Optical path multiplexing method, device and equipment using intelligent monitoring

Abstract

The invention relates to an optical path multiplexing method, device and equipment using intelligent monitoring. According to the method, spreading code parameters are input into a trained optical signal-to-noise ratio grading prediction model to obtain a predicted optical signal-to-noise ratio grade, then a corresponding optical signal-to-noise ratio prediction model is selected as a target prediction model according to the predicted optical signal-to-noise ratio grade, and a predicted optical signal-to-noise ratio is obtained through prediction by using the target prediction model according to optical signal parameters. The optical signal-to-noise ratio prediction model can use a lighter model architecture, so that the delay of obtaining the predicted optical signal-to-noise ratio through reasoning is lower, and the timeliness of intelligent monitoring is improved.

Description

Technical Field

[0001] The present invention is applicable to the field of intelligent monitoring, and in particular relates to an optical path multiplexing method, device and equipment using intelligent monitoring. Background Art

[0002] With the rapid development of information technology, data traffic has exploded, and people's requirements for communication bandwidth and transmission efficiency are increasing. As a key means to increase the capacity of optical fiber communication systems and make full use of optical fiber spectrum resources, optical path multiplexing technology has gone through several development stages and is widely used in modern communication network architecture.

[0003] Traditional optical path multiplexing methods mainly include wavelength division multiplexing (WDM), time division multiplexing (TDM) and code division multiplexing (CDM). Among them, code division multiplexing uses unique spread spectrum codes to distinguish the signals of each user, so that they can share the same frequency band and time period, and uses the good autocorrelation and low cross-correlation characteristics of spread spectrum codes to ensure communication, which can highlight its advantages in mobile communications and some optical communication scenarios.

[0004] In the complex and ever-changing actual communication environment, optical signals are subject to interference and degradation from a variety of factors. In order to ensure the reliability and stability of signal transmission, it is necessary to obtain optical signal parameters through real-time intelligent monitoring, analyze the optical signal parameters, and obtain evaluation indicators for optical signal transmission. A common evaluation indicator is the optical signal-to-noise ratio. Monitoring and controlling the optical signal-to-noise ratio can assist in evaluating the health of the system. When the optical signal-to-noise ratio drops abnormally, it may be a signal that there are potential problems in the system, which requires timely maintenance and repair.

[0005] In the prior art, there are methods that use artificial intelligence models to predict the collected optical signal parameters to obtain the predicted optical signal-to-noise ratio. However, intelligent monitoring of optical networks needs to meet real-time requirements. In actual operation, it is necessary to quickly collect, process and output monitoring results for optical signals. However, complex artificial intelligence models will produce high latency, resulting in the inability to provide monitoring results in a timely manner. For example, when sudden signal interference or failure occurs in the optical network, if it is not detected and measures are not taken in time, it may cause serious communication interruption.

[0006] Therefore, how to improve the timeliness of intelligent monitoring has become an urgent problem to be solved. Summary of the invention

[0007] In view of this, embodiments of the present invention provide an optical path multiplexing method, device and apparatus using intelligent monitoring to solve the problem.

[0008] In a first aspect, a method for optical path multiplexing using intelligent monitoring is provided, the method comprising: At a target time point, using a preset monitoring device to obtain optical signal parameters and spread spectrum code parameters of a target optical fiber, wherein the target optical fiber uses code division multiplexing for communication; Inputting the spreading code parameters into a trained optical signal to noise ratio classification prediction model to obtain a predicted optical signal to noise ratio level; Determine, from M trained optical signal-to-noise ratio prediction models, an optical signal-to-noise ratio prediction model corresponding to the predicted optical signal-to-noise ratio level as a target prediction model, where M is an integer greater than zero; The optical signal parameters are input into the target prediction model to obtain a predicted optical signal-to-noise ratio corresponding to the target time point, and the predicted optical signal-to-noise ratio is used to assist in adjusting the optical transmitting end, optical amplifier and optical output end corresponding to the target optical fiber.

