Optical fiber port state identification method and device, and scanning gun

Abstract

The invention relates to the field of information processing, in particular to an optical fiber port state recognition method and device and a scanning gun. The method comprises the steps that port labels on an ODF disk are scanned to obtain port information, the ports on the ODF disk are provided with corresponding labels, and the labels comprise the port information of the corresponding ports; uploading the port information to a terminal, wherein the port information is used for indicating the terminal to bind the label and the port; when it is confirmed that binding of the label and the port is completed, scanning the label of a to-be-identified port on an ODF disk to obtain port information of the to-be-identified port, and synchronously collecting image information of the to-be-identified port; identifying a port state according to the acquired image information to obtain state information of the to-be-identified port; associating the state information with the port information of the port to be identified; and transmitting the associated state information and port information to the terminal. According to the embodiment of the invention, the method achieves the recognition of the state of the optical fiber port, and provides an effective condition for the state management of the optical fiber port.

Description

Technical Field

[0001] The present invention relates to the field of information processing, and more specifically, to an optical fiber port state identification method and device, and a scanning gun. Background Art

[0002] The communication room is one of the core facilities of modern communication technology, including the storage of network equipment network connection, network security management, data security and backup, and room management and maintenance. It carries the infrastructure of wireless communication, provides people with convenient communication services, plays a vital role in the information society, and provides important guarantees for the stability and reliability of network communications. For the ODF racks set up in the communication room, the traditional management method is to record them manually. Since there are many ODF ports in the ODF rack, the manual maintenance cost is high. At the same time, when the number and status of dumb resources such as ODF ports and jump fibers are digitally modified, it is necessary for the operation and maintenance personnel to go to the site for manual identification, which has low identification efficiency, and there are various problems such as the operation and maintenance personnel not reporting or input errors leading to reporting errors. Summary of the invention

[0003] The present invention aims to overcome at least one defect (shortcoming) of the above-mentioned prior art and provide a method and device for identifying the status of an optical fiber port, and a scanning gun for achieving the effect of real-time identification of the status of an optical fiber port.

[0004] According to a first aspect of the present application, a method for identifying an optical fiber port status is provided, the method comprising:

[0005] Scanning a port label on the ODF disk to obtain port information, wherein a port on the ODF disk is installed with a corresponding label, and the label contains the port information of the corresponding port;

[0006] Uploading the port information to a terminal, wherein the port information is used to instruct the terminal to bind the tag and the port;

[0007] When it is confirmed that the label and the port are bound, the label of the port to be identified on the ODF disk is scanned to obtain the port information of the port to be identified, and the image information of the port to be identified is simultaneously collected;

[0008] Identify the port status according to the collected image information to obtain the status information of the port to be identified;

[0009] Associating the status information with the port information of the port to be identified;

[0010] The associated state information and port information are transmitted to the terminal.

[0011] The optical fiber port status recognition method can realize the status recognition of the optical fiber port status, and recognizes the collected optical fiber port status image by synchronously collecting the corresponding label of the port and the optical fiber port status image, and judges the optical fiber port status by combining an efficient image processing chip, so that the port information and port status information of the port can be synchronously obtained, with fast recognition speed and high accuracy.

[0012] Optionally, scanning the label of the port to be identified on the ODF disk to obtain the port information of the port to be identified, and collecting the image information of the port to be identified includes:

[0013] Scan the label corresponding to the port to be identified on the ODF disk through radio frequency identification to obtain the port information corresponding to the port to be identified;

[0014] The image collection area corresponding to the port to be identified on the ODF disk is photographed to collect image information of the port to be identified.

[0015] The RFID scanning and shooting rely on a scanner. The scanner scans and identifies the labels corresponding to the ports to be identified to obtain the port information corresponding to the ports, and shoots the image collection area corresponding to the ports to be identified. The image information of the ports to be identified is obtained by shooting, and the two are associated to facilitate subsequent updates and status queries of any port status.

