Spectrometer resource accuracy automatic detection system and method based on digital twinning and ai

Abstract

The application discloses a digital twin and AI-based optical splitter resource accuracy automatic detection system and method, which comprises the following modules: a digital twin module for digital twin modeling of an optical splitter device; a twin construction module for generating a construction scheme, a post-construction twin ecological model and related characteristic value change conditions; an image acquisition module for acquiring image information of a port panel of the optical splitter device; an image analysis module for extracting optical splitter device port state and characteristic information; a port change labeling module for analyzing and labeling changes in the optical splitter device port state, extracting characteristic values and characteristic value change conditions; a reality & twin verification module for verifying the optical splitter characteristic value change conditions and judging the optical splitter resource use accuracy; and an abnormal occupation alarm module for prompting further on-site review of the verified abnormal optical splitter. The application realizes automatic identification and illegal warning of optical splitter device resources.

Description

Technical Field

[0001] This invention belongs to the field of optical splitting equipment technology, specifically relating to an automatic detection system and method for optical splitter resource accuracy based on digital twins and AI. Background Technology

[0002] Currently, optical broadband services mainly rely on optical splitters as end-point access devices. However, optical splitters are passive optical power distribution devices and cannot automatically collect port occupancy status. Resource accuracy management can only be achieved through on-site verification and manual recording by maintenance personnel. Although the optical broadband service activation process requires staff to take photos of the optical splitters, this can only be done manually, resulting in a large workload and low verification rate.

[0003] Deep learning-based object detection technology has seen widespread application in computer vision in recent years. It eliminates the need for manually designed features; instead, it trains corresponding models for different detection scenarios, significantly improving detection accuracy and generalization. With the upgrading of video surveillance equipment and the improvement of terminal imaging capabilities, the widespread application and popularization of high-definition video / image acquisition and transmission have significantly enhanced the level of detail recognition in videos / images, providing strong support for the accuracy and feasibility of automatic image recognition by optical splitting devices.

[0004] With the widespread adoption of digital twin technology, it has also begun to be applied to the field of equipment management. For optical splitter equipment with a large number of ports, the use of digital twin technology for twin management can effectively improve the accuracy of optical splitter resource management. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to address the shortcomings of the prior art by providing an automatic detection system and method for the accuracy of optical splitter resources based on digital twins and AI, so as to realize automatic identification and violation warning of optical splitter resources.

[0006] To achieve the above-mentioned technical objectives, the technical solution adopted by the present invention is as follows:

[0007] The automatic detection system for splitter resource accuracy based on digital twins and AI includes: a digital twin module, a twin construction module, an image acquisition module, an image analysis module, a port change annotation module, a reality & twin verification module, and an abnormal occupancy alarm module.

[0008] Among them, the digital twin module: uses digital twin technology to create a digital twin model of the information of the optical splitter equipment;

[0009] Twin construction module: Based on the digital twin module and combined with the construction work order information, the construction is simulated on the digital twin model of the splitter, the construction plan is generated, and the corresponding post-construction twin model and related feature value changes are generated.

[0010] Image acquisition module: Acquires image information from the port panel of the optical splitter via a monitoring camera or acquisition terminal and uploads it to the image analysis module;

[0011] Image analysis module: The video / image analysis server identifies the acquired video or images, extracts and records the port status and feature information of the optical splitter;

[0012] Port Change Annotation Module: Combines the port status and feature information of the optical splitter extracted from the current video or image with the status and feature information from the previous image to analyze and annotate the changes in the port status of the optical splitter, and extract feature values ​​and the changes in feature values.

[0013] Reality & Twin Verification Module: Based on the on-site splitter feature value data obtained by the image analysis module and the splitter feature value changes obtained by the port change annotation module, the module verifies the splitter feature values ​​in the digital twin module and the feature value changes generated by the twin construction module to determine the accuracy of splitter resource usage.

[0014] Abnormal usage alarm module: For splitters with abnormal use of splitter resources, query the person in charge of the splitter equipment and prompt relevant staff to conduct further on-site verification.

[0015] To optimize the above technical solution, the specific measures also include:

[0016] The information of the aforementioned optical splitter device includes basic information, port information, port status, port characteristics, wire sequence status, wire sequence label, and wire sequence characteristic information.

[0017] The aforementioned optical splitter port statuses include idle, occupied, and blocked states.

