Channel type identification method and device, electronic equipment and storage medium

Abstract

This application provides a channel type identification method, apparatus, electronic device, and storage medium, which can solve the technical problem of poor channel type identification performance in related technologies. The method includes: measuring a reference signal to determine the channel characteristics of the channel corresponding to the reference signal; determining the channel type based on the channel characteristics; and the channel type being correlated with the number of dominant paths in the channel. Since the transmit power, modulation format, frame structure, and other parameters of the reference signal are known information at the receiver, the superposition effects of non-inherent features such as noise and interference can be effectively filtered out, and the extracted channel features can accurately map the channel type. This eliminates the high-order computational steps of spectrum estimation, significantly reducing the processor's computational load and memory usage, adapting to the application needs of low-to-medium computing power terminal devices, and ensuring the stability and reliability of the channel type determination results by avoiding interference from non-inherent features.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to methods, apparatus, electronic devices, and storage media for channel type identification. Background Technology

[0002] Wireless channel type identification can provide crucial prior information for core functional modules such as channel measurement and channel estimation, thereby significantly improving the overall performance of wireless communication systems while effectively reducing the complexity of system algorithms. However, related technologies directly rely on the inherent propagation characteristics of the channel (such as power delay spectrum, Doppler spectrum, or channel matrix rank) to determine the channel type, which cannot simultaneously meet the requirements of low complexity and high discrimination accuracy, resulting in poor channel type identification performance. Summary of the Invention

[0003] To overcome the technical problem of poor channel type identification performance in related technologies, this application provides a channel type identification method, apparatus, electronic device, and storage medium.

[0004] According to a first aspect of the embodiments of this application, a channel type identification method is provided, the channel type identification method comprising: measuring a reference signal to determine the channel characteristics of the channel corresponding to the reference signal; determining the channel type of the channel based on the channel characteristics; the channel type being associated with the number of dominant paths in the channel; and the dominant path being used to characterize transmission paths in the channel whose signal power ratio is greater than a preset threshold.

[0005] In some possible implementations, the channel type includes at least one of the following: a first non-line-of-sight (NLOS) channel; the number of dominant paths in the first NLOS channel is zero; a line-of-sight (LOS) channel; the number of dominant paths in the line-of-sight (LOS) channel is one; a dynamic point selection channel; the number of dominant paths in the dynamic point selection channel is one; a second non-line-of-sight (NLOS) channel; the number of dominant paths in the second NLOS channel is one; a single-frequency network (SFM) channel; the SFM channel includes at least two dominant paths.

[0006] In some possible implementations, channel characteristics include channel time-domain characteristics and / or channel frequency-domain characteristics.

[0007] In some possible implementations, the channel time-domain characteristics include time-domain correlation coefficients.

[0008] In some possible implementations, the reference signal includes a first signal and a second signal transmitted at different times. Measuring the reference signal to determine the channel characteristics of the channel corresponding to the reference signal includes: determining a first channel estimate based on the first signal; determining a second channel estimate based on the second signal; determining a first frequency domain channel inner product based on the first channel estimate and the second channel estimate; determining a first channel power normalization result for the first signal and the second channel estimate based on the first channel estimate and the second channel estimate; and determining a time domain correlation coefficient based on the first frequency domain channel inner product and the first channel power normalization result.

[0009] In some possible implementations, the first signal and the second signal are configured on the first subframe; the reference signal further includes a third signal and a fourth signal configured on the second subframe, wherein the first subframe and the second subframe are non-overlapping time-domain resources; the reference signal is measured to determine the channel characteristics of the channel corresponding to the reference signal, including: determining the first channel time-domain characteristics of the first signal and the second signal, the second channel time-domain characteristics of the first signal and the third signal, the third channel time-domain characteristics of the first signal and the fourth signal, the fourth channel time-domain characteristics of the second signal and the third signal, the fifth channel time-domain characteristics of the second signal and the fourth signal, and the sixth channel time-domain characteristics of the third signal and the fourth signal; and determining the channel characteristics based on the first channel time-domain characteristics, the second channel time-domain characteristics, the third channel time-domain characteristics, the fourth channel time-domain characteristics, the fifth channel time-domain characteristics, and the sixth channel time-domain characteristics.

[0010] In some possible implementations, determining the channel type includes: selecting pairs of reference signals from the reference signals and calculating the Orthogonal Frequency Division Multiplexing (OFDM) symbol spacing for each pair; for multiple pairs of reference signals with the same OFDM symbol spacing, determining the time-domain characteristics of the spacing of the multiple pairs of reference signals based on the time-domain correlation coefficients of each pair; for a single pair of reference signals with a unique OFDM symbol spacing, using the time-domain correlation coefficient of the single pair of reference signals as the time-domain characteristic of the single pair of reference signals; and obtaining the set of channel time-domain characteristics based on the time-domain characteristics of the multiple pairs of reference signals and the time-domain characteristics of the single pair of reference signals.

[0011] In some possible implementations, determining the channel type includes: determining a first interval time-domain feature based on a first channel time-domain feature and a sixth channel time-domain feature when the interval between the OFDM symbols of the first signal and the second signal is equal to the interval between the OFDM symbols of the third signal and the fourth signal; determining a second interval time-domain feature based on a second channel time-domain feature and a fifth channel time-domain feature when the interval between the OFDM symbols of the first signal and the third signal is equal to the interval between the OFDM symbols of the second signal and the fourth signal; determining a third interval time-domain feature based on a third channel time-domain feature when the interval between the OFDM symbols of the first signal and the second signal is different from the interval between the OFDM symbols of the second signal and the third signal; determining a fourth interval time-domain feature based on a fourth channel time-domain feature; and determining channel features based on the first interval time-domain feature, the second interval time-domain feature, the third interval time-domain feature, and the fourth interval time-domain feature.

[0012] In some possible implementations, determining the first frequency domain channel inner product based on the first channel estimate and the second channel estimate includes: determining a first power delay spectrum of the first signal based on the first channel estimate; determining a second power delay spectrum of the second signal based on the second channel estimate; setting the coefficients of other regions in the first power delay spectrum except for the target region to zero to obtain a third power delay spectrum; the target region includes at least one spectral peak region; setting the coefficients of other regions in the second power delay spectrum except for the target region to zero to obtain a fourth power delay spectrum; and determining the first frequency domain channel inner product based on the third power delay spectrum and the fourth power delay spectrum.

