Signal transmission method and device, electronic equipment and readable storage medium

Abstract

This application provides a signal transmission method applied at a transmitting end, the transmitting end including a first equalizer. The method includes: performing equalization processing on a signal to be transmitted based on the first equalizer to obtain a first signal, and sending the first signal to a receiving end; acquiring a feedback signal sent by the receiving end; the feedback signal is obtained after equalizing the first signal based on a second equalizer within the receiving end; using the feedback signal and the signal to be transmitted as inputs to a preset equalization parameter adjustment model, acquiring a first equalization parameter and a second equalization parameter output by the equalization parameter adjustment model; adjusting the first equalizer according to the first equalization parameter, and sending the second equalization parameter to the receiving end; the second equalization parameter is used by the receiving end to adjust the second equalizer; performing equalization processing on the signal to be transmitted based on the adjusted first equalizer to obtain a second signal, and sending the second signal to the receiving end. This method can improve the equalization efficiency of the signal transmission process.

Description

Technical Field

[0001] This application belongs to the field of communication technology, and in particular relates to a signal transmission method, apparatus, electronic device and readable storage medium. Background Technology

[0002] During the process of a signal traveling from the transmitting end to the receiving end through the transmission channel, signal distortion can occur due to external interference. In severe cases, this can lead to signal distortion, resulting in errors and affecting the quality of signal transmission.

[0003] In existing technologies, Peripheral Component Interconnect Express (PCIe) equalization technology employs methods such as pre-emphasis, deemphasis, or Finite Impulse Response (FIR) filters at the transmitting end to combat inter-symbol interference, and methods such as Continuous-Time Linear Equalization (CTLE) at the receiving end to improve high-frequency attenuation. This results in signal equalization at both the transmitting and receiving ends to improve signal transmission quality.

[0004] However, the equalization parameters involved at both the transmitting and receiving ends are numerous, and negotiation of these parameters is required at both ends via the PCIe bus protocol stack. The equalization parameters are then continuously adjusted based on the negotiation results until the optimal equalization parameters are reached, thereby improving signal transmission quality. Due to the complexity of the equalization parameter negotiation process, existing signal transmission methods suffer from low equalization efficiency. Summary of the Invention

[0005] This application provides a signal transmission method, apparatus, electronic device, and readable storage medium to solve the problem of low equalization efficiency in existing signal transmission methods.

[0006] To solve the above-mentioned technical problems, this application is implemented as follows:

[0007] In a first aspect, embodiments of this application propose a signal transmission method applied at a transmitting end, the transmitting end including a first equalizer, the method comprising:

[0008] The first equalizer performs equalization processing on the signal to be transmitted to obtain a first signal, and then sends the first signal to the receiving end.

[0009] The feedback signal sent by the receiving end is obtained; the feedback signal is obtained by equalizing the first signal based on the second equalizer in the receiving end.

[0010] The feedback signal and the signal to be transmitted are used as inputs to a preset equalization parameter adjustment model to obtain the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model.

[0011] The first equalizer is adjusted according to the first equalization parameter, and the second equalization parameter is sent to the receiving end; the second equalization parameter is used by the receiving end to adjust the second equalizer.

[0012] The signal to be transmitted is equalized based on the adjusted first equalizer to obtain a second signal, and the second signal is sent to the receiving end.

[0013] Optionally, the step of using the feedback signal and the signal to be transmitted as inputs to a preset equalization parameter adjustment model, and obtaining the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model, includes:

[0014] The feedback signal and the signal to be transmitted are used as inputs to the equalization parameter adjustment model;

[0015] Based on the activation parameter and inter-symbol parameter in the equalization parameter adjustment model, as well as the feedback signal and the signal to be transmitted, the first equalization parameter and the second equalization parameter are determined.

[0016] Obtain the first equilibrium parameter and the second equilibrium parameter output by the equilibrium parameter adjustment model.

[0017] Optionally, the equilibrium parameter adjustment model is obtained in the following way:

[0018] The training samples are input into the model to be trained; the training samples include the signal sub-samples to be transmitted and the feedback signal sub-samples corresponding to the signal sub-samples to be transmitted.

[0019] Obtain the model output value of the model to be trained, and determine the model loss value based on the model output value and the sample labels corresponding to the model training samples; the sample labels include the first equalization parameter and the second equalization parameter corresponding to the signal sub-sample to be transmitted;

[0020] The model parameters of the model to be trained are adjusted according to the model loss value, and the current model to be trained is determined as the equilibrium parameter adjustment model when the preset stopping condition is met.

[0021] Optionally, after performing equalization processing on the signal to be transmitted based on the adjusted first equalizer to obtain a second signal, and sending the second signal to the receiving end, the method further includes:

[0022] Obtain the latest feedback signal sent by the receiving end; the latest feedback signal is obtained based on the second signal after the second equalizer performs equalization processing;

[0023] Based on the latest feedback signal and the signal to be transmitted, determine the bit error rate corresponding to the latest feedback signal and the signal to be transmitted;

[0024] If the bit error rate meets the preset threshold requirement, a transmission success instruction is sent to the receiving end; the transmission success instruction is used to inform the receiving end that the bit error rate meets the preset threshold requirement.

[0025] Secondly, embodiments of this application propose a signal transmission method applied at a receiving end, the receiving end including a second equalizer, the method comprising:

[0026] The first signal received by the transmitting end is obtained after the first equalizer performs equalization processing on the signal to be transmitted.

[0027] The first signal is processed by the second equalizer to obtain a feedback signal, and the feedback signal is sent to the transmitting end. The transmitting end is used to take the feedback signal and the signal to be transmitted as inputs to a preset equalization parameter adjustment model, obtain the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model, adjust the first equalizer according to the first equalization parameter, and send the second equalization parameter to the receiving end.

[0028] Receive the second equalization parameter sent by the sending end, and adjust the second equalizer according to the second equalization parameter;

[0029] The receiving end receives the second signal obtained after the transmitting end performs equalization processing on the signal to be transmitted based on the adjusted first equalizer.

[0030] Optionally, after receiving the second signal obtained by the transmitting end after equalizing the signal to be transmitted based on the adjusted first equalizer, the method further includes:

[0031] The second signal is equalized based on the adjusted second equalizer to obtain the latest feedback signal, and the latest feedback signal is sent to the transmitting end; the receiving end is used to determine the bit error rate corresponding to the latest feedback signal and the signal to be transmitted based on the latest feedback signal and the signal to be transmitted, and to send a transmission success instruction to the receiving end if the bit error rate meets the preset threshold requirement; the transmission success instruction is used to inform the receiving end that the bit error rate meets the preset threshold requirement.

[0032] Optionally, the method further includes:

[0033] Receive the transmission success command sent by the sending end;

[0034] In response to the successful transmission command, the feedback signal is processed in a specified manner.

[0035] Thirdly, embodiments of this application provide a signal transmission device applied at a transmitting end, the transmitting end including a first equalizer, the device comprising:

[0036] The first execution module is used to perform equalization processing on the signal to be transmitted based on the first equalizer to obtain a first signal, and send the first signal to the receiving end.

