Extraction device and extraction method

Abstract

This extraction device comprises: a pre-processing unit that divides, per symbol period, the trajectory of a point determined on the basis of a modulated electric field waveform; and a distribution processing unit that generates a frequency distribution of at least one among the points and the trajectories as a feature quantity of the electric field waveform. The pre-processing unit may separate the electric field waveform into at least one among an intensity waveform, a real waveform, and an imaginary waveform. The points may be sample points for intensity, a real component, or an imaginary component. The points may be sample points determined on a Poincare sphere or a complex plane representing the real waveform and the imaginary waveform.

Description

Extraction apparatus and extraction method 【0001】 The present invention relates to an extraction apparatus and an extraction method. This application claims priority under PCT / JP2024 / 043571, which was filed internationally on 10 December 2024, and the contents of that application are incorporated herein by reference. 【0002】 To increase the capacity, reduce latency, and lower the power consumption of optical communication systems, the All-Photonics Network (APN) is being investigated (see Non-Patent Document 1). In an All-Photonics Network, optical nodes relay optical signals as optical signals, thereby directly connecting user devices on opposing networks using optical signals. 【0003】 When a user device is newly connected to the all-photonics network and a new route is requested between the user devices, the control unit assigns optical transmission paths that satisfy a specified code error rate as the new route between the user devices. Alternatively, the control unit could select an optical transmission path that satisfies the specified code error rate by actually transmitting optical signals through each path and trial and error while changing the parameters of each optical transmission path. However, route design requires an enormous amount of time. 【0004】 One method for designing routes in a short time is based on a technique for estimating the transmission quality of optical signals (see Non-Patent Literature 2). In this method, the transmission quality is estimated in a short time for each candidate new route. Transmission quality is expressed using an index that indicates the communication quality in an optical communication system. Examples of indicators of communication quality include the code error rate, the Q (Quality factor) value, and the signal-to-noise ratio (SNR). For example, if the specified value for the code error rate is met, it may be determined that the specified value for transmission quality is met. By having the control device assign optical transmission paths that meet the specified value for transmission quality as new routes between user devices, the route design time is shortened. 【0005】Non-Patent Document 2 discloses a method for estimating transmission quality in a short time using a pre-trained machine learning model (artificial neural network). In Non-Patent Document 2, each pre-trained model corresponding to the optical transmission path and the receiving device is cascaded. The feature quantities of the electric field waveform propagate through each of the cascaded pre-trained models. The code error rate in the pre-trained model that ultimately acquires the electric field waveform is estimated as the transmission quality. Figure 39 shows a first example of a model (pre-trained model) for an optical transmission path with multiple spans. Multiple "Model #1" (ANN: artificial neural network) may be integrated into one "Model #1'". Figure 40 shows a second example of a model (pre-trained model) for an optical transmission path with multiple spans. "Model #1" and "Model #2" may be integrated into one "Model #3". 【0006】 In an all-photonics network, user devices located far apart from each other are directly connected optically via one or more optical nodes. Each optical node is equipped with an optical switch. The optical switch relays optical signals as optical signals without performing photoelectric conversion. Here, the control unit estimates the code error rate for each candidate new path using a technique for estimating the transmission quality of optical signals. 【0007】 The control unit selects a path from among the candidate new paths that satisfies a specified value for the code error rate. The control unit assigns the selected path as the path between user devices. Based on the path between user devices, the control unit designs the optical signal path at the optical nodes. Here, the control unit outputs optical transmission path information to the estimation unit. The optical transmission path information includes, for example, the transmission distance L between each optical node (span), the intensity P of the optical signal input to each optical node, and the intensity P of the optical signal at the receiving user device. ＲＸ The estimation unit outputs the estimated code error rate, based on the optical transmission path information, as the transmission quality to the control device for each candidate new path. 【0008】In optical transmission lines with multiple spans, optical amplifiers are inserted between the spans. These optical amplifiers compensate for optical fiber losses in the optical signal. The optical signal output from the transmitting user equipment (transmitter) is input into the optical fiber. The optical fiber outputs the optical signal to the next span. Through this repetition, the optical signal is finally received by the receiving user equipment (receiver). 【0009】 S. Kaneko, M. Yoshino, N. Shibata, R. Igarashi, J. Kani, and T. Yoshida, "Photonic gateway accommodating all types of wavelength paths for digital-coherent and IM-DD user terminals in all-photonic metro-access converged networks," in Journal of Optical Communications and Networking, vol. 16, no. 3, pp. 304-316, March 2024.Ryo Igarashi, Ryo Koma, Kazutaka Hara, Jun-ichi Kani, and Tomoaki Yoshida “Fast QoT estimation method using cascaded artificial neural network for real-time path provisioning in IMDD based all-optical networks “, in Optics Express, vol. 32, no.2, pp. 1176-1187, January 2024. 【0010】 For transmission quality to be estimated, feature quantities of the electric field waveform must be extracted from that waveform. In Non-Patent Document 2, the electric field waveform, which is the target of feature quantity extraction, is input to a nonlinear filter (not shown). The transfer function of the nonlinear filter is determined according to the tap coefficients. The tap coefficients are determined by a tap coefficient calculation unit (not shown). 【0011】The tap coefficient calculation unit updates the tap coefficients, which reduce the difference between the electric field waveform output from the nonlinear filter and a predetermined reference electric field waveform, using an algorithm such as the least mean square (LMS) method. The tap coefficient calculation unit outputs the updated tap coefficients to the nonlinear filter. The nonlinear filter updates the electric field waveform output from the nonlinear filter based on the updated tap coefficients. 【0012】 The tap coefficient calculation unit updates the tap coefficients until the difference between the electric field waveform output from the nonlinear filter and the reference electric field waveform falls below a threshold. The final obtained tap coefficients are uniquely determined for the electric field waveform input to the nonlinear filter. Therefore, the final obtained tap coefficients can be used as feature quantities for the electric field waveform input to the nonlinear filter. 【0013】 However, if the difference between the electric field waveform input to the nonlinear filter and the reference electric field waveform is large, the results of methods such as the least squares method may not converge, and the characteristic features of the electric field waveform may not be correctly extracted from it. Therefore, the reference electric field waveform must be predetermined based on the electric field waveform of the optical signal, the characteristics of the optical signal transmitter, the transmission distance of the optical signal, and the symbol pattern of the optical signal, so that the difference between the electric field waveform input to the nonlinear filter and the reference electric field waveform is small. 【0014】 Thus, there is a problem in that, in addition to the electric field waveform of the optical signal (optical electric field waveform), it is not possible to extract the characteristic quantities of the electric field waveform of an optical signal from the electric field waveform itself without additional information such as the characteristics of the optical signal transmitting device, the transmission distance of the optical signal, and the symbol pattern of the optical signal. 【0015】 In view of the above circumstances, the present invention aims to provide an extraction device and extraction method that can extract characteristic quantities of the electric field waveform of an optical signal solely from that electric field waveform. 【0016】One aspect of the present invention is an extraction device comprising a preprocessing unit that divides the trajectory of points determined based on a modulated electric field waveform into symbol periods, and a distribution processing unit that generates a frequency distribution of at least one of the points and the trajectory as a feature quantity of the electric field waveform. 【0017】 One aspect of the present invention is an extraction method performed by an extraction device, comprising the steps of: dividing the trajectory of points determined based on a modulated electric field waveform into symbol periods; and generating a frequency distribution of at least one of the points and the trajectory as a feature quantity of the electric field waveform. 【0018】 This invention makes it possible to extract characteristic features of the electric field waveform of an optical signal solely from that electric field waveform. 【0019】This figure shows an example of the configuration of the communication system in the first embodiment. This figure shows an example of the configuration of the extraction unit in the first embodiment. This figure shows an example of the trajectory of intensity sample points in the first embodiment. This figure shows an example of the trajectory of sample points in the first embodiment, for each symbol period. This is an overview view showing an example of the frequency distribution of sample points in the first embodiment, for each sample phase. This figure shows an example of the frequency distribution of sample points in the first embodiment, for each sample phase. This figure shows an example of the normalized frequency distribution in the first embodiment, for each sample phase. This figure shows an example of the configuration of the learning system in the sixth embodiment. This flowchart shows an example of the operation of the extraction unit in the first embodiment. This figure shows an example of the configuration of the extraction unit in the second embodiment. This figure shows an example of the process of adding noise to the frequency distribution of light intensity in the second embodiment. This figure shows an example of the configuration of the extraction unit in the third embodiment. This figure shows an example of the trajectory of symbol points on the IQ plane in the third embodiment, for each symbol period. This is an overview view showing an example of the frequency distribution of trajectories in the third embodiment. This figure shows an example of the frequency distribution of trajectories in the third embodiment. This figure shows an example of the configuration of the extraction unit in the fourth embodiment. This figure shows an example of the process of removing the phase offset from the trajectory of a symbol point in the IQ plane in the fourth embodiment, for each symbol period. This is an overview view showing an example of the frequency distribution of the trajectory with the phase offset removed in the fourth embodiment. This figure shows an example of the frequency distribution of the trajectory with the phase offset removed in the fourth embodiment. This figure shows an example of the configuration of the extraction unit in the fifth embodiment. This figure shows an example of a symbol point defined on a Poincaré sphere in the fifth embodiment. This figure shows an example of the trajectory of a symbol point on a Poincaré sphere for the mth period in the fifth embodiment. This is an overview view showing an example of the frequency distribution of the trajectory of a symbol point on a Poincaré sphere in the fifth embodiment. This figure shows examples of electric field waveforms used as datasets when generating trained models in each embodiment from the first to the fifth embodiment. This figure shows examples of electric field waveforms acquired by the extraction unit from a measuring instrument in each embodiment from the first to the fifth embodiment. This figure shows an example of the configuration of the communication system in the sixth embodiment.This figure shows an example of the configuration of the correction unit in the sixth embodiment. This flowchart shows an example of the operation of the correction unit in the sixth embodiment. This figure shows an example of the configuration of the correction unit in the seventh embodiment. This figure shows an example of the configuration of the correction unit in the eighth embodiment. This figure shows an example of the configuration of the correction unit in a modified version of the eighth embodiment. This figure shows an example of the configuration of the communication system in the ninth embodiment. This figure shows an example of sample phase correction for an electric field waveform with a sample frequency shift in the ninth embodiment. This figure shows an example of the configuration of the communication system in the tenth embodiment. This figure shows an example of frequency offset compensation in the tenth embodiment. This figure shows an example of the configuration of the communication system in the eleventh embodiment. This figure shows an example of the configuration of the communication system in a modified version of the eleventh embodiment. This figure shows an example of the hardware configuration of the control device in each embodiment. This figure shows a first example of a model of an optical transmission path having multiple spans. This figure shows a second example of a model of an optical transmission path having multiple spans. 