[0013] In some possible implementations, the channel type is determined based on channel characteristics, including: obtaining the channel type by means of a channel type identification model based on the channel characteristics; wherein the channel type identification model is trained based on multiple samples; each sample in the multiple samples corresponds to a different channel type label, and each sample includes channel characteristics corresponding to multiple orthogonal frequency division multiplexing (OFDM) symbol intervals.

[0014] In some possible implementations, the channel type is obtained by: when the OFDM symbol spacing of the channel characteristics is greater than the OFDM symbol spacing threshold, determining the channel type based on the channel characteristics and the decision tree depth threshold using a channel type identification model.

[0015] In some possible implementations, obtaining the channel type of the channel includes: acquiring the channel characteristics of the reference signal at multiple time points; and determining the channel type of the channel at each of the multiple time points using a channel type identification model based on the channel characteristics of the reference signal at multiple time points.

[0016] According to a second aspect of the embodiments of this application, a channel type identification device is provided, comprising: a data processing unit and a channel identification unit; the data processing unit is configured to measure a reference signal to determine the channel characteristics of the channel corresponding to the reference signal; the channel identification unit is configured to determine the channel type of the channel based on the channel characteristics; the channel type is associated with the number of dominant paths in the channel; the dominant path is used to characterize the transmission path in the channel whose signal power ratio is greater than a preset threshold.

[0017] In some possible implementations, the data processing unit is configured to: determine a first channel estimate based on a first signal; determine a second channel estimate based on a second signal; determine a first frequency domain channel inner product based on the first channel estimate and the second channel estimate; determine a first channel power normalization result for the first signal and the second signal based on the first channel estimate and the second channel estimate; and determine a time domain correlation coefficient based on the first frequency domain channel inner product and the first channel power normalization result.

[0018] In some possible implementations, the data processing unit is used to determine the first channel time-domain characteristics of the first signal and the second signal, the second channel time-domain characteristics of the first signal and the third signal, the third channel time-domain characteristics of the first signal and the fourth signal, the fourth channel time-domain characteristics of the second signal and the third signal, the fifth channel time-domain characteristics of the second signal and the fourth signal, and the sixth channel time-domain characteristics of the third signal and the fourth signal, respectively; and to determine the channel characteristics based on the first channel time-domain characteristics, the second channel time-domain characteristics, the third channel time-domain characteristics, the fourth channel time-domain characteristics, the fifth channel time-domain characteristics, and the sixth channel time-domain characteristics.

[0019] In some possible implementations, the channel identification unit is used to select pairs of reference signals from the reference signals, calculate the orthogonal frequency division multiplexing (OFDM) symbol spacing for each reference signal pair; for multiple sets of reference signal pairs with the same OFDM symbol spacing, determine the time-domain characteristics of the interval of the multiple sets of reference signal pairs based on the time-domain correlation coefficient of each reference signal pair in the multiple sets of reference signal pairs; for a single set of reference signal pairs with a unique OFDM symbol spacing, use the time-domain correlation coefficient of the single set of reference signals as the time-domain characteristics of the single set of reference signals; and obtain the channel time-domain characteristic set of the channel based on the time-domain characteristics of the multiple sets of reference signal pairs and the time-domain characteristics of the single set of reference signals.

[0020] In some possible implementations, the channel identification unit is used to determine a first interval time-domain feature based on a first channel time-domain feature and a sixth channel time-domain feature when the interval between the OFDM symbols of the first signal and the second signal is equal to the interval between the OFDM symbols of the third signal and the fourth signal; to determine a second interval time-domain feature based on a second channel time-domain feature and a fifth channel time-domain feature when the interval between the OFDM symbols of the first signal and the third signal is equal to the interval between the OFDM symbols of the second signal and the fourth signal; to determine a third interval time-domain feature based on a third channel time-domain feature when the interval between the OFDM symbols of the first signal and the second signal is different from the interval between the OFDM symbols of the second signal and the third signal; to determine a fourth interval time-domain feature based on a fourth channel time-domain feature; and to determine channel features based on the first interval time-domain feature, the second interval time-domain feature, the third interval time-domain feature, and the fourth interval time-domain feature.

[0021] In some possible implementations, the data processing unit is configured to: determine a first power delay spectrum of a first signal based on a first channel estimate; determine a second power delay spectrum of a second signal based on a second channel estimate; set the coefficients of regions other than the target region in the first power delay spectrum to zero to obtain a third power delay spectrum; the target region includes at least one spectral peak region; set the coefficients of regions other than the target region in the second power delay spectrum to zero to obtain a fourth power delay spectrum; and determine a first frequency domain channel inner product based on the third and fourth power delay spectra.

[0022] In some possible implementations, the channel identification unit includes a channel type identification model, used to obtain the channel type based on channel characteristics through the channel type identification model; wherein, the channel type identification model is trained based on multiple samples; each sample in the multiple samples corresponds to a different channel type label, and each sample includes channel characteristics corresponding to multiple orthogonal frequency division multiplexing (OFDM) symbol intervals.

[0023] In some possible implementations, the channel identification unit is used to determine the channel type based on the channel characteristics and the decision tree depth threshold, using a channel type identification model, when the OFDM symbol spacing of the channel characteristics is greater than the OFDM symbol spacing threshold.

[0024] In some possible implementations, the channel identification unit is used to acquire the channel characteristics of the reference signal at multiple times; based on the channel characteristics of the reference signal at multiple times, the channel type of the channel at each of the multiple times is determined by the channel type identification model.

[0025] According to a third aspect of the present application, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method described in any one of the first aspects.

[0026] According to a fourth aspect of the embodiments of this application, a non-transitory computer-readable storage medium is provided that stores computer instructions for causing a computer to perform the method described in any one of the first aspects.

[0027] According to a fifth aspect of the embodiments of this application, a computer program product is provided, including a computer program and computer instructions for causing a computer to perform the method described in any one of the first aspects.

