Channel parameter determination method and apparatus, device, chip and medium

Abstract

This disclosure relates to a method, apparatus, device, chip, and medium for determining channel parameters, belonging to the field of wireless communication technology. The method includes: determining target received signals at multiple pilot positions from a received signal; performing channel estimation based on known pilot signals and the target received signals at the multiple pilot positions to obtain estimated information of the channel frequency domain response at the corresponding pilot positions; determining target-related information based on the estimated information of the channel frequency domain response at each pilot position; and determining the target channel parameters corresponding to the target-related information based on the mapping relationship between the pre-learned related information and channel parameters. Therefore, based on the pre-learned mapping relationship, accurate and efficient conversion from target-related information to target channel parameters can be achieved, significantly reducing the computational complexity required to determine the target channel parameters, helping to shorten data processing time, meeting the needs of real-time communication, and optimizing the user experience.

Description

Technical Field

[0001] This disclosure relates to the field of wireless communication technology, and in particular to a method, apparatus, electronic device, chip, storage medium, and computer program product for determining channel parameters. Background Technology

[0002] In the field of wireless communication, the channel serves as the medium for signal transmission. Channel parameters vary with time, space, and frequency, making them crucial for data transmission. However, determining channel parameters in related technologies involves high computational complexity, resulting in lengthy data processing times and failing to meet the demands of real-time communication. Summary of the Invention

[0003] This disclosure provides a method, apparatus, electronic device, chip, storage medium, and computer program product for determining channel parameters, to at least solve the problem of high computational complexity in determining channel parameters in related technologies. The technical solution of this disclosure is as follows:

[0004] According to a first aspect of the present disclosure, a method for determining channel parameters is provided, comprising: determining target received signals at a plurality of pilot positions from received signals; performing channel estimation based on known pilot signals and the target received signals at the plurality of pilot positions to obtain estimated information of the channel frequency domain response at the corresponding pilot positions; determining target related information based on the estimated information of the channel frequency domain response at each pilot position; wherein the target related information is used to indicate the correlation between the estimated information at different times and / or the correlation between the estimated information at different frequencies; and determining target channel parameters corresponding to the target related information based on the mapping relationship between the pre-learned related information and channel parameters.

[0005] According to a second aspect of the present disclosure, a channel parameter determination apparatus is provided, comprising: a first determination module configured to determine target received signals at a plurality of pilot positions from received signals; an estimation module configured to perform channel estimation based on known pilot signals and the target received signals at the plurality of pilot positions to obtain estimated information of the channel frequency domain response at the corresponding pilot positions; a second determination module configured to determine target related information based on the estimated information of the channel frequency domain response at each pilot position; wherein the target related information is used to indicate the correlation between the estimated information at different times and / or the correlation between the estimated information at different frequencies; and a third determination module configured to determine the target channel parameters corresponding to the target related information based on a mapping relationship between pre-learned related information and channel parameters.

[0006] According to a third aspect of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the method for determining channel parameters according to the first aspect of the present disclosure.

[0007] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, on which computer program instructions are stored, which, when executed by a processor, implement the steps of the method for determining channel parameters described in the first aspect of the present disclosure.

[0008] According to a fifth aspect of the present disclosure, a chip is provided, the chip including an interface circuit and a processing circuit coupled to each other, the interface circuit being used to input or output signals, and the processing circuit being configured to implement the steps of the method for determining channel parameters according to the first aspect of the present disclosure.

[0009] According to a sixth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method for determining channel parameters described in the first aspect of the present disclosure.

[0010] The technical solution provided by the embodiments of this disclosure brings at least the following beneficial effects: It determines the target received signal at multiple pilot positions from the received signal; based on the known pilot signals, it performs channel estimation on the target received signal at the multiple pilot positions to obtain estimated information of the channel frequency domain response at the corresponding pilot positions; and based on the estimated information of the channel frequency domain response at each pilot position, it determines target-related information. The target-related information is used to indicate the correlation between estimated information at different times and / or the correlation between estimated information at different frequencies. Based on the mapping relationship between the pre-learned related information and channel parameters, it determines the target channel parameters corresponding to the target-related information. Therefore, based on the pre-learned mapping relationship, a precise and efficient conversion from target-related information to target channel parameters can be achieved without calculating the estimation accuracy index of all channel parameters individually to determine the target channel parameters from all channel parameters. This significantly reduces the computational complexity required to determine the target channel parameters, helps shorten data processing time, meets the needs of real-time communication, and optimizes the user experience.

[0011] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0012] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0013] Figure 1 This is a flowchart illustrating a method for determining channel parameters according to an exemplary embodiment.

[0014] Figure 2 This is a flowchart illustrating a method for determining channel parameters according to another exemplary embodiment.

[0015] Figure 3 This is a flowchart illustrating a method for determining channel parameters according to another exemplary embodiment.

[0016] Figure 4 This is a flowchart illustrating a method for determining channel parameters according to another exemplary embodiment.

[0017] Figure 5 This is a flowchart illustrating a method for determining channel parameters according to another exemplary embodiment.

[0018] Figure 6 This is a flowchart illustrating a model training method according to an exemplary embodiment.

[0019] Figure 7 This is a schematic diagram of a channel parameter determination device according to an exemplary embodiment.

[0020] Figure 8 This is a schematic diagram of the structure of an electronic device according to an exemplary embodiment.

[0021] Figure 9 This is a schematic diagram of the structure of a chip according to an exemplary embodiment. Detailed Implementation

[0022] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0023] It should be noted that the terms "first," "second," etc., used in this disclosure and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this disclosure.

[0024] The following description, with reference to the accompanying drawings, describes a method, apparatus, electronic device, chip, storage medium, and computer program product for determining channel parameters according to embodiments of the present disclosure.

[0025] Figure 1 This is a flowchart illustrating a method for determining channel parameters according to an exemplary embodiment, such as... Figure 1 As shown, the method for determining channel parameters according to an embodiment of this disclosure includes the following steps.

[0026] S101, determine the target received signal at multiple pilot positions from the received signal.

[0027] It should be noted that the execution subject of the channel parameter determination method in this embodiment is an electronic device, such as a terminal device, vehicle, robot, server, chip, etc. Terminal devices include mobile phones, wearable devices (such as smartwatches and smart glasses), laptops, etc., and vehicles include in-vehicle terminals, in-vehicle controllers, etc. The channel parameter determination method in this embodiment can be executed by the channel parameter determination device, which can be configured in any electronic device to execute the channel parameter determination method.

[0028] There are no major restrictions on the received signals, such as including signals received from the communication transmitter.

[0029] Pilot location refers to the time-frequency resource index used to carry pilot signals. For example, pilot location includes both time-domain and frequency-domain locations, which can be represented using time-domain and frequency-domain resource indices. There are no strict limitations on time-domain and frequency-domain resources; for instance, time-domain resources include OFDM (Orthogonal Frequency Division Multiplexing) symbols, and frequency-domain resources include subcarriers. Pilot locations can be preset or dynamically set in real-time; further limitations are not specified here.

[0030] The target received signal at the pilot position refers to the signal actually received at that pilot position; it is also called the actual received pilot signal, the observed value of the pilot signal, etc. The target received signal may differ at different pilot positions.

[0031] The known pilot signal refers to the pre-set pilot signal, also known as the theoretical value of the pilot signal. The known pilot signal may be different at different pilot positions. For example, the known pilot signal is pre-set at the communication transmitter before transmitting the signal, and can be pre-stored in the local storage space of the communication transmitter and the local storage space of the communication receiver.

[0032] It is understandable that, due to the influence of channel frequency domain response (such as amplitude attenuation and phase rotation), the target received signal at the pilot location often differs from the known pilot signal.

[0033] S102, based on the known pilot signal and the target received signal at multiple pilot positions, channel estimation is performed to obtain the estimated information of the channel frequency domain response at the corresponding pilot position.

[0034] It should be noted that the estimated information of the channel frequency domain response at the pilot location is also called the channel estimation result at the pilot location. For example, the estimated information of the channel frequency domain response is used to indicate the channel's amplitude attenuation coefficient (also called amplitude gain, amplitude response), phase rotation angle (also called phase offset, phase response), etc. The estimated information of the channel frequency domain response may be different at different pilot locations.