[0018] In the aforementioned Reality & Twin Verification Module, a basic comparison of feature information in the real world and the twin is performed. If the feature information is consistent, it is determined that there is no abnormality. If the features of the real world and the twin change, intelligent verification is performed to detect abnormal usage. For problems that the machine cannot accurately identify, feedback is given to human verification, while the machine algorithm is optimized. The accuracy of the real-world splitter resource usage is determined through information verification.

[0019] The above-described system implements an automatic detection method for the accuracy of beam splitter resources based on digital twins and AI, characterized in that the beam splitter resource accuracy checking steps include:

[0020] Step 1: The digital twin module uses digital twin technology to create a digital twin model of the information of the beam splitter equipment, generate a running beam splitter model, and support the extraction of feature values ​​by modifying feature parameters, participating in the accuracy verification of video / images;

[0021] Step 2: The image acquisition module collects port video information of the optical splitter in real time through the video monitoring equipment and sends the collected video stream information to the video analysis server.

[0022] Step 3: In the video analysis server, the video is parsed and processed to extract the feature information of the splitting device, identify the port status of the splitting device, and send the relevant feature information of the splitting device and port usage status information to the port change annotation module to realize port change annotation.

[0023] Step 4: The Reality & Twin Verification Module sends the feature information of the beam splitter image / video obtained in Step 3 to the digital twin server to complete the twin setting and generate the corresponding twin beam splitter feature information in the scene. The feature information of the real image / video and the scene-revised twin beam splitter feature information are then verified.

[0024] Step 5: The abnormal occupancy alarm module analyzes the abnormal situations found in Step 4, obtains the corresponding construction personnel information through the basic information of the optical splitter, and sends relevant abnormal alarms to prompt the staff to conduct on-site verification.

[0025] The aforementioned characteristic parameters include environment, angle, lighting, visibility, and occlusion parameters;

[0026] The characteristic information of the beam splitter is divided into two parts: one part is the characteristic information of the beam splitter itself, and the other part is the characteristic information related to the current environment of the beam splitter and the acquisition angle during the acquisition.

[0027] Step four above includes: performing a basic comparison of feature information between the real and twin versions, and determining that there are no anomalies if the feature information is consistent; performing intelligent verification through error analysis, simulation judgment, and machine recognition algorithms to identify abnormal usage if the features of the real and twin versions change; providing feedback to human verification for problems that the machine cannot accurately identify, while optimizing the machine algorithm; verifying the accuracy of resource usage through information verification, and synchronizing information with the abnormal usage module if an anomaly is found.

[0028] The above-described system implements an automatic detection method for the accuracy of beam splitter resources based on digital twins and AI. The method is characterized by the following steps for checking the accuracy of beam splitter construction:

[0029] Step 1: The digital twin module uses digital twin technology to create a digital twin model of the information of the beam splitter equipment, generate a running beam splitter model, and support the extraction of feature values ​​by modifying feature parameters, participating in the accuracy verification of video / images;

[0030] Step 2: When construction work order information is generated, the twin construction module calls the running beam splitter model from the digital twin service, performs construction simulation on it according to the work order content, generates the optimal construction plan, generates the design beam splitter model and related feature values, and supports the extraction of running state >> design state feature values ​​and their changes by modifying feature parameters, participating in the accuracy verification of construction.

[0031] Step 3: Before and after construction, the image acquisition module collects the port video information of the optical splitter in real time through the video monitoring equipment, and sends the collected video stream information to the video analysis server;

[0032] Step 4: Image analysis module. In the video analysis server, the images before and after construction are analyzed and processed to extract the feature information of the splitting equipment, identify the port usage status information of the splitting equipment, and send the relevant splitting equipment feature information and port usage status information to the port change annotation module for port change annotation service.

[0033] Step 5: The Reality & Twin Verification Module sends the feature information of the beam splitter images / videos before and after construction obtained in Step 4 to the Digital Twin / Twin Construction Module. This completes the twin setup and generates corresponding twin beam splitter feature information and feature value change information for the scene. The module then verifies the feature information and feature value change information of the real image / video with the twin beam splitter feature information and feature value change information after scene revision to check the accuracy of the construction. If abnormal construction is found, the module synchronizes the information with the abnormal occupancy module.

