Communication device monitoring method, apparatus, terminal and storage medium

Abstract

The application provides a communication equipment monitoring method and device, a terminal and a storage medium, wherein the method comprises: optimizing a YOLO target detection model according to historical erection scene images; identifying real-time erection scene images according to the optimized YOLO target detection model, generating feature images and determining the equipment type of the communication equipment; searching historical fault images according to the equipment type of the communication equipment, judging whether the communication equipment has a fault risk according to the comparison result of the feature images and the historical fault images; when the communication equipment has a fault risk, generating prompt information and sending the prompt information to the personal terminal of a worker. The communication equipment monitoring method and device, the terminal and the storage medium provided by the application can replace manual identification of whether the communication equipment has a fault risk by using the YOLO target detection model, thereby reducing the maintenance difficulty of the worker and facilitating timely processing of potential risks.

Description

Technical Field

[0001] This invention belongs to the field of information technology, and in particular relates to a method, device, terminal and storage medium for monitoring communication equipment. Background Technology

[0002] With the rapid development of 5G technology, the penetration rate of related communication equipment is also increasing. To ensure that communication equipment maintains normal working capabilities, staff need to conduct regular inspections to promptly identify equipment malfunctions. During daily operation, small components of communication equipment (such as cables and antennas) inevitably suffer minor damage such as scratches and misalignment. While these minor damages do not directly cause equipment malfunctions, they leave visible marks on the exterior. As the equipment ages, these marks become potential risks for future malfunctions. Conventional inspection methods cannot detect such damage in a timely manner, thus failing to provide effective solutions.

[0003] Furthermore, as the scenarios continue to expand, communication equipment not only needs to be installed in densely populated areas such as cities and rural areas, but also in rugged mountainous areas or harsh desert transition zones. This will further increase the difficulty of inspections for staff and make it even more difficult for them to discover potential risks on the communication equipment. Summary of the Invention

[0004] In view of this, the present invention aims to provide a communication equipment monitoring method, apparatus, terminal and storage medium to solve the above-mentioned technical problems.

[0005] To achieve the above objectives, the technical solution created by this invention is implemented as follows:

[0006] In a first aspect, embodiments of the present invention provide a method for monitoring communication devices, including:

[0007] Acquire historical installation scene images of communication equipment, and optimize the YOLO target detection model based on the historical installation scene images;

[0008] Acquire real-time images of the communication equipment installation scene, identify the real-time installation scene images based on the optimized YOLO target detection model, generate feature images with anchor boxes marked with communication equipment, and determine the equipment type of the communication equipment.

[0009] Based on the equipment type of the communication equipment, search for historical fault images, and determine whether the communication equipment has a fault risk by comparing the feature image with the anchor box marked by the communication equipment with the historical fault images.

[0010] When there is a risk of communication equipment failure, a prompt message is generated and sent to the staff's personal terminal.

[0011] Furthermore, acquiring historical deployment scene images of the communication equipment includes:

[0012] Obtain the imaging ratio of historical installation scene images of communication equipment and the actual volume parameters of the communication equipment;

[0013] The optimization of the YOLO object detection model based on historical installation scene images includes:

[0014] Based on the imaging ratio of historical scene images and the actual volume parameters of the communication equipment, the initial anchor frame size of the YOLO target detection model is set.

[0015] Furthermore, acquiring historical deployment scene images of the communication equipment includes:

[0016] Acquire image clarity of historical deployment scenes of communication equipment;

[0017] The optimization of the YOLO object detection model based on historical installation scene images includes:

[0018] When the image clarity of historical installation scene images of communication equipment is less than the preset clarity threshold, the focus slice parameters of the YOLO object detection model are adjusted according to the amount of image noise.

[0019] Furthermore, the step of determining whether the communication device has a fault risk based on the comparison results between the feature image with the communication device marked with an anchor frame and the historical fault image includes:

[0020] Calculate the image similarity between the feature image with the anchor box marked by the communication device and the historical fault image. When the image similarity is greater than a preset similarity threshold, it is determined that the communication device has a fault risk.

