A device panel diagram intelligent generation method, device and apparatus

Abstract

The application provides a device panel diagram intelligent generation method and device, and equipment. The method comprises the following steps: according to a device model of a to-be-processed device, querying panel model information that has been constructed, and determining target panel model information matched with the device model of the to-be-processed device; according to real-time state information of a panel entity of the to-be-processed device, determining, from panel entity information included in the target panel model information, target panel entity image elements matched with the real-time state information of the panel entity; and generating a real-time device panel diagram of the to-be-processed device according to panel frame information of the to-be-processed device, arrangement information of the panel entity, and the target panel entity image elements. The method can improve the efficiency of fault troubleshooting and processing.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method, apparatus and device for intelligent generation of device panel diagrams. Background Technology

[0002] In the field of equipment management, device panels are crucial for displaying equipment status information, enabling maintenance personnel to quickly grasp the operational status of equipment. Currently, traditional device panel diagrams are mostly drawn manually or generated based on fixed templates. Manual drawing is inefficient when dealing with various equipment models or hardware changes, requiring repeated drawing; fixed templates lack flexibility and are difficult to adapt to the personalized layouts and real-time status changes of different devices, for example, they cannot accurately display the unique interface and indicator light designs of new network devices.

[0003] Furthermore, panel diagrams generated using traditional methods are typically static displays, failing to reflect the real-time operating status and data changes of the equipment. Maintenance personnel must rely on additional tools or systems to obtain real-time information, increasing operational complexity and time costs. For example, when device port traffic changes or indicator light statuses shift, static panel diagrams cannot be updated promptly, affecting maintenance personnel's intuitive judgment of the equipment's status and potentially delaying troubleshooting and resolution.

[0004] Existing technologies also include solutions for customizing the panel of each device, but this approach requires independent development and testing for each device, resulting in a large workload, long delivery cycle, and high cost. Summary of the Invention

[0005] In view of this, this application provides a method, apparatus, and device for intelligent generation of device panel diagrams, so as to improve the efficiency and flexibility of device panel diagram generation.

[0006] According to a first aspect of the embodiments of this application, a device panel diagram intelligent generation method is provided, comprising: Based on the device model of the device to be processed, query the constructed panel model information to determine the target panel model information that matches the device model of the device to be processed; wherein, the panel model information includes panel frame information and panel entity information for various device models; the panel entity information includes the arrangement information and image elements of the panel entities; different states of the same panel entity correspond to different image elements; Based on the real-time status information of the panel entity of the device to be processed, the target panel entity image element that matches the real-time status information of the panel entity is determined from the panel entity information included in the target panel model information. Based on the panel frame information, panel entity layout information, and target panel entity image elements of the device to be processed, a real-time device panel diagram of the device to be processed is generated.

[0007] According to a second aspect of the embodiments of this application, a device panel diagram intelligent generation apparatus is provided, comprising: The query unit is used to query the constructed panel model information based on the device model of the device to be processed, and determine the target panel model information that matches the device model of the device to be processed; wherein, the panel model information includes panel frame information and panel entity information for various device models; the panel entity information includes the arrangement information and image elements of the panel entities; different states of the same panel entity correspond to different image elements; The determining unit is used to determine, based on the real-time status information of the panel entity of the device to be processed, a target panel entity image element that matches the real-time status information of the panel entity from the panel entity information included in the target panel model information. The generation unit is used to generate a real-time device panel diagram of the device to be processed based on the panel frame information, panel entity arrangement information, and target panel entity image elements of the device to be processed.

[0008] By applying the embodiments of this application, based on the device model of the device to be processed, the constructed panel model information is queried to determine the target panel model information that matches the device model of the device to be processed. Based on the real-time status information of the panel entities of the device to be processed, the target panel entity image elements that match the real-time status information of the panel entities are determined from the panel entity information included in the target panel model information. Then, based on the panel frame information, the arrangement information of the panel entities, and the target panel entity image elements of the device to be processed, a real-time device panel diagram of the device to be processed is generated. By pre-constructing panel models of at least a variety of device models and generating device panel diagrams of corresponding device models based on the constructed panel models, the efficiency and flexibility of device panel diagram generation are improved. In addition, by setting different image elements for different states of the same panel entity in the panel model, during the device panel generation process, matching image elements can be selected for the panel entities based on the real-time status information of the panel entities and reflected in the generated device panel diagram. Thus, relevant personnel can know the real-time status of the panel entities based on the real-time device panel diagram of the device to be processed, improving the efficiency of fault diagnosis and handling. Attached Figure Description

[0009] Figure 1 This is a schematic flowchart of a device panel diagram intelligent generation method provided in an embodiment of this application; Figure 2 This is a schematic diagram of an intelligent generation process for a device panel diagram provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a device panel diagram intelligent generation device provided in an embodiment of this application; Figure 4 This is a schematic diagram of another device panel diagram intelligent generation device provided in the embodiments of this application; Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0010] To enable those skilled in the art to better understand the technical solutions in the embodiments of this application, some technical terms involved in the embodiments of this application will be explained below.

[0011] 1. SNMP (Simple Network Management Protocol): Used for monitoring and managing network devices (such as routers, switches, and servers).

[0012] 2. XML (eXtensible Markup Language): A text format used for storing and transmitting structured data.

[0013] 3. JSON (JavaScript Object Notation): A lightweight data interchange format derived from JavaScript and now widely used in web development.

[0014] 4. CLI (Command-Line Interface): An interface for interacting with a computer through text commands.

[0015] 5. ResNet (Residual Network): Deep learning (computer vision), a deep convolutional neural network architecture proposed by Microsoft Research.

[0016] 6. Inception (also known as GoogLeNet): Deep learning (computer vision), a convolutional neural network architecture proposed by Google.

[0017] 7. Softmax: A mathematical function used to transform any real vector into a probability distribution. It is often used as the activation function of the output layer of a neural network to solve multi-classification problems (such as identifying the category of objects in an image).

[0018] 8. Canny Edge Detection: A classic image processing algorithm used to extract sharp, continuous edges from images. It is one of the most commonly used edge detection methods in computer vision, widely applied in object detection, image segmentation, and other fields.

