Same-channel optical fiber detection method, device and equipment, storage medium and program product

By acquiring fiber vibration data and applying multiple curve similarity algorithms to weighted judgments, the problem of low recognition efficiency and accuracy of the same groove fiber is solved, and efficient and accurate fiber recognition is achieved, adapting to the rapid development of fiber networks and dynamic business needs.

CN118936845APending Publication Date: 2024-11-12CHINA MOBILE COMM LTD RES INST +1
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202410954747.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-16
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the prior art, the recognition efficiency and recognition accuracy of the Tonggo fiber are low, which cannot meet the rapid development of fiber networks and dynamic business needs. Especially in large-scale fiber networks around the world, there are problems of insufficient identification accuracy and generalization capabilities.

Method used

By obtaining the optical fiber vibration data, the vibration event generation curve is extracted, and the curve similarity algorithms such as cosine similarity, Euclidean distance and dynamic time regularization are used to make weighted judgments to identify whether the optical fiber is a homoglobulin fiber, and the intelligent sensing unit and Integrated learning technology enables automatic recognition.

Benefits of technology

It improves the recognition efficiency and accuracy of the same groove optical fiber, adapts to the rapid development of computing power networks, enhances the recognition ability in complex network scenarios, and achieves an average accuracy of 95%.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118936845A_ABST
    Figure CN118936845A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a same-channel optical fiber detection method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring optical fiber vibration data of a first optical fiber and optical fiber vibration data of a second optical fiber; according to a first vibration event extracted from the optical fiber vibration data of the first optical fiber, generating a first curve of the first vibration event changing along with time; according to a second vibration event extracted from the optical fiber vibration data of the second optical fiber, generating a second curve of the second vibration event changing along with time; determining the similarity between the first curve and the second curve according to a plurality of curve similarity algorithms; and performing weighted judgment on the similarity obtained through the multiple curve similarity algorithms to obtain a detection result for representing whether the first optical fiber and the second optical fiber are the same-channel optical fibers or not.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of optical transmission technology, and in particular, relates to a method, device, equipment, storage medium and program product for detecting a same-groove optical fiber. Background Art

[0002] In the related art, co-groove optical fibers can be identified by manual investigation, or optical cable routing information can be entered in advance to construct optical cable dumb resources that can be systematically managed. However, when co-groove optical fibers are identified by the above-mentioned manual investigation method or the manual entry of optical cable routing information, there is a problem of low co-groove optical fiber identification efficiency and recognition accuracy. Summary of the invention

[0003] In order to solve the problem of low same-groove optical fiber identification efficiency and low identification accuracy in the related art, the embodiments of the present application provide a same-groove optical fiber detection method, device, equipment, storage medium and program product.

[0004] The present application provides a method for detecting a same-groove optical fiber, the method comprising:

[0005] Acquire optical fiber vibration data of the first optical fiber and optical fiber vibration data of the second optical fiber;

[0006] Generate a first curve of the variation of the first vibration event over time according to a first vibration event extracted from the optical fiber vibration data of the first optical fiber; generate a second curve of the variation of the second vibration event over time according to a second vibration event extracted from the optical fiber vibration data of the second optical fiber;

[0007] determining the similarity between the first curve and the second curve according to a plurality of curve similarity algorithms;

[0008] A weighted decision is made on the similarities obtained by the plurality of curve similarity algorithms to obtain a detection result for characterizing whether the first optical fiber and the second optical fiber are optical fibers with the same groove.

[0009] In some embodiments, acquiring the fiber vibration data of the first optical fiber and the fiber vibration data of the second optical fiber includes: collecting the fiber vibration data of the first optical fiber and the fiber vibration data of the second optical fiber through a phase-sensitive optical time domain reflectometry (φ-OTDR).

[0010] In some embodiments, the optical fiber vibration data is continuous light intensity amplitude data on a time axis; before generating a first curve of the first vibration event changing with time based on the first vibration event extracted from the optical fiber vibration data of the first optical fiber, the method further includes: determining the first vibration event in the optical fiber vibration data of the first optical fiber based on the light intensity amplitude greater than a light intensity amplitude threshold in the optical fiber vibration data of the first optical fiber, and extracting the first vibration event; before generating a second curve of the second vibration event changing with time based on the second vibration event extracted from the optical fiber vibration data of the second optical fiber, the method further includes: determining the second vibration event in the optical fiber vibration data of the second optical fiber based on the light intensity amplitude greater than a light intensity amplitude threshold in the optical fiber vibration data of the second optical fiber, and extracting the second vibration event.

[0011] It can be seen that when the light intensity amplitude in the optical fiber vibration data is greater than the light intensity amplitude threshold, it can be considered that there is a high probability of a vibration event regarding the light intensity amplitude in the optical fiber vibration data. Therefore, based on the light intensity amplitude in the optical fiber vibration data that is greater than the light intensity amplitude threshold, the vibration event in the optical fiber vibration data can be determined more accurately.

[0012] In some embodiments, determining a first vibration event in the fiber vibration data of the first optical fiber based on a light intensity amplitude greater than a light intensity amplitude threshold in the fiber vibration data of the first optical fiber comprises: when the fiber vibration data of the first optical fiber includes N consecutive light intensity amplitudes greater than the light intensity amplitude threshold on the time axis, determining the first vibration event in the fiber vibration data of the first optical fiber based on the N light intensity amplitudes greater than the light intensity amplitude threshold; N is an integer greater than 1; determining a second vibration event in the fiber vibration data of the second optical fiber based on a light intensity amplitude greater than the light intensity amplitude threshold in the fiber vibration data of the second optical fiber comprises: when the fiber vibration data of the second optical fiber includes M consecutive light intensity amplitudes greater than the light intensity amplitude threshold on the time axis, determining the second vibration event in the fiber vibration data of the second optical fiber based on the M light intensity amplitudes greater than the light intensity amplitude threshold; M is an integer greater than 1.