[0016] Optionally, the identifying the port status according to the collected image information to obtain the status information of the port to be identified includes:

[0017] The AI ​​intelligent recognition model is used to extract shape features and / or image features from the collected image information, and the port status of the port to be identified is identified according to the extracted shape features and image features to obtain the status information of the port to be identified.

[0018] The AI ​​intelligent recognition model can analyze and learn autonomously based on the increasing data, and then adjust its own algorithm model to improve its adaptability. It can process a large amount of sample data, extract, classify, mine and analyze information quickly and accurately, continuously optimize the recognition process, improve recognition efficiency and accuracy, and have a certain degree of security and confidentiality, and can build a safe, stable, efficient, reliable and cost-effective working form.

[0019] Optionally, the AI ​​intelligent recognition model is integrated into the K210 chip.

[0020] The K210 chip has low power consumption but strong computing power, which is suitable for edge computing scenarios, powerful neural network acceleration capabilities, and can perform machine vision and auditory processing. It has a dual-core 64-bit RISC-V processor, each core is equipped with an independent FPU (floating point unit), which can efficiently perform complex computing tasks. At the same time, it provides a variety of communication interfaces, including UART, SPI, I2C, JTAG and USB, etc., which is convenient for communication with other devices or systems. It has machine vision capabilities, can perform real-time image processing and analysis, and is suitable for a variety of visual recognition tasks. The method will apply its advantages and can efficiently identify fiber port status images.

[0021] Optionally, the AI ​​intelligent recognition model is pre-trained based on the following training steps:

[0022] The AI ​​intelligent recognition model is pre-trained based on the following training steps:

[0023] Image sample data of the acquisition port;

[0024] Preprocessing the image sample data, and annotating the port status of the preprocessed image sample data to obtain an annotation result;

[0025] The labeled image sample data is split into a training set and a validation set;

[0026] The AI ​​intelligent recognition model is trained and tested according to the training set and the validation set to obtain a pre-trained AI intelligent recognition model.

[0027] The pre-trained AI intelligent recognition model can learn deeper feature representations through training on a large amount of sample data, and has a certain feature foundation, so that it can perform better on specific tasks, reduce dependence on a large amount of labeled data, and enable the model to perform well even when there is less data, reduce consumption of computing resources and time, and make the training process more efficient. Optionally, the status information includes one or more of the port type status, port occupancy status, and port availability status.

[0028] The status information includes not only the port type but also the port occupancy status and the port availability status, which can timely provide maintenance personnel with the actual status of the optical fiber port, facilitating reasonable and effective judgment, thereby implementing corresponding management measures for the optical fiber.

[0029] Optionally, the port occupation state includes an idle state and an occupied state, and the port available state includes an available state and a damaged state.

[0030] According to a second aspect of the present application, a device for identifying an optical fiber port state is provided, the device comprising:

[0031] A scanning module, used for scanning a port label on the ODF disk to obtain port information, wherein a corresponding label is installed on the port on the ODF disk, and the label contains the port information of the corresponding port;

[0032] A transmission and receiving module, used for uploading the port information to a terminal, wherein the port information is used for instructing the terminal to bind the tag and the port;

[0033] An image acquisition module, used for acquiring image information of a port;

[0034] A control module, for controlling the scanning module and the image acquisition module to work synchronously when it is confirmed that the binding between the label and the port is completed, so that the scanning module scans the label of the port to be identified on the ODF disk to obtain the port information of the port to be identified, and the image acquisition module synchronously acquires the image information of the port to be identified;

[0035] An intelligent identification module is used to identify the port status according to the collected image information and obtain the status information of the port to be identified;

[0036] The control module is further used to associate the state information with the port information of the port to be identified;

[0037] The transmission and receiving module is also used to transmit the associated state information and port information to the terminal.

[0038] The optical fiber port status identification device has each module as an indispensable part, and the modules cooperate with each other. The scanning module scans the label to obtain the port information; the port information is then uploaded to the terminal via the transmission and reception module, and the port information is used to instruct the terminal to bind the label and the port; when the control module confirms that the label and the port have been bound, the scanning module and the image acquisition module are controlled to work synchronously, so that the scanning module scans the label of the port to be identified on the ODF disk to obtain the port information of the port to be identified, and the image acquisition module synchronously acquires the image information of the port to be identified; the control module associates the port information and image information of the port to be identified to form a corresponding relationship; the image information of the port to be identified is collected and finally reaches the intelligent recognition module, and the port status of the collected image information is identified to obtain the status information of the port to be identified. The transmission and reception module is also used to transmit the associated status information and port information to the terminal.

