Signal processing method and device, electronic equipment, medium and chip

Abstract

The invention provides a signal processing method and device, electronic equipment, a medium and a chip, and relates to the technical field of signal processing, and the method comprises the steps: obtaining a first signal which comprises a pilot signal and a data signal; training a channel related parameter prediction model based on the pilot signal and the data signal to obtain a target model; acquiring a second signal, and determining a channel correlation coefficient corresponding to the second signal by using the target model; and processing the second signal based on the channel correlation coefficient corresponding to the second signal, training a channel correlation parameter prediction model by adding a data signal as training data on the basis of the pilot signal, and predicting the second signal by using the trained channel correlation parameter prediction model. According to the method, the channel correlation coefficient corresponding to the second signal is obtained, so that when the channel correlation coefficient is used for processing the second signal, the influence of processing delay on real-time estimation of the frequency of the second signal can be overcome, and prediction and tracking are realized.

Description

Technical Field

[0001] The present disclosure relates to the technical field of signal processing, and in particular, to a signal processing method, apparatus, electronic device, medium, and chip. Background Art

[0002] In related signal processing solutions, it is defined to estimate the carrier frequency offset (CFO) using a short training sequence (STS) / long training sequence (LTS). Usually, the known repeated sequence of STS (i.e., the pilot signal) is first used to roughly estimate the carrier frequency offset, and then the repeated sequences of two LTSs are used for further estimation, which can achieve the estimation of the carrier frequency offset. However, at low signal-to-noise ratios, there is still a large frequency offset estimation error in this method, and real-time prediction and tracking of signals cannot be achieved. Summary of the Invention

[0003] The present disclosure provides a signal processing method, apparatus, electronic device, medium, and chip to solve the problem that real-time prediction and tracking cannot be achieved due to frequency offset errors in related solutions.

[0004] An embodiment of the first aspect of the present disclosure provides a signal processing method, which includes: obtaining a first signal, where the first signal includes a pilot signal and a data signal; training a channel correlation parameter prediction model based on the pilot signal and the data signal to obtain a target model; obtaining a second signal, and using the target model to determine a channel correlation coefficient corresponding to the second signal; and processing the second signal based on the channel correlation coefficient corresponding to the second signal.

[0005] In some embodiments of the present disclosure, training a channel correlation parameter prediction model based on the pilot signal and the data signal to obtain a target model includes: determining a channel correlation coefficient corresponding to the first signal based on the pilot signal and the data signal; using the channel correlation coefficient corresponding to the first signal as training data to iteratively train the correlation parameter prediction model; determining a prediction error for each iterative training, and ending the training to obtain the target model when the prediction error meets a preset condition.

[0006] In some embodiments of the present disclosure, determining a channel correlation coefficient corresponding to the first signal based on the pilot signal and the data signal includes: determining a channel estimation value corresponding to the i-th data in the sequence of the first signal based on the pilot signal and the data signal; performing segmentation processing on the first signal to obtain n segmented signals, where the sequence length of each segmented signal is w, and n≥2; and performing correlation processing on the channel estimation values of the n segmented signals to obtain a channel correlation coefficient corresponding to the first signal.

[0007] In some embodiments of the present disclosure, determining a channel estimation value corresponding to the i-th data in the sequence of the first signal based on a pilot signal and a data signal includes: performing symbol reconstruction and decoding processing on the data signal to obtain a first reconstructed symbol; performing reliability processing on the first reconstructed symbol to obtain a second reconstructed symbol, where the reliability processing is used to determine whether the first reconstructed symbol is the reconstructed symbol closest to the data signal; and performing channel estimation based on the pilot signal and the second reconstructed symbol to obtain the channel estimation value corresponding to the i-th data in the sequence of the first signal.

[0008] In some embodiments of the present disclosure, performing correlation processing on the channel estimation values of n segmented signals to obtain a channel correlation coefficient corresponding to the first signal includes: correlating the channel estimation value corresponding to the i-th data with the channel estimation value corresponding to the (i - w)-th data to obtain w correlation values, where the i-th data belongs to the first segmented signal among the n segmented signals, and the (i - w)-th data belongs to the segmented signal preceding the first segmented signal; and summing the w correlation values to obtain the channel correlation coefficient corresponding to the first signal.

[0009] In some embodiments of the present disclosure, determining a prediction error for each iterative training includes: determining a delay decision parameter; and determining the prediction error according to the delay decision parameter, the channel correlation coefficient corresponding to the first signal, the number of taps of the coefficient to be predicted, and the iterative coefficient.

[0010] In some embodiments of the present disclosure, determining the delay decision parameter includes: determining whether there is frequency drift in the current communication system; in the case where there is no frequency drift in the current communication system, determining the delay decision parameter as a preset value; and in the case where there is frequency drift in the current communication system, determining the delay decision parameter according to the decoding delay, the calculation delay, and the sequence length w of each segmented signal.

[0011] In some embodiments of the present disclosure, processing the second signal based on the channel correlation coefficient corresponding to the second signal includes: determining a phase angle corresponding to the second signal based on the channel correlation coefficient corresponding to the second signal; determining a frequency offset of the second signal based on the phase angle and the sequence length w of each segmented signal; and performing deviation correction processing on the second signal based on the frequency offset.

[0012] A second aspect embodiment of the present disclosure provides a signal processing apparatus, which includes:

[0013] An acquisition module, configured to acquire a first signal, where the first signal includes a pilot signal and a data signal;

[0014] A training module, configured to train a channel correlation parameter prediction model based on the pilot signal and the data signal to obtain a target model;

[0015] A determination module, configured to obtain a second signal and determine a channel correlation coefficient corresponding to the second signal by using a target model;

[0016] A processing module, configured to process the second signal based on the channel correlation coefficient corresponding to the second signal.