[0034] Step Six: The abnormal occupancy alarm module analyzes the abnormal situations found in Step Four, obtains the corresponding construction personnel information through the basic information of the optical splitter, sends relevant abnormal alarm information, and prompts the staff to conduct on-site verification.

[0035] The present invention has the following beneficial effects:

[0036] 1. Introduce AI video / image analysis capabilities and link them with information such as construction records of optical splitting equipment to achieve automatic detection of construction compliance of optical splitting equipment and automatic identification of optical splitting equipment resource status, replacing manual inspection, thereby realizing intelligent management of port resources, improving the level of network security production services, achieving the goal of reducing operational costs and increasing efficiency, and solving problems such as inaccurate optical splitting equipment port status that cannot be put into production and use, huge sunk costs, and failure to detect illegal construction operations of important optical splitting equipment in a timely manner;

[0037] 2. Extract environmental and acquisition angle features from the beam splitter through image / video analysis and simulate them in a twin model. Extract the corresponding twin feature information, investigate the influence of the beam splitter's environment and acquisition status, ensure the accuracy of information verification, and eliminate the differences in the beam splitter's state between the twin environment and the actual acquisition process.

[0038] 3. Introduce digital twin technology to create digital twins of the splitter resources. By comparing and verifying the twin simulation of the current status of the splitter with the actual acquired video images, the accuracy of the splitter resource usage can be judged. This enables accurate identification and management of the splitter equipment resources, avoiding the problem of abnormal alarms caused by errors in the identification of densely packed splitter ports when there are port obstructions or low monitoring pixels.

[0039] 4. By relying on digital twins and combining them with construction work orders to complete the twin simulation of construction, the optimal construction plan is generated, and on-site construction is guided and the construction results are verified. By simulating the construction work orders, the characteristic value changes of the optimal execution plan are generated, and the changes of image characteristic values ​​of video / image acquisition before and after construction are verified. If the changes exceed the tolerance, an early warning is issued and manual verification is performed to ensure the accuracy of construction. Attached Figure Description

[0040] Figure 1 This is a schematic diagram of the automatic detection system for the accuracy of spectrometer resources based on digital twins and AI, as described in this invention.

[0041] Figure 2 This is the operational logic diagram of the automatic detection system for the accuracy of spectrometer resources based on digital twins and AI, as described in this invention.

[0042] Figure 3 This is a logic diagram for checking the accuracy of the splitter resources in this invention;

[0043] Figure 4 This is a logic diagram for checking the accuracy of the beam splitter construction of the present invention. Detailed Implementation

[0044] The embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0045] Example 1

[0046] like Figure 1-2 As shown, the present invention provides an automatic detection system for the accuracy of splitter resources based on digital twins and AI, comprising: a digital twin module, a twin construction module, an image acquisition module, an image analysis module, a port change annotation module, a real-world & twin verification module, and an abnormal occupancy alarm module;

[0047] Among them, the digital twin module: uses digital twin technology to create a digital twin model of the information of the optical splitter equipment, providing support for twin construction and twin verification;

[0048] Twin construction module: Based on the digital twin module and combined with the construction work order information, the construction is simulated on the digital twin model of the splitter to generate a construction plan and a corresponding post-construction twin model and related feature value changes. This supports on-site and twin verification after construction to ensure the accuracy of construction.

[0049] The twin construction module prioritizes construction simulation on the twin model when a construction order is generated, generates the best construction plan and corresponding twin model, records the characteristic changes after construction, and helps to verify the accuracy of construction through twin verification after on-site construction.

[0050] Image acquisition module: Acquires image information from the port panel of the optical splitter via a monitoring camera or acquisition terminal, and uploads it to the video / image analysis server;

[0051] Image analysis module: After acquiring video / images of the physical assets, the video / image analysis server identifies the acquired video or images, extracts and records the port status and feature information of the optical splitting device;

[0052] Port Change Annotation Module: Combines the port status and feature information of the optical splitter extracted from the current video or image with the status and feature information from the previous image to analyze and annotate the changes in the port status of the optical splitter, extract feature values ​​and feature value changes, and use them for reality & twin verification.

[0053] Reality & Twin Verification Module: Based on the on-site splitter feature value data obtained by the image analysis module and the splitter feature value changes obtained by the port change annotation module, the module verifies the splitter feature values ​​in the digital twin module and the feature value changes generated by the twin construction module to determine the accuracy of splitter resource usage.