[0039] Optionally, the intelligent identification module is implemented by a K210 chip, and the K210 chip is used to identify the port status of the collected image information to obtain the status information of the port to be identified.

[0040] According to a third aspect of the present application, a scanning gun is provided, and the scanning gun is used in the optical fiber port status identification method of the first aspect mentioned above.

[0041] The scanning gun can complete the identification of the optical fiber port status. The scanning gun scans the port label on the ODF disk to obtain the port information, wherein the port on the ODF disk is installed with a corresponding label, and the label contains the port information of the corresponding port; the port information obtained by scanning is then uploaded to the terminal, and the port information is used to instruct the terminal to bind the label and the port; when the scanning gun confirms that the label and the port are bound, it uses its own radio frequency identification function to scan the label of the port to be identified on the ODF disk to obtain the port information of the port to be identified, and uses the shooting function of the scanning gun to synchronously collect the image information of the port to be identified; the port status is identified according to the collected image information to obtain the status information of the port to be identified; the status information is associated with the port information of the port to be identified; and the associated status information and port information are transmitted to the terminal.

[0042] Based on any one of the above aspects, the method and device provided in the embodiments of the present application can identify the fiber optic port status, synchronously collect the port information and the fiber optic port status image on the label corresponding to the port, and identify the collected fiber optic port status image through an efficient image processing chip to determine the fiber optic port status type, thereby obtaining the port information and port status information of the port with fast recognition speed and high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 A step diagram of a method for identifying optical fiber port status provided in this embodiment.

[0045] Figure 2 A schematic diagram of an AI intelligent recognition model pre-training for a method for identifying a fiber port status provided in this embodiment.

[0046] Figure 3 A schematic diagram of functional modules of a device for identifying optical fiber port status provided by this embodiment. DETAILED DESCRIPTION

[0047] The drawings of this application are only used for illustrative purposes and should not be construed as limiting the present application. In order to better illustrate the following embodiments, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product; it is understandable to those skilled in the art that some well-known structures and their descriptions in the drawings may be omitted.

[0048] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0049] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0050] At present, optical cable management is mainly carried out through manual operation and maintenance. When an emergency occurs, it often takes a long time to respond and handle it, which may lead to business interruption and revenue loss. At the same time, human operation is easily affected by factors such as fatigue and negligence, which may cause errors, system failures and even data loss. As the scale of the system expands, the model that relies on manual operation and maintenance requires more human resources, resulting in a significant increase in maintenance costs. The efficiency and capabilities of manual operation and maintenance are difficult to expand linearly with the growth of business, which restricts development. The lack of unified operating standards and processes makes it difficult to ensure the quality of operation and maintenance, and it is also difficult to conduct effective management and auditing. Manual identification and manual ledger recording have low levels of automation and intelligence, are difficult to implement, and cannot form effective management.

[0051] This embodiment provides a technical solution that can solve the above-mentioned problem. The specific implementation methods of this application are described in detail below in conjunction with the accompanying drawings.

[0052] like Figure 1 As shown, this embodiment provides a method for identifying the state of an optical fiber port, which may include the following steps:

[0053] S110, scanning the label of the port on the ODF disk to obtain the port information, wherein the port on the ODF disk is installed with a corresponding label, and the label contains the port information of the corresponding port;

[0054] In this embodiment, the tag can be a radio frequency tag (RFID), an NFC tag, a barcode, a QR code, a ZETA tag, a UWB tag, or infrared communication technology, etc. The above marking technology can be attached to the marker to uniquely identify and track the marker, and can automatically collect and record relevant information of the marker without human intervention, thereby improving the efficiency and accuracy of data collection and facilitating real-time updating of various real-time status such as inventory.

