CN116684769A

CN116684769A - Digital twin data acquisition method and system based on optical communication scene

Info

Publication number: CN116684769A
Application number: CN202310890553.8A
Authority: CN
Inventors: 李勇; 汤峻峰
Original assignee: Shenzhen Tianxinlang Technology Co ltd
Current assignee: Shenzhen Tianxinlang Technology Co ltd
Priority date: 2023-07-20
Filing date: 2023-07-20
Publication date: 2023-09-01
Anticipated expiration: 2043-07-20
Also published as: CN116684769B

Abstract

The application discloses a digital twin data acquisition method and system based on an optical communication scene. Wherein the method comprises the following steps: constructing a physical model of an optical communication system, wherein the physical model comprises a light source, an optical fiber, an optical amplifier and a light detector; constructing a data model of the optical communication system; mapping the physical model and the data model by utilizing a digital twin technology to construct a data twin model of the optical network system; transmitting optical communication data generated by a physical model of the optical communication system to the data twinning model by using a sensor system and a data transmission system; and carrying out data analysis on the optical communication data through the data twin model to obtain a data analysis result. In this way, fault diagnosis of the optical network system can be achieved.

Description

Digital twin data acquisition method and system based on optical communication scene

Technical Field

The application relates to the field of data acquisition, in particular to a digital twin data acquisition method and system based on an optical communication scene.

Background

Digital twinning refers to synchronously updating a digital model of a physical entity and a real-world counterpart thereof, thereby realizing the whole life cycle management and optimization of the physical entity. Optical communication is a communication mode for transmitting information based on optical technology, and uses optical fibers as transmission media to convert information into optical signals for transmission. Compared with the traditional telecommunication technology, the optical communication has the advantages of higher transmission rate, larger bandwidth, lower loss, longer transmission distance and the like.

During deployment of an optical network, the optical network needs to be complex commissioned to provide fault diagnosis and optimization comments. And the introduction of the data twinning technology provides new technical support and solution ideas for the optical network debugging.

Disclosure of Invention

The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides a digital twin data acquisition method and system based on an optical communication scene. Wherein the method comprises the following steps: constructing a physical model of an optical communication system, wherein the physical model comprises a light source, an optical fiber, an optical amplifier and a light detector; constructing a data model of the optical communication system; mapping the physical model and the data model by utilizing a digital twin technology to construct a data twin model of the optical network system; transmitting optical communication data generated by a physical model of the optical communication system to the data twinning model by using a sensor system and a data transmission system; and carrying out data analysis on the optical communication data through the data twin model to obtain a data analysis result. In this way, fault diagnosis of the optical network system can be achieved.

According to a first aspect of the present application, there is provided a method for obtaining digital twin data in an optical communication scenario, comprising:

constructing a physical model of an optical communication system, wherein the physical model comprises a light source, an optical fiber, an optical amplifier and a light detector;

constructing a data model of the optical communication system;

mapping the physical model and the data model by utilizing a digital twin technology to construct a data twin model of the optical network system;

transmitting optical communication data generated by a physical model of the optical communication system to the data twinning model by using a sensor system and a data transmission system; the method comprises the steps of,

and carrying out data analysis on the optical communication data through the data twin model to obtain a data analysis result.

In the above method for obtaining digital twin data based on an optical communication scenario, the optical communication data is the power and the signal-to-noise ratio of optical signals of an optical network system at a plurality of predetermined time points within a predetermined time period;

the data analysis is performed on the optical communication data through the data twin model to obtain a data analysis result, which comprises the following steps:

the power and the signal-to-noise ratio of the optical signals of the optical network system at a plurality of preset time points are respectively arranged into an optical signal power time sequence input vector and an optical signal-to-noise ratio time sequence input vector according to the time dimension;

The optical signal power time sequence input vector and the optical signal to noise ratio time sequence input vector pass through a time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain an optical signal power time sequence feature vector and an optical signal to noise ratio time sequence feature vector;

fusing the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector through a cascading function to obtain a classification feature vector; the method comprises the steps of,

and the classification feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the optical network system has faults or not.

In the above method for obtaining digital twin data in an optical communication scenario, the step of passing the optical signal power timing sequence input vector and the optical signal to noise ratio timing sequence input vector through a timing sequence feature extractor based on a one-dimensional convolutional neural network model to obtain an optical signal power timing sequence feature vector and an optical signal to noise ratio timing sequence feature vector includes:

inputting the optical signal power time sequence input vector into the time sequence feature extractor based on the one-dimensional convolutional neural network model to obtain the optical signal power time sequence feature vector; the method comprises the steps of,

and inputting the optical signal-to-noise ratio time sequence input vector into the time sequence feature extractor based on the one-dimensional convolutional neural network model to obtain the optical signal-to-noise ratio time sequence feature vector.