[0037] The first acquisition module is used to acquire the feedback signal sent by the receiving end; the feedback signal is obtained by equalizing the first signal based on the second equalizer in the receiving end.

[0038] The second acquisition module is used to take the feedback signal and the signal to be transmitted as inputs to a preset equalization parameter adjustment model, and acquire the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model.

[0039] An adjustment module is used to adjust the first equalizer according to the first equalization parameter, and send the second equalization parameter to the receiving end; the second equalization parameter is used by the receiving end to adjust the second equalizer.

[0040] The second execution module is used to perform equalization processing on the signal to be transmitted based on the adjusted first equalizer to obtain a second signal, and to send the second signal to the receiving end.

[0041] Optionally, the second acquisition module is specifically used for:

[0042] The feedback signal and the signal to be transmitted are used as inputs to the equalization parameter adjustment model;

[0043] Based on the activation parameter and inter-symbol parameter in the equalization parameter adjustment model, as well as the feedback signal and the signal to be transmitted, the first equalization parameter and the second equalization parameter are determined.

[0044] Obtain the first equilibrium parameter and the second equilibrium parameter output by the equilibrium parameter adjustment model.

[0045] Optionally, the equilibrium parameter adjustment model is obtained in the following way:

[0046] The training samples are input into the model to be trained; the training samples include the signal sub-samples to be transmitted and the feedback signal sub-samples corresponding to the signal sub-samples to be transmitted.

[0047] Obtain the model output value of the model to be trained, and determine the model loss value based on the model output value and the sample labels corresponding to the model training samples; the sample labels include the first equalization parameter and the second equalization parameter corresponding to the signal sub-sample to be transmitted;

[0048] The model parameters of the model to be trained are adjusted according to the model loss value, and the current model to be trained is determined as the equilibrium parameter adjustment model when the preset stopping condition is met.

[0049] Optionally, the device further includes:

[0050] The third acquisition module is used to acquire the latest feedback signal sent by the receiving end after the second execution module performs equalization processing on the signal to be transmitted based on the adjusted first equalizer to obtain a second signal and sends the second signal to the receiving end; the latest feedback signal is obtained based on the equalization processing of the second signal by the second equalizer;

[0051] The determining module is used to determine the bit error rate corresponding to the latest feedback signal and the signal to be transmitted based on the latest feedback signal and the signal to be transmitted.

[0052] The sending module is used to send a transmission success instruction to the receiving end when the bit error rate meets the preset threshold requirement; the transmission success instruction is used to inform the receiving end that the bit error rate meets the preset threshold requirement.

[0053] Fourthly, embodiments of this application provide a signal transmission device applied at a receiving end, the receiving end including a second equalizer, the device comprising:

[0054] The first receiving module is used to receive the first signal sent by the transmitting end after the first equalizer has performed equalization processing on the signal to be transmitted.

[0055] The feedback module is used to perform equalization processing on the first signal based on the second equalizer to obtain a feedback signal, and send the feedback signal to the transmitting end; the transmitting end is used to take the feedback signal and the signal to be transmitted as inputs to a preset equalization parameter adjustment model, obtain the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model, adjust the first equalizer according to the first equalization parameter, and send the second equalization parameter to the receiving end;

[0056] The adjustment module is used to receive the second equalization parameters sent by the sending end, and adjust the second equalizer according to the second equalization parameters;

[0057] The second receiving module is used to receive the second signal obtained by the transmitting end after equalizing the signal to be transmitted based on the adjusted first equalizer.

[0058] Optionally, the device further includes:

[0059] The third receiving device is used to receive the transmission success instruction sent by the sending end;

[0060] The processing module is used to perform specified processing on the feedback signal in response to the transmission success command.

[0061] Fifthly, embodiments of this application provide an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the signal transmission method as described in the first aspect.

[0062] In a sixth aspect, embodiments of this application provide a readable storage medium that, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the signal transmission method as described in the first aspect.

[0063] In this embodiment, the feedback signal is obtained by the receiving end after the signal to be transmitted has been equalized by the first equalizer. Therefore, the feedback signal is associated with the first equalizer and the second equalizer. The feedback signal and the signal to be transmitted are input into the equalization parameter adjustment model to obtain the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model. This allows the first equalization parameter and the second equalization parameter to be matched with the signal to be transmitted, the first equalizer, and the second equalizer, respectively. Adjusting the first equalizer according to the first equalization parameter makes the adjusted first equalizer more compatible with the signal to be transmitted, improving the equalization effect of the adjusted first equalizer on the signal to be transmitted, thereby improving the signal quality of the second signal. Then, the second signal is sent to the receiving end so that the receiving end can perform equalization processing on the second signal based on the adjusted second equalizer to obtain the equalized second signal. Since adjusting the second equalizer according to the second equalization parameter makes the adjusted second equalizer more compatible with the signal to be transmitted, the signal quality of the equalized second signal can be improved. Compared to existing signal transmission methods, this approach avoids the negotiation process between the transmitter and receiver regarding equalization parameters. The first and second equalization parameters are obtained directly based on the equalization parameter adjustment model, which improves the efficiency of obtaining equalization parameters and, to some extent, enhances the equalization efficiency of the signal transmission process between the transmitter and receiver. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 This is a flowchart illustrating the steps of a signal transmission method provided in an embodiment of this application;

[0066] Figure 2 This is a schematic diagram of the neural network model to be trained provided in an embodiment of this application;

[0067] Figure 3 This is a schematic diagram of the signal transmission process in the prior art;

[0068] Figure 4 This is a schematic diagram of the equalization process of the signal transmission method provided in the embodiments of this application;

[0069] Figure 5 This is a flowchart of another signal transmission method provided in an embodiment of this application;

[0070] Figure 6 This is a structural diagram of a signal transmission device provided in an embodiment of this application;

[0071] Figure 7 This is a structural diagram of another signal transmission device provided in the embodiments of this application;

[0072] Figure 8 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0073] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0074] Figure 1 This is a flowchart of a method provided in an embodiment of this application, such as... Figure 1 As shown, the method is applied to a transmitting end, which includes a first equalizer, and the method includes:

[0075] Step 101: Based on the first equalizer, perform equalization processing on the signal to be transmitted to obtain a first signal, and send the first signal to the receiving end.

[0076] In this embodiment, the transmitting end and the receiving end can be computer devices such as computers and servers. The transmitting end and the receiving end can be connected via a bus and signal transmission can be achieved through the bus, such as a PCIe bus. The first equalizer can be an equalizer used to combat inter-symbol interference during signal transmission, such as an equalizer that can pre-emphasize / de-emphasize signals, or an FIR equalizer. The second equalizer can be an equalizer that improves high-frequency attenuation problems, such as a decision feedback equalizer (DFE) or a CTLE equalizer. This is merely an example, and this embodiment does not impose limitations.

[0077] In this embodiment, the signal to be transmitted can be input to a first equalizer. The first equalizer performs equalization processing on each bit of the signal to be transmitted according to its preset equalization parameters to obtain the equalized signal to be transmitted. The equalized signal to be transmitted is then sent to the receiving end as the first signal. Specifically, for any current bit of the signal to be transmitted, the voltage values ​​of the previous bit, the current bit, and the next bit are weighted and summed according to the weight coefficients of the previous bit, the current bit, and the next bit. The summation result is used as the equalized current bit. Based on the equalization processing of each bit of the signal to be transmitted by the first equalizer, the equalized bits are combined to obtain the equalized signal to be transmitted.

