Equalization parameter adjusting method, circuit, chip, transceiver and storage system

Abstract

The invention provides an equalization parameter adjusting method and circuit, a chip, a transceiver and a storage system. The method comprises the following steps: acquiring a transmission signal transmitted by a channel; extracting a plurality of equalization features from the transmission signal; determining a required feature set of each equalizer according to the plurality of equalization features, the plurality of channel features of the channel and a current required feature requirement of an equalization network model of at least one equalizer; and predicting a plurality of equalization parameters of each equalizer according to the equalization network model of each equalizer and the corresponding required feature set, and transmitting the plurality of equalization parameters to the corresponding equalizer, so that each equalizer performs signal compensation on the received signal according to the corresponding plurality of equalization parameters.

Description

Technical Field

[0001] The present application relates to the technical field of integrated circuit design, and in particular to a method for adjusting equalization parameters, a circuit, a chip, a transceiver and a storage system. Background Art

[0002] As the rate of information transmission continues to increase, the transmission channel causes a long tail phenomenon, which increasingly attenuates the high-frequency components of the signal and deteriorates the transmission quality of the signal. At the same time, the impact of noise on the quality of signal transmission is becoming increasingly serious. At present, equalization technology has become one of the effective methods to solve this problem. In order to adapt to the characteristics of channel aging and changes in transmission characteristics, adaptive circuits have become an indispensable part of equalization technology. They can effectively track channel changes to compensate for high-frequency attenuated signals in real time. However, as the tail of the channel increases, more and more equalization parameters need to be adaptively adjusted by adaptive circuits. Since traditional adaptive circuits only support the adjustment of one equalization parameter at a time, multiple equalization parameters can only be adjusted by increasing the complexity of the adaptive circuit. However, this method has high complexity and power consumption, and cannot meet the power and performance requirements of applications such as high-performance computing processors, high-performance AI (Artificial Intelligence) computing, the Internet of Things, and wireless edge. Therefore, how to adaptively adjust multiple equalization parameters without sacrificing performance has become an urgent problem to be solved. Summary of the invention

[0003] In order to solve the above-mentioned technical problems, the embodiments of the present application creatively provide a method, circuit, chip, transceiver and storage system for adjusting equalization parameters.

[0004] According to a first aspect of the present application, a method for adjusting an equalization parameter is provided, the method comprising: Acquire a transmission signal transmitted by a channel; extracting a plurality of equalization features from the transmission signal; determining a required feature set for each equalizer based on the plurality of equalization features, the plurality of channel features of the channels, and current required feature requirements of an equalization network model of at least one equalizer; According to the equalization network model of each equalizer and the corresponding required feature set, multiple equalization parameters of each equalizer are predicted, and the multiple equalization parameters are transmitted to the corresponding equalizer, so that each equalizer performs signal compensation on the received signal according to the corresponding multiple equalization parameters.

[0005] According to an embodiment of the present application, the method further includes: Acquire multiple pulse signals transmitted sequentially by the channel; A plurality of channel characteristics of the channel are obtained from the plurality of pulse signals.

[0006] According to an embodiment of the present application, the at least one equalizer includes a first equalizer and a second equalizer, and the multiple equalization parameters of the second equalizer include multiple first set equalization parameters and multiple second set equalization parameters; accordingly, predicting the multiple equalization parameters of each equalizer according to the equalization network model of each equalizer and the corresponding required feature set includes: Predicting a plurality of equalization parameters of the first equalizer according to the equalization network model of the first equalizer and the corresponding required feature set; predicting a plurality of first set equalization parameters of the second equalizer according to the equalization network model of the second equalizer and the corresponding required feature set; A plurality of second set equalization parameters of the second equalizer are predicted according to the adaptive parameter adjustment circuit of the second equalizer.

[0007] According to an embodiment of the present application, each equalizer performs signal compensation on a received signal according to corresponding multiple equalization parameters, including: The first equalizer receives the transmission signal transmitted by the channel, and uses the corresponding multiple equalization parameters to perform signal compensation on the transmission signal to obtain a first compensated signal; The second equalizer receives the first compensation signal, and uses the corresponding multiple equalization parameters to perform signal compensation on the first compensation signal to obtain a second compensation signal.

[0008] According to an embodiment of the present application, the equalization network models of the first equalizer and the second equalizer are trained in the following manner: Acquire multiple training pulse signals transmitted sequentially by the channel, extract multiple training features from the multiple training pulse signals, and store the multiple training features in a mutual information library; Acquire a training transmission signal transmitted by a channel, and acquire a training output signal after being compensated by a first equalizer and a second equalizer signal; extracting a plurality of training equalization features from the training transmission signal; Training the equalization network model of the first equalizer according to the feature optimization mechanism, the plurality of training features, the plurality of training equalization features, the training output signal, the plurality of current equalization parameters of the first equalizer, and the required feature requirements of the first equalizer; Training the equalization network model of the second equalizer according to the feature optimization mechanism, the plurality of training features, the plurality of training equalization features, the training output signal, the plurality of current equalization parameters of the second equalizer, and the required feature requirements of the second equalizer; The balanced network model includes the currently required characteristic requirements of the balanced network model.

[0009] According to an embodiment of the present application, the feature optimization mechanism includes: Randomly select a random feature from the multiple training features and the multiple training balanced features, and gradually increase the number of random features to train the balanced network model through the scoreboard until the parameter accuracy of the balanced network model is no greater than a set threshold and the number of the random features reaches a set condition or the number of random features reaches a maximum; The setting condition is that the number of random features is the minimum when the parameter accuracy of the balanced network model is not greater than a set threshold.

[0010] According to an embodiment of the present application, randomly selecting a random feature from the multiple training features and the multiple training balanced features, and gradually increasing the number of random features through a scoreboard to train the balanced network model until the parameter accuracy of the balanced network model is no greater than a set threshold and the number of random features reaches a set condition or the number of random features reaches a maximum, includes: Randomly select a random feature from the multiple training features and the multiple training balanced features; Based on the random features and the current balanced network model, determining the parameter accuracy of the current balanced network model; When the parameter accuracy is not greater than the set threshold, determine whether the random feature is a minimum feature set. If it is a minimum feature set, store the random feature directly in the mutual information library. If it is not a minimum feature set, perform feature clipping and retrain the balanced network model based on the scoreboard. When the parameter accuracy is greater than the set threshold, determine whether the random feature is the maximum feature set; In the case where the feature set is not the maximum, the number of random features is increased, and the balanced network model is trained based on the scoreboard until the parameter accuracy of the balanced network model is not greater than the set threshold and the number of random features reaches the set condition or the number of random features reaches the maximum, and the current multiple random features are stored in the mutual information library as the current required feature requirements of the balanced network model; When the random features are the largest feature set, stop training the balanced network model and store the current random features in the mutual information library as the current required feature requirements of the balanced network model.