[0021] Furthermore, based on the comparison results between the feature image with the communication device marked with an anchor frame and the historical fault images, it is determined whether the communication device has a fault risk:

[0022] Calculate the positional offset between the marked anchor frame and the communication device in the historical fault image. If the positional offset is less than a preset offset threshold, it is determined that the communication device has a fault risk.

[0023] Furthermore, after sending the notification information to the staff's personal terminal, the communication device monitoring method includes:

[0024] Obtain feedback information from staff, classify the fault risk of communication equipment according to the feedback information, generate a training image set based on the classification results and the feature images of communication equipment with fault risk, and perform deep training on the YOLO object detection model based on the training image set.

[0025] Furthermore, after generating a training image set based on the classification results and feature images of communication devices at risk of failure, the communication device monitoring method further includes:

[0026] Generate an extreme weather filter and add it as a filter layer to the training image set.

[0027] Secondly, embodiments of the present invention also provide a communication device monitoring apparatus, comprising:

[0028] The optimization module is used to acquire historical installation scene images of communication equipment and optimize the YOLO target detection model based on these images.

[0029] The generation module is used to acquire real-time installation scene images of communication equipment, identify the real-time installation scene images based on the optimized YOLO target detection model, generate feature images with anchor boxes marked by communication equipment, and determine the equipment type of the communication equipment.

[0030] The judgment module is used to search for historical fault images based on the equipment type of the communication equipment, and to determine whether the communication equipment has a fault risk based on the comparison results between the feature image with the anchor box marked by the communication equipment and the historical fault images.

[0031] The alert module is used to generate alert messages when there is a risk of communication equipment failure and send the alert messages to the staff's personal terminals.

[0032] Thirdly, embodiments of the present invention also provide a terminal, including:

[0033] One or more processors;

[0034] Storage device for storing one or more programs;

[0035] Imaging device, used to capture images;

[0036] When the one or more programs are executed by the one or more processors, the one or more processors implement the communication device monitoring method provided in the above embodiments.

[0037] Fourthly, embodiments of the present invention also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the communication device monitoring method provided in the above embodiments.

[0038] Compared with existing technologies, the communication device monitoring method, apparatus, terminal, and storage medium described in this invention have the following advantages:

[0039] This invention provides a communication equipment monitoring method, apparatus, terminal, and storage medium. It optimizes the YOLO target detection model based on historical deployment scene images, thereby improving the compatibility between the YOLO target detection model and communication equipment, and increasing the speed and accuracy of the YOLO target detection model in identifying communication equipment. Secondly, this invention can identify real-time deployment scene images based on the optimized YOLO target detection model, thus replacing manual monitoring of communication equipment. Furthermore, this invention can determine whether there are fault risks in the communication equipment based on the identification results of the optimized YOLO target detection model, thereby promptly identifying potential risks and facilitating effective handling by staff. Attached Figure Description

[0040] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments and descriptions of the invention are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0041] Figure 1 A flowchart of the communication device monitoring method described in Embodiment 1 of the present invention is provided;

[0042] Figure 2 A flowchart of the communication device monitoring method described in Embodiment 2 of the present invention is provided;

[0043] Figure 3 A flowchart of the communication device monitoring method described in Embodiment 3 of the present invention is provided;

[0044] Figure 4 A flowchart of the communication device monitoring method described in Embodiment 4 of the present invention is provided;

[0045] Figure 5 This invention provides a schematic diagram of the communication equipment monitoring device described in Embodiment 5 of the present invention.

[0046] Figure 6 The structural diagram of the terminal described in Embodiment Six of the present invention is shown. Detailed Implementation

[0047] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0048] Example 1

[0049] Figure 1 The flowchart of the communication device monitoring method provided in Embodiment 1 of the present invention specifically includes the following steps:

[0050] Step 110: Obtain historical installation scene images of the communication equipment, and optimize the YOLO target detection model based on the historical installation scene images.

