Optical fiber same route detection method, related equipment, storage medium and computer program product
By deploying optical fibers with routing detection equipment in the cloud and using neural network models to process the static and dynamic characteristics of optical fibers, the problems of existing equipment portability and high-performance algorithms are solved, and the accuracy and efficiency of detection are improved.
Patent Information
- Application Number
- CN202410977276.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-15
AI Technical Summary
Existing optical fiber and routing detection equipment cannot take into account both portability and high-performance algorithm capabilities, resulting in insufficient detection accuracy and efficiency of large or lightweight devices.
By deploying the first device in the cloud, using the trained preset neural network model, receiving detection requests sent by the second device, extracting static and dynamic features of the fiber pair, predicting and sending the same routing status information, high-performance algorithms are realized integration and portability.
It improves the accuracy and efficiency of optical fiber co-routing detection, reduces the size of the equipment, improves the recognition capability, and achieves both portability and high-performance algorithms.
Smart Images

Figure CN118971960A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of transmission and bearing technology, and in particular to an optical fiber co-routing detection method, related equipment, storage medium and computer program product. Background Art
[0002] At present, when performing co-routing detection on any two optical fibers, large-scale optical fiber co-routing detection devices / equipment are usually used to test different optical fiber segments inside the machine room. In order to conduct co-routing detection more flexibly and portable, portable optical fiber co-routing detection equipment / instruments have been developed. However, these portable optical fiber co-routing detection equipment / instruments have abandoned high power consumption and high-performance algorithm capabilities, and only some simple co-routing identification algorithms are integrated on the optical fiber co-routing detection equipment / instruments.
[0003] However, when a large optical fiber co-routing detection device is used to detect the co-routing of any two optical fibers, the large optical fiber co-routing detection device has the problem of being large in size and difficult to carry; and when a portable optical fiber co-routing detection device is used to detect the co-routing of any two optical fibers, the current portable optical fiber co-routing detection device is limited by the lightweight characteristics of the device itself and cannot integrate and expand high-power consumption and high-performance algorithms. Therefore, it is urgent to propose a device that can take into account both portability and high-performance algorithm capabilities. Summary of the invention
[0004] The implementation law of the present application provides a fiber co-routing detection method, related equipment, storage medium and computer program product, which can achieve the portability of the equipment while taking into account the high-performance algorithm capabilities of the equipment.
[0005] The technical solution of the embodiment of the present application is implemented as follows:
[0006] In a first aspect, an embodiment of the present application provides a method for detecting the same route of an optical fiber, the method being applied to a first device, the first device being deployed in the cloud, the method comprising:
[0007] Receiving a detection request sent by a second device; wherein the detection request carries first data, and the first data includes target data of the optical fiber pair to be predicted;
[0008] Determine a first feature and / or a second feature corresponding to the first data; wherein the first feature at least includes a static feature of the optical fiber pair to be predicted, and the second feature at least includes a dynamic feature of the optical fiber pair to be predicted;
[0009] Based on at least one of the first feature and the second feature, a first model determines a prediction result of the optical fiber pair to be predicted, and sends the prediction result to the second device; wherein the first model at least includes a trained preset neural network model; and the prediction result includes the co-routing status information of the optical fiber pair to be predicted.
[0010] In a second aspect, an embodiment of the present application provides a method for detecting the same route of an optical fiber, the method being applied to a second device, the method comprising:
[0011] Acquire second data; wherein the second data at least includes original data of the optical fiber pair to be predicted;
[0012] Performing a preprocessing operation on the second data to obtain first data corresponding to the second data;
[0013] Sending a detection request to a first device; wherein the detection request carries the first data, the first data includes target data of the optical fiber pair to be predicted, and the target data is data obtained by preprocessing the original data of the optical fiber pair to be predicted;
[0014] Receive the prediction result sent by the first device; wherein the prediction result includes the co-routing state information of the optical fiber pair to be predicted.
[0015] In a third aspect, an embodiment of the present application provides a first device, the first device comprising: a first receiving unit, a determining unit, and a first sending unit; wherein,
[0016] The first receiving unit is configured to receive a detection request sent by the second device; wherein the detection request carries first data, the first data includes target data of the optical fiber pair to be predicted, and the target data is data obtained by preprocessing the original data of the optical fiber pair to be predicted;
[0017] The determining unit is configured to determine a first feature and / or a second feature corresponding to the first data; wherein the first feature at least includes a static feature of the optical fiber pair to be predicted, and the second feature at least includes a dynamic feature of the optical fiber pair to be predicted; and determine a prediction result of the optical fiber pair to be predicted based on at least one of the first feature and the second feature and a first model;
[0018] The first sending unit is used to send the prediction result to the second device; wherein the first model at least includes a trained preset neural network model; and the prediction result includes the co-routing status information of the optical fiber pair to be predicted.
[0019] In a fourth aspect, an embodiment of the present application provides a first device, the first device comprising: a first processor and a first memory; wherein:
[0020] The first memory is used to store a computer program that can be run on the processor;
[0021] The first processor is used to execute the optical fiber co-routing detection method as described above when running the computer program.
[0022] In a fifth aspect, an embodiment of the present application provides a second device, the second device comprising: an acquisition unit, an operation unit, a second sending unit, and a second receiving unit; wherein:
[0023] The acquisition unit is used to acquire second data; wherein the second data at least includes original data of the optical fiber pair to be predicted;
[0024] The operation unit is used to perform a preprocessing operation on the second data to obtain first data corresponding to the second data;
[0025] The second sending unit is used to send a detection request to the first device; wherein the detection request carries the first data, the first data includes target data of the optical fiber pair to be predicted, and the target data is data obtained by preprocessing the original data of the optical fiber pair to be predicted;
[0026] The second receiving unit is used to receive the prediction result sent by the first device; wherein the prediction result includes the co-routing state information of the optical fiber pair to be predicted.
[0027] In a sixth aspect, an embodiment of the present application provides a second device, the second device comprising: a second processor and a second memory; wherein:
[0028] The second memory is used to store a computer program that can be run on the processor;
[0029] The second processor is used to execute the optical fiber co-routing detection method as described above when running the computer program.
[0030] In a seventh aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program code stored thereon. When the computer program code is executed by a computer, the optical fiber co-routing detection method as described above is implemented.
[0031] In an eighth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the optical fiber co-routing detection method as described above.
[0032] The embodiment of the present application provides a method for detecting the co-routing of optical fibers, related devices, storage media and computer program products, wherein a first device is deployed in the cloud, and the first device receives a detection request sent by a second device; wherein the detection request carries first data, and the first data includes target data of the optical fiber pair to be predicted; a first feature and / or a second feature corresponding to the first data is determined; wherein the first feature at least includes a static feature of the optical fiber pair to be predicted, and the second feature at least includes a dynamic feature of the optical fiber pair to be predicted; a prediction result of the optical fiber pair to be predicted is determined based on at least one of the first feature and the second feature and a first model, and the prediction result is sent to the second device; wherein the first model at least includes a trained preset neural network model; the prediction result includes the co-routing status information of the optical fiber pair to be predicted; the second device obtains second data; wherein the second data at least includes original data of the optical fiber pair to be predicted; the second device performs a preprocessing operation on the second data to obtain the first data corresponding to the second data; and a detection request is sent to the first device. It can be seen that the second device can obtain the original data of the optical fiber pair to be predicted, and perform preprocessing operations on the original data of the optical fiber pair to be predicted to obtain the first data, and then send the detection request carrying the first data to the first device; the first device can first determine the first feature and / or the second feature corresponding to the first data, the first feature at least includes the static feature of the optical fiber pair to be predicted, and the second feature at least includes the dynamic feature of the optical fiber pair to be predicted, and then the co-routing state information of the optical fiber pair to be predicted can be determined based on at least one of the first feature and the second feature and the trained preset neural network model, that is, the second device can send the first data to be detected to the first device, and the first device can detect and process the first data through the trained preset neural network model, so as to accurately identify the co-routing of the optical fiber pair to be predicted, thereby improving the recognition accuracy; and the first device is deployed in the cloud, and the first device proposed in the embodiment of the present application takes into account both portability and high-performance algorithm capabilities. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 Schematic diagram of the optical fiber co-routing detection method proposed in the embodiment of the present application Figure 1 ;
[0034] Figure 2 A schematic diagram of the static feature composition structure proposed in the embodiment of the present application;
[0035] Figure 3 A schematic diagram of the process of obtaining the curve features proposed in the embodiment of the present application;
[0036] Figure 4 Schematic diagram of the two-dimensional space-time vibration amplitude waterfall proposed in the embodiment of the present application Figure 1 ;
[0037] Figure 5A schematic diagram of the model training process proposed in the embodiment of the present application;
[0038] Figure 6 Schematic diagram of the optical fiber co-routing detection method proposed in the embodiment of the present application Figure 2 ;
[0039] Figure 7 Schematic diagram of the optical fiber co-routing detection method proposed in the embodiment of the present application Figure 3 ;
[0040] Figure 8 This is a schematic diagram of the structure of the artificial intelligence optical fiber co-route online identification system proposed in the embodiment of the present application;
[0041] Fig. 9 Schematic diagram of the optical fiber co-routing detection method proposed in the embodiment of the present application Figure 4 ;
[0042] Fig.10 Schematic diagram of the two-dimensional space-time vibration amplitude waterfall proposed in the embodiment of the present application Figure 2 ;
[0043] Fig.11 A schematic diagram of the detection process of the cloud-coordinated artificial intelligence optical fiber co-routing system proposed in an embodiment of the present application;
[0044] Fig.12 Schematic diagram of the composition structure of the first device proposed in the embodiment of the present application Figure 1 ;
[0045] Fig.13 Schematic diagram of the composition structure of the first device proposed in the embodiment of the present application Figure 2 ;
[0046] Fig.14 Schematic diagram of the composition structure of the second device proposed in the embodiment of the present application Figure 1 ;
[0047] Fig.15 Schematic diagram of the composition structure of the second device proposed in the embodiment of the present application Figure 2 . DETAILED DESCRIPTION
[0048] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. It is understood that the specific embodiments described herein are only used to explain the related applications, rather than to limit the applications. It should also be noted that, for ease of description, only the parts related to the related applications are shown in the accompanying drawings.