In the above method for obtaining digital twin data in an optical communication scenario, inputting the optical signal power timing sequence input vector into the one-dimensional convolutional neural network model-based timing sequence feature extractor to obtain the optical signal power timing sequence feature vector includes:

using each layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model, respectively carrying out forward transfer on input data of the layers:

carrying out convolution processing on input data to obtain a first convolution feature vector;

pooling the first convolution feature vector to obtain a first pooled feature vector; the method comprises the steps of,

non-linear activation is carried out on the first pooled feature vector to obtain a first activated feature vector;

the output of the last layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model is the time sequence feature vector of the optical signal power, and the input of the first layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model is the time sequence input vector of the optical signal power.

In the above method for obtaining digital twin data in an optical communication scenario, inputting the optical signal-to-noise ratio time sequence input vector into the time sequence feature extractor based on the one-dimensional convolutional neural network model to obtain the optical signal-to-noise ratio time sequence feature vector includes:

Each layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model is used for respectively carrying out input data in forward transfer of the layer:

performing convolution processing on the input data to obtain a second convolution feature vector;

pooling the second convolution feature vector to obtain a second pooled feature vector; the method comprises the steps of,

non-linearly activating the second pooled feature vector to obtain a second activated feature vector;

the output of the last layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model is the time sequence feature vector of the signal to noise ratio of the optical signal, and the input of the first layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model is the time sequence input vector of the signal to noise ratio of the optical signal.

In the above method for obtaining digital twin data in an optical communication scenario, the step of fusing the optical signal power timing sequence feature vector and the optical signal-to-noise ratio timing sequence feature vector by a cascading function to obtain a classification feature vector includes:

fusing the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector through a cascading function according to the following cascading formula to obtain the classification feature vector;

Wherein, the cascade formula is:

；

wherein ,representing the power timing characteristic vector of the optical signal, < >>Time sequence characteristic vector representing the signal to noise ratio of the optical signal, < >> and />Are column vectors, +.>For the optical signal power timing feature vector and the optical signalDistance matrix between signal-to-noise ratio time sequence feature vectors, < >>Transposed vector representing vector, "> and />All represent point convolution operations, ">To activate the function +.>Representing a splicing operation->Representing vector multiplication>Representing the classification feature vector.

In the above method for obtaining digital twin data in an optical communication scenario, the classifying feature vector is passed through a classifier to obtain a classifying result, where the classifying result is used to indicate whether a fault exists in an optical network system, and the method includes:

performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; the method comprises the steps of,

and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

According to a second aspect of the present application, there is provided a digital twin data acquisition system in an optical communication scenario, comprising:

The system comprises a physical model construction module, a physical model analysis module and a physical model analysis module, wherein the physical model construction module is used for constructing a physical model of an optical communication system, and the physical model comprises a light source, an optical fiber, an optical amplifier and a light detector;

a data model component module for constructing a data model of the optical communication system;

the mapping module is used for mapping the physical model and the data model by utilizing a digital twin technology so as to construct a data twin model of the optical network system;

the transmission module is used for transmitting optical communication data generated by the physical model of the optical communication system to the data twin model by utilizing a sensor system and a data transmission system; the method comprises the steps of,

and the data analysis module is used for carrying out data analysis on the optical communication data through the data twin model so as to obtain a data analysis result.

In the above-mentioned digital twin data acquisition system based on the optical communication scene, the optical communication data is the power and the signal-to-noise ratio of the optical signal of the optical network system at a plurality of predetermined time points within a predetermined time period;

wherein, the data analysis module includes:

the vector arrangement unit is used for respectively arranging the power and the signal-to-noise ratio of the optical signals of the optical network system at a plurality of preset time points into an optical signal power time sequence input vector and an optical signal-to-noise ratio time sequence input vector according to the time dimension;

The time sequence feature extraction unit is used for enabling the optical signal power time sequence input vector and the optical signal to noise ratio time sequence input vector to pass through a time sequence feature extractor based on a one-dimensional convolutional neural network model so as to obtain an optical signal power time sequence feature vector and an optical signal to noise ratio time sequence feature vector;

the fusion unit is used for fusing the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector through a cascading function to obtain a classification feature vector; the method comprises the steps of,

and the classification unit is used for passing the classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the optical network system has faults or not.

In the above-mentioned digital twin data acquisition system based on an optical communication scenario, the timing sequence feature extraction unit is configured to:

According to a third aspect of the present application, there is provided an electronic device comprising: a processor; and a memory having stored therein computer program instructions that, when executed by the processor, cause the processor to perform the method of the first aspect.

According to a fourth aspect of the present application there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the method according to the first aspect.

Compared with the prior art, the method and the system for acquiring the digital twin data based on the optical communication scene provided by the application comprise the following steps: constructing a physical model of an optical communication system, wherein the physical model comprises a light source, an optical fiber, an optical amplifier and a light detector; constructing a data model of the optical communication system; mapping the physical model and the data model by utilizing a digital twin technology to construct a data twin model of the optical network system; transmitting optical communication data generated by a physical model of the optical communication system to the data twinning model by using a sensor system and a data transmission system; and carrying out data analysis on the optical communication data through the data twin model to obtain a data analysis result. The data analysis result is used for indicating whether the optical network system has faults, so that fault diagnosis of the optical network system can be realized.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art. The following drawings are not intended to be drawn to scale, emphasis instead being placed upon illustrating the principles of the application.