[0028] According to a sixth aspect of the embodiments of this application, a chip system is provided. The chip system includes a processing unit and an interface circuit. The processing unit obtains program instructions through the interface circuit. The program instructions are executed by the processing unit. The processing unit is used to execute the communication method described in the first aspect and any one thereof.

[0029] The channel type identification method provided in this application has the following beneficial effects: By measuring the reference signal, the channel characteristics of the channel corresponding to the reference signal are determined. Since the parameters such as the transmit power, modulation format, and frame structure of the reference signal are known information at the receiver, the superposition effects of non-inherent features such as noise and interference can be effectively filtered out, so that the extracted channel characteristics can accurately map the channel type. In this way, based on the channel characteristics, the channel type is determined, that is, the number of dominant paths in the transmission path whose signal power ratio is greater than a preset threshold. This not only eliminates the high-order calculation steps of spectrum estimation, greatly reducing the processor's computational load and memory usage, adapting to the application needs of low-to-medium computing power terminal devices, but also ensures the stability and reliability of the channel type identification results by avoiding interference from non-inherent features.

[0030] In addition, the channel type can be directly used as accurate prior information for core functional modules such as channel measurement and channel estimation. Subsequent modules can be configured with adaptation strategies based on the number of dominant paths. For example, a low-complexity direct path modeling algorithm can be used for single dominant path channels, and a multi-path joint estimation scheme can be enabled for multi-dominant path channels. This can significantly improve the overall transmission performance of the wireless communication system while reducing the complexity of the system algorithm.

[0031] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0032] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0033] Figure 1 A flowchart illustrating a channel type identification method provided in an embodiment of this application;

[0034] Figure 2 A flowchart illustrating a channel type identification method provided in an embodiment of this application; Figure 3 A flowchart illustrating a channel type identification method provided in an embodiment of this application; Figure 4 A flowchart illustrating a channel type identification method provided in an embodiment of this application; Figure 5 A flowchart illustrating a channel type identification method provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of the channel type identification model in a channel type identification method provided in an embodiment of this application; Figure 7 A schematic diagram of the support vector machine classification rules in a channel type identification method provided in this application embodiment; Figure 8 This is a schematic diagram of the structure of a fully connected neural network in a channel type identification method provided in an embodiment of this application; Figure 9 This is a schematic diagram of the structure of a recurrent neural network in a channel type identification method provided in an embodiment of this application; Figure 10 This is a schematic diagram of the architecture of a channel type identification device provided in an embodiment of this application; Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application; Figure 12 This is a schematic diagram of a chip system provided in an embodiment of this application. Detailed Implementation

[0035] Some embodiments of this application will be described in detail herein, examples of which are illustrated in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. Various changes, modifications, and equivalents of the methods, apparatus, and / or systems described herein will become apparent upon understanding this application. For example, the order of operations described herein is merely illustrative and is not limited to those orders set forth herein, but can be changed as will become apparent upon understanding this application, except for operations that must be performed in a specific order. Furthermore, for clarity and brevity, descriptions of features known in the art may be omitted.

[0036] The embodiments described in the following examples of this application do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0037] The wireless channel, as the carrier of signal transmission in a wireless communication system, has propagation characteristics directly determined by the propagation environment, the relative motion of the transmitting and receiving ends, and the distribution of scattering objects. It is a crucial link connecting the transmitting and receiving ends. The propagation characteristics of the channel are mainly reflected in the transmission path structure, signal power distribution, and time-varying patterns. These characteristics change dynamically with the scene, thus having a decisive impact on the signal transmission quality.

[0038] In practical wireless communication scenarios, based on the standard-defined typical channel model, channels can be classified into different types according to the propagation path structure and statistical characteristics.

[0039] For example, in non-line-of-sight (NLOS) channels, represented by time-delay line A / B / C (TDL-A / B / C) channels, signal propagation relies on multipath reflection and scattering, the path distribution is random, there is no obvious energy-dominant path, and the Doppler spread is small, and the channel impulse response exhibits diffuse characteristics.

[0040] For example, in a Line-of-Sight (LOS) channel, which corresponds to a TDL-D / E channel, there is an unobstructed main path. The signal power of the main path is much higher than that of the other scattering paths, resulting in concentrated channel energy and stable statistical characteristics.

[0041] For example, multi-direct-path channels, with single-frequency network (HST-SFN) channels as a typical example, are suitable for co-frequency network communication in high-speed mobile scenarios. Multiple LOS paths with uneven intensity superimposed exist within the channel, exhibiting significant non-Gaussian characteristics and time-varying differences.

[0042] Channel estimation and channel measurement are core modules of the physical layer in wireless communication systems. Their performance directly determines the effectiveness of subsequent functions such as signal demodulation, modulation and coding scheme (MCS) configuration, and link adaptive optimization. Channel measurement obtains fundamental physical parameters of the channel (such as path delay, signal power, and Doppler shift), providing raw data support for channel estimation. Channel estimation, through analysis and inversion of measurement data, yields core parameters such as channel impulse response and channel matrix, providing accurate link information for signal processing at both the transmitter and receiver, ultimately ensuring the transmission reliability and spectral efficiency of the communication link.

[0043] In related technologies, channel estimation and measurement often employ a unified and fixed algorithm framework and modeling strategy, meaning that the same parameter estimation model (such as least squares estimation or linear least mean square error estimation) and data processing flow are used for all types of channels. This homogenized approach cannot adapt to the differentiated characteristics of different channels. For example, using a low-rank modeling strategy for LOS channels for NLOS channels will lead to a mismatch between the estimation model and the actual channel due to ignoring multipath dispersion characteristics, significantly increasing the estimation error. Furthermore, using a multipath joint estimation algorithm for NLOS channels for LOS channels introduces redundant computational steps, significantly increasing system computational overhead and processing latency. Moreover, using a single-path or multipath uniform distribution model for multiple LOS channels in HST-SFN will fail to adapt to the superposition characteristics of multiple main paths, resulting in decreased measurement accuracy and insufficient stability of estimation results, ultimately limiting the performance of the entire communication system.