[0017] In some embodiments of the present disclosure, a training module is configured to: determine a channel correlation coefficient corresponding to a first signal based on a pilot signal and a data signal; use the channel correlation coefficient corresponding to the first signal as training data to iteratively train a correlation parameter prediction model; determine a prediction error for each iterative training, and end the training when the prediction error meets a preset condition to obtain a target model.

[0018] In some embodiments of the present disclosure, the training module is further configured to: determine a channel estimation value corresponding to the i-th data in the sequence of the first signal based on the pilot signal and the data signal; perform segmentation processing on the first signal to obtain n segmented signals, where the sequence length of each segmented signal is w, and n≥2; perform correlation processing on the channel estimation values of the n segmented signals to obtain a channel correlation coefficient corresponding to the first signal.

[0019] In some embodiments of the present disclosure, the training module is further configured to: perform symbol reconstruction and decoding processing on the data signal to obtain a first reconstructed symbol; perform reliability processing on the first reconstructed symbol to obtain a second reconstructed symbol, where the reliability processing is used to determine whether the first reconstructed symbol is the reconstructed symbol closest to the data signal; perform channel estimation based on the pilot signal and the second reconstructed symbol to obtain a channel estimation value corresponding to the i-th data in the sequence of the first signal.

[0020] In some embodiments of the present disclosure, the training module is further configured to: associate the channel estimation value corresponding to the i-th data with the channel estimation value corresponding to the (i - w)-th data to obtain w association values, where the i-th data belongs to the first segmented signal among the n segmented signals, and the (i - w)-th data belongs to the segmented signal preceding the first segmented signal; sum the w association values to obtain a channel correlation coefficient corresponding to the first signal.

[0021] In some embodiments of the present disclosure, the training module is further configured to: determine a delay decision parameter; determine a prediction error according to the delay decision parameter, the channel correlation coefficient corresponding to the first signal, the number of taps of the coefficient to be predicted, and an iteration coefficient.

[0022] In some embodiments of the present disclosure, the training module is further configured to: determine whether there is frequency drift in the current communication system; when there is no frequency drift in the current communication system, determine the delay decision parameter as a preset value; when there is frequency drift in the current communication system, determine the delay decision parameter according to the decoding delay, the calculation delay, and the sequence length w of each segmented signal.

[0023] In some embodiments of the present disclosure, a processing module is configured to: determine a phase angle corresponding to a second signal based on a channel correlation coefficient corresponding to the second signal; determine a frequency offset of the second signal based on the phase angle and the sequence length w of each segmented signal; and perform deviation correction processing on the second signal based on the frequency offset.

[0024] An embodiment of the third aspect of the present disclosure provides an electronic device, including: 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 to enable the at least one processor to execute the method described in the embodiment of the first aspect of the present disclosure.

[0025] An embodiment of the fourth aspect of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method described in the embodiment of the first aspect of the present disclosure.

[0026] An embodiment of the fifth aspect of the present disclosure provides a chip, which includes at least one processor and a communication interface; the communication interface is configured to receive a signal input to the chip or a signal output from the chip, and the processor communicates with the communication interface and implements the method described in the first aspect of the present disclosure through logic circuits or by executing code instructions.

[0027] In summary, according to the signal processing method proposed by the present disclosure, a first signal is obtained, and the first signal includes a pilot signal and a data signal; based on the pilot signal and the data signal, a channel correlation parameter prediction model is trained to obtain a target model; a second signal is obtained, and the target model is used to determine a channel correlation coefficient corresponding to the second signal; based on the channel correlation coefficient corresponding to the second signal, the second signal is processed. By adding a data signal as training data to the pilot signal to train the channel correlation parameter prediction model, and then using the trained channel correlation parameter prediction model to predict the second signal to obtain the channel correlation coefficient corresponding to the second signal, when the second signal is processed using the channel correlation coefficient corresponding to the second signal, the influence of processing delay on the real-time estimation of the frequency of the second signal can be overcome, thereby achieving prediction and tracking.

[0028] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure and do not constitute an improper limitation to the present disclosure.

[0030] Figure 1 Schematic diagram of a frame structure provided by an embodiment of the present disclosure;

[0031] Figure 2 Schematic diagram of a carrier frequency offset error provided by an embodiment of the present disclosure;

[0032] Figure 3 Flowchart of a signal processing method provided by an embodiment of the present disclosure;

[0033] Figure 4 Flowchart of a signal processing method provided by an embodiment of the present disclosure;

[0034] Figure 5 Flowchart of a method for determining a delay decision parameter provided by an embodiment of the present disclosure;

[0035] Figure 6 Flowchart of a signal processing method provided by an embodiment of the present disclosure;

[0036] Figure 7 Schematic diagram of the structure of a signal processing device provided by an embodiment of the present disclosure;

[0037] Figure 8 Schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure;

[0038] Figure 9 Schematic diagram of the structure of a chip provided by an embodiment of the present disclosure. Detailed implementation manners

[0039] The embodiments of the present disclosure are described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The implementations described below with reference to the accompanying drawings.

[0040] In the Bluetooth 6.0 Higher Data Throughput (HDT) standard, the use of STS / LTS estimation for carrier frequency offset estimation is defined, and its frame structure is as Figure 1 shown, where STS is the short training sequence and LTS is the long training sequence, that is, the known repeated sequence of STS is used for coarse estimation of the carrier frequency offset, and the repeated sequences of two segments of LTS are used for further estimation. Figure 2 The error level of the CFO estimation is given. At low signal-to-noise ratio, there is still a 10 kHz frequency offset estimation error. For the rate-enhanced HDT mode, new pi / 4 QPSK, 8PSK, and 16QAM modulation methods are adopted, and their demodulation performance is severely limited by the phase rotation caused by the carrier frequency offset.