Fig. 1 is a flowchart of a method for obtaining digital twin data in an optical communication scenario according to an embodiment of the present application.

Fig. 2 is an application scenario diagram of substep S150 of a digital twin data acquisition method in an optical communication scenario according to an embodiment of the present application.

Fig. 3 is a flowchart of sub-step S150 of the digital twin based data acquisition method in an optical communication scenario according to an embodiment of the present application.

Fig. 4 is a schematic diagram of a sub-step S150 of a digital twin data acquisition method in an optical communication scenario according to an embodiment of the present application.

Fig. 5 is a flowchart of substep S152 of the digital twin based data acquisition method in an optical communication scenario according to an embodiment of the present application.

Fig. 6 is a flowchart of substep S154 of the digital twin based data acquisition method in an optical communication scenario according to an embodiment of the present application.

Fig. 7 is a block diagram of a digital twinning-based data acquisition system in an optical communication scenario according to an embodiment of the present application.

Fig. 8 is a block diagram of the data analysis module in the digital twin data acquisition system in an optical communication scenario according to an embodiment of the present application.

Fig. 9 is a block diagram of an electronic device according to an embodiment of the application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are also within the scope of the application.

As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.

A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.

Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.

Based on this, in the technical solution of the present application, a data twinning technique is introduced into an optical network communication system, that is, a data twinning model of the optical network communication system is constructed, and fault diagnosis is performed on the optical network system through the optical network system obtained by the data twinning model of the optical network communication system.

Specifically, a physical model of an optical communication system is first constructed, wherein the physical model includes a light source, an optical fiber, an optical amplifier, and a light detector. A data model of the optical communication system is then constructed. The physical model and the data model are then mapped using digital twinning techniques to construct a data twinning model of the optical network system. Further, optical communication data generated by the physical model of the optical communication system is transmitted to the data twinning model by using a sensor system and a data transmission system. And then, carrying out data analysis on the optical communication data through the data twin model to obtain a data analysis result.

Accordingly, as shown in fig. 1, the method for obtaining data based on digital twin in an optical communication scene includes: s110, constructing a physical model of an optical communication system, wherein the physical model comprises a light source, an optical fiber, an optical amplifier and a light detector; s120, constructing a data model of the optical communication system; s130, mapping the physical model and the data model by utilizing a digital twin technology to construct a data twin model of the optical network system; s140, transmitting optical communication data generated by a physical model of the optical communication system to the data twinning model by using a sensor system and a data transmission system; and S150, carrying out data analysis on the optical communication data through the data twin model to obtain a data analysis result.

Specifically, in one specific example of the present application, the optical communication data is power and signal-to-noise ratio of an optical signal of an optical network system at a plurality of predetermined time points within a predetermined time period. Correspondingly, the process of carrying out data analysis on the optical communication data through the data twin model to obtain a data analysis result comprises the following steps.

Firstly, the power and the signal-to-noise ratio of the optical signals of the optical network system at a plurality of preset time points are respectively arranged into an optical signal power time sequence input vector and an optical signal-to-noise ratio time sequence input vector according to the time dimension. That is, the power and the signal-to-noise ratio of the optical signal of the optical network system are data structured along a time dimension to obtain the optical signal power timing input vector and the optical signal-to-noise ratio timing input vector.

And then, the optical signal power time sequence input vector and the optical signal to noise ratio time sequence input vector are passed through a time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain an optical signal power time sequence feature vector and an optical signal to noise ratio time sequence feature vector. That is, in the technical scheme of the application, the time sequence feature extractor of the one-dimensional convolutional neural network model is used for carrying out one-dimensional convolutional coding on the optical signal power time sequence input vector and the optical signal to noise ratio time sequence input vector so as to capture the local time sequence correlation mode feature of the optical signal power and the local time sequence correlation mode feature of the optical signal to noise ratio. It should be understood that, in the technical solution of the present application, the optical signal power timing characteristic vector and the optical signal-to-noise ratio timing characteristic vector are respectively used to reflect the fluctuation characteristic of the power of the optical signal in the timing direction and the waveform characteristic of the signal-to-noise ratio of the optical signal in the timing direction.

And then, fusing the optical signal power time sequence characteristic vector and the optical signal to noise ratio time sequence characteristic vector to obtain a classification characteristic vector. In particular, in the technical scheme of the application, considering that the power of the optical signal and the signal-to-noise ratio of the optical signal are two state indexes for reflecting the optical signal at the same time, the optical signal power time sequence characteristic vector and the optical signal-to-noise ratio time sequence characteristic vector have implicit correlation at a logic level. Based on the above, in the technical scheme of the application, the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector are fused through a cascading function to obtain a classification feature vector. In particular, the cascading function has a certain logic reasoning capability, and the correlation information between the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector is mined, so that the network can be promoted to extract additional implicit correlation features from the feature distribution of the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector, and the precision of the feature expression of the classification feature vector is improved in this way.

