;

[0032] Searching for structured graph metadata corresponding to the monitoring abnormal data;

[0033] Generate monitoring alarm information according to the abnormality type, the abnormality occurrence time and the structured graph metadata corresponding to the monitoring abnormality data.

[0034] In a second aspect, the present application also provides a substation alarm system based on graphic element monitoring, comprising:

[0035] A data acquisition module, used to acquire monitoring video data of the substation;

[0036] A graphic element recognition module is used to perform graphic element recognition processing on the monitoring video data to obtain structured graphic element data;

[0037] An anomaly detection module, used to input the structured graph metadata into a preset anomaly recognition model to obtain an anomaly detection result corresponding to the monitoring video data, wherein the preset anomaly recognition model is trained based on the structured graph metadata in the historical data;

[0038] An alarm information generating module, configured to generate monitoring alarm information according to the monitoring abnormality data when it is determined based on the abnormality detection result that the structured graph metadata contains monitoring abnormality data;

[0039] The alarm information push module is used to push the monitoring alarm information.

[0040] 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:

[0041] Obtain monitoring video data of the substation;

[0042] Performing image element recognition processing on the surveillance video data to obtain structured image element data;

[0043] Inputting the structured graph metadata into a preset anomaly recognition model to obtain an anomaly detection result corresponding to the monitoring video data, wherein the preset anomaly recognition model is trained based on the structured graph metadata in the historical data;

[0044] In a case where it is determined based on the abnormality detection result that the structured graph metadata contains monitoring abnormality data, generating monitoring alarm information according to the monitoring abnormality data;

[0045] Push the monitoring alarm information.

[0046] 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:

[0047] Obtain monitoring video data of the substation;

[0048] Performing image element recognition processing on the surveillance video data to obtain structured image element data;

[0049] Inputting the structured graph metadata into a preset anomaly recognition model to obtain an anomaly detection result corresponding to the monitoring video data, wherein the preset anomaly recognition model is trained based on the structured graph metadata in the historical data;

[0050] In a case where it is determined based on the abnormality detection result that the structured graph metadata contains monitoring abnormality data, generating monitoring alarm information according to the monitoring abnormality data;

[0051] Push the monitoring alarm information.

[0052] 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:

[0053] Obtain monitoring video data of the substation;

[0054] Performing image element recognition processing on the surveillance video data to obtain structured image element data;

[0055] Inputting the structured graph metadata into a preset anomaly recognition model to obtain an anomaly detection result corresponding to the monitoring video data, wherein the preset anomaly recognition model is trained based on the structured graph metadata in the historical data;

[0056] In a case where it is determined based on the abnormality detection result that the structured graph metadata contains monitoring abnormality data, generating monitoring alarm information according to the monitoring abnormality data;

[0057] Push the monitoring alarm information.

[0058] The above-mentioned substation alarm method, system, computer device, computer-readable storage medium and computer program product based on primitive monitoring, first obtain the monitoring video data of the substation; then perform primitive recognition processing on the monitoring video data to obtain structured primitive metadata; input the structured primitive metadata into a preset abnormal recognition model to obtain the abnormal detection result corresponding to the monitoring video data, the preset abnormal recognition model is obtained based on the structured primitive metadata in the historical data training; when it is determined based on the abnormal detection result that the structured primitive metadata contains the monitoring abnormal data, the monitoring alarm information is generated according to the monitoring abnormal data; and the monitoring alarm information is pushed. The present application embeds video primitives into the substation monitoring system, and after obtaining the monitoring video data, extracts the structured primitive metadata in the monitoring video through primitive recognition processing, thereby completing the abnormal recognition processing during the operation of the substation based on the structured primitive metadata, and issues an alarm based on the result of abnormal recognition. The primitive embedding can effectively improve the monitoring efficiency, real-time and data processing capability of the video monitoring in the substation, and comprehensively improve the real-time and accuracy of the monitoring system. The alarm can also promptly notify the user of abnormal conditions, and comprehensively improve the alarm efficiency of abnormal conditions in the substation. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] 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.