[0054] Abnormal usage alarm module: For splitters with abnormal use of splitter resources, query the person in charge of the splitter equipment and prompt relevant staff to conduct further on-site verification.

[0055] In this embodiment, the information of the optical splitter device includes basic information, port information, port status, port characteristics, wire sequence status, wire sequence label, and wire sequence characteristic information.

[0056] The port status of the optical splitter includes idle, occupied, and blocked states.

[0057] In the aforementioned Reality & Twin Verification Module, a basic comparison is performed on the feature information of the real and twin data. If the feature information is consistent, it is determined that there is no abnormality. If the features of the real and twin data change, intelligent verification is performed through error analysis, simulation judgment, machine recognition algorithms, etc., to detect abnormal usage. For problems that the machine cannot accurately identify, feedback is given to human verification, while the machine algorithm is optimized. The accuracy of the real-world splitter resource usage is determined through information verification.

[0058] Example 2

[0059] like Figure 3 As shown, according to the automatic detection method for splitter resource accuracy based on digital twins and AI implemented by the system, the splitter resource accuracy checking steps include:

[0060] Step 1: The digital twin module uses digital twin technology to perform digital twin modeling on the basic information, port information, port status, port characteristics, line sequence status, line sequence label, line sequence characteristics, and other related information of the splitter device, generating a running splitter model. It also supports the extraction of feature values ​​by modifying feature parameters such as environment, angle, illumination, visibility, and occlusion, and participates in the accuracy verification of video / images.

[0061] Step 2: The image acquisition module collects port video information of the optical splitter in real time through the video monitoring equipment and sends the collected video stream information to the video analysis server.

[0062] Step 3: The image analysis module parses and processes the video on the video analysis server, extracts the feature information of the splitter equipment, identifies the port usage status information of the splitter equipment, and sends the relevant splitter equipment feature information and port usage status information to the port change annotation module for port change annotation service.

[0063] The characteristic information of the beam splitter is divided into two parts: one part is the characteristic information of the beam splitter itself, and the other part is the relevant characteristic information such as the current environment of the beam splitter and the acquisition angle during the acquisition.

[0064] This invention does not limit the specific feature range of the optical splitting device. The two parts of features collected are based on the ability to meet the requirements of setting environmental and other feature values ​​for digital twin services / twin construction services and generating valid and verifiable twin feature information.

[0065] The port usage status information of the optical splitter includes, but is not limited to, port occupancy, idleness, obstruction, and line sequence characteristics, in accordance with the requirements for change labeling.

[0066] Step 4: The Reality & Twin Verification Module sends the feature information of the beam splitter image / video obtained in Step 3, including environmental, angle, lighting, visibility, and occlusion features, to the digital twin server to complete the twin setup and generate corresponding twin beam splitter feature information for the scene. The feature information of the real image / video and the scene-revised twin beam splitter feature information are then verified.

[0067] During information verification, a basic comparison of the feature information in reality and the twin is conducted, and the judgment is that there are no abnormalities if the feature information is consistent.

[0068] Intelligent verification is performed through error analysis, simulation judgment, and machine recognition algorithms to detect abnormal occupancy when changes occur in the real-world and twin characteristics.

[0069] For issues where the machine cannot perform accurate identification, feedback is provided for manual verification, while the machine algorithm is optimized. The accuracy of resource usage is checked through information verification; if anomalies are detected, information is synchronized with the abnormal resource usage module.

[0070] Step 5: The abnormal occupancy alarm module analyzes the abnormal situations found in Step 4, obtains the corresponding construction personnel information through the basic information of the optical splitter, and sends relevant abnormal alarms to prompt the staff to conduct on-site verification.

[0071] This invention does not limit the specific meaning of abnormal alarm information, but rather focuses on meeting the needs of staff.

[0072] Example 3

[0073] like Figure 4 As shown, according to the automatic detection method for the accuracy of beam splitter resources based on digital twins and AI implemented by the system, the accuracy check steps for beam splitter construction include:

[0074] Step 1: The digital twin module uses digital twin technology to perform digital twin modeling on the basic information, port information, port status, port characteristics, line sequence status, line sequence label, line sequence characteristics, and other related information of the splitter device, generating a running splitter model. It also supports the extraction of feature values ​​by modifying feature parameters such as environment, angle, illumination, visibility, and occlusion, and participates in the accuracy verification of video / images.