[0009] In a second aspect, an optical path multiplexing device using intelligent monitoring is provided, the device comprising: A parameter acquisition module, used to acquire optical signal parameters and spread spectrum code parameters of a target optical fiber using a preset monitoring device at a target time point, wherein the target optical fiber uses code division multiplexing for communication; A level prediction module, used for inputting the spreading code parameters into a trained optical signal to noise ratio classification prediction model to obtain a predicted optical signal to noise ratio level; A model determination module, used to determine the optical signal-to-noise ratio prediction model corresponding to the predicted optical signal-to-noise ratio level as a target prediction model from M trained optical signal-to-noise ratio prediction models, where M is an integer greater than zero; The optical signal-to-noise ratio prediction module is used to input the optical signal parameters into the target prediction model to obtain the predicted optical signal-to-noise ratio corresponding to the target time point, and the predicted optical signal-to-noise ratio is used to assist in adjusting the optical transmitting end, optical amplifier and optical output end corresponding to the target optical fiber.

[0010] In a third aspect, an embodiment of the present invention provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the optical path multiplexing method as described in the first aspect when executing the computer program.

[0011] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the optical path multiplexing method as described in the first aspect is implemented.

[0012] Compared with the prior art, the present invention has the following beneficial effects: By inputting the spread spectrum code parameters into the trained optical signal-to-noise ratio hierarchical prediction model, the predicted optical signal-to-noise ratio level is obtained, and then the corresponding optical signal-to-noise ratio prediction model is selected as the target prediction model according to the predicted optical signal-to-noise ratio level. The target prediction model is used to predict the optical signal-to-noise ratio according to the optical signal parameters. The optical signal-to-noise ratio prediction model can use a lighter model architecture, thereby making the delay of inferring the predicted optical signal-to-noise ratio lower, thereby improving the timeliness of intelligent monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0014] Figure 1 This is a schematic diagram of an application environment of an optical path multiplexing method using intelligent monitoring provided by Embodiment 1 of the present invention; Figure 2 It is a flowchart of an optical path multiplexing method using intelligent monitoring provided in the first embodiment of the present invention; Figure 3 is a structural schematic diagram of an optical path multiplexing device using intelligent monitoring provided in Embodiment 2 of the present invention; Figure 4 It is a structural schematic diagram of a computer device using an optical path multiplexing method using intelligent monitoring provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0015] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0016] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0017] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0018] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]", depending on the context.

[0019] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0020] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0021] It should be understood that the order of execution of the steps in the following embodiments does not imply a precedence of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0022] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0023] The optical path multiplexing method using intelligent monitoring provided in the first embodiment of the present invention can be applied in the following aspects: Figure 1 In the application environment, the server communicates with the client. The client includes but is not limited to PDA, desktop computer, notebook computer, ultra-mobile personal computer (UMPC), netbook, cloud terminal device, personal digital assistant (PDA) and other terminal devices. The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0024] See also Figure 2, is a flow chart of an optical path multiplexing method using intelligent monitoring provided in the first embodiment of the present invention. The optical path multiplexing method can be applied to Figure 1 The server in the example receives the optical signal parameters and spread spectrum code parameters of the target optical fiber collected by each preset monitoring device at the target time point. The server deploys a trained optical signal-to-noise ratio classification prediction model and M trained optical signal-to-noise ratio prediction models. The server predicts the predicted optical signal-to-noise ratio corresponding to the target time point and sends the predicted optical signal-to-noise ratio to the client to assist the client in optimizing and adjusting the optical transmitter, optical amplifier, and optical output end corresponding to the target optical fiber. Figure 2 As shown, the optical path multiplexing method may include the following steps: Step S201: obtaining optical signal parameters and spread spectrum code parameters of a target optical fiber using a preset monitoring device at a target time point.

[0025] Among them, the target optical fiber uses code division multiplexing for communication, and the target time point may refer to the current time point that needs to be intelligently monitored. In this embodiment, intelligent monitoring may refer to intelligently monitoring the optical signal-to-noise ratio based on the optical signal parameters and spread spectrum code parameters acquired in real time. Code division multiplexing (CDM) is a communication technology that allows multiple users to communicate at the same time and in the same frequency band. The core of code division multiplexing is to use different spread spectrum codes to distinguish signals of different users. Each user's signal is modulated by a unique spread spectrum code. The spread spectrum code usually has good autocorrelation and low cross-correlation.

[0026] Optionally, the acquired optical signal parameters include at least: optical signal intensity and spectrum.

[0027] Among them, the optical signal strength can be determined by measuring the optical signal power in the target optical fiber. The preset monitoring device used to collect the optical signal power can be an optical power meter, and the preset monitoring device used to collect the spectrum can be a spectrum analyzer, an optical spectrometer, etc.

