Method and device for identifying potential quality hazard of optical cable line

Abstract

The invention relates to a method and device for identifying potential quality hazards of an optical cable line, and belongs to the technical field of inspection, and the method comprises the steps: registering unmanned aerial vehicle information to an unmanned aerial vehicle platform, and enabling the unmanned aerial vehicle platform to transmit the unmanned aerial vehicle information to an optical network platform; updating the route state of the inspection route of the optical network platform; newly building a tour-inspection plan and generating tour-inspection points; generating a work order according to the inspection plan, sending the work order to an inspection route worker, and after the inspection route worker reaches a preset range of the inspection route, controlling the unmanned aerial vehicle to fly according to the inspection route for inspection and collection; the unmanned aerial vehicle sends a collection result to the unmanned aerial vehicle platform, and the unmanned aerial vehicle platform sends the collection result to the optical network platform in real time; after the optical network platform receives the inspection point image in the collection result, a pre-trained model is called to recognize and judge whether line quality hidden danger exists in the inspection point image or not; if yes, potential quality hazard early warning information is generated; and quality hidden danger early warning information is sent to management personnel. According to the invention, the inspection efficiency and safety are improved.

Description

Technical Field

[0001] The invention belongs to the field of patrol inspection technology, and in particular relates to a method and a device for identifying quality hazards of optical cable lines. Background Art

[0002] With the rapid development of Internet information technology, cloud computing, big data, artificial intelligence and other technologies have been widely used. Behind this, the safety and stability of optical cable lines, as the physical medium for signal transmission, have become increasingly important. At present, the important way to ensure the safety of optical cable facilities is still for operators to send line patrol personnel to conduct regular inspections of optical cables, relying on manual inspections to detect abnormalities and solve problems.

[0003] Through actual investigation, it is found that relying solely on traditional manual inspections can no longer meet the growing demand for efficient and accurate inspections. Outside the city, the optical cable routing may be in some areas with complex geographical conditions, making it inconvenient for line inspectors to approach for inspections. If accurate coverage is required, line inspectors must shuttle back and forth between optical cable facilities and roads, which is not only inefficient, but also poses a safety hazard to personnel. Therefore, an efficient and safe optical cable facility hidden danger identification solution is needed. Summary of the invention

[0004] In view of the above deficiencies in the prior art, the purpose of the invention is to provide a method and device for identifying quality hazards of optical cable lines, to collect images of optical cable facilities, to analyze the images of optical cable facilities to generate hazard warning information, so as to improve the efficiency of discovering and managing safety hazards of optical cable facilities, to reduce labor costs and ensure personnel safety, and to ensure the safe and stable operation of the services carried by the optical cables.

[0005] In a first aspect of the present invention, a method for identifying potential quality problems of an optical cable line is proposed, which is applied to a system including: a UAV platform and an optical network platform connected, comprising:

[0006] Register the drone information to the drone platform, and the drone platform sends the drone information to the optical network platform;

[0007] Update the route status of the optical network platform inspection route;

[0008] The optical network platform receives the operation of creating a new inspection plan, creates a new inspection plan, and generates inspection points according to the route status and the inspection plan;

[0009] Generate a work order based on the inspection plan and send it to the inspection route personnel. After arriving at the preset range of the inspection route, the inspection route personnel will operate the drone to fly along the inspection route to collect inspection point images, flight tracks and GPS coordinates;

[0010] The drone sends the collected inspection point images, flight tracks, and GPS coordinates to the drone platform in real time, and the drone platform sends the inspection point images, flight tracks, and GPS coordinates to the optical network platform in real time;

[0011] After receiving the inspection point image, the optical network platform calls the pre-trained YOLOX algorithm model to identify and determine whether there are line quality risks in the inspection point image;

[0012] If the judgment result is that there is a quality risk of the line, the facility points in the image with the quality risk will be marked with a frame to generate quality risk warning information;

[0013] Send quality risk warning information to management personnel.

[0014] Furthermore, in the above method for identifying potential quality problems of optical cable lines, updating the route status of the inspection route of the optical network platform includes:

[0015] Upon receiving an operation of creating or changing an inspection route, creating or changing the inspection route on the optical network platform, and sending the newly created or changed inspection route to the drone platform;

[0016] After the UAV successfully completes the test flight on the newly created or changed inspection route, the route status is modified on the UAV platform and sent to the optical network platform.