[0055] In an optional implementation, an RFID tag is installed on each port of the ODF disk according to the port information. The RFID tag serves as an identification to facilitate the search and positioning of the corresponding port. The RFID tag stores the port information in advance. The port information may include the location, size, model, manufacturer information, serial number and other attribute information of the port. The RFID tag is scanned using the radio frequency identification function of the scanner to obtain the port information of the corresponding port. The form of the port label of the ODF disk is not specifically limited.

[0056] In this embodiment, before installing an RFID tag on each port of the ODF disk, it is necessary to install a tag on the ODF rack to which the ODF disk belongs to facilitate management at the terminal. The tag of the ODF rack includes any one of a radio frequency tag (RFID), an NFC tag, a barcode, a QR code, a ZETA tag, a UWB tag, etc.

[0057] In an optional implementation, an NFC tag is fixed to the ODF rack. By scanning the NFC tag, the ODF rack and the terminal can be bound. Scanning an NFC tag means adding a new ODF rack. The increase or decrease of the ODF rack can be displayed on the terminal through the NFC tag. The tag form of the ODF rack includes but is not limited to this.

[0058] S120, uploading the port information to a terminal, wherein the port information is used to instruct the terminal to bind the tag and the port;

[0059] In this embodiment, the port information can be uploaded through a web form or by using FTP client software to upload files. It can also be uploaded through Secure File Transfer Protocol (SFTP), physical storage media, direct memory access (DMA), network attached storage (NAS), peer-to-peer network (P2P), content distribution network (CDN), database migration tool, command line tool, etc. The upload method selected depends on the size of the data, security requirements, transmission distance and user's technical familiarity.

[0060] In an optional implementation, the scanner scans the radio frequency tag (RFID) installed corresponding to the port and sends a radio frequency signal through the transmitting antenna. When the RFID tag enters its working area, the tag is activated and the information stored in it is read, and then uploaded to the terminal through the connected Bluetooth. The uploading method is not limited.

[0061] The port information is uploaded to facilitate the terminal or the background to bind the port and the corresponding label to form a binding relationship, so that the port information of the corresponding port can be obtained when the label of the port is scanned later.

[0062] S130, when it is confirmed that the label and the port are bound, scanning the label of the port to be identified on the ODF disk to obtain the port information of the port to be identified, and collecting the image information of the port to be identified;

[0063] In this embodiment, when the tag and the port are bound, the binding confirmation may be in the form of confirmation information or an instruction of binding completion, or in various feedback forms such as a signal.

[0064] In an optional implementation, the confirmation information is in the form of feedback after terminal binding is completed, and the confirmation information is received to perform image acquisition, status recognition tasks, etc. The feedback form includes but is not limited to this.

[0065] In this embodiment, the label of the port to be identified on the ODF disk is scanned to obtain the port information of the port to be identified, and the image information of the port to be identified is synchronously collected, and the port information and image information of the port to be identified obtained synchronously are associated. This can be performed in any time period after obtaining the confirmation information, and can be executed according to a specified task.

[0066] In an optional implementation, when the port and the label binding operation corresponding to the port are completed, it is necessary to identify the status of one or several or a certain optical fiber port on an ODF rack, which is not specifically limited here.

[0067] In this embodiment, the scanning of the label and the collection of the image information of the port are performed synchronously, so that when the label is read to determine the corresponding port, the image information of the corresponding port can be synchronously acquired, thereby identifying the port status of the corresponding port, and further completing the port information reading and port status identification of the same port.

[0068] S140, identifying the port status according to the collected image information to obtain the status information of the port to be identified, including:

[0069] The AI ​​intelligent recognition model is used to extract shape features and / or image features from the collected image information, and the port status of the port to be identified is identified according to the extracted shape features and image features to obtain the status information of the port to be identified.

[0070] In this embodiment, the port status is identified based on the collected image information to obtain the status information of the port to be identified. There are many methods of image recognition, including template matching, feature matching, deep learning, support vector machine (SVM), k-nearest neighbor algorithm (k-NN), independent component analysis (ICA), etc.