[0049] At present, optical fiber co-routing detection devices / instruments use distributed sensing technologies such as optical time-domain reflectometer (OTDR) and distributed fiber-optic vibration sensor (DVS) to detect co-routing optical fibers. Usually, large-scale detection devices / equipment are used to test different fiber segments inside the machine room. Therefore, in order to carry out co-routing detection flexibly and portable, some portable optical fiber co-routing detection devices / instruments have abandoned the high-power and high-performance algorithm capabilities and only integrated some simple and preliminary co-routing identification algorithms on the instrument.
[0050] However, one type of current optical fiber co-routing detection device has the problem of being large and difficult to carry; while another type of existing portable optical fiber co-routing detection device is limited by the lightweight characteristics of the device itself and cannot integrate and expand high-power consumption and high-performance algorithms. Therefore, it is urgent to propose a device that can take into account both portability and high-performance algorithm capabilities.
[0051] In order to solve the problem that the current optical fiber co-routing detection device cannot take into account both portability and high-performance algorithm capabilities, the embodiment of the present application provides an optical fiber co-routing detection method, related equipment, storage medium and computer program product, wherein a first device receives a detection request sent by a second device; wherein the detection request carries first data, and the first data includes target data of the optical fiber pair to be predicted; a first feature and / or a second feature corresponding to the first data is determined; wherein the first feature at least includes a static feature of the optical fiber pair to be predicted, and the second feature at least includes a dynamic feature of the optical fiber pair to be predicted; based on at least one of the first feature and the second feature and a first model, a prediction result of the optical fiber pair to be predicted is determined, and the prediction result is sent to the second device; wherein the first model at least includes a trained preset neural network model; the prediction result includes co-routing status information of the optical fiber pair to be predicted; the second device obtains second data; wherein the second data at least includes original data of the optical fiber pair to be predicted; the second device performs a preprocessing operation on the second data to obtain first data corresponding to the second data; and a detection request is sent to the first device. It can be seen that the second device can obtain the original data of the optical fiber pair to be predicted, and perform preprocessing operations on the original data of the optical fiber pair to be predicted to obtain the first data, and then send the detection request carrying the first data to the first device; the first device can first determine the first feature and / or the second feature corresponding to the first data, the first feature at least includes the static feature of the optical fiber pair to be predicted, and the second feature at least includes the dynamic feature of the optical fiber pair to be predicted, and then the co-routing state information of the optical fiber pair to be predicted can be determined based on at least one of the first feature and the second feature and the trained preset neural network model, that is, the second device can send the first data to be detected to the first device, and the first device can detect and process the first data through the trained preset neural network model, so as to accurately identify the co-routing of the optical fiber pair to be predicted, thereby improving the recognition accuracy; and the first device is deployed in the cloud, and the first device proposed in the embodiment of the present application takes into account both portability and high-performance algorithm capabilities.
[0052] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.
[0053] Embodiment 1
[0054] The embodiment of the present application provides a method for detecting the same route of an optical fiber. The method is applied to a first device, and the first device is deployed in the cloud. Figure 1 Schematic diagram of the optical fiber co-routing detection method proposed in the embodiment of the present application Figure 1 ,like Figure 1 As shown, the optical fiber co-routing detection method may include the following steps:
[0055] Step 101: Receive a detection request sent by a second device; wherein the detection request carries first data, and the first data includes target data of a fiber pair to be predicted.
[0056] In an embodiment of the present application, the first device may receive a detection request sent by the second device.
[0057] It should be noted that, in the embodiments of the present application, the first device may be deployed in the cloud, for example, the first device may be a cloud server, and the present application does not specifically limit the device type of the first device.
[0058] It should be noted that, in the embodiments of the present application, the second device may be a terminal device, and the present application does not specifically limit the device type of the second device.
[0059] It should be noted that, in an embodiment of the present application, the first data may include target data of the optical fiber pair to be predicted, and may also include target data of the optical cable pair to be predicted; wherein, the target data of the optical fiber pair to be predicted may be data obtained by preprocessing the original data of the optical fiber pair to be predicted, and the target data of the optical cable pair to be predicted may be data obtained by preprocessing the original data of the optical cable pair to be predicted. The method for obtaining the target data of the present application is not specifically limited.
[0060] Step 102: Determine a first feature and / or a second feature corresponding to the first data; wherein the first feature at least includes a static feature of the optical fiber pair to be predicted, and the second feature at least includes a dynamic feature of the optical fiber pair to be predicted.
[0061] In an embodiment of the present application, after receiving the detection request sent by the second device, the first device may determine the first feature and / or the second feature corresponding to the first data.
[0062] It should be noted that, in an embodiment of the present application, when determining the first feature corresponding to the first data, the first device can determine the curve feature corresponding to the first data and determine the static event feature corresponding to the first data; wherein the static event feature is used to characterize the quality information of the optical fiber pair to be predicted and / or the optical cable pair to be predicted; and then the static feature can be generated based on the curve feature and the static event feature.
[0063] It should be noted that, in the embodiments of the present application, the static event characteristics corresponding to the first data are used to characterize the quality information of the optical fiber pair to be predicted and / or the optical cable pair to be predicted. The quality information may include attenuation, reflection, fusion and aging, etc. The present application does not specifically limit the amount and type of information included in the quality information.
[0064] It should be noted that, in the embodiments of the present application, Figure 2 This is a schematic diagram of the static feature composition structure proposed in the embodiment of the present application, such as Figure 2As shown, after determining the curve feature corresponding to the first data and determining the static event feature corresponding to the first data, the first device can generate a static feature based on the curve feature and the static event feature (event feature).
[0065] It should be noted that, in the embodiments of the present application, Figure 3 A schematic diagram of the process of obtaining the curve features proposed in the embodiment of the present application is shown in FIG. Figure 3 As shown, when the first device determines the curve characteristics corresponding to the first data, it can obtain the first curve (OTDR curve) corresponding to the first data; wherein the first curve contains a one-dimensional sequence signal corresponding to the first data; then the first sequence characteristics corresponding to the first curve can be determined based on the first curve and the second model; and further, the curve characteristics can be determined based on the first sequence characteristics and the fully connected layer.
[0066] It should be noted that, in the embodiments of the present application, the second model at least includes a long short-term memory network (LSTM) model, and the present application does not specifically limit the model type of the second model.
[0067] It should be noted that, in the embodiment of the present application, when the first device obtains the first curve (OTDR curve) corresponding to the first data, it can parse and extract the OTDR curve from the original sor file of the OTDR.
[0068] It should be noted that, in an embodiment of the present application, when the first device determines the second feature corresponding to the first data, it can obtain dynamic parameter information corresponding to the first data; wherein the dynamic parameter information includes one or more of the occurrence time of the dynamic event signal, the occurrence location of the dynamic event signal, and the intensity information of the dynamic event signal; and then the second feature can be determined based on the dynamic parameter information.
[0069] For example, in the embodiments of the present application, Figure 4 Schematic diagram of the two-dimensional space-time vibration amplitude waterfall proposed in the embodiment of the present application Figure 1 ,like Figure 4 As shown, for the second feature (dynamic feature), what is stored in the database is a two-dimensional space-time vibration amplitude waterfall chart. The two dimensions in the waterfall chart are time (time points) and space (Spatial points). The points in the waterfall chart represent the intensity of the dynamic feature, that is, the occurrence time of the dynamic event signal corresponding to the first data, the occurrence position of the dynamic event signal and the intensity information of the dynamic event signal can be obtained, and then the two-dimensional space-time vibration amplitude waterfall chart can be generated based on the occurrence time of the dynamic event signal, the occurrence position of the dynamic event signal and the intensity information of the dynamic event signal.
[0070] That is to say, the present application can extract the first feature and / or the second feature of the first data through a first device deployed in the cloud, thereby solving the problem that the current optical fiber co-routing detection device is large in size and difficult to carry, and greatly reducing the detection cost of co-routing optical fibers.
[0071] Step 103, based on at least one of the first feature and the second feature, the first model determines the prediction result of the optical fiber pair to be predicted, and sends the prediction result to the second device; wherein the first model at least includes a trained preset neural network model; the prediction result includes the co-routing status information of the optical fiber pair to be predicted.
[0072] In an embodiment of the present application, after determining the first feature and / or the second feature corresponding to the first data, the first device can determine a prediction result of the optical fiber pair to be predicted based on at least one of the first feature and the second feature and the first model, and send the prediction result to the second device.
[0073] It should be noted that, in an embodiment of the present application, the first model may include a trained preset neural network model, and the trained preset neural network model may include an LSTM model, a convolutional neural network (CNN), and a recurrent neural network (RNN). The present application does not specifically limit the model type of the first model.
[0074] It should be noted that in an embodiment of the present application, the prediction result may include the co-routing status information of the optical fiber pair to be predicted and / or the co-routing status information of the optical cable pair to be predicted. The co-routing status information may include the co-cable status and the co-groove status. The present application does not specifically limit the status type included in the co-routing status information.
[0075] It should be noted that, in an embodiment of the present application, when the first device determines the prediction result of the optical fiber pair to be predicted and / or the optical cable pair to be predicted based on at least one of the first feature and the second feature and the first model, at least one of the first feature and the second feature can be input into the first model, and then the prediction result of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can be obtained.