[0019] To make the above-mentioned objectives, features and advantages of the embodiments of this application more apparent and understandable, the technical solutions of the embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0020] Please see Figure 1 This is a flowchart illustrating a method for intelligently generating device panel diagrams according to an embodiment of this application. Figure 1 As shown, the intelligent generation method for device panel diagrams may include the following steps: Step 101: Based on the device model of the device to be processed, query the constructed panel model information to determine the target panel model information that matches the device model of the device to be processed; wherein, the panel model information includes panel frame information and panel entity information of at least one device model; the panel entity information includes the arrangement information and image elements of the panel entities; different states of the same panel entity correspond to different image elements.

[0021] For example, the layout information of the panel entities may include the spatial distribution data of the various entity components constituting the device panel on a two-dimensional plane, which may include, but is not limited to, some or all of the information such as the position coordinates (e.g., pixel coordinates), arrangement order, alignment method, adjacent spacing, and the size (width, height, shape) of each entity itself.

[0022] For example, an object detection algorithm identifies the bounding box of each entity, which records the top-left corner coordinates (x, y), width w, and height h of the entity. Furthermore, based on the coordinates and dimensions of each bounding box, the horizontal / vertical spacing, arrangement order, and alignment relationships between entities can be calculated, thus obtaining complete layout information.

[0023] For example, the image elements of an entity can be included in the generated panel diagram as graphical information to express the appearance characteristics of a device entity (such as a port, indicator light, board, etc.). This information may include, but is not limited to, some or all of the entity's shape, color, fill style, border style, icon, text label, color or flashing mode of status indicator light, etc.

[0024] For example, panel frame information may include geometric and spatial data extracted from the device panel image to describe the panel structure frame. This may include, but is not limited to, some or all of the information such as the outer boundary contour of the device panel, the geometric feature parameters of the device panel (such as the total area and perimeter of the device panel), the position and direction of the main internal dividing lines, and the size (width, height, area) and shape of each enclosed sub-region (such as the functional area and the display area).

[0025] In this embodiment, panel models of device panels for various device models can be pre-built. During the generation of the device panel diagram, the panel model information that has been built can be queried based on the device model of the device to be processed (i.e., the device for which the device panel diagram needs to be generated), and the panel model information that matches the device model of the device to be processed (which can be called the target panel model information) can be determined.

[0026] In this embodiment of the application, the panel model information may include panel frame information and panel entity information.

[0027] The panel entity information may include the arrangement of panel entities and image elements.

[0028] In order for the panel diagram to reflect the different states of the panel entity, different states of the same panel entity can correspond to different image elements. Therefore, the state of the panel entity can be determined based on the image elements of the panel entity in the panel diagram.

[0029] Step 102: Based on the real-time status information of the panel entity of the device to be processed, determine the target panel entity image element that matches the real-time status information of the panel entity from the panel entity information included in the target panel model information.

[0030] In this embodiment of the application, during the generation of the device panel diagram, real-time status information of the panel entity of the device to be processed can be obtained, and based on the real-time status information of the panel entity of the device to be processed, panel entity image elements (which can be referred to as target panel entity image elements) that match the real-time status information of the panel entity are determined from the panel entity information included in the target panel model information.

[0031] For example, data can be collected from the device to be processed at regular intervals to determine the real-time status information of the panel entity of the device to be processed.

[0032] Step 103: Generate a real-time device panel diagram of the device to be processed based on the panel frame information, panel entity layout information, and target panel entity image elements of the device to be processed.

[0033] In this embodiment of the application, after determining the panel frame information, panel entity layout information, and target panel entity image elements of the device to be processed in the manner described above, a real-time device panel diagram of the device to be processed can be generated based on the determined panel frame information, panel entity layout information, and target panel entity image elements. Thus, relevant personnel can obtain the real-time status of the panel entities based on the real-time device panel diagram of the device to be processed, thereby improving the efficiency of fault diagnosis and processing.

[0034] It should be noted that, in the embodiments of this application, the device panel may include the front panel, rear panel or side panel of the device to be processed. For any panel of any device to be processed, a real-time device panel diagram can be generated according to the scheme provided in the embodiments of this application.

[0035] It can be seen that, in Figure 1 In the illustrated method, based on the device model of the device to be processed, the pre-constructed panel model information is queried to determine the target panel model information that matches the device model of the device to be processed. Then, based on the real-time status information of the panel entities of the device to be processed, the target panel entity image elements that match the real-time status information of the panel entities are determined from the panel entity information included in the target panel model information. Subsequently, based on the panel frame information, panel entity arrangement information, and target panel entity image elements of the device to be processed, a real-time device panel diagram of the device to be processed is generated. By pre-constructing panel models of at least several device models and generating corresponding device panel diagrams based on the constructed panel models, the efficiency and flexibility of device panel diagram generation are improved. Furthermore, by setting different image elements for different states of the same panel entity in the panel model, during the device panel generation process, matching image elements can be selected for the panel entity based on the real-time status information of the panel entity and reflected in the generated device panel diagram. Thus, relevant personnel can obtain the real-time status of the panel entities based on the real-time device panel diagram of the device to be processed, improving the efficiency of fault diagnosis and handling.

[0036] In some embodiments, the real-time status information of the panel entity of the device to be processed is obtained in the following ways: A data interaction channel is established with the device under test through a designated communication interface; the designated communication interface may be a standard network management protocol interface or a customized access interface driven by the device's private communication protocol. Based on the type of communication interface, an information retrieval request is sent to the device to be processed using an access method that matches that interface. Receive the response returned by the device to be processed, and parse it to obtain the real-time operating status information of the panel entity of the device to be processed; Based on the real-time operating status information of the panel entity of the device to be processed, determine the real-time status of the corresponding panel entity.

[0037] For example, in order to obtain the real-time status information of the panel entity of the device to be processed, a data interaction channel can be established with the device to be processed through a specified communication interface.

[0038] The communication interface can be a standard network management protocol interface (such as an SNMP interface or a CLI interface) or a custom access interface driven by a proprietary communication protocol.

[0039] Information retrieval requests can be sent using a matching access method based on the interface type.

[0040] For example, for devices that support standard network management protocols, pre-configured protocol parameters can be collected, such as the SNMP community string and port number, or the CLI username / password. The system retrieves the value corresponding to the specified OID through SNMP GET / GETNEXT operations, or sends a preset command through CLI. After the device returns a response, the system parses the SNMP variable bindings or CLI text output, extracts the real-time operating status information of the panel entity of the device to be processed, and converts it into a unified format for storage.