[0071] In an optional implementation, the AI ​​intelligent recognition model integrated in the K210 chip extracts shape features and / or image features from the collected image information, and uses the extracted shape features and / or image features for matching, thereby identifying the port status to obtain the status information of the port to be identified. In the recognition process, the K210 chip is used as the main control module, which contains a KPU general neural network processor with built-in convolution, batch normalization, activation, and pooling operation units, which can detect the fiber port status.

[0072] This embodiment adopts the K210 chip as the main control module, uses the internal KPU general neural network calculation core processor, and utilizes its parallel computing processing capability to improve the model matrix operation, thereby improving the reasoning speed and efficiency of the model and realizing rapid detection of the fiber optic port status.

[0073] The whole process of processing image sample data based on K210 chip is divided into collecting sample data, preprocessing, labeling, data splitting, modifying training parameters, exporting tflite model, and converting it into inference model file in kmodel format that can be used by nncase. The specific implementation process includes:

[0074] Collect image sample data of the port. The image sample data comes from the optical fiber disks with different light intensities. Use the camera to take pictures of the optical fiber port status in turn and save them. Specifically, the image captured by the camera can be cropped in the middle, and only the image with a size of 240*240 pixels in the middle part is taken and saved as a jpg format image.

[0075] The collected sample data is preprocessed to process some useless data, including missing data, wrong data format, wrong data or duplicate data. After preprocessing, the preprocessed image sample data is labeled to separate the fiber port type and status under normal circumstances into two data groups.

[0076] In an optional implementation, the state of the port includes one or more of a port type state, a port occupied state, and a port available state. The port type state includes a port type FC or SC, the port occupied state includes an idle state and an occupied state, and the port available state includes an available state and a damaged state. Based on this, the port state of each port may include an idle FC header, an idle SC header, an occupied FC header, an occupied SC header, damaged, or empty.

[0077] The marking results are distinguished by marking, and the marking can be divided into five categories, including free FC header, free SC header, occupied FC header, occupied SC header, damaged or empty.

[0078] The labeled data results are divided into training set and validation set. According to the ratio of 8:2, 80% of the image data are randomly extracted from the labeled data as the training set, and 20% of the image data are used as the validation set. The training parameters need to be modified according to the data volume and hardware parameters, and the parameters are adjusted according to the epoch iteration number value, batch size value, learnrate learning rate value and classification number value.

[0079] The model file in tflite format is obtained through training with the TensorFlow deep learning framework, and then the model file in tflite format is converted into the kmodel format that can be used by NNCASE. The kmodel format is finally exported through NNCASE module compilation. Then, the fiber optic port type and status detection application is designed using the MaixPy language to realize the inference model KPU loading and KPU image data processing, and finally the fiber optic port status detection results are output.

[0080] After training and testing the KPU universal neural network inside the K210 chip, it can be directly used for subsequent processing and recognition of port image information.

[0081] S150, associating the state information with the port information of the port to be identified;

[0082] In an optional implementation, the status information is associated with the port information of the port to be identified by a scanner, which scans the port information to be identified and identifies the port status information, associates the port status information with the port information to be identified, and uploads them to the terminal together.

[0083] S160: Transmit the associated state information and port information to the terminal.

[0084] In this embodiment, the association enables the terminal to receive status information and port information and match them with the port, so that the port status information and port information can be associated and saved, and the port status to be identified can be displayed in real time, making it easy to understand the port status information based on the port information.

[0085] In this embodiment, the terminal may be integrated with the scanning device or may be independent.

[0086] In an optional implementation, the terminal may be a mobile phone APP terminal, and the port information and optical fiber port status information collected and identified by scanning with a scanner will be uploaded to the mobile phone APP terminal via a Bluetooth connection, so as to facilitate viewing and timely understanding of the working status of the optical fiber port. The terminal is not specifically limited.