[0011] According to an embodiment of the present application, the first equalizer is a continuous time linear equalizer, and the second equalizer is a decision feedback equalizer.

[0012] According to one embodiment of the present application, the multiple training pulse signals include a single-bit response and a long pulse response, the training transmission signal is a pseudo-random sequence, the multiple training features include low-frequency gain, high-frequency gain and high-frequency range, and the multiple training equalization features include eye width and eye height.

[0013] According to an embodiment of the present application, the multiple equalization parameters of the first equalizer include a high-frequency gain, a zero point, a first pole, and a second pole, and the multiple equalization parameters of the second equalizer include a plurality of tap coefficients.

[0014] According to a second aspect of the present application, there is provided an equalization circuit, the equalization circuit comprising: A channel, connected to the signal sending end, for receiving a transmission signal from the signal sending end and transmitting it; at least one equalizer connected to the channel; An equalizer adjustment device is connected to at least one equalizer and is used to obtain a transmission signal transmitted by a channel; extract multiple equalization features from the transmission signal; determine the required feature set of each equalizer based on the multiple equalization features, multiple channel features of the channel and the current required feature requirements of the equalization network model of at least one equalizer; predict multiple equalization parameters of each equalizer based on the equalization network model of each equalizer and the corresponding required feature set, and transmit the multiple equalization parameters to the corresponding equalizer so that each equalizer performs signal compensation on the received signal according to the corresponding multiple equalization parameters.

[0015] According to an embodiment of the present application, the equalization circuit further includes: The adaptive parameter adjustment circuit is connected to one of the equalizers and is used to adjust the corresponding equalization parameters of the connected equalizer.

[0016] According to a third aspect of the present application, a balancing chip is provided, comprising the above-mentioned balancing circuit.

[0017] According to a fourth aspect of the present application, a transceiver is provided, comprising the above-mentioned equalization chip.

[0018] According to a fifth aspect of the present application, a storage system is provided, comprising the above-mentioned transceiver.

[0019] According to the sixth aspect of the present application, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the above-mentioned methods for adjusting the equalization parameters of the present application.

[0020] According to a seventh aspect of the present application, a computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any of the above-mentioned methods for adjusting the equalization parameters of the present application.

[0021] The embodiments of the present application provide a method, circuit, chip, transceiver and storage system for adjusting equalization parameters, which obtain a transmission signal transmitted by a channel; extract multiple equalization features from the transmission signal; determine the required feature set of each equalizer based on the multiple equalization features, multiple channel features of the channel and the current required feature requirements of the equalization network model of at least one equalizer; predict multiple equalization parameters of each equalizer based on the equalization network model of each equalizer and the corresponding required feature set, and transmit the multiple equalization parameters to the corresponding equalizer, so that each equalizer performs signal compensation on the received signal according to the corresponding multiple equalization parameters. By using the equalization network model based on deep learning to adapt the equalizer, the simultaneous adjustment of multiple equalization parameters is achieved while avoiding increased power consumption, thereby improving signal transmission performance.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become readily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, wherein: In the drawings, the same or corresponding reference numerals represent the same or corresponding parts.

[0024] Figure 1 A schematic diagram of the structure of the equalization circuit provided in an embodiment of the present application is shown; Figure 2 A schematic diagram of the implementation flow of the method for adjusting the equalization parameters provided in an embodiment of the present application is shown; Figure 3 A schematic diagram of the implementation flow of the equalization parameter prediction operation of the equalization parameter adjustment method provided in an embodiment of the present application is shown; Figure 4 A schematic diagram showing the implementation flow of the signal compensation operation of the equalization parameter adjustment method provided in an embodiment of the present application is shown; Figure 5 A schematic diagram of the implementation flow of the equalization network model training operation of the equalization parameter adjustment method provided in an embodiment of the present application is shown; Figure 6 A schematic diagram showing the operation flow of the feature optimization mechanism of the equalization parameter adjustment method provided in an embodiment of the present application is shown; Figure 7 A training architecture diagram showing a specific application example of the equalization network model training of the equalization parameter adjustment method provided in an embodiment of the present application; Figure 8 A schematic diagram of the composition structure of a specific application example of the equalization circuit provided in an embodiment of the present application is shown; Fig. 9 A schematic diagram of the structure of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] In order to make the purpose, features, and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0026] The technical solution of the present application is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0027] First, the application scenario of the embodiment of the present application is described. When a signal is transmitted through a channel, it is often affected by channel characteristics (such as frequency selective fading, delay spread, multipath effect, etc.), resulting in signal distortion and interference. In order to overcome these unfavorable factors and improve the quality and reliability of signal transmission, an equalizer is needed to compensate for the signal transmitted through the channel. The working principle of the equalizer is to compensate the signal based on its own equalization parameters. Since channel characteristics often vary with time, frequency and spatial position, it is usually necessary to adaptively adjust the equalizer, that is, adaptively adjust the equalization parameters of the equalizer.

[0028] Traditional equalization parameter adjustment is generally based on adaptive circuits, and equalizer adaptation is achieved through conventional algorithms or methods built into adaptive circuits. For example, the adaptive circuit of CTLE (Continuous Time Linear Equalizer) usually uses signal slope detection and other methods to automatically adjust the equalization coefficient of CTLE, and the adaptive circuit of DFE usually uses LMS (Learning Management System) algorithm to automatically adjust the equalization coefficient of DFE (Decision Feedback Equalizer), but traditional adaptive circuits cannot adjust multiple equalization parameters at the same time. Therefore, in order to solve the above problems, the embodiments of the present application provide an adjustment method, circuit, chip, transceiver and storage system for equalization parameters.

[0029] Figure 1 A schematic diagram of the structure of the equalization circuit provided in an embodiment of the present application is shown.

[0030] The method for adjusting the equalization parameters in the embodiment of the present application is based on Figure 1 The equalization circuit shown is implemented as shown. Figure 1 The equalization circuit of the embodiment of the present application includes a channel, at least one equalizer, and an equalizer adjustment device connected to the equalizer.

