Signal determination method, apparatus, storage medium, and processor of a receiver

Abstract

The application discloses a signal determination method and device of a receiver, a storage medium and a processor. The method comprises the following steps: in response to a first target radio frequency signal from a transmitter, determining a baseband signal corresponding to the first target radio frequency signal; extracting a first original parameter corresponding to the transmitter in an I path and a Q path and a second original parameter corresponding to the receiver in the I path and the Q path from the baseband signal; determining target relationship information between the first original parameter and the second original parameter; inputting the target relationship information and the first target radio frequency signal into a target model for demodulation to obtain a second target radio frequency signal transmitted by the receiver in the I path and the Q path. The application solves the technical problem that the amplitudes and phases of the carriers in the I path and the Q path are all erroneous.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication, in particular to a signal determination method and device of a receiver, a storage medium and a processor. BACKGROUND

[0002] At present, in the process of estimating the amplitude and phase of the transmitter and the receiver, due to the nonlinearity of the device, the carrier of the I path and the Q path may both have amplitude and phase errors, thereby causing the transmitter and the receiver to have the possibility of in-phase quadrature (IQ) mismatch, thereby causing the carrier of the I path and the Q path to have amplitude and phase errors.

[0003] At present, there is no effective solution to the above-mentioned technical problem that the carrier of the I path and the Q path both have amplitude and phase errors. SUMMARY

[0004] The embodiments of the present application provide a signal determination method and device of a receiver, a storage medium and a processor to at least solve the technical problem that the carrier of the I path and the Q path both have amplitude and phase errors.

[0005] According to an aspect of the embodiments of the present application, a signal determination method of a receiver is provided. The method can include: in response to a first target radio frequency signal from a transmitter, determining a baseband signal corresponding to the first target radio frequency signal, wherein the first target radio frequency signal is obtained by modulating an original radio frequency signal to be modulated by the transmitter; extracting, from the baseband signal, a first original parameter corresponding to the transmitter in the I path and the Q path respectively, and a second original parameter corresponding to the receiver in the I path and the Q path respectively, wherein the I path and the Q path are orthogonal to each other, the I path is used to transmit the real part of the baseband signal, the Q path is used to transmit the imaginary part of the baseband signal, the first original parameter is used to represent the amplitude parameter and the phase parameter corresponding to the transmitter in the I path and the Q path respectively, and the second original parameter is used to represent the amplitude parameter and the phase parameter corresponding to the receiver in the I path and the Q path respectively; determining target relationship information between the first original parameter and the second original parameter, wherein the target relationship information is used to represent the relationship of the first original parameter and the second original parameter arranged in a matrix structure; inputting the target relationship information and the first target radio frequency signal into a target model for demodulation to obtain a second target radio frequency signal transmitted by the receiver in the I path and the Q path respectively, wherein the target model is used to represent the mapping relationship between the first target radio frequency signal and the second target radio frequency signal.

[0006] Optionally, determining the target relationship information between the first original parameter and the second original parameter includes: determining a correlation matrix between the first original parameter and the second original parameter; performing dimension reduction processing on the correlation matrix; and determining the correlation matrix after the dimension reduction processing as the target relationship information.

[0007] Optionally, the target relationship information and the first target radio frequency signal are input into the target model for demodulation to obtain the second target radio frequency signal transmitted by the receiver in the I path and the Q path respectively, including: determining a target parameter in the target relationship information, wherein the target parameter is used to represent at least one element in the correlation matrix; inputting the target parameter and the first target radio frequency signal into the target model for demodulation to obtain the second target radio frequency signal.

[0008] Optionally, the target parameter in the target relationship information is determined, including: determining an expectation value of the correlation matrix; according to the expectation value, position information corresponding to an initial parameter in the target relationship information is determined as initial position information in the target gradient descent model, wherein the initial parameter is used to represent at least one initial element in the correlation matrix, and the target gradient descent model is obtained by training the original gradient descent model based on at least an initial position information sample and a target parameter sample, wherein the initial position information sample is historical position information satisfying the original gradient descent model, and the target parameter sample is a historical parameter sample satisfying the original gradient descent model; the target parameter is determined based on the initial position information.

[0009] Optionally, the target parameter is determined based on the initial position information, including: determining at least one first target parameter satisfying the expectation value, wherein the first target parameter is used to represent a descent slope of the target gradient descent model; the target parameter is determined based on the initial position information and the at least one first target parameter.

[0010] Optionally, the target parameter is determined based on the initial position information and the at least one first target parameter, including: in response to the expectation value being a target expectation value, at least one second target parameter satisfying the target expectation value is obtained, wherein the second target parameter is used to represent a target descent slope of the target gradient descent model satisfying the target expectation value; the at least one first target parameter is adjusted to the at least one second target parameter; the target parameter is determined based on the initial position information and the at least one second target parameter.

[0011] Optionally, the target parameter is determined based on the initial position information and the at least one second target parameter, including: determining a convergence speed of the target gradient descent model; the initial position information and the at least one second target parameter are input into the target gradient descent model for gradient descent processing according to the convergence speed to obtain the target parameter.

[0012] Optionally, the first original parameter corresponding to the sending device in the I path and the Q path and the second original parameter corresponding to the receiving device in the I path and the Q path are extracted from the baseband signal, including: calibrating the baseband signal; the first original parameter and the second original parameter are extracted from the calibrated baseband signal.

[0013] According to another aspect of the embodiments of the present application, a signal sending method of a transmitter is provided. The method can include: obtaining an original radio frequency signal; modulating the original radio frequency signal to obtain a first target radio frequency signal, wherein the first target radio frequency signal is used for demodulation with target relationship information between a first original parameter and a second original parameter input into a target model to obtain a second target radio frequency signal transmitted by a receiver in an I path and a Q path respectively, the I path and the Q path are orthogonal to each other, the I path is used for transmitting a real part of a baseband signal, the Q path is used for transmitting an imaginary part of the baseband signal, the target relationship information is used for representing a relationship of the first original parameter and the second original parameter arranged according to a matrix structure, the target model is used for representing a mapping relationship between the first target radio frequency signal and the second target radio frequency signal, the first original parameter and the second original parameter are extracted from the baseband signal corresponding to the first target radio frequency signal, the first original parameter is used for representing corresponding amplitude parameters and phase parameters of the transmitter in the I path and the Q path respectively, and the second original parameter is used for representing corresponding amplitude parameters and phase parameters of the receiver in the I path and the Q path respectively; and sending the first target radio frequency signal to the receiver.

