Optical distribution frame resource confirmation method and system

Abstract

The application provides an optical distribution frame resource confirmation method and system, and belongs to the technical field of network support, and comprises the following steps: determining a target optical distribution frame based on optical distribution frame input data and an optical distribution frame panel diagram; acquiring an optical distribution frame terminal identification library established based on image recognition; and determining terminal resources in the target optical distribution frame based on the optical distribution frame terminal identification library. The application adopts the image recognition technology based on artificial intelligence to quickly confirm and compare the optical distribution frame resources, which not only ensures the resource accuracy, but also reduces the labor cost, shortens the time for checking the optical fiber resources, and improves the competitiveness of operators.

Description

Technical Field

[0001] This invention relates to the field of network support technology, and in particular to a method and system for verifying optical distribution box resources. Background Technology

[0002] In recent years, with the accelerated pace of network construction by operators, the structure of communication networks has become increasingly complex, and transmission resources have undertaken a considerable portion of the network construction.

[0003] As a crucial component of the last mile in the access network, dumb resources such as optical distribution boxes and optical fiber splitters occupy a significant proportion of network resources. It's easy to see that the current management of dumb resources presents three major challenges: 1. The existing network information nodes are numerous and widely dispersed, exhibiting a network scale effect. As the number increases, the difficulty and cost of maintenance amplify exponentially; 2. On-site terminal equipment cannot be monitored or connected to the network, and may even lack power access, making traditional networking methods inconvenient; 3. Routine business operations often require on-site personnel, resulting in low efficiency and compromised accuracy and timeliness of information.

[0004] To address the management and verification of existing dummy resources such as fiber optic access, a new and efficient verification method is needed to overcome the shortcomings of current methods that rely too heavily on manual maintenance. Summary of the Invention

[0005] This invention provides a method and system for confirming optical distribution box resources, which solves the problem that the existing technology relies on manual confirmation of optical distribution box resources, resulting in low identification accuracy and a large consumption of manpower and resources.

[0006] In a first aspect, the present invention provides a method for confirming optical junction box resources, comprising:

[0007] Based on the data entered into the optical distribution box and the panel diagram of the optical distribution box, the target optical distribution box is determined;

[0008] Obtain an optical junction box terminal identification library established based on image recognition, and determine the terminal resources in the target optical junction box based on the optical junction box terminal identification library.

[0009] According to the present invention, a method for confirming optical distribution box resources, wherein determining the target optical distribution box based on the optical distribution box input data and the optical distribution box panel diagram includes:

[0010] The basic information and advanced attributes of the optical distribution box are determined according to the networking requirements, and the basic information and advanced attributes are used to form the optical distribution box data.

[0011] Obtain a panel image of an optical switch box that meets the recognition criteria, compare the panel image of the optical switch box with the data entered in the optical switch box, obtain a comparison result that is greater than the accuracy threshold, and determine the target optical switch box based on the comparison result.

[0012] According to a method for confirming optical distribution box resources provided by the present invention, obtaining an optical distribution box panel diagram that meets the identification conditions includes:

[0013] If it is determined that the proportion of objects in the optical junction box panel image is within a preset range, then the optical junction box panel image is determined to meet the recognition conditions.

[0014] According to the method for confirming optical distribution box resources provided by the present invention, the step of determining the target optical distribution box based on the optical distribution box input data and the optical distribution box panel diagram further includes:

[0015] If it is determined that the optical switch box panel diagram is not the target optical switch box, then adjust the optical switch box input data and / or the optical switch box panel diagram.

[0016] According to the method for confirming optical junction box resources provided by the present invention, the step of obtaining an optical junction box terminal identification library established based on image recognition includes:

[0017] Collect more than a preset number of optical junction box panel images;

[0018] Determine the labeling sample corresponding to the multiple optical junction box panel diagram samples based on the terminal status;

[0019] The labeled image sample is decomposed into multiple small image blocks to obtain the labeling results of the labeled image sample, and terminal identification information is generated based on the labeling results;

[0020] The terminal identification information is input into a preset small neural network, and the terminal identification information corresponding to each small image block is extracted into a number sequence to form the optical junction box terminal identification library.