[0017] Furthermore, in the above method for identifying potential quality problems of optical cable lines, generating inspection points according to route status and inspection plans includes:

[0018] Add the inspection routes with available status to the inspection plan;

[0019] The optical cable facility points corresponding to the inspection route are automatically brought into the inspection plan to generate inspection points;

[0020] Among them, the inspection route is established based on the actual physical route of the optical cable.

[0021] Furthermore, in the above method for identifying quality hazards of optical cable lines, after generating quality hazard warning information, the method further includes:

[0022] The inspection point image, route name, warning time and work order ID corresponding to the storage quality hazard warning information.

[0023] Furthermore, in the above method for identifying potential risks in optical cable line quality, the training method of the pre-trained YOLOX algorithm model includes:

[0024] Determine the types of facilities that need to be automatically identified by the YOLOX algorithm model, the normal and abnormal conditions of the facilities, and determine the scenarios in which the YOLOX algorithm model should be applied;

[0025] Obtain multiple image files for training the YOLOX algorithm model, annotate the scenes and facility types that need to be identified in the image files, and the normal and abnormal conditions of the facilities in the image files to obtain the annotation results;

[0026] Generate a data training set from image files and annotation results;

[0027] Modify the YOLOX algorithm model code according to the facility type, normal and abnormal conditions of the facility that the YOLOX algorithm model needs to automatically identify, and set the application scenario of the YOLOX algorithm model;

[0028] Modify the YOLOX algorithm model according to the deployment environment to support running the YOLOX algorithm model only through CPU device training, add recognition logic within the picture frame, and improve the output of the recognition result threshold judgment;

[0029] Use the data training set to train the YOLOX algorithm model to generate a recognition weight file. During the generation of the recognition weight file, the YOLOX algorithm model configuration is tuned to obtain a pre-trained YOLOX algorithm model.

[0030] Furthermore, in the above method for identifying quality hazards of optical cable lines, after controlling the drone to fly along the inspection route to collect inspection point images, flight trajectories and GPS coordinates, it also includes:

[0031] After the inspection is completed, the images of the inspection points are summarized and organized, and the summarized and organized images are used to upgrade and train the YOLOX algorithm model.

[0032] Furthermore, in the above method for identifying quality hazards of optical cable lines, the labeled image file is labeled using LabelImg;

[0033] Generate a data training set from image files and annotation results, including: writing a Python script to generate a data training set from image files and annotation results in the VOC standard format.

[0034] In a second aspect of the present invention, a device for identifying potential quality problems of an optical cable line is provided, which is applied to a system including: a UAV platform and an optical network platform connected, comprising:

[0035] Registration module: used to register drone information to the drone platform, and the drone platform sends the drone information to the optical network platform;

[0036] Update module: used to update the route status of the optical network platform inspection route;

[0037] New module: used for the optical network platform to receive the operation of creating a new inspection plan, create a new inspection plan, and generate inspection points according to the route status and inspection plan;

[0038] Collection module: used to generate work orders according to the inspection plan and send the work orders to the inspection route personnel. After arriving at the preset range of the inspection route, the inspection route personnel operate the drone to fly along the inspection route to collect inspection point images, flight tracks and GPS coordinates;

[0039] The first sending module is used for the drone to send the collected inspection point images, flight tracks, and GPS coordinates to the drone platform in real time, and the drone platform sends the inspection point images, flight tracks, and GPS coordinates to the optical network platform in real time;

[0040] Judgment module: After the optical network platform receives the inspection point image, it calls the pre-trained YOLOX algorithm model to identify and judge whether there are line quality risks in the inspection point image;

[0041] Generation module: if the judgment result is that there is a quality hazard of the line, the facility points in the image with the quality hazard will be marked with a frame to generate quality hazard warning information;

[0042] The second sending module is used to send quality risk warning information to management personnel.

[0043] According to a third aspect of the present invention, an electronic device is provided, comprising: a processor and a memory;

[0044] The processor is used to execute any one of the above methods for identifying quality hazards of optical cable lines by calling the program or instruction stored in the memory.

[0045] In a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a program or instruction, and the program or instruction enables a computer to execute any one of the above methods for identifying quality risks of an optical cable line.