[0076] Exemplarily, in an embodiment of the present application, the first device can construct a comprehensive feature vector matrix based on the first feature, i.e., the static feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and then the comprehensive feature vector matrix can be input into a trained preset neural network model, thereby obtaining the same routing status information of the optical fiber pair to be predicted and / or the optical cable pair to be predicted.
[0077] Exemplarily, in an embodiment of the present application, the first device can input the dynamic characteristics (two-dimensional space-time vibration amplitude matrix) of the optical fiber pair to be predicted and / or the optical cable pair to be predicted into a trained preset neural network model, and then obtain the co-routing status information of the optical fiber pair to be predicted and / or the optical cable pair to be predicted.
[0078] That is to say, in the embodiment of the present application, the first device in the cloud can detect the predicted optical fiber pair and / or the predicted optical cable pair through a trained preset neural network model to obtain a judgment result of whether the predicted optical fiber pair and / or the predicted optical cable pair are co-routed, that is, the first device in the embodiment of the present application can integrate and expand a high-power consumption and high-performance algorithm, and the first device is deployed in the cloud, thereby greatly improving the portability of the detection device, reducing the size of the optical fiber co-route detection device, and improving the co-route recognition capability of the device.
[0079] It should be noted that in an embodiment of the present application, the first device may also include a co-routing resource database, which may include channel labels, optical cable labels, geographic locations, static features, and dynamic features, etc. The present application does not specifically limit the type and amount of information included in the co-routing resource database.
[0080] It should be noted that in the embodiments of the present application, information such as the cable number, channel label and geographical location of each optical fiber / optical cable in the same-route resource database can be manually entered during measurement; and for the static characteristics and dynamic characteristics of each optical fiber / optical cable in the same-route resource database, the above-mentioned method of obtaining the first characteristic and the second characteristic can be referred to.
[0081] It should be noted that in an embodiment of the present application, as shown in Table 1 below, the information stored in the same routing resource database for each optical fiber / cable is as follows. The same routing resource database may include channel labels, cable labels, cable lengths, geographic locations and routing map information, static features, and dynamic features.
[0082] Table 1 Information composition table of the same routing resource database
[0083]
[0084] It should be noted that, in the embodiment of the present application, after the first device constructs the same-route resource database, it can perform cloud model training and reasoning based on the optical fiber pairs in the same-route resource database. For example, a comprehensive feature vector matrix can be constructed based on the static features of a pair of optical fibers / optical cables to store the comprehensive feature vectors of the optical fiber pair to be identified. The comprehensive feature vector matrix constructed by the static features of the optical fiber / optical cable can be input into the neural network model to train it and obtain the prediction result. Figure 5A schematic diagram of the model training process proposed in the embodiment of the present application is shown in FIG. Figure 5 As shown, in the horizontal direction, the left side is the splicing of the event characteristics and curve characteristics of a pair of optical fibers that need to be judged whether they are in the same cable. The value "0" on the right side represents the same cable label, and the value "1" represents different cable labels. Whether the pair of optical fibers are in the same cable is determined by the channel label, cable label, and geographic location routing map information in the same routing resource database.
[0085] It should be noted that in an embodiment of the present application, the first device can use the above information (comprehensive feature vector) as the input of the neural network model to train the model, and can judge the accuracy of the model based on whether the cable labels are the same, and then store the trained model, i.e., the preset neural network model.
[0086] It should be noted that in an embodiment of the present application, the first device can also obtain the dynamic characteristics of a pair of optical fibers / optical cables, and then can input the two-dimensional waterfall diagram (two-dimensional space-time vibration amplitude data matrix) of a pair of optical fibers / optical cables into the neural network model for training, and judge the accuracy of the model based on whether the same groove label is used, and then the trained model, i.e., the preset neural network model, can be stored.
[0087] That is to say, in an embodiment of the present application, the first device can construct a co-routing resource database, and perform cloud-based model training and reasoning based on the optical fiber pairs / optical cable pairs in the co-routing resource database to obtain a trained neural network model, and then after receiving the detection request sent by the second device, the data carried by the detection request can be detected based on the trained neural network model, thereby obtaining the co-routing status information of the optical fiber pair to be predicted and / or the co-routing status information of the optical cable pair to be predicted.
[0088] In summary, the first device is deployed in the cloud, and the first device can receive a detection request sent by the second device; wherein the detection request carries first data, and the first data includes data preprocessed from the original data of the optical fiber pair to be predicted, and / or data preprocessed from the original data of the optical cable pair to be predicted. Then, the first device can extract static features and / or dynamic features of the first data, and then can construct a comprehensive feature vector matrix based on the first feature, i.e., the static features of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and input the comprehensive feature vector matrix into a trained preset neural network model, so as to obtain the co-routing status of the optical fiber pair to be predicted and / or the optical cable pair to be predicted. Information, and the dynamic characteristics (two-dimensional space-time vibration amplitude matrix) of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can also be input into the trained preset neural network model, so as to obtain the co-route status information of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, that is, the first device in the embodiment of the present application can integrate and expand the high-power consumption and high-performance algorithm, and detect the optical fiber pair to be predicted and / or the optical cable pair to be predicted through the trained preset neural network model to obtain the judgment result of whether the optical fiber pair to be predicted and / or the optical cable pair to be predicted are co-routed, and the first device is deployed in the cloud. It can be seen that the first device in the embodiment of the present application can take into account both portability and high-performance algorithm capabilities.
[0089] An embodiment of the present application provides a method for detecting co-routing of optical fibers, which is applied to a first device, wherein the first device receives a detection request sent by a second device; wherein the detection request carries first data, and the first data includes data pre-processed from the original data of the optical fiber pair to be predicted, and / or data pre-processed from the original data of the optical cable pair to be predicted; a first feature and / or a second feature corresponding to the first data are determined; wherein the first feature at least includes static features of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and the second feature at least includes dynamic features of the optical fiber pair to be predicted and / or the optical cable pair to be predicted; based on at least one of the first feature and the second feature and a first model, a prediction result of the optical fiber pair to be predicted and / or the optical cable pair to be predicted is determined, and the prediction result is sent to the second device; wherein the first model at least includes a trained preset neural network model; and the prediction result includes co-routing status information of the optical fiber pair to be predicted and / or the co-routing status information of the optical cable pair to be predicted. It can be seen that after receiving the first data, the first device can first determine the first feature and / or the second feature corresponding to the first data, the first feature at least includes the static feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and the second feature at least includes the dynamic feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and then the prediction result of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can be determined based on at least one of the first feature and the second feature and the trained preset neural network model, that is, the co-routing state information of the optical fiber pair to be predicted and / or the co-routing state information of the optical cable pair to be predicted. The embodiment of the present application can detect the optical fiber pair to be predicted and / or the optical cable pair to be predicted through the trained preset neural network model, so as to accurately identify the co-routing of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, thereby improving the recognition efficiency and recognition accuracy; and the first device is deployed in the cloud, that is, the first device takes into account both portability and high-performance algorithm capabilities.
[0090] Embodiment 2
[0091] Based on the above embodiment, another embodiment of the present application provides a method for detecting the same route of an optical fiber, which is applied to a second device. Figure 6 Schematic diagram of the optical fiber co-routing detection method proposed in the embodiment of the present application Figure 2 ,like Figure 6 As shown, the optical fiber co-routing detection method may include the following steps:
[0092] Step 201: Acquire second data; wherein the second data at least includes original data of the optical fiber pair to be predicted.
[0093] In an embodiment of the present application, the second device may acquire the second data.
[0094] It should be noted that, in the embodiments of the present application, the second device may be a terminal device, and the present application does not specifically limit the device type of the second device.
[0095] It should be noted that, in the embodiments of the present application, the second data at least includes original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and the present application does not specifically limit the type and quantity of the data included in the second data.
[0096] It should be noted that, in an embodiment of the present application, when the second device obtains the second data of the optical fiber pair to be predicted, it can obtain the third data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted; wherein the third data includes the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted collected by the OTDR unit; fourth data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can also be obtained; wherein the fourth data includes the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted collected by the DVS unit; and the second data can be determined based on the third data and the fourth data.
[0097] Furthermore, in an embodiment of the present application, when the second device determines the second data based on the third data and the fourth data, it can parse the third data to obtain fifth data; wherein the fifth data at least includes curve characteristic data and event characteristic data; then the fourth data can be converted to obtain sixth data; wherein the sixth data at least includes two-dimensional matrix data corresponding to the fourth data, and the two-dimensional matrix data is used to characterize parameter information of the dynamic event signal; and then the second data can be determined based on the fifth data and the sixth data.
[0098] Exemplarily, in an embodiment of the present application, as shown in Table 2 below, the second device can collect the original data (OTDR data) of the optical fiber pair to be predicted and / or the optical cable pair to be predicted through the OTDR unit, and the collected file is the original sor file, which can then be further parsed into curve characteristic data and event characteristic data based on the original sor file; the original data (vibration data) of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can also be collected based on the DVS unit, and then the vibration data can be converted into plain text form of a waterfall chart, expressed as a two-dimensional space-time vibration amplitude data matrix (two-dimensional matrix data).
[0099] Table 2 Collection format of raw data
[0100]
[0101] Step 202: perform a preprocessing operation on the second data to obtain first data corresponding to the second data.
[0102] In an embodiment of the present application, after acquiring the second data, the second device may perform a preprocessing operation on the second data to obtain the first data corresponding to the second data.