[0028] Specifically, in one embodiment, the optical signal parameters may also include various parameters that affect the transmission of the optical signal, such as the temperature and humidity of the environment in which the target optical fiber is located.

[0029] Optionally, the spread spectrum code parameters include at least: a bit error rate, an autocorrelation peak value, and a cross-correlation peak value.

[0030] Among them, the preset monitoring equipment used for collecting the bit error rate can be a bit error rate tester, an oscilloscope, etc., and the preset monitoring equipment used for collecting the autocorrelation peak and the cross-correlation peak can be a correlator, a vector signal analyzer, etc.

[0031] The above steps of using preset monitoring equipment to obtain the optical signal parameters and spread spectrum code parameters of the target optical fiber at the target time point, and the target optical fiber using code division multiplexing for communication, can provide a data basis for subsequent optical signal to noise ratio grading prediction and optical signal to noise ratio prediction, and ensure the accuracy of the prediction.

[0032] Step S202: input the spreading code parameters into the trained optical signal to noise ratio classification prediction model to obtain the predicted optical signal to noise ratio level.

[0033] Among them, the trained optical signal to noise ratio classification prediction model can be used to predict the optical signal to noise ratio level according to the spread spectrum code parameters. The optical signal to noise ratio level can refer to dividing the optical signal to noise ratio into multiple levels using fuzzy classification ideas, and different optical signal to noise ratio levels correspond to different optical signal to noise ratio value intervals.

[0034] The above step of inputting the spread spectrum code parameters into the trained optical signal to noise ratio hierarchical prediction model to obtain the predicted optical signal to noise ratio level facilitates the subsequent determination of a suitable optical signal to noise ratio prediction model according to the predicted optical signal to noise ratio level, and then performs optical signal to noise ratio prediction, thereby improving the accuracy and timeliness of optical signal to noise ratio prediction.

[0035] Step S203: Determine, from the M trained optical signal to noise ratio prediction models, an optical signal to noise ratio prediction model corresponding to the predicted optical signal to noise ratio level as a target prediction model.

[0036] Wherein, M is an integer greater than zero, the optical signal to noise ratio prediction model may be used to predict the optical signal to noise ratio according to the optical signal parameters, and the target prediction model may refer to the optical signal to noise ratio prediction model ultimately used to predict the optical signal to noise ratio.

[0037] Optionally, the optical path multiplexing method further includes: Obtaining N historical signal parameters and their corresponding historical spreading code parameters and historical optical signal-to-noise ratios, where N is an integer greater than zero; Perform clustering processing according to all historical optical signal-to-noise ratios to obtain K cluster sets and their corresponding cluster centers, where K is an integer greater than zero; According to the numerical sorting of cluster centers, the corresponding basic optical signal-to-noise ratio levels are assigned to the K cluster sets respectively; For any cluster set, all historical optical signal-to-noise ratios in the cluster set are traversed, the historical optical signal-to-noise ratios are used as first label data, and the historical optical signal parameters corresponding to the historical optical signal-to-noise ratios are used as first sample data corresponding to the first label data, to obtain a plurality of groups of first sample data and first label data having a corresponding relationship; According to each group of first sample data and first label data, a preset optical signal to noise ratio prediction model is trained to obtain a trained optical signal to noise ratio prediction model, and the trained optical signal to noise ratio prediction model corresponds to a basic optical signal to noise ratio level of the cluster set.

[0038] Among them, the historical signal parameter may refer to the historically collected optical signal parameter, which corresponds to the historical spread spectrum code parameter and the historical optical signal-to-noise ratio. Since the historical optical signal-to-noise ratio is a numerical value, the clustering process is equivalent to forming a cluster set with historical optical signal-to-noise ratios with similar numerical values. The cluster set contains several historical optical signal-to-noise ratios, and the cluster center may refer to the mean of each historical optical signal-to-noise ratio in the corresponding cluster set.

[0039] Specifically, the clustering method may adopt the DBSCAN clustering algorithm, which does not need to specify the number of cluster sets and is more suitable for complex optical signal-to-noise ratio prediction scenarios.

[0040] According to the numerical sorting of the cluster centers, the K cluster sets are respectively assigned corresponding basic optical signal-to-noise ratio levels, which may mean that the basic optical signal-to-noise ratio levels are assigned to the corresponding cluster sets in the order of the numerical values ​​of the cluster centers from small to large. The basic optical signal-to-noise ratio level may be an integer in the range of [1, K]. The basic optical signal-to-noise ratio level assigned to the cluster center with the smallest numerical value is 1, and the basic optical signal-to-noise ratio level assigned to the cluster center with the largest numerical value is K.