[0035] Channel estimation is performed based on known pilot signals and target received signals at multiple pilot locations to obtain estimated information about the channel frequency domain response at the corresponding pilot locations. Any channel estimation method from related technologies can be used to achieve this, without much limitation here. For example, channel estimation methods include LS (Least Squares) estimation, MMSE (Minimum Mean Square Error) estimation, interpolation-based estimation, etc.

[0036] In some possible implementations, channel estimation is performed based on known pilot signals and target received signals at multiple pilot locations to obtain estimated information of the channel frequency domain response at the corresponding pilot location. This includes signal estimation based on known pilot signals at any pilot location and target received signals at the corresponding pilot location to obtain estimated information of the channel frequency domain response at the corresponding pilot location.

[0037] For example, taking LS estimation as an example, the estimated information of the channel frequency domain response at the corresponding pilot position can be determined based on the ratio of the target received signal at any pilot position to the known received signal at the corresponding pilot position.

[0038] For example, if the complex representation of the known pilot signal at pilot position 1 is 1+j0, and the complex representation of the target received signal at pilot position 1 is 0.6-j0.8, then the estimated information of the channel frequency domain response at pilot position 1 is h1=(0.6-j0.8) / 1=0.6-j0.8.

[0039] S103, Based on the estimated information of the channel frequency domain response at each pilot position, determine the target-related information; wherein, the target-related information is used to indicate the correlation between the estimated information at different times and / or the correlation between the estimated information at different frequencies.

[0040] It should be noted that no excessive restrictions are placed on the target-related information, such as mutual information, covariance, correlation coefficient, and MI (mutual information).

[0041] Based on the estimated information of the channel frequency domain response at each pilot position, target-related information can be determined. This can be achieved by using any of the relevant information acquisition methods in the relevant technology, without further restrictions here.

[0042] In some possible implementations, the target-related information includes a first type of related information and a second type of related information. The first type of related information is used to indicate the correlation between estimated information at different times, while the second type of related information is used to indicate the correlation between estimated information at different frequencies.

[0043] Based on the estimated channel frequency domain response information at each pilot location, target-related information is determined, including the cross-correlation information of the estimated channel frequency domain response information at each pilot time domain location as the first type of target-related information, and the cross-correlation information of the estimated channel frequency domain response information at each pilot frequency domain location as the second type of target-related information.

[0044] For example, taking pilot positions 1 to 20 as an example, the time domain positions of pilot positions 1 to 5 are OFDM symbol 1, the time domain positions of pilot positions 6 to 10 are OFDM symbol 2, the time domain positions of pilot positions 11 to 15 are OFDM symbol 3, and the time domain positions of pilot positions 16 to 20 are OFDM symbol 4.

[0045] The frequency domain positions of pilot positions 1, 6, 11, and 16 are subcarrier 1; the frequency domain positions of pilot positions 2, 7, 12, and 17 are subcarrier 2; the frequency domain positions of pilot positions 3, 8, 13, and 18 are subcarrier 3; the frequency domain positions of pilot positions 4, 9, 14, and 19 are subcarrier 4; and the frequency domain positions of pilot positions 5, 10, 15, and 20 are subcarrier 5.

[0046] Taking the cross-correlation of the estimated channel frequency domain response information at OFDM symbols 1 and 2 as an example, the average value of the estimated channel frequency domain response information at pilot positions 1 to 5 can be obtained. The average value of the estimated channel frequency domain response information at pilot positions 6 to 10 is obtained. .

[0047] The calculation process for the cross-correlation information of the estimated channel frequency domain response at OFDM symbols 1 and 2 is as follows:

[0048] in, The cross-correlation information of the estimated channel frequency domain response at OFDM symbols 1 and 2. OFDM symbol 1 i Channel frequency domain response at each subcarrier OFDM symbol 2 Channel frequency domain response at each subcarrier This is the complex conjugate operator.

[0049] Alternatively, the calculation process for the cross-correlation information of the estimated channel frequency domain response at OFDM symbols 1 and 2 is as follows:

[0050] It should be noted that the calculation process of the cross-correlation information of the estimated channel frequency domain response at any other two OFDM symbols can refer to the calculation process of the cross-correlation information of the estimated channel frequency domain response at OFDM symbols 1 and 2, and will not be repeated here.

[0051] S104. Based on the mapping relationship between the relevant information and the channel parameters obtained in advance, determine the target channel parameters corresponding to the target relevant information.

[0052] In the field of wireless communication, the channel serves as the medium for signal transmission. Channel parameters vary with time, space, and frequency, making them crucial for data transmission. However, determining channel parameters in related technologies involves high computational complexity, resulting in lengthy data processing times and failing to meet the demands of real-time communication.

[0053] For example, when determining the Doppler expansion parameter, most related technologies involve iterating through all Doppler expansion parameters and calculating the estimation accuracy index of each Doppler expansion parameter in order to determine the actual Doppler expansion parameter from all Doppler expansion parameters. This is especially computationally complex when there are many Doppler expansion parameters that need to be iterated through.

[0054] In this disclosure, the estimated information of the channel frequency domain response at each pilot position can be considered to determine target-related information. This target-related information indicates the correlation between estimated information at different times and / or between estimated information at different frequencies. Based on the pre-learned mapping relationship between the relevant information and channel parameters, the target channel parameters corresponding to the target-related information are determined. Therefore, based on the pre-learned mapping relationship, a precise and efficient conversion from target-related information to target channel parameters can be achieved without calculating the estimation accuracy index of all channel parameters individually to determine the target channel parameters. This significantly reduces the computational complexity required to determine the target channel parameters, helps shorten data processing time, meets the needs of real-time communication, and optimizes the user experience.

[0055] No restrictions are placed on any channel parameter, such as Doppler spread parameter, frequency offset parameter, time delay spread parameter, coherence bandwidth parameter, etc.

[0056] In some possible implementations, the target channel parameters corresponding to the target-related information are determined based on the mapping relationship between pre-learned relevant information and channel parameters. This includes determining the target channel parameters corresponding to the target-related information based on the mapping relationship using a target model. Therefore, the target channel parameters corresponding to the target-related information can be determined using a target model based on the mapping relationship. Target models have advantages such as fast inference speed and high accuracy, which helps improve the efficiency and accuracy of determining the target channel parameters.

[0057] In some possible implementations, the target channel parameters corresponding to the target-related information are determined based on the mapping relationship between the relevant information and the channel parameters obtained in advance. This includes determining the channel parameters corresponding to the relevant information that matches the target-related information based on the mapping relationship, and determining the target channel parameters corresponding to the relevant information that matches the target-related information based on the channel parameters corresponding to the relevant information that matches the target-related information.

[0058] In some possible implementations, after determining the target channel parameters corresponding to the target-related information, at least one of the following is also included: Method 1: Based on the target channel parameters, demodulate the received signal to obtain demodulated data after demodulation processing of the received signal.

[0059] Therefore, considering the demodulation of the received signal by the target channel parameters, the computational complexity required to determine the target channel parameters is relatively low, which helps to improve the demodulation efficiency of the received signal.

[0060] For example, the received signal can be demodulated based on the Doppler spread parameter and frequency offset parameter to obtain demodulated data.

[0061] Method 2: Determine the channel estimation period based on the target channel parameters.

[0062] Therefore, the target channel parameters can be taken into account to determine the channel estimation period. The computational complexity required to determine the target channel parameters is relatively low, which helps to improve the efficiency of determining the channel estimation period.

[0063] For example, the channel estimation period can be determined based on the Doppler extension parameters.

[0064] It should be noted that this disclosure does not impose any restrictions on the execution sequence of steps S101-S104. Figure 1 The example is only executed in the order of steps S101-S104.

[0065] The method for determining channel parameters provided in this disclosure involves identifying target received signals at multiple pilot positions from the received signal, performing channel estimation on the target received signals at the multiple pilot positions based on the known pilot signals, obtaining estimated information of the channel frequency domain response at the corresponding pilot positions, and determining target-related information based on the estimated information of the channel frequency domain response at each pilot position. The target-related information is used to indicate the correlation between estimated information at different times and / or the correlation between estimated information at different frequencies. Based on the mapping relationship between the pre-learned relevant information and channel parameters, the target channel parameters corresponding to the target-related information are determined. Therefore, based on the pre-learned mapping relationship, a precise and efficient conversion from target-related information to target channel parameters can be achieved without calculating the estimation accuracy index of all channel parameters individually to determine the target channel parameters from all channel parameters. This significantly reduces the computational complexity required to determine the target channel parameters, helps shorten data processing time, meets the needs of real-time communication, and optimizes the user experience.