[0014] According to an aspect of the embodiments of the present application, a signal determination apparatus of a receiver is provided. The apparatus can include: a first determination unit configured to determine a baseband signal corresponding to a first target radio frequency signal from a transmitter in response to the first target radio frequency signal, wherein the first target radio frequency signal is obtained by modulating an original radio frequency signal to be modulated by the transmitter; an extraction unit configured to extract a first original parameter corresponding to the transmitter in an I path and a Q path respectively and a second original parameter corresponding to the receiver in the I path and the Q path respectively from the baseband signal, wherein the I path and the Q path are orthogonal to each other, the I path is used for transmitting a real part of the baseband signal, the Q path is used for transmitting an imaginary part of the baseband signal, the first original parameter is used for representing corresponding amplitude parameters and phase parameters of the transmitter in the I path and the Q path respectively, and the second original parameter is used for representing corresponding amplitude parameters and phase parameters of the receiver in the I path and the Q path respectively; a second determination unit configured to determine target relationship information between the first original parameter and the second original parameter, wherein the target relationship information is used for representing a relationship of the first original parameter and the second original parameter arranged according to a matrix structure; and a demodulation unit configured to input the target relationship information and the first target radio frequency signal into a target model for demodulation to obtain a second target radio frequency signal transmitted by the receiver in the I path and the Q path respectively, wherein the target model is used for representing a mapping relationship between the first target radio frequency signal and the second target radio frequency signal.

[0015] According to another aspect of the embodiments of the present application, a computer readable storage medium is also provided. The computer readable storage medium includes a stored program, wherein the program controls a device where the computer readable storage medium is located to perform the signal determination method of the receiver according to the embodiments of the present application when the program is running.

[0016] According to another aspect of the embodiments of the present application, a processor is further provided. The processor is configured to run a program, wherein the program, when executed by the processor, implements the signal determination method of the receiver of the embodiments of the present application.

[0017] According to another aspect of the embodiments of the present application, a computer program product is further provided. The computer program product comprises a computer program, wherein the computer program, when executed by a processor, implements the signal determination method of the receiver of the embodiments of the present application.

[0018] In the embodiments of the present application, when determining the signal of the receiver, in response to the first target radio frequency signal from the transmitter, the baseband signal corresponding to the first target radio frequency signal can be determined, and then from the determined baseband signal, the first original parameters corresponding to the transmitter in the I path and the Q path respectively, and the second original parameters corresponding to the receiver in the I path and the Q path respectively can be extracted. That is, the embodiments of the present application can obtain the amplitude parameters and the phase parameters corresponding to the transmitter in the I path and the Q path respectively, and the amplitude parameters and the phase parameters corresponding to the receiver in the I path and the Q path respectively, and then determine the target relationship information between the obtained first original parameters and the second original parameters, and input the determined target relationship information and the first target radio frequency signal into the target model for demodulation, so as to obtain the second target radio frequency signal transmitted by the receiver in the I path and the Q path respectively, thereby achieving the purpose of ensuring the accuracy of the estimation of the amplitude and the phase, solving the technical problem that the errors of the amplitudes and the phases of the carriers in the I path and the Q path occur, and achieving the technical effect that the errors of the amplitudes and the phases of the carriers in the I path and the Q path can be avoided. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and serve to explain the present application. In the drawings:

[0020] FIG. 1(a) is a flow chart of a signal determination method of a receiver according to an embodiment of the present application;

[0021] FIG. 1(b) is a flow chart of a signal transmission method of a transmitter according to an embodiment of the present application;

[0022] Figure 2 FIG. 2 is a schematic diagram of a communication system model of an IQ modulation and demodulation according to the related art;

[0023] Figure 3 FIG. 3 is a schematic diagram of the EVM effect after repeated iteration according to an embodiment of the present application;

[0024] FIG. 4(a) is a schematic diagram of a signal determination device of a receiver according to an embodiment of the present application;

[0025] Figure 4(b) is a schematic diagram of a signal sending device of a transmitter according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the persons skilled in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by the persons skilled in the art without creative labor should belong to the protection scope of the present application.

[0027] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in other than the order illustrated or described herein. In addition, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0028] According to the embodiments of the present application, a signal determination method of a receiver is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0029] Figure 1(a) is a flowchart of a signal determination method of a receiver according to an embodiment of the present application. As shown in Figure 1(a), the method can include the following steps:

[0030] Step S101, in response to a first target radio frequency signal from a transmitter, determining a baseband signal corresponding to the first target radio frequency signal.

[0031] In the technical solution provided by the above step S101 of the present application, the above-mentioned first target radio frequency signal can be a radio frequency signal to be transmitted by the transmitter to the receiver.

[0032] In this embodiment, a baseband signal corresponding to the first target radio frequency signal is determined in response to the first target radio frequency signal from the transmitter. Optionally, the embodiment de-noises the first target radio frequency signal received by the receiver from the transmitter, enhances the de-noised first target radio frequency signal, and converts the enhanced first target radio frequency signal to obtain the baseband signal corresponding to the first target radio frequency signal.

[0033] It should be noted that the de-noising operation can be used to remove noise signals in the first target radio frequency signal, and the enhancement operation can be used to enhance non-noise signals in the first target radio frequency signal.

[0034] Step S102, extracting the first original parameters corresponding to the transmitter in the I path and the Q path, respectively, and the second original parameters corresponding to the receiver in the I path and the Q path, respectively, from the baseband signal.

[0035] In the technical solution provided by the above step S102 of the present application, the first original parameters can be used to represent the amplitude parameters and the phase parameters corresponding to the transmitter in the I path and the Q path, respectively, and the second original parameters can be used to represent the amplitude parameters and the phase parameters corresponding to the receiver in the I path and the Q path, respectively.

[0036] In this embodiment, the I path and the Q path can be orthogonal to each other. The I path can be used to transmit the real part of the baseband signal, and the Q path can be used to transmit the imaginary part of the baseband signal.