[0041] For devices that do not support standard protocols, a driver or acquisition tool developed according to the device's proprietary communication protocol specification can be loaded. This driver is responsible for establishing the underlying connection (such as a serial port or a custom TCP port) and encapsulating the information acquisition request according to the proprietary protocol's data frame format, for example, constructing a byte stream containing command codes and checksums. After receiving the raw response from the device, the driver parses the real-time operating status information of the device's panel entity according to the protocol rules and then reports it to the upper-layer monitoring module.

[0042] For example, in order to improve the real-time performance and accuracy of data acquisition, data can be collected periodically at preset time intervals (such as 5 seconds).

[0043] For example, the real-time operating status information of the panel entity of the device to be processed may include, but is not limited to, at least one of the following: port traffic information, board temperature information, and power status information.

[0044] Based on the real-time operating status information of the panel entity of the device to be processed, the real-time status of the corresponding panel entity can be determined.

[0045] In one example, determining the real-time status of the corresponding panel entity based on the real-time operating status information of the panel entity of the device to be processed may include: For port-type panel entities, the status of the panel entity is determined based on the real-time port traffic information of the panel entity and the preset traffic threshold.

[0046] For example, the state of a port-type panel entity includes a fault state (Down) or a normal state (UP), and in the normal state, multiple different states corresponding to different port traffic ranges.

[0047] For example, for panel entities of port type, traffic thresholds corresponding to different states can be preset. For instance, traffic overload thresholds for different types of ports can be set (e.g., a 100Mbps port is considered overloaded if its traffic exceeds 80Mbps, and a 1Gbps port is considered overloaded if its traffic exceeds 800Mbps).

[0048] Accordingly, for any port type of panel entity, the panel entity can be determined to be in a fault state or a normal state based on the real-time operating status information of the panel entity obtained from the device to be processed. If the panel entity is in a normal state, the state of the panel entity can be further determined based on the real-time port traffic information of the panel entity and a preset traffic threshold. This state can include some or all of the states such as idle state, light load state, normal state, and overload state.

[0049] For example, for a 100Mbps port, if the real-time port traffic of the panel entity exceeds 80Mbps, the panel entity can be determined to be in an overload state.

[0050] In one example, determining the real-time status of the corresponding panel entity based on the real-time operating status information of the panel entity of the device to be processed may include: For board-type panel entities, the state of the panel entity is determined based on the real-time temperature information of the panel entity and a preset trend prediction algorithm.

[0051] For example, the state of a board-type panel entity includes a normal state or an abnormal state, and, in the normal state, multiple different states corresponding to different temperature ranges.

[0052] For example, for board-type panel entities, the temperature change trend can be predicted by combining the device's hardware specifications and operating environment, and algorithms such as linear regression or multinomial regression can be used to determine whether the panel entity's temperature is abnormal.

[0053] If the temperature of the panel entity is determined to be normal (i.e., the board status is normal), the status of the panel entity can be further determined based on the temperature information of the panel entity and the preset temperature threshold. This status can include some or all of the following: low temperature status, normal status, and high temperature status.

[0054] In one example, determining the real-time status of the corresponding panel entity based on the real-time operating status information of the panel entity of the device to be processed may include: For indicator light type panel entities, the state of the panel entity is determined based on the state of the associated target corresponding to the panel entity.

[0055] For example, the states of an indicator light type panel entity include an on state or an off state, and different color states when the light is on.

[0056] For example, considering that indicator lights on a device panel are typically associated with targets such as devices or ports to indicate the status of the associated target, such as a fault status or a normal status, the status of an indicator light-type panel entity can be determined based on the status of its associated target.

[0057] For example, for a panel entity of the indicator light type, the state transition conditions of the indicator light can be predefined (such as the transition from off to on may be due to device startup or fault recovery), and the state of the panel entity can be determined based on the state transition conditions of the indicator light and the operating status information of the associated target.

[0058] In some embodiments, generating a real-time device panel diagram of the device to be processed based on the panel frame information, panel entity arrangement information, and target panel entity image elements of the device to be processed may include: For a specified panel entity, data annotations are made on the specified panel entity in the real-time device panel diagram based on the real-time operating status information of the specified panel entity; wherein, the specified panel entity includes the panel entity that needs to display real-time operating status information.

[0059] For example, for a panel entity (which can be called a specified panel entity) that needs to display real-time operating status information (such as port traffic, board temperature, etc.), the specified panel entity can be labeled with data in the real-time device panel diagram based on the real-time operating status information of the specified panel entity.

[0060] For example, a graphics library (such as OpenCV) can be used to add text information to the generated device panel diagram to visually display real-time operating status information. For instance, port traffic values ​​can be added near the port image, in the format "traffic value Mbps".

[0061] In some embodiments, generating a real-time device panel diagram of the device to be processed based on the panel frame information, panel entity arrangement information, and target panel entity image elements of the device to be processed may include: Based on the real-time operating status information of the panel entities and the mapping relationship between preset data values ​​and display effects, the real-time display effect of the panel entities in the real-time device panel diagram of the device to be processed is determined.

[0062] For example, the mapping relationship between preset data values ​​and display effects can include the mapping relationship between preset data values ​​and different image elements of the panel entity.

[0063] For a panel entity, the mapped image element (different image elements can correspond to different states) can be determined based on the real-time operating status information of the panel entity. The matching image element is then determined as the real-time display effect of the panel entity in the real-time device panel diagram.

[0064] For example, the data annotations for a specified panel entity in the real-time device panel diagram can also be displayed with different effects based on different values.

[0065] For example, for temperature data, add temperature values ​​near the board image and change the color of the values ​​according to the temperature level, such as green for normal temperature, yellow for near-critical temperature, and red for above-critical temperature.

[0066] Accordingly, relevant configuration information for drawing data annotations and visualization effects can be pre-configured, such as color mapping tables and font styles.

[0067] For example, a color map can be used to record the mapping relationship between different data values ​​and different display effects, such as the mapping relationship between different data values ​​and different image elements, or the mapping relationship between different data values ​​and the colors of different labeled data, etc.

[0068] In some embodiments, panel model information is constructed in the following manner: For any device model's device panel, obtain the device panel image for that device type; A deep learning feature extraction model is used to extract features from a device panel image, and a classification model is used to perform entity recognition on the extracted features to obtain the panel entities in the device panel image; and, Extract panel frame information from the device panel image; Extract image elements corresponding to the identified panel entities from the device panel image and record the metadata of each image element; wherein, the metadata of the image element includes the position information of the image element in the device panel, the type of the entity to which it belongs and the corresponding panel entity state; the image elements corresponding to the same panel entity include: the image elements of the panel entity extracted from the panel images of the panel entity in different states; Based on the panel entities, panel frame information, image elements corresponding to the panel entities, and metadata of the image elements in the device panel image, construct the panel model for this device model.