[0051] Object detection technology is a computer vision technique that uses object detection models to find specific objects in an image. It can not only identify the types of these objects but also mark their locations for easier subsequent analysis. The YOLO object detection model described in this embodiment is a convolutional neural network structure. Compared to other neural networks with proposal boxes, the YOLO object detection model only needs to view the image once to find matching feature information and determine the target location, thus achieving higher recognition speed and accuracy.

[0052] To further improve the compatibility between the YOLO object detection model and communication devices, this embodiment optimizes the YOLO object detection model based on historical deployment scene images of the communication devices. Optionally, in this embodiment, the optimization of the YOLO object detection model can be achieved by optimizing the initial anchor frame size and the focus slice parameters.

[0053] When optimizing the YOLO target detection model by optimizing the initial anchor frame size, obtaining historical installation scene images of the communication equipment can be specifically optimized by: obtaining the imaging ratio of the historical installation scene images and the actual volume parameters of the communication equipment. Correspondingly, optimizing the YOLO target detection model based on the historical installation scene images can be specifically optimized by: setting the initial anchor frame size of the YOLO target detection model based on the imaging ratio of the historical installation scene images and the actual volume parameters of the communication equipment.

[0054] In the training process of traditional neural network models, predicted bounding boxes are typically output based on initial anchor boxes. These predicted boxes are then compared with the ground truth bounding boxes, the difference between them is calculated, and the network parameters are updated iteratively. Therefore, the initial anchor boxes are a crucial component. In this embodiment, since the volume of the communication device is constant and the position of the device used to acquire images does not change, the size of the image formed by the communication device is constant. The size of the image formed by the communication device can be determined based on its actual volume parameters and the imaging ratio of historical scene images. Setting the size of the initial anchor boxes based on this image size reduces the computational load of subsequent training, thereby improving the optimization efficiency of the YOLO object detection model.

[0055] When optimizing the YOLO object detection model by optimizing the focus slice parameters, obtaining historical installation scene images of the communication equipment can be specifically optimized by: improving the image clarity of these historical installation scene images. Correspondingly, optimizing the YOLO object detection model based on these historical installation scene images can be specifically optimized by: adjusting the focus slice parameters of the YOLO object detection model according to the amount of image noise when the image clarity of the historical installation scene images of the communication equipment is less than a preset clarity threshold.

[0056] It's important to note that the Focus layer is a special downsampling method in YOLO, typically used to extract associated features from images and convert them into corresponding high-dimensional information. In practice, adjacent features are stacked in different channels to form multi-dimensional information, and then a slicing operation is used to split the high-resolution image (feature map) into multiple low-resolution images / feature maps. Traditionally, interlaced slicing is used. However, since the images acquired in this embodiment are affected by external environmental factors (such as light intensity, rain, snow, and sandstorms), although image preprocessing is possible, interfering pixels will still exist in the image. If an interlaced slicing method is used, these interfering features may be amplified.

[0057] To address this issue, this embodiment adjusts the focus slicing parameters based on the clarity of the actual image. Specifically, in the absence of interference, interlaced slicing is used; in the presence of interfering pixels, the parameters can be adjusted to skip two (or at most three) rows. Correspondingly, a relationship can be established between the number of noise points in the image and the interlaced parameter, allowing for flexible adjustment of the slicing parameters to avoid amplifying interfering features and affecting the final recognition result. Subsequently, 3x3 convolution is used to extract different features, forming multi-channel, multi-dimensional information, thereby reducing noise generated by external factors. This avoids interference with multi-dimensional information extraction while reducing some floating-point computation.

[0058] In addition, after optimizing the YOLO target detection model, the optimized YOLO target detection model should be trained using a large number of images of common communication equipment installation scenarios, thereby further improving the recognition accuracy and speed of the YOLO target detection model.

[0059] Step 120: Obtain real-time installation scene images of communication equipment, identify the real-time installation scene images according to the optimized YOLO target detection model, generate feature images with communication equipment marker anchor boxes, and determine the equipment type of the communication equipment.