[0013] It can be seen that when the optical fiber vibration data includes multiple continuous light intensity amplitudes greater than the light intensity amplitude threshold on the time axis, it can be considered that there is a high probability of vibration events regarding the light intensity amplitude in the optical fiber vibration data. Therefore, based on the multiple light intensity amplitudes greater than the light intensity amplitude threshold, the vibration events in the optical fiber vibration data can be determined more accurately.

[0014] In some embodiments, the plurality of curve similarity algorithms include at least two of the following algorithms: a cosine similarity (CS) algorithm, an Euclidean distance (ED) algorithm, and a dynamic time warping (DTW) algorithm.

[0015] In some embodiments, performing a weighted judgment on the similarities obtained by the multiple curve similarity algorithms to obtain a detection result for characterizing whether the first optical fiber and the second optical fiber are co-groove optical fibers includes: performing a weighted summation on the similarities obtained by the multiple curve similarity algorithms to obtain a weighted summation result; when the weighted summation result is greater than or equal to a first set value, determining that the detection result indicates that the first optical fiber and the second optical fiber are co-groove optical fibers; and when the weighted summation result is less than the first set value, determining that the detection result indicates that the first optical fiber and the second optical fiber are not co-groove optical fibers.

[0016] It can be seen that in the embodiment of the present application, the same-groove optical fiber is not identified based on a single curve similarity algorithm, but a weighted summation result is obtained based on the comprehensive consideration of the similarities obtained by multiple curve similarity algorithms. Therefore, according to the size relationship between the weighted summation result and the first set value, the detection result can be obtained more accurately, that is, the same-groove optical fiber can be identified more accurately.

[0017] In some embodiments, before performing weighted summation on the similarities obtained by the multiple curve similarity algorithms, the method further includes: when the similarity obtained by any one of the multiple curve similarity algorithms is greater than or equal to a second set value, updating the similarity obtained by the corresponding similarity algorithm to 1; when the similarity obtained by any one of the similarity algorithms is less than the second set value, updating the similarity obtained by the corresponding similarity algorithm to 0.

[0018] It can be seen that in the embodiment of the present application, the similarity obtained by any similarity algorithm can be updated to 1 or 0 according to the size relationship between the similarity obtained by the corresponding similarity algorithm and the second set value, so that the similarities obtained by multiple curve similarity algorithms can be simply and efficiently weighted.

[0019] In some embodiments, before performing weighted summation on the similarities obtained by the multiple curve similarity algorithms and obtaining the weighted summation result, the method further includes: determining a weighting coefficient for each curve similarity algorithm according to an average accuracy rate of each curve similarity algorithm in the multiple curve similarity algorithms.

[0020] It can be seen that when determining the weighting coefficient of the curve similarity algorithm according to the average accuracy of the curve similarity algorithm, it is beneficial to assign a higher weighting coefficient to the algorithm with a higher average accuracy, which helps to reduce the impact of the algorithm with a lower average accuracy on the accuracy of the detection result.

[0021] The present application also provides a detection device for a same-groove optical fiber, the device comprising:

[0022] An acquisition module, used to acquire optical fiber vibration data of the first optical fiber and optical fiber vibration data of the second optical fiber;

[0023] A first processing module, configured to generate a first curve of the variation of the first vibration event over time according to a first vibration event extracted from the optical fiber vibration data of the first optical fiber; and to generate a second curve of the variation of the second vibration event over time according to a second vibration event extracted from the optical fiber vibration data of the second optical fiber;

[0024] The second processing module is used to determine the similarity between the first curve and the second curve according to multiple curve similarity algorithms; perform weighted judgment on the similarities obtained by the multiple curve similarity algorithms to obtain a detection result for characterizing whether the first optical fiber and the second optical fiber are co-groove optical fibers.

[0025] An embodiment of the present application also provides an electronic device, comprising a processor and a memory for storing a computer program that can be run on the processor; wherein the processor is used to run the computer program to execute any of the above-mentioned methods for detecting the same-groove optical fiber.

[0026] The embodiment of the present application further provides a computer storage medium on which a computer program is stored. When the computer program is executed by a processor, any one of the above-mentioned methods for detecting the same-groove optical fiber is implemented.

[0027] An embodiment of the present application further provides a computer program product, including a computer program, which implements any of the above-mentioned methods for detecting the same-groove optical fiber when executed by a processor.

[0028] It can be seen that the embodiment of the present application does not need to identify the same-groove optical fiber by manual investigation or manual entry of optical cable routing information. Instead, after the vibration event is extracted from the optical fiber vibration data of the two optical fibers, the detection result of whether the two optical fibers are the same-groove optical fiber can be automatically obtained according to the similarity of the two curves of the vibration event changing with time, thereby improving the recognition efficiency of the same-groove optical fiber; further, the embodiment of the present application can fully obtain the characteristics between curves through a variety of similarity algorithms. Since the similarities obtained by a variety of curve similarity algorithms can be weighted, the similarities obtained by a variety of curve similarity algorithms can be combined to improve the recognition accuracy of the same-groove optical fiber. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a flow chart of a method for detecting a same-groove optical fiber according to an embodiment of the present application;

[0030] Figure 2 A schematic diagram of using the output results of multiple learners to make weighted decisions in an embodiment of the present application;

[0031] Figure 3 This is a system structure block diagram for realizing the same-groove optical fiber identification in the embodiment of the present application;

[0032] Figure 4 A flowchart of another method for detecting a same-groove optical fiber according to an embodiment of the present application;

[0033] Figure 5 A schematic diagram of the structure of a detection device for a same-groove optical fiber according to an embodiment of the present application;

[0034] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] Affected by the inherent passive characteristics, the dumb resources in the optical cable have long lacked effective monitoring and operation and maintenance methods, resulting in the problem of the main and backup routing optical fibers in the same trench. When laying optical cable lines for customers, operators need to meet the 1+1 protection requirements of the optical channel or even the 1+1+1 protection requirements, and the main service and backup protection path optical fibers cannot be in the same trench. Here, the 1+1+1 protection requirement means that for one main optical fiber, equipment optical fiber and redundant optical fiber need to be laid. Once the main and backup co-groove optical fibers are interrupted, user services will be interrupted and it will take a long time to recover.