【0020】 Embodiments of the present invention will be described in detail with reference to the drawings. (First Embodiment) Figure 1 is a diagram showing an example configuration of a communication system 1 in the first embodiment. The communication system 1 is a system that communicates using optical signals. The communication system 1 comprises a user device 2, an optical node 3, a control device 4, an optical node 5, a user device 6, and an optical transmission line 7. The communication system 1 may further include optical nodes and an optical transmission line. The communication system 1 may also further include a user device. 【0021】 Optical node 3 comprises a splitter 31, a measuring instrument 32, a communication interface 33, and an optical switch 34. Control device 4 comprises an extraction unit 41a, a candidate output unit 42, an estimation unit 43, a determination unit 44, and a communication interface 45. Optical node 5 comprises a communication interface 51 and an optical switch 52. Optical transmission path 7 comprises, for example, an optical fiber. Optical transmission path 7 may also include, for example, an optical amplifier. 【0022】<User Device 2>The user device 2 is a communication device of the first user. In FIG. 1, as an example, the user device 2 is newly connected to the optical node 3. The user device 2 requests the control device 4 to open a new path between the user device 2 and the user device 6. In this case, the user device 2 transmits the electric field waveform E of the optical signal ０ to the measuring device 32 via the splitter 31. 【0023】 <Optical Node 3>The optical node 3 is a first relay device for optical signals. The splitter 31 branches the optical signal (transmission signal) transmitted from the user device 2 to the measuring device 32 and the optical switch 34. For example, the splitter 31 outputs the electric field waveform E of the optical signal transmitted from the user device 2 that requested the opening of the new path ０ to the measuring device 32. The measuring device 32 measures the electric field waveform E of the optical signal transmitted from the user device 2 ０ and outputs the electric field waveform E of the transmitted optical signal ０ to the extraction unit 41a via the control channel. 【0024】 The communication interface 33 acquires the internal connection information in the optical switch 34 from the communication interface 45 via the control channel. The optical switch 34 switches the internal connection (connection relationship between the input port and output port of the optical signal) in the optical switch 34 based on the internal connection information determined by the control device 4. 【0025】 <Control Device 4>The control device 4 (extraction device) designs the path of the optical signal. The control device 4 manages the path of the optical signal by controlling the internal connections of each optical node in the communication system 1 based on the designed path. For example, the control device 4 allocates an optical transmission path that satisfies the specified value of the transmission quality to the path of the optical signal between the user device 2 and the user device 6. 【0026】 The extraction unit 41a extracts the feature amount A ０ from the electric field waveform E ０ The extraction unit 41a uses a learned model, for example, in the inference stage of machine learning, to extract the feature amount A ０ of the electric field waveform E ０ from the electric field waveform E ０ and the feature amount A of the electric field waveform E０ Extraction is performed from the electric field waveform E. The extraction unit 41a is used to extract the electric field waveform E. ０ Feature A ０ This is output to the determination unit 44. 【0027】 The candidate output unit 42 selects multiple route candidates as candidates for a new route based on the status information of each optical node and each optical transmission path in the communication system 1. For example, the candidate output unit 42 selects optical node 3, optical node 5, and optical transmission path 7 as one of the route candidates. The candidate output unit 42 outputs the transmission path configuration information (hereinafter referred to as "candidate information") of the selected route candidates (hereinafter referred to as "candidate information") to the determination unit 44. The candidate information includes, for example, the number of spans N and the length L of the optical transmission path of the nth span. ｎ The intensity P of the optical signal input to the nth span. ｎ The intensity P of the optical signal received by the user device 6 in the subsequent stage of the Nth span. ＲＸ This includes each candidate route. 【0028】 The estimation unit 43 calculates the electric field waveform E ０ Feature A ０ The decision unit 44 obtains candidate information about the selected path candidate. The estimation unit 43 then obtains the electric field waveform E ０ Feature A ０ Based on the candidate information for the selected route candidate, the transmission quality is estimated for each route candidate. The estimation unit 43 outputs the transmission quality of each route candidate to the determination unit 44. 【0029】 The determination unit 44 determines the electric field waveform E ０ Feature A ０ The extraction unit 41a obtains the following. The decision unit 44 obtains candidate information for the selected multiple path candidates from the candidate output unit 42. The decision unit 44 obtains the electric field waveform E ０ Feature A ０ The system outputs candidate information for the selected multiple route candidates to the estimation unit 43. The determination unit 44 selects an optical transmission path that satisfies a specified value for transmission quality (e.g., code error rate) from among the selected multiple route candidates. 【0030】The determination unit 44 determines the internal connections in the optical switch 34 and the optical switch 52 based on the selected optical transmission path. The communication interface 45 outputs the internal connection information in the optical switch 34 to the communication interface 33 via the control channel of the optical node 3. The communication interface 45 outputs the internal connection information in the optical switch 52 to the communication interface 51 via the control channel of the optical node 5. 【0031】 <Optical Node 5> Optical node 5 is a second relay device for optical signals. Communication interface 51 obtains internal connection information for optical switch 52 from communication interface 45 via a control channel. Based on the internal connection information determined by control device 4, optical switch 52 switches its internal connections (optical signal input port and output port). This opens up the optical signal path between user device 2 and user device 6. 【0032】 <User Device 6> User device 6 is a communication device of the second user. User device 6 acquires optical signals from user device 2 via the opened path. User device 6 may also transmit optical signals to user device 2 via the opened path. 【0033】 Next, an example of the configuration of the extraction unit 41a will be described. Figure 2 shows an example of the configuration of the extraction unit 41a in the first embodiment. The extraction unit 41a comprises a pre-processing unit 411a, a distribution processing unit 412, a normalization unit 413, and a reduction unit 414. Note that the normalization unit 413 in the extraction unit 41a may be provided either before or after the distribution processing unit 412. 【0034】 The extraction unit 41a acquires an electric field waveform E (discrete waveform) containing arbitrary waveform distortion from the measuring instrument 32. The electric field waveform E is, for example, an intensity-modulated NRZ (Non-Return to Zero) signal. The electric field waveform E is represented as a complex time waveform. The extraction unit 41a outputs the feature quantity A of the electric field waveform E to the determination unit 44. 【0035】Here, the preprocessing unit 411a separates the electric field waveform input from the measuring instrument 32 into the intensity trajectory (intensity time waveform), the real component trajectory (I-axis component), and the imaginary component trajectory (Q-axis component). That is, the preprocessing unit 411a separates the electric field waveform input from the measuring instrument 32 into the intensity time waveform (intensity waveform), the real component trajectory (real waveform), and the imaginary component trajectory (imaginary waveform). The intensity trajectory is calculated based on the square of the absolute value of the complex number (real component and imaginary component). 【0036】 Figure 3 shows an example of the trajectory of intensity sample points (sample point group) in the first embodiment. The preprocessing unit 411a performs a 5x oversampling on the intensity waveform 100 (intensity trajectory) as an example. The circles represent the starting point of the sample points in the mth period (first sample point). The triangles represent the points from the second to the fourth sample points in the mth period. The squares represent the ending point of the sample points in the mth period (fifth sample point). 【0037】 Figure 4 shows an example of the trajectory 101 of the sample points in the first embodiment, for each symbol period. The preprocessing unit 411a divides the trajectory 101 of the sample points (sample point group) determined based on the modulated electric field waveform E into symbol periods. The preprocessing unit 411a may also divide the trajectory 101 of the sample points determined based on the periodically modulated electric field waveform E into symbol periods. 【0038】 Figure 5 is an overview view showing an example of the frequency distribution of sample points in the first embodiment, for each sample phase. The distribution processing unit 412 generates a frequency distribution (probability density distribution) of at least one of the sample points and the trajectory of the sample points. 【0039】Figure 6 shows an example of the frequency distribution of sample points in the first embodiment, for each sample phase. For example, the distribution processing unit 412 generates the frequency distribution of sample points as a feature A of the electric field waveform E. For example, the distribution processing unit 412 may generate the frequency distribution of the trajectory 101 of the sample points as a feature A of the electric field waveform E. For example, the distribution processing unit 412 may generate the frequency distribution of the sample points and the trajectory 101 of the sample points as a feature A of the electric field waveform E. The frequency distribution of sample points may be generated for each light intensity. 