[0078] For example, the first equalizer can be a three-tap FIR equalizer. For any bit in the signal to be transmitted, the equalizer has three inputs: the previous bit, the current bit to be transmitted, and the next bit. These three bits are added together with certain weights to produce the equalized current bit output. The equalized current bit can be represented by the pre-cursor coefficient, cusor coefficient, and post-cursor coefficient of the three-tap FIR equalizer. The pre-cursor coefficient represents the weight coefficient of the previous bit, the cusor coefficient represents the weight coefficient of the current bit, and the post-cursor coefficient represents the weight coefficient of the next bit. See the following formula (1):

[0079] V(k)=ξ (k-1) V(k-1)+ξ (k) V(k)+ξ (k+1) V(k+1) (1)

[0080] Where k represents the current transmission time, V(k) represents the current transmitted bit, V(k-1) represents the previous bit, V(k+1) represents the next bit, and ξ (k-1) ξ represents the pre-cursor coefficient. (k) ξ represents the Cusor coefficient.(k+1) This represents the Post-cursor coefficient.

[0081] Step 102: Obtain the feedback signal sent by the receiving end; the feedback signal is obtained by equalizing the first signal based on the second equalizer in the receiving end.

[0082] In this embodiment, after receiving the first signal, the receiving end can perform equalization processing on the first signal based on the second equalizer within the receiving end, and then send the equalized first signal as a feedback signal to the receiving end. Specifically, the first signal can be input into the second equalizer, which performs equalization processing on each bit of the first signal according to its preset equalization parameters to obtain the equalized first signal, and then uses the equalized first signal as the feedback signal. For example, the second equalizer can be a CTLE equalizer. The CTLE equalizer is used to suppress low-frequency components and compensate for high-frequency components through preset equalization parameters, and to reduce waveform distortion by peak clipping and valley filling. The equalization parameters of the CTLE equalizer can be multiplied by each bit of the first signal to obtain the equalized bits, thereby achieving equalization processing of the first signal and obtaining the equalized first signal. Then, the equalized first signal is sent as a feedback signal to the receiving end, and the sending end obtains the feedback signal sent by the receiving end.

[0083] Step 103: Use the feedback signal and the signal to be transmitted as inputs to a preset equalization parameter adjustment model to obtain the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model.

[0084] In this embodiment, the transmitting end inputs the feedback signal and the signal to be transmitted into a preset equalization parameter adjustment model. The equalization parameter adjustment model simulates the transmission process of the signal to be transmitted from the first equalizer, to the channel between the transmitting and receiving ends, and then to the second equalizer, based on the signal to be transmitted, the feedback signal, and preset activation parameters and inter-symbol parameters. Based on the input signal to be transmitted, the output feedback signal, and the activation and inter-symbol parameters during this transmission process, the optimal equalization parameters corresponding to the first equalizer (i.e., the first equalization parameter) and the optimal equalization parameters corresponding to the second equalizer (i.e., the second equalization parameter) are determined. Then, the equalization parameter adjustment model outputs the first and second equalization parameters, and the transmitting end obtains the first and second equalization parameters output by the equalization parameter adjustment model. The activation parameter represents the high-frequency attenuation information corresponding to the channel between the transmitting and receiving ends, and the inter-symbol parameters characterize the inter-symbol interference information of the signal to be transmitted.

[0085] In this embodiment of the application, the equalization parameter adjustment model can be obtained by training a neural network model. The model training samples may include historical transmission signal data of the transmitting end and feedback signal data of the receiving end corresponding to the historical transmission signal data. The sample labels corresponding to the model training samples may include the equalization parameters of the transmitting end and the equalization parameters of the receiving end corresponding to the historical transmission signal data.

[0086] Alternatively, multiple random binary digital signals can be preset as the signals to be transmitted, and arbitrary combinations of weight coefficients can be preset as the equalization parameters of the first equalizer. The signals to be transmitted are then processed by the first equalizer and sent to the receiving end. The feedback signal from the receiving end, after being processed by the second equalizer, is obtained, resulting in a pair of transmitted signal sub-samples and feedback signal sub-samples, as well as the corresponding equalization parameters of the transmitting end and the receiving end. Then, by adjusting the step size within a certain range, the equalization parameters of the first and second equalizers are adjusted to generate a sample space composed of the signals to be transmitted, the feedback signal, the equalization parameters of the transmitting end, and the equalization parameters of the receiving end. When training the neural network model to be trained, the transmitted signal sub-samples and the corresponding feedback signal sub-samples are obtained from the sample space as model training samples, and the first and second equalization parameters corresponding to the transmitted signal sub-samples are obtained as sample labels.

[0087] In this embodiment, when training the neural network model to be trained (i.e., the training model), training samples can be input into the training model. The training model learns sample labels and outputs a first equalization parameter and a second equalization parameter. The first and second equalization parameters are used as the model output values, and the first and second equalization parameters corresponding to historical transmitted signal data are used as sample label values. The loss value between the model output value and the sample label value is calculated. If a preset stopping condition is met, an equalization parameter adjustment model is obtained. The preset stopping condition can be that the loss value is less than a preset loss threshold. This is merely an example, and this embodiment does not impose any limitations.

[0088] Step 104: Adjust the first equalizer according to the first equalization parameter, and send the second equalization parameter to the receiving end; the second equalization parameter is used by the receiving end to adjust the second equalizer.

[0089] In this embodiment, adjusting the first equalizer according to the first equalization parameter can specifically involve adjusting the equalization parameters internal to the first equalizer to the first equalization parameter. For example, the first equalizer is a three-tap FIR equalizer, and the first equalization parameter includes the latest pre-cursor coefficient, cusor coefficient, and post-cursor coefficient corresponding to the three-tap FIR equalizer. The original pre-cursor coefficient, cusor coefficient, and post-cursor coefficient internal to the three-tap FIR equalizer can be adjusted to the latest pre-cursor coefficient, cusor coefficient, and post-cursor coefficient. The sending end sends the second equalization parameter to the receiving end, and the receiving end adjusts the equalization parameters internal to the second equalizer to the second equalization parameter.

[0090] Step 105: Based on the adjusted first equalizer, perform equalization processing on the signal to be transmitted to obtain a second signal, and send the second signal to the receiving end.

[0091] In this embodiment, the transmitting end can input the signal to be transmitted into an adjusted first equalizer. The adjusted first equalizer performs equalization processing on each bit of the signal to be transmitted according to the first equalization parameters, obtaining a second signal after re-equalization, and then sends the second signal to the receiving end. Specifically, for any current bit of the signal to be transmitted, the voltage values ​​of the previous bit, the current bit, and the next bit are weighted and summed according to the latest weight coefficients of the previous bit, the current bit, and the next bit. The latest summation result is used as the current bit after re-equalization. After re-equalizing each bit of the signal to be transmitted based on the adjusted first equalizer, the re-equalized bits are combined to obtain the second signal.