[0037] In this embodiment, the amplitude parameters corresponding to the transmitter in the I path and the Q path, respectively, can include an amplitude factor corresponding to the transmitter in the I path and an amplitude factor corresponding to the transmitter in the Q path, the phase parameters corresponding to the transmitter in the I path and the Q path, respectively, can include a phase factor corresponding to the transmitter in the I path and a phase factor corresponding to the transmitter in the Q path, the amplitude parameters corresponding to the receiver in the I path and the Q path, respectively, can include an amplitude factor corresponding to the receiver in the I path and an amplitude factor corresponding to the receiver in the Q path, and the phase parameters corresponding to the receiver in the I path and the Q path, respectively, can include a phase factor corresponding to the receiver in the I path and a phase factor corresponding to the receiver in the Q path.

[0038] In this embodiment, after determining the baseband signal corresponding to the first target radio frequency signal in response to the first target radio frequency signal from the transmitter, the first original parameters corresponding to the transmitter in the I and Q paths respectively and the second original parameters corresponding to the receiver in the I and Q paths respectively are extracted from the baseband signal. Alternatively, based on the determination of the baseband signal corresponding to the first target radio frequency signal, the first original parameters corresponding to the transmitter in the I and Q paths respectively and the second original parameters corresponding to the receiver in the I and Q paths respectively can be obtained by calibrating the baseband signal and extracting parameters from the calibrated baseband signal, for example, the amplitude parameters and phase parameters corresponding to the transmitter in the I and Q paths and the amplitude parameters and phase parameters corresponding to the receiver in the I and Q paths.

[0039] It should be noted that the above calibration operation can include at least one of the following operations: direct current bias calibration operation and frequency offset calibration operation, etc., and the above parameter extraction operation can include at least one of the following operations: demodulation operation, filtering operation and spectrum analysis operation, etc., which are only exemplified and not specifically limited.

[0040] In step S103, target relationship information between the first original parameters and the second original parameters is determined.

[0041] In the technical solution provided by the above step S103 of the present application, the target relationship information can be used to represent the relationship of the first original parameters and the second original parameters arranged in a matrix structure. The matrix structure can be, but is not limited to, a 2x2 matrix structure, which is only exemplified and not specifically limited.

[0042] In this embodiment, after extracting the first original parameters corresponding to the transmitter in the I and Q paths respectively and the second original parameters corresponding to the receiver in the I and Q paths respectively from the baseband signal, the target relationship information between the first original parameters and the second original parameters is determined. Alternatively, based on the determination of the first original parameters and the second original parameters, the correlation matrix between the first original parameters and the second original parameters can be determined, and according to the determined correlation matrix, the target relationship information between the first original parameters and the second original parameters can be determined, that is, the relationship of the first original parameters and the second original parameters arranged in a matrix structure can be determined.

[0043] In step S104, the target relationship information and the first target radio frequency signal are input into a target model for demodulation to obtain the second target radio frequency signal transmitted by the receiver in the I and Q paths respectively.

[0044] In the technical solution provided by the above step S104 of the present application, the target model can be used to represent the mapping relationship between the first target radio frequency signal and the second target radio frequency signal.

[0045] In this embodiment, the second target radio frequency signal can represent a radio frequency signal transmitted by the receiver in the I path and a radio frequency signal transmitted by the receiver in the Q path.

[0046] In this embodiment, after the target relationship information between the first original parameter and the second original parameter is determined, the target relationship information and the first target radio frequency signal are input into the target model for demodulation to obtain the second target radio frequency signal transmitted by the receiver in the I path and the Q path, respectively. Alternatively, in this embodiment, the target relationship information between the first original parameter and the second original parameter and the first target radio frequency signal are input into the target model for demodulation to obtain the second target radio frequency signal transmitted by the receiver in the I path and the Q path, respectively, for example, a radio frequency signal transmitted by the receiver in the I path and a radio frequency signal transmitted by the receiver in the Q path, which are only used for illustration and are not limited in a specific manner.

[0047] The steps S101-S104 described above in the present application, when determining the signal of the receiver, in response to the first target radio frequency signal from the transmitter, can determine the baseband signal corresponding to the first target radio frequency signal, and then from the determined baseband signal, the first original parameter corresponding to the transmitter in the I path and the Q path and the second original parameter corresponding to the receiver in the I path and the Q path can be extracted. That is, in the embodiment of the present application, the first original parameter and the second original parameter corresponding to the amplitude parameter and the phase parameter of the transmitter in the I path and the Q path and the amplitude parameter and the phase parameter of the receiver in the I path and the Q path can be obtained from the determined baseband signal, and then the target relationship information between the obtained first original parameter and the second original parameter is determined, and the determined target relationship information and the first target radio frequency signal are input into the target model for demodulation to obtain the second target radio frequency signal transmitted by the receiver in the I path and the Q path, respectively, so as to achieve the purpose of ensuring the accuracy of the estimation of the amplitude and the phase, solve the technical problem that the amplitude and the phase errors occur in the carriers of the I path and the Q path, and achieve the technical effect that the amplitude and the phase errors can be avoided in the carriers of the I path and the Q path.

[0048] The above method of this embodiment will be further introduced as follows.

[0049] As an optional embodiment, in step S103, the target relationship information between the first original parameter and the second original parameter includes: determining the correlation matrix between the first original parameter and the second original parameter; performing dimension reduction processing on the correlation matrix; and determining the dimension-reduced correlation matrix as the target relationship information.

[0050] In this embodiment, after extracting the first original parameters corresponding to the transmitter in at least one branch and the second original parameters corresponding to the receiver in at least one branch from the baseband signal, the correlation matrix between the first original parameters and the second original parameters is determined. Alternatively, the correlation matrix between the first original parameters and the second original parameters can be determined on the basis of the first original parameters corresponding to the transmitter in at least one branch and the second original parameters corresponding to the receiver in at least one branch being determined. In this embodiment, after the correlation matrix between the first original parameters and the second original parameters is determined, the determined correlation matrix is subjected to dimension reduction processing, and the correlation matrix subjected to dimension reduction processing is determined as the target relationship information. Alternatively, the determined correlation matrix can be subjected to dimension reduction conversion on the basis of the correlation matrix being determined, and the correlation matrix subjected to dimension reduction conversion is determined as the target relationship information. Since the dimension of the correlation matrix is reduced, the technical effect of reducing the complexity of the original model can be achieved. The correlation matrix between the first original parameters and the second original parameters can be represented by a 2x2 matrix in formula (1) as follows:

[0051]

[0052] wherein y i may be used to represent the signal received by the receiver in the i-th branch, y q may be used to represent the signal received by the receiver in the q-th branch, a ti may be used to represent the amplitude factor of the transmitter in the i-th branch, a tq may be used to represent the amplitude factor of the transmitter in the q-th branch, may be used to represent the phase factor of the transmitter in the i-th branch, may be used to represent the phase factor of the transmitter in the q-th branch, a ri may be used to represent the amplitude factor of the receiver in the i-th branch, a rq may be used to represent the amplitude factor of the receiver in the q-th branch, may be used to represent the phase factor of the receiver in the i-th branch, may be used to represent the phase factor of the receiver in the q-th branch, x i may be used to represent the signal to be transmitted by the transmitter in the i-th branch, x q may be used to represent the signal to be transmitted by the transmitter in the q-th branch.