[0041] In addition, devices such as crystal oscillators used in Bluetooth have relatively low precision compared to cellular systems. To achieve the designed peak rate, the design solution needs to overcome the frequency offset caused by the devices.

[0042] To solve the problems existing in the related art, the present disclosure proposes a signal processing method, which includes obtaining a first signal, where the first signal includes a pilot signal and a data signal; training a channel-related parameter prediction model based on the pilot signal and the data signal to obtain a target model; obtaining a second signal, and using the target model to determine the channel-related coefficient corresponding to the second signal; processing the second signal based on the channel-related coefficient corresponding to the second signal. By adding the data signal to the pilot signal as training data to train the channel-related parameter prediction model, and then using the trained channel-related parameter prediction model to predict the second signal to obtain the channel-related coefficient corresponding to the second signal. Furthermore, when processing the second signal using the channel-related coefficient corresponding to the second signal, the influence of processing delay on the real-time frequency estimation of the second signal can be overcome, thereby achieving prediction and tracking.

[0043] The signal processing method proposed by the present disclosure can be widely applied to the field of signal processing, not limited to the high data throughput mode of Bluetooth, and can be extended to other mobile communication fields, including scenarios where frequency offsets exist in wireless communication signals such as cellular, WiFi, and satellite.

[0044] The following will introduce in detail the signal processing method provided by the present application with reference to the accompanying drawings.

[0045] Figure 3 It is a flowchart of a signal processing method provided by an embodiment of the present disclosure. As Figure 3 shown, the signal processing method includes steps 301 to 304.

[0046] Step 301, obtain a first signal, where the first signal includes a pilot signal and a data signal.

[0047] In some embodiments, the method described in the present disclosure can be executed by a terminal, such as a mobile phone, a computer, etc. It can also be executed by an AI server. Further, the method described in the present disclosure can also be executed by a chip, such as a baseband chip, a Bluetooth chip, a WiFi chip, etc.

[0048] In some embodiments, there can be one, two, or more first signals, and the present application does not limit the number of the first signals.

[0049] In some embodiments, the first signal can be a preprocessed signal.

[0050] In some embodiments, a receiver can be used to obtain the first signal from the channel. Specifically, it is not limited to the receiver of any device, as long as it has a signal receiving function, such as a terminal.

[0051] In some embodiments, a pilot signal refers to a signal with both known sequence of content and position.

[0052] In some embodiments, a data signal refers to a signal containing actual information.

[0053] In some embodiments, the first signal may include Bluetooth signals, WiFi signals, cellular signals, etc.

[0054] Step 302: Based on the pilot signal and the data signal, train a channel-related parameter prediction model to obtain a target model.

[0055] In some embodiments, the channel-related parameter refers to the average channel correlation coefficient. Specifically, the pilot signal and the data signal can be segmented at fixed intervals, and the channel correlation and classification are performed through the segmented signals to obtain the average channel correlation coefficient.

[0056] In some embodiments, the channel-related parameter prediction model can be a linear prediction model.

[0057] In some embodiments, by training the channel-related parameter prediction model based on the pilot signal and the data signal to obtain a target model, and since the target model is a trained model, when a signal is received again, the target model can be directly used to obtain the channel-related parameter corresponding to the signal, thereby improving the speed and accuracy of obtaining the channel correlation coefficient corresponding to the signal.

[0058] Step 303: Obtain a second signal and use the target model to determine the channel correlation coefficient corresponding to the second signal.

[0059] In some embodiments, the second signal may also include a pilot signal and a data signal.

[0060] In some embodiments, the number of the second signals can be multiple.

[0061] In some embodiments, the second signal may include Bluetooth signals, WiFi signals, cellular signals, etc.

[0062] In some embodiments, the foregoing first signal is used for training the target model, and the second signal is used for prediction of the target model.

[0063] In some embodiments, the formats and the numbers of the first signal and the second signal can be the same or different.

[0064] In some embodiments, by using the target model to determine the channel correlation coefficient corresponding to the second signal, the speed and accuracy of obtaining the channel correlation coefficient for the second signal can be improved.

[0065] Step 304: Process the second signal based on the channel correlation coefficient corresponding to the second signal.

[0066] In some embodiments, based on the channel correlation coefficient corresponding to the second signal, the frequency offset of the second signal can be calculated, and then the calculated frequency offset is used to correct the second signal.

[0067] In some embodiments, by processing the second signal based on the channel correlation coefficient corresponding to the second signal, the accuracy of frequency offset estimation can be improved, and then the tracking of the second signal can be achieved.

[0068] In summary, according to the signal processing method proposed in the present disclosure, a first signal is obtained, and the first signal includes a pilot signal and a data signal; based on the pilot signal and the data signal, a channel correlation parameter prediction model is trained to obtain a target model; a second signal is obtained, and the target model is used to determine the channel correlation coefficient corresponding to the second signal; the second signal is processed based on the channel correlation coefficient corresponding to the second signal. By adding the data signal as training data on the basis of the pilot signal to train the channel correlation parameter prediction model, and then using the trained channel correlation parameter prediction model to predict the second signal to obtain the channel correlation coefficient corresponding to the second signal. Furthermore, when processing the second signal using the channel correlation coefficient corresponding to the second signal, the influence of processing delay on the real-time frequency estimation of the second signal can be overcome, so as to achieve prediction and tracking.