[0092] For example, the first equalizer can be a three-tap FIR equalizer. The pre-cursor coefficients, cusor coefficients, and post-cursor coefficients inside the adjusted three-tap FIR equalizer are the latest pre-cursor coefficients, cusor coefficients, and post-cursor coefficients corresponding to the first equalization parameters. The adjusted current transmitted bits can be obtained by referring to formula (1), thereby obtaining the signal to be transmitted after re-equalization, and the signal to be transmitted after re-equalization is sent to the receiving end as the second signal.

[0093] In this embodiment, the feedback signal is obtained by the receiving end after the signal to be transmitted has been equalized by the first equalizer. Therefore, the feedback signal is associated with the first equalizer and the second equalizer. The feedback signal and the signal to be transmitted are input into the equalization parameter adjustment model to obtain the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model. This allows the first equalization parameter and the second equalization parameter to be matched with the signal to be transmitted, the first equalizer, and the second equalizer, respectively. Adjusting the first equalizer according to the first equalization parameter makes the adjusted first equalizer more compatible with the signal to be transmitted, improving the equalization effect of the adjusted first equalizer on the signal to be transmitted, thereby improving the signal quality of the second signal. Then, the second signal is sent to the receiving end so that the receiving end can perform equalization processing on the second signal based on the adjusted second equalizer to obtain the equalized second signal. Since adjusting the second equalizer according to the second equalization parameter makes the adjusted second equalizer more compatible with the signal to be transmitted, the signal quality of the equalized second signal can be improved. Compared to existing signal transmission methods, this approach avoids the negotiation process between the transmitter and receiver regarding equalization parameters. The first and second equalization parameters are obtained directly based on the equalization parameter adjustment model, which improves the efficiency of obtaining equalization parameters and, to some extent, enhances the equalization efficiency of the signal transmission process between the transmitter and receiver.

[0094] Optionally, step 103 may include the following steps:

[0095] Step 1031: Use the feedback signal and the signal to be transmitted as inputs to the equalization parameter adjustment model.

[0096] Step 1032: Based on the activation parameter and inter-symbol parameter in the equalization parameter adjustment model, as well as the feedback signal and the signal to be transmitted, determine the first equalization parameter and the second equalization parameter.

[0097] Step 1033: Obtain the first equilibrium parameter and the second equilibrium parameter output by the equilibrium parameter adjustment model.

[0098] In this embodiment, the activation parameter represents the high-frequency attenuation information corresponding to the channel between the transmitter and receiver, and the inter-symbol parameter represents the inter-symbol interference information of the signal to be transmitted. The transmitter inputs the feedback signal and the signal to be transmitted into the equalization parameter adjustment model. The equalization parameter adjustment model simulates the transmission process of the signal to be transmitted from the first equalizer, to the channel between the transmitter and receiver, and then to the second equalizer, based on the signal to be transmitted, the feedback signal, the activation parameter, and the inter-symbol parameter. Based on the input signal to be transmitted, the output feedback signal, and the activation parameter and inter-symbol parameter of this transmission process, the optimal equalization parameter corresponding to the first equalizer (i.e., the first equalization parameter) and the optimal equalization parameter corresponding to the second equalizer (i.e., the second equalization parameter) are determined. Then, the equalization parameter adjustment model outputs the first equalization parameter and the second equalization parameter, and the transmitter obtains the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model.

[0099] In this embodiment, the feedback signal and the signal to be transmitted are used as inputs to the equalization parameter adjustment model; based on the activation parameters and inter-symbol parameters in the equalization parameter adjustment model, as well as the feedback signal and the signal to be transmitted, the first equalization parameter and the second equalization parameter are determined; and the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model are obtained. This allows for convenient determination of the first and second equalization parameters based on the activation parameters and inter-symbol parameters in the equalization parameter adjustment model, as well as the feedback signal and the signal to be transmitted, improving the efficiency of equalization parameter acquisition and, to some extent, improving the equalization efficiency of the signal transmission process between the transmitting and receiving ends.

[0100] Optionally, the equilibrium parameter adjustment model is obtained in the following way:

[0101] Step 201: Input the model training samples into the model to be trained; the model training samples include the signal sub-samples to be transmitted and the feedback signal sub-samples corresponding to the signal sub-samples to be transmitted.

[0102] Step 202: Obtain the model output value of the model to be trained, and determine the model loss value based on the model output value and the sample labels corresponding to the model training samples; the sample labels include the first equalization parameter and the second equalization parameter corresponding to the signal sub-sample to be transmitted.

[0103] Step 203: Adjust the model parameters of the model to be trained according to the model loss value, and determine the current model to be trained as the equilibrium parameter adjustment model when the preset stopping condition is met.

[0104] In this embodiment of the application, the signal sub-sample to be transmitted may include the historical transmission signal data of the transmitting end, the feedback signal sub-sample corresponding to the signal sub-sample to be transmitted may include the feedback signal data of the receiving end corresponding to the historical transmission signal data, and the sample label corresponding to the model training sample may include the equalization parameter of the transmitting end corresponding to the historical transmission signal data, i.e., the first equalization parameter, and the equalization parameter of the receiving end corresponding to the second equalization parameter.

[0105] Alternatively, multiple random binary digital signals can be preset as the signals to be transmitted, and arbitrary weight coefficient combinations can be preset as the equalization parameters of the first equalizer. The signals to be transmitted are processed by the first equalizer and then sent to the receiving end. The feedback signal from the receiving end, after being processed by the second equalizer, is obtained, resulting in a pair of transmitted signal sub-samples and feedback signal sub-samples, as well as the corresponding equalization parameters of the transmitting end and the receiving end. Then, by adjusting the step size within a certain range, the equalization parameters of the first and second equalizers are adjusted to generate a sample space composed of the signals to be transmitted, the feedback signal, the equalization parameters of the transmitting end, and the equalization parameters of the receiving end. When training the neural network model to be trained, the transmitted signal sub-samples and the corresponding feedback signal sub-samples are obtained from the sample space as model training samples, and the first and second equalization parameters corresponding to the transmitted signal sub-samples are obtained as sample labels. This is only an example, and the embodiments of this application do not limit this.

[0106] In this embodiment, the model parameters of the model to be trained may include activation parameters and inter-symbol parameters. The activation parameters represent the high-frequency attenuation of the channel between the transmitter and receiver, while the inter-symbol parameters characterize the inter-symbol interference of the transmitted signal. This embodiment simulates the signal transmission process in the channel between the transmitter and receiver using the activation parameters and inter-symbol parameters. Based on the transmitted signal sub-samples, feedback signal sub-samples, activation parameters, and inter-symbol parameters, the model to be trained determines the optimal equalization parameters corresponding to the first equalizer at the transmitter as the first equalization parameters, and determines the optimal equalization parameters corresponding to the receiver as the second equalization parameters. The preset stopping condition may be that the number of training iterations reaches a preset requirement, or that the model loss value meets a preset threshold requirement; this embodiment does not impose any restrictions on this.