And then, the classification feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the optical network system has faults or not. That is, the classifier is used to determine a class probability tag to which the classification feature vector belongs, where the class probability tag is used to indicate whether there is a fault in the optical network system. In this way, a data twinning technique is introduced into an optical network communication system, that is, a data twinning model of the optical network communication system is constructed, and fault diagnosis is performed on the optical network system through the optical network system acquired by the data twinning model of the optical network communication system.

In the technical scheme of the application, the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector respectively express the time sequence associated distribution feature of the power of the optical signal and the time sequence associated distribution feature of the signal to noise ratio of the optical signal, so that the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector respectively have the segment type local associated feature distribution feature of the time sequence distribution dimension. Therefore, when the classification feature vector is obtained by fusing the optical signal power timing feature vector and the optical signal to noise ratio timing feature vector by using a cascading function, the fusion is expected to be performed based on local segment feature distribution characteristics of the optical signal power timing feature vector and the optical signal to noise ratio timing feature vector, so as to improve the fusion effect of the classification feature vector on the optical signal power timing feature vector and the optical signal to noise ratio timing feature vector.

The applicant of the present application therefore bases on a cascading function, for example, on the optical signal power timing eigenvector, e.g., denoted asAnd the optical signal-to-noise ratio timing feature vector, e.g., denoted +.>Performing a piecewise enrichment fusion of the local sequence semantics to obtain said classification feature vector, e.g. denoted +. >The method is specifically expressed as follows:

；

wherein , and />All represent point convolution operations, ">To activate the function +.>Representing a splicing operation->For the optical signal power timing feature vector +.>And the optical signal-to-noise ratio timing feature vectorDistance matrix between, i.e.)>，/>Is->And->Distance between-> and />Are column vectors.

Here, the partial sequence semantic segment enrichment fuses the coding effect of the sequence-based segment feature distribution on the directional semantics in the predetermined distribution direction of the sequence to embed the similarity between the sequence segments as a re-weighting factor for the inter-sequence correlation, thereby capturing the similarity between sequences based on the feature representation (feature appearance) at each segment level, realizing the optical signal power timing feature vectorAnd the optical signal-to-noise ratio timing feature vector +.>Is enriched in the local fragment level semantics of (2) thereby promoting the classification feature vector +.>The fusion expression effect of the classification feature vector improves the accuracy of the classification result obtained by the classifier.

Fig. 2 is an application scenario diagram of substep S150 of a digital twin data acquisition method in an optical communication scenario according to an embodiment of the present application. As shown in fig. 2, in this application scenario, first, optical communication data (for example, D illustrated in fig. 2) generated by a physical model of the optical communication system, the optical communication data being power and signal-to-noise ratio of an optical signal of the optical network system at a plurality of predetermined time points within a predetermined period of time, is acquired, and then the optical communication data is input to a server (for example, S illustrated in fig. 2) that is deployed with a digital twin-based data acquisition algorithm in the optical communication scenario, wherein the server is capable of processing the optical communication data using the digital twin-based data acquisition algorithm in the optical communication scenario to obtain a classification result for indicating whether or not there is a fault in the optical network system.

Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.

Fig. 3 is a flowchart of sub-step S150 of the digital twin based data acquisition method in an optical communication scenario according to an embodiment of the present application. As shown in fig. 3, according to the method for obtaining digital twin data in an optical communication scenario, the optical communication data is the power and the signal-to-noise ratio of optical signals of an optical network system at a plurality of predetermined time points in a predetermined time period; the data analysis is performed on the optical communication data through the data twin model to obtain a data analysis result, which comprises the following steps: s151, arranging the power and the signal-to-noise ratio of the optical signals of the optical network system at a plurality of preset time points into an optical signal power time sequence input vector and an optical signal-to-noise ratio time sequence input vector according to the time dimension respectively; s152, the optical signal power time sequence input vector and the optical signal to noise ratio time sequence input vector are processed through a time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain an optical signal power time sequence feature vector and an optical signal to noise ratio time sequence feature vector; s153, fusing the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector through a cascading function to obtain a classification feature vector; and S154, the classification feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the optical network system has faults or not.

Fig. 4 is a schematic diagram of a sub-step S150 of a digital twin data acquisition method in an optical communication scenario according to an embodiment of the present application. As shown in fig. 4, in the network architecture, first, the power and the signal-to-noise ratio of the optical signals of the optical network system at the plurality of predetermined time points are respectively arranged into an optical signal power timing input vector and an optical signal-to-noise ratio timing input vector according to a time dimension; then, the optical signal power time sequence input vector and the optical signal to noise ratio time sequence input vector are passed through a time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain an optical signal power time sequence feature vector and an optical signal to noise ratio time sequence feature vector; then, fusing the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector through a cascading function to obtain a classification feature vector; and finally, the classification feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the optical network system has faults or not.