[0087] In an optional embodiment, illustratively, Figure 2 A schematic diagram of pre-training of an AI intelligent recognition model for a method for identifying a fiber port status provided in an embodiment of the present application, wherein the specific steps of step S140 may include:

[0088] S141, collecting image sample data of the port;

[0089] S142, preprocessing the image sample data, and annotating the port status of the preprocessed image sample data to obtain an annotation result;

[0090] S143, splitting the labeled image sample data into a training set and a validation set;

[0091] S144. Train and test the AI ​​intelligent recognition model according to the training set and the validation set to obtain a pre-trained AI intelligent recognition model.

[0092] The optical fiber port status identification method of the present application binds the port and the label in advance. When the port status needs to be obtained, the port information is obtained by scanning the label corresponding to the port. While scanning, the image information of the port is synchronously collected. The port status is identified by the image information, and finally the port information and port status of the port are obtained, thereby completing the port status identification in one step. The whole method is simple to operate and the identification is fast, and the effect of implementing the identification of the optical fiber port status can be achieved.

[0093] like Figure 3 As shown, the embodiment of the present application further provides a fiber optic port status identification device 610.

[0094] Optionally, the optical fiber port state identification device 610 may include:

[0095] A scanning module 611 is used to scan the labels of each port on the ODF disk one by one to obtain the port information, wherein each port on the ODF disk is installed with a corresponding label, and the label contains the port information of the corresponding port;

[0096] In this embodiment, the scanning module 611 can be used to perform Figure 1 As shown in step S110 , for a detailed description of the scanning module 611 , reference may be made to the description of step S110 .

[0097] The transmission and receiving module 612 is used to upload the port information one by one and obtain confirmation information of successful binding of the tag and the corresponding port, wherein the confirmation information is generated after binding the corresponding tag and the port according to the port information obtained by scanning;

[0098] In this embodiment, the transmission and reception module 612 can be used to perform Figure 1 As shown in step S120, for the detailed description of the transmission and reception module 612, reference may be made to the description of step S120.

[0099] Image acquisition module 613, used for acquiring image information of the port;

[0100] In this embodiment, the image acquisition module 613 can be used to perform Figure 1 As shown in step S130, for the detailed description of the image acquisition module 613, reference may be made to the description of step S130.

[0101] The control module 614 is used to control the scanning module and the image acquisition module to work synchronously after obtaining the confirmation information, so that the scanning module scans the label of the port to be identified on the ODF disk to obtain the port information of the port to be identified, and the image acquisition module synchronously acquires the image information of the port to be identified;

[0102] The control module 614 is also used to associate the port information and image information of the port to be identified obtained synchronously;

[0103] In this embodiment, the control module 614 can be used to execute Figure 1 As shown in step S140 , for a detailed description of the control module 614 , reference may be made to the description of step S140 .

[0104] Intelligent identification module 615, used to identify the port status according to the collected image information to obtain the status information of the port to be identified;

[0105] In this embodiment, the intelligent identification module 615 can be used to perform Figure 1 As shown in step S150, for a detailed description of the intelligent identification module 615, reference may be made to the description of step S150.

[0106] The control module 616 is further configured to summarize the port information and state information of the port to be identified based on the association to complete the state identification of the port to be identified.

[0107] In this embodiment, the control module 616 can be used to execute Figure 1 As shown in step S160, for the detailed description of the control module 616, reference may be made to the description of step S160.

[0108] It can be understood that the above-mentioned device embodiments and the above-mentioned method embodiments can correspond to each other, and similar descriptions of the device embodiments can refer to the method embodiments. To avoid repetition, it will not be repeated here. A fiber optic port state identification device provided in an embodiment of the present application can execute a fiber optic port state identification method provided in any embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method. The functional modules of the fiber optic port state identification device can be implemented in the form of hardware, can be implemented by instructions in the form of software, and can also be implemented by a combination of hardware and software modules.

[0109] Specifically, each step of the method embodiment of the present application can be completed by the hardware integrated logic circuit and / or software instructions in the processor, and the steps of the optical fiber port status identification method in the embodiment of the present application can be directly embodied as a hardware coding processor, or a combination of hardware and software modules in the coding processor. Optionally, the software module can be located in a random access memory, a read-only memory, a programmable read-only memory, a flash memory, an electrically erasable programmable memory, a register, and other storage media. The storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps in the above method embodiment in combination with its hardware.