[0103] It should be noted that, in an embodiment of the present application, when the second device performs a preprocessing operation on the second data to obtain the first data corresponding to the second data, it can filter the fifth data based on the first preset threshold and the average amplitude value to obtain the seventh data, and filter the sixth data based on the first preset threshold and the average amplitude value to obtain the eighth data; wherein the average amplitude value at least includes the average amplitude value of the historical data; and then the first data can be determined based on the seventh data and the eighth data.
[0104] It should be noted that, in the embodiments of the present application, the first preset threshold value may be set to 10% or other values, and the present application does not specifically limit the size of the first preset threshold value.
[0105] Illustratively, in an embodiment of the present application, when the second device performs preprocessing operations on the fifth data and the sixth data to obtain the first data, it can filter out the bottom noise that is less than 10% of the average amplitude value. In actual applications, the size of the first preset threshold can be adjusted according to actual conditions.
[0106] Step 203, sending a detection request to the first device; wherein the detection request carries first data, the first data includes target data of the optical fiber pair to be predicted, and the target data is data obtained by preprocessing the original data of the optical fiber pair to be predicted.
[0107] In an embodiment of the present application, after the second device performs a preprocessing operation on the second data and obtains the first data corresponding to the second data, it can send a detection request to the first device.
[0108] Step 204: Receive the prediction result sent by the first device; wherein the prediction result includes the co-routing state information of the optical fiber pair to be predicted.
[0109] In an embodiment of the present application, after sending a detection request to the first device, the second device can receive the prediction result sent by the first device; wherein the prediction result includes the co-routing status information of the optical fiber pair to be predicted and / or the co-routing status information of the optical cable pair to be predicted.
[0110] To summarize, the second device can obtain the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and perform preprocessing operations on the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted to obtain the first data, and then send a detection request carrying the first data to the first device, so that the first device detects the first data, and receives the prediction result sent by the first device, which includes the co-routing status information of the optical fiber pair to be predicted and / or the co-routing status information of the optical cable pair to be predicted, that is, the second device does not need to detect the first data, and can complete the detection of the first data through the first device deployed in the cloud, thereby improving the detection efficiency and detection accuracy of the optical fiber pair to be predicted and / or the optical cable pair to be predicted.
[0111] The embodiment of the present application provides a method for detecting the co-routing of optical fibers, which is applied to a second device, wherein the second device obtains second data; wherein the second data at least includes the original data of the optical fiber pair to be predicted; the second data is preprocessed to obtain the first data corresponding to the second data; a detection request is sent to the first device; wherein the detection request carries the first data, the first data includes the target data of the optical fiber pair to be predicted, and the target data is the data after the original data of the optical fiber pair to be predicted is preprocessed; the prediction result sent by the first device is received; wherein the prediction result includes the co-routing state information of the optical fiber pair to be predicted. It can be seen that the second device can first obtain the second data, i.e., the original data of the optical fiber pair to be predicted; and preprocess the second data to obtain the first data corresponding to the second data, and then send the detection request carrying the first data to the first device for detection. Since the data carried in the detection request sent by the second device is the preprocessed data, the subsequent detection accuracy of the first data by the first device can be improved, thereby improving the co-routing recognition accuracy of the optical fiber pair to be predicted.
[0112] Embodiment 3
[0113] Based on the above embodiments, another embodiment of the present application provides a method for detecting the same route of an optical fiber, which is applied to a first device and a second device. Figure 7 Schematic diagram of the optical fiber co-routing detection method proposed in the embodiment of the present application Figure 3 ,like Figure 7 As shown, the optical fiber co-routing detection method may include the following steps:
[0114] Step 301: A second device obtains second data; wherein the second data at least includes original data of a fiber pair to be predicted.
[0115] It should be noted that, in the embodiments of the present application, the second device may be a terminal device, and the present application does not specifically limit the device type of the second device.
[0116] It should be noted that, in the embodiments of the present application, the second data at least includes original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and the present application does not specifically limit the type and quantity of the data included in the second data.
[0117] It should be noted that, in an embodiment of the present application, when the second device obtains the second data of the optical fiber pair to be predicted, it can obtain the third data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted; wherein the third data includes the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted collected by the OTDR unit; fourth data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can also be obtained; wherein the fourth data includes the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted collected by the DVS unit; and the second data can be determined based on the third data and the fourth data.
[0118] Furthermore, in an embodiment of the present application, when the second device determines the second data based on the third data and the fourth data, it can parse the third data to obtain fifth data; wherein the fifth data at least includes curve characteristic data and event characteristic data; then the fourth data can be converted to obtain sixth data; wherein the sixth data at least includes two-dimensional matrix data corresponding to the fourth data, and the two-dimensional matrix data is used to characterize parameter information of the dynamic event signal; and then the second data can be determined based on the fifth data and the sixth data.
[0119] Exemplarily, in an embodiment of the present application, as shown in Table 1 above, the second device can collect the original data (OTDR data) of the optical fiber pair to be predicted and / or the optical cable pair to be predicted through the OTDR unit, and the collected file is the original sor file, and then it can be further parsed into curve characteristic data and event characteristic data based on the original sor file; it can also collect the original data (vibration data) of the optical fiber pair to be predicted and / or the optical cable pair to be predicted based on the DVS unit, and then the vibration data can be converted into plain text form of a waterfall chart, which is expressed as a two-dimensional space-time vibration amplitude data matrix (two-dimensional matrix data).
[0120] Step 302: The second device performs a preprocessing operation on the second data to obtain first data corresponding to the second data.
[0121] It should be noted that, in an embodiment of the present application, when the second device performs a preprocessing operation on the second data to obtain the first data corresponding to the second data, it can filter the fifth data based on the first preset threshold and the average amplitude value to obtain the seventh data, and filter the sixth data based on the first preset threshold and the average amplitude value to obtain the eighth data; wherein the average amplitude value at least includes the average amplitude value of the historical data; and then the first data can be determined based on the seventh data and the eighth data.
[0122] It should be noted that, in the embodiments of the present application, the first preset threshold value may be set to 10% or other values, and the present application does not specifically limit the size of the first preset threshold value.
[0123] Illustratively, in an embodiment of the present application, when the second device performs preprocessing operations on the fifth data and the sixth data to obtain the first data, it can filter out the bottom noise that is less than 10% of the average amplitude value. In actual applications, the size of the first preset threshold can be adjusted according to actual conditions.
[0124] Step 303: The second device sends a detection request to the first device; wherein the detection request carries first data, the first data includes target data of the optical fiber pair to be predicted, and the target data is data obtained by preprocessing the original data of the optical fiber pair to be predicted.
[0125] Step 304: The first device determines a first feature and / or a second feature corresponding to the first data; wherein the first feature at least includes a static feature of the optical fiber pair to be predicted, and the second feature at least includes a dynamic feature of the optical fiber pair to be predicted.
[0126] It should be noted that, in an embodiment of the present application, when determining the first feature corresponding to the first data, the first device can determine the curve feature corresponding to the first data and determine the static event feature corresponding to the first data; wherein the static event feature is used to characterize the quality information of the optical fiber pair to be predicted and / or the optical cable pair to be predicted; and then the static feature can be generated based on the curve feature and the static event feature.
[0127] It should be noted that, in the embodiments of the present application, the static event characteristics corresponding to the first data are used to characterize the quality information of the optical fiber pair to be predicted and / or the optical cable pair to be predicted. The quality information may include attenuation, reflection, fusion and aging, etc. The present application does not specifically limit the amount and type of information included in the quality information.
[0128] It should be noted that, in the embodiments of the present application, Figure 2 As shown, after determining the curve feature corresponding to the first data and determining the static event feature corresponding to the first data, the first device can generate a static feature based on the curve feature and the static event feature (event feature).
[0129] It should be noted that, in the embodiments of the present application, Figure 3 As shown, when the first device determines the curve characteristics corresponding to the first data, it can obtain the first curve (OTDR curve) corresponding to the first data; wherein the first curve contains a one-dimensional sequence signal corresponding to the first data; then the first sequence characteristics corresponding to the first curve can be determined based on the first curve and the second model; and further, the curve characteristics can be determined based on the first sequence characteristics and the fully connected layer.
[0130] It should be noted that, in the embodiments of the present application, the second model at least includes an LSTM model, and the present application does not specifically limit the model type of the second model.
[0131] It should be noted that, in the embodiment of the present application, when the first device obtains the first curve (OTDR curve) corresponding to the first data, it can parse and extract the OTDR curve from the original sor file of the OTDR.
[0132] It should be noted that, in an embodiment of the present application, when the first device determines the second feature corresponding to the first data, it can obtain dynamic parameter information corresponding to the first data; wherein the dynamic parameter information includes one or more of the occurrence time of the dynamic event signal, the occurrence location of the dynamic event signal, and the intensity information of the dynamic event signal; and then the second feature can be determined based on the dynamic parameter information.
[0133] For example, in the embodiments of the present application, Figure 4 As shown, for the second feature (dynamic feature), what is stored in the database is a two-dimensional space-time vibration amplitude waterfall chart, in which the two dimensions are time and space, and the points in the waterfall chart represent the intensity of the dynamic feature, that is, the occurrence time of the dynamic event signal corresponding to the first data, the occurrence position of the dynamic event signal and the intensity information of the dynamic event signal can be obtained, and then the two-dimensional space-time vibration amplitude waterfall chart can be generated based on the occurrence time of the dynamic event signal, the occurrence position of the dynamic event signal and the intensity information of the dynamic event signal.
[0134] That is to say, the present application can extract the first feature and / or the second feature of the first data through a first device deployed in the cloud, thereby solving the problem that the current optical fiber co-routing detection device is large in size and difficult to carry, and greatly reducing the detection cost of co-routing optical fibers.
[0135] Step 305: The first device determines a prediction result of the optical fiber pair to be predicted based on at least one of the first feature and the second feature and a first model, and sends the prediction result to the second device; wherein the first model at least includes a trained preset neural network model; and the prediction result includes co-routing status information of the optical fiber pair to be predicted.