[0060] Once the YOLO object detection model is optimized, real-time images of the communication equipment installation scene can be captured by a camera near the installation area. The optimized YOLO object detection model then identifies these real-time installation scene images. During the identification process, the YOLO object detection model adds marked anchor boxes around the location of the communication equipment and determines the degree of matching between the image within the marked anchor box and the existing communication equipment, thereby identifying the type of communication equipment.

[0061] Step 130: Search for historical fault images based on the equipment type of the communication equipment. Based on the comparison results between the feature image with the anchor frame marked by the communication equipment and the historical fault images, determine whether the communication equipment has a fault risk.

[0062] Once the device type of the communication equipment is determined, historical fault images can be searched based on the device type. These historical fault images may include images of communication equipment that has already experienced a fault and images of communication equipment with obvious fault risks. Subsequently, the feature image marked with an anchor frame for the communication equipment is compared with the historical fault images, thereby using the comparison results to determine whether the communication equipment has a fault risk.

[0063] Step 140: When there is a risk of failure in the communication equipment, generate a prompt message and send the prompt message to the staff's personal terminal.

[0064] When a communication device is determined to be at risk of failure, a notification message should be generated and sent to the staff's personal terminal to facilitate timely on-site inspection and maintenance. It should be noted that the notification message should include the type of communication device and the location of the potential failure, thereby reducing the actual workload of the staff.

[0065] This embodiment acquires historical installation scene images of communication equipment and optimizes the YOLO target detection model based on these images. It then acquires real-time installation scene images of the communication equipment and uses the optimized YOLO target detection model to identify these images, generating feature images with communication equipment markers and determining the equipment type. Based on the equipment type, it searches historical fault images and compares these images with the feature images to determine if the communication equipment has a fault risk. When a fault risk is detected, a notification is generated and sent to the operator's personal terminal. This approach uses the YOLO target detection model to replace manual identification of communication equipment fault risks, reducing the difficulty of maintenance and facilitating timely handling of potential risks.

[0066] Example 2

[0067] Figure 2 This is a flowchart of a communication device monitoring method provided in Embodiment 2 of the present invention. This embodiment is an optimization based on the above embodiment. In this embodiment, after sending the prompt information to the staff's personal terminal, the following step is added:

[0068] Obtain feedback information from staff, classify the fault risk of communication equipment according to the feedback information, generate a training image set based on the classification results and the feature images of communication equipment with fault risk, and perform deep training on the YOLO object detection model based on the training image set.

[0069] Specifically, the communication device monitoring method provided in this embodiment includes:

[0070] Step 210: Obtain historical installation scene images of the communication equipment, and optimize the YOLO target detection model based on the historical installation scene images.

[0071] Step 220: Obtain real-time installation scene images of communication equipment, identify the real-time installation scene images according to the optimized YOLO target detection model, generate feature images with communication equipment marker anchor boxes, and determine the equipment type of the communication equipment.

[0072] Step 230: Search for historical fault images based on the equipment type of the communication equipment. Based on the comparison results between the feature image with the anchor frame marked by the communication equipment and the historical fault images, determine whether the communication equipment has a fault risk.

[0073] Step 240: When there is a risk of failure in the communication equipment, generate a prompt message and send the prompt message to the staff's personal terminal.

[0074] Step 250: Obtain feedback information from staff, classify the fault risk of communication equipment according to the feedback information, generate a training image set based on the classification results and the feature images of communication equipment with fault risk, and perform deep training on the YOLO object detection model based on the training image set.