[0110] In the specific implementation process, the scanning module 611 can be implemented by an RFID scanning device, the image acquisition module 613 can be implemented by a camera, the control module 614 can be implemented by a K210 chip as a main control module, and the transmission and receiving module 612 can be implemented by a commonly used communication module, such as a 4G communication module, a 5G communication module, etc. In the specific implementation, the scanning module 611, the transmission and receiving module 612, the image acquisition module 613, and the control module 614 can be integrated on a handheld terminal. The handheld terminal can be used to conveniently identify the status of the port on the ODF rack, making the entire operation simple, fast and convenient, and realizing the port status identification in one step, thereby achieving the effect of identifying the status of the optical fiber port.

[0111] The present application also provides a scanning gun, which is specifically used to perform the following steps:

[0112] Scanning a port label on the ODF disk to obtain port information, wherein a port on the ODF disk is installed with a corresponding label, and the label contains the port information of the corresponding port;

[0113] Uploading the port information to a terminal, wherein the port information is used to instruct the terminal to bind the tag and the port;

[0114] When it is confirmed that the label and the port are bound, the label of the port to be identified on the ODF disk is scanned to obtain the port information of the port to be identified, and the image information of the port to be identified is collected;

[0115] Identify the port status according to the collected image information to obtain the status information of the port to be identified;

[0116] Associating the status information with the port information of the port to be identified;

[0117] The associated state information and port information are transmitted to the terminal.

[0118] In this embodiment, the scanning gun can realize the recognition of the status of the optical fiber port. The scanning gun obtains the port information by scanning the corresponding label of the port, and uses the scanning gun to take a picture of the status image of the port. Combined with the built-in efficient image processing chip, the captured optical fiber port status image is recognized to judge the optical fiber port status. The port information and port status information of the port can be obtained synchronously and the two can be associated, which can provide an effective status reference with fast recognition speed and high accuracy.

[0119] In a specific implementation process, scanning the label of the port to be identified on the ODF disk to obtain the port information of the port to be identified, and collecting the image information of the port to be identified may include:

[0120] Scan the label corresponding to the port to be identified on the ODF disk through radio frequency identification to obtain the port information corresponding to the port to be identified;

[0121] The image collection area corresponding to the port to be identified on the ODF disk is photographed to collect image information of the port to be identified.

[0122] The radio frequency identification function of the scanner is used to obtain the port information by scanning the corresponding port label; the shooting function of the scanner can shoot the image collection area corresponding to the port to be identified on the ODF disk to realize the collection of image information of the port to be identified.

[0123] In a specific implementation process, the identifying of the port status according to the collected image information to obtain the status information of the port to be identified may include:

[0124] The AI ​​intelligent recognition model is used to extract shape features and / or image features from the collected image information, and the port status of the port to be identified is identified according to the extracted shape features and image features to obtain the status information of the port to be identified.

[0125] The scanner has a built-in K210 chip, and the AI ​​intelligent recognition model is integrated in the K210 chip. The AI ​​intelligent recognition model integrated in the K210 chip extracts shape features and / or image features from the collected image information, and uses the extracted shape features and / or image features for matching, thereby identifying the port status and obtaining the status information of the port to be identified. In a preferred embodiment, the AI ​​intelligent recognition model can be pre-trained based on the following training steps: collect image sample data of the port;

[0126] Preprocessing the image sample data, and annotating the port status of the preprocessed image sample data to obtain an annotation result;

[0127] The labeled image sample data is split into a training set and a validation set;

[0128] The AI ​​intelligent recognition model is trained and tested according to the training set and the validation set to obtain a pre-trained AI intelligent recognition model.

[0129] The AI ​​intelligent recognition model is pre-trained to learn common features from a large amount of image data. In the target task, the pre-trained model can better utilize these common features to improve performance, which helps to improve the generalization ability of the model, that is, to perform well on unseen image data, while reducing relatively high costs. In traditional image processing models, usually only the modeling of a single task is focused, but in the scenario where pre-training is combined with image processing models, a more complex model architecture can be designed to handle multiple tasks at the same time, effectively improving the efficiency of image processing.