【0040】 Furthermore, the distribution processing unit 412 may generate frequency distributions for the locus of the real component (real part waveform) and the locus of the imaginary component (imaginary part waveform), similar to the procedure for generating the frequency distribution of the intensity locus (intensity waveform). Alternatively, feature quantities of the electric field waveform may be extracted from the electric field waveform based on the frequency distribution of the locus of the real component, the frequency distribution of the locus of the imaginary component, and the frequency distribution of the intensity locus. For example, for the same sample phase, feature quantities of the electric field waveform may be extracted from the electric field waveform based on the sum of the frequencies of the real component, the imaginary component, and the intensity. 【0041】 Figure 7 shows an example of a normalized frequency distribution in the first embodiment, for each sample phase. When the distortion of the electric field waveform is used as a feature, if the distortion of the electric field waveform input to the extraction unit 41a is the same, the same feature should be output from the extraction unit 41a even if the intensity P or total number of periods M of the electric field waveform are different. Therefore, the normalization unit 413 normalizes the frequency distribution for each sample phase so that the integral value of the frequency becomes a predetermined value (for example, 1) for each symbol phase (symbol period). Alternatively, the normalization unit 413 may concatenate the frequency distributions of each sample phase as a one-dimensional array. 【0042】 To reduce the size of the trained model into which the features of the electric field waveform are input, the reduction unit 414 may reduce the dimensionality of the features using a dimensionality reduction method. The dimensionality reduction method is, for example, principal component analysis (PCA). The reduction unit 414 outputs the feature A to which the dimensionality reduction method has been applied to the determination unit 44. 【0043】Next, a machine learning learning system will be described. Figure 8 shows an example configuration of the learning system 10 in the first embodiment. The learning system 10 is a system that generates a trained model using machine learning techniques. The learning system 10 comprises a generation device 20 and a learning device 30. The generation device 20 comprises a characteristic information generation unit 201 and an extraction unit 41a. The learning device 30 comprises a storage device 301 and a learning unit 302. 【0044】 When the estimation unit 43 estimates transmission quality using a machine learning model, that machine learning model needs to be generated in advance as a trained model. Therefore, during the machine learning training phase, the generation device 20 creates a set of training data including training data (transmission path configuration information) and correct labels (transmission quality information). 【0045】 Here, the characteristic information generation unit 201 may be the actual optical nodes and optical transmission lines in the communication system 1, or it may be a simulator (computer) that simulates the actual devices. The characteristic information generation unit 201 generates the characteristic information generation unit for each parameter (length L of the optical transmission line) used as learning data (explanatory variables). ｎ , the intensity of the optical signal P ｎ , and the intensity P of the optical signal ＲＸ The characteristic information generation unit 201 generates the electric field waveform E associated with each parameter used as learning data and the transmission quality information used as the correct label (target variable). The characteristic information generation unit 201 records each parameter used as learning data and the transmission quality information used as the correct label in the storage device 301. The characteristic information generation unit 201 generates the electric field waveform E associated with each parameter used as learning data. ｎ This is output to the extraction unit 41a. 【0046】 The extraction unit 41a receives the electric field waveform E input from the characteristic information generation unit 201. ｎ Feature A ｎ It converts to the following. The extraction unit 41a selects feature A as one of the parameters used as training data. ｎ This is recorded in the storage device 301. 【0047】During the machine learning training phase, the learning device 30 generates a trained model using the set of training data generated by the generation device 20. Here, the storage device 301 stores each parameter (feature A) used as training data. ｎ , length L of the optical transmission path ｎ , the intensity of the optical signal P ｎ , and the intensity P of the optical signal ＲＸ The system stores the transmission quality information used as the correct label, along with the training data set. The learning unit 302 generates a trained model by performing a training process using the training data set stored in the storage device 301. The storage device 301 stores the generated trained model. 【0048】 Before starting the machine learning inference stage, the estimation unit 43 retrieves the trained model from the storage device 301. During the machine learning inference stage, the estimation unit 43 calculates the feature quantity A of the electric field waveform to be inferred. ｎ And the length L of the optical transmission path ｎ And the intensity of the light signal P ｎ And the intensity of the light signal P ＲＸ The data is input to the trained model. The estimation unit 43 obtains the transmission quality (e.g., the code error rate) in the optical signal path from the trained model. In this way, the estimation unit 43 estimates the transmission quality in the optical signal path. 【0049】 Next, an example of the operation of the extraction unit 41a in the communication system 1 will be described. Figure 9 is a flowchart showing an example of the operation of the extraction unit 41a in the first embodiment. The preprocessing unit 411a divides the trajectory of the sample points, which is determined based on the modulated electric field waveform, into symbol periods. The electric field waveform may be modulated periodically (step S101). The distribution processing unit 412 generates the frequency distribution of the sample points as a feature of the electric field waveform. The distribution processing unit 412 may also generate the frequency distribution of the trajectory of the sample points as a feature of the electric field waveform (step S102). 【0050】As described above, the preprocessing unit 411a separates the electric field waveform into at least one of the intensity trajectory (intensity waveform), the real component trajectory (real waveform), and the imaginary component trajectory (imaginary waveform). The preprocessing unit 411a divides the point trajectory (discrete electric field waveform) determined based on the modulated electric field waveform into symbol periods. The preprocessing unit 411a may divide the point trajectory determined based on the modulated electric field waveform into symbol periods. A point is a sample point defined in the intensity waveform 100, the real component, or the imaginary component. The point trajectory is the time waveform of the sample point. The distribution processing unit 412 generates a frequency distribution of at least one of the points and trajectories as a feature quantity of the electric field waveform. The distribution processing unit 412 generates a frequency distribution of sample points for each phase (sample phase) of the sample point defined in the time direction of the intensity waveform 100, the time direction of the real waveform, or the time direction of the imaginary waveform. The distribution processing unit 412 may generate a frequency distribution of sample points for each phase of a sample point (sample phase) defined in the direction of light intensity of the intensity waveform 100, the direction of the real component of the real waveform, or the direction of the imaginary component of the imaginary waveform. 【0051】 This makes it possible to extract the characteristic features of the electric field waveform of an optical signal solely from that electric field waveform. This also makes it possible to suppress the complexity of the configuration of communication system 1. Furthermore, it makes it possible to suppress an increase in the cost and power consumption of communication system 1. 【0052】 The normalization unit 413 may normalize the characteristic quantities of the electric field waveform. For example, the normalization unit 413 may normalize the integral value of the frequency distribution of sample points so that the integral value of the frequency distribution of sample points becomes a predetermined value. 【0053】 (Second Embodiment) In the second embodiment, the main difference from the first embodiment is that noise is added to the frequency distribution of the sample points. The second embodiment will be explained focusing on the differences from the first embodiment. 【0054】 Figure 10 shows an example of the configuration of the extraction unit 41b in the second embodiment. The extraction unit 41b comprises a preprocessing unit 411b, a distribution processing unit 412, a normalization unit 413, a reduction unit 414, and a noise unit 415. 【0055】The frequency distribution (features) changes according to the signal-to-noise ratio (SNR) of the electric field waveform. Therefore, it is desirable that the set of training data used in subsequent machine learning training phases be easily generated so that features of electric field waveforms containing various types of noise can be extracted during the inference phase of machine learning. Accordingly, the noise unit 415 receives the frequency distribution (discretized probability density distribution) and a function representing the noise (for example, a Gaussian function) as input from the distribution processing unit 412. The amount of noise is, for example, the noise intensity σ ２ It is expressed using 【0056】 Figure 11 shows an example of the process of adding noise to the frequency distribution of light intensity in the second embodiment. The noise unit 415 adds the input noise to the input frequency distribution (discretized probability density distribution). For example, the noise unit 415 convolves the input noise (a function representing the noise) onto the input frequency distribution. The noise unit 415 outputs the frequency distribution with the added noise to the normalization unit 413. 【0057】 As described above, the noise unit 415 may add noise to the frequency distribution of sample points (discretized probability density distribution). For example, the noise unit 415 may perform a convolution operation of a predetermined function (e.g., a Gaussian function) on the frequency distribution of sample points. 【0058】 This makes it possible to extract feature characteristics from the electric field waveform of an optical signal solely from that waveform. Furthermore, feature characteristics from electric field waveforms containing various types of noise can be extracted during the inference stage of machine learning. 【0059】 (Third Embodiment) In the first and second embodiments, the frequency distribution of sample points in the intensity waveform was determined for each sample phase. In the first embodiment, the frequency distribution of sample points for the in-phase component trajectory (real part waveform) or the quadrature-phase component trajectory (imaginary part waveform) may also be determined for each sample phase. 【0060】In contrast, the main difference between the third embodiment and the first and second embodiments is that the frequency distribution of the trajectories of symbol points in the IQ (in-phase and orthogonal-phase) plane (complex plane) is extracted from the electric field waveform as a feature. The third embodiment will be explained focusing on the differences from the first and second embodiments. 【0061】 Figure 12 shows an example of the configuration of the extraction unit 41c in the third embodiment. The extraction unit 41c comprises a preprocessing unit 411c, a distribution processing unit 412, a normalization unit 413, and a reduction unit 414. 【0062】 The electric field waveform E is, for example, a signal with four values. A signal with four values ​​is, for example, a Quadrature Phase Shift Keying (QPSK) signal. The preprocessor 411a separates the electric field waveform input from the measuring instrument 32 into the trajectory of the real component (time waveform) and the trajectory of the imaginary component (time waveform). The preprocessor 411c plots the symbol points and the trajectories of the symbol points on the IQ plane based on the trajectories of the real component and the imaginary component. 【0063】 Figure 13 shows an example of the trajectory of a symbol point in the IQ plane in the third embodiment, for each symbol period. Circles represent the symbol point corresponding to the starting point of the sample point in the m-th period (first sample point). Squares represent the symbol point corresponding to the ending point of the sample point in the m-th period (fifth sample point). Dashed lines represent the trajectory of the symbol point. The preprocessing unit 411c divides the trajectory of the symbol point, which is determined based on the modulated electric field waveform E, for each symbol period. The preprocessing unit 411c may also divide the trajectory of the symbol point, which is determined based on the periodically modulated electric field waveform E, for each symbol period. 