[0069] Based on Figure 3 the embodiments shown, Figure 4 A flowchart of a signal processing method proposed in the present disclosure is further shown. Figure 4 Based on Figure 3 the embodiments shown, steps 302 and 303 are further defined. As Figure 4 shown, the method includes the following steps:

[0070] Step 401: Obtain a first signal, where the first signal includes a pilot signal and a data signal.

[0071] In some embodiments, the principle of step 401 is the same as that of step 301, and reference can be made to the relevant descriptions of the embodiments shown in step 301, which will not be elaborated here.

[0072] Step 402: Perform symbol reconstruction and decoding processing on the data signal to obtain a first reconstructed symbol.

[0073] In some embodiments, symbol reconstruction usually includes processes of preprocessing, demodulation, and symbol detection, and is used to convert the data signal into a modulated signal.

[0074] In some embodiments, the decoding process is used to convert the modulated signal into the original bit symbols, that is, by performing symbol reconstruction and decoding processing on the data signal, obtaining the first reconstructed symbol is the process of converting the data signal into bit symbols.

[0075] In some embodiments, the first reconstructed symbol may include reliable reconstructed symbols and unreliable reconstructed symbols. Among them, the reliable reconstructed symbol refers to the reconstructed symbol that is closest to the data signal. For example, due to the influence of channel noise, etc., the received data signal is (0.8, -0.5, 1.2, 0.9), and the first reconstructed signal is initially determined to be (1, 0, 1, 1). It is necessary to determine whether this first reconstructed symbol is the reconstructed symbol closest to the data signal (0.8, -0.5, 1.2, 0.9). Furthermore, the accuracy of frequency offset estimation can be improved by processing the reliable reconstructed symbols.

[0076] Step 403: Perform reliability processing on the first reconstructed symbol to obtain the second reconstructed symbol. The reliability processing is used to determine whether the first reconstructed symbol is the reconstructed symbol closest to the data signal.

[0077] In some embodiments, the second reconstructed symbol is the reconstructed symbol closest to the data signal.

[0078] In some embodiments, soft values can be used to perform reliability processing on the first reconstructed symbol to obtain the second reconstructed symbol. Specifically, the soft values can be represented in the form of probability or in the form of logarithmic likelihood ratio. Taking the soft value in the form of logarithmic likelihood ratio as an example, by calculating the logarithmic likelihood ratio of the data signal, quantifying and mapping the logarithmic likelihood ratio, the reliability of each first reconstructed signal is obtained. For example, a positive logarithmic likelihood ratio represents the reliability that the bit is 1, and a negative logarithmic likelihood ratio represents the reliability that the bit is 0. Since the soft value itself represents the reliable probability, the larger its absolute value, the higher the reliability of the first reconstructed symbol.

[0079] In some embodiments, the distance of the constellation points can also be used to perform reliability processing on the first reconstructed symbol to obtain the second reconstructed symbol. Specifically, by calculating the Euclidean distance between the received first reconstructed symbol and each possible symbol in the modulation constellation diagram, the reliability of each first reconstructed symbol is evaluated. For example, during the demodulation process, the signal received by the receiver may not exactly fall on the ideal constellation point position due to the influence of noise and interference. Therefore, it is necessary to determine which constellation point the received signal is closest to and quantify this degree of closeness. For example, the Euclidean distance between the data signal and the constellation point can be calculated respectively. The smaller the Euclidean distance, the higher the reliability of the first reconstructed symbol.

[0080] Step 404: Based on the pilot signal and the second reconstructed symbol, perform channel estimation to obtain the channel estimation value H corresponding to the i-th data in the sequence of the first signali .

[0081] In some embodiments, least-squares channel estimation may be performed on the pilot signal and the second reconstructed symbol to obtain the channel estimation value H corresponding to the i-th data in the sequence of the first signal i .

[0082] In some embodiments, minimum mean square error channel estimation may also be performed on the pilot signal and the second reconstructed symbol to obtain the channel estimation value H corresponding to the i-th data in the sequence of the first signal i .

[0083] In some embodiments, taking the least-squares channel estimation as an example of the channel estimation method, the channel estimation value H corresponding to the i-th data in the sequence of the first signal i is represented by the following mathematical expression:

[0084] H i = conj(R i ) * S i / (conj(R i ) * R i );

[0085] where S i is the pilot signal and the data signal, R i is the pilot signal and the second reconstructed symbol, conj() is the conjugate operation of a complex number, and H i is the channel estimation value corresponding to the i-th data in the sequence of the first signal.

[0086] Step 405: Segment the first signal to obtain n segmented signals, where the sequence length of each segmented signal is w and n ≥ 2.

[0087] In some embodiments, the sequence lengths of each first signal may be the same or different, and this application does not limit this.

[0088] In some embodiments, segmenting each first signal may obtain the same or different numbers of segmented signals, and the length of each segment may also be the same or different.

[0089] In some embodiments, for example, segmenting a first signal with a sequence length of 10 results in two segmented signals, each with a sequence length of 5; segmenting a first signal with a sequence length of 20 results in two segmented signals, each with a sequence length of 10; and segmenting a first signal with a sequence length of 20 results in four segmented signals, each with a sequence length of 5.

[0090] Step 406: The channel estimation value H corresponding to the i-th datai is associated with the channel estimation value H corresponding to the (i - w)-th data i-w to obtain w associated values.