[0041] For any cluster set, all historical optical signal-to-noise ratios in the cluster set are traversed, and each historical optical signal-to-noise ratio is used as the first label data. Each first label data corresponds to a historical optical signal parameter as the first sample data corresponding to the first label data, so that several groups of first sample data and first label data with corresponding relationships can be obtained.

[0042] According to each group of first sample data and first label data, the preset optical signal-to-noise ratio prediction model is trained to obtain a trained optical signal-to-noise ratio prediction model, which corresponds to the cluster set and further corresponds to the basic optical signal-to-noise ratio level of the cluster set. It can be known that each cluster set has a corresponding trained optical signal-to-noise ratio prediction model.

[0043] In this embodiment, multiple corresponding optical signal to noise ratio prediction models are trained according to multiple cluster sets. Compared with the prior art method of using a single optical signal to noise ratio prediction model to predict all optical signal parameters, although the versatility of the optical signal to noise ratio prediction model is reduced, the input of the optical signal to noise ratio prediction model is more concentrated, making the training process of the optical signal to noise ratio prediction model easier to fit, and the number of model layers and parameters required for the optical signal to noise ratio prediction model are correspondingly reduced, thereby improving the inference speed of the trained optical signal to noise ratio prediction model in real-time prediction, thereby improving the timeliness of intelligent monitoring.

[0044] Optionally, the optical path multiplexing method further includes: For any cluster set, traverse all historical optical signal-to-noise ratios in the cluster set, use historical spread spectrum code parameters corresponding to the historical optical signal-to-noise ratio as second sample data, use the basic optical signal-to-noise ratio level of the cluster set as second label data, and form a plurality of sample label pairs from the second label data and each second sample data; Traverse all cluster sets to obtain all sample label pairs; According to all sample label pairs, the optical signal-to-noise ratio classification prediction model is trained to obtain a trained optical signal-to-noise ratio classification prediction model.

[0045] For any cluster set, the second label data and each second sample data form a sample label pair corresponding to each second sample data.

[0046] Specifically, the optical signal-to-noise ratio grading prediction model is a classification model. Compared with the regression model to which the optical signal-to-noise ratio prediction model belongs, the classification model has a smaller model architecture and is less difficult to train.

[0047] Therefore, this embodiment uses the optical signal to noise ratio classification prediction model to first predict the optical signal to noise ratio level, and then selects the corresponding optical signal to noise ratio prediction model for prediction. It can reduce the complexity of the optical signal to noise ratio prediction related model as much as possible without affecting the accuracy of the optical signal to noise ratio prediction, thereby improving the reasoning speed of the optical signal to noise ratio prediction, that is, improving the timeliness of intelligent monitoring.

[0048] Optionally, a preset optical signal to noise ratio prediction model is trained according to each group of first sample data and first label data to obtain a trained optical signal to noise ratio prediction model, wherein the trained optical signal to noise ratio prediction model corresponds to a basic optical signal to noise ratio level of the cluster set, including: Inputting the first sample data into a preset optical signal-to-noise ratio prediction model to obtain first prediction data; Calculate a first training loss according to the first prediction data, the first label data corresponding to the first sample data, and the first loss function; The parameters of the preset optical signal to noise ratio prediction model are trained according to the first training loss until the first training loss converges, thereby obtaining a trained optical signal to noise ratio prediction model.

[0049] Among them, the first loss function can adopt the mean square error loss function.

[0050] Specifically, according to the first training loss, the parameters of the preset optical signal to noise ratio prediction model are trained using the gradient descent method until the first training loss converges to obtain a trained optical signal to noise ratio prediction model.

[0051] Optionally, the optical signal-to-noise ratio classification prediction model is trained according to all sample label pairs to obtain a trained optical signal-to-noise ratio classification prediction model, including: Inputting the second sample data into a preset optical signal-to-noise ratio hierarchical prediction model to obtain second prediction data; Calculate a second training loss according to the second prediction data, the second label data corresponding to the second sample data, and the second loss function; The optical signal to noise ratio classification prediction model is trained according to the second training loss until the second training loss converges, thereby obtaining a trained optical signal to noise ratio classification prediction model.