[0053] As an optional embodiment, in step S104, the target relationship information and the first target radio frequency signal are input into the target model for demodulation to obtain the second target radio frequency signal transmitted by the receiver in the I path and the Q path respectively, including: determining the target parameter in the target relationship information; inputting the target parameter and the first target radio frequency signal into the target model for demodulation to obtain the second target radio frequency signal.

[0054] In this embodiment, the target parameter can be used to represent at least one element in the correlation matrix. For example, the target parameter can be a parameter value when the error vector magnitude (EVM) is the smallest.

[0055] In this embodiment, after the target relationship information between the first original parameter and the second original parameter is determined, the target parameter in the target relationship information is determined; and the target parameter and the first target radio frequency signal are input into the target model for demodulation to obtain the second target radio frequency signal. Alternatively, the target parameter can be determined from the original parameters in the target relationship information, and the determined target parameter and the first target radio frequency signal are input into the target model for demodulation to obtain the second target radio frequency signal transmitted by the receiver in the I path and the Q path respectively. For example, the radio frequency signal transmitted by the receiver in the I path and the radio frequency signal transmitted by the receiver in the Q path can be obtained. Since the target parameter and the first target radio frequency signal are demodulated by using the target model to obtain the second target radio frequency signal transmitted by the receiver in the I path and the Q path respectively, the technical effect of improving the accuracy of the received signal obtained by the receiver is achieved, which is only exemplified here and is not limited specifically.

[0056] Alternatively, the target relationship information can be realized by the following formula (2):

[0057]

[0058] wherein a 11 , a 12 and a 22 can be used to represent the amplitude parameter value considering the sin function and the cos function comprehensively.

[0059] As an optional embodiment, the target parameter in the target relationship information is determined, including: determining the expected value of the correlation matrix; according to the expected value, the position information corresponding to the original parameter in the target relationship information is determined as the initial position information in the target gradient descent model; and the target parameter is determined based on the initial position information.

[0060] In this embodiment, the initial parameter can be used to represent at least one initial element in the correlation matrix. The target gradient descent model can be obtained by training the original gradient descent model based on at least one initial position information sample and at least one target parameter sample. The initial position information sample can be historical position information satisfying the original gradient descent model, and the target parameter sample can be historical parameter sample satisfying the original gradient descent model.

[0061] In this embodiment, the original gradient descent model can be constructed based on a gradient descent algorithm.

[0062] In this embodiment, after determining the target relationship information between the first original parameter and the second original parameter, the expected value of the correlation matrix is determined; according to the expected value, the position information corresponding to the initial parameter in the target relationship information is determined as the initial position information in the target gradient descent model; and the target parameter is determined based on the initial position information. Alternatively, in this embodiment, based on the determined expected value of the correlation matrix, according to the size of the determined expected value, the position information corresponding to the initial parameter in the target relationship information is determined as the initial position information in the target gradient descent model, and the determined initial position information is convex optimized, so that the target parameter in the target model can be obtained. Since the target parameter is obtained by convex optimizing the initial position information in the target gradient descent model, the technical effect of improving the accuracy of the parameter can be achieved.

[0063] As an optional embodiment, determining the target parameter based on the initial position information includes: determining at least one first target parameter satisfying the expected value; and determining the target parameter based on the initial position information and the at least one first target parameter.

[0064] In this embodiment, the first target parameter can be used to represent the descent slope of the target gradient descent model. For example, the first target parameter can be represented by the descent slope f'(x k ), which is only used as an example and is not limited.

[0065] In this embodiment, after the position information corresponding to the initial parameter in the target relationship information is determined as the initial position information in the target gradient descent model according to the expected value, at least one first target parameter satisfying the expected value is determined, wherein the first target parameter is used to represent the descent slope of the target gradient descent model; and the target parameter is determined based on the initial position information and the at least one first target parameter. Alternatively, in this embodiment, at least one first target parameter satisfying the expected value of the correlation matrix can be determined based on the determined expected value, and the target parameter can be determined according to the initial position information x k , the learning rate a and the descent slope f'(x k), the target parameter in the target model can be determined. Since the target parameter needs to be determined according to the initial position information, the learning rate and the descending slope, the technical effect that the accuracy of the parameter can be improved is realized.

[0066] Optionally, the target gradient descent model can be realized by the following formula (3):

[0067] x k+1 = x k - αf'(x k )(3)

[0068] Wherein, x k+1 may be used to represent the next position of the initial position in the target gradient descent model.

[0069] As an optional embodiment, the target parameter is determined based on the initial position information and the at least one first target parameter, comprising: in response to the expectation value being a target expectation value, obtaining at least one second target parameter satisfying the target expectation value; adjusting the at least one first target parameter to the at least one second target parameter; and determining the target parameter based on the initial position information and the at least one second target parameter.

[0070] In this embodiment, the second target parameter can be used to represent the target descending slope of the target gradient descent model satisfying the target expectation value.

[0071] In this embodiment, after the at least one first target parameter satisfying the expectation value is determined, in response to the expectation value being a target expectation value, at least one second target parameter satisfying the target expectation value is obtained; the at least one first target parameter is adjusted to the at least one second target parameter; and the target parameter is determined based on the initial position information and the at least one second target parameter. Optionally, this embodiment judges the relationship between the expectation value of the correlation matrix and the target expectation value through the determined correlation matrix, and if it is judged that the expectation value of the correlation matrix is the target expectation value, at least one second target parameter satisfying the target expectation value can be obtained. Then, the at least one first target parameter satisfying the expectation value is adjusted to the at least one second target parameter, and the target parameter is determined according to the initial position information x k and the second target parameter in the target gradient descent model. Since the target parameter needs to be determined according to the initial position information and the second target parameter in the target gradient descent model, the technical effect that the accuracy of the parameter can be improved is realized.