[0044] To achieve the optimization effect of "on-demand modeling and precise adaptation," accurate channel type identification can be completed before channel estimation and measurement. On the one hand, for LOS channels (TDL-D / E), a main path-first measurement and estimation strategy can be adopted based on the identification results, focusing on the extraction of direct main path parameters, simplifying multipath redundancy processing steps, and reducing system algorithm complexity while ensuring estimation accuracy. On the other hand, for NLOS channels (TDL-A / B / C), a multipath distribution adaptation model can be enabled to optimize the sampling and analysis logic of measurement data and improve the ability to capture diffuse multipaths. For HST-SFN multi-LOS channels, a multi-main-path separation and joint estimation strategy can be configured to adapt to non-Gaussian characteristics and multipath superposition patterns, ensuring the accuracy and stability of the estimation results.

[0045] Among them, the determination of channel type can be achieved based on the extraction and analysis of inherent physical quantities of the channel.

[0046] For example, based on the power delay profile (PDP), discrimination is achieved by characterizing the signal power distribution on different delay paths. The PDP of the LOS channel has a single power-dominant main path, the PDP of the NLOS channel has a uniformly diffuse power distribution, and the PDP of the HST-SFN channel is characterized by the superposition of power peaks of multiple main paths. Classification is completed by calculating quantitative indicators such as the power ratio of the main path and the delay spread. However, this method requires complex time-domain sampling, Fourier transform and other spectrum estimation operations, which has a large computational cost and a long processing delay.

[0047] For example, based on the Doppler Power Spectrum (DPS) and the time-varying characteristics of the channel, the DPS of the LOS channel is a concentrated peak shape, the DPS of the NLOS channel is a wideband U-shaped extended spectrum, and the DPS of the HST-SFN channel is a superposition of multiple spectral peaks. The spectral shape data needs to be obtained through multiple iterations of the time-domain reference signal. Similarly, there are problems of high spectral estimation complexity and poor real-time performance.

[0048] For example, channel matrix rank or structure analysis is suitable for multiple-input multiple-output (MIMO) systems. The channel matrix of LOS channels tends to be low-rank, while the channel matrix of NLOS channels tends to be full-rank and has poor stability. However, the discrimination threshold of this method is easily affected by noise interference, antenna array configuration and signal-to-noise ratio. The blurred boundary leads to insufficient discrimination accuracy and makes it difficult to adapt to complex dynamic communication scenarios.

[0049] The channel type discrimination methods in related technologies cannot simultaneously meet the dual requirements of low complexity and high discrimination accuracy, and cannot provide efficient and reliable prior support for channel estimation and measurement.

[0050] To address the above issues, this application provides a channel type identification method applicable to wireless communication signal processing scenarios including 2G, 3G, 4G, 5G New Radio (5G NR), Bluetooth, Wireless Fidelity (WiFi), and Satellite Communication Technology (SatCom). This application relies solely on conventional measurement results of the reference signal for channel type determination, eliminating the need for additional measurement and spectrum estimation processes. This enables low-complexity wireless channel type identification, reducing pilot overhead and computational complexity.

[0051] Figure 1 This is a flowchart illustrating a channel type identification method provided in an embodiment of this application. Figure 1 As shown, in some embodiments, the channel type identification method includes the following steps: S101, Measure the reference signal to determine the channel characteristics of the channel corresponding to the reference signal.

[0052] There are various forms of reference signal implementation, such as tracking reference signal (TRS), cell-specific reference signal (CRS), or demodulation reference signal (DMRS). It is understood that this application does not limit the specific implementation form of the reference signal.

[0053] In some embodiments, channel characteristics include channel time-domain characteristics and / or channel frequency-domain characteristics. In one implementation, measuring the tracking reference signal TRS can determine the channel time-domain characteristics. In another implementation, measuring the demodulation reference signal DMRS can determine the fused time-domain and frequency-domain characteristics of the channel.

[0054] There are various ways to implement the transmission of a reference signal. In some embodiments, the reference signal includes signals transmitted at different times. Signals transmitted at different times are located in different time units.

[0055] In one implementation, the reference signal includes a first signal and a second signal transmitted at different times. For example, the first signal and the second signal can be located at positions corresponding to different Orthogonal Frequency Division Multiplexing (OFDM) symbols on the same subframe. For instance, the first signal might be located at the position corresponding to OFDM symbol "4" on the first subframe, and the second signal at the position corresponding to OFDM symbol "8" on the first subframe. Alternatively, the first signal and the second signal can be located at positions corresponding to different OFDM symbols on different subframes. For instance, the first signal might be located at the position corresponding to OFDM symbol "4" on the first subframe, and the second signal at the position corresponding to OFDM symbol "8" on the second subframe. The first and second subframes can be adjacent subframes or non-adjacent subframes. For example, the first signal and the second signal can also be located at positions corresponding to the same OFDM symbol on different subframes. For instance, the first signal might be located at the position corresponding to OFDM symbol "4" on the first subframe. The second signal is located at the position corresponding to the OFDM symbol "4" on the second subframe.

[0056] In some embodiments, a subframe contains 14 OFDM symbols.

[0057] In one implementation, the reference signal includes a first signal, a second signal, a third signal, and a fourth signal transmitted at different times. The first, second, third, and fourth signals form four transmission sequences in the time domain. The modulation format, transmit power, and sequence structure of each transmission sequence are completely identical, differing only in their time-domain transmission times. For example, the first signal is located at the position corresponding to OFDM symbol "4" in the first subframe. The second signal is located at the position corresponding to OFDM symbol "8" in the first subframe. The third signal is located at the position corresponding to OFDM symbol "4" in the second subframe. The fourth signal is located at the position corresponding to OFDM symbol "8" in the second subframe. Alternatively, the first signal is located at the position corresponding to OFDM symbol "5" in the first subframe. The second signal is located at the position corresponding to OFDM symbol "9" in the first subframe. The third signal is located at the position corresponding to OFDM symbol "4" in the second subframe. The fourth signal is located at the position corresponding to OFDM symbol "8" in the second subframe.

[0058] It is understood that the foregoing merely provides several feasible implementations of the time-domain transmission location of the reference signal, illustrating that reference signals transmitted at different times can be carried in different levels of time-domain resource units, while clearly presenting the positional correlation of reference signals within the same subframe and between different subframes. In practical applications, for scenarios containing a larger number of reference signals, parameters such as the number of reference signals transmitted, the specific time-domain resource location, the subframe interval, and the OFDM symbol interval can be flexibly set based on the channel tracking accuracy requirements, system overhead control, and latency indicators of the wireless communication system. This application does not limit the specific time-domain transmission format of the reference signal.