【0064】 Figure 14 is an overview view showing an example of the frequency distribution of trajectories in the third embodiment. The distribution processing unit 412 generates a frequency distribution (probability density distribution) of at least one of the symbol points and the trajectories of the symbol points. 【0065】Figure 15 shows an example of the frequency distribution of the trajectory in the third embodiment. For example, the distribution processing unit 412 generates the frequency distribution of the symbol points as feature quantity A of the electric field waveform E. For example, the distribution processing unit 412 may generate the frequency distribution of the trajectory 102 of the symbol points as feature quantity A of the electric field waveform E. For example, the distribution processing unit 412 may generate the frequency distribution of the symbol points and the trajectory 102 of the symbol points as feature quantity A of the electric field waveform E. The frequency distribution of the symbol points may be generated for each real component (I-axis component) or for each imaginary component (Q-axis component). 【0066】 As described above, the preprocessing unit 411c separates the electric field waveform into at least the locus of the real component and the locus of the imaginary component from the locus of the intensity, the locus of the real component, and the locus of the imaginary component. The preprocessing unit 411c divides the locus of points (discrete electric field waveform) determined based on the modulated electric field waveform into symbol periods. The preprocessing unit 411c may also divide the locus of points determined based on a periodically modulated electric field waveform into symbol periods. The distribution processing unit 412 generates a frequency distribution of at least one of the points and locus as a feature quantity of the electric field waveform. The points are sample points determined on the complex plane (IQ plane) representing the real component and the imaginary component. The locus of points may be a time waveform of a sample point determined on the complex plane. The distribution processing unit 412 may generate a frequency distribution of sample points for each phase of the sample points in the time direction of the intensity waveform 100, the time direction of the real component waveform, or the time direction of the imaginary component waveform. The distribution processing unit 412 may generate a frequency distribution of sample points for each phase of a sample point (sample phase) defined in the direction of light intensity of the intensity waveform 100, the direction of the real component of the real waveform, or the direction of the imaginary component of the imaginary waveform. 【0067】 This makes it possible to extract characteristic features of the electric field waveform of an optical signal solely from that electric field waveform. 【0068】 (Fourth Embodiment) In the fourth embodiment, the main difference from the first to third embodiments is that the phase offset of the symbol points in the IQ plane is removed. The fourth embodiment will be explained focusing on the differences from the first to third embodiments. 【0069】The waveform distortion of the electric field waveform does not change with respect to the phase offset of the symbol point in the IQ plane. Therefore, since the code error rate does not change with respect to the phase offset, information about the phase offset is unnecessary for feature extraction. Thus, in the fourth embodiment, the phase offset of the symbol point is removed. 【0070】 Figure 16 shows an example of the configuration of the extraction unit 41d in the fourth embodiment. The extraction unit 41d comprises a preprocessing unit 411d, a distribution processing unit 412, a normalization unit 413, a reduction unit 414, and a removal unit 416. 【0071】 Figure 17 shows an example of the process for removing the phase offset from the trajectory of a symbol point in the IQ plane in the fourth embodiment, for each symbol period. In Figure 17, a phase offset of 45 degrees is given to the trajectory of the symbol point exemplified in Figure 13 as an example. The preprocessing unit 411d divides the trajectory of the symbol point, which is determined based on the electric field waveform E to which a 45-degree phase offset is given, for each symbol period. 【0072】 The removal unit 416 removes the phase offset included in the trajectory of the symbol point so that the phase of the symbol point (circle) corresponding to the starting point of the sample point in the m-th period becomes a predetermined phase (for example, 0 degrees). This makes it possible to obtain a constant frequency distribution even if the electric field waveform E input to the preprocessing unit 411d contains a phase offset. 【0073】 Figure 18 is an overview view showing an example of the frequency distribution of a trajectory with phase offset removed in the fourth embodiment. The distribution processing unit 412 generates a frequency distribution (probability density distribution) of at least one of the symbol points with phase offset removed and the trajectory of the symbol points with phase offset removed. 【0074】Figure 19 shows an example of the frequency distribution of a trajectory with phase offset removed in the fourth embodiment. For example, the distribution processing unit 412 generates the frequency distribution of symbol points with phase offset removed as feature quantity A of the electric field waveform E. For example, the distribution processing unit 412 may generate the frequency distribution of the trajectory 103 of symbol points with phase offset removed as feature quantity A of the electric field waveform E. For example, the distribution processing unit 412 may generate the frequency distribution of symbol points with phase offset removed and the trajectory 103 of symbol points with phase offset removed as feature quantity A of the electric field waveform E. 【0075】 As described above, the removal unit 416 may remove the phase offset of the symbol point trajectory. This makes it possible to extract the feature quantities of the electric field waveform of the optical signal solely from that electric field waveform. Furthermore, it is possible to suppress an increase in the number of training data sets. 【0076】 The removal unit 416 may be provided between the pre-processing unit 411a and the distribution processing unit 412 in the extraction unit 41a of the first embodiment. Similarly, the removal unit 416 may be provided between the pre-processing unit 411b and the distribution processing unit 412 in the extraction unit 41b of the second embodiment. Furthermore, the removal unit 416 may be provided between the pre-processing unit 411c and the distribution processing unit 412 in the extraction unit 41c of the third embodiment. 【0077】 (Fifth Embodiment) In the fifth embodiment, the main difference from the first to fourth embodiments is that the frequency distribution of the trajectories of the symbol points on the Poincaré sphere is extracted as a feature. The fifth embodiment will be explained focusing on the differences from the first to fourth embodiments. 【0078】 Figure 20 shows an example of the configuration of the extraction unit 41e in the fifth embodiment. The extraction unit 41e comprises a pre-processing unit 411e, a distribution processing unit 412, a normalization unit 413, and a reduction unit 414. The extraction unit 41e may also include a noise unit 415. The extraction unit 41e may also include a removal unit 416 prior to the distribution processing unit 412. 【0079】Figure 21 shows an example of symbol points defined in the Poincaré sphere 8 in the fifth embodiment. Each symbol point is arranged three-dimensionally in the Poincaré sphere 8. 【0080】 Figure 22 shows an example of the trajectory of the symbol point on the Poincaré sphere 8 in the fifth embodiment, for the mth period. The trajectory of the symbol point is determined by the time change of the position of the symbol point on the Poincaré sphere 8. 【0081】 Figure 23 is an overview view showing an example of the frequency distribution of the trajectories of symbol points on the Poincaré sphere 8 in the fifth embodiment. The distribution processing unit 412 generates a frequency distribution (probability density distribution) of at least one of the symbol points and the trajectories 104 of the symbol points for each symbol period. 【0082】 As described above, the preprocessing unit 411e separates the electric field waveform into at least the locus of the real component and the locus of the imaginary component, which are the locus of the intensity (intensity waveform), the locus of the real component (real waveform), and the locus of the imaginary component (imaginary waveform). The preprocessing unit 411e divides the locus of points (discrete electric field waveform) determined based on the modulated electric field waveform into symbol periods. The preprocessing unit 411e may also divide the locus of points determined based on a periodically modulated electric field waveform into symbol periods. The distribution processing unit 412 generates a frequency distribution of at least one of the points and locus as a feature quantity of the electric field waveform. The points are sample points defined on the Poincaré sphere 8, which represent the locus of the real component and the locus of the imaginary component. The locus of points may also be the time waveform of the sample points defined on the Poincaré sphere 8. The distribution processing unit 412 may generate a frequency distribution of sample points for each phase of a sample point in the time direction of the intensity waveform 100, the time direction of the real part waveform, or the time direction of the imaginary part waveform. The distribution processing unit 412 may also generate a frequency distribution of sample points for each phase of a sample point (sample phase) defined in the light intensity direction of the intensity waveform 100, the real part component direction of the real part waveform, or the imaginary part component direction of the imaginary part waveform. Furthermore, the distribution processing unit 412 may also generate a frequency distribution of sample points for each phase of a sample point defined in the S1 axis direction, the S2 axis direction, or the S3 axis direction. 【0083】This makes it possible to extract characteristic features of the electric field waveform of an optical signal solely from that electric field waveform. 【0084】 Next, the problems of the first to fifth embodiments will be described. In the stage where a trained model is generated (training stage), the electric field waveform calculated by an ideal simulation is used as a dataset to generate the trained model. In contrast, in the stage where the estimation unit 43 estimates the transmission quality of each path candidate using the trained model (estimation stage), the extraction unit provided in the control device 4 (extraction device) uses the electric field waveform E acquired by the actual measuring instrument 32. ０ From, electric field waveform E ０ The features are extracted. The extracted features are input into a pre-trained model provided in the extraction unit. 【0085】 Thus, if there is a difference in the electric field waveform used in the learning stage and the estimation stage, a difference will also occur in the feature quantities extracted by the extraction unit. Therefore, the difference in the extracted feature quantities may affect the estimation result of transmission quality in the estimation stage. In other words, there is a problem that the accuracy of the estimation unit 43's estimation of transmission quality based on the electric field waveform measured by the measuring instrument 32 (actual device) cannot be improved. 【0086】 Figure 24 shows examples of electric field waveforms (electric field waveforms calculated by an ideal simulation) used as datasets when generating trained models in each of the first to fifth embodiments. The electric field waveforms exemplified in Figure 24 are discrete waveforms (discrete-time signals) oversampled at a sampling rate of five times the symbol period as an example. In the simulation, the sampling phase and signal-to-noise ratio (SNR) can be set arbitrarily. In the electric field waveforms exemplified in Figure 24, the sampling phase was adjusted so that the symbol phase (symbol position) occurs at multiples of n = 5 (where n is the sample number). In the simulation, ideal sampling without sample frequency shift is possible. In that case, the sampling phase does not change even if the number of samples increases. 