[0031] The channel is connected to the signal sending end, and the channel can receive and transmit the transmission signal of the signal sending end.

[0032] In order to compensate the transmission signal transmitted by the channel, the equalization circuit is configured with at least one equalizer to perform signal compensation on the transmission signal based on the equalizer.

[0033] The equalizer adjustment device is connected to the equalizer and is used to realize the self-adaptation of the equalizer, that is, to adaptively adjust the multiple equalization parameters of the equalizer. The equalizer adjustment device is configured to execute the equalization parameter adjustment method of the embodiment of the present application, that is, the equalizer adjustment device is used to obtain the transmission signal transmitted by the channel; extract multiple equalization features from the transmission signal; determine the required feature set of each equalizer according to the multiple equalization features, multiple channel features of the channel and the current required feature requirements of the equalization network model of at least one equalizer; predict multiple equalization parameters of each equalizer according to the equalization network model of each equalizer and the corresponding required feature set, and transmit the multiple equalization parameters to the corresponding equalizer, so that each equalizer performs signal compensation on the received signal according to the corresponding multiple equalization parameters.

[0034] In one embodiment of the present application, in order to more accurately adapt the equalizer, an adaptive parameter adjustment circuit may be configured for one of the equalizers, so as to adjust the equalization parameters of the equalizer in combination with the adaptive parameter adjustment circuit and the equalization network model. The adaptive parameter adjustment circuit is configured in the equalizer adjustment device as a part of the equalizer adjustment device.

[0035] Figure 2 A schematic diagram of the implementation flow of the method for adjusting the equalization parameters provided in an embodiment of the present application is shown.

[0036] refer to Figure 2, an embodiment of the present application provides a method for adjusting equalization parameters, which at least includes: operation 101, obtaining a transmission signal transmitted by a channel; operation 102, extracting multiple equalization features from the transmission signal; operation 103, determining a required feature set for each equalizer based on multiple equalization features, multiple channel features of a channel, and current required feature requirements of an equalization network model of at least one equalizer; operation 104, predicting multiple equalization parameters of each equalizer based on the equalization network model of each equalizer and the corresponding required feature set, and transmitting the multiple equalization parameters to the corresponding equalizer, so that each equalizer performs signal compensation on the received signal according to the corresponding multiple equalization parameters.

[0037] In operation 101, a transmission signal transmitted by a channel is acquired.

[0038] After the signal sending end connected to the channel sends a transmission signal, the channel receives the transmission signal and transmits it.

[0039] In operation 102, a plurality of equalization features are extracted from a transmission signal.

[0040] After the signal is transmitted through the channel, it is affected by the channel characteristics and its quality is degraded. Therefore, it is necessary to analyze and process the transmitted signal to extract multiple equalization features to provide a basis for subsequent signal compensation. Among them, equalization features refer to features that can reflect the interference and attenuation of the transmission signal during the channel transmission process, such as eye height, eye width, etc.

[0041] Among them, the eye height refers to the size of the eye diagram on the vertical axis (usually the amplitude axis), which reflects the amplitude stability of the signal during transmission and is closely related to the signal-to-noise ratio. On the eye diagram, the larger the eye height, the more stable the signal amplitude and the less affected by noise and interference. The eye width refers to the size of the eye diagram on the horizontal axis (usually the time axis), which reflects the total jitter of the signal, that is, the temporal instability of the signal during transmission. The larger the eye width, the more uniform the time interval of the signal and the smaller the jitter.

[0042] In operation 103, a required feature set for each equalizer is determined based on a plurality of equalization features, a plurality of channel features of the channel, and current required feature requirements of an equalization network model of at least one equalizer.

[0043] In one embodiment of the present application, multiple channel characteristics of a channel are extracted in advance, specifically including: obtaining multiple pulse signals transmitted sequentially by the channel; and obtaining multiple channel characteristics of the channel from the multiple pulse signals.

[0044] Among them, acquiring multiple pulse signals transmitted sequentially by the channel can be regarded as sending a pulse signal acquisition instruction to the signal sending end connected to the channel, so that the signal sending end sends a pulse signal to the channel in response to the pulse signal acquisition instruction. Among them, when sending the acquisition instruction, the requirement of sending the pulse signal can be synchronously sent, so that the signal sending end sends a pulse signal with specific waveform, frequency and phase characteristics.

[0045] After a series of pulse signals pass through the channel, pulse signals that introduce channel distortion and interference characteristics can be obtained. By analyzing and extracting features from these pulse signals, multiple channel features representing channel characteristics can be obtained, such as low-frequency gain, high-frequency gain, high-frequency range, etc.

[0046] The equalizer adjustment device has trained an equalizer network model for each equalizer. Since the equalizer network model is continuously iterated and optimized in real time, the equalizer network model also needs to carry the current required feature requirements of the model. The current required feature requirements of the model refer to the input feature type of the model. For example, the current required feature requirements of the equalizer network model can be feature A for the model input.

[0047] In this way, after obtaining multiple equalization features and multiple channel features, features corresponding to currently required feature requirements can be selected from the multiple equalization features and the multiple channel features to obtain a required feature set for the equalizer.

[0048] In one embodiment of the present application, the equalization network model is a deep learning network model, which is pre-trained to have the ability to predict the equalization parameters of the equalizer based on the characteristics of the signal.

[0049] In operation 104, multiple equalization parameters of each equalizer are predicted based on the equalization network model of each equalizer and the corresponding required feature set, and the multiple equalization parameters are transmitted to the corresponding equalizer so that each equalizer performs signal compensation on the received signal according to the corresponding multiple equalization parameters.

[0050] The required feature set of the equalizer is input into its corresponding equalization network model, thereby obtaining multiple equalization parameters of the equalizer.

[0051] After obtaining the multiple equalization parameters, the multiple equalization parameters are transmitted to the corresponding equalizer, so that the equalizer updates its own multiple equalization parameters and performs signal compensation on the received signal based on the updated multiple equalization parameters.

[0052] In this way, the solution of the embodiment of the present application, by using a deep learning-based equalization network model to adapt the equalizer, achieves simultaneous adjustment of multiple equalization parameters while avoiding increased power consumption, thereby improving signal transmission performance.

[0053] Figure 3A schematic diagram of the implementation flow of the equalization parameter prediction operation of the equalization parameter adjustment method provided in an embodiment of the present application is shown.