[0091] In some embodiments, the i-th data belongs to the first segmented signal among n segmented signals, and the (i - w)-th data belongs to the segmented signal preceding the first segmented signal;

[0092] In some embodiments, taking the example in step 405 where the first signal with a sequence length of 10 is segmented to obtain two segmented signals, each with a sequence length of 5, the length w is 5, and the number of segments n is 2. The channel estimation value H6 corresponding to the 6th data is associated with the channel estimation value H1 corresponding to the 1st data; the channel estimation value H7 corresponding to the 7th data is associated with the channel estimation value H2 corresponding to the 2nd data; the channel estimation value H8 corresponding to the 8th data is associated with the channel estimation value H3 corresponding to the 3rd data; the channel estimation value H9 corresponding to the 9th data is associated with the channel estimation value H4 corresponding to the 4th data; the channel estimation value H 10 corresponding to the 10th data is associated with the channel estimation value H5 corresponding to the 5th data, and 5 associated values can be obtained.

[0093] Step 407: Sum the w associated values to obtain the channel correlation coefficient corresponding to the first signal.

[0094] In some embodiments, the mathematical expression of the channel correlation coefficient corresponding to the first signal is represented by the following formula:

[0095]

[0096] where H i is the channel estimation value corresponding to the i-th data, conj(H i-w ) is the conjugate operation of the channel estimation value H corresponding to the (i - w)-th data i-w , and C n is the channel correlation coefficient corresponding to the first signal.

[0097] Step 408: Use the channel correlation coefficient corresponding to the first signal as training data to iteratively train the relevant parameter prediction model.

[0098] In some embodiments, there are at least two channel correlation coefficients corresponding to the first signal.

[0099] In some embodiments, the more channel correlation coefficients corresponding to the first signal, that is, the more input samples of the relevant parameter prediction model, the better the training effect of the relevant parameter prediction model.

[0100] Step 409: Determine the delay decision parameter.

[0101] In some embodiments, the delay determination parameter is a parameter used to determine the signal delay during the signal processing.

[0102] In some embodiments, the delay determination parameter can be determined according to whether there is frequency drift in the current communication system.

[0103] Specifically, as Figure 5 , Figure 5 is a flowchart of a method for determining the delay determination parameter.

[0104] Step 501, determine whether there is frequency drift in the current communication system.

[0105] In some embodiments, the communication system is used to specify characteristics such as the way, format, rate, etc. of information transmission. The communication system in this application can be a communication system with a Bluetooth 6.0 HDT frame format, or a cellular 2G system, or a personalized time-domain system, a radio, etc.

[0106] In some embodiments, it can be determined whether there is frequency drift in the current communication system according to historical experience. Specifically, it can be determined whether there is frequency drift in the current communication system according to the materials of the devices used in the communication system. Taking the current communication system as a communication system with a Bluetooth 6.0 HDT frame format as an example, if the stability of devices such as crystal oscillators used in Bluetooth is poor, there is a certain frequency drift.

[0107] Step 502, when there is no frequency drift in the current communication system, determine that the delay determination parameter is a preset value.

[0108] In some embodiments, when there is no frequency drift in the current communication system, there is no need to perform deviation correction processing on the current communication system. Therefore, it can be determined that the delay determination parameter is zero, that is, the preset value is zero.

[0109] Step 503, when there is frequency drift in the current communication system, determine the delay determination parameter according to the decoding delay, calculation delay, and the sequence length w of each segmented signal.

[0110] In some embodiments, the decoding delay refers to the time required from when the receiver receives the encoded data to successfully decoding and restoring the original information.

[0111] In some embodiments, the calculation delay refers to the time required for data processing and algorithm execution by the receiver from the input data to complete the signal processing task.

[0112] In some embodiments, the mathematical expression of the delay determination parameter is represented by the following formula:

[0113] pre_dist = (d1 + d2) / w;

[0114] Among them, d1 is the decoding delay, d2 is the calculation delay, w is the length of the segmented signal of the first signal, and pre_dist is the delay determination parameter.

[0115] Step 410: Determine the prediction error according to the delay determination parameter, the channel correlation coefficient corresponding to the first signal, the number of taps of the coefficient to be predicted, and the iteration coefficient. End the training when the prediction error meets the preset conditions to obtain the target model.

[0116] In some embodiments, the mathematical expression for determining the prediction error is represented by the following formula:

[0117]

[0118] a k = a k + step * err c C n-pre_dist-k ...k = 0, 1,..., len - 1;

[0119] Among them, pre_dist is the delay determination parameter, k refers to the kth tap, C n is the channel correlation coefficient corresponding to the first signal, len is the number of taps of the coefficient to be predicted, a k is the iteration coefficient, is the conjugate operation of a k , err is the prediction error, and step is the coefficient of gradient descent.

[0120] In some embodiments, the number of taps of the coefficient to be predicted refers to the number of taps of the channel correlation parameter of the second signal.

[0121] In some embodiments, the iteration coefficient refers to the coefficient for each iteration during training.

[0122] In some embodiments, ending the training when the prediction error meets the preset conditions may include ending the training when the prediction error meets the error threshold, or may include ending the training when the prediction error shows no improvement after consecutive multiple iterations.

[0123] Step 411: Obtain the second signal and use the target model to determine the channel correlation coefficient corresponding to the second signal.

[0124] In some embodiments, the principle of step 411 is the same as that of step 303. For the relevant description of the embodiment shown in step 303, reference can be made, and details are not described here again.

[0125] In some embodiments, the mathematical expression for the channel correlation coefficient corresponding to the second signal is represented by the following formula:

[0126]

[0127] Among them, C n+pred is the channel correlation coefficient corresponding to the second signal, and C n-k is the channel correlation coefficient corresponding to the (n - k)-th signal, is the iteration coefficient a k for the conjugate operation.

[0128] It should be noted that the second signal can be a certain segment of the first signal after segmentation. Taking the example in step 405 above, where the first signal with a sequence length of 10 is segmented to obtain two segmented signals, each with a sequence length of 5, the second signal can be the first segment of the first signal after segmentation or the second segment of the first signal after segmentation.