[0136] It should be noted that, in an embodiment of the present application, the first model may include a trained preset neural network model, and the trained preset neural network model may include an LSTM model, CNN, and RNN. The present application does not specifically limit the model type of the first model.
[0137] It should be noted that in an embodiment of the present application, the prediction result may include the co-routing status information of the optical fiber pair to be predicted and / or the co-routing status information of the optical cable pair to be predicted. The co-routing status information may include the co-cable status and the co-groove status. The present application does not specifically limit the status type included in the co-routing status information.
[0138] It should be noted that, in an embodiment of the present application, when the first device determines the prediction result of the optical fiber pair to be predicted and / or the optical cable pair to be predicted based on at least one of the first feature and the second feature and the first model, at least one of the first feature and the second feature can be input into the first model, and then the prediction result of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can be obtained.
[0139] Exemplarily, in an embodiment of the present application, the first device can construct a comprehensive feature vector matrix based on the first feature, i.e., the static feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and then the comprehensive feature vector matrix can be input into a trained preset neural network model, thereby obtaining the same routing status information of the optical fiber pair to be predicted and / or the optical cable pair to be predicted.
[0140] Exemplarily, in an embodiment of the present application, the first device can input the dynamic characteristics (two-dimensional space-time vibration amplitude matrix) of the optical fiber pair to be predicted and / or the optical cable pair to be predicted into a trained preset neural network model, and then obtain the co-routing status information of the optical fiber pair to be predicted and / or the optical cable pair to be predicted.
[0141] That is to say, in the embodiment of the present application, the first device in the cloud can detect the predicted optical fiber pair and / or the predicted optical cable pair through a trained preset neural network model to obtain a judgment result of whether the predicted optical fiber pair and / or the predicted optical cable pair are co-routed, that is, the first device in the embodiment of the present application can integrate and expand a high-power consumption and high-performance algorithm, and the first device is deployed in the cloud, thereby greatly improving the portability of the detection device, reducing the size of the optical fiber co-route detection device, and improving the co-route recognition capability of the device.
[0142] It should be noted that in an embodiment of the present application, the first device may also include a co-routing resource database, which may include channel labels, optical cable labels, geographic locations, static features, and dynamic features, etc. The present application does not specifically limit the type and amount of information included in the co-routing resource database.
[0143] It should be noted that in the embodiments of the present application, information such as the cable number, channel label and geographical location of each optical fiber / optical cable in the same-route resource database can be manually entered during measurement; and for the static characteristics and dynamic characteristics of each optical fiber / optical cable in the same-route resource database, the above-mentioned method of obtaining the first characteristic and the second characteristic can be referred to.
[0144] It should be noted that in an embodiment of the present application, as shown in Table 2 above, the information stored in the same routing resource database for each optical fiber / optical cable is as follows. The same routing resource database may include channel labels, cable labels, cable lengths, geographic locations and routing map information, static features, and dynamic features.
[0145] It should be noted that, in the embodiment of the present application, after the first device has constructed the same-route resource database, it can perform cloud model training and reasoning based on the fiber pairs in the same-route resource database. For example, a comprehensive feature vector matrix can be constructed based on the static features of a pair of optical fibers / optical cables to store the comprehensive feature vectors of the optical fiber pair to be identified. The comprehensive feature vector matrix constructed based on the static features of the optical fiber / optical cable can be input into the neural network model to train it and obtain prediction results, such as Figure 5 As shown, in the horizontal direction, the left side is the splicing of the event characteristics and curve characteristics of a pair of optical fibers that need to be judged whether they are in the same cable. The value "0" on the right side represents the same cable label, and the value "1" represents different cable labels. Whether the pair of optical fibers are in the same cable is determined by the channel label, cable label, and geographic location routing map information in the same routing resource database.
[0146] It should be noted that in an embodiment of the present application, the first device can use the above information (comprehensive feature vector) as the input of the neural network model to train the model, and can judge the accuracy of the model based on whether the cable labels are the same, and then store the trained model, i.e., the preset neural network model.
[0147] It should be noted that in an embodiment of the present application, the first device can also obtain the dynamic characteristics of a pair of optical fibers / optical cables, and then can input the two-dimensional waterfall diagram (two-dimensional space-time vibration amplitude data matrix) of a pair of optical fibers / optical cables into the neural network model for training, and judge the accuracy of the model based on whether the same groove label is used, and then the trained model, i.e., the preset neural network model, can be stored.
[0148] That is to say, in an embodiment of the present application, the first device can construct a co-routing resource database, and perform cloud-based model training and reasoning based on the optical fiber pairs / optical cable pairs in the co-routing resource database to obtain a trained neural network model, and then after receiving the detection request sent by the second device, the data carried by the detection request can be detected based on the trained neural network model, thereby obtaining the co-routing status information of the optical fiber pair to be predicted and / or the co-routing status information of the optical cable pair to be predicted.
[0149] In summary, the second device can obtain the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and perform preprocessing operations on the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted to obtain the first data, and then send a detection request carrying the first data to the first device, the first device is deployed in the cloud, the first device can extract the static features and / or dynamic features of the first data, and then can construct a comprehensive feature vector matrix based on the first feature, that is, the static features of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and input the comprehensive feature vector matrix into the trained preset neural network model, so that the co-path of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can be obtained. From the status information, the dynamic characteristics (two-dimensional space-time vibration amplitude matrix) of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can also be input into the trained preset neural network model, so that the co-route status information of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can be obtained, that is, the first device in the embodiment of the present application can integrate and expand high-power consumption and high-performance algorithms, and detect the optical fiber pair to be predicted and / or the optical cable pair to be predicted through the trained preset neural network model to obtain the judgment result of whether the optical fiber pair to be predicted and / or the optical cable pair to be predicted are co-routed, and the first device is deployed in the cloud. It can be seen that the first device in the embodiment of the present application can take into account both portability and high-performance algorithm capabilities.
[0150] The embodiment of the present application provides a method for detecting the same route of an optical fiber. The method is applied to a first device and a second device. The first device is deployed in the cloud. The first device receives a detection request sent by the second device. The detection request carries first data. The first data includes data after preprocessing the original data of the optical fiber pair to be predicted and / or data after preprocessing the original data of the optical cable pair to be predicted. The first feature and / or the second feature corresponding to the first data are determined. The first feature at least includes the static feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and the second feature at least includes the dynamic feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted. ; Based on at least one of the first feature and the second feature, the first model determines the prediction result of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and sends the prediction result to the second device; wherein the first model at least includes a trained preset neural network model; the prediction result includes the co-routing status information of the optical fiber pair to be predicted and / or the co-routing status information of the optical cable pair to be predicted; the second device obtains second data; wherein the second data at least includes the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted; the second device performs a preprocessing operation on the second data to obtain the first data corresponding to the second data; and sends a detection request to the first device. It can be seen that the second device can obtain the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and pre-process the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted to obtain the first data, and then send the detection request carrying the first data to the first device; the first device can first determine the first feature and / or the second feature corresponding to the first data, the first feature at least includes the static feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and the second feature at least includes the dynamic feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and then the co-routing state information of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can be determined based on at least one of the first feature and the second feature and the trained preset neural network model, that is, the second device can send the first data to be detected to the first device, and the first device can detect and process the first data through the trained preset neural network model, so that the optical fiber pair to be predicted and / or the optical cable pair to be predicted can be accurately identified for the co-routing, thereby improving the recognition accuracy; and the first device is deployed in the cloud, and the first device proposed in the embodiment of the present application takes into account both portability and high-performance algorithm capabilities.
[0151] Embodiment 4
[0152] Based on the above embodiments, another embodiment of the present application provides a method for detecting the same route of optical fibers, and proposes a cloud-cooperative artificial intelligence online identification method and system for the same route of optical fibers. Figure 8 This is a schematic diagram of the structure of the artificial intelligence optical fiber co-route online identification system proposed in the embodiment of the present application, as shown in Figure 8As shown, the system mainly includes the following three parts: (1) optical fiber / optical cable; (2) small detection terminal (second device); (3) cloud service system (first device); wherein the small monitoring terminal may include: data preprocessing unit, OTRD distributed sensing unit, DVS distributed sensing unit; the cloud service system may include: same routing resource database, neural network training reasoning, machine learning training reasoning function module.
[0153] It should be noted that, in the embodiments of the present application, Fig. 9 Schematic diagram of the optical fiber co-routing detection method proposed in the embodiment of the present application Figure 4 ,like Fig. 9 As shown, the cloud-coordinated artificial intelligence optical fiber co-routing online detection method and the overall detection process of the system may include the following steps: Step 401, the small detection terminal collects raw data from the optical fiber / optical cable through OTDR and DVS; Step 402, the small detection terminal performs data preprocessing operations on the raw data, and then reports the preprocessed data to the cloud service system through wireless transmission; Step 403, the cloud service system completes the construction of the co-routing resource database based on the received data and the manually entered information, and is responsible for completing the training and reasoning of models such as neural networks or machine learning; Step 404, when the cloud service system completes the reasoning, it will send the detection results to the small detection terminal by wireless transmission to complete the real-time display of the results.
[0154] It should be noted that, in the embodiment of the present application, the data format collected by the small detection terminal (second device) is as shown in Table 1 above. The second device can collect the original data (OTDR data) of the optical fiber pair to be predicted and / or the optical cable pair to be predicted through the OTDR unit. The collected file is the original sor file, and then it can be further parsed into curve characteristic data and event characteristic data based on the original sor file; it can also collect the original data (vibration data) of the optical fiber pair to be predicted and / or the optical cable pair to be predicted based on the DVS unit, and then the vibration data can be converted into plain text form of a waterfall chart, which is expressed as a two-dimensional space-time vibration amplitude data matrix (two-dimensional matrix data).