[0021] According to a method for confirming optical distribution box resources provided by the present invention, the step of determining the terminal resources in the target optical distribution box based on the optical distribution box terminal identification library includes:

[0022] The optical switch box panel image corresponding to the target optical switch box is reduced by pixel sampling to obtain the reduced panel image;

[0023] If the terminal information in the reduced rear panel diagram is consistent with that in the optical junction box terminal identification library, the terminal information is output as the terminal resource; otherwise, the terminal information is determined to be an error.

[0024] According to the present invention, a method for confirming the resources of an optical junction box is provided, wherein the terminal status includes an idle status, an occupied status, and a vacant status.

[0025] Secondly, the present invention also provides an optical junction box resource verification system, comprising:

[0026] The first processing module is used to determine the target optical distribution box based on the data entered into the optical distribution box and the panel diagram of the optical distribution box;

[0027] The second processing module is used to obtain an optical junction box terminal identification library established based on image recognition, and to determine the terminal resources in the target optical junction box based on the optical junction box terminal identification library.

[0028] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the optical junction box resource confirmation method as described above.

[0029] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the optical junction box resource confirmation method as described above.

[0030] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the optical junction box resource confirmation method as described above.

[0031] The optical distribution box resource verification method and system provided by this invention uses artificial intelligence-based image recognition technology to quickly verify and compare optical distribution box resources. This not only ensures resource accuracy but also reduces manpower costs, shortens the time spent on optical fiber resource verification, and enhances the competitiveness of operators. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0033] Figure 1 This is a flowchart illustrating the optical junction box resource confirmation method provided by the present invention;

[0034] Figure 2 This is a flowchart of the rapid confirmation process for optical junction box resources provided by the present invention;

[0035] Figure 3This is a flowchart of the training process for the optical junction box terminal identification library provided by the present invention;

[0036] Figure 4 This is a flowchart of the optical junction box terminal identification process provided by the present invention;

[0037] Figure 5 This is a schematic diagram of the optical junction box resource confirmation system provided by the present invention;

[0038] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0040] Since access network resources are the foundation for telecommunications companies to provide services to the outside world, making full use of network resources and improving resource management and utilization efficiency are key to achieving enterprise informatization. As communication networks become increasingly complex, improving production efficiency becomes increasingly important, which can enhance the full-service competitiveness of operators.

[0041] This invention proposes a novel method for confirming optical junction box resources. Figure 1 This is a flowchart illustrating the optical junction box resource verification method provided by the present invention, as follows: Figure 1 As shown, it includes:

[0042] Step 100: Based on the data entered into the optical distribution box and the panel diagram of the optical distribution box, determine the target optical distribution box;

[0043] Step 200: Obtain the optical junction box terminal identification library established based on image recognition, and determine the terminal resources in the target optical junction box based on the optical junction box terminal identification library.

[0044] The fiber optic junction box involved in this invention is a junction device that provides termination and patching for backbone and distribution layer optical cables. After the optical cable is introduced into the junction box, it is fixed, terminated, and distributed. Then, patch cords are used to connect the backbone and distribution layer optical cables. The fiber optic junction box is mainly used as an interface device at the junction of backbone and distribution optical cables in an optical cable access network. The structure of the fiber optic junction box mainly consists of a box body, internal metal parts, optical fiber connectors, and spare parts. In summary, the application of fiber optic junction boxes in local optical cable networks is important for the effective management and rational planning and utilization of optical fiber cores, improving the refined management of optical fiber cores, and making the construction of optical fiber networks more flexible and scalable, allowing the physical optical cable network to better serve the development and construction of telecommunications services.