[0060] Figure 1 This is an application environment diagram of a substation alarm method based on graphic element monitoring in one embodiment;

[0061] Figure 2 It is a flowchart of a substation alarm method based on graphic element monitoring in one embodiment;

[0062] Figure 3 is a schematic flow chart of a primitive recognition step in one embodiment;

[0063] Figure 4 It is a flowchart of a substation alarm method based on graphic element monitoring in another embodiment;

[0064] Figure 5 is a structural block diagram of a substation alarm system based on graphic element monitoring in one embodiment;

[0065] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0066] 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.

[0067] The substation alarm method based on graphic element monitoring provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. At the same time, the terminal 102 is also connected to multiple image acquisition devices 106 arranged in the substation, and can obtain the monitoring video data collected by the image acquisition device, so as to realize the recognition and alarm of abnormal conditions in the substation. The terminal 102 obtains the monitoring video data collected by the image acquisition device 106, and then performs image element recognition processing on the monitoring video data to obtain structured image element data; the structured image element data is input into the preset abnormal recognition model to obtain the abnormal detection result corresponding to the monitoring video data, and the preset abnormal recognition model is obtained based on the structured image element data in the historical data. Training is obtained; when it is determined based on the abnormal detection result that the structured image element data contains monitoring abnormal data, monitoring alarm information is generated according to the monitoring abnormal data; the monitoring alarm information is pushed so that the staff can understand the abnormality of the substation, and at the same time, these monitoring information can also be transmitted to the server 104 through the network for storage. The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, or a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0068] In an exemplary embodiment, Figure 2 As shown in FIG. 1 , a substation alarm method based on graphic element monitoring is provided, and the method is applied to Figure 1 The terminal 102 in the example is used as an example to illustrate, including the following steps 201 to 209. Among them:

[0069] Step 201, obtaining monitoring video data of the substation.

[0070] Step 203: perform graphic element recognition processing on the surveillance video data to obtain structured graphic element data.

[0071] The monitoring video data refers to the monitoring video continuously collected by the image acquisition devices 106 installed at various locations in the substation. The primitive recognition processing refers to analyzing the monitoring video data, identifying key primitives in the video, such as equipment status indications, personnel activity trajectories, etc., and displaying the information contained in these primitives through structured primitive metadata.

[0072] Exemplarily, the present application can collect basic data for abnormal alarms through an image acquisition device 106 deployed inside a substation. After the image acquisition device 106 has acquired images, the acquired images can be transmitted to the terminal 102 so that the acquired videos can be analyzed through the terminal 102. Then it is determined whether there is an abnormality in the substation, and an alarm related to the abnormality is processed. The terminal 102 will perform image element recognition processing on the monitoring video data to obtain structured image element data. The terminal 102 can specifically perform in-depth analysis on the received monitoring video data through image processing and machine learning algorithms. By identifying key image elements in the video, such as equipment status indications, personnel activity trajectories, etc. The accuracy and real-time nature of image element recognition are the core advantages of this solution, which can help operators quickly understand the operating status of the substation. In a specific embodiment, the image acquisition device 106 can be implemented by a high-definition camera, and the deployed high-definition camera can be used to capture video data of various key locations of the substation in real time, and the analog video signal can be converted into a high-quality digital signal using advanced analog-to-digital conversion technology. Thereby ensuring the clarity and accuracy of the video data, providing a reliable data basis for subsequent image element recognition.

[0073] Step 205 , input the structured graph metadata into a preset anomaly recognition model to obtain an anomaly detection result corresponding to the monitoring video data, where the preset anomaly recognition model is trained based on the structured graph metadata in the historical data.

[0074] The preset anomaly recognition model refers to a machine learning model that has been pre-trained to identify whether structured graph metadata contains abnormal information. By analyzing the structured graph metadata, the algorithm model identifies the normal behavior pattern. Once a deviation from the preset pattern is found, such as abnormal operation of equipment or misoperation by personnel, an anomaly detection result can be generated.

[0075] For example, in order to complete the abnormal alarm processing of the substation, after obtaining the structured graph metadata, it is also necessary to identify and process the data representing the key monitoring information of the substation. Therefore, the model training data can be constructed based on the structured graph metadata in the historical data, and then the abnormal recognition model can be pre-trained based on the deep learning method. During processing, the structured graph metadata can be directly input into the preset abnormal recognition model to obtain the abnormal detection results corresponding to the monitoring video data. The abnormal detection results will be fed back to the user and other modules of the system in real time so that timely countermeasures can be taken to ensure the safe and stable operation of the substation.