[0072] Optionally, if it is judged that the expectation value of the correlation matrix is not the target expectation value, the initial position information x kand the second target parameter, determine the target parameter, continue the convex optimization until the expectation value of the correlation matrix is the target expectation value, and then determine the target parameter according to the initial position information x k and the second target parameter, determine the target parameter.

[0073] As an optional embodiment, the target parameter is determined based on the initial position information and at least one second target parameter, including: determining a convergence speed of the target gradient descent model; and inputting the initial position information and the at least one second target parameter into the target gradient descent model according to the convergence speed to obtain the target parameter.

[0074] In this embodiment, the convergence speed can be represented by a learning rate a.

[0075] In this embodiment, after the at least one first target parameter is adjusted to the at least one second target parameter, the convergence speed of the target gradient descent model is determined; and the initial position information and the at least one second target parameter are input into the target gradient descent model according to the convergence speed to obtain the target parameter. Optionally, the learning rate a of the target gradient descent model can be determined, and the initial position information and the second target parameter are input into the target gradient descent model according to the determined learning rate a to obtain the target parameter in the target model. That is, by inputting the initial position information x k , the learning rate a and the slope f'(x k ) into the target gradient descent model to perform gradient descent calculation, the target parameter in the target model can be obtained. Since the target parameter needs to be determined according to the initial position information and the second target parameter in the target gradient descent model, the technical effect of improving the accuracy of obtaining the parameter can be achieved.

[0076] As an optional embodiment, the step S102 extracts the first original parameter corresponding to the transmitter in the I path and the Q path and the second original parameter corresponding to the receiver in the I path and the Q path from the baseband signal, including: calibrating the baseband signal; and extracting the first original parameter and the second original parameter from the calibrated baseband signal.

[0077] In this embodiment, after determining the baseband signal corresponding to the first target radio frequency signal in response to the first target radio frequency signal from the transmitter, the baseband signal is calibrated; the first original parameter and the second original parameter are extracted from the calibrated baseband signal. Optionally, based on the determination of the baseband signal corresponding to the first target radio frequency signal, the calibration of the baseband signal, and the parameter extraction of the calibrated baseband signal, the first original parameter corresponding to the transmitter in the I path and the Q path respectively, and the second original parameter corresponding to the receiver in the I path and the Q path respectively can be obtained, for example, the amplitude parameter and the phase parameter corresponding to the transmitter in the I path and the Q path respectively, and the amplitude parameter and the phase parameter corresponding to the receiver in the I path and the Q path respectively. Since the above-mentioned first original parameter and the above-mentioned second original parameter are extracted from the calibrated baseband signal, the technical effect of improving the accuracy of obtaining the original parameter can be achieved.

[0078] According to the embodiment of the present application, a signal transmission method of a transmitter is provided, and Fig. 1(b) is a flow chart of a signal transmission method of a transmitter according to an embodiment of the present application. As shown in Fig. 1(b), the method can include the following steps:

[0079] In step S111, an original radio frequency signal is obtained.

[0080] In the technical solution provided in the above step S111 of the present application, the transmitter can obtain the original radio frequency signal with modulation.

[0081] In step S112, the original radio frequency signal is modulated to obtain a first target radio frequency signal, wherein the first target radio frequency signal is used for inputting the target relationship information between the first original parameter and the second original parameter into a target model for demodulation to obtain a second target radio frequency signal transmitted by the receiver in the I path and the Q path respectively, the target relationship information is used to represent the relationship of the first original parameter and the second original parameter arranged according to the matrix structure, the target model is used to represent the mapping relationship between the first target radio frequency signal and the second target radio frequency signal, the first original parameter and the second original parameter are extracted from the baseband signal corresponding to the first target radio frequency signal, the first original parameter is used to represent the amplitude parameter and the phase parameter corresponding to the transmitter in the I path and the Q path respectively, and the second original parameter is used to represent the amplitude parameter and the phase parameter corresponding to the receiver in the I path and the Q path respectively.

[0082] In the technical solution provided in the above step S112 of the present application, after obtaining the original radio frequency signal, the obtained original radio frequency signal is modulated to obtain the first target radio frequency signal.

[0083] In step S113, the first target radio frequency signal is sent to the receiver.

[0084] In the technical scheme provided in the step S113 of the present application, after the original radio frequency signal is modulated to obtain the first target radio frequency signal, in the case that the transmitter sends the first target radio frequency signal to the receiver, the second target radio frequency signal transmitted by the receiver in the I path and the Q path can be obtained.

[0085] In the embodiment of the present application, when the signal of the receiver is determined, the first target radio frequency signal from the transmitter can be determined, and the baseband signal corresponding to the first target radio frequency signal can be determined. Then, the first original parameter corresponding to the transmitter in the I path and the Q path and the second original parameter corresponding to the receiver in the I path and the Q path can be extracted from the determined baseband signal. That is, the embodiment of the present application can obtain the amplitude parameter and the phase parameter corresponding to the transmitter in the I path and the Q path, and the amplitude parameter and the phase parameter corresponding to the receiver in the I path and the Q path. Then, the target relationship information between the determined first original parameter and the second original parameter is determined, and the determined target relationship information and the first target radio frequency signal are input into the target model for demodulation, so that the second target radio frequency signal transmitted by the receiver in the I path and the Q path can be obtained. Thus, the accuracy of the estimation of the amplitude and the phase can be ensured, the technical problem that the amplitude and the phase errors of the carriers in the I path and the Q path occur is solved, and the technical effect that the amplitude and the phase errors of the carriers in the I path and the Q path can be avoided is achieved.

[0086] The technical scheme of the embodiment of the present application will be described below in conjunction with the preferred embodiments.

[0087] In the estimation process of the amplitude and the phase of the transmitter and the receiver, due to the nonlinearity of the device, the amplitude and the phase errors of the carriers in the I path and the Q path may occur, so that the IQ mismatch of the transmitter and the receiver may occur, and the technical problem that the amplitude and the phase errors of the carriers in the I path and the Q path occur.

[0088] For example, Figure 2 is a schematic diagram of an IQ modulation and demodulation communication system model according to the related art, as Figure 2 shown, the communication system model can include a sending end 201 and a receiving end 202. The sending end 201 may have an IQ imbalance, and the receiving end 202 may also have an IQ imbalance, so that the technical problem that the amplitude and the phase errors of the carriers in the I path and the Q path occur.