[0054] refer to Figure 3 In one embodiment of the present application, at least one equalizer includes a first equalizer and a second equalizer, and the multiple equalization parameters of the second equalizer include multiple first set equalization parameters and multiple second set equalization parameters; accordingly, based on the equalization network model of each equalizer and the corresponding required feature set, the multiple equalization parameters of each equalizer are predicted, including: operation 201, predicting the multiple equalization parameters of the first equalizer based on the equalization network model of the first equalizer and the corresponding required feature set; operation 202, predicting the multiple first set equalization parameters of the second equalizer based on the equalization network model of the second equalizer and the corresponding required feature set; operation 203, predicting the multiple second set equalization parameters of the second equalizer based on the adaptive parameter adjustment circuit of the second equalizer.

[0055] In one embodiment of the present application, at least one equalizer is two equalizers, including a first equalizer and a second equalizer. The second equalizer is configured with an adaptive parameter adjustment circuit, and the equalization parameters of the second equalizer are configured to be completed based on the equalization network model and the adaptive parameter adjustment circuit. Among them, the multiple equalization parameters that the second equalizer needs to adjust can be divided into multiple first set equalization parameters and multiple second set equalization parameters.

[0056] In operation 201 , a plurality of equalization parameters of the first equalizer are predicted according to an equalization network model of the first equalizer and a corresponding required feature set.

[0057] The multiple equalization parameters of the first equalizer are configured to all be performed using the equalization network model. Therefore, by inputting the required feature set of the first equalizer into the equalization network model, the corresponding multiple equalization parameters can be obtained.

[0058] In operation 202 , a plurality of first set equalization parameters of the second equalizer are predicted according to an equalization network model of the second equalizer and a corresponding required feature set.

[0059] Specifically, the plurality of first set equalization parameters of the second equalizer may continue to be acquired from the corresponding equalization network model, and the required feature set corresponding to the second equalizer is input into the equalization network model to obtain the plurality of first set equalization parameters.

[0060] In operation 203 , a plurality of second set equalization parameters of the second equalizer are predicted according to the adaptive parameter adjustment circuit of the second equalizer.

[0061] The equalizer adjustment device controls the adaptive parameter adjustment circuit to predict the multiple second set equalization parameters of the second equalizer. The process of the adaptive parameter adjustment circuit predicting the multiple second set equalization parameters can refer to the process of the conventional adaptive circuit adaptively adjusting the equalization parameters of the equalizer, for example, predicting the equalization parameters based on some adaptive algorithms (such as recursive least squares method, Kalman filter, etc.) built into the adaptive parameter adjustment circuit, which will not be described in detail here.

[0062] Therefore, the embodiment of the present application achieves the adaptation of the equalizer by cleverly combining the adaptive algorithm and deep learning, eliminating part of the adaptive circuit, reducing complexity and power consumption, improving the adaptive speed, and realizing simultaneous adaptive adjustment of multiple equalization parameters.

[0063] Figure 4 A schematic diagram of the implementation flow of the signal compensation operation of the equalization parameter adjustment method provided in an embodiment of the present application is shown.

[0064] refer to Figure 4 In one embodiment of the present application, each equalizer performs signal compensation on the received signal according to the corresponding multiple equalization parameters, including: operation 301, the first equalizer receives the transmission signal transmitted by the channel, and uses the corresponding multiple equalization parameters to perform signal compensation on the transmission signal to obtain a first compensated signal; operation 302, the second equalizer receives the first compensated signal, and uses the corresponding multiple equalization parameters to perform signal compensation on the first compensated signal to obtain a second compensated signal.

[0065] When there are two equalizers, the two equalizers are usually connected in series to jointly realize compensation for the signal. Therefore, the compensation for the signal by each equalizer in the embodiment of the present application can be divided into compensation by the first equalizer and compensation by the second equalizer. The first equalizer is connected to the channel by default, and the second equalizer is connected in series after the first equalizer by default.

[0066] The first equalizer first receives the transmission signal of the channel, and performs signal compensation on the transmission signal based on the corresponding multiple equalization parameters to obtain a first compensated signal. The first compensated signal then flows into the second equalizer, and the second equalizer compensates the first compensated signal again based on the multiple equalization parameters to obtain a second compensated signal.

[0067] Figure 5 A schematic diagram of the implementation flow of the equalization network model training operation of the equalization parameter adjustment method provided in an embodiment of the present application is shown.

[0068] refer to Figure 5In one embodiment of the present application, the equalization network model of the first equalizer and the second equalizer can be obtained by training the following operations: operation 401, obtaining multiple training pulse signals transmitted sequentially by the channel, extracting multiple training features from the multiple training pulse signals, and storing the multiple training features in a mutual information library; operation 402, obtaining a training transmission signal transmitted by the channel, and obtaining a training output signal after compensation by the first equalizer and the second equalizer signal; operation 403, extracting multiple training equalization features from the training transmission signal; operation 404, training the equalization network model of the first equalizer according to a feature selection mechanism, multiple training features, multiple training equalization features, a training output signal, multiple current equalization parameters of the first equalizer, and the required feature requirements of the first equalizer; operation 405, training the equalization network model of the second equalizer according to a feature selection mechanism, multiple training features, multiple training equalization features, a training output signal, multiple current equalization parameters of the second equalizer, and the required feature requirements of the second equalizer; wherein the equalization network model includes the current required feature requirements of the equalization network model.

[0069] In operation 401, a plurality of training pulse signals sequentially transmitted by a channel are acquired, a plurality of training features are extracted from the plurality of training pulse signals, and the plurality of training features are stored in a mutual information library.

[0070] First, a training pulse signal acquisition instruction is sent to the signal sending end, so that the signal sending end sends multiple training pulse signals to the channel. After the multiple training pulse signals are transmitted through the channel, they already carry the influence of the channel characteristics. At this time, based on the analysis and feature extraction of the multiple pulse signals, multiple training features representing the channel characteristics can be obtained, such as channel attenuation, low-frequency gain or high-frequency gain.

[0071] Among them, the pulse signal is an impulse response, which is mainly used for testing channels.

[0072] After obtaining multiple training features, the training features are stored in a mutual information library for subsequent model training.

[0073] In operation 402, a training transmission signal transmitted by a channel is obtained, and a training output signal after signal compensation by a first equalizer and a second equalizer is obtained.

[0074] After obtaining a plurality of training features of the channel, an actual training transmission signal is obtained from a signal transmitting end, and a training output signal obtained after the training transmission signal passes through an equalizer is obtained.