[0129] Step 412: Process the second signal based on the channel correlation coefficient corresponding to the second signal.

[0130] Based on Figure 3 the embodiment shown, Figure 6 Figure 24 further shows a flowchart of a signal processing method proposed by the present disclosure. Figure 6 Based on Figure 3 the embodiment shown, step 304 is further defined. As Figure 6 shown, the method includes the following steps:

[0131] Step 601: Determine the phase angle corresponding to the second signal based on the channel correlation coefficient corresponding to the second signal.

[0132] In some embodiments, the channel correlation coefficient corresponding to the second signal refers to the channel correlation coefficient predicted and output by the target model.

[0133] In some embodiments, the mathematical expression for determining the phase angle corresponding to the second signal is represented by the following formula:

[0134] θ = atan2(C n+pred );

[0135] where θ is the phase angle corresponding to the second signal, C n+pred is the channel correlation coefficient corresponding to the second signal, and atan() is the operation for finding the phase angle.

[0136] In some embodiments, by using the channel correlation coefficient corresponding to the second signal predicted and output by the target model to determine the phase angle corresponding to the second signal, the influence of the offset on the phase angle can be reduced.

[0137] Step 602: Determine the frequency offset of the second signal based on the phase angle and the sequence length w of each segmented signal.

[0138] In some embodiments, the frequency offset of the second signal is a predicted frequency offset.

[0139] In some embodiments, the mathematical expression for determining the frequency offset of the second signal is represented by the following formula:

[0140] f esti = θ / w;

[0141] where θ is the phase angle corresponding to the second signal, w is the sequence length of each segmented signal, and f esti is the frequency offset of the second signal.

[0142] In some embodiments, the larger the phase angle corresponding to the second signal, the larger the frequency offset of the second signal; the smaller the phase angle corresponding to the second signal, the smaller the frequency offset of the second signal.

[0143] In some embodiments, by determining the frequency offset of the second signal based on the phase angle and the sequence length w of each segmented signal, the accuracy of the offset estimation can be improved.

[0144] Step 603: Perform deviation correction processing on the second signal based on the frequency offset.

[0145] In some embodiments, by performing deviation correction processing on the second signal based on a more accurate frequency offset, real-time prediction and tracking of the frequency can be achieved.

[0146] In summary, the signal processing method proposed according to the present disclosure includes: obtaining a first signal, where the first signal includes a pilot signal and a data signal; performing symbol reconstruction and decoding processing on the data signal to obtain a first reconstructed symbol; performing reliability processing on the first reconstructed symbol to obtain a second reconstructed symbol; performing channel estimation based on the pilot signal and the second reconstructed symbol to obtain a channel estimation value H corresponding to the i-th data in the sequence of the first signal i ; performing segmentation processing on the first signal to obtain n segmented signals, where the sequence length of each segmented signal is w, and n ≥ 2; the channel estimation value H corresponding to the i-th data i , and the channel estimation value H corresponding to the (i - w)-th data i-wAssociate them to obtain w associated values; sum up the w associated values to obtain the channel correlation coefficient corresponding to the first signal; use the channel correlation coefficient corresponding to the first signal as training data to iteratively train the relevant parameter prediction model; determine the delay decision parameter; determine the prediction error according to the delay decision parameter, the channel correlation coefficient corresponding to the first signal, the number of taps of the coefficient to be predicted, and the iteration coefficient, and end the training when the prediction error meets the preset condition to obtain the target model; obtain the second signal, and use the target model to determine the channel correlation coefficient corresponding to the second signal; process the second signal based on the channel correlation coefficient corresponding to the second signal. The method of the present disclosure performs symbol reconstruction and decoding processing on the data signal to obtain the reconstructed symbol, and uses the channel correlation coefficients corresponding to the pilot signal and the reconstructed symbol as training data to train the relevant parameter prediction model, so as to timely predict and correct the frequency offset of the second signal, overcome the influence of the reconstruction delay on the real-time frequency estimation of the second signal, thereby realizing prediction and tracking. Moreover, by performing reliability processing on the first reconstructed symbol to obtain the second reconstructed symbol, the prediction accuracy of the relevant parameter prediction model can be improved when using the channel correlation coefficient corresponding to the reconstructed symbol as training data.

[0147] Therefore, the present solution has the following beneficial effects:

[0148] 1. In the method of the present disclosure, by adding a data signal to the pilot signal as training data to train the channel correlation parameter prediction model, and then using the trained channel correlation parameter prediction model to predict the second signal to obtain the channel correlation coefficient corresponding to the second signal, and further when processing the second signal using the channel correlation coefficient corresponding to the second signal, the influence of the processing delay on the real-time frequency estimation of the second signal can be overcome, thereby realizing prediction and tracking.

[0149] 2. In the method of the present disclosure, by performing reliability processing on the first reconstructed symbol to obtain the second reconstructed symbol, the prediction accuracy of the relevant parameter prediction model can be improved when using the channel correlation coefficient corresponding to the reconstructed symbol as training data.

[0150] Figure 7 The following is a schematic structural diagram of a signal processing device 700 provided by an embodiment of the present disclosure. As Figure 7 shown, the signal processing device includes:

[0151] An acquisition module 710, configured to acquire a first signal, where the first signal includes a pilot signal and a data signal;

[0152] A training module 720, configured to train a channel correlation parameter prediction model based on the pilot signal and the data signal to obtain a target model;

[0153] A determination module 730, configured to obtain a second signal and determine a channel correlation coefficient corresponding to the second signal by using a target model;

[0154] A processing module 740, configured to process the second signal based on the channel correlation coefficient corresponding to the second signal.