[0089] In order to solve the above technical problems, the embodiment of the present application proposes a signal determination method of a receiving device, uses the carrier amplitude and phase of a transmitter and a receiver to perform mathematical modeling, and simplifies an in-phase quadrature (IQ) imbalance matrix, so as to determine a received signal obtained by the receiver, thereby achieving the purpose of ensuring the accuracy of the estimation of the amplitude and the phase, solving the technical problem that the amplitude and the phase errors of the carriers of the I path and the Q path occur, and realizing the technical effect that the amplitude and the phase errors of the carriers of the I path and the Q path can be avoided.

[0090] In the method proposed in the embodiment of the present application, after a radio frequency signal is received by a receiver, a baseband signal is obtained after passing through a low noise amplifier, frequency down conversion and analog-to-digital conversion (ADC) sampling. Before IQ amplitude imbalance is performed, some preprocessing is performed, for example, time synchronization, direct current bias calibration, frequency offset calibration and the like.

[0091] In the embodiment, considering that a low pass filter filters out a double frequency component, the received signal y after IQ demodulation can be derived as i 、 q , ti 、 tq 、 ri 、 rq 、 , 11 , 22 , 12 , 21 ,

[0092] In the embodiment, the unknown variables are reduced from 8 to 4, and a complex trigonometric function matrix is changed into a matrix of a single variable. The matrix is referred to as an IQ matrix. Since the mathematical expectation of the IQ matrix is known, by traversing the possible values of each element in the matrix, the corresponding EVM is calculated, so as to determine the IQ matrix when the EVM is the smallest. In order to shorten the calculation time, a convex optimization method is used to calculate the signal received in the corresponding branch at the receiving end.

[0093] In the embodiment, the convex optimization method can include the following steps:

[0094] Step 1: according to the baseband signal of an existing machine type, the value range of each element of the IQ matrix is determined.

[0095] Step 2: a 12 ,a 21a 22 unchanged, a 11 may be respectively taken as 0.95, 1, 1.05, and then through channel estimation and channel equalization, the corresponding EVM can be obtained.

[0096] In the technical solution provided in the above step two of the application, after determining the value range of each element of the IQ matrix according to the baseband signal of the existing machine type, step two is entered, the a 11 corresponding to the minimum EVM value is taken as the initial position of the subsequent gradient descent method.

[0097] Step three, at the above initial position, the EVM slope f'(x k ) is calculated, and the next position x k+1 is calculated according to formula (3).

[0098] After the next position x k+1 is calculated according to formula (3), step four, step five and step six are entered, when left and right lateral jumps or the EVM is greater than the last value, the learning rate a is reduced, at the same time, in order to control the algorithm accuracy, when the step is less than the preset minimum value, the step is set to the preset minimum value, and after experiencing repeated iterations, the EVM can reach the trough, thereby obtaining the a 11 ' when the EVM minimum value is obtained. For example, Figure 3 is a schematic diagram of the EVM effect after repeated iterations according to an embodiment of the application, as shown in Figure 3 , in the interval [1.01, 1.015], the EVM can reach the trough.

[0099] After the a 11 ' when the EVM minimum value is obtained is obtained, step seven is entered, the value a 11 ' obtained by the above convex optimization is substituted back into the IQ matrix, and then the other elements in the IQ matrix are subjected to the above convex optimization operation, thereby obtaining the optimal solution of each element.

[0100] In this embodiment, the value range of each element of the IQ matrix is determined according to the baseband signal of the existing machine type, a 12 , a 21 , a 22 unchanged, the a 11 value is taken, the a 11 corresponding to the minimum EVM value is taken as the initial position of the subsequent gradient descent method, at the above initial position, the EVM slope f'(x k), and according to formula (3), the next position is calculated, and when the left and right lateral jump or the EVM is greater than the last time, the learning rate is reduced, and at the same time, in order to control the accuracy of the algorithm, when the step is less than the preset minimum value, the step is set to the preset minimum value, and after experiencing repeated iterations, the EVM can reach the trough, thereby obtaining a 11 , thereby achieving the purpose of ensuring the accuracy of the amplitude and phase estimation, solving the technical problem of the amplitude and phase errors of the I and Q carriers, and realizing the technical effect of avoiding the amplitude and phase errors of the I and Q carriers.

[0101] According to an embodiment of the present application, a signal determination device of a receiver is also provided. It should be noted that the signal determination device of the receiver can be used to execute the signal determination method of the receiver in the embodiments.

[0102] FIG. 4(a) is a schematic diagram of a signal determination device of a receiver according to an embodiment of the present application. As shown in FIG. 4(a), the signal determination device 400 of the receiver can include a first determination unit 401, an extraction unit 402, a second determination unit 403, and a demodulation unit 404.

[0103] The first determination unit 401 is configured to determine a baseband signal corresponding to a first target radio frequency signal in response to the first target radio frequency signal from a transmitter, wherein the first target radio frequency signal is obtained by modulating an original radio frequency signal to be modulated by the transmitter.

[0104] The extraction unit 402 is configured to extract a first original parameter corresponding to the transmitter in the I and Q paths respectively and a second original parameter corresponding to the receiver in the I and Q paths respectively from the baseband signal, wherein the I and Q paths are orthogonal to each other, the I path is used to transmit the real part of the baseband signal, the Q path is used to transmit the imaginary part of the baseband signal, the first original parameter is used to represent the amplitude parameter and the phase parameter corresponding to the transmitter in the I and Q paths respectively, and the second original parameter is used to represent the amplitude parameter and the phase parameter corresponding to the receiver in the I and Q paths respectively.

[0105] The second determination unit 403 is configured to determine target relationship information between the first original parameter and the second original parameter, wherein the target relationship information is used to represent the relationship of the first original parameter and the second original parameter arranged in a matrix structure.

[0106] The demodulation unit 404 is configured to input the target relationship information and the first target radio frequency signal into a target model for demodulation to obtain a second target radio frequency signal transmitted by the receiver in the I and Q paths respectively, wherein the target model is used to represent the mapping relationship between the first target radio frequency signal and the second target radio frequency signal.

[0107] Optionally, the second determining unit 403 can include: a first determining module, configured to determine a correlation matrix between the first original parameter and the second original parameter; a dimension reduction module, configured to perform dimension reduction processing on the correlation matrix; and a second determining module, configured to determine the correlation matrix after the dimension reduction processing as the target relationship information.