[0046] The beneficial effects of the present invention are as follows: the present invention registers drone information to the drone platform, and the drone platform sends the drone information to the optical network platform; updates the route status of the optical network platform inspection route; the optical network platform receives the operation of creating a new inspection plan, creates a new inspection plan, and generates inspection points according to the route status and the inspection plan; generates a work order according to the inspection plan, and sends the work order to the inspection route personnel, who, after arriving within the preset range of the inspection route, operate the drone to fly along the inspection route to collect inspection point images, flight trajectories and GPS coordinates; the drone sends the collected inspection point images, flight trajectories and GPS coordinates to the drone platform in real time, and the drone platform sends the inspection point images, flight trajectories and GPS coordinates to the optical network platform in real time; after receiving the inspection point image, the optical network platform calls the pre-trained YOLOX algorithm model to identify and determine whether there are line quality hazards in the inspection point image; if the judgment result is that there are line quality hazards, the facility points in the image where the quality hazards are generated will be marked with frames, and quality hazard warning information will be generated; and the quality hazard warning information will be sent to the management personnel. The present invention collects images of optical cable facilities, analyzes the images of optical cable facilities to generate hidden danger warning information, thereby improving the efficiency of discovering and managing safety hazards of optical cable facilities, reducing labor costs and ensuring personnel safety, and ensuring the safe and stable operation of the services carried by the optical cables. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are only used to illustrate specific embodiments and are not considered to limit the present invention. In the entire drawings, the same reference symbols represent the same components. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0048] Figure 1 A method diagram for identifying quality risks of optical cable lines provided by an embodiment of the present invention;

[0049] Figure 2 A method diagram for updating the route status of an inspection route of an optical network platform provided by an embodiment of the present invention;

[0050] Figure 3 A method diagram for generating inspection points according to route status and inspection plan provided by an embodiment of the present invention;

[0051] Figure 4 A diagram of a training method for a pre-trained YOLOX algorithm model provided in an embodiment of the present invention;

[0052] Figure 5 A diagram of a device for identifying quality risks of optical cable lines provided by an embodiment of the present invention;

[0053] Figure 6A schematic block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making creative work should fall within the scope of protection of the present invention.

[0055] Furthermore, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concepts disclosed in the present invention.

[0056] In the description of the present invention, the terms "first", "second", and "third" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be internal communication between two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0057] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of methods and systems consistent with some aspects of the present invention as detailed in the appended claims.

[0058] The present invention proposes a method, device, electronic device and storage medium for identifying quality hazards of optical cable lines, collects images of optical cable facilities, analyzes the images of optical cable facilities to generate hazard warning information, thereby improving the efficiency of discovering and managing safety hazards of optical cable facilities, reducing labor costs and ensuring personnel safety, and ensuring the safe and stable operation of the services carried by the optical cables.

[0059] Before introducing the embodiments of the present invention, professional terms involved in the present invention are first introduced.

[0060] YOLOX (You Only Look Once version X): is a new target detection algorithm proposed in 2021. This algorithm inherits the original advantages of the YOLO series and is improved on the basis of YOLOv3-SPP. It achieves a perfect balance between speed and accuracy by introducing innovative technologies such as decoupling head, no anchor points and advanced label allocation strategies.

[0061] LabelImg: It is a graphic image annotation tool written in Python, with a graphical interface using Qt. The annotated annotations are saved as XML files in Pascal VOC format. In addition, it also supports YOLO and CreateML formats.

[0062] VOC (Visual Object Classes) format: is a dataset format for image recognition, especially for target detection tasks. It was introduced by the Pascal VOC Challenge and provides a complete set of standardized datasets for image classification and target detection. VOC format datasets usually contain three main parts: a JPEGImages directory, which stores all image files; an Annotations directory, which stores XML format annotation files corresponding to the images in the JPEGImages directory; and an ImageSets directory, which contains a series of text files used to divide the dataset.

[0063] Method Embodiment

[0064] Figure 1 A diagram of a method for identifying quality risks of optical cable lines provided by an embodiment of the present invention.