[0075] Step 2: When a construction work order is generated, the twin construction module calls the running beam splitter model from the digital twin service, performs construction simulation on it based on the work order content, generates the optimal construction plan, and generates the design beam splitter model and related feature values. It also supports the extraction of running state >> design state feature values ​​and their changes by modifying feature parameters such as environment, angle, illumination, visibility, and occlusion, and participates in the accuracy verification of construction.

[0076] Step 3: Before and after construction, the image acquisition module collects the port video information of the optical splitter in real time through the video monitoring equipment, and sends the collected video stream information to the video analysis server.

[0077] Step 4: Image analysis module. In the video analysis server, the images before and after construction are analyzed and processed to extract the feature information of the splitter equipment, identify the port usage status information of the splitter equipment, and send the relevant splitter equipment feature information and port usage status information to the port change annotation module for port change annotation service.

[0078] The characteristic information of the beam splitter is divided into two parts: one part is the characteristic information of the beam splitter itself, and the other part is the relevant characteristic information such as the current environment of the beam splitter and the acquisition angle during the acquisition.

[0079] This invention does not limit the specific feature range of the optical splitting device. The two parts of features collected are based on the ability to meet the requirements of setting environmental and other feature values ​​for digital twin services / twin construction services and generating valid and verifiable twin feature information.

[0080] The port usage status information of the optical splitter includes, but is not limited to, port occupancy, idleness, obstruction, and line sequence characteristics, in accordance with the requirements for change labeling.

[0081] Step 5: The Reality & Twin Verification Module sends the feature information of the beam splitter images / videos before and after construction obtained in Step 4, including environmental, angle, lighting, visibility, and occlusion features, to the digital twin / twin construction server. This completes the twin setup and generates corresponding twin beam splitter feature information and feature value change information for the scene. The module then verifies the feature information and feature value change information of the real image / videos with the scene-revised twin beam splitter feature information and feature value change information to check the accuracy of the construction. If abnormal construction is detected, the module synchronizes the information with the abnormal occupancy module.

[0082] Step Six: The abnormal occupancy alarm module analyzes the abnormal situations found in Step Four, obtains the corresponding construction personnel information through the basic information of the optical splitter, sends relevant abnormal alarm information, and prompts the staff to conduct on-site verification.

[0083] This invention does not limit the specific meaning of abnormal alarm information, but rather focuses on meeting the needs of staff.

[0084] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should be considered within the scope of protection of the present invention.

Claims

1. A digital twin and AI based optical splitter resource accuracy automatic detection system, characterized in that, Comprise: Digital twin module, twin construction module, image acquisition module, image analysis module, port change annotation module, reality & twin verification module, abnormal occupation alarm module; Among them, the digital twin module: through digital twin technology, the information of the optical splitter device is digitally twin modeled; Twin construction module: relying on the digital twin module, combined with the construction work order information, simulating construction on the digital twin model of the optical splitter, generating a construction scheme, and generating a corresponding post-construction twin model and related characteristic value changes; Image acquisition module: through the monitoring camera or acquisition terminal, the image information of the port panel of the optical splitting device is collected and uploaded to the image analysis module; Image analysis module: through the video / image analysis server, the collected video or image is recognized, and the optical splitting device port state and feature information are extracted and recorded; Port change annotation module: the optical splitting device port state and feature information analyzed and extracted in this video or image are combined with the state and feature information in the previous image, the change of the optical splitting device port state is analyzed and annotated, and the characteristic value and characteristic value change are extracted; Reality & twin verification module: based on the feature value data of the on-site optical splitter obtained by the image analysis module and the feature value change of the optical splitter obtained by the port change annotation module, the feature value of the optical splitter in the digital twin module and the feature value change data generated by the twin construction module are verified to judge the accuracy of the optical splitter resource use; Abnormal occupation alarm module: for the optical splitter with abnormal optical splitter resource use, the optical splitting device responsible person is queried and associated, and the relevant staff is prompted to further on-site review.

2. The digital twin and AI based optical splitter resource accuracy automatic detection system according to claim 1, wherein, The information of the optical splitter device includes basic information, port information, port state, port feature, line sequence state, line sequence label, and line sequence feature information.

3. The digital twin and AI based optical splitter resource accuracy automatic detection system according to claim 1, wherein, The optical splitting device port state includes idle, occupied, and blocked states.