[0076] Step 207 : when it is determined based on the anomaly detection result that the structured graph metadata contains monitoring anomaly data, monitoring alarm information is generated according to the monitoring anomaly data.

[0077] Step 209: Push monitoring alarm information.

[0078] Exemplarily, the preset anomaly recognition model will analyze and process the input structured graph metadata to determine whether there are any anomalies in the monitoring information contained in the structured graph metadata. When abnormal conditions such as abnormal equipment operation or personnel operation deviating from the normal mode occur, the anomaly detection result of the corresponding abnormal condition will be directly output. When the equipment is operating normally, an abnormal detection result indicating no abnormality will be output. In the case where it is determined based on the anomaly detection result that the structured graph metadata contains monitoring abnormal data, monitoring alarm information can be directly generated based on the monitoring abnormal data, and alarm processing can be performed through the monitoring alarm information. The alarm process is specifically designed for real-time response. Once an abnormal condition is detected, detailed alarm information will be immediately generated, including the type of abnormality, the time of occurrence, the graph elements involved, etc. These alarm messages will be quickly pushed to users to ensure that users can respond quickly and handle them in a timely manner, effectively avoiding potential security risks.

[0079] The above-mentioned substation alarm method based on primitive monitoring is to first obtain the monitoring video data of the substation; then perform primitive recognition processing on the monitoring video data to obtain structured primitive metadata; input the structured primitive metadata into a preset abnormal recognition model to obtain the abnormal detection result corresponding to the monitoring video data, and the preset abnormal recognition model is obtained based on the structured primitive metadata in the historical data training; when it is determined based on the abnormal detection result that the structured primitive metadata contains the monitoring abnormal data, the monitoring alarm information is generated according to the monitoring abnormal data; and the monitoring alarm information is pushed. This application embeds video primitives into the substation monitoring system, and after obtaining the monitoring video data, extracts the structured primitive metadata in the monitoring video through primitive recognition processing, so as to complete the abnormal recognition processing during the operation of the substation based on the structured primitive metadata, and issue an alarm based on the result of abnormal recognition. The primitive embedding can effectively improve the monitoring efficiency, real-time and data processing capability of the video monitoring in the substation, and comprehensively improve the real-time and accuracy of the monitoring system. The alarm can also promptly notify the user of abnormal conditions, and comprehensively improve the alarm efficiency of abnormal conditions in the substation.

[0080] In an exemplary embodiment, Figure 3 As shown, step 203 includes:

[0081] Step 302: Performing graphic element recognition processing on the surveillance video data to identify target key graphic elements in the surveillance video data.

[0082] Step 304: determine the primitive type corresponding to the target key primitive.

[0083] Step 306: Convert the corresponding target key primitive into structured primitive data based on the primitive type.

[0084] Among them, the target key element refers to the key element information related to the design abnormality recognition and processing, such as equipment icons, operation instructions, and personnel activities. Different types of element information also correspond to different structured element data.

[0085] For example, multiple different types of graphics elements can be preset in advance according to the equipment and specific scenarios included in the substation, and different structured graphics element data can be designed for different types of graphics elements, such as equipment status data, personnel behavior time series, etc. Then, when identifying graphics elements, deep learning computer vision technology can be used to perform in-depth analysis on the digital monitoring video data, such as using image recognition algorithms YOLOv3 or Mask R-CNN to identify key graphics elements such as equipment icons, operation instructions and personnel activities and mark the specific types of these graphics elements. The recognition results are then converted into structured data, such as equipment status data, personnel behavior time series, etc., which are convenient for real-time monitoring and management. In this embodiment, by performing classification and structured processing of graphics elements, different types of graphics element data can be effectively sorted out, thereby ensuring the efficiency and accuracy of subsequent abnormality identification.

[0086] In an exemplary embodiment, the method further includes: obtaining a primitive information display mode; performing page generation processing based on the structured primitive data and the primitive information display mode to obtain a primitive display information page; pushing the primitive display information page; and obtaining alarm threshold information based on feedback from the primitive display information page. Step 207 includes: in the case where it is determined that the structured primitive data contains monitoring abnormality data based on the abnormality detection result and the alarm threshold information, generating monitoring alarm information based on the monitoring abnormality data.