[0036] In related technologies, manual inspection is usually used to sort out the optical cable routes in the operator's existing network. It is necessary to carry out manual tapping and manual monitoring at the same time, and the recognition efficiency and accuracy of the same-groove optical fiber are low. Some operators will also adopt a semi-intelligent method to build optical cable dumb resources that can be systematically managed by entering the optical cable routing information in advance, and use the network management platform to distinguish the same-groove optical fiber. With the development of computing power networks, the scale of optical networks continues to increase. When the same-groove optical fiber is identified by the above-mentioned manual line inspection method or the manual entry of optical cable routing information, the recognition efficiency and accuracy of the same-groove optical fiber will be further reduced. In addition, in the network where the service is dynamically established and released, the offline identification method cannot meet the requirements of dynamic service issuance. The total length of optical cables in the world's largest optical fiber network exceeds 63 million kilometers. The method that relies solely on small data sets and offline training also faces huge challenges in generalization and real-time capabilities. Therefore, there is an urgent need for an efficient and accurate means to improve the accuracy of optical fiber same-groove identification to improve the survivability of the network and ensure the quality of service of the operator's network.

[0037] In summary, the solution of manually checking and identifying co-groove optical fibers is extremely dependent on manpower, and the efficiency and accuracy of co-groove optical fiber identification are low; the semi-intelligent method of extracting and entering optical cable routing information cannot adapt to the rapid development of computing power networks.

[0038] In order to solve the above technical problems and to address the hazards caused by the same-groove optical fiber, a technical solution of the embodiment of the present application is proposed.

[0039] The following is a further detailed description of the embodiments of the present application in conjunction with the accompanying drawings and examples. It should be understood that the embodiments provided herein are only used to explain the embodiments of the present application and are not intended to limit the embodiments of the present application. In addition, the embodiments provided below are partial embodiments for implementing the present application, rather than providing all embodiments for implementing the present application. In the absence of conflict, the technical solutions recorded in the embodiments of the present application can be implemented in any combination.

[0040] It should be noted that, in the embodiments of the present application, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a method or device including a series of elements includes not only the elements explicitly recorded, but also includes other elements not explicitly listed, or also includes elements inherent to the implementation of the method or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other related elements (such as steps in a method or units in a device, for example, a unit may be a part of a circuit, a part of a processor, a part of a program or software, etc.) in the method or device including the element.

[0041] The detection method of the same-groove optical fiber provided in the embodiment of the present application includes a series of steps, but the detection method of the same-groove optical fiber provided in the embodiment of the present application is not limited to the recorded steps. Similarly, the detection device of the same-groove optical fiber provided in the embodiment of the present application includes a series of modules, but the device provided in the embodiment of the present application is not limited to including the modules explicitly recorded, and can also include modules required to obtain relevant information or perform processing based on information.

[0042] Figure 1 Flow chart of a method for detecting a same-groove optical fiber according to an embodiment of the present application, as shown in FIG. Figure 1 As shown, the process may include:

[0043] Step 101: Obtain optical fiber vibration data of a first optical fiber and optical fiber vibration data of a second optical fiber.

[0044] In some embodiments, an intelligent sensing unit deployed inside the network can be used to collect optical fiber vibration data from optical fibers in an actual network environment; for example, the optical fiber vibration data of the first optical fiber and the optical fiber vibration data of the second optical fiber can be collected by a phase-sensitive optical time domain reflectometer, and accurate collection of optical fiber vibration data can be achieved by the phase-sensitive optical time domain reflectometer.

[0045] Exemplarily, the optical fiber vibration data may be continuous light intensity amplitude data on a time axis or other data used to represent changes in light intensity amplitude.

[0046] Step 102: Based on a first vibration event extracted from the fiber vibration data of the first optical fiber, generate a first curve of the first vibration event changing with time; based on a second vibration event extracted from the fiber vibration data of the second optical fiber, generate a second curve of the second vibration event changing with time.

[0047] In order to ensure reliable identification of optical fibers with the same groove, it is necessary to preprocess the long-term vibration light intensity data of the two monitored optical fibers; illustratively, the process of preprocessing the optical fiber vibration data of the first optical fiber and the optical fiber vibration data of the second optical fiber is as follows: based on the relationship between the continuous light intensity amplitude data and the light intensity amplitude threshold on the time axis, vibration events are respectively extracted from the optical fiber vibration data of the first optical fiber and the optical fiber vibration data of the second optical fiber.

[0048] Step 103: Determine the similarity between the first curve and the second curve according to a plurality of curve similarity algorithms.

[0049] In some embodiments, the multiple curve similarity algorithms include at least two of the following algorithms: CS algorithm, ED algorithm, and DTW algorithm.

[0050] The CS algorithm determines the similarity between two vectors by calculating the cosine of the angle between them. The cosine similarity is the dot product of the two vectors divided by the product of the moduli of the two vectors. For example, in L i and L j When L represents two curves of length n, i and L j The cosine similarity can be calculated using formula (1).

[0051]

[0052] Among them, Similarity(L i ,L j ) indicates L i and L j The cosine similarity between them, n is a positive integer, L i The corresponding vector can be represented by n elements, L ik Indicates L i The kth element in the corresponding vector; L j The corresponding vector can be represented by n elements, L jk Indicates L j The kth element in the corresponding vector.

[0053] The ED algorithm is a commonly used distance measurement method. When calculating the similarity of curves, the similarity between curves can be measured by representing the curves as discrete point sets and then calculating the Euclidean distance between these points. i and L j The Euclidean distance between the two curves is the square root of the sum of the squares of the Euclidean distances between the corresponding points on the two curves; i and L j The smaller the Euclidean distance between them, the smaller the curve L i and L j For example, curve L i is a p-dimensional trajectory segment of length n, the curve L i It can be represented as a discrete point set consisting of n discrete points, and the curve L j is a p-dimensional trajectory segment of length n, the curve L j It can be represented as a discrete point set consisting of n discrete points, and the curve L i and L j The Euclidean distance between them can be calculated using formula (2).