[0075] In operation 403, a plurality of training equalization features are extracted from a training transmission signal.

[0076] After the training transmission signal is transmitted through the channel, it is affected by the channel characteristics and changes occur in the training transmission signal. A plurality of training equalization features that can represent the influence of the channel characteristics are obtained from the training transmission signal.

[0077] In operation 404, the equalization network model of the first equalizer is trained according to the feature selection mechanism, the plurality of training features, the plurality of training equalization features, the training output signal, the plurality of current equalization parameters of the first equalizer, and the required feature requirements of the first equalizer.

[0078] The equalization parameters of each equalizer are different, and accordingly, the required feature requirements of each equalizer are also different. Among them, the required feature requirements of the equalizer can be regarded as having associated features for adjusting the equalization parameters of the current equalizer, and can be configured according to the actual equalization parameters of the equalizer, which will not be repeated here.

[0079] The training features, training equalization features, current multi-equalization parameters and training output signals are used together as training data of the corresponding equalizer to train the equalization network model of the equalizer to obtain the equalization network model.

[0080] In the process of training the equalizing network model, in addition to considering the required feature requirements of the equalizer, a feature optimization mechanism is also configured to improve the robustness and accuracy of the equalizing network model through the feature optimization mechanism.

[0081] In this embodiment of the present application, the equalizing network model of the first equalizer is trained according to the feature selection mechanism, training features, training equalizing features, training output signals, the current multiple equalizing parameters of the first equalizer, and the feature requirements required by the first equalizer, so that the equalizing network model of the first equalizer has the ability to predict the corresponding multiple equalizing parameters according to any required feature or any combination of features, thereby obtaining the equalizing network model of the first equalizer.

[0082] In one embodiment of the present application, the model architecture of the balanced network model can be a convolutional neural network, a recurrent neural network, etc.

[0083] In operation 405, the equalizing network model of the second equalizer is trained according to the feature selection mechanism, multiple training features, multiple training equalizing features, a training output signal, multiple current equalizing parameters of the second equalizer, and the required feature requirements of the second equalizer; wherein the equalizing network model includes the current required feature requirements of the equalizing network model.

[0084] The equalizing network model of the second equalizer is trained through a feature selection mechanism, multiple training features, multiple training equalizing features, a training output signal, multiple current equalizing parameters of the second equalizer, and the feature requirements required by the second equalizer, so that the equalizing network model of the second equalizer has the ability to predict its corresponding multiple equalizing parameters based on any required feature or any combination of features.

[0085] Among them, since the model training is based on the feature optimization mechanism, after the balanced network model is trained, the balanced network model needs to carry its currently required feature requirements, that is, the feature type of the input of the trained balanced network model.

[0086] In one embodiment of the present application, the feature selection mechanism includes: randomly selecting a random feature from multiple training features and multiple training balanced features, and gradually increasing the number of random features through a scoreboard to train the balanced network model until the parameter accuracy of the balanced network model is no greater than a set threshold and the number of random features reaches a set condition or the number of random features reaches a maximum; wherein the set condition is that the number of random features is the minimum value when the parameter accuracy of the balanced network model is no greater than the set threshold.

[0087] The main purpose of the feature optimization mechanism is to ensure the parameter accuracy of the equalization parameters output by the equalization network model while minimizing the number of input features of the equalization network model to reduce computational complexity and power consumption.

[0088] The feature selection mechanism can be considered as randomly selecting random features from multiple training features and multiple training balanced features, and gradually increasing the number of random features based on the control of the scoreboard until the scoreboard determines that the parameter accuracy of multiple balanced parameters output by the balanced network model reaches the set threshold and the number of random features reaches the set condition or the number of random features reaches the maximum. The set condition is that the number of random features is the minimum value when the parameter accuracy of the balanced network model is not greater than the set threshold.

[0089] In one embodiment of the present application, a parameter threshold is configured for each equalization parameter, and the parameter accuracy of each equalization parameter is the ratio of the equalization parameter to the parameter threshold. The parameter accuracy is used to determine whether the fluctuation range of the equalization parameter is within certain requirements. The fluctuation range requirement of the equalization parameter is the setting threshold of the parameter accuracy, which can be configured according to actual conditions, such as 5%, 6%, etc.

[0090] When the number of random features increases to the maximum, that is, multiple random features are all the features required by the equalizer, no more random features can be added. Therefore, the training of the equalization network model is also considered completed.

[0091] Figure 6A schematic diagram of the operation flow of the feature optimization mechanism of the equalization parameter adjustment method provided in an embodiment of the present application is shown.

[0092] refer to Figure 6 In one embodiment of the present application, a random feature is randomly selected from a plurality of training features and a plurality of training balanced features, and the number of random features is gradually increased through a scoreboard to train the balanced network model until the parameter accuracy of the balanced network model is not greater than a set threshold and the number of random features reaches a set condition or the number of random features reaches a maximum, including: operation 501, randomly selecting a random feature from a plurality of training features and a plurality of training balanced features; operation 502, based on the random feature and the current balanced network model, determining the parameter accuracy of the current balanced network model; operation 503, when the parameter accuracy is not greater than the set threshold, determining whether the random feature is a minimum feature set, if it is a minimum feature set, directly storing the random feature in a mutual information library, if it is not a minimum feature set, Perform feature clipping and retrain the balanced network model based on the scoreboard; Operation 504, when the parameter accuracy is greater than the set threshold, determine whether the random feature is the maximum feature set; Operation 505, when it is not the maximum feature set, increase the number of random features, and train the balanced network model based on the scoreboard until the parameter accuracy of the balanced network model is not greater than the set threshold and the number of random features reaches the set condition or the number of random features reaches the maximum, and store the current multiple random features in the mutual information library as the current required feature requirements of the balanced network model; Operation 506, when the random feature is the maximum feature set, stop training the balanced network model, and store the current random feature in the mutual information library as the current required feature requirements of the balanced network model.

[0093] In operation 501, a random feature is randomly selected from a plurality of training features and a plurality of training equalization features.

[0094] The feature selection mechanism aims to train the balanced network model by gradually adding features. First, a random feature is randomly selected from multiple training features and multiple training balanced features as the training input data for the training balanced network model.

[0095] In operation 502 , based on the random characteristics and the current balancing network model, the parameter accuracy of the current balancing network model is determined.