[0065] In a first aspect of the present invention, a method for identifying potential quality problems of optical cable lines is proposed, which is applied to a system including: a UAV platform and an optical network platform connected, combined with Figure 1 , including eight steps from S1 to S8:

[0066] S1: Register the drone information to the drone platform, and the drone platform sends the drone information to the optical network platform.

[0067] Specifically, in an embodiment of the present invention, the drone equipment is included in the system management as a resource, the data communication between the drone platform and the optical network platform is opened, the purchased drone information is registered to the drone platform, and the drone platform sends the drone information to the optical network platform.

[0068] S2: Update the route status of the optical network platform inspection route.

[0069] Specifically, in the embodiment of the present invention, the method for updating the route status of the inspection route of the optical network platform is described in detail below. The route status of the inspection route is divided into two types: available and unavailable.

[0070] S3: The optical network platform receives the operation of creating a new inspection plan, creates a new inspection plan, and generates inspection points according to the route status and the inspection plan.

[0071] Specifically, in an embodiment of the present invention, a new inspection plan is created on the optical network platform. The inspection modes in the inspection plan include: a mixed inspection mode of foot inspection and drone inspection, and vehicle inspection and drone inspection. The method of generating inspection points according to the route status and the inspection plan is described in detail below.

[0072] S4: Generate a work order according to the inspection plan and send it to the inspection route personnel. After arriving at the preset range of the inspection route, the inspection route personnel operate the drone to fly along the inspection route to collect inspection point images, flight trajectories and GPS coordinates.

[0073] Specifically, in an embodiment of the present invention, a work order is generated according to the inspection plan, and the work order is sent to the inspection route personnel. After the inspection route personnel arrive at the preset range of the inspection route by patrolling on foot or by car, they operate the drone to fly along the inspection route to collect inspection point images, flight trajectories and GPS coordinates.

[0074] S5: The drone sends the collected inspection point images, flight tracks, and GPS coordinates to the drone platform in real time, and the drone platform sends the inspection point images, flight tracks, and GPS coordinates to the optical network platform in real time.

[0075] Specifically, in an embodiment of the present invention, the drone sends the collected inspection point images, flight trajectories, and GPS coordinates to the drone platform in real time. The drone platform synchronizes the inspection point images, flight trajectories, and GPS coordinates to the optical network platform in real time. The optical network platform is responsible for judging the execution status of the inspection points, the completion status of the work orders, and whether the images contain any line quality risks.

[0076] S6: After receiving the inspection point image, the optical network platform calls the pre-trained YOLOX algorithm model to identify and determine whether there are line quality risks in the inspection point image.

[0077] Specifically, in an embodiment of the present invention, a training method of a pre-trained YOLOX algorithm model is described in detail below. The pre-trained YOLOX algorithm model can directly identify and determine whether there are line quality risks in the inspection point image, which is simple and fast.

[0078] S7: If the judgment result is that there is a quality hazard of the line, the facility points in the image where the quality hazard occurs will be marked with frames to generate quality hazard warning information.

[0079] Specifically, in the embodiment of the present invention, if the judgment result is that there is a potential quality hazard in the line, the facility points in the picture corresponding to the image generating the potential quality hazard are marked with frames to generate potential quality hazard warning information.

[0080] S8: Send quality risk warning information to management personnel.

[0081] Specifically, in the embodiment of the present invention, quality risk warning information is sent to management personnel, and the management personnel intervene and handle the problem in a timely manner.

[0082] It should be understood that by using drones instead of manual labor, they can get as close to optical cable facilities as possible in dangerous areas and can provide rapid and mobile coverage in emergency scenarios, thus ensuring full-scene coverage of the managed lines and the personal safety of the workers.

[0083] Figure 2 A method diagram for updating the route status of an inspection route of an optical network platform provided in an embodiment of the present invention.

[0084] Furthermore, in the above method for identifying the quality risks of optical cable lines, the route status of the inspection route of the optical network platform is updated, combined with Figure 2 , including two steps from S21 to S22:

[0085] S21: receiving an operation of creating or changing an inspection route, creating or changing an inspection route on the optical network platform, and sending the newly created or changed inspection route to the drone platform;

[0086] S22: After the UAV successfully completes the test flight on the newly created or changed inspection route, the route status is modified on the UAV platform and sent to the optical network platform.