[0108] Optionally, the demodulating unit 404 can include: a third determining module, configured to determine a target parameter in the target relationship information, where the target parameter is used to represent at least one element in the correlation matrix; and a demodulating module, configured to input the target parameter and the first target radio frequency signal into the target model for demodulation to obtain the second target radio frequency signal.

[0109] Optionally, the third determining module can include: a first determining submodule, configured to determine an expected value of the correlation matrix; a second determining submodule, configured to determine, according to the expected value, position information corresponding to an initial parameter in the target relationship information as initial position information in a target gradient descent model, where the initial parameter is used to represent at least one initial element in the correlation matrix, and the target gradient descent model is obtained by training the original gradient descent model based on at least an initial position information sample and a target parameter sample, where the initial position information sample is historical position information satisfying the original gradient descent model, and the target parameter sample is a historical parameter sample satisfying the original gradient descent model; and a third determining submodule, configured to determine the target parameter based on the initial position information.

[0110] Optionally, the third determining submodule can determine the target parameter based on the initial position information by performing the following steps: determining at least one first target parameter satisfying the expected value, where the first target parameter is used to represent a descent slope of the target gradient descent model; and determining the target parameter based on the initial position information and the at least one first target parameter.

[0111] Optionally, the third determining submodule can determine the target parameter based on the initial position information and the at least one first target parameter by performing the following steps: in response to the expected value being a target expected value, obtaining at least one second target parameter satisfying the target expected value, where the second target parameter is used to represent a target descent slope of the target gradient descent model satisfying the target expected value; adjusting the at least one first target parameter to the at least one second target parameter; and determining the target parameter based on the initial position information and the at least one second target parameter.

[0112] Optionally, the third determining submodule can determine the target parameter based on the initial position information and the at least one second target parameter by performing the following steps: determining a convergence speed of the target gradient descent model; and inputting the initial position information and the at least one second target parameter into the target gradient descent model for gradient descent processing according to the convergence speed to obtain the target parameter.

[0113] Optionally, the extracting unit 402 can comprise: a calibration module, configured to calibrate the baseband signal; and an extracting module, configured to extract the first original parameter and the second original parameter from the calibrated baseband signal.

[0114] In this embodiment, the first determining unit is configured to determine a baseband signal corresponding to a first target radio frequency signal from the transmitter in response to the first target radio frequency signal, wherein the first target radio frequency signal is obtained by modulating an original radio frequency signal to be modulated by the transmitter; the extracting unit is configured to extract a first original parameter corresponding to the transmitter in an I path and a Q path respectively, and a second original parameter corresponding to the receiver in the I path and the Q path respectively from the baseband signal, wherein the I path and the Q path are orthogonal to each other, the I path is used to transmit a real part of the baseband signal, the Q path is used to transmit an imaginary part of the baseband signal, the first original parameter is used to represent an amplitude parameter and a phase parameter corresponding to the transmitter in the I path and the Q path respectively, and the second original parameter is used to represent an amplitude parameter and a phase parameter corresponding to the receiver in the I path and the Q path respectively; the second determining unit is configured to determine target relationship information between the first original parameter and the second original parameter, wherein the target relationship information is used to represent a relationship of arranging the first original parameter and the second original parameter according to a matrix structure; and the demodulating unit is configured to input the target relationship information and the first target radio frequency signal into a target model to demodulate, so as to obtain a second target radio frequency signal transmitted by the receiver in the I path and the Q path respectively, wherein the target model is used to represent a mapping relationship between the first target radio frequency signal and the second target radio frequency signal, so as to achieve the purpose of ensuring the accuracy of the estimation of the amplitude and the phase, solve the technical problem that the amplitude and the phase errors occur in the I path and the Q path, and achieve the technical effect that the amplitude and the phase errors in the I path and the Q path can be avoided.

[0115] According to the embodiments of the present application, a signal sending device of a transmitter is further provided. It should be noted that the signal sending device of the transmitter can be used to execute the signal sending method of the transmitter in the embodiments.

[0116] FIG. 4(b) is a schematic diagram of a signal sending device of a transmitter according to an embodiment of the present application. As shown in FIG. 4(b), the signal sending device 410 of the transmitter can comprise an obtaining unit 411, a modulating unit 412 and a sending unit 413.

[0117] The obtaining unit 411 is configured to obtain an original radio frequency signal.

[0118] The modulation unit 412 is configured to modulate the original radio frequency signal to obtain a first target radio frequency signal, wherein the first target radio frequency signal is used for demodulation of target relationship information between the first original parameter and the second original parameter in the target model to obtain a second target radio frequency signal transmitted by the receiver in an I path and a Q path, the I path and the Q path are orthogonal to each other, the I path is used for transmitting a real part of a baseband signal, the Q path is used for transmitting an imaginary part of the baseband signal, the target relationship information is used for representing a relationship of the first original parameter and the second original parameter arranged according to a matrix structure, the target model is used for representing a mapping relationship between the first target radio frequency signal and the second target radio frequency signal, the first original parameter and the second original parameter are extracted from the baseband signal corresponding to the first target radio frequency signal, the first original parameter is used for representing corresponding amplitude parameters and phase parameters of the transmitter in the I path and the Q path, and the second original parameter is used for representing corresponding amplitude parameters and phase parameters of the receiver in the I path and the Q path.

[0119] The sending unit 413 is configured to send the first target radio frequency signal to the receiver.

[0120] According to the embodiments of the present application, a computer readable storage medium is also provided, which includes a stored program, wherein the program performs the method in the embodiments.

[0121] According to the embodiments of the present application, a processor is also provided, which is used to run a program, wherein the program is run by the processor to perform the method in the embodiments.

[0122] According to the embodiments of the present application, a computer program product is also provided, which includes a computer program, wherein the computer program is run by the processor to implement the method in the embodiments of the present application.

[0123] The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0124] In the above-mentioned embodiments of the present application, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0125] In the several embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the unit embodiment described above is only schematic. For example, the division of the units can be a logical function division. There can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed units can be indirect coupling or communication connection through some interface, unit or module, and can be electrical or other forms.

[0126] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed to multiple units. Part or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

[0127] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0128] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the part that contributes to the related art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method of each embodiment of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various program code storage media.