[0155] It should be noted that in the embodiment of the present application, the second device can use the threshold method to filter out the bottom noise less than 10% (first preset threshold) of the average amplitude value for the collected raw data of the OTDR and DVS, so as to obtain the first data, and 10% is an empirical value obtained in a test. In the application, the size of the threshold (first preset threshold) is usually adjusted according to the actual situation.
[0156] It should be noted that in the embodiments of the present application, the method for constructing a same-route resource database is introduced below. The same-route resource database proposed in the present application may include channel labels, optical cable labels, geographic locations, static features, and dynamic features, etc. The present application does not specifically limit the type and amount of information included in the same-route resource database.
[0157] It should be noted that in the embodiments of the present application, information such as the cable number, channel label and geographical location of each optical fiber / optical cable in the same-route resource database can be manually entered during measurement; and for the static characteristics and dynamic characteristics of each optical fiber / optical cable in the same-route resource database, the above-mentioned method of obtaining the first characteristic and the second characteristic can be referred to.
[0158] It should be noted that in the embodiments of the present application, for static characteristics, the optical fiber Rayleigh backscattering signal contains a large amount of optical fiber characteristic information, such as connectors, joints, fusion points, optical fiber itself, etc., so the optical fiber quality can be evaluated by indicators such as attenuation, reflection, fusion and aging, which represent the static characteristics of the optical fiber. The OTDR data of the optical fiber contains multiple characteristics. In the present application, the two parts of optical fiber feature processing may include: curve features and event features, and the specific steps are as follows: Step 1: The first device can parse and extract the OTDR curve (first curve) from the original OTDR sor file, and the curve is expressed as a one-dimensional sequence signal; Step 2: The above one-dimensional sequence signal is input into the LSTM (second model) to generate a sequence feature of length N (first sequence feature); Step 3: The sequence feature of length N obtained in the above step is fed into the fully connected layer to generate a curve feature of length M; Step 4: For the event features of the optical fiber, four feature values can be selected from the original sor file parameters, including: event type, event location, return loss and fusion loss, to construct an event feature vector (static event feature); wherein, the event types include: reflection, attenuation, gain, etc.
[0159] That is to say, in the embodiments of the present application, Figure 3 As shown, when determining the curve feature, the first device can obtain a first curve (OTDR curve) corresponding to the first data; wherein the first curve includes a one-dimensional sequence signal corresponding to the first data; then the first sequence feature corresponding to the first curve can be determined based on the first curve and the second model; and then the curve feature can be determined based on the first sequence feature and the fully connected layer; as shown Figure 2 As shown, after determining the curve feature corresponding to the first data and determining the event feature (static event feature) corresponding to the first data, the first device can generate a static feature based on the curve feature and the event feature.
[0160] It should be noted that in the embodiment of the present application, for dynamic features, what is stored in the database is a two-dimensional spatiotemporal vibration amplitude waterfall diagram. Fig.10 Schematic diagram of the two-dimensional space-time vibration amplitude waterfall proposed in the embodiment of the present application Figure 2 ,like Fig.10 As shown, the two dimensions in the waterfall chart are time and space. The points in the waterfall chart represent the intensity of dynamic features. For the collected dynamic events, a two-dimensional spatiotemporal vibration amplitude waterfall chart is generated according to the time when the dynamic event occurred, the location where the dynamic event occurred, and the intensity of the dynamic event.
[0161] It should be noted that in an embodiment of the present application, as shown in Table 2 above, the information stored in the same routing resource database for each optical fiber / optical cable is as follows. The same routing resource database may include channel labels, cable labels, cable lengths, geographic locations and routing map information, static features, and dynamic features.
[0162] It should be noted that, in the embodiment of the present application, after the first device has constructed the same-route resource database, it can perform cloud model training and reasoning based on the fiber pairs in the same-route resource database. For example, a comprehensive feature vector matrix can be constructed based on the static features of a pair of optical fibers / optical cables to store the comprehensive feature vectors of the optical fiber pair to be identified. The comprehensive feature vector matrix constructed based on the static features of the optical fiber / optical cable can be input into the neural network model to train it and obtain prediction results, such as Figure 5 As shown, in the horizontal direction, the left side is the splicing of the event characteristics and curve characteristics of a pair of optical fibers that need to be judged whether they are in the same cable. The value "0" on the right side represents the same cable label, and the value "1" represents different cable labels. Whether the pair of optical fibers are in the same cable is determined by the channel label, cable label, and geographic location routing map information in the same routing resource database.
[0163] Further, in the embodiment of the present application, the first device can use the above information as the input of the neural network / machine learning model (neural network model) to train the model, and judge the accuracy of the model according to whether the cable labels are the same, and the trained model will be stored in the cloud service system. When there is a need to identify the same cable fiber pair again, the fiber comprehensive feature vector matrix can be used as the input of the trained model to output the judgment result.
[0164] Further, in the embodiment of the present application, for dynamic features, the first device can input a two-dimensional waterfall diagram of a pair of optical fiber pairs into a neural network / machine learning model (neural network model) for training, and judge the accuracy of the model according to whether they have the same groove label, and the trained model will be stored in the cloud service system. When there is a need to identify the same groove optical fiber pair again, the two-dimensional waterfall diagram is used as the input of the trained model to output the judgment result.
[0165] That is to say, in an embodiment of the present application, the first device can construct a co-routing resource database, and perform cloud-based model training and reasoning based on the optical fiber pairs / optical cable pairs in the co-routing resource database to obtain a trained neural network model, and then after receiving the detection request sent by the second device, the data carried by the detection request can be detected based on the trained neural network model, thereby obtaining the co-routing status information of the optical fiber pair to be predicted and / or the co-routing status information of the optical cable pair to be predicted.
[0166] It should be noted that, in the embodiments of the present application, Fig.11 A schematic diagram of the detection process of the cloud-coordinated artificial intelligence optical fiber co-routing system proposed in the embodiment of the present application is shown in FIG. Fig.11 As shown, the overall detection process of the cloud-coordinated artificial intelligence optical fiber co-routing system may include the following contents: the second device may perform optical fiber sensing data acquisition, and then perform data preprocessing operations; the second device may collect the original data (OTDR data) of the optical fiber pair to be predicted and / or the optical cable pair to be predicted through the OTDR unit, and the collected file is the original sor file, and then it can be further parsed into curve feature data and event feature data based on the original sor file; the original data (vibration data) of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can also be collected based on the DVS unit, and then the vibration data can be converted into plain text form of a waterfall chart, which is expressed as a two-dimensional space-time vibration amplitude data matrix (two-dimensional matrix data); for the collected original data of OTDR and DVS, the threshold method is used to filter out the bottom noise that is less than 10% (the first preset threshold) of the average amplitude value, so that the first data can be obtained, and 10% is an empirical value obtained in a test. In applications, the size of the threshold (first preset threshold) is usually adjusted according to actual conditions; then the first device can store it in a co-routing resource database, which can include channel labels, optical cable labels, geographic locations, static features, and dynamic features, etc., and then the first device can train and reason about the cloud model based on the optical fiber pairs in the co-routing resource database. For example, a comprehensive feature vector matrix can be constructed based on the static features of a pair of optical fibers / optical cables to store the comprehensive feature vectors of the optical fiber pair to be identified. The comprehensive feature vector matrix constructed by the static features of the optical fiber / optical cable can be input into the neural network model for training to obtain a prediction result, such as Figure 5As shown, in the horizontal direction, the left side is the splicing of the event characteristics and curve characteristics of a pair of optical fibers that need to be judged whether they are in the same cable, the value "0" on the right side represents the same cable label, and the value "1" represents different cable labels. Whether the pair of optical fibers that are judged to be in the same cable is obtained by the channel label, cable label, and geographic location routing map information in the same routing resource database; the first device can use the above information as the input of the neural network / machine learning model (neural network model) to train the model, and judge the accuracy of the model based on whether the cable label is the same, and the trained model will be stored in the cloud service system. When the optical fiber pair that needs to be judged to be in the same cable appears again, the optical fiber comprehensive feature vector matrix can be used as the input of the trained model to output the judgment result; for dynamic features, the first device can be trained by inputting the two-dimensional waterfall diagram of a pair of optical fiber pairs into the neural network / machine learning model (neural network model), and judge the accuracy of the model based on whether the channel label is the same. The trained model will be stored in the cloud service system. When the optical fiber pair that needs to be judged to be in the same channel appears again, the two-dimensional waterfall diagram is used as the input of the trained model to output the judgment result.
[0167] In summary, the second device can obtain the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and perform preprocessing operations on the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted to obtain the first data, and then send a detection request carrying the first data to the first device, the first device is deployed in the cloud, the first device can extract the static features and / or dynamic features of the first data, and then can construct a comprehensive feature vector matrix based on the first feature, that is, the static features of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and input the comprehensive feature vector matrix into the trained preset neural network model, so that the co-path of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can be obtained. From the status information, the dynamic characteristics (two-dimensional space-time vibration amplitude matrix) of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can also be input into the trained preset neural network model, so that the co-route status information of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can be obtained, that is, the first device in the embodiment of the present application can integrate and expand high-power consumption and high-performance algorithms, and detect the optical fiber pair to be predicted and / or the optical cable pair to be predicted through the trained preset neural network model to obtain the judgment result of whether the optical fiber pair to be predicted and / or the optical cable pair to be predicted are co-routed, and the first device is deployed in the cloud. It can be seen that the first device in the embodiment of the present application can take into account both portability and high-performance algorithm capabilities.