[0066] In some possible implementations, the mapping relationship includes at least one of the following: The first mapping relationship between the first type of related information and the first type of channel parameters; wherein, the first type of related information is used to indicate the correlation between the estimated information at different times, and the first type of channel parameters are used to indicate the degree of time-domain variation of the channel; The second mapping relationship between the second type of related information and the second type of channel parameters; wherein the second type of related information is used to indicate the correlation between estimated information at different frequencies, and the second type of channel parameters is used to indicate the degree of frequency domain variation of the channel.

[0067] Therefore, the first mapping relationship between the first type of relevant information and the first type of channel parameters can be learned in advance, so that the accurate and efficient conversion between the first type of relevant information and the first type of channel parameters can be achieved based on the first mapping relationship learned in advance.

[0068] It is possible to learn in advance the second mapping relationship between the second type of related information and the second type of channel parameters, so that the accurate and efficient conversion between the second type of related information and the second type of channel parameters can be achieved based on the pre-learned second mapping relationship.

[0069] It should be noted that the relevant content of the first type of related information and the second type of related information can be found in the above embodiments, and will not be repeated here. No restrictions are placed on the first type of channel parameters or the second type of channel parameters. In some possible implementations, the first type of channel parameters includes at least one of Doppler spread parameters and frequency offset parameters; the second type of channel parameters includes at least one of delay spread parameters and coherence bandwidth parameters.

[0070] Figure 2 This is a flowchart illustrating a method for determining channel parameters according to another exemplary embodiment, such as... Figure 2 As shown, the method for determining channel parameters according to an embodiment of this disclosure includes the following steps.

[0071] S201, determine the target received signal at multiple pilot positions from the received signal.

[0072] S202, based on the known pilot signal and the target received signal at multiple pilot positions, channel estimation is performed to obtain the estimated information of the channel frequency domain response at the corresponding pilot position.

[0073] S203, Based on the estimated information of the channel frequency domain response at each pilot position, determine the target-related information; wherein, the target-related information is used to indicate the correlation between the estimated information at different times and / or the correlation between the estimated information at different frequencies.

[0074] The details of steps S201-S203 can be found in the above embodiments and will not be repeated here.

[0075] S204, Based on the first mapping relationship and the first type of relevant information in the target-related information, determine the first type of channel parameters corresponding to the target-related information.

[0076] In this embodiment, the accurate and efficient conversion between the first type of related information and the first type of channel parameters can be achieved based on the first mapping relationship learned in advance. It is not necessary to calculate the estimation accuracy index of all the first type of channel parameters one by one. In order to determine the first type of channel parameters corresponding to the target related information from all the first type of channel parameters, the computational complexity required to determine the first type of channel parameters can be significantly reduced, which helps to shorten the data processing time, meet the needs of real-time communication, and optimize the user experience.

[0077] For example, continuing with pilot positions 1 to 20, the first type of relevant information in the target-related information can be determined based on the estimated information of the channel frequency domain response at pilot positions 1 to 20. This first type of relevant information includes the cross-correlation information of the estimated channel frequency domain response at OFDM symbols 1 and 2. The cross-correlation information of the estimated channel frequency domain response at OFDM symbols 1 and 3. The cross-correlation information of the estimated channel frequency domain response at OFDM symbols 1 and 4. The cross-correlation information of the estimated channel frequency domain response at OFDM symbols 2 and 3. The cross-correlation information of the estimated channel frequency domain response at OFDM symbols 2 and 4. The cross-correlation information of the estimated channel frequency domain response at OFDM symbols 3 and 4. .

[0078] Based on the first mapping relationship between the first type of relevant information and the first type of channel parameters, and the first type of relevant information in the target-related information, the Doppler spread parameters and frequency offset parameters corresponding to the target-related information are determined.

[0079] In some possible implementations, the first mapping relationship is determined based on the mapping relationship between the first type of related information, the third type of related information, and the first type of channel parameters; wherein the third type of related information is used to indicate the correlation between the estimated information at any given time.

[0080] Based on the first mapping relationship and the first type of relevant information in the target-related information, the first type of channel parameters corresponding to the target-related information are determined. This includes determining the first type of channel parameters corresponding to the target-related information based on the first mapping relationship, the first type of relevant information in the target-related information, and the third type of relevant information in the target-related information. Therefore, based on the pre-learned first mapping relationship, accurate and efficient conversion between the first type of relevant information, the third type of relevant information, and the first type of channel parameters can be achieved. Compared to relying solely on the first type of relevant information to determine the first type of channel parameters, this method comprehensively considers the first mapping relationship between the first type of relevant information, the third type of relevant information, and the first type of channel parameters to determine the first type of channel parameters, thus improving the accuracy of the first type of channel parameters.

[0081] For example, continuing with pilot positions 1 to 20, the third type of relevant information in the target-related information can be determined based on the estimated information of the channel frequency domain response at pilot positions 1 to 20. This third type of relevant information includes the autocorrelation information of the estimated channel frequency domain response at OFDM symbol 1. The autocorrelation information of the estimated channel frequency domain response at OFDM symbol 2. The autocorrelation information of the estimated channel frequency domain response at OFDM symbol 3. The autocorrelation information of the estimated channel frequency domain response at OFDM symbol 4. .

[0082] Based on the first mapping relationship between the first type of relevant information, the third type of relevant information and the first type of channel parameters, as well as the first type of relevant information in the target-related information and the third type of relevant information in the target-related information, the Doppler spread parameters and frequency offset parameters corresponding to the target-related information are determined.

[0083] In some cases, the covariance matrix A can be determined, as follows:

[0084] in, The cross-correlation information of the estimated channel frequency domain response at OFDM symbols 2 and 1, and the cross-correlation information of the estimated channel frequency domain response at OFDM symbols 3 and 1. The cross-correlation information of the estimated channel frequency domain response at OFDM symbols 4 and 1. The cross-correlation information of the estimated channel frequency domain response at OFDM symbols 3 and 2. The cross-correlation information of the estimated channel frequency domain response at OFDM symbols 4 and 2. The cross-correlation information of the estimated channel frequency domain response at OFDM symbols 4 and 3. .

[0085] Based on the first mapping relationship between the first type of relevant information, the third type of relevant information and the first type of channel parameters, and the covariance matrix A, the Doppler spread parameter and frequency offset parameter corresponding to the covariance matrix A are determined.

[0086] Alternatively, since the covariance matrix A is a conjugate symmetric matrix, based on the first mapping relationship between the first type of related information, the third type of related information, and the first type of channel parameters, and the elements of the upper triangular part of the covariance matrix A (i.e., ) and the elements on the main diagonal (i.e. ), determine the Doppler spread parameter and frequency offset parameter corresponding to the covariance matrix A.

[0087] It should be noted that the third type of relevant information is used to indicate the correlation between estimated information at any given time. For example, the third type of relevant information is also used to indicate the channel power at any given time.

[0088] In some possible implementations, target-related information is determined based on the estimated channel frequency domain response at each pilot location. This includes determining the cross-correlation information of the estimated channel frequency domain response at each pilot time-domain location as a first type of related information in the target-related information, and determining the autocorrelation information of the estimated channel frequency domain response at each pilot time-domain location as a third type of related information in the target-related information. Thus, the cross-correlation information of the estimated channel frequency domain response at each pilot time-domain location can be determined to obtain the first type of related information in the target-related information, and the autocorrelation information of the estimated channel frequency domain response at each pilot time-domain location can be determined to obtain the third type of related information in the target-related information.

[0089] For example, the autocorrelation information of the estimated channel frequency domain response at OFDM symbol 1. For example, the average of the squared amplitudes of the estimated channel frequency domain response at pilot positions 1 to 5 can be obtained. As .

[0090] It should be noted that the calculation process of the autocorrelation information of the estimated channel frequency domain response at the other OFDM symbols can be referred to the calculation process of the autocorrelation information of the estimated channel frequency domain response at OFDM symbol 1, and will not be repeated here.

[0091] This disclosure does not impose any restrictions on the execution sequence of steps S201-S204. Figure 2 The example only demonstrates the execution of steps S201-S204 in sequence.