[0054]

[0055] Among them, D E (L i ,L j ) represents the curve Li and L j The Euclidean distance between For curve L i The p-dimensional coordinate of the k-th point in the corresponding discrete point set, For curve L j The p-th dimension coordinate of the k-th point in the corresponding discrete point set.

[0056] The DTW algorithm is a commonly used method for calculating curve similarity. It measures the similarity between curves by defining a cost function on the curve and then using a dynamic programming algorithm to find a path that minimizes the cost. The DTW algorithm can also be used to compare two curves that are not completely aligned in time. The sum of the shortest paths calculated by DTW is the curve similarity. For example, curve L i It can be represented as a discrete point set consisting of n discrete points, and the curve L j It can be represented as a discrete point set consisting of n discrete points, and the curve L i The i-th discrete point in the corresponding discrete point set and the curve L j The shortest distance D between the jth discrete points in the corresponding discrete point set min (i,j) can be calculated by formula (3).

[0057] D min (i,j)=min{D min (i,j-1),D min (i-1,j),D min (i-1,j-1)}+M(i,j) (3)

[0058] Among them, D min (i,j-1) represents curve L i The i-th discrete point in the corresponding discrete point set and the curve L j The shortest distance between the j-1th discrete points in the corresponding discrete point set, D min (i-1,j) represents curve L i The i-1th discrete point in the corresponding discrete point set and the curve L j The shortest distance between the jth discrete points in the corresponding discrete point set, D min (i-1,j-1) represents the curve L i The i-1th discrete point in the corresponding discrete point set and the curve L j The shortest distance between the j-1th discrete points in the corresponding discrete point set; M(i,j) represents the curve L i The i-th discrete point in the corresponding discrete point set and the curve L j The metric function of the distance between the jth discrete points in the corresponding discrete point set.

[0059] In calculating D min (i,j) after that, we can determine D min The number of path segments R of (i, j) is calculated, and the average distance D is obtained by formula (4).

[0060]

[0061] In the embodiment of the present application, D may be used as one of the criteria for subsequently distinguishing whether two optical fibers share the same groove.

[0062] Step 104: performing weighted judgment on the similarities obtained by using multiple curve similarity algorithms to obtain a detection result for characterizing whether the first optical fiber and the second optical fiber are the same groove optical fibers.

[0063] In practical applications, steps 101 to 104 can be implemented based on a processor, and the processor can be at least one of an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, and a microprocessor.

[0064] It can be seen that the embodiment of the present application does not need to identify the same-groove optical fiber by manual investigation or manual entry of optical cable routing information. Instead, after the vibration event is extracted from the optical fiber vibration data of the two optical fibers, the detection result of whether the two optical fibers are the same-groove optical fiber can be automatically obtained according to the similarity of the two curves of the vibration event changing with time, thereby improving the recognition efficiency of the same-groove optical fiber; further, the embodiment of the present application can fully obtain the characteristics between curves through a variety of similarity algorithms. Since the similarities obtained by a variety of curve similarity algorithms can be weighted, the similarities obtained by a variety of curve similarity algorithms can be combined to improve the recognition accuracy of the same-groove optical fiber.

[0065] In some embodiments of the present application, before generating a first curve of the first vibration event changing over time based on the first vibration event extracted from the fiber vibration data of the first optical fiber, the method further comprises: determining the first vibration event in the fiber vibration data of the first optical fiber based on a light intensity amplitude greater than a light intensity amplitude threshold in the fiber vibration data of the first optical fiber;

[0066] Before generating a second curve of the second vibration event changing with time based on the second vibration event extracted from the fiber vibration data of the second optical fiber, the method also includes: determining the second vibration event in the fiber vibration data of the second optical fiber based on the light intensity amplitude in the fiber vibration data of the second optical fiber that is greater than a light intensity amplitude threshold.

[0067] Here, the optical fiber vibration data can be represented by a curve in a two-dimensional coordinate system, where the horizontal axis is time and the vertical axis is light intensity amplitude.

[0068] In the embodiment of the present application, it is necessary to distinguish and extract vibration events from the optical fiber vibration data. For example, the threshold method can be used to make a binary judgment on the vibration event. In the optical fiber vibration data, the light intensity amplitude greater than the light intensity amplitude threshold is marked as 1, and the light intensity amplitude less than or equal to the light intensity amplitude threshold is marked as 0. Then, the vibration event in the optical fiber vibration data can be determined according to the light intensity amplitude marked as 1. The light intensity amplitude threshold can be preset according to actual needs.

[0069] It can be seen that when the light intensity amplitude in the optical fiber vibration data is greater than the light intensity amplitude threshold, it can be considered that there is a high probability of a vibration event regarding the light intensity amplitude in the optical fiber vibration data. Therefore, based on the light intensity amplitude in the optical fiber vibration data that is greater than the light intensity amplitude threshold, the vibration event in the optical fiber vibration data can be determined more accurately.

[0070] In some embodiments of the present application, the process of determining a first vibration event in the fiber vibration data of the first optical fiber according to a light intensity amplitude greater than a light intensity amplitude threshold in the fiber vibration data of the first optical fiber may include: when the fiber vibration data of the first optical fiber includes N consecutive light intensity amplitudes greater than the light intensity amplitude threshold on the time axis, determining the first vibration event in the fiber vibration data of the first optical fiber according to the N light intensity amplitudes greater than the light intensity amplitude threshold; N is an integer greater than 1;

[0071] A process for determining a second vibration event in the fiber optic vibration data of the second optical fiber based on a light intensity amplitude greater than a light intensity amplitude threshold in the fiber optic vibration data of the second optical fiber comprises: when the fiber optic vibration data of the second optical fiber includes M consecutive light intensity amplitudes greater than the light intensity amplitude threshold on a time axis, determining the second vibration event in the fiber optic vibration data of the second optical fiber based on the M light intensity amplitudes greater than the light intensity amplitude threshold; M is an integer greater than 1.

[0072] Here, the values ​​of N and M can be set according to actual needs, and the values ​​of N and M can be equal or unequal.