[0155] In some embodiments of the present disclosure, a training module 720 is configured to: determine a channel correlation coefficient corresponding to a first signal based on a pilot signal and a data signal; use the channel correlation coefficient corresponding to the first signal as training data to iteratively train a correlation parameter prediction model; determine a prediction error for each iterative training, and end the training when the prediction error meets a preset condition to obtain a target model.

[0156] In some embodiments of the present disclosure, the training module 720 is further configured to: determine a channel estimation value corresponding to the i-th data in the sequence of the first signal based on the pilot signal and the data signal; perform segmentation processing on the first signal to obtain n segmented signals, where the sequence length of each segmented signal is w and n≥2; perform correlation processing on the channel estimation values of the n segmented signals to obtain a channel correlation coefficient corresponding to the first signal.

[0157] In some embodiments of the present disclosure, the training module 720 is further configured to: perform symbol reconstruction and decoding processing on the data signal to obtain a first reconstructed symbol; perform reliability processing on the first reconstructed symbol to obtain a second reconstructed symbol, and the reliability processing is used to determine whether the first reconstructed symbol is the reconstructed symbol closest to the data signal; perform channel estimation based on the pilot signal and the second reconstructed symbol to obtain a channel estimation value corresponding to the i-th data in the sequence of the first signal.

[0158] In some embodiments of the present disclosure, the training module 720 is further configured to: associate the channel estimation value corresponding to the i-th data with the channel estimation value corresponding to the (i - w)-th data to obtain w association values, where the i-th data belongs to the first segmented signal among the n segmented signals, and the (i - w)-th data belongs to the previous segmented signal of the first segmented signal; sum the w association values to obtain a channel correlation coefficient corresponding to the first signal.

[0159] In some embodiments of the present disclosure, the training module 720 is further configured to: determine a delay decision parameter; determine a prediction error according to the delay decision parameter, the channel correlation coefficient corresponding to the first signal, the number of taps of the coefficient to be predicted, and an iteration coefficient.

[0160] In some embodiments of the present disclosure, the training module 720 is further configured to: determine whether there is frequency drift in the current communication system; when there is no frequency drift in the current communication system, determine that the delay decision parameter is a preset value; when there is frequency drift in the current communication system, determine the delay decision parameter according to the decoding delay, the calculation delay, and the sequence length w of each segmented signal.

[0161] In some embodiments of the present disclosure, the processing module 740 is configured to: determine the phase angle corresponding to the second signal based on the channel correlation coefficient corresponding to the second signal; determine the frequency offset of the second signal based on the phase angle and the sequence length w of each segmented signal; and perform deviation correction processing on the second signal based on the frequency offset.

[0162] In summary, through the signal processing device, a first signal is obtained, where the first signal includes a pilot signal and a data signal; based on the pilot signal and the data signal, a channel correlation parameter prediction model is trained to obtain a target model; a second signal is obtained, and the target model is used to determine the channel correlation coefficient corresponding to the second signal; based on the channel correlation coefficient corresponding to the second signal, the second signal is processed. By adding the data signal as training data to the pilot signal to train the channel correlation parameter prediction model, and then using the trained channel correlation parameter prediction model to predict the second signal to obtain the channel correlation coefficient corresponding to the second signal, and further when processing the second signal using the channel correlation coefficient corresponding to the second signal, the influence of the processing delay on the real-time frequency estimation of the second signal can be overcome, so as to achieve prediction and tracking.

[0163] In the above embodiments provided by the present application, the methods and devices provided by the embodiments of the present application are introduced. To implement the various functions in the methods provided by the embodiments of the present application, the electronic device may include a hardware structure and software modules, and implement the above various functions in the form of a hardware structure, a software module, or a combination of a hardware structure and a software module. A certain function among the above various functions may be executed in the form of a hardware structure, a software module, or a combination of a hardware structure and a software module.

[0164] Figure 8 FIG. 800 is a block diagram of an electronic device 800 for implementing the above signal processing method according to an exemplary embodiment. For example, the electronic device 800 may be a mobile phone, a computer, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0165] Refer to Figure 8, the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0166] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above methods. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0167] The memory 804 is configured to store various types of data to support the operation of the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk.

[0168] The power component 806 provides power to various components of the electronic device 800. The power component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

[0169] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of touch or swipe actions but also detect the duration and pressure associated with the touch or swipe operations. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the electronic device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each of the front camera and the rear camera can be a fixed optical lens system or have a focal length and optical zoom capabilities.

[0170] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC) that is configured to receive external audio signals when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 further includes a speaker for outputting audio signals.

[0171] The I / O interface 812 provides an interface between the processing component 802 and a peripheral interface module, which can be a keyboard, a click wheel, buttons, etc. These buttons can include but are not limited to: a home button, a volume button, a power button, and a lock button.

[0172] The sensor component 814 includes one or more sensors for providing status assessments of various aspects of the electronic device 800. For example, the sensor component 814 can detect the on / off state of the electronic device 800, the relative positioning of components, such as the display and keypad of the electronic device 800. The sensor component 814 can also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor component 814 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor component 814 can also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor component 814 can further include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0173] The communication component 816 is configured to facilitate communication between the electronic device 800 and other devices in a wired or wireless manner. The electronic device 800 may access a communication standard-based wireless network, such as WiFi, 2G or 3G, 4G LTE, 5G NR (New Radio), or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0174] In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above-described method.

[0175] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as the memory 804 including instructions, and the above instructions can be executed by the processor 820 of the electronic device 800 to complete the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, Random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0176] Embodiments of the present disclosure also propose a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the signal processing method described in the above embodiments of the present disclosure.

[0177] Embodiments of the present disclosure also propose a computer program product, including a computer program, and the computer program executes the signal processing method described in the above embodiments of the present disclosure when being executed by a processor.