[0092] The channel parameter determination method provided in the embodiments of this disclosure determines the first type of channel parameters corresponding to the target-related information based on a first mapping relationship and a first type of related information in the target-related information. Therefore, based on the pre-learned first mapping relationship, a precise and efficient conversion between the first type of related information and the first type of channel parameters can be achieved. This eliminates the need to calculate the estimation accuracy index of all first-type channel parameters individually to determine the first-type channel parameters corresponding to the target-related information from all first-type channel parameters. This significantly reduces the computational complexity required to determine the first-type channel parameters, helps shorten data processing time, meets the needs of real-time communication, and optimizes the user experience.

[0093] The following describes the process of obtaining the cross-correlation information of the estimated channel frequency domain response at each pilot frequency domain location.

[0094] For example, taking the cross-correlation information of the estimated channel frequency domain response at subcarriers 1 and 2 as an example, the average value of the estimated channel frequency domain response at pilot positions 1, 6, 11, and 16 can be obtained. The average value of the estimated channel frequency domain response at pilot positions 2, 7, 12, and 17 is obtained. .

[0095] The calculation process of the cross-correlation information of the estimated channel frequency domain response at subcarriers 1 and 2 is as follows:

[0096] in, The cross-correlation information of the estimated channel frequency domain response at subcarriers 1 and 2. For the first Channel frequency domain response at subcarrier 1 of OFDM symbol For the first Channel frequency domain response at subcarrier 2 of OFDM symbol This is the complex conjugate operator.

[0097] Alternatively, the calculation process for the cross-correlation information of the estimated channel frequency domain response at subcarriers 1 and 2 is as follows:

[0098] It should be noted that the calculation process of the cross-correlation information of the estimated channel frequency domain response at any other two subcarriers can be referred to the calculation process of the cross-correlation information of the estimated channel frequency domain response at subcarriers 1 and 2, and will not be repeated here.

[0099] Figure 3 This is a flowchart illustrating a method for determining channel parameters according to another exemplary embodiment, such as... Figure 3 As shown, the method for determining channel parameters according to an embodiment of this disclosure includes the following steps.

[0100] S301, determine the target received signal at multiple pilot positions from the received signal.

[0101] S302, based on the known pilot signal and the target received signal at multiple pilot positions, channel estimation is performed to obtain the estimated information of the channel frequency domain response at the corresponding pilot position.

[0102] S303, Based on the estimated information of the channel frequency domain response at each pilot position, determine the target-related information; wherein, the target-related information is used to indicate the correlation between the estimated information at different times and / or the correlation between the estimated information at different frequencies.

[0103] The relevant content of steps S301-S303 can be referred to the above embodiments, and will not be repeated here.

[0104] S304. Based on the second mapping relationship and the second type of relevant information in the target-related information, determine the second type of channel parameters corresponding to the target-related information.

[0105] In this embodiment, the accurate and efficient conversion between second-type related information and second-type channel parameters can be achieved based on the second mapping relationship learned in advance. It is not necessary to calculate the estimation accuracy index of all second-type channel parameters one by one to determine the second-type channel parameters corresponding to the target related information from all second-type channel parameters. This can significantly reduce the computational complexity required to determine the second-type channel parameters, help shorten the data processing time, meet the needs of real-time communication, and optimize the user experience.

[0106] For example, continuing with pilot positions 1 to 20, the second type of relevant information in the target-related information can be determined based on the estimated channel frequency domain response information at pilot positions 1 to 20. This second type of relevant information includes the cross-correlation information of the estimated channel frequency domain response information at subcarriers 1 and 2. The cross-correlation information of the estimated channel frequency domain response at subcarriers 1 and 3. The cross-correlation information of the estimated channel frequency domain response information at subcarriers 1 and 4. The cross-correlation information of the estimated channel frequency domain response at subcarriers 1 and 5. The cross-correlation information of the estimated channel frequency domain response at subcarriers 2 and 3. The cross-correlation information of the estimated channel frequency domain response information at subcarriers 2 and 4. The cross-correlation information of the estimated channel frequency domain response information at subcarriers 2 and 5. The cross-correlation information of the estimated channel frequency domain response information at subcarriers 3 and 4. The cross-correlation information of the estimated channel frequency domain response information at subcarriers 3 and 5. The cross-correlation information of the estimated channel frequency domain response information at subcarriers 4 and 5. .

[0107] Based on the second mapping relationship between the second type of related information and the second type of channel parameters, as well as the second type of related information in the target related information, the delay spread parameter and coherence bandwidth parameter corresponding to the target related information are determined.

[0108] In some possible implementations, the second mapping relationship is determined based on the mapping relationship between the second type of related information, the fourth type of related information, and the second type of channel parameters; wherein the fourth type of related information is used to indicate the correlation between the estimated information at any frequency.

[0109] Based on the second mapping relationship and the second type of relevant information in the target-related information, the second type of channel parameters corresponding to the target-related information are determined. This includes determining the second type of channel parameters based on the second mapping relationship, the second type of relevant information in the target-related information, and the fourth type of relevant information in the target-related information. Therefore, based on the pre-learned second mapping relationship, a precise and efficient conversion between the second type of relevant information, the fourth type of relevant information, and the second type of channel parameters can be achieved. Compared to relying solely on the second type of relevant information to determine the second type of channel parameters, this method comprehensively considers the second mapping relationship between the second type of relevant information, the fourth type of relevant information, and the second type of channel parameters to determine the second type of channel parameters, thus improving the accuracy of the second type of channel parameters.

[0110] For example, continuing with pilot positions 1 to 20, the fourth type of relevant information in the target-related information can be determined based on the estimated channel frequency domain response information at pilot positions 1 to 20. This fourth type of relevant information includes the autocorrelation information of the estimated channel frequency domain response information at subcarrier 1. The autocorrelation information of the estimated channel frequency response at subcarrier 2. The autocorrelation information of the estimated channel frequency response at subcarrier 3. The autocorrelation information of the estimated channel frequency response at subcarrier 4. The autocorrelation information of the estimated channel frequency response at subcarrier 5. .

[0111] Based on the second mapping relationship between the second type of related information, the fourth type of related information and the second type of channel parameters, as well as the second type of related information and the fourth type of related information in the target related information, the delay spread parameter and coherence bandwidth parameter corresponding to the target related information are determined.

[0112] In some cases, the covariance matrix B can be determined, as follows:

[0113] in, The cross-correlation information of the estimated channel frequency domain response at subcarriers 2 and 1 is given. The cross-correlation information of the estimated channel frequency domain response at subcarriers 3 and 1 is given. The cross-correlation information of the estimated channel frequency domain response at subcarriers 4 and 1 is given. The cross-correlation information of the estimated channel frequency domain response at subcarriers 5 and 1 is given. The cross-correlation information of the estimated channel frequency domain response at subcarriers 3 and 2 is given. The cross-correlation information of the estimated channel frequency domain response at subcarriers 4 and 2 is given. The cross-correlation information of the estimated channel frequency domain response at subcarriers 5 and 2 is given. The cross-correlation information of the estimated channel frequency domain response at subcarriers 4 and 3 is given. The cross-correlation information of the estimated channel frequency domain response at subcarriers 5 and 3 is given. The cross-correlation information is the estimated information of the channel frequency domain response at subcarriers 5 and 4.

[0114] Based on the second mapping relationship between the second type of related information, the fourth type of related information and the second type of channel parameters, and the covariance matrix B, the delay spread parameter and coherence bandwidth parameter corresponding to the covariance matrix B are determined.

[0115] Alternatively, since the covariance matrix B is a conjugate symmetric matrix, based on the second mapping relationship between the second type of related information, the fourth type of related information, and the second type of channel parameters, and the elements of the upper triangular part of the covariance matrix B (i.e., ) and the elements on the main diagonal (i.e. ), determine the delay spread parameter and coherence bandwidth parameter corresponding to the covariance matrix B.

[0116] It should be noted that the fourth type of related information is used to indicate the correlation between estimated information at any given frequency. For example, the fourth type of related information is also used to indicate the channel power at any given frequency.

[0117] In some possible implementations, target-related information is determined based on the estimated channel frequency response information at each pilot location. This includes determining the cross-correlation information of the estimated channel frequency response information at each pilot location as the second type of related information in the target-related information, and determining the autocorrelation information of the estimated channel frequency response information at each pilot location as the fourth type of related information in the target-related information. Thus, the cross-correlation information of the estimated channel frequency response information at each pilot location can be determined to obtain the second type of related information in the target-related information, and the autocorrelation information of the estimated channel frequency response information at each pilot location can be determined to obtain the fourth type of related information in the target-related information.