[0107] Figure 2 This is a schematic diagram of the neural network model to be trained provided in the embodiments of this application, such as... Figure 2As shown, the channel is a black box for both the transmitter and receiver. In this embodiment, the activation parameters are introduced into the neural network model to be trained (i.e., the training model) based on the attenuation of high-frequency components during channel transmission. Influence factors between signal bits are also introduced to construct inter-symbol parameters. Because the high-frequency and low-frequency components carried by the previous, current, and next bits are different during signal transmission, their attenuation in the channel is different, resulting in different inter-symbol interference for each bit. A hidden layer can be defined to represent the different hidden states of the signal during channel transmission. See also... Figure 2 The neural network model to be trained may include an input layer, a hidden layer, and an output layer. The input layer is used to receive the input model training samples, the hidden layer is used to set the activation parameters and inter-symbol parameters, and the output layer is used to output the first equalization parameter and the second equalization parameter.

[0108] In this embodiment, the model training process may include: inputting the transmitted signal sub-samples and the feedback signal sub-samples corresponding to the signal sub-samples to be transmitted into the model to be trained; the model to be trained outputs a first equalization parameter and a second equalization parameter as the model output value. Based on the first and second equalization parameters (i.e., the sample label values) corresponding to the signal sub-samples to be transmitted in the sample labels, the difference between the model output value and the sample label value is calculated as the model loss value. Then, the activation parameters and inter-symbol parameters of the model to be trained are adjusted according to the model loss value. Specifically, the attenuation component of the activation parameters and the high-frequency and low-frequency components in the inter-symbol parameters are adjusted according to the model loss value, for example, reducing the 2dB attenuation component to 1dB, so that the activation parameters and inter-symbol parameters better match the actual channel characteristics between the transmitter and receiver. Under the condition of meeting a preset threshold requirement, an equalization parameter adjustment model is obtained. The preset threshold requirement may be that the loss value is less than a preset loss threshold. Under the condition of reaching a preset stopping condition, the current model to be trained can be determined as the equalization parameter adjustment model.

[0109] In this embodiment, training samples are input into the model to be trained. These training samples include a sub-sample of the signal to be transmitted and a corresponding feedback signal sub-sample. The model output value of the model to be trained is obtained, and a model loss value is determined based on the model output value and the sample labels corresponding to the training samples. The sample labels include a first equalization parameter and a second equalization parameter corresponding to the sub-sample of the signal to be transmitted. The model parameters of the model to be trained are adjusted according to the model loss value, and when a preset stopping condition is met, the current model to be trained is determined as the equalization parameter adjustment model. This allows the first and second equalization parameters output by the equalization parameter adjustment model to better match the signal to be transmitted, thereby improving the accuracy of the first and second equalization parameters output by the equalization parameter adjustment model and, to a certain extent, improving the equalization effect of the signal transmission method of this application.

[0110] Optionally, after step 105, the method further includes:

[0111] Step 301: Obtain the latest feedback signal sent by the receiving end; the latest feedback signal is obtained based on the second signal after the second equalizer performs equalization processing.

[0112] In this embodiment, after receiving the second signal, the receiving end can perform equalization processing on the second signal based on a second equalizer, and then send the equalized second signal as the latest feedback signal to the receiving end. Specifically, the second signal can be input into the second equalizer, which performs equalization processing on each bit of the second signal according to its preset equalization parameters to obtain the equalized second signal, and then uses the equalized second signal as the latest feedback signal. For example, the second equalizer can be a CTLE equalizer, and the equalization parameters of the CTLE equalizer can be multiplied by each bit of the second signal to obtain the equalized bits, thereby achieving equalization processing of the second signal and obtaining the equalized second signal. Then, the equalized second signal is sent as the latest feedback signal to the receiving end, and the sending end obtains the latest feedback signal sent by the receiving end.

[0113] Step 302: Determine the bit error rate corresponding to the latest feedback signal and the signal to be transmitted based on the latest feedback signal and the signal to be transmitted.

[0114] In this embodiment, the binary code of each bit of the latest feedback signal and the signal to be transmitted can be compared to determine the bit errors, i.e., the erroneous bits, in the signal transmission process between the transmitting and receiving ends. Then, the bit error rate (Symbol Error Rate, SER) of the signal to be transmitted can be calculated based on the number of bit errors and the total number of bits in the signal to be transmitted. Specifically, it can be referred to the following formula (2):

[0115] Bit error rate = Bit errors during transmission / Total number of bits transmitted in the signal to be transmitted × 100% (2)

[0116] Step 303: If the bit error rate meets the preset threshold requirement, send a transmission success instruction to the receiving end; the transmission success instruction is used to inform the receiving end that the bit error rate meets the preset threshold requirement.

[0117] In this embodiment, the preset threshold requirement can be set according to the actual needs of signal transmission between the transmitting and receiving ends. The preset threshold requirement can be a bit error rate of 0 or a fixed value, for example, a preset threshold requirement of SER≤10E-6. This is only an example for illustration, and this embodiment does not impose any limitations on it.

[0118] In this embodiment of the application, when the bit error rate meets the preset threshold requirement, such as when the bit error rate is 0 or less than the preset threshold, it indicates that the signal to be transmitted has been successfully transmitted from the sending end to the receiving end. The sending end can send a transmission success instruction to the receiving end. The transmission success instruction can be a special code agreed upon by the sending end and the receiving end. This embodiment of the application does not limit this.

[0119] In another feasible implementation, if the bit error rate does not meet the preset threshold requirement, it indicates that the signal to be transmitted has not been successfully transmitted to the receiving end. The first equalizer and the second equalizer need to be adjusted again. Steps 103 to 105 and steps 301 to 302 of the aforementioned embodiment can be executed repeatedly until the signal to be transmitted is successfully transmitted, i.e., the bit error rate meets the preset threshold requirement, and a transmission success command is sent to the receiving end.

[0120] In this embodiment, the latest feedback signal sent by the receiving end is obtained; the latest feedback signal is obtained after the second signal is equalized by the second equalizer; the bit error rate corresponding to the latest feedback signal and the signal to be transmitted is determined according to the latest feedback signal and the signal to be transmitted; if the bit error rate meets the preset threshold requirement, a transmission success instruction is sent to the receiving end; the transmission success instruction is used to inform the receiving end that the bit error rate meets the preset threshold requirement. Thus, since the latest feedback signal is obtained after the second signal is equalized by the adjusted second equalizer, and the bit error rate is determined based on the latest feedback signal and the signal to be transmitted, it is convenient to determine whether the signal to be transmitted has been successfully transmitted based on whether the bit error rate meets the preset threshold requirement. Sending a transmission success instruction to the receiving end when the signal to be transmitted is successfully transmitted, i.e., when the bit error rate meets the preset threshold requirement, to inform the receiving end that the signal to be transmitted has been successfully transmitted, can improve the practicality of the signal transmission method in this embodiment.

[0121] Figure 3 This is a schematic diagram of the signal transmission process in existing technology, such as... Figure 3 As shown, the signal to be transmitted is converted from parallel data to serial data by a serializer. The signal to be transmitted is then processed by the equalizer at the transmitting end: a feed forward equalizer (FFE) and output. After being transmitted through the channel, the receiving end receives the signal through a CTLE equalizer and a DFE equalizer and performs equalization processing. The equalized signal is then converted from serial data to parallel data by a deserializer and output.