More specifically, in step S151, the power and the signal-to-noise ratio of the optical signals of the optical network system at the plurality of predetermined time points are respectively arranged into an optical signal power timing input vector and an optical signal-to-noise ratio timing input vector according to a time dimension. That is, the power and the signal-to-noise ratio of the optical signal of the optical network system are data structured along a time dimension to obtain the optical signal power timing input vector and the optical signal-to-noise ratio timing input vector.

More specifically, in step S152, the optical signal power timing input vector and the optical signal to noise ratio timing input vector are passed through a timing feature extractor based on a one-dimensional convolutional neural network model to obtain an optical signal power timing feature vector and an optical signal to noise ratio timing feature vector. The optical signal power time sequence characteristic vector and the optical signal to noise ratio time sequence characteristic vector are respectively used for reflecting fluctuation characteristics of the power of the optical signal in the time sequence direction and waveform characteristics of the signal to noise ratio of the optical signal in the time sequence direction.

It should be appreciated that convolutional neural network (Convolutional Neural Network, CNN) is an artificial neural network and has wide application in the fields of image recognition and the like. The convolutional neural network may include an input layer, a hidden layer, and an output layer, where the hidden layer may include a convolutional layer, a pooling layer, an activation layer, a full connection layer, etc., where the previous layer performs a corresponding operation according to input data, outputs an operation result to the next layer, and obtains a final result after the input initial data is subjected to a multi-layer operation.

Accordingly, in one specific example, as shown in fig. 5, passing the optical signal power timing input vector and the optical signal to noise ratio timing input vector through a timing feature extractor based on a one-dimensional convolutional neural network model to obtain an optical signal power timing feature vector and an optical signal to noise ratio timing feature vector, including: s1521, inputting the optical signal power time sequence input vector into the time sequence feature extractor based on the one-dimensional convolutional neural network model to obtain the optical signal power time sequence feature vector; and S1522, inputting the optical signal to noise ratio time sequence input vector into the time sequence feature extractor based on the one-dimensional convolutional neural network model to obtain the optical signal to noise ratio time sequence feature vector.

Accordingly, in one specific example, inputting the optical signal power timing input vector into the one-dimensional convolutional neural network model-based timing feature extractor to obtain the optical signal power timing feature vector, comprising: using each layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model, respectively carrying out forward transfer on input data of the layers: carrying out convolution processing on input data to obtain a first convolution feature vector; pooling the first convolution feature vector to obtain a first pooled feature vector; performing nonlinear activation on the first pooled feature vector to obtain a first activated feature vector; the output of the last layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model is the time sequence feature vector of the optical signal power, and the input of the first layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model is the time sequence input vector of the optical signal power.

Accordingly, in one specific example, inputting the optical signal to noise ratio timing input vector into the one-dimensional convolutional neural network model-based timing feature extractor to obtain the optical signal to noise ratio timing feature vector, including: using each layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model, respectively carrying out forward transfer on input data of the layers: performing convolution processing on the input data to obtain a second convolution feature vector; pooling the second convolution feature vector to obtain a second pooled feature vector; and performing nonlinear activation on the second pooled feature vector to obtain a second activated feature vector; the output of the last layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model is the time sequence feature vector of the signal to noise ratio of the optical signal, and the input of the first layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model is the time sequence input vector of the signal to noise ratio of the optical signal.

More specifically, in step S153, the optical signal power timing feature vector and the optical signal-to-noise ratio timing feature vector are fused by a cascading function to obtain a classification feature vector. In particular, in the technical scheme of the application, considering that the power of the optical signal and the signal-to-noise ratio of the optical signal are two state indexes for reflecting the optical signal at the same time, the optical signal power time sequence characteristic vector and the optical signal-to-noise ratio time sequence characteristic vector have implicit correlation at a logic level. Based on the above, in the technical scheme of the application, the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector are fused through a cascading function to obtain a classification feature vector.

It should be appreciated that the cascading function has a certain logic reasoning capability, and the correlation information between the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector is mined, which can promote the network to extract additional implicit correlation features from the feature distribution of the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector, and in this way, the feature expression accuracy of the classification feature vector is improved.

Accordingly, in one specific example, fusing the optical signal power timing feature vector and the optical signal-to-noise ratio timing feature vector by a cascading function to obtain a classification feature vector includes: fusing the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector through a cascading function according to the following cascading formula to obtain the classification feature vector; wherein, the cascade formula is:

；

wherein ,representing the power timing characteristic vector of the optical signal, < >>Time sequence characteristic vector representing the signal to noise ratio of the optical signal, < >> and />Are column vectors, +.>For the distance matrix between the optical signal power time sequence characteristic vector and the optical signal to noise ratio time sequence characteristic vector,/for the optical signal power time sequence characteristic vector>Transposed vector representing vector, "> and />All represent point convolution operations, ">To activate the function +.>Representing a splicing operation->Representing vector multiplication>Representing the classification feature vector.