[0118] For example, the autocorrelation information of the estimated channel frequency domain response at subcarrier 1. For example, the average of the squared amplitudes of the estimated channel frequency response at pilot positions 1, 6, 11, and 16 can be obtained as... .

[0119] It should be noted that the calculation process of the autocorrelation information of the estimated channel frequency domain response at the other subcarriers can be referred to the calculation process of the autocorrelation information of the estimated channel frequency domain response at subcarrier 1, and will not be repeated here.

[0120] This disclosure does not impose any restrictions on the execution sequence of steps S301-S304. Figure 3 The example only demonstrates the execution of steps S301-S304 in sequence.

[0121] The channel parameter determination method provided in the embodiments of this disclosure determines the second type of channel parameters corresponding to the target-related information based on a second mapping relationship and second-type related information in the target-related information. Therefore, based on the pre-learned second mapping relationship, accurate and efficient conversion between second-type related information and second-type channel parameters can be achieved without calculating the estimation accuracy index of all second-type channel parameters individually to determine the second-type channel parameters corresponding to the target-related information from all second-type channel parameters. This significantly reduces the computational complexity required to determine the second-type channel parameters, helps shorten data processing time, meets the needs of real-time communication, and optimizes the user experience.

[0122] Figure 4 This is a flowchart illustrating a method for determining channel parameters according to another exemplary embodiment, such as... Figure 4 As shown, the method for determining channel parameters according to an embodiment of this disclosure includes the following steps.

[0123] S401, determine the target received signal at multiple pilot positions from the received signal.

[0124] S402, based on the known pilot signal and the target received signal at multiple pilot positions, channel estimation is performed to obtain the estimated information of the channel frequency domain response at the corresponding pilot position.

[0125] S403, Based on the estimated information of the channel frequency domain response at each pilot position, determine the target-related information; wherein, the target-related information is used to indicate the correlation between the estimated information at different times and / or the correlation between the estimated information at different frequencies.

[0126] The details of steps S401-S403 can be found in the above embodiments and will not be repeated here.

[0127] S404, in response to the input layer obtaining target-related information, the first hidden state of the target-related information is determined through the first hidden layer based on the mapping relationship.

[0128] S405, the k-th hidden state of the target-related information is determined by the (k-1)-th hidden state and mapping relationship of the k-th hidden layer; where k is a positive integer greater than 1 and not greater than M.

[0129] S406 determines the probability of each channel parameter under any category by using the Mth hidden state and mapping relationship based on target-related information in the output layer.

[0130] S407, take the channel parameter with the highest probability under any category as the target channel parameter under the corresponding category of the target-related information.

[0131] In this embodiment, the target model includes a fully connected neural network, which includes an input layer, M hidden layers, and an output layer; where M is a positive integer.

[0132] The hidden state refers to the output value of the hidden layer, which is the feature representation of the input data learned by the hidden layer. In this embodiment, the inference process of the fully connected neural network can be implemented using any inference method of fully connected neural networks in related technologies; no further limitations are imposed here.

[0133] For example, a fully connected neural network includes one input layer, There are one hidden layer and one output layer, with corresponding node numbers of respectively. The number of hidden layers M ranges from 1 to 16, and the number of nodes in each hidden layer... The value range is 1 to 1024.

[0134] The output of each node in hidden layer 1, i.e., the first hidden state related to the target, is defined as follows: The calculation method is as follows:

[0135] in, yes 3D matrix yes 3D vector, target-related information for Dimensional vector. This is the activation function used in the first hidden layer.

[0136] Hidden layer The output of each node, i.e., the k-th hidden state related to the target, is defined as follows: ( The calculation method is as follows:

[0137] in, This represents the (k-1)th hidden state related to the target, i.e., the hidden layer. The output of each node, yes 3D matrix yes dimensional vector, For hidden layer The activation function used.

[0138] The output of each node in the output layer, i.e., the probability of each channel parameter, is defined as follows: The calculation method is as follows:

[0139] in, The Mth hidden state (i.e., hidden layer) of the target-related information. (output of each node) yes 3D matrix yes dimensional vector, This refers to the activation function used in the output layer.

[0140] In this embodiment, , The number of Doppler extension parameters, The number of frequency offset parameters, Let be the probability of the i-th channel parameter (Doppler spread parameter or frequency offset parameter), where i is not greater than 1. Positive integers.

[0141] Available from The probability of the largest value is determined, and the Doppler expansion parameter corresponding to the probability of the largest value is used as the Doppler expansion parameter corresponding to the target-related information.

[0142] Available from The probability of the highest value is determined, and the frequency offset parameter corresponding to the highest probability is used as the frequency offset parameter corresponding to the target-related information.

[0143] It should be noted that this disclosure does not impose any restrictions on the execution sequence of steps S401-S407. Figure 4 The example only demonstrates the execution of steps S401-S407 in sequence.

[0144] The channel parameter determination method provided in the embodiments of this disclosure, in response to the input layer obtaining target-related information, determines the first hidden state of the target-related information based on a mapping relationship through the first hidden layer, and determines the k-th hidden state of the target-related information based on the (k-1)-th hidden state and the mapping relationship through the k-th hidden layer; where k is a positive integer greater than 1 and not greater than M. The probability of each channel parameter under any category is determined through the output layer based on the M-th hidden state and the mapping relationship of the target-related information. The channel parameter with the highest probability under any category is taken as the target channel parameter for the corresponding category of the target-related information. Therefore, the target-related information can be processed by a fully connected neural network to determine the target channel parameters corresponding to the target-related information. Fully connected neural networks have advantages such as simple structure, ease of implementation, and stable training, which helps to improve the efficiency and accuracy of target channel parameter determination.

[0145] Figure 5 This is a flowchart illustrating a method for determining channel parameters according to another exemplary embodiment, such as... Figure 5 As shown, the method for determining channel parameters according to an embodiment of this disclosure includes the following steps.

[0146] S501, determine the target received signal at multiple pilot positions from the received signal.

[0147] S502, based on the known pilot signal and the target received signal at multiple pilot positions, channel estimation is performed to obtain the estimated information of the channel frequency domain response at the corresponding pilot position.

[0148] S503, based on the estimated information of the channel frequency domain response at each pilot position, determine the target-related information; wherein, the target-related information is used to indicate the correlation between the estimated information at different times and / or the correlation between the estimated information at different frequencies.

[0149] The relevant content of steps S501-S503 can be found in the above embodiments, and will not be repeated here.

[0150] S504: Based on the mapping relationship, determine the candidate channel parameters corresponding to the target-related information through any decision tree.

[0151] S505, based on a voting mechanism, determines the target channel parameters corresponding to the target-related information from the candidate channel parameters determined by multiple decision trees.

[0152] In this embodiment, the target model includes a random forest, which comprises multiple decision trees.

[0153] The inference process of random forest can be implemented using any inference method of random forest in related technologies, and no further restrictions are imposed here.

[0154] For example, random forests include A decision tree, when At this point, the random forest degenerates into a decision tree. Each decision tree provides its own classification result (i.e., candidate channel parameters) based on the input data. Finally, a vote is taken based on the classification results of multiple decision trees, and the classification result with the most votes becomes the final classification result (i.e., the target channel parameters). It should be noted that the input data in this embodiment includes target-related information.

[0155] Let's take a binary tree structure as an example to illustrate the reasoning process of a single decision tree. The implementation of a single decision tree is as follows: The bottom layer of a decision tree consists of leaf nodes, each corresponding to a classification result. If the decision process falls into a leaf node, the final classification result of the decision tree is determined. Apart from the leaf nodes in the bottom layer, each node in the remaining layers of the decision tree takes a feature from the input data and determines whether it meets specific conditions to decide which child node the node will move to next.

[0156] Assuming that the order relation is used as the decision condition for each node, then the decision node for each non-leaf node can be represented as follows: ,in Indicates the feature number, The order relation threshold means that for input data... ,like The next step is to choose to enter the left branch, otherwise enter the right branch; and so on.

[0157] Specifically, for those with The decision tree of nodes within a layer, based on input data It will experience The final judgment was obtained through this process. First determination: The root node has preset parameters. It is obtained through pre-training, where the first parameter is a value. Given a sequence number, the second parameter is a real threshold. (Decision) Check if the condition is true. If true, proceed to the left branch connected to the root node and mark the result as true. Otherwise, proceed to the right branch connected to the root node, and mark the judgment result as... .