[0069] For example, for any device model's device panel, during the process of building the panel model, the device panel image of that device type can be obtained.

[0070] For example, the device panel image can be captured by an image acquisition device and uploaded to the system.

[0071] For example, a high-definition camera can be used to photograph the device panel. During the photographing process, uniform lighting can be ensured to avoid the impact of shadows and reflections on image quality. For larger device panels, multiple perspective shots can be taken, and then image stitching algorithms can be used to combine multiple photos into a complete image of the device panel.

[0072] Upload the captured photos of the device panel to the system's designated storage location via the network or an external storage device. Upon receiving the image, the system can verify the image format (supporting common image formats such as JPEG and PNG). If the image format does not meet the requirements, the system can prompt the user to re-upload or perform a format conversion.

[0073] For example, once a device panel image that meets the requirements is obtained, on the one hand, a deep learning feature extraction model can be used to extract features from the device panel image, and on the other hand, a classification model can be used to perform entity recognition on the extracted features to obtain the panel entities in the device panel image.

[0074] For example, feature extraction can be performed using convolutional neural networks, taking the ResNet-50 model as an example. This model contains multiple convolutional layers, pooling layers, and residual blocks. The preprocessed input image first passes through a convolutional layer with a kernel size of 7×7 and a stride of 2. Subsequently, convolution operations are performed layer by layer, with the kernel size gradually decreasing to 1×1, and the stride adjusted according to the layer's requirements (the stride for deeper layers is typically 1). These convolutional operations extract local features of various entities in the image.

[0075] Pooling layers employ max pooling or average pooling to downsample the feature maps, reducing data dimensionality while preserving key features. In residual blocks, skip connections are used to add the input to the output after multiple convolutional layers, mitigating the vanishing gradient problem during deep network training and improving feature extraction performance.

[0076] The extracted features are fed into a trained classification model, which is trained on a large amount of labeled device panel image data.

[0077] For example, the classification model can use a Softmax classifier to classify features, outputting a probability value for each entity category, and selecting the category with the highest probability value as the recognition result. Thus, it can identify entities such as Ethernet ports, optical ports, circuit boards, power modules, and various indicator lights, as well as their order. For instance, the model can identify whether an Ethernet port is an RJ45 interface or an SFP+ interface and determine its arrangement order on the panel.

[0078] For example, during the model training and tuning phase, cross-validation methods (such as K-fold cross-validation, where K is 5 or 10) can be used to evaluate and tune the model to improve recognition accuracy.

[0079] In one example, the above-mentioned entity recognition using a classification model based on extracted features may include: For the identified panel entities, the identification results are corrected based on the spatial and / or logical relationships between the identified panel entities.

[0080] For example, to improve recognition accuracy, post-processing algorithms can be used to correct the recognition results of panel entities.

[0081] By analyzing the spatial and logical relationships between entities, potential misidentifications can be corrected.

[0082] For example, based on the device's design specifications and common layouts, such as Ethernet ports typically arranged in an array and optical ports potentially adjacent to specific types of boards, when two adjacent interfaces are identified, it can be determined whether their types and locations are logically consistent. If not, the identification results are rechecked.

[0083] For example, rule-based systems or machine learning algorithms (such as Conditional Random Fields, or CRFs) can be used to model the relationships between panel entities, thereby achieving more accurate correction of panel entity recognition results.

[0084] Having obtained a device panel image that meets the requirements, the panel frame information is then extracted from the device panel image.

[0085] In one example, the extraction of panel frame information from a device panel image as described above may include: Edge information of the device panel image is extracted using an edge detection algorithm, and connectivity is performed based on the strength of the edges to obtain the edge contour. The edge contour is optimized using morphological operations to obtain the optimized contour; The main frame outline of the device panel is selected from the optimized outline using the geometric features of the outline, and used as the panel frame.

[0086] For example, for the acquired device panel image, edge detection algorithms can be used to extract the edge information of the device panel image. For instance, the Canny edge detection algorithm can be used to extract the edge information of the image and perform connectivity connections based on the strength of the edge intensity.

[0087] For example, by setting a high threshold (e.g., 200) and a low threshold (e.g., 100), strong edges and weak edges are detected, and weak edges are connected to strong edges to form a complete edge profile.

[0088] The edge contour is optimized using morphological operations (such as dilation and erosion) to remove small noisy edges and fill holes in the contour, resulting in an optimized contour.

[0089] By utilizing the geometric features of the contour (such as area, perimeter, aspect ratio, etc.), the main frame contour of the device panel is selected from the optimized contour, thereby determining the panel boundary and main area division, which serves as the panel frame.

[0090] For example, for the acquired device panel image, the image elements corresponding to the identified panel entities can be extracted from the device panel image, and the metadata of each image element can be recorded.

[0091] For example, the metadata of an image element may include the image element's location information in the device panel, its entity type, and the corresponding panel entity state; the image element corresponding to the same panel entity includes: the image element of the panel entity extracted from the panel images of the panel entity in different states.

[0092] In one example, the process of extracting the image elements corresponding to the identified panel entities from the device panel image and recording the metadata of each image element may include: Using image segmentation algorithms, image elements corresponding to the identified panel entities are segmented from the device panel image and saved as independent image files; Record the metadata of each image element; the metadata also includes the filename corresponding to the image element.

[0093] For example, a panel model for the device model can be constructed based on the panel entity, panel frame information, image elements corresponding to the panel entity, and metadata of the image elements in the device panel image.

[0094] To enable those skilled in the art to better understand the technical solutions provided in the embodiments of this application, the technical solutions provided in the embodiments of this application are described below with reference to specific examples.

[0095] In this embodiment, a solution for intelligently generating device panel diagrams is provided, which achieves efficient, real-time, and accurate generation of device panels through the following improvements: 1) Precise image analysis and entity recognition: Utilizing advanced deep learning image recognition algorithms, the uploaded device panel photos are analyzed comprehensively and meticulously.

[0096] For example, during the algorithm training phase, a large amount of image data of different models of device panels is collected, covering various common and special device types. Various panel entities (such as Ethernet ports, optical ports, boards, stacking situations, power modules, various indicator lights, etc., hereinafter referred to as entities) are accurately labeled. The labeling content includes not only the entity type, but also its size, position, orientation and other detailed information.