[0122] Figure 4 This is a schematic diagram of the equalization process of the signal transmission method provided in the embodiments of this application, as shown below. Figure 4As shown, the signal to be transmitted is input into the first equalizer at the transmitting end for equalization processing to obtain a first signal. This first signal is then transmitted to the receiving end via the channel between the transmitting and receiving ends. The receiving end inputs the first signal into a second equalizer for equalization processing to obtain a feedback signal, which is then returned to the transmitting end. The transmitting end inputs the signal to be transmitted and the feedback signal into the equalization parameter adjustment model to obtain the first equalization parameter and the second equalization parameter output by the model. The transmitting end adjusts the first equalizer according to the first equalization parameter and sends the second equalization parameter to the receiving end for adjustment. Then, the signal to be transmitted is input into the adjusted first equalizer for equalization processing to obtain a second signal, which is then sent to the receiving end. The receiving end performs equalization processing on the second signal based on the second equalizer to obtain the latest feedback signal, which is returned to the transmitting end. The transmitting end determines the latest bit error rate (BER) based on the signal to be transmitted and the latest feedback signal. If the BER meets a preset threshold, a transmission success command is sent to the receiving end; otherwise, the signal to be transmitted and the latest feedback signal are input into the equalization parameter adjustment model again, and this process is repeated until the BER meets the preset threshold, indicating that the signal to be transmitted has been successfully transmitted to the receiving end.

[0123] Figure 5 This is a flowchart of another signal transmission method provided in an embodiment of this application, as shown below. Figure 5 As shown, this signal transmission method is applied at a receiving end, which includes a second equalizer, and the method includes:

[0124] Step 401: Receive the first signal sent by the transmitting end, which is obtained after the first equalizer has performed equalization processing on the signal to be transmitted.

[0125] Step 402: The first signal is processed by the second equalizer to obtain a feedback signal, and the feedback signal is sent to the transmitting end; the transmitting end is used to take the feedback signal and the signal to be transmitted as inputs to a preset equalization parameter adjustment model, obtain the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model, adjust the first equalizer according to the first equalization parameter, and send the second equalization parameter to the receiving end.

[0126] Step 403: Receive the second equalization parameter sent by the sending end, and adjust the second equalizer according to the second equalization parameter.

[0127] Step 404: Receive the second signal obtained by the transmitting end after equalizing the signal to be transmitted based on the adjusted first equalizer.

[0128] In this embodiment, the receiving end can be a computer device such as a computer or server. The transmitting end and the receiving end can be connected via a bus and signal transmission can be achieved through the bus, such as a PCIe bus. The second equalizer can be an equalizer that improves high-frequency attenuation, such as a DFE equalizer or a CTLE equalizer. This is only an example and this embodiment does not limit the scope of the application.

[0129] In this embodiment, after receiving the first signal, the receiving end can input the first signal into a second equalizer. The second equalizer performs equalization processing on each bit of the first signal according to its preset equalization parameters to obtain the equalized first signal. For example, the second equalizer can be a CTLE equalizer. The CTLE equalizer is used to suppress low-frequency components and compensate for high-frequency components through preset equalization parameters. By peak clipping and valley filling, waveform distortion can be reduced. The equalization parameters of the CTLE equalizer can be multiplied by each bit of the first signal to obtain the equalized bits, thereby achieving equalization processing of the first signal and obtaining the equalized first signal. Then, the equalized first signal is sent to the receiving end as a feedback signal.

[0130] In this embodiment, the steps performed by the transmitting end can be referred to the description of steps 103-106 in the aforementioned embodiments, and will not be repeated here. Specifically, the receiving end adjusts the second equalizer according to the second equalization parameter by adjusting the internal equalization parameters of the second equalizer to the second equalization parameter. For example, the original equalization parameters of the CTLE equalizer are adjusted to the second equalization parameter. Then, the receiving end receives the second signal obtained by the transmitting end after equalizing the signal to be transmitted based on the adjusted first equalizer.

[0131] In this embodiment, the feedback signal is obtained by the receiving end after the signal to be transmitted has been equalized by the first equalizer. Therefore, the feedback signal is associated with the first equalizer and the second equalizer. The feedback signal and the signal to be transmitted are input into the equalization parameter adjustment model to obtain the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model. This allows the first equalization parameter and the second equalization parameter to be matched with the signal to be transmitted, the first equalizer, and the second equalizer, respectively. Adjusting the first equalizer according to the first equalization parameter makes the adjusted first equalizer more compatible with the signal to be transmitted, improving the equalization effect of the adjusted first equalizer on the signal to be transmitted, thereby improving the signal quality of the second signal. Then, the second signal is sent to the receiving end so that the receiving end can perform equalization processing on the second signal based on the adjusted second equalizer to obtain the equalized second signal. Since adjusting the second equalizer according to the second equalization parameter makes the adjusted second equalizer more compatible with the signal to be transmitted, the signal quality of the equalized second signal can be improved. Compared to existing signal transmission methods, this approach avoids the negotiation process between the transmitter and receiver regarding equalization parameters. The first and second equalization parameters are obtained directly based on the equalization parameter adjustment model, which improves the efficiency of obtaining equalization parameters and, to some extent, enhances the equalization efficiency of the signal transmission process between the transmitter and receiver.

[0132] Optionally, after step 404, the method further includes:

[0133] Step 501: The second signal is subjected to equalization processing based on the adjusted second equalizer to obtain the latest feedback signal, and the latest feedback signal is sent to the transmitting end; the receiving end is used to determine the bit error rate corresponding to the latest feedback signal and the signal to be transmitted based on the latest feedback signal and the signal to be transmitted, and to send a transmission success instruction to the receiving end if the bit error rate meets the preset threshold requirement; the transmission success instruction is used to inform the receiving end that the bit error rate meets the preset threshold requirement.

[0134] In this embodiment, after receiving the second signal, the receiving end can input the second signal into an adjusted second equalizer. The adjusted second equalizer performs equalization processing on each bit of the second signal according to the second equalization parameters to obtain the equalized second signal. For example, the second equalizer can be a CTLE equalizer, which can multiply the second equalization parameters by each bit of the second signal to obtain the equalized bits, thereby achieving equalization processing of the second signal and obtaining the equalized second signal. Then, the equalized second signal is sent to the receiving end as the latest feedback signal. The steps performed by the transmitting end can refer to the description of steps 301 to 303 in the aforementioned embodiments, and will not be repeated here.

[0135] In this embodiment, the second signal is equalized using the adjusted second equalizer to obtain a latest feedback signal, which is then sent to the transmitting end. The receiving end determines the bit error rate (BER) corresponding to the latest feedback signal and the signal to be transmitted based on the latest BER and the signal to be transmitted. If the BER meets a preset threshold requirement, the receiving end sends a transmission success instruction to the receiving end. The transmission success instruction informs the receiving end that the BER meets the preset threshold requirement. This allows the transmitting end to easily determine the BER based on the latest feedback signal and the signal to be transmitted, and conveniently judge whether the signal to be transmitted has been successfully transmitted based on whether the BER meets the preset threshold requirement, thus improving the practicality of the signal transmission method in this embodiment.

[0136] Optionally, the method further includes:

[0137] Step 601: Receive the transmission success instruction sent by the sending end.