[0096] The current random feature is used as the input of the balanced network model to obtain multiple balanced parameters output by the balanced network model based on the random feature, and the multiple balanced parameters are calculated with the corresponding parameter threshold to obtain the parameter accuracy of each balanced parameter. Among them, the parameter accuracy of each balanced parameter constitutes the parameter accuracy of the current balanced network model.

[0097] In operation 503, when the parameter accuracy is not greater than the set threshold, it is determined whether the random feature is the minimum feature set. If it is the minimum feature set, the random feature is directly stored in the mutual information library. If it is not the minimum feature set, feature clipping is performed and the balanced network model is retrained based on the scoreboard.

[0098] When the parameter accuracy corresponding to the current random feature is not greater than the set threshold, it means that the current balanced network model has met the requirements. However, in order to ensure that the computational complexity of the balanced network model is optimal, it is necessary to determine whether the current random feature is the minimum feature set. If so, the random feature is saved in the mutual information library and used as the current required feature requirements of the current balanced network model. If it is not the minimum feature set, feature clipping is performed, and the balanced network model is retrained based on the random feature after feature clipping through the scoreboard control until the random feature is the minimum feature set and the parameter accuracy is not greater than the set threshold. Among them, the minimum feature set means that the number of random features is minimized.

[0099] Among them, saving the current random feature to the mutual information library can be regarded as storing the feature type of the current random feature in the mutual information library, so as to use the feature type of the random feature as the current required feature requirement of the equilibrium network model.

[0100] For example, when a random feature is applied in the training process of the balanced network model, if the parameter accuracy is not greater than the set threshold, such as 5%, the minimum feature set is determined for the random feature. If it is the minimum feature set, it is directly stored in the mutual information library; if it is not the minimum feature set, feature clipping is performed and the balanced network model is retrained based on the scoreboard.

[0101] In operation 504, when the parameter accuracy is greater than the set threshold, it is determined whether the random feature is a maximum feature set.

[0102] If the current parameter accuracy is greater than the set threshold, it means that the current balanced network model cannot meet the usage requirements. At this time, it is necessary to determine whether the random features have reached the maximum feature set. The maximum feature set means that the number of random features has reached the maximum. For example, the number of features that can be used in the balanced network model is 5. When the number of random features reaches 5, the random features are determined to be the maximum feature set.

[0103] For example, if the accuracy is higher than a set threshold, such as 5%, a maximum feature set determination is performed.

[0104] In operation 505, when it is not the maximum feature set, the number of random features is increased, and the balanced network model is trained based on the scoreboard until the parameter accuracy of the balanced network model is no greater than the set threshold and the number of random features reaches the set condition or the number of random features reaches the maximum, and the current multiple random features are stored in the mutual information library as the current required feature requirements of the balanced network model.

[0105] If the random features are not the maximum feature set, the random features are gradually added, and the balanced network model is gradually trained based on the scoreboard until the parameter accuracy of the balanced network model is no greater than the set threshold and the number of random features reaches the set condition or the number of random features reaches the maximum.

[0106] After the balanced network model is trained, the final multiple random features of the current balanced network model are also saved in the mutual information library for subsequent use.

[0107] For example, if it is not the maximum feature set at this time, the features are expanded, that is, the types of random features are increased, and the feature set is optimized until the parameter accuracy is less than or equal to the set threshold, and then the mutual information library is updated.

[0108] In one embodiment of the present application, the number of random features is increased, and the balanced network model is trained based on the scoreboard until the parameter accuracy of the balanced network model is not greater than the set threshold and the number of random features reaches the set condition or the number of random features reaches the maximum, which can be regarded as: In the process of adding random features, if the parameter accuracy is controlled within the set threshold, the minimum feature set of multiple random features is judged and feature clipping is performed. Then, under the control of the scoreboard, the balanced network model is retrained. If the parameter accuracy is still within the set threshold under the minimum feature set after feature clipping, the feature type of the current random feature is updated to the mutual information library. If the parameter accuracy exceeds the set threshold after clipping the feature, the last random feature that has just been clipped is re-filled. In the process of increasing the number of random features, if the parameter accuracy exceeds the set threshold, the maximum feature set judgment is performed. If the maximum feature set is reached, all current random features are stored in the mutual information library. If they are within the maximum feature set, the features are expanded and the added random features are input into the current equilibrium network model based on the scoreboard to control the equilibrium network model to be retrained.

[0109] In operation 506 , when the random feature is the maximum feature set, the training of the balanced network model is stopped, and the current random feature is stored in the mutual information library as the current required feature requirement of the balanced network model.

[0110] If the random features are already the maximum feature set, stop training the balanced network model and store the current random features in the mutual information library for subsequent use.

[0111] In order to further illustrate the solution of the embodiment of the present application for training a balanced network model based on a feature selection mechanism, a specific application example is provided below for illustration.

[0112] Figure 7 A training architecture diagram of a specific application example of the equalization network model training of the equalization parameter adjustment method provided in an embodiment of the present application is shown.

[0113] refer to Figure 7 In this specific application example of the embodiment of the present application, the specific process of using the feature selection mechanism to train the equalization network model includes: preprocessing the data passing through the channel; using the preprocessed data and the output data for model training and optimization; wherein the model training and optimization are based on the scoreboard, the mutual information library and the parameter accuracy judgment, and the parameter accuracy judgment is based on the parameter threshold. The data passing through the channel can be regarded as the above-mentioned multiple training pulse signals and training transmission signals, the output data can be regarded as the training output signal, and the preprocessing refers to extracting multiple training features and multiple training equalization features from multiple training pulse signals and multiple training transmission signals.

[0114] It should be noted that the description of this specific application example of the present application is different from the above Figure 6 The description of the feature selection mechanism is similar and has similar beneficial effects, so it is not repeated here.

[0115] In one embodiment of the present application, Figure 5-Figure 7 The model training method described in any of the attached figures performs iterative optimization on the equalization network model in real time to adapt to the real-time characteristic requirements of the channel. For the specific process, please refer to Figure 5-Figure 7 Description of any of the accompanying drawings. For example, when a new transmission signal is received, an iterative optimization of the equalization network model is performed based on the scoreboard, the mutual information library, the parameter accuracy judgment and the new transmission signal.

[0116] In one implementation of the present application, the first equalizer is a CTLE, and the second equalizer is a DFE.