The method comprises the steps that the local sequence semantics are subjected to segmented enrichment fusion, the sequence-based segment feature distribution is used for encoding directional semantics in the preset distribution direction of the sequence, similarity embedding among sequence segments is used as a re-weighting factor for inter-sequence association, so that similarity between sequences at each segment level based on feature appearance is captured, the enrichment fusion of the optical signal power time sequence feature vector and the local segment level semantics of the optical signal to noise ratio time sequence feature vector is realized, the fusion expression effect of the classification feature vector is improved, and the accuracy of classification results obtained by the classification feature vector through a classifier is improved.

More specifically, in step S154, the classification feature vector is passed through a classifier to obtain a classification result, which is used to indicate whether or not there is a failure in the optical network system. In this way, a data twinning technique is introduced into an optical network communication system, that is, a data twinning model of the optical network communication system is constructed, and fault diagnosis is performed on the optical network system through the optical network system acquired by the data twinning model of the optical network communication system.

That is, in the technical solution of the present application, the labels of the classifier include that there is a fault (first label) of the optical network system and that there is no fault (second label) of the optical network system, where the classifier determines to which classification label the classification feature vector belongs through a soft maximum function. It should be noted that the first tag p1 and the second tag p2 do not include a manually set concept, and in fact, during the training process, the computer model does not have a concept of "whether the optical network system has a fault", which is only two kinds of classification tags, and the probability that the output feature is under the two classification tags, that is, the sum of p1 and p2 is one. Therefore, the classification result of whether the optical network system has a fault is actually converted into a class probability distribution conforming to the two classes of the natural law through classifying the labels, and the physical meaning of the natural probability distribution of the labels is essentially used instead of the language text meaning of whether the optical network system has a fault.

It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.

Accordingly, in one specific example, as shown in fig. 6, the classification feature vector is passed through a classifier to obtain a classification result, where the classification result is used to indicate whether the optical network system has a fault, and the method includes: s1541, performing full-connection coding on the classification feature vector by using a full-connection layer of the classifier to obtain a coded classification feature vector; and S1542, inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

In summary, according to the method for acquiring digital twin data in an optical communication scenario according to the embodiment of the present application, firstly, the power and the signal-to-noise ratio of the optical signals of the optical network system at the plurality of predetermined time points are respectively arranged into an optical signal power timing input vector and an optical signal-to-noise ratio timing input vector according to a time dimension, then, the optical signal power timing input vector and the optical signal-to-noise ratio timing input vector are passed through a timing feature extractor based on a one-dimensional convolutional neural network model to obtain an optical signal power timing feature vector and an optical signal-to-noise ratio timing feature vector, then, the optical signal power timing feature vector and the optical signal-to-noise ratio timing feature vector are fused through a cascading function to obtain a classification feature vector, and finally, the classification feature vector is passed through a classifier to obtain a classification result for indicating whether a fault exists in the optical network system.

Fig. 7 is a block diagram of a digital twinning-based data acquisition system 100 in an optical communication scenario in accordance with an embodiment of the present application. As shown in fig. 7, a digital twin data acquisition system 100 in an optical communication scenario according to an embodiment of the present application includes: a physical model construction module 110 for constructing a physical model of an optical communication system, wherein the physical model includes a light source, an optical fiber, an optical amplifier, and a light detector; a data model component module 120 for constructing a data model of the optical communication system; a mapping module 130, configured to map the physical model and the data model by using a digital twin technique to construct a data twin model of the optical network system; a transmission module 140, configured to transmit optical communication data generated by the physical model of the optical communication system to the data twinning model by using a sensor system and a data transmission system; and a data analysis module 150, configured to perform data analysis on the optical communication data through the data twinning model to obtain a data analysis result.

In one example, in the above-mentioned digital twin data acquisition system 100 based on the optical communication scenario, the optical communication data is the power and the signal-to-noise ratio of the optical signal of the optical network system at a plurality of predetermined time points within a predetermined time period; as shown in fig. 8, the data analysis module 150 includes: a vector arrangement unit 151, configured to arrange the power and the signal-to-noise ratio of the optical signals of the optical network system at the plurality of predetermined time points into an optical signal power timing input vector and an optical signal-to-noise ratio timing input vector according to a time dimension, respectively; a time sequence feature extraction unit 152, configured to pass the optical signal power time sequence input vector and the optical signal to noise ratio time sequence input vector through a time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain an optical signal power time sequence feature vector and an optical signal to noise ratio time sequence feature vector; a fusion unit 153, configured to fuse the optical signal power timing feature vector and the optical signal-to-noise ratio timing feature vector by a cascading function to obtain a classification feature vector; and a classification unit 154, configured to pass the classification feature vector through a classifier to obtain a classification result, where the classification result is used to indicate whether the optical network system has a fault.