【0087】Figure 25 shows examples of electric field waveforms acquired by the extraction unit from the measuring instrument 32 (actual device) in each of the first to fifth embodiments. In electric field waveforms acquired from the actual device, the sample phase changes randomly. For this reason, the sample phase is shifted in Figure 25. For example, in the region where the sample number n is small (0 ≤ n < 25), the symbol phase is shifted by one sample compared to the electric field waveform exemplified in Figure 24. 【0088】 Furthermore, if the frequency during electric field waveform generation (symbol repetition frequency) differs from the sampling frequency, the amount of sample phase shift changes as the sample number n increases. In other words, a sample frequency shift occurs. In Figure 25, the amount of sample phase shift, which was 1 in the region where the sample number n is small (0 ≤ n < 25), becomes 2 as the sample number n increases. Note that electric field waveforms obtained from the actual device may contain noise corresponding to the characteristics of the measuring instrument 32. 【0089】 In the communication system 1 in each embodiment from the first to the fifth embodiment, the electric field waveform E acquired from the measuring instrument 32 (actual device) ０ The feature quantities extracted from are input to the estimation unit 43. Here, at least one of the sample phase shift, sample frequency shift, and noise is the electric field waveform E ０ Because it is included in [the data], the accuracy of the transmission quality estimation may decrease. 【0090】 If a trained model is generated during the training phase using features extracted from an ideal electric field waveform, it is preferable that similar features extracted from an ideal electric field waveform are input to the trained model of the estimation unit 43 during the inference phase. Therefore, in each of the embodiments from the sixth to the eleventh embodiment, features extracted from the same ideal electric field waveform as in the training phase are input to the trained model of the estimation unit 43 during the inference phase. 【0091】 (Sixth Embodiment) The main difference in the sixth embodiment from the first to fifth embodiments is that a correction unit is provided before the extraction unit. The sixth embodiment will be explained focusing on the differences from the first to fifth embodiments. 【0092】 Figure 26 shows an example configuration of the communication system 1 in the sixth embodiment. The communication system 1 is a system that communicates using optical signals. The communication system 1 comprises a user device 2, an optical node 3, a control device 4, an optical node 5, a user device 6, and an optical transmission line 7. The communication system 1 may further include optical nodes and an optical transmission line. The communication system 1 may also further include a user device. 【0093】 Optical node 3 comprises a splitter 31, a measuring instrument 32, a communication interface 33, and an optical switch 34. The measuring instrument 32 comprises a receiver (not shown) and an analog-to-digital converter (not shown). The control device 4 comprises an extraction unit 41, a candidate output unit 42, an estimation unit 43, a determination unit 44, a communication interface 45, and a correction unit 46a. Optical node 5 comprises a communication interface 51 and an optical switch 52. The optical transmission line 7 comprises, for example, an optical fiber. The optical transmission line 7 may also include, for example, an optical amplifier. 【0094】 The correction unit 46a processes the electric field waveform E before it is input to the preprocessing unit provided in the extraction unit 41. ０ This is acquired from the measuring instrument 32 via the control channel. The correction unit 46a corrects the electric field waveform (corrected electric field waveform E) in which at least the sample phase shift of the sample phase shift and noise has been corrected. ｏｕｔ The output is input to the preprocessing unit provided in the extraction unit 41. 【0095】 Figure 27 shows an example of the configuration of the correction unit 46a in the sixth embodiment. The correction unit 46a comprises a code sequence output unit 461, a waveform generation unit 462, an upsampling execution unit 463, a downsampling execution unit 464, an upsampling execution unit 465, a sample phase correction unit 466, a downsampling execution unit 467, a first filter 468, and a phase shift removal unit 469. The first filter 468 is, for example, a Finite Impulse Response (FIR) filter or a Volterra nonlinear filter (VNLF). 【0096】The code sequence output unit 461 generates a predetermined code sequence (training signal). The waveform generation unit 462 generates discrete electric field waveforms (discrete waveforms) based on this predetermined code sequence. The discrete waveforms generated by the waveform generation unit 462 are free from waveform distortion. For example, in the case of an optical transmission system based on a non-return to zero (NRZ) signal, the discrete waveforms generated by the waveform generation unit 462 are waveforms with good eye aperture. Since the sample phase of the discrete waveforms generated by the waveform generation unit 462 is known, the waveforms do not contain sample phase shift. Furthermore, the discrete waveforms generated by the waveform generation unit 462 are noise-free waveforms. In contrast to this, the electric field waveform E in the sixth embodiment ０ This is a training signal generated based on the same code sequence as the code sequence output unit 461. 【0097】 The upsampling execution unit 463 (first upsampling execution unit) uses the sampling rate of the discrete waveform generated by the waveform generation unit 462 and the electric field waveform E that has been upsampled by the upsampling execution unit 465 (second upsampling execution unit). ０ Upsampling is performed on the discrete waveform generated by the waveform generation unit 462 so that the sampling rate is the same as that of the downsampling unit 463. The upsampling execution unit 463 inputs the upsampled discrete waveform to the downsampling execution unit 464 and the sample phase correction unit 466. 【0098】 The downsampling execution unit 464 (first downsampling execution unit) performs downsampling on the discrete waveform that has been upsampled by the upsampling execution unit 463. That is, the downsampling execution unit 464 lowers the sampling rate of the discrete waveform that has been upsampled by the upsampling execution unit 463 so that the sampling rate and sample phase of the discrete waveform become the sampling rate and sample phase assumed in the trained model. 【0099】The upsampling execution unit 465 (second upsampling execution unit) processes the electric field waveform E input from the measuring instrument 32. ０ Upsampling is performed on the electric field waveform E input from the measuring instrument 32. ０ Increase the sampling rate. 【0100】 The sample phase correction unit 466 processes the discrete waveform after upsampling and the electric field waveform E after upsampling. ０ Based on the cross-correlation with the sampling phase, symbol synchronization processing is performed at the sampling phase granularity. This is done to the electric field waveform E input from the measuring instrument 32. ０ The sampling phase and symbol phase become known. 【0101】 In other words, the sample phase correction unit 466 uses the electric field waveform E, which is input to the first filter 468 from the downsampling execution unit 467, as the target value (target waveform). ０ The sample phase of the sample phase correction unit 466 is corrected in advance. Since the sample phase of the discrete waveform generated by the waveform generation unit 462 is known, the electric field waveform E is synchronized with the sample phase of this discrete waveform. ０ The sample phase is corrected. This suppresses the occurrence of delay in the first filter 468, so the sample phase of the discrete waveform output from the first filter 468 becomes known. 【0102】 The downsampling execution unit 467 (second downsampling execution unit) processes the electric field waveform E obtained by upsampling execution unit 465 so that it matches the sampling rate and sample phase assumed in the trained model. ０ Lower the sampling rate. 【0103】 The first filter 468 performs filtering on the discrete waveform that has been downsampled by the downsampling execution unit 464. As a result, the first filter 468 processes the electric field waveform E whose sample phase has been corrected by the sample phase correction unit 466. ０The waveform distortion of the (target waveform) is transferred to the discrete waveform from which downsampling has been performed. 【0104】 The characteristics (transfer function) of the first filter 468 are determined as the tap coefficients of the first filter 468. The tap coefficients are determined using an equalization algorithm (for example, the least squares method (LMS)). In this case, the electric field waveform E is set as the target value (target waveform) of the least squares mean. ０ By using this, the waveform distortion of the discrete waveform output from the first filter 468 is reduced by the electric field waveform E ０ The waveform distortion will be similar to that of the (target waveform) (see Non-Patent Document 2). 【0105】 Therefore, the phase shift removal unit 469 removes the sample phase shift from the discrete waveform output from the first filter 468. For example, if the leading edge of the electric field waveform used for feature extraction in the training phase of the trained model is the symbol phase, the phase shift removal unit 469 removes the sample phase shift from the discrete waveform used for feature extraction in the extraction unit 41 (corrected electric field waveform E ｏｕｔ The phase shift removal unit 469 removes a portion of the discrete waveform sample so that the leading edge of the ) also becomes the symbol phase. The phase shift removal unit 469 then processes the discrete waveform from which the sample phase shift (second sample phase) has been removed into the corrected electric field waveform E ｏｕｔ The data is then input to the preprocessing unit provided in the extraction unit 41. 【0106】 Next, an example of the operation of the correction unit 46a will be described. Figure 28 is a flowchart showing an example of the operation of the correction unit 46a in the sixth embodiment. The code sequence output unit 461 outputs a predetermined code sequence (training signal) to the waveform generation unit 462 (step S201). The waveform generation unit 462 generates a discrete waveform with a predetermined sample phase based on the predetermined code sequence output from the waveform generation unit 462 (step S202). The upsampling execution unit 463 performs upsampling on the generated discrete waveform (step S203). The downsampling execution unit 464 performs downsampling on the discrete waveform that has been upsampled (step S204). 【0107】 The upsampling execution unit 465 processes the modulated electric field waveform E ０Upsampling is performed on the electric field waveform E input from the measuring instrument 32. ０ Upsampling is performed on the electric field waveform E. ０ This may be modulated periodically (step S205). 【0108】 The sample phase correction unit 466 processes the electric field waveform E after upsampling. ０ The upsampling execution unit 465 acquires the upsampled discrete waveform E from the upsampling execution unit 463. The sample phase correction unit 466 acquires the upsampled electric field waveform E ０ For this, synchronization processing is performed based on the cross-correlation with the discrete waveform (a discrete waveform with a predetermined sample phase) on which upsampling has been performed. That is, the sample phase correction unit 466 performs synchronization processing based on the cross-correlation with the electric field waveform E ０ The phase of the first sample is corrected (step S206). 【0109】 The downsampling execution unit 467 performs downsampling on the electric field waveform from which the first sample phase shift has been corrected. The downsampling execution unit 467 inputs the downsampled electric field waveform, from which the first sample phase shift has been corrected, to the first filter as the target waveform (step S207). 【0110】 The first filter 468 transfers the waveform distortion of the electric field waveform, which has had the first sample phase shift corrected, to the discrete waveform on which downsampling has been performed (step S208). The phase shift removal unit 469 removes the second sample phase shift that occurred in the discrete waveform on which the waveform distortion has been transferred (step S209). The phase shift removal unit 469 inputs the discrete waveform from which the second sample phase shift has been removed as a modulated electric field waveform to the preprocessing unit provided in the extraction unit 41. The electric field waveform may be periodically modulated (step S210). 