[0129] The above is only the preferred embodiment of the present application. It should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A signal determination method for a receiver, characterized by, The method comprises the steps of: determining a baseband signal corresponding to a first target radio frequency signal from a transmitter, wherein the first target radio frequency signal is obtained by modulating an original radio frequency signal to be modulated by the transmitter; extracting a first original parameter corresponding to the transmitter in an I path and a Q path and a second original parameter corresponding to the receiver in the I path and the Q path from the baseband signal, wherein the I path and the Q path are orthogonal to each other, the I path is used to transmit the real part of the baseband signal, the Q path is used to transmit the imaginary part of the baseband signal, the first original parameter is used to represent the amplitude parameter and the phase parameter corresponding to the transmitter in the I path and the Q path respectively, and the second original parameter is used to represent the amplitude parameter and the phase parameter corresponding to the receiver in the I path and the Q path respectively; determining target relationship information between the first original parameter and the second original parameter, wherein the target relationship information is used to represent the relationship of arranging the first original parameter and the second original parameter in a matrix structure; inputting the target relationship information and the first target radio frequency signal into a target model for demodulation to obtain a second target radio frequency signal transmitted by the receiver in the I path and the Q path, wherein the target model is used to represent the mapping relationship between the first target radio frequency signal and the second target radio frequency signal.

2. The method of claim 1, wherein, The method for determining the target relationship information between the first original parameter and the second original parameter comprises: determining a correlation matrix between the first original parameter and the second original parameter; and performing dimension reduction processing on the correlation matrix; determining the correlation matrix after the dimension reduction processing as the target relationship information.

3. The method of claim 2, wherein, The method for inputting the target relationship information and the first target radio frequency signal into the target model for demodulation to obtain the second target radio frequency signal transmitted by the receiver in the I path and the Q path comprises: determining a target parameter in the target relationship information, wherein the target parameter is used to represent at least one element in the correlation matrix; inputting the target parameter and the first target radio frequency signal into the target model for demodulation to obtain the second target radio frequency signal.

4. The method of claim 3, wherein, The method for determining the target parameter in the target relationship information comprises: determining an expected value of the correlation matrix; determining position information corresponding to an initial parameter in the target relationship information as initial position information in a target gradient descent model according to the expected value, wherein the initial parameter is used to represent at least one initial element in the correlation matrix, the target gradient descent model is obtained by training an original gradient descent model based on at least an initial position information sample and a target parameter sample, the initial position information sample is historical position information satisfying the original gradient descent model, and the target parameter sample is historical parameter sample satisfying the original gradient descent model; determining the target parameter based on the initial position information.

5. The method of claim 4, wherein, The method for determining the target parameter based on the initial position information comprises: determining at least one first target parameter satisfying the expected value, wherein the first target parameter is used to represent a descending slope of the target gradient descent model; determining the target parameter based on the initial position information and the at least one first target parameter.

6. The method of claim 5, wherein, determining the target parameter based on the initial position information and the at least one first target parameter, comprising: in response to the expected value being a target expected value, obtaining at least one second target parameter satisfying the target expected value, wherein the second target parameter is used to represent a target descending slope of the target gradient descent model satisfying the target expected value; adjusting the at least one first target parameter to the at least one second target parameter; determining the target parameter based on the initial position information and the at least one second target parameter.

7. The method of claim 6, wherein, determining the target parameter based on the initial position information and the at least one second target parameter, comprising: determining a convergence speed of the target gradient descent model; inputting the initial position information and the second target parameter into the target gradient descent model for gradient descent processing according to the convergence speed, to obtain the target parameter.

8. The method according to any one of claims 1 to 7, characterized in that, extracting, from the baseband signal, a first original parameter corresponding to the transmitter in the I path and the Q path respectively, and a second original parameter corresponding to the receiver in the I path and the Q path respectively, comprising: calibrating the baseband signal; extracting the first original parameter and the second original parameter from the calibrated baseband signal.

9. A signal transmission method of a transmitter, characterized by, comprising: obtaining an original radio frequency signal; modulating the original radio frequency signal to obtain a first target radio frequency signal, wherein the first target radio frequency signal is used to input into a target model with target relationship information between a first original parameter and a second original parameter, to demodulate to obtain a second target radio frequency signal transmitted by a receiver in an I path and a Q path respectively, the I path and the Q path being orthogonal to each other, the I path being used to transmit a real part of a baseband signal, the Q path being used to transmit an imaginary part of the baseband signal, the target relationship information being used to represent a relationship of the first original parameter and the second original parameter arranged in a matrix structure, the target model being used to represent a mapping relationship between the first target radio frequency signal and the second target radio frequency signal, the first original parameter and the second original parameter being extracted from a baseband signal corresponding to the first target radio frequency signal, the first original parameter being used to represent amplitude parameters and phase parameters corresponding to the transmitter in the I path and the Q path respectively, the second original parameter being used to represent amplitude parameters and phase parameters corresponding to the receiver in the I path and the Q path respectively; sending the first target radio frequency signal to the receiver.

10. A signal determination device of a receiver, characterized in that comprising: a first determining unit, configured to determine a baseband signal corresponding to a first target radio frequency signal from a transmitter in response to the first target radio frequency signal, wherein the first target radio frequency signal is obtained by modulating an original radio frequency signal to be modulated by the transmitter; extracting, from the baseband signal, a first original parameter corresponding to the transmitter in an I path and a Q path respectively and a second original parameter corresponding to the receiver in the I path and the Q path respectively, wherein the I path and the Q path are orthogonal to each other, the I path is used for transmitting a real part of the baseband signal, the Q path is used for transmitting an imaginary part of the baseband signal, the first original parameter is used for representing an amplitude parameter and a phase parameter corresponding to the transmitter in the I path and the Q path respectively, and the second original parameter is used for representing an amplitude parameter and a phase parameter corresponding to the receiver in the I path and the Q path respectively; determining a target relationship information between the first original parameter and the second original parameter, wherein the target relationship information is used for representing a relationship of arranging the first original parameter and the second original parameter in a matrix structure; demodulating the target relationship information and the first target radio frequency signal in a target model to obtain a second target radio frequency signal transmitted by the receiver in the I path and the Q path respectively, wherein the target model is used for representing a mapping relationship between the first target radio frequency signal and the second target radio frequency signal.

11. A computer readable storage medium, characterized in that, The computer readable storage medium comprises a stored program, wherein the program controls the device where the computer readable storage medium is located to execute the method in any one of claims 1 to 9 when the program is running.

12. A processor, comprising: The processor is used for running a program, wherein the program is executed by the processor to execute the method in any one of claims 1 to 9 when the program is running.

13. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the method in any one of claims 1 to 9.

Images