In one example, in the above-mentioned digital twin data acquisition system 100 based on the optical communication scenario, the timing feature extraction unit 152 is configured to: inputting the optical signal power time sequence input vector into the time sequence feature extractor based on the one-dimensional convolutional neural network model to obtain the optical signal power time sequence feature vector; and inputting the optical signal-to-noise ratio time sequence input vector into the time sequence feature extractor based on the one-dimensional convolutional neural network model to obtain the optical signal-to-noise ratio time sequence feature vector.

In one example, in the above-mentioned digital twin data acquisition system 100 based on an optical communication scenario, inputting the optical signal power timing input vector into the one-dimensional convolutional neural network model-based timing feature extractor to obtain the optical signal power timing feature vector includes: using each layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model, respectively carrying out forward transfer on input data of the layers: carrying out convolution processing on input data to obtain a first convolution feature vector; pooling the first convolution feature vector to obtain a first pooled feature vector; performing nonlinear activation on the first pooled feature vector to obtain a first activated feature vector; the output of the last layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model is the time sequence feature vector of the optical signal power, and the input of the first layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model is the time sequence input vector of the optical signal power.

In one example, in the above-mentioned digital twin data acquisition system 100 based on an optical communication scenario, inputting the optical signal to noise ratio timing input vector into the one-dimensional convolutional neural network model-based timing feature extractor to obtain the optical signal to noise ratio timing feature vector includes: using each layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model, respectively carrying out forward transfer on input data of the layers: performing convolution processing on the input data to obtain a second convolution feature vector; pooling the second convolution feature vector to obtain a second pooled feature vector; and performing nonlinear activation on the second pooled feature vector to obtain a second activated feature vector; the output of the last layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model is the time sequence feature vector of the signal to noise ratio of the optical signal, and the input of the first layer of the time sequence feature extractor based on the one-dimensional convolutional neural network model is the time sequence input vector of the signal to noise ratio of the optical signal.

In one example, in the above-mentioned digital twin data acquisition system 100 based on the optical communication scenario, the fusion unit 153 is configured to: fusing the optical signal power time sequence feature vector and the optical signal to noise ratio time sequence feature vector through a cascading function according to the following cascading formula to obtain the classification feature vector; wherein, the cascade formula is:

；

wherein ,representing the power timing characteristic vector of the optical signal, < >>Time sequence characteristic vector representing the signal to noise ratio of the optical signal, < >> and />Are column vectors, +.>For the distance matrix between the optical signal power time sequence characteristic vector and the optical signal to noise ratio time sequence characteristic vector,/for the optical signal power time sequence characteristic vector>Transposition of a representation vectorVector (S)> and />All represent point convolution operations, ">To activate the function +.>Representing a splicing operation->Representing vector multiplication>Representing the classification feature vector.

In one example, in the above-mentioned digital twin data acquisition system 100 based on the optical communication scenario, the classifying unit 154 is configured to: performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

Here, it will be understood by those skilled in the art that the specific functions and operations of the respective modules in the above-described digital twin-based data acquisition system 100 in the optical communication scenario have been described in detail in the above description of the digital twin-based data acquisition method in the optical communication scenario with reference to fig. 1 to 6, and thus, repetitive descriptions thereof will be omitted.

As described above, the digital twin based data acquisition system 100 in an optical communication scenario according to an embodiment of the present application may be implemented in various wireless terminals, such as a server or the like having a digital twin based data acquisition algorithm in an optical communication scenario. In one example, the digital twinning based data acquisition system 100 in an optical communication scenario according to embodiments of the present application may be integrated into a wireless terminal as a software module and/or hardware module. For example, the digital twinned data acquisition system 100 in an optical communication scenario may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the digital twinning-based data acquisition system 100 in the optical communication scenario may also be one of many hardware modules of the wireless terminal.

Alternatively, in another example, the digital twinning-based data acquisition system 100 in an optical communication scenario may be a separate device from the wireless terminal, and the digital twinning-based data acquisition system 100 in an optical communication scenario may be connected to the wireless terminal through a wired and/or wireless network and transmit interactive information in accordance with a agreed data format.

Exemplary electronic device

Next, an electronic device according to an embodiment of the present application is described with reference to fig. 9.

Fig. 9 illustrates a block diagram of an electronic device according to an embodiment of the application.

As shown in fig. 9, the electronic device 10 includes one or more processors 11 and a memory 12.

The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer readable storage medium that can be executed by the processor 11 to perform the functions in the library book management method of the various embodiments of the present application described above and/or other desired functions. Various contents such as cascade feature vectors may also be stored in the computer-readable storage medium.

In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown).

The input means 13 may comprise, for example, a keyboard, a mouse, etc.

The output device 14 may output various information including the classification result and the like to the outside. The output means 14 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.

Of course, only some of the components of the electronic device 10 that are relevant to the present application are shown in fig. 9 for simplicity, components such as buses, input/output interfaces, etc. are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.