[0075] Upon receiving the alert, staff will proceed to the vicinity of the communication equipment for inspection and maintenance. Therefore, staff feedback provides a more accurate and specific reflection of the equipment's damage. Based on this feedback, the risk level of the communication equipment's failure can be categorized. For example, failure risk can be divided into high, medium, and low categories. High failure risk indicates that the equipment will fail within a short period and requires immediate repair; medium failure risk indicates substantial damage but no immediate failure; and low failure risk indicates only surface damage and can withstand long-term operation. Subsequently, a training image set is generated based on the categorization results and feature images of the equipment at risk. This training image set is then used to perform deep training on the YOLO object detection model, enabling it to differentiate the failure risk levels of communication equipment. Accordingly, once the YOLO object detection model possesses this ability, the failure risk level can be added to the alert message during subsequent operations, or the message sending time can be adjusted based on the failure risk level to further improve ease of use for staff.

[0076] Optionally, since the area where communication equipment is set up is usually outdoors, weather conditions can affect the real-time setup scene images. In order to further improve the recognition accuracy of the YOLO target detection model, this embodiment can also generate an extreme weather filter after generating a training image set based on the classification results and the feature images of communication equipment with fault risks, and add the extreme weather filter to the training image set in the form of a filter layer.

[0077] For example, the extreme weather filter may be one or more of the following: rain / snow weather filter, sandstorm weather filter, high brightness filter, and low brightness filter. During processing, a filter layer may be generated based on one or more of the rain / snow weather filter, sandstorm weather filter, high brightness filter, and low brightness filter, and the filter layer may be added to the training image, thereby further improving the depth training effect of the training image set on the YOLO object detection model.

[0078] This embodiment adds the following steps after sending the prompt information to the staff's personal terminal: obtaining feedback information from the staff, classifying the fault risk of the communication equipment according to the feedback information, generating a training image set based on the classification results and feature images of the communication equipment with fault risks, and performing deep training on the YOLO object detection model based on the training image set. This allows for the classification of communication equipment fault risks based on staff feedback and the generation of a training image set containing the classification results, facilitating deep training of the YOLO object detection model and further improving its recognition accuracy and ease of use.

[0079] Example 3

[0080] Figure 3 This is a flowchart of a communication equipment monitoring method provided in Embodiment 3 of the present invention. This embodiment is an optimization based on the above embodiments. In this embodiment, the step of determining whether the communication equipment has a fault risk based on the comparison results between the feature image with the communication equipment marker anchor frame and historical fault images is specifically optimized as follows:

[0081] Calculate the image similarity between the feature image with the anchor box marked by the communication device and the historical fault image. When the image similarity is greater than a preset similarity threshold, it is determined that the communication device has a fault risk.

[0082] Accordingly, the communication device monitoring method provided in this embodiment includes:

[0083] Step 310: Obtain historical installation scene images of the communication equipment, and optimize the YOLO target detection model based on the historical installation scene images.

[0084] Step 320: Obtain real-time installation scene images of communication equipment, identify the real-time installation scene images according to the optimized YOLO target detection model, generate feature images with communication equipment marker anchor boxes, and determine the equipment type of the communication equipment.

[0085] Step 330: Search for historical fault images based on the device type of the communication device, calculate the image similarity between the feature image with the communication device marker anchor box and the historical fault image, and determine that the communication device has a fault risk when the image similarity is greater than the preset similarity threshold.

[0086] In practical use, the outer surface of communication equipment (such as the protective layer of transmission cables) will inevitably suffer damage due to scratches or corrosion. As the years of use increase, these damages will gradually penetrate inward, eventually leading to malfunctions and affecting the normal operation of the communication equipment. Therefore, the presence of damage on the surface of communication equipment can be used to determine whether the equipment is at risk of failure.

[0087] Specifically, when damage is present on the surface of a communication device, a distinct pattern or texture will appear on the feature image marked with the communication device's anchor frame. Since the communication device in the historical fault images has already malfunctioned, similar patterns or textures will also appear on the communication device in those historical fault images. At this point, the image similarity between the feature image marked with the communication device's anchor frame and the historical fault image can be calculated. The higher the image similarity, the more similar the damage on the current communication device is to the damage on the malfunctioning communication device, indicating more severe damage on the current device. When the image similarity exceeds a preset similarity threshold, it can be determined that the current communication device is at risk of malfunction, and relevant personnel should be notified for timely handling to prevent further malfunction.