[0138] Step 602: In response to the transmission success command, perform specified processing on the latest feedback signal.

[0139] In this embodiment of the application, the receiving end may include a deserializer. The receiving end receives a transmission success instruction sent by the sending end. In response to the transmission success instruction, the receiving end can input the latest feedback signal into the deserializer for decoding to obtain parallel data. Then, the parallel data can be processed in other ways according to actual needs. This is only an example and this embodiment of the application does not limit the scope of the application.

[0140] In this embodiment, a transmission success command is received from the transmitting end; in response to the transmission success command, the latest feedback signal undergoes specified processing. Thus, since the signal transmission command is sent from the transmitting end to the receiving end when the bit error rate meets a preset threshold requirement, and the bit error rate is determined by the transmitting end based on the signal to be transmitted and the latest feedback signal from the receiving end, it is easy to determine that the receiving end has successfully received the signal to be transmitted, and the latest feedback signal can be specified, thereby improving the practicality of the signal transmission method in this embodiment.

[0141] See Figure 6 This application provides a signal transmission device applied at a transmitting end, the transmitting end including a first equalizer, and the device 70 including:

[0142] The first execution module 701 is used to perform equalization processing on the signal to be transmitted based on the first equalizer to obtain a first signal, and send the first signal to the receiving end.

[0143] The first acquisition module 702 is used to acquire the feedback signal sent by the receiving end; the feedback signal is obtained by equalizing the first signal based on the second equalizer in the receiving end.

[0144] The second acquisition module 703 is used to take the feedback signal and the signal to be transmitted as inputs to a preset equalization parameter adjustment model, and acquire the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model.

[0145] The adjustment module 704 is used to adjust the first equalizer according to the first equalization parameter, and send the second equalization parameter to the receiving end; the second equalization parameter is used by the receiving end to adjust the second equalizer.

[0146] The second execution module 705 is used to perform equalization processing on the signal to be transmitted based on the adjusted first equalizer to obtain a second signal, and send the second signal to the receiving end.

[0147] Optionally, the second acquisition module 703 is specifically used for:

[0148] The feedback signal and the signal to be transmitted are used as inputs to the equalization parameter adjustment model;

[0149] Based on the activation parameter and inter-symbol parameter in the equalization parameter adjustment model, as well as the feedback signal and the signal to be transmitted, the first equalization parameter and the second equalization parameter are determined.

[0150] Obtain the first equilibrium parameter and the second equilibrium parameter output by the equilibrium parameter adjustment model.

[0151] Optionally, the equilibrium parameter adjustment model is obtained in the following way:

[0152] The training samples are input into the model to be trained; the training samples include the signal sub-samples to be transmitted and the feedback signal sub-samples corresponding to the signal sub-samples to be transmitted.

[0153] Obtain the model output value of the model to be trained, and determine the model loss value based on the model output value and the sample labels corresponding to the model training samples; the sample labels include the first equalization parameter and the second equalization parameter corresponding to the signal sub-sample to be transmitted;

[0154] The model parameters of the model to be trained are adjusted according to the model loss value, and the current model to be trained is determined as the equilibrium parameter adjustment model when the preset stopping condition is met.

[0155] Optionally, the device 70 further includes:

[0156] The third acquisition module is used to acquire the latest feedback signal sent by the receiving end after the second execution module performs equalization processing on the signal to be transmitted based on the adjusted first equalizer to obtain a second signal and sends the second signal to the receiving end; the latest feedback signal is obtained based on the equalization processing of the second signal by the second equalizer;

[0157] The determining module is used to determine the bit error rate corresponding to the latest feedback signal and the signal to be transmitted based on the latest feedback signal and the signal to be transmitted.

[0158] The sending module is used to send a transmission success instruction to the receiving end when the bit error rate meets the preset threshold requirement; the transmission success instruction is used to inform the receiving end that the bit error rate meets the preset threshold requirement.

[0159] The signal transmission device and the signal transmission method described in the foregoing embodiments have the same advantages over the prior art, and will not be repeated here.

[0160] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0161] See Figure 7 This application provides another signal transmission device applied at a receiving end, the receiving end including a second equalizer, the device 80 including:

[0162] The first receiving module 801 is used to receive the first signal sent by the transmitting end after the first equalizer has performed equalization processing on the signal to be transmitted.

[0163] Feedback module 802 is used to perform equalization processing on the first signal based on the second equalizer to obtain a feedback signal, and send the feedback signal to the transmitting end; the transmitting end is used to take the feedback signal and the signal to be transmitted as inputs to a preset equalization parameter adjustment model, obtain the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model, adjust the first equalizer according to the first equalization parameter, and send the second equalization parameter to the receiving end.

[0164] The adjustment module 803 is used to receive the second equalization parameters sent by the transmitting end, and adjust the second equalizer according to the second equalization parameters;

[0165] The second receiving module 804 is used to receive the second signal obtained by the transmitting end after the signal to be transmitted is equalized based on the adjusted first equalizer.

[0166] Optionally, the device 80 further includes:

[0167] The third receiving device is used to receive the transmission success instruction sent by the sending end;

[0168] The processing module is used to perform specified processing on the feedback signal in response to the transmission success command.

[0169] The signal transmission device and the signal transmission method described in the foregoing embodiments have the same advantages over the prior art, and will not be repeated here.

[0170] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0171] This application also provides an electronic device, see [link to document]. Figure 8 The system includes: a processor 901, a memory 902, and a computer program 9021 stored in the memory and executable on the processor. When the processor executes the program, it implements the alarm data processing method of the foregoing embodiments.

[0172] This application also provides a readable storage medium that, when the instructions in the storage medium are executed by the processor of an electronic device, enables the electronic device to perform the alarm data processing method of the foregoing embodiments.

[0173] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. The structure required to construct such a system is obvious from the above description. Furthermore, this application is not directed to any particular programming language. It should be understood that the content of this application described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of this application.

[0174] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0175] Similarly, it should be understood that, in order to simplify this application and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of this application, various features of this application are sometimes grouped together into a single embodiment, figure, or description thereof. However, this method of disclosure should not be construed as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of this application.

[0176] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0177] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the sequencing device according to this application. This application can also be implemented as a device or apparatus program for performing part or all of the methods described herein. Such an implementation of this application can be stored on a computer-readable medium, or can take the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0178] It should be noted that the above embodiments are illustrative of this application and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0179] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0180] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

[0181] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0182] It should be noted that the various data-related processes in the embodiments of this application are carried out in compliance with the relevant data protection laws and policies of the country where the location is located, and with the authorization granted by the owner of the corresponding device.