[0097] The model is trained using mature convolutional neural networks such as ResNet and Inception. By adjusting parameters such as the number of network layers, kernel size, and stride, the model performance is optimized so that it can accurately identify various entities on the panel and their sorting methods.

[0098] 2) Flexible panel modeling and metadata management: Based on the identified entity information, targeted panel modeling is performed for each model of equipment.

[0099] The various image elements extracted from the image and the panel frame diagram are saved as metadata. The metadata can be saved in XML or JSON format, and details such as the file name, format, coordinate position in the panel, and entity type of each image element are recorded.

[0100] Furthermore, considering that various entities may exist in multiple states, corresponding image elements are generated for each entity state. For example, for the power module, image elements are generated for three states: "On (normal power supply)," "On (low battery)," and "Off." For indicator lights, image elements are generated for different states such as "On (solid green - normal)," "On (solid red - fault)," "Off," and "Blinking (blinking yellow - warning)." This meticulous modeling and metadata management approach enables the generated panel model to comprehensively and accurately reflect all possible states of the device.

[0101] 3) Real-time data acquisition and analysis: Establish a stable connection with the equipment, and collect the entity data information related to the panel reported by the equipment in real time through standardized data acquisition interfaces (such as SNMP, CLI, etc.) and custom acquisition protocols for special equipment.

[0102] For example, the collected data includes real-time port traffic, board operating temperature, power module battery percentage, and indicator light status.

[0103] Data analysis algorithms are used to process the collected data, accurately determine the real-time status of each entity, and provide a basis for real-time generation of panel diagrams.

[0104] 4) Real-time panel diagram generation: Based on the dynamic information and status of each entity obtained from the analysis, combined with the previously generated entity image elements and basic panel framework diagram, a panel diagram that can reflect real-time data and status is quickly generated.

[0105] For example, an automated image processing algorithm can be used to accurately embed the entity image elements of the corresponding state into the corresponding positions of the panel frame diagram, and the image elements can be appropriately adjusted according to real-time data.

[0106] For example, the color intensity of the port image can be changed according to the port traffic volume (the higher the traffic, the redder the color), or a traffic value indicator (in Mbps) can be added; for temperature data, temperature values ​​can be added near the board image, and the color of the values ​​can be changed according to the temperature (green for normal temperature, yellow for near critical temperature, and red for above critical temperature).

[0107] The device panel diagrams generated in the above manner can intuitively and in real time display the operating status of the equipment, providing maintenance personnel with accurate and timely visual information about the equipment, which greatly improves maintenance efficiency.

[0108] The implementation details of the intelligent generation device panel diagram are explained in detail below with reference to the accompanying drawings.

[0109] like Figure 2 As shown, the intelligent generation process for device panel diagrams may include: I. Acquisition and Uploading of Device Panel Images

[0110] 1.1 Image Acquisition: High-definition cameras are used to photograph the device panel. During the photographing process, uniform lighting is ensured to avoid the impact of shadows and reflections on image quality. For larger device panels, multiple perspective shots can be used, and then image stitching algorithms are employed to combine multiple photos into a complete image of the device panel.

[0111] 1.2 Image Upload: Upload the captured photo of the device panel to the system's designated storage location via the network or external storage device. Upon receiving the image, the system can verify the image format (supporting common image formats such as JPEG and PNG). If the image format does not meet the requirements, the system can prompt the user to re-upload or perform format conversion.

[0112] II. Image Analysis and Entity Recognition.

[0113] 2.1 Data Preprocessing: 2.1.1 Grayscale conversion: Converting a color image to a grayscale image reduces the amount of data while retaining key information of the image.

[0114] For example, a weighted average method can be used to convert a color image to a grayscale image.

[0115] For example, a color image can be converted to a grayscale image in the following way: Gray=0.299×R+0.587×G+0.114×B Where R, G, and B are the red, green, and blue channel values ​​of the color image, respectively.

[0116] 2.1.2 Noise Reduction: The image is denoised using a Gaussian filtering algorithm.

[0117] For example, define a Gaussian kernel function, select an appropriate Gaussian kernel size (such as 3x3, 5x5, etc.) and standard deviation (such as 1.0, 1.5, etc.) according to the image noise situation, and apply the Gaussian kernel to the image through convolution operation to remove Gaussian noise in the image.

[0118] 2.1.3 Normalization: Unify the pixel values ​​of the image to the range of [0, 1] to facilitate subsequent feature extraction and analysis.

[0119] For example, the pixel values ​​of an image can be standardized to the range [0, 1] in the following way. NormalizedPixel=(Pixel-MinPixel) / (MaxPixel-MinPixel) Where Pixel is the original pixel value, and MinPixel and MaxPixel are the minimum and maximum pixel values ​​in the image, respectively.

[0120] 2.2 Feature Extraction: Feature extraction is performed using convolutional neural networks.

[0121] Take the ResNet-50 model as an example. This model contains multiple convolutional layers, pooling layers, and residual blocks. The preprocessed input image first passes through a convolutional layer with a kernel size of 7×7 and a stride of 2. Then, convolution operations are performed layer by layer, with the kernel size gradually decreasing to 1×1, and the stride adjusted according to the layer's requirements (the stride for deeper layers is typically 1). These convolutional operations extract local features of various entities in the image.

[0122] Pooling layers employ max pooling or average pooling to downsample the feature maps, reducing data dimensionality while preserving key features. In residual blocks, skip connections are used to add the input to the output after multiple convolutional layers, mitigating the vanishing gradient problem during deep network training and improving feature extraction performance.

[0123] 2.3 Entity Recognition: The extracted features are input into a trained classification model, which is trained based on a large amount of labeled device panel image data.

[0124] For example, the classification model can use a Softmax classifier to classify features, outputting a probability value for each entity category, and selecting the category with the highest probability value as the recognition result. Thus, it can identify entities such as Ethernet ports, optical ports, circuit boards, power modules, and various indicator lights, as well as their order. For instance, the model can identify whether an Ethernet port is an RJ45 interface or an SFP+ interface and determine its arrangement order on the panel.

[0125] For example, during the model training and tuning phase, cross-validation methods (such as K-fold cross-validation, where K is 5 or 10) can be used to evaluate and tune the model to improve recognition accuracy.

[0126] 2.4 Result Correction: To improve the recognition accuracy, post-processing algorithms can be used to correct the recognition results of panel entities.