[0073] For example, when there are multiple consecutive light intensity amplitudes marked as 1 in the optical fiber vibration data, if the consecutive light intensity amplitudes marked as 1 meet the set conditions, the light intensity amplitude at the center position can be selected as a reference among the multiple consecutive light intensity amplitudes marked as 1, and a certain time length is extended from the reference to the left and right ends as a vibration event. For example, the set condition can be that the number of consecutive light intensity amplitudes marked as 1 is greater than or equal to a preset number, and the preset number can be an integer greater than or equal to 2.

[0074] In actual scenarios, there is a delay in the optical fiber communication link. For example, there is a delay in different trench sections of two optical fibers. For the delay in the optical fiber communication link, when the sampling period of the φ-OTDR is 1 / 1000s, the vibration event is intercepted with a time interval length of 2s during the data preprocessing process, and the start time of the vibration event is recorded. Exemplarily, the first curve or the second curve of the vibration event changing with time is a vibration event curve with a time period of 2s in a two-dimensional coordinate system, and the horizontal axis of the two-dimensional coordinate system is time and the vertical axis is the light intensity amplitude.

[0075] It can be seen that when the optical fiber vibration data includes multiple continuous light intensity amplitudes greater than the light intensity amplitude threshold on the time axis, it can be considered that there is a high probability of vibration events regarding the light intensity amplitude in the optical fiber vibration data. Therefore, based on the multiple light intensity amplitudes greater than the light intensity amplitude threshold, the vibration events in the optical fiber vibration data can be determined more accurately.

[0076] In some embodiments of the present application, a process of performing weighted judgment on the similarities obtained by multiple curve similarity algorithms to obtain a detection result may include: performing weighted summation on the similarities obtained by multiple curve similarity algorithms to obtain a weighted summation result; when the weighted summation result is greater than or equal to a first set value, determining that the detection result indicates that the first optical fiber and the second optical fiber are co-groove optical fibers; when the weighted summation result is less than the first set value, determining that the detection result indicates that the first optical fiber and the second optical fiber are not co-groove optical fibers.

[0077] Here, the first setting value can be set according to actual needs, for example, the first setting value is 0.5.

[0078] It can be seen that in the embodiment of the present application, the same-groove optical fiber is not identified based on a single curve similarity algorithm, but a weighted summation result is obtained based on the comprehensive consideration of the similarities obtained by multiple curve similarity algorithms. Therefore, according to the size relationship between the weighted summation result and the first set value, the detection result can be obtained more accurately, that is, the same-groove optical fiber can be identified more accurately.

[0079] In some embodiments of the present application, before performing weighted summation on the similarities obtained by multiple curve similarity algorithms, the method also includes: when the similarity obtained by any similarity algorithm among the multiple curve similarity algorithms is greater than or equal to a second set value, updating the similarity obtained by the corresponding similarity algorithm to 1; when the similarity obtained by any similarity algorithm is less than the second set value, updating the similarity obtained by the corresponding similarity algorithm to 0.

[0080] Exemplarily, the second setting value can be set according to actual needs, for example, the second setting value is 0.5.

[0081] In the embodiment of the present application, multiple learners can be set, and each of the multiple learners is used to use a curve similarity algorithm to calculate the similarity between two curves, and output the detection result of whether the first optical fiber and the second optical fiber are co-groove optical fibers. Exemplarily, after obtaining the first curve and the second curve, the first curve and the second curve are input into each learner, and each learner is used to calculate the similarity of the first curve and the second curve, and the relationship between the similarity and the second set value is updated to update the similarity; for example, when the similarity calculated by the learner is greater than or equal to the second set value, the similarity is updated to 1, and 1 is output. At this time, the output data of the learner indicates that the first optical fiber and the second optical fiber are co-groove optical fibers; when the similarity calculated by the learner is less than the second set value, the similarity is updated to 0, and 0 is output. At this time, the output data of the learner indicates that the first optical fiber and the second optical fiber are not co-groove optical fibers.

[0082] For example, refer to Figure 2 , learner 1, learner 2 and learner 3 can be used to represent learners that execute CS algorithm, ED algorithm and DTW algorithm respectively, and the output data of learner 1, learner 2 and learner 3 represent their respective co-groove fiber detection results, and the output data of any learner can be 0 or 1. After learner 1, learner 2 and learner 3 output data, in the integrated learner, the idea of ​​integrated learning can be used to perform weighted judgment on the output data of learner 1, learner 2 and learner 3 to obtain the detection result.

[0083] It can be seen that in the embodiment of the present application, the similarity obtained by any similarity algorithm can be updated to 1 or 0 according to the size relationship between the similarity obtained by the corresponding similarity algorithm and the second set value, so that the similarities obtained by multiple curve similarity algorithms can be simply and efficiently weighted.

[0084] In some embodiments of the present application, before weighted summing the similarities obtained by multiple curve similarity algorithms to obtain the weighted summation result, the weighting coefficient of each curve similarity algorithm can also be determined according to the average accuracy of each curve similarity algorithm in the multiple curve similarity algorithms.

[0085] Exemplarily, after the various learners each output data, the detection result H can be calculated according to formula (5).

[0086]

[0087] Where q represents the number of learners, ρ i represents the weighted coefficient of the similarity algorithm used by the i-th learner, f i represents the output data of the i-th learner, f i The value of is 0 or 1. δ[·] is a weighted decision function. For example, When the value of is greater than or equal to 0.5, The value of is 1; When the value of is less than 0.5, The value of is 0.

[0088] In the embodiment of the present application, when the detection result H is equal to 1, it can be considered that the first optical fiber and the second optical fiber are co-groove optical fibers, and when the detection result H is equal to 0, it can be considered that the first optical fiber and the second optical fiber are not co-groove optical fibers.

[0089] In some embodiments, if there is a curve similarity algorithm with a lower average accuracy that affects the accuracy of the detection result, the weighting coefficient of the curve similarity algorithm can be adjusted to assign a higher weighting coefficient to the algorithm with a higher average accuracy so that it plays a greater role in ensemble learning.