[0045] Specifically, the resource information of the fiber optic distribution boxes in the network resources is pre-entered manually, i.e., the optical distribution box entry data. Usually, the relevant data is entered directly on the configuration webpage or client. Then, the panel image of the optical distribution box is obtained by taking a picture. By combining the above optical distribution box entry data and the optical distribution box panel image, the two pieces of information are compared to determine whether it is the target optical distribution box, i.e., the specific optical distribution box that needs to be used in this network.

[0046] Furthermore, after determining the basic information of the optical distribution box, it is also necessary to confirm the terminal information on the optical distribution box. By training with artificial intelligence image recognition, an optical distribution box terminal recognition library is constructed and compared with the target optical distribution box to obtain the terminal resources in the target optical distribution box.

[0047] This invention, starting from the complex communication network data, introduces image recognition technology without changing the original system software architecture to achieve rapid identification and calibration of resources such as optical junction boxes and optical fiber distribution boxes, thereby improving the accuracy of dumb resources and reducing manual workload.

[0048] Based on the above embodiments, determining the target optical cross-connect box based on the optical cross-connect box input data and the optical cross-connect box panel diagram includes:

[0049] The basic information and advanced attributes of the optical distribution box are determined according to the networking requirements, and the basic information and advanced attributes are used to form the optical distribution box data.

[0050] Obtain a panel image of an optical switch box that meets the recognition criteria, compare the panel image of the optical switch box with the data entered in the optical switch box, obtain a comparison result that is greater than the accuracy threshold, and determine the target optical switch box based on the comparison result.

[0051] According to a method for confirming optical distribution box resources provided by the present invention, obtaining an optical distribution box panel diagram that meets the identification conditions includes:

[0052] If it is determined that the proportion of objects in the optical junction box panel image is within a preset range, then the optical junction box panel image is determined to meet the recognition conditions.

[0053] The step of determining the target optical cross-connect box based on the data entered into the optical cross-connect box and the panel diagram of the optical cross-connect box further includes:

[0054] If it is determined that the optical switch box panel diagram is not the target optical switch box, then adjust the optical switch box input data and / or the optical switch box panel diagram.

[0055] Specifically, because the existing process for adding dumb resources to the network relies on manual maintenance of optical junction boxes and terminals to ensure their accuracy, even this manual review process is prone to errors. Therefore, it is proposed that... Figure 2 The diagram shows a rapid confirmation process for optical junction box resources.

[0056] First, the optical distribution box and terminals are entered, then the optical distribution box panel diagram is uploaded. After panel recognition and comparison analysis, the optical distribution box resources can be confirmed.

[0057] When manually entering data for optical junction boxes, information confirmation is usually divided into basic information and advanced attributes. For example, the basic information includes, but is not limited to, the name, the city, the district / county, the installation location, the facility type, the facility name, the coordinates including longitude and latitude, and the business category. The advanced attributes include, but are not limited to, the number of faces, the number of modules per face, the number of rows per module per face, the number of columns per module per face, the project name, and the life cycle status.

[0058] It is understood that, in order to ensure that the uploaded optical junction box panel image can be quickly and accurately identified in this invention, some recognition conditions are set for the image of the optical junction box panel, such as the object occupying a certain preset range in the photo, such as 60%-90%, and having a clear outline.

[0059] In addition, if the panel recognition and comparison fails, the system will set up to input data into the optical junction box, or readjust the panel diagram of the optical junction box, or update the data of both types of data at the same time.

[0060] This invention first determines reasonable optical distribution box resources, providing more accurate data support for subsequent confirmation of optical distribution box terminal resources.

[0061] Based on any of the above embodiments, obtaining the optical junction box terminal identification library established based on image recognition includes:

[0062] Collect more than a preset number of optical junction box panel images;

[0063] Determine the labeling sample corresponding to the multiple optical junction box panel diagram samples based on the terminal status;

[0064] The labeled image sample is decomposed into multiple small image blocks to obtain the labeling results of the labeled image sample, and terminal identification information is generated based on the labeling results;

[0065] The terminal identification information is input into a preset small neural network, and the terminal identification information corresponding to each small image block is extracted into a number sequence to form the optical junction box terminal identification library.