[0088] Step 340: When there is a risk of failure in the communication equipment, generate a prompt message and send the prompt message to the staff's personal terminal.

[0089] This embodiment determines whether a communication device has a fault risk by comparing a feature image with a communication device marker frame with historical fault images. Specifically, it optimizes this process by calculating the image similarity between the feature image with the communication device marker frame and the historical fault images. If the image similarity is greater than a preset similarity threshold, it determines that the communication device has a fault risk. This allows for the timely detection of potential risks on communication devices by judging whether they have a fault risk based on image similarity.

[0090] Example 4

[0091] Figure 4 This is a flowchart of a communication equipment monitoring method provided in Embodiment 4 of the present invention. This embodiment is an optimization based on the above embodiments. In this embodiment, the step of determining whether the communication equipment has a fault risk based on the comparison results between the feature image with the communication equipment marker anchor frame and historical fault images is specifically optimized as follows:

[0092] Calculate the positional offset between the marked anchor frame and the communication device in the historical fault image. If the positional offset is less than a preset offset threshold, it is determined that the communication device has a fault risk.

[0093] Accordingly, the communication device monitoring method provided in this embodiment includes:

[0094] Step 410: Obtain historical installation scene images of the communication equipment, and optimize the YOLO target detection model based on the historical installation scene images.

[0095] Step 420: Obtain real-time installation scene images of communication equipment, identify the real-time installation scene images according to the optimized YOLO target detection model, generate feature images with communication equipment marker anchor boxes, and determine the equipment type of the communication equipment.

[0096] Step 430: Search historical fault images according to the device type of the communication device, calculate the positional offset between the marked anchor frame and the communication device in the historical fault image, and determine that the communication device has a fault risk when the positional offset is less than the preset offset threshold.

[0097] In practical use, the relative position of communication equipment (such as base station antennas) usually does not change with the increase of its service life. However, under the action of external forces (such as extreme winds or human impact), communication equipment may experience abnormal movement. If the abnormal movement is small, the communication equipment can still maintain normal operation; if the abnormal movement is large, it will directly lead to damage to the communication equipment. Therefore, the positional offset of the communication equipment can be used to determine whether there is a risk of failure.

[0098] Specifically, since the marker anchor boxes in the feature image can reflect the actual location of the communication device, the location of the communication device in the historical fault image can be set as a reference point, and the positional offset between the marker anchor boxes and the communication device in the historical fault image can be calculated. Because the communication device in the historical fault image has already failed, the smaller the positional offset between the marker anchor boxes and the communication device in the historical fault image, the more severe the current positional offset of the communication device. When the positional offset is less than a preset offset threshold, it can be determined that the current communication device is at risk of failure, and relevant personnel should be notified for timely handling to prevent further failure.

[0099] Step 440: When there is a risk of failure in the communication equipment, generate a prompt message and send the prompt message to the staff's personal terminal.

[0100] This embodiment determines whether a communication device has a fault risk by comparing a feature image with a marked anchor frame and historical fault images. Specifically, it calculates the positional offset between the marked anchor frame and the communication device in the historical fault image. If the positional offset is less than a preset offset threshold, it determines that the communication device has a fault risk. This allows for the timely detection of potential risks on the communication device by judging whether it has a fault risk based on the positional offset.

[0101] Example 5

[0102] Figure 5 This is a schematic diagram of the communication equipment monitoring device provided in Embodiment 5 of the present invention, as shown below. Figure 5 As shown, the device includes:

[0103] The optimization module 510 is used to acquire historical installation scene images of communication equipment and optimize the YOLO target detection model based on the historical installation scene images;

[0104] The generation module 520 is used to acquire real-time installation scene images of communication equipment, identify the real-time installation scene images according to the optimized YOLO target detection model, generate feature images with communication equipment marker anchor boxes, and determine the equipment type of the communication equipment.