[0059] In some embodiments, a measurement module in the field of wireless communication can measure communication parameters based on a reference signal to determine the channel characteristics of the channel corresponding to the reference signal. Since the transmission parameters (sequence structure, time domain position, transmission power, etc.) of the reference signal are known information at the receiver, the measurement module at the receiver can use coherent detection technology to filter out the influence of non-inherent features such as noise and cross-port interference, and perform channel estimation for each received sequence of reference signals to obtain the channel characteristics.

[0060] For example, taking the Tracking Reference Signal (TRS) as the reference signal in a Multiple-Input Multiple-Output (MIMO) communication scenario, the transmitter sends the same TRS sequence bound to the same transmit antenna port multiple times at different times and different OFDM symbol positions in the time domain, according to the TRS pilot pattern pre-configured in the 5G NR system. Since the transmission parameters of the TRS sequence (sequence structure, time domain position, transmit power, etc.) are known information at the receiver, the receiver measurement module can use coherent detection technology to filter out the influence of non-inherent features such as noise and cross-port interference, and perform channel estimation on each TRS received sequence to obtain the channel impulse response of the channel corresponding to the transmit antenna port at each time domain moment, thereby obtaining the time domain response characteristics of the channel at each time moment.

[0061] In some embodiments, the channel time-domain characteristics include a time-domain correlation coefficient. For example, based on the channel estimation results of the TRS sequence, the receiver measurement module calculates the time-domain correlation coefficient for the channel corresponding to the transmit antenna port. The determination of the time-domain correlation coefficient can be found in the embodiments described later.

[0062] S102, Based on channel characteristics, determine the channel type.

[0063] The channel type is related to the number of dominant paths in the channel. The dominant path is used to characterize the transmission path in the channel whose signal power ratio is greater than a preset threshold.

[0064] In some embodiments, the channel type is associated with the number of dominant paths in the channel, which can be "different numbers of dominant paths correspond to different channel types".

[0065] In some embodiments, the channel type is associated with the number of dominant paths in the channel, which may be "determining the channel type based on the number of dominant paths by determining the number of dominant paths in the channel". In some embodiments, for multiple candidate channel types that may correspond to the same number of dominant paths, the channel type is associated with the number of dominant paths in the channel. This can be achieved by "determining the number of dominant paths based on channel characteristics to complete a preliminary classification; and combining channel characteristics to determine a channel type from the results of the preliminary classification." The following is a detailed explanation.

[0066] In some embodiments, the channel type includes at least one of the following: The first non-line-of-sight (NLOS) channel. The number of dominant paths in the first NLOS channel is zero, meaning it does not include dominant paths.

[0067] Line-of-sight (LOS) channel. The number of dominant paths in a line-of-sight (LOS) channel is one.

[0068] Dynamic Point Selection (HST-DPS) channel. The number of dominant paths in a dynamic point selection channel is one.

[0069] The second non-line-of-sight (NLOS) channel. The number of dominant paths in the second NLOS channel is one. For example, the second NLOS channel can be an NLOS channel with a deployed Reconfigurable Intelligence Surface (RIS), where the path formed by reflections from the RIS is typically the dominant path.

[0070] Single-frequency network channel. A single-frequency network channel includes at least two dominant paths. For example, a single-frequency network channel can be a High Speed ​​Train - Single Frequency Network (HST-SFN) channel.

[0071] In some embodiments, the channel type is determined based on the time-domain correlation coefficient.

[0072] For example, the theoretical basis for determining channel type based on time-domain correlation coefficient includes at least one of the following: In the case of a conventional NLOS channel without a dominant path, the time-domain correlation coefficient exhibits the characteristics of a zero-order Bessel function (or a decaying sinc function), with a relatively small imaginary part and a large amplitude attenuation.

[0073] When the channel contains a single dominant path, the time-domain correlation coefficient exhibits a single-frequency rotation characteristic, with a relatively large imaginary part and a small amplitude attenuation.

[0074] When the channel contains two or more dominant paths, the time-domain correlation coefficient represents the superposition of a corresponding number of single-frequency rotating signals.

[0075] By executing steps S101 to S102, the reference signal is measured to determine the channel characteristics of the channel corresponding to the reference signal. Since the parameters of the reference signal, such as transmit power, modulation format, and frame structure, are known information at the receiver, the superposition effects of non-inherent features such as noise and interference can be effectively filtered out. The extracted channel characteristics can accurately map the channel type. Thus, based on the channel characteristics, the channel type is determined—that is, the number of dominant paths in the transmission path whose signal power ratio is greater than a preset threshold. This eliminates the need for high-order calculations in spectral estimation, significantly reducing the processor's computational load and memory usage, adapting to the application needs of low-to-medium computing power terminal devices. Furthermore, by avoiding interference from non-inherent features, the stability and reliability of the channel type determination results are ensured. Ultimately, this provides high-quality prior information support for subsequent core modules such as channel estimation, achieving overall system performance optimization and improvement.

[0076] like Figure 2 As shown, in some embodiments, the reference signal includes a first signal and a second signal transmitted at different times. When performing step S101, the reference signal is measured to determine the channel characteristics of the channel corresponding to the reference signal, including the following steps: S201, Determine the first channel estimate based on the first signal.

[0077] The first signal, also known as the first reference signal (such as TRS, DMRS, etc., transmitted from the same transmit antenna port at a specific time-domain location), is used in some embodiments to estimate the channel response of the first signal on each frequency-domain resource particle (RE) using a coherent detection algorithm, thus obtaining a first channel estimate. (i iterates through all frequency domains RE occupied by the reference signal).

[0078] S202, Determine the second channel estimate based on the second signal.

[0079] The second signal, also known as the second reference signal (such as TRS, DMRS, etc., transmitted from the same transmit antenna port at a specific time-domain location), is used in some embodiments to estimate the channel response of the second signal on each frequency-domain resource particle (RE) using a coherent detection algorithm, thus obtaining a second channel estimate. (i iterates through all frequency domains RE occupied by the reference signal).