[0087] Among them, the image source information display mode refers to the method of displaying different types of identified image element information, such as real-time video stream, equipment status icon and text description, etc. The alarm threshold information is the alarm threshold set by the user based on the actual display of the image element information, so as to ensure that the alarm can adapt to the specific situation of the current substation.

[0088] Exemplarily, the solution of the present application also provides data display and interaction functions. By designing a user-friendly interface, the identified video element information is presented in an intuitive way, such as real-time video stream, device status icon and text description. Users can perform real-time monitoring based on the pushed element display information page, such as zooming in, switching monitoring points, viewing historical records, etc., and interactive functions are provided, such as marking important events, setting alarm thresholds, etc. Therefore, in subsequent alarms, the detected abnormal detection results and alarm threshold information can be combined for alarm identification. Only when an abnormality occurs and the abnormality exceeds the set alarm threshold, it will be determined that the structured element data contains monitoring abnormality data, and then the monitoring alarm information is generated according to the monitoring abnormality data. In this embodiment, an intuitive user interface is provided through the element display information page, which is convenient for users to perform monitoring operations and alarm settings, thereby improving the accuracy and real-time performance of the alarm process.

[0089] In one embodiment, pushing the graphic element display information page includes: compressing and encrypting the graphic element display information page to obtain display information encrypted data; and pushing the graphic element display information page based on the display information encrypted data.

[0090] Exemplarily, for the data transmission process, in addition to directly displaying the graphic element information on the processing terminal, the present application can also upload the graphic element information to a remote server. At this time, it is necessary to compress and encrypt the relevant data content of the graphic element display information page to be uploaded. By adopting efficient data compression and encryption technology, the secure transmission of graphic element information is ensured. The communication process supports a variety of communication protocols and network environments to ensure that data can be transmitted stably under different network conditions. At the same time, the process also has data synchronization and backup functions to ensure the integrity and reliability of monitoring data. For encryption processing, efficient Zstandard or TLS encryption technology can be used to ensure the security and integrity of video graphic element information during transmission. In this embodiment, the security and efficiency of graphic element display information during remote transmission can be effectively guaranteed through encryption and compression processing of graphic element data.

[0091] In an exemplary embodiment, the method also includes: obtaining historical surveillance video data; performing graphic element recognition processing on the historical surveillance video data to obtain training graphic element data; performing abnormal category labeling processing on the training graphic element data to obtain model training data; and performing model training on the initial abnormality recognition model based on the model training data to obtain a preset abnormality recognition model.

[0092] Exemplarily, the present application also includes a training process for an anomaly recognition model. During training, an initial anomaly recognition model can be constructed based on a deep learning algorithm. Then, historical monitoring video data is collected to construct training samples, and then various types of training image metadata are extracted through image recognition processing. The training image metadata is then annotated with abnormal categories to obtain model training data. If there is no abnormality, it is directly marked as no abnormality, and if there is an abnormality, the corresponding abnormality type needs to be annotated. The annotated model training data is then divided into a training set and a test set, and these model training data are used to supervise the initial anomaly recognition model to obtain a preset anomaly recognition model. In this embodiment, the training process of the anomaly recognition model is completed by collecting historical monitoring data, which can effectively ensure the efficiency of the model training process and ensure the accuracy of anomaly recognition.

[0093] In an exemplary embodiment, step 207 includes: extracting the exception type and exception occurrence time corresponding to the monitoring exception data; searching for structured metadata corresponding to the monitoring exception data; and generating monitoring alarm information based on the exception type, exception occurrence time and structured metadata corresponding to the monitoring exception data.

[0094] For example, in the abnormal alarm processing process, when an abnormal situation is detected and an alarm is required, detailed alarm information will be generated immediately, including the abnormal type and occurrence time. At the same time, in order to ensure the completeness of the information in the abnormal alarm process, the primitives involved in the monitoring abnormal data can also be found. These alarm information will be pushed to the user quickly to ensure that the user can respond quickly and handle it in time, effectively avoiding potential security risks.