[0105] The judgment module 530 is used to search for historical fault images according to the equipment type of the communication equipment, and to determine whether the communication equipment has a fault risk based on the comparison results between the feature image with the anchor box marked by the communication equipment and the historical fault images.

[0106] The prompt module 540 is used to generate prompt information when there is a risk of failure in the communication equipment, and send the prompt information to the staff's personal terminal.

[0107] The communication equipment monitoring device provided in this embodiment can optimize the YOLO target detection model through an optimization module, and through the cooperation of the generation and judgment modules, it can determine whether there is a risk of failure in the communication equipment based on real-time scene images of the communication equipment. It can also send timely reminders to staff through an alert module. Compared with existing technologies, it can replace manual identification of communication equipment failure risks, thereby reducing the maintenance difficulty for staff and facilitating timely handling of potential risks.

[0108] Based on the above embodiments, the optimization module includes:

[0109] The first optimization unit is used to obtain the imaging ratio of historical installation scene images of communication equipment and the actual volume parameters of communication equipment, and to set the initial anchor frame size of the YOLO target detection model based on the imaging ratio of historical installation scene images and the actual volume parameters of communication equipment.

[0110] Based on the above embodiments, the optimization module further includes:

[0111] The second optimization unit is used to obtain the image clarity of historical installation scene images of communication equipment, and when the image clarity of historical installation scene images of communication equipment is less than a preset clarity threshold, adjust the focus slice parameters of the YOLO target detection model according to the number of image noise.

[0112] Based on the above embodiments, the determination module includes:

[0113] The first judgment unit is used to calculate the image similarity between the feature image with the communication device marker anchor box and the historical fault image. When the image similarity is greater than the preset similarity threshold, it is determined that the communication device has a fault risk.

[0114] Based on the above embodiments, the determination module further includes:

[0115] The second judgment unit is used to calculate the positional offset between the marked anchor frame and the communication device in the historical fault image. When the positional offset is less than a preset offset threshold, it is determined that the communication device has a fault risk.

[0116] Based on the above embodiments, the device includes:

[0117] The feedback training module is used to obtain feedback information from staff, classify the fault risk of communication equipment according to the feedback information, generate a training image set based on the classification results and feature images of communication equipment with fault risk, and perform deep training on the YOLO object detection model based on the training image set.

[0118] Based on the above embodiments, the device further includes:

[0119] The filter module is used to generate extreme weather filters and add them as filter layers to the training image set.

[0120] The communication equipment monitoring device provided in this embodiment of the invention can execute the communication equipment monitoring method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0121] Example 6

[0122] Figure 6 This is a schematic diagram of the structure of a terminal provided in Embodiment Six of the present invention. Figure 6 A block diagram is shown of an exemplary terminal 12 suitable for implementing embodiments of the present invention. Figure 6 The terminal 12 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0123] like Figure 6 As shown, terminal 12 is presented in the form of a general-purpose computing device. The components of terminal 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0124] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0125] Terminal 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by terminal 12, including volatile and non-volatile media, removable and non-removable media.

[0126] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache 32. Terminal 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 6 Not shown; usually referred to as a "hard drive"). Although Figure 6 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0127] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0128] Terminal 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the terminal 12, and / or with any device that enables the terminal 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, terminal 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of terminal 12 via bus 18. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with terminal 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0129] Furthermore, the terminal described in this embodiment should also include a shooting device (not shown in the figure), which can be a common image acquisition device such as a camera in the prior art. The shooting device can capture images of the communication device, thereby facilitating the monitoring of the communication device.

[0130] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the communication device monitoring method provided in the embodiments of the present invention.

[0131] Example 7

[0132] Embodiment 7 of the present invention also provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform any of the communication device monitoring methods provided in the above embodiments.