[0080] S203, determine the first frequency domain channel inner product based on the first channel estimate and the second channel estimate.

[0081] In some embodiments, the formula for calculating the first frequency domain channel inner product includes: ; in, Represented as the resource element (RE) index of the reference signal in the frequency domain; This is represented as the first channel estimate of the first signal in the i-th frequency domain RE; This is expressed as the second channel estimate of the second signal in the i-th frequency domain RE; Represented as The conjugate of complex numbers.

[0082] S204, Based on the first channel estimate and the second channel estimate, determine the first channel power normalization result of the first signal and the second signal.

[0083] In some embodiments, the formula for calculating the normalized result of the first channel power includes: ; in, The channel power of the first signal is expressed as the sum of its values. The channel power of the second signal is expressed as the sum of its values. Represented as the resource element (RE) index of the reference signal in the frequency domain; This is represented as the first channel estimate of the first signal in the i-th frequency domain RE; This is expressed as the second channel estimate of the second signal in the i-th frequency domain RE; Represented as The conjugate of complex numbers.

[0084] S205, determine the time-domain correlation coefficient based on the first frequency domain channel inner product and the first channel power normalization result.

[0085] In some embodiments, the formula for calculating the time-domain correlation coefficient includes: ; in, Represented as the time-domain correlation coefficient; Represented as the resource element (RE) index of the reference signal in the frequency domain; This is represented as the first channel estimate of the first signal in the i-th frequency domain RE; This is expressed as the second channel estimate of the second signal in the i-th frequency domain RE; Represented as The conjugate of complex numbers.

[0086] Since the channel is a complex value, the correlation operation uses conjugate processing to ensure the result is a real number, reflecting the phase matching degree of the two channels. The channel estimates on all frequency domain REs are multiplied by their conjugates and then summed to reflect the linear correlation between the two channels in the frequency domain. The sum of the squared magnitudes of the channel estimates on each frequency domain RE represents the total energy of the channel in the frequency domain. The square roots of the channel power sums of the two signals are multiplied to eliminate the influence of the absolute value of the channel power on the correlation coefficient, ensuring that the correlation coefficient only reflects the time-varying characteristics of the channel. The closer p is to 1, the smaller the time-domain variation of the channels corresponding to the two reference signals (e.g., LOS channels, where the propagation path is stable). The closer p is to 0, the more drastic the time-domain variation of the channel (e.g., NLOS channels, where multipath scattering leads to strong time-varying characteristics). Thus, the time-domain correlation coefficient is obtained, serving as a time-domain characteristic of the channel.

[0087] like Figure 3 As shown, in some embodiments, the first signal and the second signal are configured on the first subframe, and the reference signal further includes a third signal and a fourth signal configured on the second subframe. The first subframe and the second subframe are non-overlapping time-domain resources. Measurements are performed on the reference signal to determine the channel characteristics of the channel corresponding to the reference signal, including: S301, determine the first channel time-domain characteristics of the first signal and the second signal, the second channel time-domain characteristics of the first signal and the third signal, the third channel time-domain characteristics of the first signal and the fourth signal, the fourth channel time-domain characteristics of the second signal and the third signal, the fifth channel time-domain characteristics of the second signal and the fourth signal, and the sixth channel time-domain characteristics of the third signal and the fourth signal, respectively.

[0088] In some embodiments, the channel time-domain characteristics (which may be time-domain correlation coefficients) of every two columns of reference signals are calculated and indexed as the OFDM symbol spacing pd of these two columns, where d represents the OFDM symbol spacing of these two columns.

[0089] For example, the following example illustrates the situation: "The first signal is located in the 4th OFDM symbol of the first subframe, the second signal is located in the 8th OFDM symbol of the first subframe, the third signal is located in the 4th OFDM symbol of the second subframe, and the fourth signal is located in the 8th OFDM symbol of the second subframe."

[0090] The time-domain characteristics of the first channel are calculated based on the first and second signals, corresponding to an OFDM symbol interval d=4. For example, the receiver extracts the frequency-domain channel estimates of the two signals. (First signal) and (Second signal) Calculate the frequency domain channel inner product and normalize the power to obtain the normalized time domain correlation coefficient p4 as the first channel time domain feature.

[0091] The second channel time-domain characteristics are calculated based on the first and third signals, corresponding to an OFDM symbol interval d=14. For example, the frequency-domain channel estimates of the two signals are extracted. (First signal) and (Third signal), the normalized time-domain correlation coefficient p14 is calculated as the time-domain feature of the second channel.

[0092] The third channel time-domain characteristics are calculated based on the first and fourth signals, corresponding to an OFDM symbol interval d=18. For example, the frequency-domain channel estimates of the two signals are extracted. (First signal) and (Fourth signal) The normalized time-domain correlation coefficient p18 is calculated and used as the time-domain feature of the third channel.

[0093] The fourth channel time-domain characteristics are calculated based on the second and third signals, corresponding to an OFDM symbol interval d=10. For example, the frequency-domain channel estimates of the two signals are extracted. (Second signal) and (Third signal) The normalized time-domain correlation coefficient p10 is calculated and used as the time-domain feature of the fourth channel.

[0094] The time-domain characteristics of the fifth channel are calculated based on the second and fourth signals, corresponding to an OFDM symbol interval d=14. For example, the frequency-domain channel estimates of the two signals are extracted. (Second signal) and (Fourth signal) The normalized time-domain correlation coefficient p14 is calculated and used as the time-domain feature of the fifth channel.

[0095] The time-domain characteristics of the sixth channel are calculated based on the third and fourth signals, corresponding to an OFDM symbol interval d=4. For example, the frequency-domain channel estimates of the two signals are extracted. (Third signal) and (Fourth signal) The normalized time-domain correlation coefficient p4 is calculated and used as the time-domain feature of the sixth channel.

[0096] It is understood that this is merely an illustrative example of using four reference signals to calculate the channel time-domain characteristics and determine the channel features through pairwise signal pair analysis of all reference signals. No restrictions are placed on the specific number of reference signals, the combination logic of the signal pairs, or the specific algorithm for feature fusion. Any technical implementation based on pairwise correlation analysis of multiple reference signals to extract channel time-domain features falls within the scope of protection of this application.