[0158] Second determination: Corresponding to the internal nodes of the first layer, with preset parameters. It is obtained through pre-training, where the first parameter in each group is a value. The second parameter is a real number threshold, defined by a specific index in the dataset. Based on the result of the first determination... Determine the parameters corresponding to the associated nodes in the second determination. . determination Check if the condition is met. If it is, proceed to the left branch connected to the internal node and mark the result as true. Otherwise, proceed to the right branch connected to that internal node, and mark the judgment result as... .

[0159] No. Secondary judgment ( ): Corresponding to the The nodes inside the layer have preset parameters. It is obtained through pre-training, where the first parameter in each group is a value. A certain index in the sequence, the second parameter is a real number threshold. According to the... Second judgment result Determine the first The parameters corresponding to the associated nodes in this determination . determination If the condition is true, proceed to the left branch connected to the internal node and mark the final decision as U; otherwise, proceed to the right branch connected to the internal node and mark the final decision as V.

[0160] Here, U and V refer to different channel parameters.

[0161] It should be noted that this disclosure does not impose any restrictions on the execution sequence of steps S501-S505. Figure 5 The example only demonstrates the sequential execution of steps S501-S505.

[0162] The channel parameter determination method provided in this disclosure determines candidate channel parameters corresponding to target-related information based on mapping relationships using any decision tree, and determines the target channel parameters corresponding to the target-related information from the candidate channel parameters determined by multiple decision trees based on a voting mechanism. Therefore, target-related information can be processed using random forests to determine the target channel parameters corresponding to the target-related information. Random forests have advantages such as high accuracy, low overfitting resistance, and good robustness, which helps improve the efficiency and accuracy of target channel parameter determination.

[0163] The training content of the target model will be described below.

[0164] Figure 6 This is a flowchart illustrating a model training method according to an exemplary embodiment, such as... Figure 6 As shown, the model training method of this disclosure includes the following steps.

[0165] S601, based on the sample estimation information of the channel frequency domain response at each sample pilot position, determine the sample-related information; wherein, the sample-related information is used to indicate the correlation between sample estimation information at different times and / or the correlation between sample estimation information at different frequencies.

[0166] S602, the target model is trained based on sample-related information and sample channel parameters; wherein, the mapping relationship is updated as the target model is trained.

[0167] It should be noted that the execution subject of the model training method in this embodiment is an electronic device, such as a terminal device, vehicle, robot, server, chip, etc. The terminal device includes mobile phone, wearable device (such as smartwatch, smart glasses), laptop, etc., and the vehicle includes vehicle terminal, vehicle controller, etc.

[0168] In some possible implementations, the target model is trained based on sample-related information and sample channel parameters, including training the target model based on a first type of related information in the sample-related information and a first type of channel parameters in the sample channel parameters; wherein, the first mapping relationship is updated as the target model is trained. It is understood that if the target model is trained based on the first type of related information in the sample-related information and the first type of channel parameters in the sample channel parameters, the target model can learn the first mapping relationship between the first type of related information and the first type of channel parameters during training, so that the first mapping relationship is updated as the target model is trained.

[0169] In some possible implementations, the first mapping relationship is determined based on the mapping relationship between first-type related information, third-type related information, and first-type channel parameters. Training the target model based on sample-related information and sample channel parameters includes training the target model based on first-type related information in the sample-related information, third-type related information in the sample-related information, and first-type channel parameters in the sample channel parameters; wherein, the first mapping relationship is updated as the target model is trained. It is understood that if the target model is trained based on first-type related information in the sample-related information, third-type related information in the sample-related information, and first-type channel parameters in the sample channel parameters, then the target model can learn the first mapping relationship between first-type related information, third-type related information, and first-type channel parameters during training, so that the first mapping relationship is updated as the target model is trained.

[0170] In some possible implementations, the target model is trained based on sample-related information and sample channel parameters, including training the target model based on second-type related information in the sample-related information and second-type channel parameters in the sample channel parameters; wherein, the second mapping relationship is updated as the target model is trained. It is understood that if the target model is trained based on second-type related information in the sample-related information and second-type channel parameters in the sample channel parameters, the target model can learn the second mapping relationship between the second-type related information and the second-type channel parameters during training, causing the second mapping relationship to be updated as the target model is trained.

[0171] In some possible implementations, the second mapping relationship is determined based on the mapping relationship between the second type of related information, the fourth type of related information, and the second type of channel parameters. Training the target model based on sample related information and sample channel parameters includes training the target model based on the second type of related information in the sample related information, the fourth type of related information in the sample related information, and the second type of channel parameters in the sample channel parameters; wherein, the second mapping relationship is updated as the target model is trained. It is understood that if the target model is trained based on the second type of related information in the sample related information, the fourth type of related information in the sample related information, and the second type of channel parameters in the sample channel parameters, then the target model can learn the second mapping relationship between the second type of related information, the fourth type of related information, and the second type of channel parameters during the training process, so that the second mapping relationship is updated as the target model is trained.

[0172] It should be noted that, based on sample-related information and sample channel parameters, the target model can be trained using any model training method from the relevant technologies, without further restrictions here.

[0173] In some possible implementations, the target model is trained based on sample-related information and sample channel parameters. This includes determining the predicted channel parameters of the sample channels using the learned mapping relationship from the target model, and training the target model based on the sample channel parameters and the predicted channel parameters. Thus, the predicted channel parameters of the sample channels can be determined using the learned mapping relationship from the target model, and the target model can be trained taking into account both the sample channel parameters and the predicted channel parameters.

[0174] For example, training the target model based on sample channel parameters and predicted channel parameters involves determining the loss function of the target model based on the sample channel parameters and predicted channel parameters, and then training the target model based on the loss function. The loss function is not subject to many restrictions; it can include cross-entropy loss function, mean squared error loss function, mean absolute error loss function, KL (Kullback-Leibler) divergence loss function, etc.

[0175] It should be noted that this disclosure does not impose any restrictions on the execution sequence of steps S601-S602. Figure 6 The example only demonstrates the execution of steps S601-S602 in sequence.

[0176] The model training method provided in this disclosure determines sample-related information based on sample estimation information of the channel frequency domain response at each sample pilot position. The sample-related information indicates the correlation between sample estimation information at different times and / or the correlation between sample estimation information at different frequencies. The target model is trained based on the sample-related information and sample channel parameters. The mapping relationship is updated as the target model is trained. Therefore, during training, the target model can learn the reasoning ability to determine sample channel parameters based on sample-related information, and can learn the mapping relationship between the relevant information and the channel parameters, so that the mapping relationship is updated as the target model is trained.

[0177] Figure 7 This is a schematic diagram of a channel parameter determination device according to an exemplary embodiment.

[0178] Reference Figure 7 The channel parameter determination device 700 of this disclosure includes: a first determination module 701, an estimation module 702, a second determination module 703, and a third determination module 704.

[0179] The first determining module 701 is configured to determine the target received signal at multiple pilot positions from the received signal; The estimation module 702 is configured to perform channel estimation based on the known pilot signal and the target received signal at the plurality of pilot positions, so as to obtain the estimated information of the channel frequency domain response at the corresponding pilot position; The second determining module 703 is configured to determine target-related information based on the estimated information of the channel frequency domain response at each pilot position; wherein the target-related information is used to indicate the correlation between the estimated information at different times and / or the correlation between the estimated information at different frequencies. The third determining module 704 is configured to determine the target channel parameters corresponding to the target related information based on the mapping relationship between the relevant information and the channel parameters obtained in advance.

[0180] In some possible implementations, the mapping relationship includes at least one of the following: A first mapping relationship between a first type of related information and a first type of channel parameters; wherein the first type of related information is used to indicate the correlation between the estimated information at different times, and the first type of channel parameters are used to indicate the degree of time-domain variation of the channel; A second mapping relationship between the second type of related information and the second type of channel parameters; wherein the second type of related information is used to indicate the correlation between the estimated information at different frequencies, and the second type of channel parameters is used to indicate the degree of frequency domain variation of the channel.

[0181] In some possible implementations, the third determining module 704 is further configured to: determine the first type of channel parameters corresponding to the target-related information based on the first mapping relationship and the first type of related information in the target-related information.