[0090] Each learner needs to determine the corresponding weighting coefficient. For example, it is necessary to calculate the average accuracy or other performance indicators obtained by cross-validation of the curve similarity algorithm used by each learner in the training set; the weighting coefficient of the curve similarity algorithm used by each learner is dynamically adjusted.

[0091] Furthermore, in order to make the sum of the weighted coefficients of various similarity algorithms equal to 1, it is also necessary to normalize the performance indicators such as the average accuracy. For example, the z-score method can be used to normalize the performance indicators so that the mean value of the performance indicator of each curve similarity algorithm is 0 and the standard deviation of the performance indicator of each curve similarity algorithm is 1. The formula for normalizing the performance indicators using the Z-score method is formula (6)

[0092]

[0093] Among them, x i represents the performance index of the i-th curve similarity algorithm, z i Indicates x i The result of normalization.

[0094] In getting z i After that, we can use the Softmax function to convert z i Converted to weighting coefficient ρ i The Softmax function can convert a set of values ​​into a probability distribution and highlight the impact of high-probability events. i Converted to weighting coefficient ρ i The formula is formula (7).

[0095]

[0096] The output value of the Softmax function represents the probability of each algorithm being selected as the best algorithm, so it can also be regarded as their weight distribution. In this way, the superiority of the algorithm will directly affect the judgment result of the integrated decision in terms of the size of the weight value, thereby improving the recognition accuracy of the integrated decision.

[0097] In an exemplary scenario, referring to Table 1, the weight coefficients of the DTW algorithm, ED algorithm and CS algorithm are 0.105, 0.473 and 0.422 respectively. Table 1 presents the detection results of case a, case b, case c and case d respectively. The occurrence ratios of case a, case b, case c and case d in all cases are 14.5%, 7.5%, 66.5% and 4.5% respectively. In Table 1, the comprehensive weight value represents the sum of the weight coefficients of the algorithms adopted by the learner whose output data is 1. In case a, the output data of the learner corresponding to the DTW algorithm, the learner corresponding to the ED algorithm, and the learner corresponding to the CS algorithm are all 1, the sum of the weighted coefficients of the DTW algorithm, the ED algorithm, and the CS algorithm is 1, and the weighted judgment result is 1; in case b, the output data of the learner corresponding to the DTW algorithm and the learner corresponding to the CS algorithm are all 1, the output data of the learner corresponding to the ED algorithm is 0, the sum of the weighted coefficients of the DTW algorithm and the CS algorithm is 0.527, and the detection result is 1; in case c, the output data of the learner corresponding to the ED algorithm and the learner corresponding to the CS algorithm are 1, the output data of the learner corresponding to the DTW algorithm is 0, the sum of the weighted coefficients of the ED algorithm and the CS algorithm is 0.895, and the detection result is 1; in case d, the output data of the learner corresponding to the DTW algorithm and the learner corresponding to the ED algorithm are all 1, the output data of the learner corresponding to the CS algorithm is 0, the sum of the weighted coefficients of the DTW algorithm and the ED algorithm is 0.578, and the detection result is 1.

[0098] Table 1 Test results of the same groove optical fiber under various conditions

[0099]

[0100] It can be seen from Table 1 that when the output data of only one of the learners corresponding to the ED algorithm and the learners corresponding to the CS algorithm is 1, if the output data of the learner corresponding to the DTW algorithm is 1, it can be determined that the comprehensive weight value exceeds 0.5, so that the detection result can be determined to be 1. It can be seen that by making a weighted judgment on the similarity of each algorithm, the accuracy of the same groove fiber identification can be improved to a certain extent.

[0101] It can be seen that when determining the weighting coefficient of the curve similarity algorithm according to the average accuracy of the curve similarity algorithm, it is beneficial to assign a higher weighting coefficient to the algorithm with a higher average accuracy, which helps to reduce the impact of the algorithm with a lower average accuracy on the accuracy of the detection result.

[0102] The embodiment of the present application proposes a method for identifying optical fibers with the same groove based on ensemble learning. The embodiment of the present application can use artificial intelligence technology to identify optical fibers with the same groove. The technical solution of the embodiment of the present application can apply the ensemble learning algorithm based on weighted judgment to the problem of identifying optical fibers with the same groove, and the detection result can be obtained by integrating the results of multiple curve similarity algorithms. The embodiment of the present application uses the principle of ensemble learning to enhance the generalization ability of the method for identifying optical fibers with the same groove in complex network scenarios. For the problem of identifying optical fibers with the same groove, multiple independent basic learners are developed. They can evaluate whether the optical fiber belongs to the same groove based on the curve of the vibration event changing with time. Finally, the output results of each learner are weighted. The performance of the integrated learner is better than that of a single learner that is not integrated, and the recognition accuracy of optical fibers with the same groove is improved.

[0103] Figure 3 This is a system structure diagram for realizing the same groove optical fiber identification in the embodiment of the present application, referring to Figure 3 In the embodiment of the present application, the intelligent sensing unit 301 deployed inside the network is used to collect optical fiber vibration data from the actual network environment, and the deployed intelligent identification unit 303 is used to identify the same-groove optical fiber; the data processing unit 302 is used to pre-process the optical fiber vibration data.

[0104] Reference Figure 4 , the process of another method for detecting a same-groove optical fiber according to an embodiment of the present application may include:

[0105] Step 401: Collect optical fiber vibration data using an intelligent sensing unit.

[0106] Here, the intelligent sensing unit can be implemented based on φ-OTDR. In actual scenarios, φ-OTDR can be used to perform long-term monitoring of the optical fiber vibration data of two optical fibers to be identified, and the collected optical fiber vibration data can be transmitted to the data processing unit.

[0107] Step 402: The data processing unit pre-processes the optical fiber vibration data.

[0108] Step 403: Use multiple learners to process the preprocessed data.

[0109] Step 404: Perform weighted decision on the output results of multiple learners.

[0110] Step 405: Output the detection result.

[0111] In the embodiment of the present application, the execution entity of steps 403 to 405 may be an intelligent recognition unit.