[0127] For example, potential misidentifications can be corrected by analyzing the spatial and logical relationships between entities.

[0128] For example, based on the device's design specifications and common layouts, such as Ethernet ports typically arranged in an array and optical ports potentially adjacent to specific types of boards, when two adjacent interfaces are identified, it can be determined whether their types and locations are logically consistent. If not, the identification results are rechecked.

[0129] For example, rule-based systems or machine learning algorithms (such as conditional random fields) can be used to model the relationships between panel entities, thereby achieving more accurate correction of panel entity recognition results.

[0130] III. Panel Modeling and Metadata Generation.

[0131] 3.1 Panel frame extraction: Extract panel frame information from the device panel image.

[0132] For example, the Canny edge detection algorithm can be used to extract edge information from an image and connect it based on the strength of the edge intensity.

[0133] For example, by setting a high threshold (e.g., 200) and a low threshold (e.g., 100), strong edges and weak edges are detected, and weak edges are connected to strong edges to form a complete edge profile.

[0134] The edge contour is optimized using morphological operations (such as dilation and erosion) to remove small noisy edges and fill holes in the contour, resulting in an optimized contour.

[0135] By utilizing the geometric features of the contour (such as area, perimeter, aspect ratio, etc.), the main frame contour of the device panel is selected from the optimized contour, thereby determining the panel boundary and main area division, which serves as the panel frame.

[0136] 3.2 Image Element Extraction and Saving: For the identified entities, extract the corresponding image elements from the device panel image and save them as metadata.

[0137] For example, image segmentation methods such as region growing algorithms or level set algorithms can be used to segment each entity from the image and save it as an independent image file (such as a PNG file), thus obtaining the image elements corresponding to each entity.

[0138] For example, for each entity, the corresponding image elements are extracted according to its different states. For instance, for an indicator light, image elements are extracted for its on, off, and flashing states.

[0139] For example, metadata information such as the position of each image element in the panel (represented by pixel coordinates), the type of entity it belongs to, and its status description can be recorded and saved as an XML or JSON file for easy access and management later.

[0140] 3.3 Model Construction: Based on the equipment model and the identified entity information, construct the panel model of the equipment model.

[0141] For example, object-oriented programming concepts can be used to define device classes, entity classes, etc. The device class contains attributes such as device model, panel frame information, and entity list, while the entity class contains attributes such as entity type, location, status, and corresponding image element file name.

[0142] For example, this information can be stored by establishing a data structure, such as using XML or JSON format, to facilitate subsequent operations and management of the model.

[0143] IV. Data Collection and Analysis.

[0144] 4.1 Data Acquisition: For devices supporting standard network management protocols, pre-configured protocol parameters can be collected, such as the SNMP community string and port number, or the CLI username / password. The system obtains the value corresponding to the specified OID through SNMP GET / GETNEXT operations, or sends preset commands through CLI. After the device returns a response, the system parses the SNMP variable bindings or CLI text output, extracts the real-time operating status information of the panel entity of the device under processing, and converts it into a unified format for storage.

[0145] For devices that do not support standard protocols, a driver or acquisition tool developed according to the device's proprietary communication protocol specification can be loaded. This driver is responsible for establishing the underlying connection (such as a serial port or a custom TCP port) and encapsulating the information acquisition request according to the proprietary protocol's data frame format, for example, constructing a byte stream containing command codes and checksums. After receiving the raw response from the device, the driver parses the real-time operating status information of the device's panel entity according to the protocol rules and then reports it to the upper-layer monitoring module.

[0146] For example, in order to improve the real-time performance and accuracy of data acquisition, data can be collected periodically at preset time intervals (such as 5 seconds).

[0147] 4.2 Data Analysis: Use data analysis algorithms to analyze the cleaned and transformed data and extract key information.

[0148] For example, for panel entities of port type, traffic thresholds corresponding to different states can be preset. For instance, traffic overload thresholds for different types of ports can be set (e.g., a 100Mbps port is considered overloaded if its traffic exceeds 80Mbps, and a 1Gbps port is considered overloaded if its traffic exceeds 800Mbps).

[0149] For board-type panel entities, temperature change trends can be predicted by combining the device's hardware specifications and operating environment, and algorithms such as linear regression or multinomial regression can be used to determine whether the panel entity's temperature is abnormal.

[0150] For panel entities of the indicator light type, the state transition conditions of the indicator light can be predefined (such as the transition from off to on may be due to device startup or fault recovery), and the state of the panel entity can be determined based on the state transition conditions of the indicator light and the state of the associated target.

[0151] V. Real-time device panel diagram generation.

[0152] 5.1 Panel Model Loading: Load the corresponding panel frame diagram and metadata from the stored panel model.

[0153] For example, the corresponding panel model can be retrieved from the model database based on the device model. For instance, the device model can be used as a keyword to search for the corresponding panel frame information and entity metadata in a JSON-formatted model file.

[0154] For example, configuration information for drawing data annotations and visualizations, such as color maps and font styles, can also be loaded.

[0155] 5.2 Element Replacement and Update: Based on the real-time status of each entity in the device, select the corresponding image element from the metadata to replace the corresponding position in the panel frame diagram.

[0156] For example, if the analysis shows that a certain indicator light is in the "on (red solid - fault)" state, then the image element at the position of that indicator light in the panel frame diagram will be replaced with the image in the "on (red solid - fault)" state.

[0157] For example, image editing libraries (such as Python's Pillow library) can be used to replace image elements, and new image elements can be pasted onto the panel frame diagram by specifying the coordinates and size of the image.

[0158] 5.3 Data Labeling and Visualization: For entities that require displaying specific data (such as port traffic, board temperature, etc.), data labeling is performed on the device panel diagram.

[0159] For example, you can use a graphics rendering library (such as OpenCV) to add text information to an image to visually display real-time data.

[0160] For example, add port traffic values ​​near the port image, in the format "traffic value Mbps".

[0161] For example, image elements can be visually adjusted based on the size and status of the data. For instance, the color intensity of the port image can be changed according to the port traffic volume, with higher traffic volumes resulting in a redder color; the color of temperature values ​​can be changed according to the board temperature, with normal temperatures in green, near-critical temperatures in yellow, and above-critical temperatures in red. For the power module's battery level, a power progress bar can be used for visualization, with the lower the battery level, the more red the progress bar becomes.

[0162] For example, a color map can be used to convert data to color. The color map predefines color values ​​according to different data ranges and states.