[0097] S302, determine the channel characteristics based on the time-domain characteristics of the first channel, the time-domain characteristics of the second channel, the time-domain characteristics of the third channel, the time-domain characteristics of the fourth channel, the time-domain characteristics of the fifth channel, and the time-domain characteristics of the sixth channel.

[0098] like Figure 4 As shown, in some embodiments, when performing step S302, determining the channel type includes the following steps: S401: Select two pairs of reference signals from the reference signals and calculate the orthogonal frequency division multiplexing (OFDM) symbol spacing for each pair of reference signals.

[0099] For example, the OFDM symbol interval d = 4 is calculated between the first and second signals. The OFDM symbol interval d = 14 is calculated between the first and third signals. The OFDM symbol interval d = 18 is calculated between the first and fourth signals. The OFDM symbol interval d = 10 is calculated between the second and third signals. The OFDM symbol interval d = 14 is calculated between the second and fourth signals. The OFDM symbol interval d = 4 is calculated between the third and fourth signals.

[0100] S402, for multiple sets of reference signal pairs with the same OFDM symbol spacing, determine the time-domain characteristics of the interval of the multiple sets of reference signal pairs based on the time-domain correlation coefficient of each reference signal pair in the multiple sets of reference signal pairs.

[0101] For example, when the interval between the OFDM symbols of the first signal and the second signal is equal to the interval between the OFDM symbols of the third signal and the fourth signal, the first interval time-domain characteristics are determined based on the time-domain characteristics of the first channel and the time-domain characteristics of the sixth channel. When the interval between the OFDM symbols of the first signal and the third signal is equal to the interval between the OFDM symbols of the second signal and the fourth signal, the second interval time-domain characteristics are determined based on the time-domain characteristics of the second channel and the time-domain characteristics of the fifth channel.

[0102] For example, p4 is the mean of the time-domain correlation coefficients of the channel responses corresponding to the TRS sequences of OFDM symbols "4" and "8" in the first subframe, and the time-domain correlation coefficients of the channel responses corresponding to the TRS sequences of OFDM symbols "4" and "8" in the second subframe. P14 is the mean of the correlation coefficients of the channel responses corresponding to the TRS sequences of OFDM symbols "4" and "4" in the first and second subframes, and the time-domain correlation coefficients of the channel responses corresponding to the TRS sequences of OFDM symbols "8" in the first and second subframes.

[0103] S403, for a single set of reference signals with a unique OFDM symbol interval, the time-domain correlation coefficient of the single set of reference signals is used as the time-domain feature of the interval of the single set of reference signals.

[0104] For example, when the interval between the OFDM symbols of the first signal and the OFDM symbols of the second signal is different from the interval between the OFDM symbols of the second signal and the OFDM symbols of the third signal, a third interval time-domain feature is determined based on the time-domain features of the third channel. And, a fourth interval time-domain feature is determined based on the time-domain features of the fourth channel.

[0105] For example, P18 is the time-domain correlation coefficient of the channel response corresponding to the TRS sequence of the first subframe OFDM symbol "4" and the second subframe OFDM symbol "8". P10 is the time-domain correlation coefficient of the channel response corresponding to the TRS sequence of the first subframe OFDM symbol "8" and the second subframe OFDM symbol "4".

[0106] S404. Based on the time-domain characteristics of multiple sets of reference signal pairs and the time-domain characteristics of a single set of reference signals, the channel time-domain characteristic set is obtained.

[0107] In some embodiments, the method of extracting channel temporal correlation by using multiple time-domain TRS sequences from the same transmit antenna port eliminates the need for complex spectral estimation calculations. Feature extraction can be achieved solely based on the known nature of the reference signal and coherent detection, offering advantages of both low complexity and high accuracy. Furthermore, it adapts to the characteristics of multi-port independent channels in MIMO scenarios, allowing for the extraction of temporal correlation features for the channels corresponding to each transmit antenna port, thus supporting subsequent multi-channel collaborative discrimination and system performance optimization.

[0108] like Figure 5 As shown, in some embodiments, when performing step S203, determining the first frequency domain channel inner product based on the first channel estimate and the second channel estimate includes the following steps: S501, determine the first power delay spectrum of the first signal based on the first channel estimate.

[0109] In some embodiments, the corresponding power delay profile (PDP) is obtained by discrete Fourier transform (DFT).

[0110] S502, determine the second power delay spectrum of the second signal based on the second channel estimate.

[0111] See step S501, which will not be repeated here.

[0112] S503, set the coefficients of the regions other than the target region in the first power delay spectrum to zero to obtain the third power delay spectrum.

[0113] The target region includes at least one spectral peak region.

[0114] For example, for each PDP spectrum, one or more peak regions on the PDP spectrum are selected, and the PDP spectral coefficients other than the aforementioned peak regions are set to zero.

[0115] S504, set the coefficients of the regions other than the target region in the second power delay spectrum to zero to obtain the fourth power delay spectrum.

[0116] See step S503, which will not be repeated here.

[0117] S505, determine the first frequency domain channel inner product based on the third power delay spectrum and the fourth power delay spectrum.

[0118] The cross product of the two PDP spectra is summed to determine the first frequency domain channel inner product. The power of the PDP spectra is then normalized to obtain the normalized time-domain correlation coefficient.

[0119] In some embodiments, when performing step S102, determining the channel type based on channel characteristics includes: obtaining the channel type of the channel by means of a channel type identification model based on the channel characteristics.

[0120] The channel type identification model is trained based on multiple samples. Each sample corresponds to a different channel type label, and each sample includes channel features corresponding to multiple Orthogonal Frequency Division Multiplexing (OFDM) symbol intervals.

[0121] There are various ways to implement a channel type identification model. For example, it can be a supervised learning model (such as a decision tree model or a supervised learning model based on statistical learning theory), or a machine learning neural network model (Feedforward Neural Network (FFNN) and Recurrent Neural Network (RNN)).

[0122] The following sections will provide detailed explanations of each point.

[0123] like Figure 6 As shown, in some embodiments, the decision tree (DT) model is a tree-like structure model that includes a root node, internal nodes, and leaf nodes.