[0168] The embodiment of the present application provides a method for detecting the same route of optical fibers. The method is applied to a first device and a second device. The first device is deployed in the cloud. The first device receives a detection request sent by the second device. The detection request carries first data. The first data includes data preprocessed from the original data of the optical fiber pair to be predicted and / or data preprocessed from the original data of the optical cable pair to be predicted. The first feature and / or the second feature corresponding to the first data are determined. The first feature at least includes the static features of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and the second feature at least includes the dynamic features of the optical fiber pair to be predicted and / or the optical cable pair to be predicted. Based on the first feature, The method comprises the following steps: determining a prediction result of the optical fiber pair to be predicted and / or the optical cable pair to be predicted by a first model, and sending the prediction result to a second device; wherein the first model at least includes a trained preset neural network model; the prediction result includes co-routing status information of the optical fiber pair to be predicted and / or the co-routing status information of the optical cable pair to be predicted; the second device obtains second data; wherein the second data at least includes original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted; the second device performs a preprocessing operation on the second data to obtain first data corresponding to the second data; and sending a detection request to the first device; wherein the detection request carries the first data. It can be seen that after receiving the first data, the first device can first determine the first feature and / or the second feature corresponding to the first data, the first feature at least includes the static feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and the second feature at least includes the dynamic feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and then the prediction result of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can be determined based on at least one of the first feature and the second feature and the trained preset neural network model, that is, the co-routing state information of the optical fiber pair to be predicted and / or the co-routing state information of the optical cable pair to be predicted. The embodiment of the present application can detect the optical fiber pair to be predicted and / or the optical cable pair to be predicted through the trained preset neural network model, so as to accurately identify the co-routing of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, thereby improving the recognition efficiency and recognition accuracy; and the first device is deployed in the cloud, that is, the first device takes into account both portability and high-performance algorithm capabilities.
[0169] Embodiment 5
[0170] Based on the above embodiments, the present application provides a first device. Fig.12 Schematic diagram of the composition structure of the first device Figure 1 ,like Fig.12 As shown, the first device 10 includes: a first receiving unit 11, a determining unit 12, and a first sending unit 13; wherein,
[0171] The first receiving unit 11 is used to receive a detection request sent by the second device; wherein the detection request carries first data, and the first data includes pre-processed data of the original data of the optical fiber pair to be predicted, and / or pre-processed data of the original data of the optical cable pair to be predicted;
[0172] The determining unit 12 is configured to determine a first feature and / or a second feature corresponding to the first data; wherein the first feature at least includes a static feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and the second feature at least includes a dynamic feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted; and determine a prediction result of the optical fiber pair to be predicted and / or the optical cable pair to be predicted based on at least one of the first feature and the second feature and a first model;
[0173] The first sending unit 13 is used to send the prediction result to the second device; wherein the first model at least includes a trained preset neural network model; the prediction result includes the co-routing status information of the optical fiber pair to be predicted and / or the co-routing status information of the optical cable pair to be predicted.
[0174] In the embodiments of the present application, further, Fig.13 Schematic diagram of the composition structure of the first device Figure 2 ,like Fig.13 As shown, the first device 10 proposed in the embodiment of the present application may also include a first processor 14, a first memory 15 storing executable instructions of the first processor 14, and further, the first device 10 may also include a first communication interface 16, and a first bus 17 for connecting the first processor 14, the first memory 15 and the first communication interface 16.
[0175] In the embodiment of the present application, the first processor 14 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. It can be understood that for different devices, the electronic device used to implement the above-mentioned processor function can also be other, and the embodiment of the present application is not specifically limited. The first device 10 can also include a first memory 15, which can be connected to the first processor 14, wherein the first memory 15 is used to store executable program code, the program code includes computer operation instructions, and the first memory 15 may include a high-speed RAM memory, and may also include a non-volatile memory, for example, at least two disk memories.
[0176] In the embodiment of the present application, the first bus 17 is used to connect the first communication interface 16, the first processor 14 and the first memory 15, and the mutual communication between these devices.
[0177] In the embodiment of the present application, the first memory 15 is used to store instructions and data.
[0178] Further, in an embodiment of the present application, the first processor 14 is used to receive a detection request sent by a second device; wherein the detection request carries first data, and the first data includes data preprocessed from the original data of the optical fiber pair to be predicted, and / or data preprocessed from the original data of the optical cable pair to be predicted; determine a first feature and / or a second feature corresponding to the first data; wherein the first feature at least includes a static feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and the second feature at least includes a dynamic feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted; determine a prediction result of the optical fiber pair to be predicted and / or the optical cable pair to be predicted based on at least one of the first feature and the second feature and a first model, and send the prediction result to the second device; wherein the first model at least includes a trained preset neural network model; and the prediction result includes co-routing status information of the optical fiber pair to be predicted and / or co-routing status information of the optical cable pair to be predicted.
[0179] In practical applications, the first memory 15 may be a volatile memory, such as a random access memory (RAM); or a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD); or a combination of the above types of memories, and provide instructions and data to the first processor 14.
[0180] An embodiment of the present application provides a first device, which receives a detection request sent by a second device; wherein the detection request carries first data, and the first data includes data preprocessed from the original data of the optical fiber pair to be predicted, and / or data preprocessed from the original data of the optical cable pair to be predicted; determines a first feature and / or a second feature corresponding to the first data; wherein the first feature at least includes static features of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and the second feature at least includes dynamic features of the optical fiber pair to be predicted and / or the optical cable pair to be predicted; determines a prediction result of the optical fiber pair to be predicted and / or the optical cable pair to be predicted based on at least one of the first feature and the second feature and a first model, and sends the prediction result to the second device; wherein the first model at least includes a trained preset neural network model; and the prediction result includes co-routing status information of the optical fiber pair to be predicted and / or co-routing status information of the optical cable pair to be predicted. It can be seen that after receiving the first data, the first device can first determine the first feature and / or the second feature corresponding to the first data, the first feature at least includes the static feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and the second feature at least includes the dynamic feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and then the prediction result of the optical fiber pair to be predicted and / or the optical cable pair to be predicted can be determined based on at least one of the first feature and the second feature and the trained preset neural network model, that is, the co-routing state information of the optical fiber pair to be predicted and / or the co-routing state information of the optical cable pair to be predicted. The embodiment of the present application can detect the optical fiber pair to be predicted and / or the optical cable pair to be predicted through the trained preset neural network model, so as to accurately identify the co-routing of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, thereby improving the recognition efficiency and recognition accuracy; and the first device is deployed in the cloud, that is, the first device takes into account both portability and high-performance algorithm capabilities.
[0181] An embodiment of the present application provides a computer-readable storage medium having a program stored thereon, and when the program is executed by a processor, the optical fiber co-routing detection method as described above is implemented.
[0182] Specifically, the program instructions corresponding to the optical fiber co-routing detection method in this embodiment can be stored on a storage medium such as a CD, a hard disk, a USB flash drive, etc. When the program instructions corresponding to the optical fiber co-routing detection method in the storage medium are read or executed by an electronic device, the following steps are included:
[0183] Receiving a detection request sent by a second device; wherein the detection request carries first data, and the first data includes pre-processed data of original data of the optical fiber pair to be predicted, and / or pre-processed data of original data of the optical cable pair to be predicted;
[0184] Determine a first feature and / or a second feature corresponding to the first data; wherein the first feature at least includes a static feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and the second feature at least includes a dynamic feature of the optical fiber pair to be predicted and / or the optical cable pair to be predicted;
[0185] Based on at least one of the first feature and the second feature, a first model determines a prediction result of the optical fiber pair to be predicted and / or the optical cable pair to be predicted, and sends the prediction result to the second device; wherein the first model at least includes a trained preset neural network model; and the prediction result includes the co-routing status information of the optical fiber pair to be predicted and / or the co-routing status information of the optical cable pair to be predicted.
[0186] The embodiment of the present application further provides a computer program product, including a computer program, which can be executed by the first processor 14 of the first device 10 to complete the steps of any of the aforementioned methods.
[0187] In the embodiments of the present application, further, Fig.14 Schematic diagram of the structure of the second device Figure 1 ,like Fig.14 As shown, the second device 20 includes: an acquisition unit 21, an operation unit 22, a second sending unit 23, and a second receiving unit 24; wherein,
[0188] The acquisition unit 21 is used to acquire second data; wherein the second data at least includes original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted;
[0189] The operation unit 22 is used to perform a preprocessing operation on the second data to obtain first data corresponding to the second data;
[0190] The second sending unit 23 is used to send a detection request to the first device; wherein the detection request carries the first data, and the first data includes the preprocessed data of the original data of the optical fiber pair to be predicted and / or the preprocessed data of the original data of the optical cable pair to be predicted;
[0191] The second receiving unit 24 is used to receive the prediction result sent by the first device; wherein the prediction result includes the co-routing state information of the optical fiber pair to be predicted and / or the co-routing state information of the optical cable pair to be predicted.
[0192] In the embodiments of the present application, further, Fig.15 Schematic diagram of the structure of the second device Figure 2 ,like Fig.15 As shown, the second device 20 proposed in the embodiment of the present application may also include a second processor 25, a second memory 26 storing executable instructions of the second processor 25, and further, the second device 20 may also include a second communication interface 27, and a second bus 28 for connecting the second processor 25, the second memory 26 and the second communication interface 27.
[0193] In the embodiment of the present application, the above-mentioned second processor 25 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. It can be understood that for different devices, the electronic device used to implement the above-mentioned processor function can also be other, and the embodiment of the present application is not specifically limited. The second device 20 can also include a second memory 26, which can be connected to the second processor 25, wherein the second memory 26 is used to store executable program code, the program code includes computer operation instructions, and the second memory 26 may include a high-speed RAM memory, and may also include a non-volatile memory, for example, at least two disk memories.