[0163] 5.4 Output Display: Output the generated real-time panel diagram to the specified display device or application interface for operation and maintenance personnel to view.

[0164] For example, it can support multiple output formats, such as PNG and JPEG, to adapt to different display needs.

[0165] For example, in the case of displaying on a webpage, the generated image file is converted to Base64 encoding format and embedded in the HTML page for display.

[0166] As can be seen, this embodiment achieves automated analysis of device panel images and rapid generation of real-time device panel diagrams. Maintenance personnel no longer need to spend a lot of time manually drawing panel diagrams or switching between multiple systems to search for device information; they can quickly and intuitively grasp the real-time status of the device simply by viewing the generated panel diagram.

[0167] Secondly, the generated panel diagrams can accurately and comprehensively reflect the real-time status of each entity on the device. Through carefully designed different image elements and flexible and diverse visualization adjustment methods, such as changing the color intensity according to port traffic and displaying corresponding image elements according to different indicator light states, maintenance personnel can have a clear understanding of the device's operating status at a glance.

[0168] Furthermore, on the one hand, the solution provided in this application completely eliminates the significant manpower costs and repetitive labor associated with manually drawing panel diagrams or using fixed templates. There is no need to assign dedicated personnel to spend considerable time drawing and updating panel diagrams, significantly reducing labor costs. On the other hand, the rapid and accurate fault diagnosis and problem-solving mechanism greatly reduces equipment downtime.

[0169] Finally, based on advanced deep learning image analysis technology, the solution provided in this application can accurately identify various entities on the device panels of different device models, customize highly accurate panel models for each device, and generate a rich variety of image elements for different states of the entities. This allows the generated panel models to perfectly adapt to various complex devices and diverse operating scenarios, offering better flexibility and accuracy compared to traditional fixed-pattern modeling methods.

[0170] The method provided in this application has been described above. The apparatus provided in this application is described below: Please see Figure 3 This is a schematic diagram of the structure of a device panel diagram intelligent generation device provided in an embodiment of this application, such as... Figure 3 As shown, the intelligent device for generating panel diagrams may include: The query unit is used to query the constructed panel model information based on the device model of the device to be processed, and determine the target panel model information that matches the device model of the device to be processed; wherein, the panel model information includes panel frame information and panel entity information for various device models; the panel entity information includes the arrangement information and image elements of the panel entities; different states of the same panel entity correspond to different image elements; The determining unit is used to determine, based on the real-time status information of the panel entity of the device to be processed, a target panel entity image element that matches the real-time status information of the panel entity from the panel entity information included in the target panel model information. The generation unit is used to generate a real-time device panel diagram of the device to be processed based on the panel frame information, panel entity arrangement information, and target panel entity image elements of the device to be processed.

[0171] In some embodiments, the determining unit is configured to obtain real-time status information of the panel entity of the device to be processed in the following manner: A data interaction channel is established with the device under test through a designated communication interface; wherein, the designated communication interface includes a standard network management protocol interface or a customized access interface driven by a device-specific communication protocol. Based on the type of the communication interface, an information retrieval request is sent to the device to be processed using an access method that matches the interface. Receive the response returned by the device to be processed, and parse it to obtain the real-time operating status information of the panel entity of the device to be processed; Based on the real-time operating status information of the panel entity of the device to be processed, the real-time status of the corresponding panel entity is determined.

[0172] In some embodiments, the determining unit determines the real-time status of a corresponding panel entity based on the real-time operating status information of the panel entity of the device to be processed, including: For a port-type panel entity, the status of the panel entity is determined based on the real-time port traffic information of the panel entity and the preset traffic threshold. The status of a port-type panel entity includes a fault status or a normal status, and in the normal status, multiple different statuses corresponding to different port traffic ranges. And / or, For board-type panel entities, the state of the panel entity is determined based on the real-time temperature information of the panel entity and a preset trend prediction algorithm; the state of the board-type panel entity includes a normal state or an abnormal state, and in the normal state, multiple different states corresponding to different temperature ranges. And / or, For indicator light type panel entities, the state of the panel entity is determined based on the state of the associated target corresponding to the panel entity; wherein, the state of the indicator light type panel entity includes an on state or an off state, and different color states in the on state.

[0173] In some embodiments, the generation unit generates a real-time device panel diagram of the device to be processed based on the panel frame information, panel entity arrangement information, and target panel entity image elements of the device to be processed, including: For a specified panel entity, data annotation is performed on the specified panel entity in the real-time device panel diagram based on the real-time operating status information of the specified panel entity; wherein, the specified panel entity includes panel entities that need to display real-time operating status information; And / or, Based on the real-time operating status information of the panel entity and the mapping relationship between preset data values ​​and display effects, the real-time display effect of the panel entity in the real-time device panel diagram of the device to be processed is determined.

[0174] In some embodiments, such as Figure 4 As shown, the intelligent device panel diagram generation device may further include: The model building unit is used to: acquire a device panel image for any device model; extract features from the device panel image using a deep learning feature extraction model and perform entity recognition on the extracted features using a classification model to obtain panel entities in the device panel image; extract panel frame information from the device panel image; extract image elements corresponding to the identified panel entities from the device panel image and record metadata for each image element; wherein, the metadata of the image element includes the position information of the image element in the device panel, the entity type to which it belongs, and the corresponding panel entity state; the image elements corresponding to the same panel entity include: image elements of the panel entity extracted from panel images of the panel entity in different states; and construct a panel model for the device model based on the panel entities, panel frame information, image elements corresponding to the panel entities, and metadata of the image elements in the device panel image.

[0175] In some embodiments, the model building unit uses a classification model to perform entity recognition on the extracted features, including: For the identified panel entities, the identification results are corrected based on the spatial and / or logical relationships between the identified panel entities.

[0176] In some embodiments, the model building unit extracts panel frame information from the device panel image, including: Edge information of the device panel image is extracted using an edge detection algorithm, and connectivity is performed based on the strength of the edge intensity to obtain the edge contour. The edge contour is optimized using morphological operations to obtain the optimized contour; The main frame outline of the device panel is selected from the optimized outline using the geometric features of the outline, and used as the panel frame.

[0177] In some embodiments, the model building unit extracts image elements corresponding to the identified panel entities from the device panel image and records metadata for each image element, including: Using an image segmentation algorithm, the image elements corresponding to the identified panel entities are segmented from the device panel image and saved as independent image files; Record the metadata of each image element; wherein, the metadata also includes the file name corresponding to the image element.