[0133] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0134] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0135] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0136] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider). 。

[0137] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for monitoring communication equipment, characterized in that... include: Acquire historical installation scene images of communication equipment, and optimize the YOLO target detection model based on the historical installation scene images; The acquisition of historical installation scene images of communication equipment includes: acquiring the image clarity of historical installation scene images of communication equipment; the optimization of the YOLO target detection model based on historical installation scene images includes: when the image clarity of historical installation scene images of communication equipment is less than a preset clarity threshold, adjusting the focus slice parameters of the YOLO target detection model according to the number of image noise. Acquire real-time images of the communication equipment installation scene, identify the real-time installation scene images based on the optimized YOLO target detection model, generate feature images with anchor boxes marked with communication equipment, and determine the equipment type of the communication equipment. Based on the equipment type of the communication equipment, search historical fault images, and determine whether the communication equipment has a fault risk by comparing the feature image with the anchor box marked by the communication equipment with the historical fault images. When there is a risk of communication equipment failure, a prompt message is generated and sent to the staff's personal terminal.

2. The communication equipment monitoring method according to claim 1, characterized in that: The acquisition of historical deployment scene images of the communication equipment includes: Obtain the imaging ratio of historical installation scene images of communication equipment and the actual volume parameters of the communication equipment; The optimization of the YOLO object detection model based on historical installation scene images includes: Based on the imaging ratio of historical scene images and the actual volume parameters of the communication equipment, the initial anchor frame size of the YOLO target detection model is set.

3. The communication equipment monitoring method according to claim 1, characterized in that: The step of determining whether the communication equipment has a fault risk based on the comparison results between the feature image with the communication equipment marked with an anchor frame and the historical fault image includes: Calculate the image similarity between the feature image with the anchor box marked by the communication device and the historical fault image. When the image similarity is greater than the preset similarity threshold, it is determined that the communication device has a fault risk.

4. The communication equipment monitoring method according to claim 1, characterized in that: The method involves comparing the feature image with the anchor frame marked with the communication device with historical fault images to determine whether the communication device has a fault risk. Calculate the positional offset between the marked anchor frame and the communication device in the historical fault image. If the positional offset is less than a preset offset threshold, it is determined that the communication device has a fault risk.

5. The communication equipment monitoring method according to claim 1, characterized in that: After the notification information is sent to the staff's personal terminal, the communication device monitoring method includes: Obtain feedback information from staff, classify the fault risk of communication equipment according to the feedback information, generate a training image set based on the classification results and the feature images of communication equipment with fault risk, and perform deep training on the YOLO object detection model based on the training image set.

6. The communication equipment monitoring method according to claim 5, characterized in that: After generating a training image set based on the classification results and feature images of communication devices at risk of failure, the communication device monitoring method further includes: Generate an extreme weather filter and add it as a filter layer to the training image set.

7. A communication equipment monitoring device, characterized in that, include: An optimization module is used to acquire historical installation scene images of communication equipment and optimize the YOLO target detection model based on the historical installation scene images. The optimization module includes a second optimization unit, which is used to acquire the image clarity of the historical installation scene images of communication equipment and adjust the focus slice parameters of the YOLO target detection model according to the number of image noise when the image clarity of the historical installation scene images of communication equipment is less than a preset clarity threshold. The generation module is used to acquire real-time installation scene images of communication equipment, identify the real-time installation scene images based on the optimized YOLO target detection model, generate feature images with anchor boxes marked by communication equipment, and determine the equipment type of the communication equipment. The judgment module is used to search for historical fault images based on the equipment type of the communication equipment, and to determine whether the communication equipment has a fault risk based on the comparison results between the feature image with the anchor box marked by the communication equipment and the historical fault images. The alert module is used to generate alert messages when there is a risk of communication equipment failure and send the alert messages to the staff's personal terminals.

8. A terminal, characterized in that, The terminal includes: One or more processors; Storage device for storing one or more programs; Imaging device, used to capture images; When the one or more programs are executed by the one or more processors, the one or more processors implement the communication device monitoring method as described in any one of claims 1-6.

9. A storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the communication device monitoring method as described in any one of claims 1-6.

Images