[0095] In one embodiment, in order to realize the monitoring and alarm of the substation, a high-definition camera network corresponding to the substation can be pre-designed. These cameras are precisely installed around key equipment, such as switch cabinets, transformers, etc., to form a full range of monitoring coverage. The specific process of the substation alarm method based on primitive monitoring in this application is referred to in Figure 4 As shown, including:

[0096] Element recognition stage: The element recognition module uses deep learning computer vision technology to conduct in-depth analysis of digital video signals and uses image recognition algorithms YOLOv3 or Mask R-CNN to identify key elements such as equipment icons, operation instructions, and personnel activities. The recognition results are converted into structured data, such as equipment status data, personnel behavior time series, etc., to facilitate real-time monitoring and management.

[0097] Data display and interaction: Through the simple and intuitive client display interface, users can clearly view real-time video streams, equipment status icons and detailed text descriptions, such as the operating status of equipment, personnel activity areas, etc. Users can monitor the substation situation in real time and perform various operations through the interface, such as zooming in to view details, switching monitoring points to fully understand the situation, marking important events and setting alarm thresholds to improve user experience and the ability to respond to emergencies.

[0098] Anomaly detection and analysis: The data processing module uses deep learning models to continuously learn and analyze primitive information. Once an abnormal operation of equipment or a deviation from normal operation is detected, the anomaly detection algorithm will be immediately activated. The anomaly detection results will be fed back to other related modules in real time so that timely countermeasures can be taken to ensure the safe and stable operation of the substation. The anomaly detection results will be fed back to other modules in real time so that timely countermeasures can be taken.

[0099] Alarm triggering and notification: The alarm module is designed to respond in real time. Once an abnormal situation is detected, detailed alarm information will be immediately generated, including the type of abnormality, the time of occurrence, the involved graphics, etc. These alarm information will be quickly pushed to the user through the client display module to ensure that the user can respond quickly and handle it in time, effectively avoiding potential security risks.

[0100] Data transmission and control: The communication module uses efficient Zstandard or TLS encryption technology to ensure the security and integrity of video element information during transmission. At the same time, the module supports two-way communication, allowing the client to upload monitoring data to the cloud server and receive remote operation instructions from the server, realizing remote monitoring and management of the substation, improving work efficiency and convenience.

[0101] It should be understood that, although the steps in the flowcharts involved in the above 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 is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may 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 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.

[0102] Based on the same inventive concept, the embodiment of the present application also provides a substation alarm system based on graphic element monitoring for implementing the substation alarm method based on graphic element monitoring involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the substation alarm system based on graphic element monitoring provided below can refer to the limitations of the substation alarm method based on graphic element monitoring above, and will not be repeated here.

[0103] In an exemplary embodiment, Figure 5 As shown, a substation alarm system based on graphic element monitoring is provided, comprising:

[0104] The data acquisition module 502 is used to acquire monitoring video data of the substation.

[0105] The graphic element recognition module 504 is used to perform graphic element recognition processing on the monitoring video data to obtain structured graphic element data.

[0106] The anomaly detection module 506 is used to input the structured graph metadata into a preset anomaly recognition model to obtain anomaly detection results corresponding to the monitoring video data. The preset anomaly recognition model is trained based on the structured graph metadata in the historical data.

[0107] The alarm information generating module 508 is used to generate monitoring alarm information according to the monitoring abnormality data when it is determined based on the abnormality detection result that the structured graph metadata contains monitoring abnormality data.

[0108] The alarm information push module 510 is used to push monitoring alarm information.

[0109] In one embodiment, the primitive recognition module 504 is specifically used for: performing primitive recognition processing on the surveillance video data to identify the target key primitives in the surveillance video data; determining the primitive type corresponding to the target key primitive; and converting the corresponding target key primitive into structured primitive data based on the primitive type.

[0110] In one embodiment, an information display module is further included, which is used to: obtain a primitive information display mode; perform page generation processing based on the structured primitive data and the primitive information display mode to obtain a primitive display information page; push the primitive display information page; and obtain alarm threshold information based on the primitive display information page feedback. The alarm information generation module 508 is specifically used to: generate monitoring alarm information according to the monitoring abnormality data when it is determined that the structured primitive data contains monitoring abnormality data based on the abnormality detection result and the alarm threshold information.

[0111] In one embodiment, the information display module is specifically used to: compress and encrypt the graphic element display information page to obtain display information encrypted data; and push the graphic element display information page based on the display information encrypted data.