[0178] Please see Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. The electronic device may include a processor 501 and a machine-readable storage medium 502 storing machine-executable instructions. The processor 501 and the machine-readable storage medium 502 can communicate via a system bus 503. Furthermore, by reading and executing the machine-executable instructions in the machine-readable storage medium 502 corresponding to the intelligent generation logic of the device panel diagram, the processor 501 can execute the intelligent generation method of the device panel diagram described above.

[0179] The machine-readable storage medium 502 mentioned herein can be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as executable instructions, data, etc. For example, a machine-readable storage medium can be: RAM (Random Access Memory), volatile memory, non-volatile memory, flash memory, storage drive (such as hard disk drive), solid-state drive, any type of storage disk (such as optical disc, DVD, etc.), or similar storage media, or combinations thereof.

[0180] This application also provides a machine-readable storage medium including machine-executable instructions, such as... Figure 5 The machine-readable storage medium 502 in the message transmission device contains machine-executable instructions that can be executed by the processor 501 in the message transmission device to implement the device panel diagram intelligent generation method described above.

Claims

1. A method for intelligently generating device panel diagrams, characterized in that, include: Based on the device model of the device to be processed, query the constructed panel model information to determine the target panel model information that matches the device model of the device to be processed; wherein, the panel model information includes panel frame information and panel entity information for various device models; the panel entity information includes the arrangement information and image elements of the panel entities; different states of the same panel entity correspond to different image elements; Based on the real-time status information of the panel entity of the device to be processed, the target panel entity image element that matches the real-time status information of the panel entity is determined from the panel entity information included in the target panel model information. Based on the panel frame information, panel entity layout information, and target panel entity image elements of the device to be processed, a real-time device panel diagram of the device to be processed is generated.

2. The method according to claim 1, characterized in that, The real-time status information of the panel entity of the device to be processed is obtained through the following methods: A data interaction channel is established with the device under test through a designated communication interface; wherein, the designated communication interface includes a standard network management protocol interface or a customized access interface driven by a device-specific communication protocol. Based on the type of the communication interface, an information retrieval request is sent to the device to be processed using an access method that matches the interface. Receive the response returned by the device to be processed, and parse it to obtain the real-time operating status information of the panel entity of the device to be processed; Based on the real-time operating status information of the panel entity of the device to be processed, the real-time status of the corresponding panel entity is determined.

3. The method according to claim 2, characterized in that, The step of determining the real-time status of the corresponding panel entity based on the real-time operating status information of the panel entity of the device to be processed includes: For a port-type panel entity, the status of the panel entity is determined based on the real-time port traffic information of the panel entity and the preset traffic threshold. The status of a port-type panel entity includes a fault status or a normal status, and in the normal status, multiple different statuses corresponding to different port traffic ranges. And / or, For board-type panel entities, the state of the panel entity is determined based on the real-time temperature information of the panel entity and a preset trend prediction algorithm; the state of the board-type panel entity includes a normal state or an abnormal state, and in the normal state, multiple different states corresponding to different temperature ranges. And / or, For indicator light type panel entities, the state of the panel entity is determined based on the state of the associated target corresponding to the panel entity; wherein, the state of the indicator light type panel entity includes an on state or an off state, and different color states in the on state.

4. The method according to claim 1, characterized in that, The step of generating a real-time device panel diagram of the device to be processed based on the panel frame information, panel entity layout information, and target panel entity image elements of the device to be processed includes: For a specified panel entity, data annotation is performed on the specified panel entity in the real-time device panel diagram based on the real-time operating status information of the specified panel entity; wherein, the specified panel entity includes panel entities that need to display real-time operating status information; And / or, Based on the real-time operating status information of the panel entity and the mapping relationship between preset data values ​​and display effects, the real-time display effect of the panel entity in the real-time device panel diagram of the device to be processed is determined.

5. The method according to any one of claims 1-4, characterized in that, Panel model information is constructed in the following way: For any device model's device panel, obtain the device panel image for that device type; A deep learning feature extraction model is used to extract features from the device panel image, and a classification model is used to perform entity recognition on the extracted features to obtain the panel entities in the device panel image; and, Extract panel frame information from the device panel image; The image elements corresponding to the identified panel entities are extracted from the device panel image, and the metadata of each image element is recorded. The metadata of the image element includes the position information of the image element in the device panel, the type of the entity to which it belongs, and the corresponding panel entity state. The image elements corresponding to the same panel entity include: the image elements of the panel entity extracted from the panel images of the panel entity in different states. Based on the panel entity, panel frame information, image elements corresponding to the panel entity, and metadata of the image elements in the device panel image, a panel model for the device model is constructed.

6. The method according to claim 5, characterized in that, The entity recognition using the extracted features via a classification model includes: For the identified panel entities, the identification results are corrected based on the spatial and / or logical relationships between the identified panel entities.

7. The method according to claim 5, characterized in that, Extracting panel frame information from the device panel image includes: Edge information of the device panel image is extracted using an edge detection algorithm, and connectivity is performed based on the strength of the edge intensity to obtain the edge contour. The edge contour is optimized using morphological operations to obtain the optimized contour; The main frame outline of the device panel is selected from the optimized outline using the geometric features of the outline, and used as the panel frame.

8. The method according to claim 5, characterized in that, The step of extracting image elements corresponding to the identified panel entities from the device panel image and recording metadata for each image element includes: Using an image segmentation algorithm, the image elements corresponding to the identified panel entities are segmented from the device panel image and saved as independent image files; Record the metadata of each image element; wherein, the metadata also includes the file name corresponding to the image element.

9. A device for intelligently generating equipment panel diagrams, characterized in that, include: The query unit is used to query the constructed panel model information based on the device model of the device to be processed, and determine the target panel model information that matches the device model of the device to be processed; wherein, the panel model information includes panel frame information and panel entity information for various device models; the panel entity information includes the arrangement information and image elements of the panel entities; different states of the same panel entity correspond to different image elements; The determining unit is used to determine, based on the real-time status information of the panel entity of the device to be processed, a target panel entity image element that matches the real-time status information of the panel entity from the panel entity information included in the target panel model information. The generation unit is used to generate a real-time device panel diagram of the device to be processed based on the panel frame information, panel entity arrangement information, and target panel entity image elements of the device to be processed.

10. An electronic device, characterized in that, The method includes a processor and a machine-readable storage medium storing machine-readable instructions executable by the processor, which in turn cause the processor to perform the method as described in any one of claims 1-7.

Images