Claims

1. A signal transmission method, characterized by, The method is applied to a sending end including a first equalizer, and the method comprises: performing equalization processing on a to-be-transmitted signal based on the first equalizer to obtain a first signal, and sending the first signal to a receiving end; obtaining a feedback signal sent by the receiving end; the feedback signal is obtained based on equalization processing on the first signal by a second equalizer in the receiving end; taking the feedback signal and the to-be-transmitted signal as inputs of a preset equalization parameter adjustment model, obtaining first equalization parameters and second equalization parameters output by the equalization parameter adjustment model; adjusting the first equalizer according to the first equalization parameters, and sending the second equalization parameters to the receiving end; the second equalization parameters are used for adjusting the second equalizer by the receiving end; performing equalization processing on the to-be-transmitted signal based on the adjusted first equalizer to obtain a second signal, and sending the second signal to the receiving end; wherein the taking the feedback signal and the to-be-transmitted signal as inputs of the preset equalization parameter adjustment model, and obtaining the first equalization parameters and the second equalization parameters output by the equalization parameter adjustment model comprises: taking the feedback signal and the to-be-transmitted signal as inputs of the equalization parameter adjustment model; determining the first equalization parameters and the second equalization parameters based on active parameters and inter-symbol parameters in the equalization parameter adjustment model, and the feedback signal and the to-be-transmitted signal; obtaining the first equalization parameters and the second equalization parameters output by the equalization parameter adjustment model.

2. The method of claim 1, wherein, The equalization parameter adjustment model is obtained by: inputting a model training sample into a to-be-trained model; the model training sample comprises a to-be-transmitted signal sub-sample and a feedback signal sub-sample corresponding to the to-be-transmitted signal sub-sample; obtaining a model output value of the to-be-trained model, and determining a model loss value according to the model output value and a sample label corresponding to the model training sample; the sample label comprises first equalization parameters and second equalization parameters corresponding to the to-be-transmitted signal sub-sample; adjusting model parameters of the to-be-trained model according to the model loss value, and determining the current to-be-trained model as the equalization parameter adjustment model in the case of reaching a preset stop condition.

3. The method of claim 2, wherein, After the performing equalization processing on the to-be-transmitted signal based on the adjusted first equalizer to obtain a second signal, and sending the second signal to the receiving end, the method further comprises: obtaining a latest feedback signal sent by the receiving end; the latest feedback signal is obtained based on equalization processing on the second signal by the second equalizer; determining a bit error rate corresponding to the latest feedback signal and the to-be-transmitted signal according to the latest feedback signal and the to-be-transmitted signal; in the case that the bit error rate meets a preset threshold requirement, sending a transmission success instruction to the receiving end; the transmission success instruction is used to inform the receiving end that the bit error rate meets the preset threshold requirement.

4. A signal transmission method characterized by, The method is applied to a receiving end including a second equalizer, and the method comprises: receive a first signal obtained by performing equalization processing on the to-be-transmitted signal based on a first equalizer by a sending end; perform equalization processing on the first signal based on a second equalizer to obtain a feedback signal, and send the feedback signal to the sending end; the sending end is configured to take the feedback signal and the to-be-transmitted signal as inputs of a preset equalization parameter adjustment model, obtain first equalization parameters and second equalization parameters output by the equalization parameter adjustment model, adjust the first equalization parameter based on the first equalization parameter, and send the second equalization parameter to the receiving end; receive the second equalization parameter sent by the sending end, and adjust the second equalization parameter based on the second equalization parameter; receive a second signal obtained by performing equalization processing on the to-be-transmitted signal based on the adjusted first equalizer by the sending end; wherein the sending end is configured to take the feedback signal and the to-be-transmitted signal as inputs of a preset equalization parameter adjustment model, obtain first equalization parameters and second equalization parameters output by the equalization parameter adjustment model, and the method comprises: taking the feedback signal and the to-be-transmitted signal as inputs of the equalization parameter adjustment model; determining the first equalization parameter and the second equalization parameter based on active parameters and inter-symbol parameters in the equalization parameter adjustment model, and the feedback signal and the to-be-transmitted signal; obtaining the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model.

5. The method of claim 4, wherein, After receiving the second signal obtained by performing equalization processing on the to-be-transmitted signal based on the adjusted first equalizer by the sending end, the method further comprises: performing equalization processing on the second signal based on the adjusted second equalizer to obtain a latest feedback signal, and sending the latest feedback signal to the sending end; the receiving end is configured to determine a bit error rate corresponding to the latest feedback signal and the to-be-transmitted signal based on the latest feedback signal and the to-be-transmitted signal, and send a transmission success instruction to the receiving end in a case where the bit error rate meets a preset threshold requirement; the transmission success instruction is used to inform the receiving end that the bit error rate meets the preset threshold requirement.

6. A signal transmission device, characterized by comprising: The sending end comprises a first equalizer, and the device comprises: a first execution module configured to perform equalization processing on a to-be-transmitted signal based on the first equalizer to obtain a first signal, and send the first signal to a receiving end; a first acquisition module configured to acquire a feedback signal sent by the receiving end; the feedback signal is obtained by performing equalization processing on the first signal based on a second equalizer in the receiving end; a second acquisition module configured to take the feedback signal and the to-be-transmitted signal as inputs of a preset equalization parameter adjustment model, and obtain first equalization parameters and second equalization parameters output by the equalization parameter adjustment model; an adjustment module configured to adjust the first equalization parameter based on the first equalization parameter, and send the second equalization parameter to the receiving end; the second equalization parameter is used for adjusting the second equalization parameter by the receiving end; The second execution module is configured to perform equalization processing on the to-be-transmitted signal based on the adjusted first equalizer to obtain a second signal, and send the second signal to the receiving end. The second obtaining module is configured to: input the feedback signal and the to-be-transmitted signal into the equalization parameter adjustment model; determine the first equalization parameter and the second equalization parameter based on the activation parameter and the inter-code parameter in the equalization parameter adjustment model, and the feedback signal and the to-be-transmitted signal; obtain the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model.

7. A signal transmission device, characterized by comprising: The receiving end comprises a second equalizer, and the device comprises: The first receiving module is configured to receive a first signal sent by the sending end, the first signal being obtained by performing equalization processing on a to-be-transmitted signal based on a first equalizer. The feedback module is configured to perform equalization processing on the first signal based on the second equalizer to obtain a feedback signal, and send the feedback signal to the sending end. The sending end is configured to input the feedback signal and the to-be-transmitted signal into a preset equalization parameter adjustment model, obtain a first equalization parameter and a second equalization parameter output by the equalization parameter adjustment model, adjust the first equalizer according to the first equalization parameter, and send the second equalization parameter to the receiving end. The adjustment module is configured to receive the second equalization parameter sent by the sending end, and adjust the second equalizer according to the second equalization parameter. The second receiving module is configured to receive a second signal sent by the sending end, the second signal being obtained by performing equalization processing on the to-be-transmitted signal based on the adjusted first equalizer. The sending end is configured to input the feedback signal and the to-be-transmitted signal into a preset equalization parameter adjustment model, obtain a first equalization parameter and a second equalization parameter output by the equalization parameter adjustment model, including: input the feedback signal and the to-be-transmitted signal into the equalization parameter adjustment model; determine the first equalization parameter and the second equalization parameter based on the activation parameter and the inter-code parameter in the equalization parameter adjustment model, and the feedback signal and the to-be-transmitted signal; 8. An electronic device, comprising: obtain the first equalization parameter and the second equalization parameter output by the equalization parameter adjustment model. The device comprises:

9. A readable storage medium, characterized by, a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the signal transmission method according to any one of claims 1-5 when executing the program. When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute the signal transmission method according to any one of claims 1-5.

Images