4. The digital twin and AI based optical splitter resource accuracy automatic detection system of claim 1, wherein, In the reality & twin verification module, the feature information in reality and twin is compared, and if the feature information is consistent, it is judged to be normal; if the feature information changes, intelligent verification is performed to find abnormal occupation; for problems that the machine cannot accurately identify, feedback is given to the artificial verification, and the machine algorithm is optimized; the accuracy of the real optical splitter resource use is judged through information verification.

5. The method for digital twin and AI based optical splitter resource accuracy automatic detection implemented by the system according to any one of claims 1-4, characterized in that, The optical splitter resource accuracy checking steps include: Step one: the digital twin module generates a running optical splitter model by digitally twin modeling the information of the optical splitter device through digital twin technology, and supports the extraction of characteristic values by modifying feature parameters, and participates in the accuracy verification of video / images; Step two: the image acquisition module collects the port video information of the optical splitting device through the video monitoring device in real time, and sends the collected video stream information to the video analysis server; Step three: in the video analysis server, the video is analyzed and processed, the feature information of the optical splitting device is extracted, the port state of the optical splitting device is identified, and the related feature information and port use state information of the optical splitting device are sent to the port change annotation module to realize port change annotation; Step four: the reality & twin verification module sends the feature information of the on-site optical splitter image / video obtained in step three to the digital twin server, completes the setting of the twin, and generates the corresponding twin optical splitter feature information in the scene, and verifies the information of the reality image / video and the revised twin optical splitter feature information in the scene; Step five: the abnormal occupation alarm module sends the corresponding construction personnel information through the optical splitting device basic information acquisition, and sends the related abnormal alarm prompt to the staff for on-site review.

6. The digital twin and AI-based optical splitter resource accuracy automatic detection method according to claim 5, characterized in that, The feature parameters include environment, angle, illumination, visibility, and shielding parameters. The optical splitting device feature information is divided into two parts, one part is the feature information of the optical splitter itself, and the other part is the feature information related to the environment and the collection angle of the current optical splitter during collection.

7. The digital twin and AI-based optical splitter resource accuracy automatic detection method according to claim 5, characterized in that, Step four includes: basic comparison of feature information in reality and twin, no abnormality is judged for consistent feature information; intelligent verification through error analysis, simulation judgment, and machine recognition algorithm is performed for abnormal occupation situation found in changed feature information of reality and twin; for problems that the machine cannot accurately identify, feedback artificial verification, and optimize the machine algorithm; through information verification, the accuracy of resource use is verified, and if an abnormality is found, information synchronization is performed to the abnormal occupation module.

8. The method of claim 1-4, wherein the method is implemented by a system based on digital twin and AI, and characterized in that, The accuracy checking steps of the optical splitter construction include: Step one: the digital twin module generates a running state optical splitter model through digital twin technology, and supports the extraction of feature values by modifying feature parameters, and participates in the accuracy verification of video / images; Step two: when the construction work order information is generated, the twin construction module calls the running state optical splitter model from the digital twin service, performs construction simulation on it according to the work order content, generates an optimal construction scheme, and generates a design state optical splitter model and related feature values, and supports the extraction of running state >> design state feature values and their changes by modifying feature parameters, and participates in the accuracy verification of construction; Step three: before and after construction, the image acquisition module acquires the port video information of the optical splitting device in real time through the video monitoring device, and sends the acquired video stream information to the video analysis server; Step four: the image analysis module analyzes and processes the images before and after construction in the video analysis server, extracts the feature information of the optical splitting device, identifies the use state information of the optical splitting device port, and sends the related feature information of the optical splitting device and the port use state information to the port change labeling module for port change labeling service; Step five: the reality & twin verification module sends the feature information of the split optical fiber image / video before and after the construction in the field obtained in step four to the digital twin / twin construction module, completes the setting of the twin, generates the twin split optical fiber feature information and feature value change information in the corresponding scene, and verifies the information of the reality image / video feature information and the feature value change information and the scene revised twin split optical fiber feature information and the feature value change information, checks the accuracy of the construction, and if abnormal construction is found, synchronizes the information to the abnormal occupation module; Step six: the abnormal occupation alarm module sends the corresponding construction personnel information through the split optical device basic information acquisition according to the abnormal situation found in step four, sends the related abnormal alarm information, and improves the on-site review of the staff.

Images