[0087] Specifically, in an embodiment of the present invention, after a route is newly created or changed, a test flight of the newly created or changed inspection route needs to be completed to ensure that the route is available and that the drone can carry out inspection work normally. After the newly created or changed inspection route passes the drone test flight, the route status is modified to available on the drone platform and feedback is given to the optical network platform.

[0088] Figure 3 A method diagram for generating inspection points according to route status and inspection plan is provided in an embodiment of the present invention.

[0089] Furthermore, in the above method for identifying the quality risks of optical cable lines, inspection points are generated according to the route status and inspection plan, and Figure 3 , including two steps from S31 to S32:

[0090] S31: adding the inspection route whose route status is available to the inspection plan;

[0091] S32: The optical cable facility points corresponding to the inspection route are automatically brought into the inspection plan to generate inspection points;

[0092] Among them, the inspection route is established based on the actual physical route of the optical cable.

[0093] Specifically, in the embodiment of the present invention, the route with the route status as available is added to the inspection plan, and the optical cable facility point corresponding to the route will be automatically brought into the inspection plan and the inspection point will be generated.

[0094] Furthermore, in the above method for identifying quality hazards of optical cable lines, after generating quality hazard warning information, the method further includes:

[0095] The inspection point image, route name, warning time and work order ID corresponding to the storage quality hazard warning information.

[0096] Specifically, in an embodiment of the present invention, the inspection point image, route name, warning time and work order ID corresponding to the quality hazard warning information are stored in a database to facilitate subsequent tracing.

[0097] Figure 4 A diagram of a training method for a pre-trained YOLOX algorithm model provided in an embodiment of the present invention.

[0098] Furthermore, in the above method for identifying the quality risks of optical cable lines, the training method of the pre-trained YOLOX algorithm model is combined with Figure 4 , including six steps from S41 to S46:

[0099] S41: Determine the types of facilities that need to be automatically identified by the YOLOX algorithm model, the normal and abnormal conditions of the facilities, and determine the scenarios for application of the YOLOX algorithm model;

[0100] S42: obtaining multiple image files for training the YOLOX algorithm model, annotating the scenes and facility types to be identified in the image files, and the normal and abnormal conditions of the facilities in the image files to obtain the annotation results;

[0101] S43: Generate a data training set from the image file and the annotation result;

[0102] S44: modify the YOLOX algorithm model code according to the facility type, normal and abnormal conditions of the facility automatically identified by the YOLOX algorithm model, and set the application scenario of the YOLOX algorithm model;

[0103] S45: Modify the YOLOX algorithm model according to the deployment environment to support running the YOLOX algorithm model only through CPU device training, add recognition logic within the picture frame, and improve the output of the recognition result threshold judgment;

[0104] S46: Use the data training set to train the YOLOX algorithm model to generate a recognition weight file, and during the generation of the recognition weight file, tune the YOLOX algorithm model configuration to obtain a pre-trained YOLOX algorithm model.

[0105] Specifically, in the embodiment of the present invention, a convolutional neural network model is built and trained to identify quality risks in facility images taken by drones. The core algorithm is implemented based on YOLOX, and LabelImg is used to annotate the scenes and types in the image files that need to be automatically identified by the algorithm, such as pole lines, signs, manholes and other facility types, normal and abnormal scenes such as complete, collapsed, missing or damaged facilities, to obtain image annotation results, and optimize the model configuration to improve the AP index.

[0106] Furthermore, in the above method for identifying quality hazards of optical cable lines, after controlling the drone to fly along the inspection route to collect inspection point images, flight trajectories and GPS coordinates, it also includes:

[0107] After the inspection is completed, the images of the inspection points are summarized and organized, and the summarized and organized images are used to upgrade and train the YOLOX algorithm model.

[0108] Specifically, in the embodiment of the present invention, the summarized and sorted images may be images of false alarms or images of other situations. The upgraded and trained YOLOX algorithm model can more accurately identify quality risks of optical cable lines.

[0109] Furthermore, in the above method for identifying quality hazards of optical cable lines, the labeled image file is labeled using LabelImg;

[0110] Generate a data training set from image files and annotation results, including: writing a Python script to generate a data training set from image files and annotation results in the VOC standard format.

[0111] Device Embodiment

[0112] Figure 5 A device for identifying quality risks of an optical cable line is provided in an embodiment of the present invention.