[0178] Embodiments of the present disclosure also propose a chip, as Figure 9 shown, the chip includes one or more interface circuits 901 and one or more processors 902; the interface circuit is configured to receive a signal and send the signal to the processor, and the signal includes computer instructions stored in a memory. When the processor executes the computer instructions, the chip executes the signal processing method described in the above embodiments of the present disclosure.

[0179] It should be noted that the terms "first", "second", etc. in the description of the present disclosure, the claims and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described here can be implemented in an order different from those illustrated or described here. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0180] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "schematic embodiments", "examples", "specific examples" or "some examples", etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0181] Any process or method description shown in the flowchart or described in other ways herein can be understood to represent a module, segment or part of code including one or more executable instructions for implementing a specific logical function or process. The scope of the preferred embodiments of the present invention includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the technical field to which the embodiments of the present invention belong.

[0182] The logic and / or steps represented in the flowchart or otherwise described herein can, for example, be considered as a definitional sequence of executable instructions for implementing logical functions, and can be embodied specifically in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processing module, or other systems that can fetch instructions from and execute the instructions of the instruction execution system, apparatus, or device. As used in this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (control method) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable medium on which a program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0183] It should be understood that various parts of the embodiments of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0184] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0185] In addition, each functional unit in various embodiments of the present invention may be integrated into one processing module, may exist physically alone for each unit, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc.

[0186] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A signal processing method, characterized in that, The method includes: Obtaining a first signal, where the first signal includes a pilot signal and a data signal; Training a channel correlation parameter prediction model based on the pilot signal and the data signal to obtain a target model; Obtaining a second signal and using the target model to determine a channel correlation coefficient corresponding to the second signal; Processing the second signal based on the channel correlation coefficient corresponding to the second signal.

2. The method according to claim 1, characterized in that, The training the channel correlation parameter prediction model based on the pilot signal and the data signal to obtain a target model includes: Determining a channel correlation coefficient corresponding to the first signal based on the pilot signal and the data signal; Using the channel correlation coefficient corresponding to the first signal as training data to perform iterative training on the correlation parameter prediction model; Determining a prediction error for each iterative training, and ending the training when the prediction error meets a preset condition to obtain the target model.

3. The method according to claim 2, wherein The determining the channel correlation coefficient corresponding to the first signal based on the pilot signal and the data signal includes: Based on the pilot signal and the data signal, determine the channel estimation value H corresponding to the i-th data in the sequence of the first signal i ; Performing segmented processing on the first signal to obtain n segmented signals, where the sequence length of each segmented signal is w, and n≥2; Performing correlation processing on the channel estimation values of the n segmented signals to obtain the channel correlation coefficient corresponding to the first signal.

4. The method according to claim 3, wherein Determining a channel estimation value H corresponding to the i-th data in the sequence of the first signal based on the pilot signal and the data signal i , comprising: Performing symbol reconstruction and decoding processing on the data signal to obtain a first reconstructed symbol; Performing reliability processing on the first reconstructed symbol to obtain a second reconstructed symbol, where the reliability processing is used to determine whether the first reconstructed symbol is the reconstructed symbol closest to the data signal; Based on the pilot signal and the second reconstructed symbol, channel estimation is performed to obtain the channel estimation value H corresponding to the i-th data in the sequence of the first signal i .

5. The method according to claim 3, wherein The performing correlation processing on the channel estimation values of the n segmented signals to obtain the channel correlation coefficient corresponding to the first signal includes: The channel estimation value H corresponding to the i-th data i is associated with the channel estimation value H i-w corresponding to the (i - w)-th data to obtain w association values, where the i-th data belongs to the first segmented signal among the n segmented signals, and the (i - w)-th data belongs to the segmented signal preceding the first segmented signal; Summing the w correlation values to obtain the channel correlation coefficient corresponding to the first signal.

6. The method according to claim 2, characterized in that, The determining the prediction error for each iterative training includes: Determining a delay decision parameter; Determining the prediction error according to the delay decision parameter, the channel correlation coefficient corresponding to the first signal, the number of taps of the coefficient to be predicted, and the iteration coefficient.

7. The method according to claim 6, wherein The determining the delay decision parameter includes: Determining whether there is frequency drift in the current communication system; When there is no frequency drift in the current communication system, determining the delay decision parameter as a preset value; When there is frequency drift in the current communication system, determining the delay decision parameter according to the decoding delay, the calculation delay, and the sequence length w of each segmented signal.

8. The method according to any one of claims 1 to 6, characterized in that, The processing the second signal based on the channel correlation coefficient corresponding to the second signal includes: Determining a phase angle corresponding to the second signal based on the channel correlation coefficient corresponding to the second signal; Determining a frequency offset of the second signal based on the phase angle and the sequence length w of each segmented signal; Performing deviation correction processing on the second signal based on the frequency offset.

9. A signal processing device, the device includes: An obtaining module, configured to obtain a first signal, where the first signal includes a pilot signal and a data signal; A training module, configured to train a channel correlation parameter prediction model based on the pilot signal and the data signal to obtain a target model; A determination module, configured to obtain a second signal and use the target model to determine a channel correlation coefficient corresponding to the second signal; A processing module, configured to process the second signal based on the channel correlation coefficient corresponding to the second signal.

10. An electronic device, characterized in that, 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 to enable the at least one processor to execute the method according to any one of claims 1 to 8.

11. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 8.

12. A chip, characterized in that, Comprising at least one processor and a communication interface; the communication interface is configured to receive a signal input to the chip or a signal output from the chip, and the processor communicates with the communication interface and implements the method according to any one of claims 1 to 8 through a logic circuit or by executing code instructions.

Images