[0112] The embodiment of the present application can use the idea of ​​ensemble learning to perform similarity analysis on the curve of vibration events changing over time, and can fully learn the characteristics of each dimension of the curve. Through simulation verification, it is found that the average accuracy of the same-groove optical fiber identification scheme of the embodiment of the present application can reach 95%.

[0113] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0114] Figure 5 Schematic diagram of the structure of the detection device of the same groove optical fiber according to the embodiment of the present application. Figure 5 As shown, the device comprises:

[0115] An acquisition module 501 is used to acquire optical fiber vibration data of a first optical fiber and optical fiber vibration data of a second optical fiber;

[0116] A first processing module 502 is used to generate a first curve of the variation of the first vibration event over time according to a first vibration event extracted from the optical fiber vibration data of the first optical fiber; and to generate a second curve of the variation of the second vibration event over time according to a second vibration event extracted from the optical fiber vibration data of the second optical fiber;

[0117] The second processing module 503 is used to determine the similarity between the first curve and the second curve according to multiple curve similarity algorithms; perform weighted judgment on the similarities obtained by the multiple curve similarity algorithms to obtain a detection result for characterizing whether the first optical fiber and the second optical fiber are the same groove optical fibers.

[0118] In some embodiments, the acquisition module 501 is used to collect the fiber vibration data of the first optical fiber and the fiber vibration data of the second optical fiber by using a phase sensitive optical time domain reflectometer.

[0119] In some embodiments, the optical fiber vibration data is continuous light intensity amplitude data on a time axis;

[0120] The first processing module 502 is further configured to determine a first vibration event in the optical fiber vibration data of the first optical fiber according to a light intensity amplitude greater than a light intensity amplitude threshold in the optical fiber vibration data of the first optical fiber, before generating a first curve of the first vibration event changing with time according to the first vibration event extracted from the optical fiber vibration data of the first optical fiber;

[0121] The first processing module 502 is further used to determine a second vibration event in the fiber optic vibration data of the second optical fiber based on a light intensity amplitude greater than a light intensity amplitude threshold in the fiber optic vibration data of the second optical fiber before generating a second curve of the second vibration event changing with time based on the second vibration event extracted from the fiber optic vibration data of the second optical fiber.

[0122] The first processing module 502 is used to determine the first vibration event in the fiber vibration data of the first optical fiber according to the light intensity amplitude greater than the light intensity amplitude threshold in the fiber vibration data of the first optical fiber, including: when the fiber vibration data of the first optical fiber includes N consecutive light intensity amplitudes greater than the light intensity amplitude threshold on the time axis, determining the first vibration event in the fiber vibration data of the first optical fiber according to the N light intensity amplitudes greater than the light intensity amplitude threshold; N is an integer greater than 1;

[0123] The first processing module 502 is used to determine a second vibration event in the fiber vibration data of the second optical fiber according to a light intensity amplitude greater than a light intensity amplitude threshold in the fiber vibration data of the second optical fiber, including: when the fiber vibration data of the second optical fiber includes M consecutive light intensity amplitudes greater than the light intensity amplitude threshold on the time axis, determining the second vibration event in the fiber vibration data of the second optical fiber according to the M light intensity amplitudes greater than the light intensity amplitude threshold; M is an integer greater than 1.

[0124] In some embodiments, the plurality of curve similarity algorithms include at least two of the following algorithms: CS algorithm, ED algorithm, and DTW algorithm.

[0125] In some embodiments, the second processing module 503 is used to perform weighted judgment on the similarities obtained by the multiple curve similarity algorithms to obtain a detection result used to characterize whether the first optical fiber and the second optical fiber are co-groove optical fibers, including: performing weighted summation on the similarities obtained by the multiple curve similarity algorithms to obtain a weighted summation result; when the weighted summation result is greater than or equal to a first set value, determining that the detection result indicates that the first optical fiber and the second optical fiber are co-groove optical fibers; when the weighted summation result is less than the first set value, determining that the detection result indicates that the first optical fiber and the second optical fiber are not co-groove optical fibers.

[0126] In some embodiments, the second processing module 503 is further used to, before performing weighted summation on the similarities obtained by the multiple curve similarity algorithms, update the similarity obtained by the corresponding similarity algorithm to 1 when the similarity obtained by any similarity algorithm among the multiple curve similarity algorithms is greater than or equal to a second set value; and update the similarity obtained by the corresponding similarity algorithm to 0 when the similarity obtained by any similarity algorithm is less than the second set value.

[0127] In some embodiments, the second processing module 503 is further used to determine a weighting coefficient of each curve similarity algorithm according to an average accuracy of each curve similarity algorithm among the multiple curve similarity algorithms before performing weighted summation on the similarities obtained by the multiple curve similarity algorithms to obtain the weighted summation result.

[0128] It should be noted that the description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.

[0129] It should be noted that in the embodiments of the present application, if the above method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a computer device (which can be a terminal, a server, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a disk or an optical disk. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0130] Correspondingly, an embodiment of the present application further provides a computer program product, which includes computer executable instructions, and the computer executable instructions are used to implement any one of the same-groove optical fiber detection methods provided in the embodiments of the present application.

[0131] Accordingly, an embodiment of the present application further provides a computer storage medium, on which computer executable instructions are stored, and the computer executable instructions are used to implement any one of the same-groove optical fiber detection methods provided in the above embodiments.

[0132] An embodiment of the present application also provides an electronic device. Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the electronic device 60 may include:

[0133] Memory 61, used for storing executable instructions;

[0134] The processor 62 is configured to implement any one of the above-mentioned methods for detecting the same-groove optical fiber when executing the executable instructions stored in the memory 61.

[0135] The processor 62 may be at least one of an ASIC, a DSP, a DSPD, a PLD, a FPGA, a CPU, a controller, a microcontroller, and a microprocessor.