According to another aspect of the present application there is also provided a non-volatile computer readable storage medium having stored thereon computer readable instructions which when executed by a computer can perform a method as described above.

Program portions of the technology may be considered to be "products" or "articles of manufacture" in the form of executable code and/or associated data, embodied or carried out by a computer readable medium. A tangible, persistent storage medium may include any memory or storage used by a computer, processor, or similar device or related module. Such as various semiconductor memories, tape drives, disk drives, or the like, capable of providing storage functionality for software.

All or a portion of the software may sometimes communicate over a network, such as the internet or other communication network. Such communication may load software from one computer device or processor to another. For example: a hardware platform loaded from a server or host computer of the video object detection device to a computer environment, or other computer environment implementing the system, or similar functioning system related to providing information needed for object detection. Thus, another medium capable of carrying software elements may also be used as a physical connection between local devices, such as optical, electrical, electromagnetic, etc., propagating through cable, optical cable, air, etc. Physical media used for carrier waves, such as electrical, wireless, or optical, may also be considered to be software-bearing media. Unless limited to a tangible "storage" medium, other terms used herein to refer to a computer or machine "readable medium" mean any medium that participates in the execution of any instructions by a processor.

The application uses specific words to describe embodiments of the application. Reference to "a first/second embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the application may be combined as suitable.

Furthermore, those skilled in the art will appreciate that the various aspects of the application are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

The foregoing is illustrative of the present invention and is not to be construed as limiting thereof. Although a few exemplary embodiments of this invention have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this invention. Accordingly, all such modifications are intended to be included within the scope of this invention as defined in the following claims. It is to be understood that the foregoing is illustrative of the present invention and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The invention is defined by the claims and their equivalents.

Claims

1. The digital twin data acquisition method based on the optical communication scene is characterized by comprising the following steps:

constructing a data model of the optical communication system;

transmitting optical communication data generated by a physical model of the optical communication system to the data twinning model by using a sensor system and a data transmission system; and

And carrying out data analysis on the optical communication data through the data twin model to obtain a data analysis result, wherein the analysis result is used for indicating whether the optical network system has faults or not.

2. The method for obtaining data based on digital twinning in an optical communication scenario according to claim 1, wherein the optical communication data is power and signal-to-noise ratio of optical signals of an optical network system at a plurality of predetermined time points within a predetermined time period;

3. The method for obtaining data based on digital twinning in an optical communication scenario according to claim 2, wherein the step of passing the optical signal power timing input vector and the optical signal to noise ratio timing input vector through a timing feature extractor based on a one-dimensional convolutional neural network model to obtain an optical signal power timing feature vector and an optical signal to noise ratio timing feature vector comprises:

4. The method for obtaining digital twin data in an optical communication scenario according to claim 3, wherein inputting the optical signal power timing input vector into the one-dimensional convolutional neural network model-based timing feature extractor to obtain the optical signal power timing feature vector comprises:

5. The method for obtaining digital twin data in an optical communication scenario according to claim 4, wherein inputting the optical signal-to-noise ratio timing input vector into the one-dimensional convolutional neural network model-based timing feature extractor to obtain the optical signal-to-noise ratio timing feature vector comprises:

6. The method for obtaining data based on digital twinning in an optical communication scenario according to claim 5, wherein the merging the optical signal power timing eigenvector and the optical signal-to-noise ratio timing eigenvector by a cascading function to obtain a classification eigenvector comprises:

wherein, the cascade formula is:

；

wherein ,representing the power timing characteristic vector of the optical signal, < > >Time sequence characteristic vector representing the signal to noise ratio of the optical signal, < >> and />Are column vectors, +.>For the distance matrix between the optical signal power time sequence characteristic vector and the optical signal to noise ratio time sequence characteristic vector,/for the optical signal power time sequence characteristic vector>Transposed vector representing vector, "> and />All represent point convolution operations, ">To activate the function +.>Representing a splicing operation->Representing vector multiplication>Representing the classification feature vector.

7. The method for obtaining data based on digital twinning in an optical communication scenario according to claim 6, wherein the classifying feature vector is passed through a classifier to obtain a classification result, where the classification result is used to indicate whether there is a fault in an optical network system, and the method includes:

8. A digital twinning-based data acquisition system in an optical communication scenario, comprising:

9. The system for obtaining data based on digital twinning in an optical communication scenario according to claim 8, wherein the optical communication data is power and signal-to-noise ratio of optical signals of an optical network system at a plurality of predetermined time points within a predetermined time period;

wherein, the data analysis module includes:

10. The system for obtaining data based on digital twinning in an optical communication scenario according to claim 9, wherein the timing feature extraction unit is configured to:

11. An electronic device, comprising: a processor; and a memory having stored therein computer program instructions that, when executed by the processor, cause the processor to perform the method of any of claims 1 to 7.

12. A computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the method of any of claims 1 to 7.