[0117] In one embodiment of the present application, multiple training pulse signals include SBR (Single Bit Response) and LPR (Long pulse Response), the training transmission signal is PRBS (Pseudo-Random Binary Sequences), multiple training features include low-frequency gain, high-frequency gain and high-frequency range, and multiple training equalization features include eye width and eye height.

[0118] In one embodiment of the present application, the multiple equalization parameters of the first equalizer include high-frequency gain, a zero point, a first pole, and a second pole, and the multiple equalization parameters of the second equalizer include multiple tap coefficients.

[0119] In one embodiment of the present application, the multiple channel characteristics also include signal attenuation. When the ratio of the high-frequency gain to the channel attenuation predicted by the equalization network model exceeds the attenuation threshold, it indicates that the equalization effort of the CTLE is too high and the equalization effort of the DFE is too low, that is, the tap coefficient of the DFE is too low. On the contrary, the tap coefficient of the DFE is too high. Therefore, the embodiment of the present application also calculates the ratio of the high-frequency gain to the channel attenuation in real time, and judges the strength of the CTLE equalization effort compared with the DFE by comparing with the attenuation threshold. Then, the judgment result and the corresponding ratio are sent to the equalizer adjustment device to adjust the equalization network models of the CTLE and the DFE through some hyperparameter optimization methods or adaptive learning rate methods, so as to achieve a balance between the equalization efforts of the CTLE and the DFE.

[0120] In order to facilitate understanding of the solution of the embodiment of the present application, a specific application example is used for illustration below.

[0121] Figure 8 A schematic diagram of the composition structure of a specific application example of the equalization circuit provided in an embodiment of the present application is shown.

[0122] refer to Figure 8 The equalization method of this specific application example of the present application is based on Figure 8 The equalization circuit of this specific application example of the present application includes FFE (Feed Forward Equalizer), channel, CTLE, DFE and equalizer adjustment device. The equalizer adjustment device is divided into a control unit, a deep learning module and an adaptive parameter adjustment circuit. The deep learning module is configured to include a first equalization network model of CTLE and a second equalization network model of DFE. The control unit is connected to the deep learning module and the adaptive parameter adjustment circuit, and is also connected to the signal transmitting end. The multiple equalization coefficients of CTLE include high-frequency gain, zero point, first pole and second pole, which are G, Wz, Wp1 and Wp2 respectively. The multiple equalization coefficients of DFE are 18 tap coefficients. This specific application example of the present application includes the following operations: S1, a control unit sends an acquisition instruction for sequentially acquiring SBR and LPR to a signal transmitting end, so that the signal transmitting end sends SBR and LPR to a channel sequentially in response to the acquisition instruction.

[0123] S2, the control unit controls the deep learning module to receive the SBR and LPR transmitted by the channel, and obtains features such as low-frequency gain, high-frequency gain, and high-frequency range from the SBR and LPR, and saves the features to the mutual information library; S3, the control unit sends an acquisition instruction for acquiring the PRBS to the signal transmitting end, so that the signal transmitting end sends the PRBS to the channel in response to the acquisition instruction.

[0124] S4, the control unit controls the deep learning module to receive the PRBS transmitted by the channel, and obtains features including eye height and eye width from the PRBS, and trains the first equalizer network model and the second equalizer network model in combination with the output of the DFE. During the training process, the equalizer network model is trained based on the features controlled by the scoreboard and the output of the DFE; wherein, the scoreboard control feature can be regarded as the scoreboard controlling the selection of features in the mutual information library according to the prediction parameter accuracy, that is, expansion or cropping, and the mutual information library is used to store the low-frequency gain, high-frequency gain, high-frequency range and other features obtained from the SBR and LPR and the features controlled by the scoreboard, and the prediction parameter accuracy is calculated based on the parameter threshold of the equalization parameter. S5, when a new transmission signal is received, the multi-equalization parameters of the CTLE are predicted using the new transmission signal, the trained first equalization network model, and the required feature requirements of the current equalization network model stored in the current mutual information library, and the predicted equalization parameters are input to the corresponding CTLE; the first 6 tap coefficients of the DFE, i.e., c k , k≤6, and use the adaptive parameter adjustment circuit to predict the last 12 tap coefficients of DFE, that is, c j , 7≤j≤18, and the predicted 18 tap coefficients are input to DFE.

[0125] Therefore, this specific application example of the present application, by cleverly combining adaptive algorithms and deep learning, realizes a CTLE+DFE combined equalization circuit with high adaptability and high equalization efficiency, greatly reducing circuit complexity and power consumption. At the same time, it also realizes real-time update of multi-dimensional equalization parameters, significantly expands the application scenarios, and also improves the high reliability of transmission signals.

[0126] It should be noted that the description of this specific application example of the embodiment of the present application is similar to the description of the above-mentioned method embodiment and the equalization circuit embodiment, and has similar beneficial effects as the method embodiment and the equalization circuit embodiment, so it will not be repeated. Figures 1 to 7 The present invention can be understood by referring to the description of any one of the accompanying drawings.

[0127] Based on the above-mentioned balancing circuit, an embodiment of the present application further provides a balancing chip, including the above-mentioned balancing circuit.

[0128] Based on the above method, the embodiment of the present application further provides a transceiver, including the above equalization chip, wherein the transceiver is specifically a SerDes transceiver for NRZ (Non-Return to Zero) high-speed link, that is, a Serializer / Deserializer transceiver.

[0129] Based on the above-mentioned equalization circuit, an embodiment of the present application also provides a storage system, including the above-mentioned transceiver.

[0130] The transceiver of the embodiment of the present application is mainly oriented to a storage system, which may include but is not limited to a storage application and a storage device.

[0131] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium, which are built into an equalizer adjustment device and are used to execute the equalization parameter adjustment method of the embodiment of the present application.

[0132] Fig. 9 A schematic block diagram of an electronic device that can be used to implement the embodiments of the present application is shown.

[0133] Electronic devices are intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0134] like Fig. 9 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory ROM 802 or a computer program loaded from a storage unit 808 to a random access memory RAM 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0135] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0136] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as the adjustment method of the equalization parameter. For example, in some embodiments, the adjustment method of the equalization parameter may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the adjustment method of the equalization parameter described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the adjustment method of the equalization parameter by any other appropriate means (e.g., by means of firmware).