[0194] In the embodiment of the present application, the second bus 28 is used to connect the second communication interface 27, the second processor 25 and the second memory 26, and the mutual communication between these devices.
[0195] In the embodiment of the present application, the second memory 26 is used to store instructions and data.
[0196] Further, in an embodiment of the present application, the above-mentioned second processor 25 is used to obtain second data; wherein, the second data at least includes the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted; preprocessing operation is performed on the second data to obtain first data corresponding to the second data; a detection request is sent to the first device; wherein the detection request carries the first data, and the first data includes the preprocessed data of the original data of the optical fiber pair to be predicted and / or the preprocessed data of the original data of the optical cable pair to be predicted; and a prediction result sent by the first device is received; wherein the prediction result includes the co-routing status information of the optical fiber pair to be predicted and / or the co-routing status information of the optical cable pair to be predicted.
[0197] In practical applications, the second memory 26 may be a volatile memory, such as a random access memory (RAM); or a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or a combination of the above types of memories, and provide instructions and data to the second processor 25.
[0198] The embodiment of the present application provides a second device, the second device acquires second data; wherein the second data at least includes the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted; performs a preprocessing operation on the second data to obtain the first data corresponding to the second data; sends a detection request to the first device; wherein the detection request carries the first data, and the first data includes the data after the original data of the optical fiber pair to be predicted and / or the data after the original data of the optical cable pair to be predicted is preprocessed; receives the prediction result sent by the first device; wherein the prediction result includes the co-routing state information of the optical fiber pair to be predicted and / or the co-routing state information of the optical cable pair to be predicted. It can be seen that the second device can first acquire the second data, i.e., the original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted; and performs a preprocessing operation on the second data to obtain the first data corresponding to the second data, and then can send the detection request carrying the first data to the first device for detection. Since the data carried in the detection request sent by the second device is the preprocessed data, the subsequent detection accuracy of the first data by the first device can be improved, thereby improving the co-routing recognition accuracy of the optical fiber pair to be predicted and / or the optical cable pair to be predicted.
[0199] An embodiment of the present application provides a computer-readable storage medium having a program stored thereon, and when the program is executed by a processor, the optical fiber co-routing detection method as described above is implemented.
[0200] Specifically, the program instructions corresponding to the optical fiber co-routing detection method in this embodiment can be stored on a storage medium such as a CD, a hard disk, a USB flash drive, etc. When the program instructions corresponding to the optical fiber co-routing detection method in the storage medium are read or executed by an electronic device, the following steps are included:
[0201] Acquire second data; wherein the second data at least includes original data of the optical fiber pair to be predicted and / or the optical cable pair to be predicted;
[0202] Performing a preprocessing operation on the second data to obtain first data corresponding to the second data;
[0203] Sending a detection request to a first device; wherein the detection request carries the first data, and the first data includes the preprocessed data of the original data of the optical fiber pair to be predicted and / or the preprocessed data of the original data of the optical cable pair to be predicted;
[0204] Receive the prediction result sent by the first device; wherein the prediction result includes the co-routing state information of the optical fiber pair to be predicted and / or the co-routing state information of the optical cable pair to be predicted.
[0205] The embodiment of the present application also provides a computer program product, including a computer program, which can be executed by the second processor 25 of the second device 20 to complete the steps of any of the aforementioned methods.
[0206] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of hardware embodiments, software embodiments, or embodiments in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.
[0207] The present application is described with reference to implementation flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0208] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which is implemented in the implementation flow diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0209] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing the steps in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0210] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application.
Claims
1. A method for detecting the same route of optical fiber, characterized in that: The method is applied to a first device, where the first device is deployed in the cloud, and the method includes: Receiving a detection request sent by a second device; wherein the detection request carries first data, and the first data includes target data of the optical fiber pair to be predicted; Determine a first feature and / or a second feature corresponding to the first data; wherein the first feature at least includes a static feature of the optical fiber pair to be predicted, and the second feature at least includes a dynamic feature of the optical fiber pair to be predicted; Based on at least one of the first feature and the second feature, a first model determines a prediction result of the optical fiber pair to be predicted, and sends the prediction result to the second device; wherein the first model at least includes a trained preset neural network model; and the prediction result includes the co-routing status information of the optical fiber pair to be predicted.
2. The method according to claim 1, characterized in that The determining a first feature corresponding to the first data includes: Determine a curve feature corresponding to the first data, and determine a static event feature corresponding to the first data; wherein the static event feature is used to characterize quality information of the optical fiber pair to be predicted; The static feature is generated based on the curve feature and the static event feature.
3. The method according to claim 2, characterized in that The determining of the curve feature corresponding to the first data includes: Acquire a first curve corresponding to the first data; wherein the first curve includes a one-dimensional sequence signal corresponding to the first data; Determine a first sequence feature corresponding to the first curve based on the first curve and the second model; wherein the second model at least includes a long short-term memory network LSTM model; The curve feature is determined based on the first sequence feature and a fully connected layer.
4. The method according to claim 1, characterized in that: The determining the second feature corresponding to the first data includes: Acquire dynamic parameter information corresponding to the first data; wherein the dynamic parameter information includes one or more of the occurrence time of the dynamic event signal, the occurrence location of the dynamic event signal, and the intensity information of the dynamic event signal; The second feature is determined based on the dynamic parameter information.
5. A method for detecting the same route of optical fiber, characterized in that: The method is applied to a second device, and the method includes: Acquire second data; wherein the second data at least includes original data of the optical fiber pair to be predicted; Performing a preprocessing operation on the second data to obtain first data corresponding to the second data; Sending a detection request to a first device; wherein the detection request carries the first data, the first data includes target data of the optical fiber pair to be predicted, and the target data is data obtained by preprocessing the original data of the optical fiber pair to be predicted; Receive the prediction result sent by the first device; wherein the prediction result includes the co-routing state information of the optical fiber pair to be predicted.
6. The method according to claim 5, characterized in that The obtaining the second data of the optical fiber pair to be predicted comprises: Acquire third data of the optical fiber pair to be predicted; wherein the third data includes original data of the optical fiber pair to be predicted collected by an optical time domain reflectometer OTDR unit; Acquire fourth data of the optical fiber pair to be predicted; wherein the fourth data includes raw data of the optical fiber pair to be predicted collected by a distributed optical fiber vibration sensor DVS unit; The second data is determined based on the third data and the fourth data.
7. The method according to claim 6, characterized in that The determining the second data based on the third data and the fourth data comprises: Analyze and process the third data to obtain fifth data; wherein the fifth data at least includes curve characteristic data and event characteristic data; Performing conversion processing on the fourth data to obtain sixth data; wherein the sixth data at least includes two-dimensional matrix data corresponding to the fourth data, and the two-dimensional matrix data is used to characterize parameter information of a dynamic event signal; The second data is determined based on the fifth data and the sixth data.
8. The method according to claim 7, characterized in that The preprocessing operation on the second data to obtain the first data corresponding to the second data includes: The fifth data is filtered based on the first preset threshold and the average amplitude value to obtain the seventh data, and the sixth data is filtered based on the first preset threshold and the average amplitude value to obtain the eighth data; wherein the average amplitude value at least includes the average amplitude value of the historical data; The first data is determined based on the seventh data and the eighth data.
9. A first device, characterized in that: The first device includes: a first receiving unit, a determining unit, and a first sending unit; wherein, The first receiving unit is configured to receive a detection request sent by the second device; wherein the detection request carries first data, the first data includes target data of the optical fiber pair to be predicted, and the target data is data obtained by preprocessing the original data of the optical fiber pair to be predicted; The determining unit is configured to determine a first feature and / or a second feature corresponding to the first data; wherein the first feature at least includes a static feature of the optical fiber pair to be predicted, and the second feature at least includes a dynamic feature of the optical fiber pair to be predicted; and determine a prediction result of the optical fiber pair to be predicted based on at least one of the first feature and the second feature and a first model; The first sending unit is used to send the prediction result to the second device; wherein the first model at least includes a trained preset neural network model; and the prediction result includes the co-routing status information of the optical fiber pair to be predicted.
10. A first device, characterized in that: The first device comprises: a first processor and a first memory; wherein, The first memory is used to store a computer program that can be run on the processor; The first processor is configured to execute the method according to any one of claims 1 to 4 when running the computer program.
11. A second device, characterized in that: The second device includes: an acquisition unit, an operation unit, a second sending unit, and a second receiving unit; wherein, The acquisition unit is used to acquire second data; wherein the second data at least includes original data of the optical fiber pair to be predicted; The operation unit is used to perform a preprocessing operation on the second data to obtain first data corresponding to the second data; The second sending unit is used to send a detection request to the first device; wherein the detection request carries the first data, the first data includes target data of the optical fiber pair to be predicted, and the target data is data obtained by preprocessing the original data of the optical fiber pair to be predicted; The second receiving unit is used to receive the prediction result sent by the first device; wherein the prediction result includes the co-routing state information of the optical fiber pair to be predicted.
12. A second device, characterized in that: The second device comprises: a second processor and a second memory; wherein, The second memory is used to store a computer program that can be run on the processor; The second processor is configured to execute the method according to any one of claims 5 to 8 when running the computer program.
13. A computer-readable storage medium, characterized in that: The storage medium stores computer program codes, which, when executed by a computer, execute the method described in any one of claims 1 to 4 or 5 to 8.
14. A computer program product comprising a computer program, characterized in that The computer program implements the method according to any one of claims 1-4 or 5-8 when executed by a processor.
Citation Information
Cited By
Network detection method, system, device and equipment and storage medium
CN119766325A
Method and system for artificial intelligence analysis of same route of transmission system
CN120614279A