【0111】 As described above, the correction unit 46a processes the electric field waveform E before it is input to the preprocessing unit provided in the extraction unit 41. ０This is obtained from the measuring instrument 32. The correction unit 46a corrects the electric field waveform (corrected electric field waveform E) in which at least the sample phase shift (first sample phase shift) of the sample phase shift (first noise) is corrected. ｏｕｔ The output is input to the preprocessing unit provided in the extraction unit 41. 【0112】 Here, the sample phase correction unit 466 corrects the electric field waveform E based on the cross-correlation with a discrete waveform having a predetermined sample phase (a discrete waveform based on a predetermined code sequence). ０ The sample phase shift of the electric field waveform (after upsampling) is corrected. The first filter 468 corrects the sample phase shift (first sample phase shift) of the electric field waveform E ０ The waveform distortion present in the waveform is transferred to the discrete waveform generated by the waveform generation unit 462 (see Non-Patent Document 2). The phase shift removal unit 469 removes the sample phase shift (second sample phase shift) caused by the first filter 468 from the discrete waveform with the transferred waveform distortion. The phase shift removal unit 469 then converts the discrete waveform from which the sample phase shift (second sample phase) has been removed into an electric field waveform (corrected electric field waveform E) with at least the sample phase shift corrected. ｏｕｔ The data is then input to the preprocessing unit provided in the extraction unit 41. 【0113】 This makes it possible to extract the characteristic features of the electric field waveform of an optical signal solely from that electric field waveform. It is possible to suppress the complexity of the configuration of the communication system 1. It is possible to suppress an increase in the cost and power consumption of the communication system 1. Furthermore, it is possible to improve the accuracy of the estimation unit 43's estimation of transmission quality based on the electric field waveform (electric field waveform including waveform distortion, sample phase shift, and noise) measured by the measuring instrument 32 (actual device). 【0114】 (Seventh Embodiment) In the seventh embodiment, the main difference from the sixth embodiment is that the discrete waveform input to the first filter 468 is pre-adjusted. The seventh embodiment will be explained focusing on the differences from the sixth embodiment. 【0115】In the sixth embodiment, a discrete waveform was input to the first filter 468. Furthermore, the target value (target waveform) of the equalization algorithm in the first filter 468 was the electric field waveform E with the sample phase corrected. ０ However, the first filter 468 received input from the downsampling execution unit 467. As a result, the first filter 468 processed the electric field waveform E ０ A discrete waveform with waveform distortion similar to that of the previous waveform was generated, but without noise. 【0116】 Here, the result of the least squares method, which is an equalization algorithm, is converged, and the electric field waveform E ０ In order for the first filter 468 to output a discrete waveform with waveform distortion similar to that of the first filter 468 to the phase shift removal unit 469, the discrete waveform input to the first filter 468 and the target waveform (electric field waveform E) must be... ０ It is important that they are similar to each other to some extent (see Non-Patent Document 2). 【0117】 However, in reality, the electric field waveform E ０ The first waveform contains waveform distortion, but the discrete waveform generated by the waveform generation unit 462 is an ideal waveform and therefore does not contain waveform distortion. For this reason, the equalization algorithm may not converge in the first filter 468. In the seventh embodiment, a second filter is provided before the first filter 468. As a preprocessing step, the second filter roughly adjusts the discrete waveform input to the first filter 468 so that the waveform distortion of the discrete waveform input to the first filter 468 resembles the waveform distortion of the target waveform. 【0118】 Figure 29 shows an example of the configuration of the correction unit 46b in the seventh embodiment. The correction unit 46b comprises a code sequence output unit 461, a waveform generation unit 462, an upsampling execution unit 463, a downsampling execution unit 464, an upsampling execution unit 465, a sample phase correction unit 466, a downsampling execution unit 467, a first filter 468, a phase shift removal unit 469, an acquisition unit 470, a coefficient determination unit 471, and a second filter 472. 【0119】 The acquisition unit 470 generates the electric field waveform E ０The parameters related to the waveform distortion of the (training signal) (for example, parameters related to the signal bandwidth of the user device 2) are acquired. The coefficient determination unit 471 determines the electric field waveform E ０ Based on the waveform distortion parameters it possesses, the tap coefficients of the second filter 472 are determined. For example, the coefficient determination unit 471 determines that the waveform distortion of the discrete waveform output from the second filter 472 is the electric field waveform E ０ The tap coefficients of the second filter 472 are determined to resemble the waveform distortion of the first filter. The second filter 472 processes the electric field waveform E ０ A discrete waveform with waveform distortion similar to that of the first filter is input to the first filter 468. Here, the sample phase of the discrete waveform input to the first filter 468 must be known. For this reason, it is desirable that the second filter 472 does not delay the sample phase of the discrete waveform input to the first filter 468 too much. 【0120】 As described above, the correction unit 46b corrects the electric field waveform E ０ Based on the waveform distortion parameters it possesses, a discrete waveform with a predetermined sample phase is adjusted. Here, the acquisition unit 470 acquires the electric field waveform E ０ The parameters related to the waveform distortion of the (training signal) are acquired. The coefficient determination unit 471 determines the electric field waveform E ０ The tap coefficients of the second filter 472 are determined based on the waveform distortion parameters of the second filter 472. The second filter 472 processes the electric field waveform E ０ A discrete waveform with waveform distortion similar to that of the first filter 468 is input to the first filter 468. 【0121】 This makes it possible to extract the characteristic features of the electric field waveform of an optical signal solely from that electric field waveform. It is possible to suppress the complexity of the configuration of the communication system 1. It is possible to suppress an increase in the cost and power consumption of the communication system 1. Furthermore, it is possible to improve the accuracy of the estimation unit 43's estimation of transmission quality based on the electric field waveform (electric field waveform including waveform distortion, sample phase shift, and noise) measured by the measuring instrument 32 (actual device). 【0122】By the second filter 472 performing coarse adjustment of the discrete waveform input to the first filter 468, the difference between the discrete waveform input to the first filter 468 and the target waveform is reduced. As a result, since the equalization algorithm of the first filter 468 converges, the first filter 468 has an electric field waveform E ０ It is possible to generate a discrete waveform having a waveform distortion similar to the waveform distortion of the electric field waveform E 【0123】 (Eighth Embodiment) In the eighth embodiment, the main difference from the sixth and seventh embodiments is that the noise included in the electric field waveform E ０ input from the measuring instrument 32 is so small that it can be ignored. In the eighth embodiment, the description will be centered on the differences from the sixth and seventh embodiments 【0124】 In the sixth and seventh embodiments, it is assumed that the noise of the electric field waveform E ０ (training signal) is large, and the first filter 468 performs a filtering process so that the large noise is removed in the discrete waveform output from the first filter 468. However, when the noise included in the electric field waveform E ０ is so small that it can be ignored, the electric field waveform E ０ with the sample phase corrected may be input to the extraction unit 41 without the noise being removed. Therefore, in the eighth embodiment, the electric field waveform E ０ with the sample phase corrected is input to the extraction unit 41 as at least an electric field waveform (corrected electric field waveform E ｏｕｔ ) with the sample phase shift corrected 【0125】 FIG. 30 is a diagram showing a configuration example of the correction unit 46c in the eighth embodiment. The correction unit 46c includes a code sequence output unit 461, a waveform generation unit 462, an upsampling execution unit 463, a downsampling execution unit 464, an upsampling execution unit 465, a sample phase correction unit 466, and a downsampling execution unit 467 【0126】 The upsampling execution unit 465 performs upsampling on the electric field waveform E ０ That is, the upsampling execution unit 465 performs upsampling on the electric field waveform E０ Increase the sampling rate. Based on the cross-correlation between the discrete waveform after upsampling and the electric field waveform E after upsampling, perform symbol synchronization processing with the granularity of the sampling phase. The downsampling execution unit 467 adjusts the sampling rate of the electric field waveform E upsampled by the upsampling execution unit 465 so that it becomes the sampling rate and sample phase assumed in the learned model. ０ ０ Decrease the sampling rate. The downsampling execution unit 467 inputs the electric field waveform E after downsampling to the extraction unit 41. ０ 【0127】 As described above, the correction unit 46c acquires the electric field waveform E before being input to the preprocessing unit provided in the extraction unit 41 from the measuring instrument 32. The correction unit 46a inputs the electric field waveform (corrected electric field waveform E) in which at least the sample phase shift among the sample phase shift and noise is corrected to the preprocessing unit provided in the extraction unit 41. ０ ｏｕｔ 【0128】 Here, perform upsampling on the electric field waveform E input from the measuring instrument 32. The sample phase correction unit 466 corrects the sample phase shift of the electric field waveform E based on the cross-correlation with a discrete waveform having a predetermined sample phase (discrete waveform based on a symbol sequence (training signal)). The downsampling execution unit 467 performs downsampling on the electric field waveform E with the sample phase shift corrected. The downsampling execution unit 467 inputs the electric field waveform E after this downsampling as the corrected electric field waveform E to the extraction unit 41. ０ ０ ０ ０ ｏｕｔ 【0129】This makes it possible to extract the characteristic features of the electric field waveform of an optical signal solely from that electric field waveform. It is possible to suppress the complexity of the configuration of the communication system 1. It is possible to suppress an increase in the cost and power consumption of the communication system 1. Furthermore, it is possible to improve the accuracy of the estimation unit 43's estimation of transmission quality based on the electric field waveform (an electric field waveform including waveform distortion, sample phase shift, and negligibly small noise) measured by the measuring instrument 32 (actual device). 【0130】 (Modification of the Eighth Embodiment) In the modification of the eighth embodiment, the main difference from the eighth embodiment is that the code sequence output unit 461 (receiving processing unit) outputs the code sequence of the electric field waveform input from the measuring instrument 32 (transmission code sequence, non-training signal) to the waveform generation unit 462. The modification of the eighth embodiment will be explained focusing on the differences from the eighth embodiment. 【0131】 In each of the embodiments from the sixth to the eighth embodiment, the electric field waveform E ０ This was a training signal whose code sequence (symbol sequence) was known. In a modified example of the eighth embodiment, the electric field waveform E ０ This does not have to be a training signal. 