[0052] Among them, the second loss function can adopt the cross entropy loss function.

[0053] Specifically, according to the second training loss, the parameters of the optical signal to noise ratio classification prediction model are trained using the gradient descent method until the second training loss converges, thereby obtaining a trained optical signal to noise ratio classification prediction model.

[0054] Step S204: input the optical signal parameters into the target prediction model to obtain the predicted optical signal-to-noise ratio corresponding to the target time point.

[0055] The predicted optical signal-to-noise ratio is used to assist in adjusting the optical transmitting end, optical amplifier and optical output end corresponding to the target optical fiber.

[0056] Specifically, the optimization and adjustment of the optical transmitting end corresponding to the target optical fiber may include optimizing the light source power, selecting a suitable modulation format, etc., the optimization and adjustment of the optical amplifier may include gain adjustment, noise suppression, etc., and the optimization and adjustment of the optical output end may include coherent reception, filtering and signal processing, etc.

[0057] In this embodiment, the spread spectrum code parameters are input into the trained optical signal-to-noise ratio hierarchical prediction model to obtain the predicted optical signal-to-noise ratio level, and then the corresponding optical signal-to-noise ratio prediction model is selected as the target prediction model according to the predicted optical signal-to-noise ratio level. The target prediction model is used to predict the optical signal parameters to obtain the predicted optical signal-to-noise ratio. The optical signal-to-noise ratio prediction model can use a lighter model architecture, thereby reducing the delay in inferring the predicted optical signal-to-noise ratio, thereby improving the timeliness of intelligent monitoring.

[0058] Corresponding to the method of the above embodiment, Figure 3The schematic diagram of the structure of an optical path multiplexing device using intelligent monitoring provided by the second embodiment of the present invention is shown. The optical path multiplexing device is applied to the server. The server receives the optical signal parameters and spread spectrum code parameters of the target optical fiber collected by each preset monitoring device at the target time point. The server is deployed with a trained optical signal-to-noise ratio classification prediction model and M trained optical signal-to-noise ratio prediction models. The server predicts the predicted optical signal-to-noise ratio corresponding to the target time point and sends the predicted optical signal-to-noise ratio to the client to assist the client in optimizing and adjusting the optical transmitting end, optical amplifier and optical output end corresponding to the target optical fiber. For ease of description, only the part related to the embodiment of the present invention is shown.

[0059] See also Figure 3 , the optical path multiplexing device comprises: A parameter acquisition module 31 is used to acquire optical signal parameters and spread spectrum code parameters of a target optical fiber using a preset monitoring device at a target time point, and the target optical fiber uses code division multiplexing for communication; The level prediction module 32 is used to input the spread spectrum code parameters into the trained optical signal to noise ratio classification prediction model to obtain the predicted optical signal to noise ratio level; A model determination module 33 is used to determine the optical signal-to-noise ratio prediction model corresponding to the predicted optical signal-to-noise ratio level as a target prediction model from M trained optical signal-to-noise ratio prediction models, where M is an integer greater than zero; The optical signal-to-noise ratio prediction module 34 is used to input the optical signal parameters into the target prediction model to obtain the predicted optical signal-to-noise ratio corresponding to the target time point. The predicted optical signal-to-noise ratio is used to assist in adjusting the optical transmitting end, optical amplifier and optical output end corresponding to the target optical fiber.

[0060] Optionally, the optical path multiplexing device further includes: A historical parameter acquisition module, used to acquire N historical signal parameters and their corresponding historical spread spectrum code parameters and historical optical signal-to-noise ratios, where N is an integer greater than zero; A clustering module is used to perform clustering processing according to all historical optical signal-to-noise ratios to obtain K cluster sets and their corresponding cluster centers, where K is an integer greater than zero; A level allocation module is used to allocate corresponding basic optical signal-to-noise ratio levels to the K cluster sets according to the numerical sorting of the cluster centers; A first sample construction module is used to traverse all historical optical signal-to-noise ratios in any cluster set, use the historical optical signal-to-noise ratio as the first label data, use the historical optical signal parameters corresponding to the historical optical signal-to-noise ratio as the first sample data corresponding to the first label data, and obtain a plurality of groups of first sample data and first label data having a corresponding relationship; The first training module is used to train a preset optical signal to noise ratio prediction model according to each group of first sample data and first label data to obtain a trained optical signal to noise ratio prediction model, wherein the trained optical signal to noise ratio prediction model corresponds to a basic optical signal to noise ratio level of the cluster set.