[0182] In some possible implementations, the first mapping relationship is determined based on the mapping relationship between the first type of related information, the third type of related information, and the first type of channel parameters; wherein, the third type of related information is used to indicate the correlation between the estimated information at any given time. The third determining module 704 is further configured to: determine the first type of channel parameters corresponding to the target-related information based on the first mapping relationship, the first type of related information in the target-related information, and the third type of related information in the target-related information.

[0183] In some possible implementations, the second determining module 703 is further configured to: determine the cross-correlation information of the estimated channel frequency domain response at each pilot time domain location as the first type of related information in the target related information; and determine the autocorrelation information of the estimated channel frequency domain response at each pilot time domain location as the third type of related information in the target related information.

[0184] In some possible implementations, the third determining module 704 is further configured to: determine the second type of channel parameters corresponding to the target-related information based on the second mapping relationship and the second type of related information in the target-related information.

[0185] In some possible implementations, the second mapping relationship is determined based on the mapping relationship between the second type of related information, the fourth type of related information, and the second type of channel parameters; wherein the fourth type of related information is used to indicate the correlation between the estimated information at any frequency; The third determining module 704 is further configured to: determine the second type of channel parameters corresponding to the target-related information based on the second mapping relationship, the second type of related information in the target-related information, and the fourth type of related information in the target-related information.

[0186] In some possible implementations, the second determining module 703 is further configured to: determine the cross-correlation information of the estimated channel frequency response at each pilot frequency domain location as the second type of related information in the target related information; and determine the autocorrelation information of the estimated channel frequency response at each pilot frequency domain location as the fourth type of related information in the target related information.

[0187] In some possible implementations, the first type of channel parameters includes at least one of Doppler spread parameters and frequency offset parameters; The second type of channel parameters includes at least one of the delay spread parameter and the coherence bandwidth parameter.

[0188] In some possible implementations, the third determining module 704 is further configured to: determine the target channel parameters corresponding to the target-related information based on the mapping relationship using the target model.

[0189] In some possible implementations, the target model includes a fully connected neural network, which includes an input layer, M hidden layers, and an output layer; where M is a positive integer. The third determining module 704 is further configured to: in response to the input layer obtaining the target-related information, determine the first hidden state of the target-related information based on the mapping relationship through the first hidden layer; determine the k-th hidden state of the target-related information based on the (k-1)-th hidden state of the target-related information and the mapping relationship through the k-th hidden layer; where k is a positive integer greater than 1 and not greater than M; determine the probability of each channel parameter under any category through the output layer based on the M-th hidden state of the target-related information and the mapping relationship; and take the channel parameter with the highest probability under any category as the target channel parameter under the corresponding category of the target-related information.

[0190] In some possible implementations, the target model includes a random forest, which includes multiple decision trees; the third determining module 704 is further configured to: determine candidate channel parameters corresponding to the target-related information based on the mapping relationship through any of the decision trees; and determine the target channel parameters corresponding to the target-related information from the candidate channel parameters determined by the multiple decision trees based on a voting mechanism.

[0191] In some possible implementations, the apparatus further includes a training module configured to: determine sample-related information based on sample estimation information of the channel frequency domain response at each sample pilot position; wherein the sample-related information is used to indicate the correlation between the sample estimation information at different times and / or the correlation between the sample estimation information at different frequencies; and train the target model based on the sample-related information and the sample channel parameters; wherein the mapping relationship is updated as the target model is trained.

[0192] In some possible implementations, the training module is further configured to: determine the predicted channel parameters of the sample channel based on the learned mapping relationship using the target model; and train the target model based on the sample channel parameters and the predicted channel parameters.

[0193] In some possible implementations, after determining the target channel parameters corresponding to the target-related information, the third determining module 704 is further configured to perform at least one of the following: demodulating the received signal based on the target channel parameters to obtain demodulated data of the received signal after demodulation processing; and determining the channel estimation period based on the target channel parameters.

[0194] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0195] The channel parameter determination apparatus provided in the embodiments of this disclosure determines target received signals at multiple pilot positions from received signals. Based on known pilot signals, channel estimation is performed on the target received signals at the multiple pilot positions to obtain estimated information of the channel frequency domain response at the corresponding pilot positions. Based on the estimated information of the channel frequency domain response at each pilot position, target-related information is determined. The target-related information is used to indicate the correlation between estimated information at different times and / or the correlation between estimated information at different frequencies. Based on the mapping relationship between the pre-learned related information and channel parameters, the target channel parameters corresponding to the target-related information are determined. Therefore, based on the pre-learned mapping relationship, accurate and efficient conversion from target-related information to target channel parameters can be achieved without calculating the estimation accuracy index of all channel parameters individually to determine the target channel parameters from all channel parameters. This significantly reduces the computational complexity required to determine the target channel parameters, helps shorten data processing time, meets the needs of real-time communication, and optimizes the user experience.

[0196] To implement the above embodiments, this disclosure also proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the method for determining channel parameters provided in this disclosure.

[0197] Figure 8 This is a schematic diagram illustrating the structure of an electronic device according to an exemplary embodiment. For example, the electronic device 800 may be a vehicle, mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0198] Reference Figure 8 The electronic device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input / output (I / O) interface 812, sensor component 814, and communication component 816.

[0199] Processing component 802 typically controls the overall operation of electronic device 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the channel parameter determination method described above. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

[0200] Memory 804 is configured to store various types of data to support the operation of electronic device 800. Examples of this data include instructions for any application or method operating on electronic device 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can 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 storage, flash memory, magnetic disk, or optical disk.

[0201] Power component 806 provides power to various components of electronic device 800. Power component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 800.

[0202] Multimedia component 808 includes a screen that provides an output interface between electronic device 800 and 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 may be implemented as a touchscreen 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 may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When electronic device 800 is in an operating mode, such as a shooting mode or video mode, the front-facing camera and / or rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0203] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when electronic device 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0204] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0205] Sensor assembly 814 includes one or more sensors for providing state assessments of various aspects of electronic device 800. For example, sensor assembly 814 can detect the on / off state of electronic device 800, the relative positioning of components such as the display and keypad of electronic device 800, changes in position of electronic device 800 or a component of electronic device 800, the presence or absence of user contact with electronic device 800, orientation or acceleration / deceleration of electronic device 800, and temperature changes of electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include an optical sensor, such as a complementary metal-oxide-semiconductor (CMOS) or charge-coupled device (CCD) image sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0206] Communication component 816 is configured to facilitate wired or wireless communication between electronic device 800 and other devices. Electronic device 800 can access wireless networks based on communication standards, such as WiFi, 4G, or 5G, or combinations thereof. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also 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), Infrared Data Association (IrDA), Ultra-Wideband (UWB), Bluetooth, and other technologies.

[0207] 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 to perform the steps of the method for determining the channel parameters described above.

[0208] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, which can be executed by a processor 820 of an electronic device 800 to complete the method for determining the channel parameters. For example, the non-transitory computer-readable storage medium may be a read-only memory (ROM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0209] To implement the above embodiments, this disclosure also proposes a non-transitory computer-readable storage medium storing computer program instructions thereon, which, when executed by a processor, implement the steps of the method for determining channel parameters provided in this disclosure.

[0210] To implement the above embodiments, this disclosure also proposes a chip including an interface circuit and a processing circuit coupled to each other. The interface circuit is used to input or output signals, and the processing circuit is configured to implement the steps of the method for determining channel parameters provided in this disclosure.

[0211] Figure 9 This is a schematic diagram illustrating the structure of a chip according to an exemplary embodiment. See also... Figure 9 The diagram shown is a schematic representation of the structure of chip 900, but it is not limited to this.

[0212] Chip 900 includes processing circuitry 901, which is configured to perform the steps of the method for determining any of the channel parameters described above.

[0213] In some embodiments, chip 900 further includes one or more interface circuits 902. In some possible embodiments, interface circuit 902 is connected to memory 903, and interface circuit 902 can be used to receive signals from memory 903 or other devices, and interface circuit 902 can be used to send signals to memory 903 or other devices. For example, interface circuit 902 can read instructions stored in memory 903 and send the instructions to processing circuit 901.

[0214] In some embodiments, the interface circuit 902 performs at least one of the communication steps such as sending and / or receiving in the above method, and the processing circuit 901 performs other steps.

[0215] In some embodiments, the terms interface circuit, interface, transceiver pin, transceiver, etc., can be used interchangeably.