【0132】 Figure 31 shows an example of the configuration of the correction unit 46d in a modified example of the eighth embodiment. The correction unit 46d comprises a code sequence output unit 461, a waveform generation unit 462, an upsampling execution unit 463, a downsampling execution unit 464, an upsampling execution unit 465, a sample phase correction unit 466, and a downsampling execution unit 467. 【0133】 The code sequence output unit 461 outputs the electric field waveform E ０ The electric field waveform E is obtained from the measuring instrument 32. The code sequence output unit 461 outputs the electric field waveform E ０The code sequence (transmitted code sequence) is identified. Here, the code sequence output unit 461 may perform waveform equalization processing using, for example, an FIR filter. Also, if the signal used in the communication system 1 is a phase-modulated signal (for example, quadruple-phase shift modulation), the code sequence output unit 461 may perform processing such as carrier frequency offset compensation and carrier phase recovery. The code sequence output unit 461 inputs the identified code sequence to the waveform generation unit 462. 【0134】 The waveform generation unit 462 generates discrete electric field waveforms (discrete waveforms) based on the identified code sequence. In this case, the electric field waveform E input to the code sequence output unit 461 ０ Even if it is not a training signal, the electric field waveform E input to the sample phase correction unit 466 from the upsampling execution unit 465 ０ As a result, the discrete waveform input to the sample phase correction unit 466 from the upsampling execution unit 463 becomes a waveform generated based on the same code sequence. Therefore, it becomes possible to synchronize the sample phase based on the cross-correlation of each waveform input to the sample phase correction unit 466. 【0135】 In addition, in the sixth and seventh embodiments, similar to the modification in the eighth embodiment, each code sequence output unit 461 outputs an electric field waveform E ０ When outputting a code sequence to the waveform generation unit 462 based on this, the electric field waveform E ０ This does not necessarily have to be a training signal. 【0136】 As described above, the code sequence output unit 461 outputs the electric field waveform E input from the measuring instrument 32. ０ The (non-training signal) is acquired. The code sequence output unit 461 outputs the electric field waveform E ０ The code sequence (transmitted code sequence) is identified. The waveform generation unit 462 generates a discrete waveform with a predetermined sample phase based on the code sequence identified by the waveform generation unit 462. 【0137】This makes it possible to extract the characteristic features of the electric field waveform of an optical signal solely from that electric field waveform. It is possible to suppress the complexity of the configuration of the communication system 1. It is possible to suppress an increase in the cost and power consumption of the communication system 1. Furthermore, it is possible to improve the accuracy of the estimation unit 43's estimation of transmission quality based on the electric field waveform (an electric field waveform including waveform distortion, sample phase shift, and negligibly small noise) measured by the measuring instrument 32 (actual device). 【0138】 (Ninth Embodiment) In the ninth embodiment, the sample frequency shift corresponding to the difference between the clock of the user device 2 and the clock of the measuring instrument 32 is measured in the electric field waveform E ０ The points that arise in this are the main differences between the ninth embodiment and the sixth to eighth embodiments. The ninth embodiment will be explained focusing on the differences from the sixth to eighth embodiments. 【0139】 In each of the embodiments from the sixth to the eighth embodiment, the electric field waveform E ０ It was assumed that no sample frequency shift occurred in this case. In contrast, for example, the electric field waveform E obtained from measuring instrument 32 (actual device) ０ In this case, a sample frequency shift may occur depending on the difference between the clock of the user device 2 (transmitter) and the clock of the measuring instrument 32. Therefore, in the ninth embodiment, the electric field waveform E with a sample frequency shift is ０ A method for correcting the sample phase will be explained below. 【0140】 Figure 32 shows an example configuration of the communication system 1 in the ninth embodiment. The control device 4 includes an extraction unit 41, a candidate output unit 42, an estimation unit 43, a determination unit 44, a communication interface 45, a correction unit 46e, a first buffer 47, and a second buffer 48. The optical node 5 includes a communication interface 51 and an optical switch 52. 【0141】 Figure 33 shows the electric field waveform E with sample frequency shift in the ninth embodiment. ０ This figure shows an example of sample phase correction for the electric field waveform E. ０ If the sample frequency shift is included, the electric field waveform E０ As illustrated in Figure 25, the sample phase in this case changes over time. In contrast, in electric field waveforms divided into predetermined short time intervals, the sample phase remains constant and does not change over time. 【0142】 Therefore, the first buffer 47 receives the electric field waveform E input from the measuring instrument 32 at a short time interval such that the change in sample phase is negligible. ０ The electric field waveform E is divided. For example, the first buffer 47 divides the electric field waveform E into a first time electric field waveform, a second time electric field waveform, and a third time electric field waveform. ０ The divided electric field waveform E is divided. The correction unit 46e corrects the divided electric field waveform E ０ For each case, the electric field waveform (corrected electric field waveform E) is corrected for at least the sample phase shift, which is the difference between the sample phase shift and the noise. ｏｕｔ The following is input into the second buffer 48. 【0143】 The second buffer 48 corrects the sample phase shift of the electric field waveform (corrected electric field waveform E ｏｕｔ The correction unit 46e acquires the corrected electric field waveform (corrected electric field waveform E) for each divided corrected electric field waveform. The second buffer 48 combines the divided electric field waveforms in the time domain to obtain an electric field waveform (corrected electric field waveform E) in which at least the sample phase shift has been corrected. ｏｕｔ The second buffer 48 inputs the electric field waveform, with the sample phase shift corrected, to the preprocessing unit provided in the extraction unit 41. 【0144】 As described above, the first buffer 47 receives the electric field waveform E input from the measuring instrument 32 at predetermined short time intervals. ０ The first buffer 47 inputs each divided electric field waveform (short-time electric field waveform) to the correction unit 46e. The second buffer 48 obtains an electric field waveform corrected for at least the sample phase shift (first sample phase shift) from the correction unit 46e for each divided electric field waveform. The second buffer 48 reconstructs an electric field waveform corrected for at least the sample phase shift by combining the divided electric field waveforms in the time domain. The second buffer 48 obtains an electric field waveform corrected for at least the sample phase shift (corrected electric field waveform E ｏｕｔ The output is input to the preprocessing unit provided in the extraction unit 41. 【0145】 This makes it possible to extract the characteristic features of the electric field waveform of an optical signal solely from that electric field waveform. It is possible to suppress the complexity of the configuration of the communication system 1. It is possible to suppress an increase in the cost and power consumption of the communication system 1. Furthermore, it is possible to improve the accuracy of the estimation unit 43's estimation of transmission quality based on the electric field waveform (electric field waveform including waveform distortion, sample phase shift, noise, and sample frequency shift) measured by the measuring instrument 32 (actual device). 【0146】 (Tenth Embodiment) In the tenth embodiment, the main difference from the sixth to ninth embodiments is that the field waveform of the optical signal includes polarization shift and frequency offset. The tenth embodiment will be explained focusing on the differences from the sixth to ninth embodiments. 【0147】 Figure 34 shows an example of the configuration of the communication system 1 in the tenth embodiment. The control device 4 includes an extraction unit 41, a candidate output unit 42, an estimation unit 43, a determination unit 44, a communication interface 45, a correction unit 46f, a polarization compensation unit 49, and an offset compensation unit 50. 【0148】 Figure 35 shows an example of frequency offset compensation in the tenth embodiment. The polarization compensation unit 49 processes the electric field waveform E before it is input to the preprocessing unit provided in the extraction unit 41. ０ It compensates for the polarization state shift. The offset compensation unit 50 also compensates for the electric field waveform E before it is input to the preprocessing unit provided in the extraction unit 41. ０ The frequency offset of the (baseband signal) is compensated. In Figure 35, the offset compensation unit 50 compensates for the polarization state shift of the electric field waveform E. ０ This compensates for the frequency offset. 【0149】 As described above, the correction unit 46f is provided before the extraction unit 41. The polarization compensation unit 49 and the offset compensation unit 50 are provided, for example, before the correction unit 46f. The polarization compensation unit 49 processes the electric field waveform E before it is input to the preprocessing unit provided in the extraction unit 41. ０The offset compensation unit 50 compensates for the polarization state shift of the electric field waveform E before it is input to the preprocessing unit. ０ The frequency offset is compensated. The correction unit 46f corrects the field waveform E, which has the polarization state shift and frequency offset compensated for. ０ Obtain it. 【0150】 This makes it possible to extract the characteristic features of the electric field waveform of an optical signal solely from that electric field waveform. It is possible to suppress the complexity of the configuration of the communication system 1. It is possible to suppress an increase in the cost and power consumption of the communication system 1. Furthermore, it is possible to improve the accuracy of the estimation unit 43's estimation of transmission quality based on the electric field waveform (electric field waveform including waveform distortion, sample phase shift, noise, polarization state shift, and frequency offset) measured by the measuring instrument 32 (actual device). 【0151】 (Eleventh Embodiment) In the eleventh embodiment, the main difference from the sixth to tenth embodiments is that noise is added to the electric field waveform input to the extraction unit 41. The tenth embodiment will be explained focusing on the differences from the sixth to tenth embodiments. 【0152】 In each of the embodiments from the sixth to the tenth embodiment, the sample phase is corrected for the electric field waveform E ０ Noise is removed from the noise-free electric field waveform E. ０ Corrected electric field waveform E ｏｕｔ This was input to the extraction unit 41. In contrast, in the training stage of the trained model provided in the estimation unit 43, if the trained model is generated using features extracted from a waveform containing predetermined noise, a corrected electric field waveform E containing noise is input, similar to the training stage. ｏｕｔ This needs to be input to the extraction unit 41. 【0153】 Figure 36 shows an example of the configuration of the communication system 1 in the 11th embodiment. The control device 4 includes an extraction unit 41, a candidate output unit 42, an estimation unit 43, a determination unit 44, a communication interface 45, a correction unit 46g, and a noise addition unit 53. 【0154】The noise-adding unit 53 acquires the electric field waveform with the sample phase shift corrected from the correction unit 46g. The noise-adding unit 53 adds noise similar to the noise in the electric field waveform used for training the trained model provided in the estimation unit 43 to the electric field waveform E with the sample phase shift corrected. ０ For example, the noise addition unit 53 adds the same amount of noise as the amount of noise in the electric field waveform used for training the trained model to the electric field waveform E with the sample phase shift corrected. ０ The noise addition unit 53 adds noise to the electric field waveform E after the sample phase shift has been corrected. ０ Corrected electric field waveform E ｏｕｔ This is then input to the extraction unit 41. 