[0061] Optionally, the optical path multiplexing device further includes: A second sample construction module is used for traversing all historical optical signal-to-noise ratios in any cluster set, taking historical spread spectrum code parameters corresponding to the historical optical signal-to-noise ratios as second sample data, taking the basic optical signal-to-noise ratio level of the cluster set as second label data, and forming a plurality of sample label pairs from the second label data and each second sample data; The traversal module is used to traverse all cluster sets and obtain all sample label pairs; The second training module is used to train the optical signal-to-noise ratio classification prediction model according to all sample label pairs to obtain a trained optical signal-to-noise ratio classification prediction model.

[0062] Optionally, the first training module includes: A first prediction unit, configured to input the first sample data into a preset optical signal-to-noise ratio prediction model to obtain first prediction data; A first loss unit, used to calculate a first training loss according to the first prediction data, the first label data corresponding to the first sample data, and a first loss function; The first training unit is used to train the parameters of the preset optical signal to noise ratio prediction model according to the first training loss until the first training loss converges to obtain the trained optical signal to noise ratio prediction model.

[0063] Optionally, the second training module includes: A second prediction unit, used for inputting the second sample data into a preset optical signal-to-noise ratio hierarchical prediction model to obtain second prediction data; A second loss unit, used to calculate a second training loss according to the second prediction data, the second label data corresponding to the second sample data, and the second loss function; The second training unit is used to train the optical signal to noise ratio classification prediction model according to the second training loss until the second training loss converges to obtain a trained optical signal to noise ratio classification prediction model.

[0064] Optionally, in the parameter acquisition module 31, the optical signal parameters acquired include at least: optical signal intensity and spectrum.

[0065] Optionally, in the parameter acquisition module 31, the spread spectrum code parameters at least include: bit error rate, autocorrelation peak value and cross-correlation peak value.

[0066] It should be noted that the information interaction, execution process and other contents between the above-mentioned modules and units are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0067] Figure 4 This is a schematic diagram of the structure of a computer device using an optical path multiplexing method using intelligent monitoring provided by the third embodiment of the present invention. Figure 4 As shown, the computer device of this embodiment includes: at least one processor ( Figure 4 Only one is shown in the figure), a memory, and a computer program stored in the memory and executable on at least one processor, wherein when the processor executes the computer program, the steps in any of the above-mentioned embodiments of the optical path multiplexing method using intelligent monitoring are implemented.

[0068] The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that Figure 4 This is merely an example of a computer device and does not constitute a limitation on the computer device. The computer device may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. For example, it may also include a network interface, a display screen, and an input device.

[0069] The processor may be a CPU, or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0070] The memory includes a readable storage medium, an internal memory, etc., wherein the internal memory may be the memory of a computer device, and the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be a hard disk of a computer device, and in other embodiments, it may also be an external storage device of the computer device, for example, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device. Further, the memory may also include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of a computer program, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0071] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the above-mentioned method embodiment, which will not be repeated here. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0072] The present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by a computer program product. When the computer program product runs on a computer device, the computer device can implement the steps in the above-mentioned method embodiment when executing.

[0073] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0074] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0075] In the embodiments provided by the present invention, it should be understood that the disclosed devices / computer equipment and methods can be implemented in other ways. For example, the device / computer equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0076] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0077] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for multiplexing optical paths using intelligent monitoring, characterized in that: The method comprises: At a target time point, using a preset monitoring device to obtain optical signal parameters and spread spectrum code parameters of a target optical fiber, wherein the target optical fiber uses code division multiplexing for communication; Inputting the spreading code parameters into a trained optical signal to noise ratio classification prediction model to obtain a predicted optical signal to noise ratio level; Determine, from M trained optical signal-to-noise ratio prediction models, an optical signal-to-noise ratio prediction model corresponding to the predicted optical signal-to-noise ratio level as a target prediction model, where M is an integer greater than zero; The optical signal parameters are input into the target prediction model to obtain a predicted optical signal-to-noise ratio corresponding to the target time point, and the predicted optical signal-to-noise ratio is used to assist in adjusting the optical transmitting end, optical amplifier and optical output end corresponding to the target optical fiber.