[0216] In some embodiments, chip 900 further includes one or more memories 903 for storing instructions. In some possible embodiments, all or part of the memories 903 may be located outside of chip 900.

[0217] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program that, when executed by a processor, implements the steps of the method for determining channel parameters provided in this disclosure.

[0218] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0219] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0220] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.

[0221] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and compact disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0222] It should be understood that various parts of this disclosure can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0223] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0224] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0225] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A method of determining channel parameters, characterized by, include: Determine the target received signal at multiple pilot positions from the received signal; Channel estimation is performed based on the known pilot signals and the target received signals at the multiple pilot positions to obtain the estimated information of the channel frequency domain response at the corresponding pilot positions; Based on the estimated information of the channel frequency domain response at each pilot position, target-related information is determined; wherein, the target-related information is used to indicate the correlation between the estimated information at different times and / or the correlation between the estimated information at different frequencies; Based on the mapping relationship between the relevant information obtained in advance and the channel parameters, the target channel parameters corresponding to the target relevant information are determined.

2. The method of claim 1, wherein, The mapping relationship includes at least one of the following: A first mapping relationship between a first type of related information and a first type of channel parameters; wherein the first type of related information is used to indicate the correlation between the estimated information at different times, and the first type of channel parameters are used to indicate the degree of time-domain variation of the channel; A second mapping relationship between the second type of related information and the second type of channel parameters; wherein the second type of related information is used to indicate the correlation between the estimated information at different frequencies, and the second type of channel parameters is used to indicate the degree of frequency domain variation of the channel.

3. The method of claim 2, wherein, The determination of the target channel parameters corresponding to the target-related information based on the mapping relationship between pre-learned relevant information and channel parameters includes: Based on the first mapping relationship and the first type of related information in the target-related information, the first type of channel parameters corresponding to the target-related information are determined.

4. The method of claim 3, wherein, The first mapping relationship is determined based on the mapping relationship between the first type of related information, the third type of related information, and the first type of channel parameters; wherein, the third type of related information is used to indicate the correlation between the estimated information at any time. The step of determining the first type of channel parameters corresponding to the target-related information based on the first mapping relationship and the first type of related information in the target-related information includes: Based on the first mapping relationship, the first type of related information in the target-related information, and the third type of related information in the target-related information, the first type of channel parameters corresponding to the target-related information are determined.

5. The method of claim 4, wherein, The estimated information based on the channel frequency domain response at each pilot location is used to determine target-related information, including: The cross-correlation information of the estimated information of the channel frequency domain response at each pilot time domain location is determined as the first type of related information in the target related information; The autocorrelation information of the estimated information of the channel frequency domain response at each pilot time domain location is determined as the third type of related information in the target related information.

6. The method of claim 2, wherein, The determination of the target channel parameters corresponding to the target-related information based on the mapping relationship between pre-learned relevant information and channel parameters includes: Based on the second mapping relationship and the second type of related information in the target related information, the second type of channel parameters corresponding to the target related information are determined.

7. The method of claim 6, wherein, The second mapping relationship is determined based on the mapping relationship between the second type of related information, the fourth type of related information, and the second type of channel parameters; wherein, the fourth type of related information is used to indicate the correlation between the estimated information at any frequency; The step of determining the second type of channel parameters corresponding to the target-related information based on the second mapping relationship and the second type of related information in the target-related information includes: Based on the second mapping relationship, the second type of related information in the target-related information, and the fourth type of related information in the target-related information, the second type of channel parameters corresponding to the target-related information are determined.

8. The method of claim 7, wherein, The estimated information based on the channel frequency domain response at each pilot location is used to determine target-related information, including: The cross-correlation information of the estimated information of the channel frequency domain response at each pilot frequency domain location is determined as the second type of related information in the target related information; The autocorrelation information of the estimated information of the channel frequency domain response at each pilot frequency domain location is determined as the fourth type of related information in the target related information.

9. The method according to any one of claims 2-8, characterized in that, The first type of channel parameters includes at least one of the Doppler spread parameter and the frequency offset parameter; The second type of channel parameters includes at least one of the delay spread parameter and the coherence bandwidth parameter.

10. The method according to any one of claims 1-8, characterized in that, The determination of the target channel parameters corresponding to the target-related information based on the mapping relationship between pre-learned relevant information and channel parameters includes: Based on the mapping relationship, the target channel parameters corresponding to the target-related information are determined using the target model.

11. The method of claim 10, wherein, The target model includes a fully connected neural network, which comprises an input layer, M hidden layers, and an output layer; where M is a positive integer. The step of determining the target channel parameters corresponding to the target-related information based on the mapping relationship using the target model includes: In response to the input layer obtaining the target-related information, the first hidden state of the target-related information is determined by the first hidden layer based on the mapping relationship; The k-th hidden state of the target-related information is determined by the (k-1)-th hidden state of the target-related information and the mapping relationship in the k-th hidden layer; where k is a positive integer greater than 1 and not greater than M. The output layer determines the probability of each channel parameter under any category based on the Mth hidden state of the target-related information and the mapping relationship. The channel parameter with the highest probability in any category is taken as the target channel parameter in the corresponding category of the target-related information.

12. The method of claim 10, wherein, The target model includes a random forest, which comprises multiple decision trees; The step of determining the target channel parameters corresponding to the target-related information based on the mapping relationship using the target model includes: Based on the mapping relationship, candidate channel parameters corresponding to the target-related information are determined using any of the decision trees. Based on the voting mechanism, the target channel parameters corresponding to the target-related information are determined from the candidate channel parameters determined by the multiple decision trees.

13. The method according to claim 10, characterized in that, The target model is trained in the following manner: Based on the sample estimation information of the channel frequency domain response at each sample pilot position, sample-related information is determined; wherein, the sample-related information is used to indicate the correlation between the sample estimation information at different times and / or the correlation between the sample estimation information at different frequencies; The target model is trained based on the sample-related information and the sample channel parameters; wherein the mapping relationship is updated as the target model is trained.

14. The method according to claim 13, characterized in that, The step of training the target model based on the sample-related information and the sample channel parameters includes: Based on the learned mapping relationship, the target model determines the predicted channel parameters of the sample channel; The target model is trained based on the sample channel parameters and the predicted channel parameters.

15. The method according to any one of claims 1-8, characterized in that, After determining the target channel parameters corresponding to the target-related information, the method further includes at least one of the following: Based on the target channel parameters, the received signal is demodulated to obtain demodulated data of the received signal after demodulation processing; Based on the target channel parameters, the channel estimation period is determined.

16. A device for determining channel parameters, characterized in that, include: The first determining module is configured to determine the target received signal at multiple pilot positions from the received signal; The estimation module is configured to perform channel estimation based on the known pilot signal and the target received signal at the plurality of pilot positions, so as to obtain the estimated information of the channel frequency domain response at the corresponding pilot position; The second determining module is configured to determine target-related information based on the estimated information of the channel frequency domain response at each pilot position; wherein the target-related information is used to indicate the correlation between the estimated information at different times and / or the correlation between the estimated information at different frequencies. The third determining module is configured to determine the target channel parameters corresponding to the target-related information based on the mapping relationship between the relevant information and the channel parameters obtained in advance.

17. The apparatus according to claim 16, characterized in that, The mapping relationship includes at least one of the following: A first mapping relationship between a first type of related information and a first type of channel parameters; wherein the first type of related information is used to indicate the correlation between the estimated information at different times, and the first type of channel parameters are used to indicate the degree of time-domain variation of the channel; A second mapping relationship between the second type of related information and the second type of channel parameters; wherein the second type of related information is used to indicate the correlation between the estimated information at different frequencies, and the second type of channel parameters is used to indicate the degree of frequency domain variation of the channel.

18. The apparatus according to claim 17, characterized in that, The third determining module is further configured to: Based on the first mapping relationship and the first type of related information in the target-related information, the first type of channel parameters corresponding to the target-related information are determined.

19. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the steps of the method according to any one of claims 1-15.

20. A non-transitory computer-readable storage medium having computer program instructions stored thereon, characterized in that, When executed by a processor, the program instructions implement the steps of the method described in any one of claims 1-15.

21. A chip, characterized in that, The chip includes an interface circuit and a processing circuit coupled to each other. The interface circuit is used to input or output signals, and the processing circuit is configured to implement the steps of the method according to any one of claims 1-15.

22. A computer program product, characterized in that, Includes a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1-15.

Images