【0155】 As described above, the noise addition unit 53 adds noise (second noise) similar to the noise in the electric field waveform used for training the trained model provided in the estimation unit 43, to the electric field waveform E with the sample phase shift corrected. ０ The noise-adding unit 53 adds noise to the electric field waveform E after the sample phase shift has been corrected. ０ Corrected electric field waveform E ｏｕｔ This is then input to the extraction unit 41. 【0156】 This makes it possible to extract the characteristic features of the electric field waveform of an optical signal solely from that electric field waveform. This makes it possible to suppress the complexity of the configuration of the communication system 1. This makes it possible to suppress an increase in the cost and power consumption of the communication system 1. Furthermore, even when a trained model is trained using characteristic features extracted from an electric field waveform containing predetermined noise (second noise), it is possible to improve the accuracy of the estimation unit 43's estimation of transmission quality based on the electric field waveform measured by the measuring instrument 32 (actual device) (an electric field waveform including waveform distortion, sample phase shift, and noise). 【0157】(Modification of the 11th Embodiment) In the modification of the 11th embodiment, the noise contained in the electric field waveform output from the correction unit is measured, and the electric field waveform including the noise added based on the measured noise is input to the extraction unit 41. This is the main difference from the 8th embodiment and the 11th embodiment. The modifications of the 8th embodiment and the 11th embodiment will be explained focusing on the differences from the 11th embodiment. 【0158】 Figure 37 shows an example of the configuration of the communication system 1 in a modified version of the 11th embodiment. The control device 4 includes an extraction unit 41, a candidate output unit 42, an estimation unit 43, a determination unit 44, a communication interface 45, a correction unit 46g, a noise addition unit 53, and a noise measurement unit 54. 【0159】 The noise measurement unit 54 measures the electric field waveform E after correcting the sample phase shift. ０ This is obtained from the correction unit 46h. The noise measurement unit 54 obtains the electric field waveform E with the sample phase shift corrected. ０ Measure the amount of noise contained within. 【0160】 The noise addition unit 53 uses the noise intensity in the electric field waveform used for training the trained model provided in the estimation unit 43 and the corrected electric field waveform E ｏｕｔ Compare the amount of noise contained in the corrected electric field waveform E with the amount of noise in the electric field waveform used to train the trained model. ｏｕｔ If the amount of noise included is insufficient, the noise addition unit 53 adds the insufficient amount of noise to the electric field waveform with the sample phase shift corrected (corrected electric field waveform E ｏｕｔ ) is granted to. 【0161】 As described above, the noise measurement unit 54 measures the electric field waveform E with the sample phase shift corrected. ０ The amount of noise contained in the electric field waveform E is measured. ０ If the amount of noise contained is insufficient, the noise addition unit 53 adds the insufficient amount of noise (second noise) to the electric field waveform E with the sample phase shift corrected. ０ To grant it. 【0162】This makes it possible to extract the characteristic features of the electric field waveform of an optical signal solely from that electric field waveform. This makes it possible to suppress the complexity of the configuration of the communication system 1. This makes it possible to suppress an increase in the cost and power consumption of the communication system 1. Furthermore, even when a trained model is trained using characteristic features extracted from an electric field waveform containing predetermined noise, it is possible to improve the accuracy of the estimation unit 43's estimation of transmission quality based on the electric field waveform measured by the measuring instrument 32 (actual device) (an electric field waveform including waveform distortion, sample phase shift, and noise). 【0163】 (Hardware Configuration) Figure 38 shows an example of the hardware configuration of the control device 4 in each embodiment. The control device 4 is implemented as software by a processor 11 such as a CPU (Central Processing Unit) executing a program stored in a storage device 12 having a non-volatile recording medium (non-temporary recording medium) and a memory 13. The program may be recorded on a computer-readable recording medium. A computer-readable recording medium is a non-temporary recording medium such as a portable medium such as a flexible disk, magneto-optical disk, ROM (Read Only Memory), CD-ROM (Compact Disc Read Only Memory), or a storage device such as a hard disk or solid-state drive (SSD) built into a computer system. The communication unit 14 performs predetermined communication processing. 【0164】 The control device 4 may be implemented via hardware including an electronic circuit (or circuitry) using, for example, an LSI (Large Scale Integrated Circuit), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array). 【0165】Although embodiments of this invention have been described in detail above with reference to the drawings, the specific configuration is not limited to these embodiments and includes designs and the like that do not depart from the spirit of this invention. Furthermore, each embodiment may be combined. 【0166】 This invention is applicable to optical communication systems. 【0167】 1...Communication system, 2...User device, 3...Optical node, 4...Control device, 5...Optical node, 6...User device, 7...Optical transmission line, 8...Poincaré sphere, 10...Learning system, 20...Generator, 30...Learning device, 31...Splitter, 32...Measuring instrument, 33...Communication interface, 34...Optical switch, 41, 41a, 41b, 41c, 41d, 41e...Extraction unit, 42...Candidate output unit, 43...Estimation unit, 44...Decision unit, 45...Communication interface, 46a, 46b, 46c, 46d, 46e, 46f, 46g, 46h...Correction unit, 47...First buffer, 48...Second buffer, 49...Polarization compensation unit, 50...Offset compensation unit, 51...Communication interface, 52...Optical switch, 53...Noise-equipped 54...Noise measurement unit, 100...Intensity waveform, 101...Trajectory, 102...Trajectory, 103...Trajectory, 104...Trajectory, 201...Characteristic information generation unit, 301...Storage device, 302...Learning unit, 411a, 411b, 411c, 411d, 411e...Preprocessing unit, 412...Distribution processing unit, 413...Normalization unit, 414...Reduction unit, 415...Noise unit, 416...Removal unit, 461...Code sequence output unit, 462...Waveform generation unit, 463...Upsampling execution unit, 464...Downsampling execution unit, 465...Upsampling execution unit, 466...Sample phase correction unit, 467...Downsampling execution unit, 468...First filter, 469...Phase shift removal unit, 470...Acquisition unit, 471...Coefficient determination unit

Claims

A preprocessing unit divides the trajectory of a point, determined based on the modulated electric field waveform, into symbol periods, A distribution processing unit generates a frequency distribution of at least one of the points and the trajectory as a feature quantity of the electric field waveform. An extraction device equipped with the following features. 　 The preprocessing unit separates the electric field waveform into at least one of the intensity trajectory, the real component trajectory, and the imaginary component trajectory. The aforementioned points are sample points for the intensity, the real component, or the imaginary component. The extraction apparatus according to claim 1, wherein the trajectory of the point is the time waveform of the sample point. 　 The preprocessing unit separates the electric field waveform into at least the locus of the real component and the locus of the imaginary component from the locus of the intensity, the locus of the real component, and the locus of the imaginary component. The extraction apparatus according to claim 1, wherein the aforementioned point is a sample point defined on the complex plane or Poincaré sphere representing the real component and the imaginary component. 　 The extraction apparatus according to claim 3, wherein the locus of the point is the locus of the sample point in the complex plane or the Poincaré sphere. 　 The extraction apparatus according to claim 3, further comprising a removal unit for removing the phase offset included in the trajectory of the real component and the trajectory of the imaginary component. 　 The extraction apparatus according to claim 1, further comprising a normalization unit for normalizing the aforementioned feature quantities. 　 The extraction device according to claim 1, further comprising a noise unit that performs a process of convolving a predetermined function onto the feature quantity. 　 The extraction apparatus according to claim 1, further comprising a correction unit that acquires the electric field waveform before it is input to the preprocessing unit, and inputs the electric field waveform, in which at least the first sample phase shift of the first sample phase shift and the first noise has been corrected, to the preprocessing unit. 　 The extraction apparatus according to claim 8, wherein the correction unit corrects the first sample phase shift of the electric field waveform based on the cross-correlation with a discrete waveform having a predetermined sample phase. 　 The extraction apparatus according to claim 9, wherein the correction unit transfers the waveform distortion of the electric field waveform, from which the first sample phase shift has been corrected, to the discrete waveform, removes the second sample phase shift that has occurred in the discrete waveform having the transferred waveform distortion, and inputs the discrete waveform from which the second sample phase shift has been removed to the preprocessing unit as the electric field waveform from which the first sample phase shift has been corrected. 　 The extraction apparatus according to claim 10, wherein the correction unit transfers the waveform distortion of the electric field waveform, whose first sample phase shift has been corrected, to the discrete waveform, which has been adjusted based on the parameters relating to the waveform distortion of the electric field waveform. 　 A first buffer divides the electric field waveform at predetermined short time intervals, and inputs each divided electric field waveform to the correction unit. The extraction apparatus according to claim 8, further comprising: a second buffer that acquires, for each divided electric field waveform, an electric field waveform in which at least the first sample phase shift has been corrected from the correction unit, and inputs the electric field waveform in which at least the first sample phase shift has been corrected to the preprocessing unit. 　 A polarization compensation unit that compensates for the deviation in the polarization state of the electric field waveform before it is input to the preprocessing unit, The extraction apparatus according to claim 8, further comprising: an offset compensation unit for compensating for the frequency offset of the electric field waveform before it is input to the preprocessing unit. 　 The extraction apparatus according to claim 8, further comprising a noise application unit that applies a second noise to the electric field waveform, which has been corrected for at least the first sample phase shift, and inputs the electric field waveform to which the second noise has been applied to the preprocessing unit. 　 An extraction method performed by an extraction device, The steps include dividing the trajectory of a point defined based on the modulated electric field waveform into symbol periods, A step of generating a frequency distribution of at least one of the points and the trajectory as a feature quantity of the electric field waveform. An extraction method that includes [a specific method]. 　 The extraction method according to claim 15, further comprising the step of acquiring the electric field waveform before it is input to a preprocessing unit provided in the extraction device that performs the division step, and inputting the electric field waveform, in which at least the first sample phase shift among the first sample phase shift and noise has been corrected, to the preprocessing unit.

Images