2. The optical path multiplexing method according to claim 1, characterized in that: The method further comprises: Obtaining N historical signal parameters and their corresponding historical spreading code parameters and historical optical signal-to-noise ratios, where N is an integer greater than zero; Perform clustering processing according to all historical optical signal-to-noise ratios to obtain K cluster sets and their corresponding cluster centers, where K is an integer greater than zero; According to the numerical sorting of cluster centers, the corresponding basic optical signal-to-noise ratio levels are assigned to the K cluster sets respectively; For any cluster set, traverse all historical optical signal-to-noise ratios in the cluster set, use the historical optical signal-to-noise ratio as the first label data, use the historical optical signal parameter corresponding to the historical optical signal-to-noise ratio as the first sample data corresponding to the first label data, and obtain several groups of first sample data and first label data having a corresponding relationship; According to each group of first sample data and first label data, a preset optical signal to noise ratio prediction model is trained to obtain a trained optical signal to noise ratio prediction model, and the trained optical signal to noise ratio prediction model corresponds to a basic optical signal to noise ratio level of the cluster set.

3. The optical path multiplexing method according to claim 2, characterized in that: The method further comprises: For any cluster set, traverse all historical optical signal-to-noise ratios in the cluster set, use the historical spread spectrum code parameters corresponding to the historical optical signal-to-noise ratio as the second sample data, use the basic optical signal-to-noise ratio level of the cluster set as the second label data, and form a plurality of sample label pairs from the second label data and each second sample data; Traverse all cluster sets to obtain all sample label pairs; The optical signal-to-noise ratio classification prediction model is trained according to all sample label pairs to obtain the trained optical signal-to-noise ratio classification prediction model.

4. The optical path multiplexing method according to claim 2, characterized in that: The step of training a preset optical signal to noise ratio prediction model according to each group of first sample data and first label data to obtain a trained optical signal to noise ratio prediction model, wherein the trained optical signal to noise ratio prediction model corresponds to a basic optical signal to noise ratio level of the cluster set, comprises: Inputting the first sample data into the preset optical signal-to-noise ratio prediction model to obtain first prediction data; Calculate a first training loss according to the first prediction data, first label data corresponding to the first sample data, and a first loss function; The parameters of the preset optical signal to noise ratio prediction model are trained according to the first training loss until the first training loss converges, thereby obtaining the trained optical signal to noise ratio prediction model.

5. The optical path multiplexing method according to claim 3, characterized in that: The step of training the optical signal-to-noise ratio classification prediction model according to all sample label pairs to obtain the trained optical signal-to-noise ratio classification prediction model comprises: Inputting the second sample data into the preset optical signal-to-noise ratio hierarchical prediction model to obtain second prediction data; Calculate a second training loss according to the second predicted data, second label data corresponding to the second sample data, and a second loss function; The optical signal to noise ratio hierarchical prediction model is trained according to the second training loss until the second training loss converges, thereby obtaining the trained optical signal to noise ratio hierarchical prediction model.

6. The optical path multiplexing method according to claim 1, characterized in that: The acquired optical signal parameters at least include: optical signal intensity and spectrum.

7. The optical path multiplexing method according to any one of claims 1 to 6, characterized in that: The spread spectrum code parameters include at least: bit error rate, autocorrelation peak value and cross-correlation peak value.

8. An optical path multiplexing device using intelligent monitoring, characterized in that: The device comprises: A parameter acquisition module, used to acquire optical signal parameters and spread spectrum code parameters of a target optical fiber using a preset monitoring device at a target time point, wherein the target optical fiber uses code division multiplexing for communication; A level prediction module, used for inputting the spreading code parameters into a trained optical signal to noise ratio classification prediction model to obtain a predicted optical signal to noise ratio level; A model determination module, used to determine the optical signal-to-noise ratio prediction model corresponding to the predicted optical signal-to-noise ratio level as a target prediction model from M trained optical signal-to-noise ratio prediction models, where M is an integer greater than zero; The optical signal-to-noise ratio prediction module is used to input the optical signal parameters into the target prediction model to obtain the predicted optical signal-to-noise ratio corresponding to the target time point, and the predicted optical signal-to-noise ratio is used to assist in adjusting the optical transmitting end, optical amplifier and optical output end corresponding to the target optical fiber.

9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the optical path multiplexing method using intelligent monitoring as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the optical path multiplexing method using intelligent monitoring according to any one of claims 1 to 7 is implemented.

Images