[0113] In a second aspect of the present invention, a device for identifying potential quality problems of optical cable lines is provided, which is applied to a system including: a UAV platform and an optical network platform connected, and combined with Figure 5 ,include:

[0114] Registration module 51: used to register the drone information to the drone platform, and the drone platform sends the drone information to the optical network platform.

[0115] Specifically, in the embodiment of the present invention, the registration module 51 incorporates the drone equipment into the system management as a resource, opens up data communication between the drone platform and the optical network platform, registers the purchased drone information to the drone platform, and the drone platform sends the drone information to the optical network platform.

[0116] Update module 52: used to update the route status of the optical network platform inspection route.

[0117] Specifically, in the embodiment of the present invention, the method in which the updating module 52 updates the route status of the optical network platform inspection route is described in detail below. The route status of the inspection route is divided into two types: available and unavailable.

[0118] New module 53: used for the optical network platform to receive the operation of creating a new inspection plan, create a new inspection plan, and generate inspection points according to the route status and the inspection plan.

[0119] Specifically, in an embodiment of the present invention, the new creation module 53 creates a new inspection plan on the optical network platform. The inspection modes in the inspection plan include: a mixed inspection mode of foot inspection and drone inspection, and vehicle inspection and drone inspection. Inspection points are generated according to the route status and the inspection plan.

[0120] Collection module 54: used to generate a work order according to the inspection plan and send the work order to the inspection route personnel. After arriving at the preset range of the inspection route, the inspection route personnel operate the drone to fly along the inspection route to collect inspection point images, flight trajectories and GPS coordinates.

[0121] Specifically, in an embodiment of the present invention, a work order is generated according to the inspection plan, and the work order is sent to the inspection route personnel. After the inspection route personnel arrive at the preset range of the inspection route by patrolling on foot or by car, they operate the drone to fly along the inspection route and collect inspection point images, flight trajectories and GPS coordinates through the collection module 54.

[0122] The first sending module 55 is used for the drone to send the collected inspection point images, flight tracks, and GPS coordinates to the drone platform in real time, and the drone platform sends the inspection point images, flight tracks, and GPS coordinates to the optical network platform in real time.

[0123] Specifically, in the embodiment of the present invention, the drone sends the collected inspection point images, flight trajectories, and GPS coordinates to the drone platform in real time through the first sending module 55. The drone platform synchronizes the inspection point images, flight trajectories, and GPS coordinates to the optical network platform in real time through the first sending module 55. The optical network platform is responsible for judging the execution status of the inspection points, the completion status of the work orders, and whether the images contain any line quality risks.

[0124] Judgment module 56: After the optical network platform receives the inspection point image, it calls the pre-trained YOLOX algorithm model to identify and judge whether there are line quality risks in the inspection point image.

[0125] Specifically, in the embodiment of the present invention, the judgment module 56 of the pre-trained YOLOX algorithm model can directly identify and judge whether there are line quality risks in the inspection point image, which is simple and quick.

[0126] Generating module 57: if the judgment result is that there is a quality hazard of the line, the facility points in the image with the quality hazard will be marked with a frame to generate quality hazard warning information.

[0127] Specifically, in the embodiment of the present invention, if the judgment result is that there is a potential quality hazard in the line, the facility points in the picture corresponding to the image generating the potential quality hazard are framed and the generating module 57 generates potential quality hazard warning information.

[0128] The second sending module 58 is used to send quality risk warning information to management personnel.

[0129] Specifically, in the embodiment of the present invention, the second sending module 58 sends quality hazard warning information to management personnel, and the management personnel intervene and handle it in a timely manner.

[0130] It should be understood that by using drones instead of manual labor, they can get as close to optical cable facilities as possible in dangerous areas and can provide rapid and mobile coverage in emergency scenarios, thus ensuring full-scene coverage of the managed lines and the personal safety of the workers.

[0131] According to a third aspect of the present invention, an electronic device is provided, comprising: a processor and a memory;

[0132] The processor is used to execute any one of the above methods for identifying quality hazards of optical cable lines by calling the program or instruction stored in the memory.

[0133] In a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a program or instruction, and the program or instruction enables a computer to execute any one of the above methods for identifying quality risks of an optical cable line.