[0112] In one embodiment, a model training module is also included, which is used to: obtain historical monitoring video data; perform graphic element recognition processing on the historical monitoring video data to obtain training graphic element data; perform abnormal category labeling processing on the training graphic element data to obtain model training data; and perform model training on the initial abnormality recognition model based on the model training data to obtain a preset abnormality recognition model.

[0113] In one embodiment, the alarm information generation module 508 is specifically used to: extract the exception type and exception occurrence time corresponding to the monitoring exception data; search for structured metadata corresponding to the monitoring exception data; and generate monitoring alarm information based on the exception type, exception occurrence time and structured metadata corresponding to the monitoring exception data.

[0114] Each module in the above-mentioned substation alarm system based on graphic element monitoring can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0115] 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 6As 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 substation alarm method based on primitive monitoring is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0116] Those skilled in the art will understand that Figure 6 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.

[0117] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0118] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0119] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0120] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0121] 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.

[0122] 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.

[0123] 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 substation alarm method based on graphic element monitoring, characterized in that: include: Obtain monitoring video data of the substation; Performing image element recognition processing on the surveillance video data to obtain structured image element data; Inputting the structured graph metadata into a preset anomaly recognition model to obtain an anomaly detection result corresponding to the monitoring video data, wherein the preset anomaly recognition model is trained based on the structured graph metadata in the historical data; In the case where it is determined based on the abnormality detection result that the structured graph metadata contains monitoring abnormality data, generating monitoring alarm information according to the monitoring abnormality data; Push the monitoring alarm information.

2. The method according to claim 1, characterized in that The step of performing image element recognition processing on the surveillance video data to obtain structured image element data includes: Performing image element recognition processing on the surveillance video data to identify target key image elements in the surveillance video data; Determine the primitive type corresponding to the target key primitive; Based on the primitive type, the corresponding target key primitive is converted into structured primitive data.

3. The method according to claim 1, characterized in that The method further comprises: Get the display mode of the graphic element information; Performing page generation processing based on the structured graphic element metadata and the graphic element information display mode to obtain a graphic element display information page; Pushing the graphic element display information page; Obtaining alarm threshold information based on feedback from the graphic element display information page; In the case where it is determined based on the abnormality detection result that the structured graph metadata includes monitoring abnormality data, generating monitoring alarm information according to the monitoring abnormality data includes: When it is determined that the structured graph metadata contains monitoring abnormality data based on the abnormality detection result and the alarm threshold information, monitoring alarm information is generated according to the monitoring abnormality data.

4. The method according to claim 3, characterized in that: The pushing of the graphic element display information page includes: Compressing and encrypting the graphic element display information page to obtain display information encrypted data; The graphic element display information page is pushed based on the display information encrypted data.

5. The method according to claim 1, characterized in that The method further comprises: Obtain historical surveillance video data; Performing image element recognition processing on the historical monitoring video data to obtain training image element data; Perform abnormal category labeling processing on the training graph metadata to obtain model training data; Model training is performed on the initial abnormality recognition model based on the model training data to obtain a preset abnormality recognition model.

6. The method according to claim 1, characterized in that The generating monitoring alarm information according to the monitoring abnormal data comprises: Extracting the abnormality type and abnormality occurrence time corresponding to the monitoring abnormality data; Searching for structured graph metadata corresponding to the monitoring abnormal data; Generate monitoring alarm information according to the abnormality type, the abnormality occurrence time and the structured graph metadata corresponding to the monitoring abnormality data.

7. A substation alarm system based on graphic element monitoring, characterized in that: include: A data acquisition module, used to acquire monitoring video data of the substation; A graphic element recognition module is used to perform graphic element recognition processing on the monitoring video data to obtain structured graphic element data; An anomaly detection module, used to input the structured graph metadata into a preset anomaly recognition model to obtain an anomaly detection result corresponding to the monitoring video data, wherein the preset anomaly recognition model is trained based on the structured graph metadata in the historical data; An alarm information generating module, configured to generate monitoring alarm information according to the monitoring abnormality data when it is determined based on the abnormality detection result that the structured graph metadata contains monitoring abnormality data; The alarm information push module is used to push the monitoring alarm information.

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