[0066] The step of determining the terminal resources in the target optical distribution box based on the optical distribution box terminal identification library includes:

[0067] The optical switch box panel image corresponding to the target optical switch box is reduced by pixel sampling to obtain the reduced panel image;

[0068] If the terminal information in the reduced rear panel diagram is consistent with that in the optical junction box terminal identification library, the terminal information is output as the terminal resource; otherwise, the terminal information is determined to be an error.

[0069] The terminal states include idle state, occupied state, and unused state.

[0070] Specifically, such as Figure 3 The flowchart shown above illustrates the training process for the optical distribution box terminal recognition library. First, images of optical distribution box panels that meet the following criteria must be collected: the object occupies 60% to 90% of the photo and its outline is clear. Then, the collected optical distribution box panel images are labeled. To ensure the training effect, a certain number of labeled photos are required, usually no less than 200. Next, the terminals are labeled according to their status. There are generally three status categories: free, busy, and empty, which correspond to the idle, occupied, and unoccupied states of the terminals, respectively. The unoccupied state refers to an empty rack without a tray, i.e., no terminals are installed.

[0071] Then, analysis data is generated based on the annotation results, and this data is then imported into a small neural network. The results of each small image patch are stored in a new sequence to form an optical junction box terminal recognition library.

[0072] Next, when identifying terminals, the image of the optical junction box panel is first reduced in pixels. The similarity is then analyzed using the optical junction box terminal identification library to make a prediction. If a match is found, the identified terminal resource is output; otherwise, an inconsistency is considered, and an incorrect result is output. Figure 4The flowchart shown is for the identification process of the optical junction box terminals. The process involves identifying the number of rows and columns of terminals. If a match is found, the comparison continues; otherwise, the application is rejected, and the data must be revised or a new photo uploaded. Then, the terminal status is compared. If a match is found, the application is considered successful and the work order is allowed to be archived. If a match is not found, the application is rejected, and the data must be revised or a new photo uploaded, until a successful match is achieved.

[0073] The proposed method for rapid verification of optical junction box resources not only ensures the accuracy of resources but also reduces the workload of manual verification, reduces the time spent on resource verification, reduces manpower input, reduces costs and increases efficiency, and enhances the competitiveness of operators.

[0074] The optical distribution box resource verification system provided by the present invention is described below. The optical distribution box resource verification system described below and the optical distribution box resource verification method described above can be referred to in correspondence.

[0075] Figure 5 This is a schematic diagram of the optical junction box resource verification system provided by the present invention, as shown below. Figure 5 As shown, it includes: a first processing module 51 and a second processing module 52, wherein:

[0076] The first processing module 51 is used to determine the target optical distribution box based on the data entered into the optical distribution box and the panel diagram of the optical distribution box; the second processing module 52 is used to obtain the optical distribution box terminal identification library established based on image recognition, and determine the terminal resources in the target optical distribution box based on the optical distribution box terminal identification library.

[0077] This invention, starting from the complex communication network data, introduces image recognition technology without changing the original system software architecture to achieve rapid identification and calibration of resources such as optical junction boxes and optical fiber distribution boxes, thereby improving the accuracy of dumb resources and reducing manual workload.

[0078] Figure 6 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 6 As shown, the electronic device may include a processor 610, a communications interface 620, a memory 630, and a communication bus 640. The processor 610, communications interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions in the memory 630 to execute an optical distribution box resource confirmation method. This method includes: determining a target optical distribution box based on optical distribution box input data and an optical distribution box panel diagram; acquiring an optical distribution box terminal identification library established based on image recognition; and determining the terminal resources in the target optical distribution box based on the optical distribution box terminal identification library.

[0079] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0080] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the optical distribution box resource confirmation method provided by the above methods. The method includes: determining a target optical distribution box based on optical distribution box input data and an optical distribution box panel diagram; obtaining an optical distribution box terminal identification library established based on image recognition; and determining the terminal resources in the target optical distribution box based on the optical distribution box terminal identification library.