[0134] Figure 6 It is a schematic block diagram of an electronic device provided by an embodiment of the present invention.

[0135] like Figure 6As shown, the electronic device includes: at least one processor 601, at least one memory 602 and at least one communication interface 603. The various components in the electronic device are coupled together through a bus system 604. The communication interface 603 is used to transmit information between external devices. It can be understood that the bus system 604 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 604 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 6 Various buses are labeled as bus system 604 .

[0136] It can be understood that the memory 602 in this embodiment can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0137] In some implementations, the memory 602 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system and application programs.

[0138] The operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application includes various application programs, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. A program that implements any method of the method for identifying quality hazards of optical cable lines provided in an embodiment of the present invention can be included in the application.

[0139] In an embodiment of the present invention, the processor 601 calls a program or instruction stored in the memory 602, specifically, a program or instruction stored in an application, and the processor 601 is used to execute the steps of each embodiment of a method for identifying quality hazards of an optical cable line provided in an embodiment of the present invention.

[0140] Register the drone information to the drone platform, and the drone platform sends the drone information to the optical network platform;

[0141] Update the route status of the optical network platform inspection route;

[0142] The optical network platform receives the operation of creating a new inspection plan, creates a new inspection plan, and generates inspection points according to the route status and the inspection plan;

[0143] Generate a work order based on the inspection plan and send it to the inspection route personnel. After arriving at the preset range of the inspection route, the inspection route personnel will operate the drone to fly along the inspection route to collect inspection point images, flight tracks and GPS coordinates;

[0144] The drone sends the collected inspection point images, flight tracks, and GPS coordinates to the drone platform in real time, and the drone platform sends the inspection point images, flight tracks, and GPS coordinates to the optical network platform in real time;

[0145] After receiving the inspection point image, the optical network platform calls the pre-trained YOLOX algorithm model to identify and determine whether there are line quality risks in the inspection point image;

[0146] If the judgment result is that there is a quality risk of the line, the facility points in the image with the quality risk will be marked with a frame to generate quality risk warning information;

[0147] Send quality risk warning information to management personnel.

[0148] Any method in the method for identifying the quality hazards of optical cable lines provided in the embodiment of the present invention can be applied to the processor 601, or implemented by the processor 601. The processor 601 can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 601 or the instructions in the form of software. The above processor 601 can be a general-purpose processor, a digital signal processor (DigitalSignal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0149] The steps of any method in the method for identifying the quality hazards of optical cable lines provided by the embodiment of the present invention can be directly embodied as being executed by a hardware decoding processor, or being executed by a combination of hardware and software units in the decoding processor. The software unit can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 602, and the processor 601 reads the information in the memory 602 and completes the steps of the method in combination with its hardware.

[0150] Those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features from different embodiments is meant to be within the scope of the present invention and to form different embodiments.

[0151] Those skilled in the art will appreciate that the description of each embodiment has its own emphasis, and for parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0152] Although the embodiments of the present invention are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims. The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of various equivalent modifications or substitutions within the technical scope disclosed by the present invention, and these modifications or substitutions should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

[0153] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for identifying potential quality problems of optical cable lines, characterized in that: Applicable to systems connecting UAV platforms and optical network platforms, including: Register the drone information to the drone platform, and the drone platform sends the drone information to the optical network platform; Update the route status of the optical network platform inspection route; The optical network platform receives the operation of creating a new inspection plan, creates a new inspection plan, and generates inspection points according to the route status and the inspection plan; Generate a work order based on the inspection plan and send it to the inspection route personnel. After arriving at the preset range of the inspection route, the inspection route personnel will operate the drone to fly along the inspection route to collect inspection point images, flight tracks and GPS coordinates; The drone sends the collected inspection point images, flight tracks, and GPS coordinates to the drone platform in real time, and the drone platform sends the inspection point images, flight tracks, and GPS coordinates to the optical network platform in real time; After receiving the inspection point image, the optical network platform calls the pre-trained YOLOX algorithm model to identify and determine whether there are line quality risks in the inspection point image; If the judgment result is that there is a quality risk of the line, the facility points in the image with the quality risk will be marked with a frame to generate quality risk warning information; Send quality risk warning information to management personnel.