[0136] The above-mentioned computer-readable storage medium and memory 62 can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory (Flash Memory), a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM) and other memories; it can also be various terminals including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0137] In some embodiments, the functions or modules included in the device provided in the embodiments of the present application can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0138] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0139] The methods disclosed in the various method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0140] The features disclosed in the various product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0141] The features disclosed in the various method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0142] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0143] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for detecting a same-groove optical fiber, characterized in that: The method comprises: Acquire optical fiber vibration data of the first optical fiber and optical fiber vibration data of the second optical fiber; Generate a first curve of the variation of the first vibration event over time according to a first vibration event extracted from the optical fiber vibration data of the first optical fiber; generate a second curve of the variation of the second vibration event over time according to a second vibration event extracted from the optical fiber vibration data of the second optical fiber; determining the similarity between the first curve and the second curve according to a plurality of curve similarity algorithms; A weighted decision is made on the similarities obtained by the plurality of curve similarity algorithms to obtain a detection result for characterizing whether the first optical fiber and the second optical fiber are optical fibers with the same groove.

2. The method according to claim 1, characterized in that The obtaining of the optical fiber vibration data of the first optical fiber and the optical fiber vibration data of the second optical fiber includes: collecting the optical fiber vibration data of the first optical fiber and the optical fiber vibration data of the second optical fiber by using a phase sensitive optical time domain reflectometer.

3. The method according to claim 1, characterized in that The optical fiber vibration data is continuous light intensity amplitude data on the time axis; Before generating a first curve of the first vibration event changing with time based on the first vibration event extracted from the fiber vibration data of the first optical fiber, the method further comprises: determining the first vibration event in the fiber vibration data of the first optical fiber based on the light intensity amplitude greater than the light intensity amplitude threshold in the fiber vibration data of the first optical fiber; extracting the first vibration event; Before generating a second curve of the vibration event changing with time based on the second vibration event extracted from the fiber vibration data of the second optical fiber, the method further includes: determining the second vibration event in the fiber vibration data of the second optical fiber based on the light intensity amplitude in the fiber vibration data of the second optical fiber that is greater than a light intensity amplitude threshold; and extracting the second vibration event.

4. The method according to claim 3, characterized in that The determining, according to the light intensity amplitude greater than the light intensity amplitude threshold in the optical fiber vibration data of the first optical fiber, a first vibration event in the optical fiber vibration data of the first optical fiber comprises: When the optical fiber vibration data of the first optical fiber includes N consecutive light intensity amplitudes greater than the light intensity amplitude threshold on the time axis, determining a first vibration event in the optical fiber vibration data of the first optical fiber according to the N light intensity amplitudes greater than the light intensity amplitude threshold; N is an integer greater than 1; The determining, according to the light intensity amplitude greater than the light intensity amplitude threshold in the optical fiber vibration data of the second optical fiber, a second vibration event in the optical fiber vibration data of the second optical fiber comprises: When the fiber vibration data of the second optical fiber includes M consecutive light intensity amplitudes greater than the light intensity amplitude threshold on the time axis, the vibration events in the fiber vibration data of the second optical fiber are determined based on the M light intensity amplitudes greater than the light intensity amplitude threshold; M is an integer greater than 1.

5. The method according to claim 1, characterized in that The multiple curve similarity algorithms include at least two of the following algorithms: a cosine similarity CS algorithm, a Euclidean distance ED algorithm, and a dynamic time warping DTW algorithm.

6. The method according to claim 1, characterized in that The weighted judgment on the similarities obtained by the multiple curve similarity algorithms to obtain a detection result for characterizing whether the first optical fiber and the second optical fiber are co-groove optical fibers includes: Performing weighted summation on the similarities obtained by the plurality of curve similarity algorithms to obtain a weighted summation result; When the weighted sum result is greater than or equal to a first set value, it is determined that the detection result indicates that the first optical fiber and the second optical fiber are co-groove optical fibers; when the weighted sum result is less than the first set value, it is determined that the detection result indicates that the first optical fiber and the second optical fiber are not co-groove optical fibers.

7. The method according to claim 6, characterized in that Before weighted summing the similarities obtained by the plurality of curve similarity algorithms, the method further comprises: When the similarity obtained by any one of the plurality of curve similarity algorithms is greater than or equal to a second set value, the similarity obtained by the corresponding similarity algorithm is updated to 1; when the similarity obtained by any one of the plurality of curve similarity algorithms is less than the second set value, the similarity obtained by the corresponding similarity algorithm is updated to 0.

8. The method according to claim 6, characterized in that Before performing weighted summation on the similarities obtained by the plurality of curve similarity algorithms to obtain a weighted summation result, the method further includes: A weighting coefficient of each curve similarity algorithm is determined according to an average accuracy rate of each curve similarity algorithm among the multiple curve similarity algorithms.

9. A detection device for a same-groove optical fiber, characterized in that: The device comprises: An acquisition module, used to acquire optical fiber vibration data of the first optical fiber and optical fiber vibration data of the second optical fiber; A first processing module, configured to generate a first curve of the variation of the first vibration event over time according to a first vibration event extracted from the optical fiber vibration data of the first optical fiber; and to generate a second curve of the variation of the second vibration event over time according to a second vibration event extracted from the optical fiber vibration data of the second optical fiber; The second processing module is used to determine the similarity between the first curve and the second curve according to multiple curve similarity algorithms; perform weighted judgment on the similarities obtained by the multiple curve similarity algorithms to obtain a detection result for characterizing whether the first optical fiber and the second optical fiber are co-groove optical fibers.

10. An electronic device, characterized in that: The electronic device comprises a processor and a memory for storing a computer program that can be run on the processor; wherein, The processor is used to run the computer program to execute the method for detecting the same-groove optical fiber according to any one of claims 1 to 8.

11. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for detecting the same-groove optical fiber according to any one of claims 1 to 8 is implemented.

12. A computer program product, comprising a computer program, characterized in that The computer program implements the method for detecting the same-groove optical fiber according to any one of claims 1 to 8 when executed by a processor.

Citation Information

Patent Citations

  • Data fusion method and device, storage medium and server

    CN111767348A

  • Optical fiber vibration event identification method based on spectrum similarity

    CN112836574A

  • Optical fiber monitoring method, device, equipment and storage medium

    CN113949446A

  • Match determination device, match determination method, storage medium

    US20210158071A1