[0137] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0138] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0139] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0140] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0141] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user's computer with a desktop synchronization window or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0142] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0143] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0144] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0145] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for adjusting equalization parameters, characterized in that: The method comprises: Acquire a transmission signal transmitted by a channel; extracting a plurality of equalization features from the transmission signal; determining a required feature set for each equalizer based on the plurality of equalization features, the plurality of channel features of the channels, and current required feature requirements of an equalization network model of at least one equalizer; According to the equalization network model of each equalizer and the corresponding required feature set, multiple equalization parameters of each equalizer are predicted, and the multiple equalization parameters are transmitted to the corresponding equalizer, so that each equalizer performs signal compensation on the received signal according to the corresponding multiple equalization parameters.

2. The method according to claim 1, characterized in that The method further comprises: Acquire multiple pulse signals transmitted sequentially by the channel; A plurality of channel characteristics of the channel are obtained from the plurality of pulse signals.

3. The method according to claim 1, characterized in that The at least one equalizer includes a first equalizer and a second equalizer, and the plurality of equalization parameters of the second equalizer include a plurality of first set equalization parameters and a plurality of second set equalization parameters; accordingly, The method predicts multiple equalization parameters of each equalizer according to the equalization network model of each equalizer and the corresponding required feature set, including: predicting a plurality of equalization parameters of the first equalizer according to the equalization network model of the first equalizer and the corresponding required feature set; predicting a plurality of first set equalization parameters of the second equalizer according to the equalization network model of the second equalizer and the corresponding required feature set; A plurality of second set equalization parameters of the second equalizer are predicted according to the adaptive parameter adjustment circuit of the second equalizer.

4. The method according to claim 3, characterized in that Each equalizer performs signal compensation on the received signal according to the corresponding multiple equalization parameters, including: The first equalizer receives the transmission signal transmitted by the channel, and uses the corresponding multiple equalization parameters to perform signal compensation on the transmission signal to obtain a first compensated signal; The second equalizer receives the first compensation signal, and uses a plurality of corresponding equalization parameters to perform signal compensation on the first compensation signal to obtain a second compensation signal.

5. The method according to claim 3, characterized in that: The equalization network models of the first equalizer and the second equalizer are trained in the following manner: Acquire multiple training pulse signals transmitted sequentially by the channel, extract multiple training features from the multiple training pulse signals, and store the multiple training features in a mutual information library; Acquire a training transmission signal transmitted by a channel, and acquire a training output signal after being compensated by a first equalizer and a second equalizer signal; extracting a plurality of training equalization features from the training transmission signal; Training the equalization network model of the first equalizer according to the feature optimization mechanism, the plurality of training features, the plurality of training equalization features, the training output signal, the plurality of current equalization parameters of the first equalizer, and the required feature requirements of the first equalizer; Training the equalization network model of the second equalizer according to the feature optimization mechanism, the plurality of training features, the plurality of training equalization features, the training output signal, the plurality of current equalization parameters of the second equalizer, and the required feature requirements of the second equalizer; The balanced network model includes the currently required characteristic requirements of the balanced network model.

6. The method according to claim 5, characterized in that The feature selection mechanism includes: Randomly select a random feature from the multiple training features and the multiple training balanced features, and gradually increase the number of random features to train the balanced network model through the scoreboard until the parameter accuracy of the balanced network model is no greater than a set threshold and the number of the random features reaches a set condition or the number of random features reaches a maximum; The setting condition is that the number of random features is the minimum when the parameter accuracy of the balanced network model is not greater than a set threshold.

7. The method according to claim 6, characterized in that The randomly selecting a random feature from the multiple training features and the multiple training balanced features, and gradually increasing the number of random features to train the balanced network model through a scoreboard until the parameter accuracy of the balanced network model is not greater than a set threshold and the number of the random features reaches a set condition or the number of random features reaches a maximum, includes: Randomly select a random feature from the multiple training features and the multiple training balanced features; Based on the random features and the current balanced network model, determining the parameter accuracy of the current balanced network model; When the parameter accuracy is not greater than the set threshold, determine whether the random feature is a minimum feature set. If it is a minimum feature set, store the random feature directly in the mutual information library. If it is not a minimum feature set, perform feature clipping and retrain the balanced network model based on the scoreboard. When the parameter accuracy is greater than the set threshold, determine whether the random feature is the maximum feature set; In the case where the feature set is not the maximum, the number of random features is increased, and the balanced network model is trained based on the scoreboard until the parameter accuracy of the balanced network model is not greater than the set threshold and the number of random features reaches the set condition or the number of random features reaches the maximum, and the current multiple random features are stored in the mutual information library as the current required feature requirements of the balanced network model; When the random features are the largest feature set, stop training the balanced network model and store the current random features in the mutual information library as the current required feature requirements of the balanced network model.

8. The method according to claim 5, characterized in that The first equalizer is a continuous time linear equalizer, and the second equalizer is a decision feedback equalizer.

9. The method according to claim 8, characterized in that The multiple training pulse signals include single-bit responses and long pulse responses, the training transmission signal is a pseudo-random sequence, the multiple training features include low-frequency gain, high-frequency gain and high-frequency range, and the multiple training equalization features include eye width and eye height.

10. The method according to claim 9, characterized in that The multiple equalization parameters of the first equalizer include a high frequency gain, a zero point, a first pole, and a second pole, and the multiple equalization parameters of the second equalizer include a plurality of tap coefficients.

11. An equalizing circuit, characterized in that: The equalization circuit comprises: A channel, connected to the signal sending end, for receiving a transmission signal from the signal sending end and transmitting it; at least one equalizer connected to the channel; An equalizer adjustment device is connected to at least one equalizer and is used to obtain a transmission signal transmitted by a channel; extract multiple equalization features from the transmission signal; determine the required feature set of each equalizer based on the multiple equalization features, multiple channel features of the channel and the current required feature requirements of the equalization network model of at least one equalizer; predict multiple equalization parameters of each equalizer based on the equalization network model of each equalizer and the corresponding required feature set, and transmit the multiple equalization parameters to the corresponding equalizer so that each equalizer performs signal compensation on the received signal according to the corresponding multiple equalization parameters.

12. The equalizing circuit according to claim 11, characterized in that: The equalization circuit further comprises: The adaptive parameter adjustment circuit is connected to one of the equalizers and is used to adjust the corresponding equalization parameters of the connected equalizer.

13. A balancing chip, characterized in that: The equalizing circuit comprises the equalizing circuit described in any one of claims 11-12.

14. A transceiver, characterized in that: Includes the balancing chip as described in claim 13.

15. A storage system, characterized in that: Comprising the transceiver of claim 14.

Images