2. A method for identifying quality hazards of optical cable lines according to claim 1, characterized in that: The updating of the route status of the inspection route of the optical network platform includes: Upon receiving an operation of creating or changing an inspection route, creating or changing the inspection route on the optical network platform, and sending the newly created or changed inspection route to the drone platform; After the UAV successfully completes the test flight on the newly created or changed inspection route, the route status is modified on the UAV platform and sent to the optical network platform.

3. A method for identifying quality hazards of optical cable lines according to claim 1, characterized in that: Generate inspection points based on route status and inspection plan, including: Add the inspection routes with available status to the inspection plan; The optical cable facility points corresponding to the inspection route are automatically brought into the inspection plan to generate inspection points; The inspection route is established based on the actual physical route of the optical cable.

4. A method for identifying quality hazards of optical cable lines according to claim 1, characterized in that: After the quality risk warning information is generated, the following steps are also included: The inspection point image, route name, warning time and work order ID corresponding to the storage quality hazard warning information.

5. A method for identifying quality hazards of optical cable lines according to claim 1, characterized in that: The training method of the pre-trained YOLOX algorithm model comprises: Determine the types of facilities that need to be automatically identified by the YOLOX algorithm model, the normal and abnormal conditions of the facilities, and determine the scenarios in which the YOLOX algorithm model should be applied; Obtain multiple image files for training the YOLOX algorithm model, annotate the scenes and facility types that need to be identified in the image files, and the normal and abnormal conditions of the facilities in the image files to obtain the annotation results; Generate a data training set from image files and annotation results; Modify the YOLOX algorithm model code according to the facility type, normal and abnormal conditions of the facility that the YOLOX algorithm model needs to automatically identify, and set the application scenario of the YOLOX algorithm model; Modify the YOLOX algorithm model according to the deployment environment to support running the YOLOX algorithm model only through CPU device training, add recognition logic within the picture frame, and improve the output of the recognition result threshold judgment; Use the data training set to train the YOLOX algorithm model to generate a recognition weight file. During the generation of the recognition weight file, the YOLOX algorithm model configuration is tuned to obtain a pre-trained YOLOX algorithm model.

6. A method for identifying quality hazards of optical cable lines according to claim 1, characterized in that: After the drone is controlled to fly and inspect along the inspection route to collect inspection point images, flight tracks and GPS coordinates, the following steps are also included: After the inspection is completed, the images of the inspection points are summarized and organized, and the summarized and organized images are used to upgrade and train the YOLOX algorithm model.

7. A method for identifying quality hazards of optical cable lines according to claim 5, characterized in that: The labeled image file is labeled using LabelImg; Generate a data training set from image files and annotation results, including: writing a Python script to generate a data training set from image files and annotation results in the VOC standard format.

8. A device for identifying potential quality problems of optical cable lines, characterized in that: Applicable to systems connecting UAV platforms and optical network platforms, including: Registration module: used to register drone information to the drone platform, and the drone platform sends the drone information to the optical network platform; Update module: used to update the route status of the optical network platform inspection route; New module: used for the optical network platform to receive the operation of creating a new inspection plan, create a new inspection plan, and generate inspection points according to the route status and inspection plan; Collection module: used to generate work orders according to the inspection plan and send the work orders to the inspection route personnel. After arriving at the preset range of the inspection route, the inspection route personnel operate the drone to fly along the inspection route to collect inspection point images, flight tracks and GPS coordinates; The first sending module is used for the drone to send the collected inspection point images, flight tracks, and GPS coordinates to the drone platform in real time, and the drone platform sends the inspection point images, flight tracks, and GPS coordinates to the optical network platform in real time; Judgment module: After the optical network platform receives the inspection point image, it calls the pre-trained YOLOX algorithm model to identify and judge whether there are line quality risks in the inspection point image; Generation module: if the judgment result is that there is a quality hazard of the line, the facility points in the image with the quality hazard will be marked with a frame to generate quality hazard warning information; The second sending module is used to send quality risk warning information to management personnel.

9. An electronic device, characterized in that: include: Processor and memory; The processor is used to execute the method for identifying quality risks of optical cable lines as described in any one of claims 1 to 7 by calling the program or instruction stored in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or instruction, and the program or instruction enables a computer to execute a method for identifying quality risks of an optical cable line as described in any one of claims 1 to 7.

Images