[0130] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the technical solution of the present invention, and are not intended to limit the specific implementation methods of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the claims of the present invention shall be included in the protection scope of the claims of the present invention.

Claims

1. A method for identifying an optical fiber port status, characterized in that: The method is applied to a scanning gun, and the method comprises: Scanning a port label on the ODF disk to obtain port information, wherein a port on the ODF disk is installed with a corresponding label, and the label contains the port information of the corresponding port; Uploading the port information to a terminal, wherein the port information is used to instruct the terminal to bind the tag and the port; When it is confirmed that the label and the port are bound, the label of the port to be identified on the ODF disk is scanned to obtain the port information of the port to be identified, and the image information of the port to be identified is collected; Identify the port status according to the collected image information to obtain the status information of the port to be identified; Associating the status information with the port information of the port to be identified; The associated state information and port information are transmitted to the terminal.

2. A method for identifying an optical fiber port status according to claim 1, characterized in that: The scanning of the label of the port to be identified on the ODF disk to obtain the port information of the port to be identified, and collecting the image information of the port to be identified, includes: Scan the label corresponding to the port to be identified on the ODF disk through radio frequency identification to obtain the port information corresponding to the port to be identified; The image collection area corresponding to the port to be identified on the ODF disk is photographed to collect image information of the port to be identified.

3. A method for identifying an optical fiber port status according to claim 2, characterized in that: The identifying of the port status according to the collected image information to obtain the status information of the port to be identified includes: The AI ​​intelligent recognition model is used to extract shape features and / or image features from the collected image information, and the port status of the port to be identified is identified according to the extracted shape features and image features to obtain the status information of the port to be identified.

4. A method for identifying an optical fiber port status according to claim 2, characterized in that: The AI ​​intelligent recognition model is integrated into the K210 chip.

5. A method for identifying optical fiber port type and status according to claim 2, characterized in that: The AI ​​intelligent recognition model is pre-trained based on the following training steps: collecting image sample data of the port; Preprocessing the image sample data, and annotating the port status of the preprocessed image sample data to obtain an annotation result; The labeled image sample data is split into a training set and a validation set; The AI ​​intelligent recognition model is trained and tested according to the training set and the validation set to obtain a pre-trained AI intelligent recognition model.

6. A method for identifying an optical fiber port status according to any one of claims 1 to 5, characterized in that: The status information includes one or more of a port type status, a port occupation status, and a port availability status.

7. A method for identifying optical fiber port status according to claim 6, characterized in that: The port occupation state includes an idle state and an occupied state, and the port available state includes an available state and a damaged state.

8. An optical fiber port status identification device, characterized in that: The device comprises: A scanning module, used for scanning a port label on the ODF disk to obtain port information, wherein a corresponding label is installed on the port on the ODF disk, and the label contains the port information of the corresponding port; A transmission and receiving module, used for uploading the port information to a terminal, wherein the port information is used for instructing the terminal to bind the tag and the port; An image acquisition module, used for acquiring image information of a port; A control module, for controlling the scanning module and the image acquisition module to work synchronously when it is confirmed that the binding between the label and the port is completed, so that the scanning module scans the label of the port to be identified on the ODF disk to obtain the port information of the port to be identified, and the image acquisition module synchronously acquires the image information of the port to be identified; An intelligent identification module is used to identify the port status according to the collected image information and obtain the status information of the port to be identified; The control module is further used to associate the state information with the port information of the port to be identified; The transmission and receiving module is also used to transmit the associated state information and port information to the terminal.

9. The optical fiber port status identification device according to claim 8, characterized in that: The intelligent identification module is implemented by a K210 chip, and the K210 chip is used to identify the port status of the collected image information to obtain the status information of the port to be identified.

10. A scanning gun, characterized in that: The scanning gun is used to execute the optical fiber port status identification method according to any one of claims 1 to 7.

Images