[0081] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program implements the optical distribution box resource confirmation method provided by the above methods. The method includes: determining a target optical distribution box based on optical distribution box input data and an optical distribution box panel diagram; acquiring an optical distribution box terminal identification library established based on image recognition; and determining the terminal resources in the target optical distribution box based on the optical distribution box terminal identification library.

[0082] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0083] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An optical convergence box resource confirmation method, characterized in that, The method comprises the following steps: Based on the optical distribution frame input data and the optical distribution frame panel diagram, the target optical distribution frame is determined; The method comprises the following steps: According to the networking requirements, the basic information and advanced attributes of the optical distribution frame are determined, and the optical distribution frame input data is formed by the basic information and the advanced attributes; An optical distribution frame panel diagram meeting the identification condition is obtained, the optical distribution frame panel diagram is compared with the optical distribution frame input data, and a comparison result greater than a correct rate threshold is obtained, and the target optical distribution frame is determined according to the comparison result; If it is determined that the optical distribution frame panel diagram is not the target optical distribution frame, the optical distribution frame input data and / or the optical distribution frame panel diagram is adjusted; An optical distribution frame terminal identification library established based on image recognition is obtained, and the terminal resources in the target optical distribution frame are determined based on the optical distribution frame terminal identification library.

2. The OCB resource confirmation method of claim 1, wherein, The method comprises the following steps: If it is determined that the object proportion in the optical distribution frame panel diagram is within a preset range, it is determined that the optical distribution frame panel diagram meets the identification condition.

3. The OCB resource confirmation method of claim 1, wherein, The method comprises the following steps: More than a preset number of optical distribution frame panel diagram samples are collected; According to the terminal state, a labeled sample corresponding to the optical distribution frame panel diagram sample is determined; The labeled sample is decomposed into multiple small blocks, the labeling result of the labeled sample is obtained, and terminal identification information is generated based on the labeling result; The terminal identification information is input into a preset small neural network, the terminal identification information corresponding to each small block is extracted into a sequence, and the optical distribution frame terminal identification library is constituted.

4. The OCB resource confirmation method of claim 3, wherein, Based on the optical distribution frame terminal identification library, the terminal resources in the target optical distribution frame are determined, which comprises the following steps: The optical distribution frame panel diagram corresponding to the target optical distribution frame is subjected to reduced pixel sampling, and a reduced panel diagram is obtained; The reduced panel diagram is compared with the optical distribution frame terminal identification library, if it is determined that the terminal information in the reduced panel diagram is consistent with the optical distribution frame terminal identification library, the terminal information is output as the terminal resources, otherwise, it is determined that the terminal information is error information.

5. The ODC resource confirmation method of claim 3 or 4, wherein, The terminal state comprises an idle state, an occupied state and an empty state.

6. An optical demarcation box resource confirmation system, characterized by, The method comprises the following steps: A first processing module is configured to determine a target optical distribution frame based on optical distribution frame input data and an optical distribution frame panel diagram; The method comprises the following steps: According to the networking requirements, the basic information and advanced attributes of the optical distribution frame are determined, and the optical distribution frame input data is formed by the basic information and the advanced attributes; an optical distribution frame panel diagram meeting the identification condition is obtained, the optical distribution frame panel diagram is compared with the optical distribution frame input data, and a comparison result greater than a correct rate threshold is obtained, and the target optical distribution frame is determined according to the comparison result; if it is determined that the optical distribution frame panel diagram is not the target optical distribution frame, the optical distribution frame input data and / or the optical distribution frame panel diagram is adjusted; A second processing module is configured to acquire a terminal identification library of the optical distribution frame established based on image recognition, and determine terminal resources in the target optical distribution frame based on the terminal identification library.

7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the optical distribution frame resource confirmation method according to any one of claims 1 to 5 when executing the program.

8. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the optical distribution frame resource confirmation method according to any one of claims 1 to 5.

Images