[0124] The root node represents the entire dataset.

[0125] Internal nodes represent a judgment condition on a feature attribute.

[0126] Leaf nodes correspond to a final prediction output, which serves as a label for the channel type in channel type determination.

[0127] Dataset partitioning criteria include information gain (e.g., ID3 algorithm), information gain ratio (e.g., C4.5 algorithm), and Gini index (e.g., CART algorithm). Decision trees are prone to overfitting, i.e., overfitting the training data, resulting in reduced generalization ability. In some embodiments, manually constraining the maximum depth of the decision tree and pruning branches can reduce the negative impact of overfitting.

[0128] After partitioning the dataset, construct the training dataset for the decision tree model. For each sample, the channel time-domain correlation coefficient can be specified. .in, ,for There are several calculable OFDM intervals. The real and imaginary parts of the channel time-domain correlation coefficient are split and used together as the input to the decision tree; that is, the actual input to the decision tree is... Based on prior knowledge of different channel models, time-domain correlation coefficients can be filtered to retain the coefficients most capable of distinguishing channel types, thereby reducing the complexity of the decision tree model and effectively avoiding overfitting. For example, time-domain correlation coefficients with larger OFDM intervals can be preferred as input. For each sample, a channel type label is given. For example, a regular NLOS channel is category 0, a channel containing one dominant path is category 1, and a channel containing multiple dominant paths is category 2.

[0129] In some embodiments, the preset maximum depth of the decision tree is A decision tree is constructed based on the training dataset mentioned above.

[0130] Channel type determination is performed based on the decision tree described above. Starting from the root node, a judgment is made based on the selected judgment variables and thresholds at each node, and the corresponding child node is then entered. This process is repeated until a leaf node (without child nodes) is reached, at which point the channel type corresponding to that leaf node is selected as the channel type for that sample.

[0131] In some embodiments, obtaining the channel type of a channel includes: when the OFDM symbol spacing of the channel characteristics is greater than the OFDM symbol spacing threshold, determining the channel type of the channel based on the channel characteristics and the decision tree depth threshold using a channel type identification model.

[0132] For example, for medium-to-high Doppler scenarios, a decision tree based on NR TRS is used to determine whether the channel type contains the dominant path.

[0133] Example 1: The maximum depth of the decision tree is limited to The input is: ; in, Represented as the real part; It is represented as the imaginary part.

[0134] Judgment conditions may be ,and ,and If the condition is met, it is determined that the dominant path is included. Otherwise, it is not considered to contain a dominant path.

[0135] Example 2: The maximum depth of the decision tree is limited to The input is: ; The conditions for judgment may be: ,and If the condition is met, it is determined that the dominant path is included. Otherwise, it is not considered to contain a dominant path.

[0136] As can be seen, the complexity of decision trees can be altered by limiting the maximum depth and adding / removing input features.

[0137] like Figure 7 As shown, in some embodiments, the Support Vector Machine (SVM) can be used for binary classification problems, and can also be extended to multi-class classification tasks by increasing the number of SVMs.

[0138] In separable scenarios, the goal of SVM is to find a hyperplane that maximizes the margin between positive and negative samples. In feature space, a hyperplane can be represented as: ; in, It is the normal vector. For bias, The input vector.

[0139] In some embodiments, the classification rules for SVMs can be expressed as: ; In some embodiments, optimal The solution is based on convex optimization and Lagrange duality.

[0140] In some embodiments, for nonlinearly separable problems, SVM can implicitly map data to a high-dimensional space using kernel functions. For example, a nonlinear Gaussian kernel is represented as: ; in, This represents support vectors.

[0141] In some embodiments, SVM can be extended to multi-class problems. For example, a classifier can be trained for each pair of classes. Alternatively, a classifier can be trained for each class and the other classes.

[0142] For details on constructing the training dataset for SVM, please refer to the section on constructing the training dataset for decision tree models; these details will not be elaborated upon here.

[0143] In some embodiments, the SVM kernel function type is preset (e.g., a regular linear kernel or a Gaussian kernel). If the number of channel types is greater than two, multiple SVM classifiers are constructed. The SVM classifiers are trained based on the training dataset described above.

[0144] In some embodiments, channel type determination is performed based on the SVM described above. If the number of channel types is greater than two, multiple SVM classifiers are used simultaneously for determination. If a classifier is trained for each pair of categories, a majority vote is used to select the category with the most votes as the output category; if a classifier is trained for each category and the other categories, the category with the largest output value (i.e., the highest confidence) is selected as the output category.

[0145] In one example, for medium-to-high Doppler scenarios, SVM is used based on NR TRS to determine the channel type and whether it contains the dominant path. The input is... Using a linear kernel, an SVM implementation was obtained. ; It is determined to contain the dominant path. It is determined that it does not contain the dominant path.

[0146] The following section will provide a detailed explanation using feedforward neural networks (FFNN) and recurrent neural networks (RNN) as examples.

[0147] like Figure 8 As shown, a feedforward neural network is a type of neural network with an acyclic graph structure. Information is passed from the input layer to the output layer along a unidirectional path in the network, without any feedback connections. Feedforward neural networks include, but are not limited to, fully-connected neural networks (FCNN) and convolutional neural networks (CNN).

[0148] In some embodiments, taking FCNN as an example, the linear transformation plus activation function performed on each neuron in the first layer can be expressed as: ; in, Indicates the first The weight matrix of the layer, This represents the bias vector of the first layer. This represents a non-linear activation function (e.g., ReLU, Sigmoid, Tanh). For input data.

[0149] The aforementioned weights and bias parameters can be updated using the gradient backpropagation algorithm to minimize the loss function (such as cross-entropy, MSE).

[0150] like Figure 9 As shown, RNN is a neural network used to model sequential data. The output at the current time step depends not only on the current input but also on the hidden state at the previous time step.

[0151] For example, for the input sequence RNN at every moment The status update is as follows: ; ; in, This indicates a hidden state, used to remember the historical information of the sequence. This is the weight matrix. For bias vectors, It is a non-linear activation function. For input, This is the output.

[0152] As can be seen, RNNs have a "chain" structure in the time dimension, with states continuously propagating in the sequence to achieve temporal memory of information.

[0153] The method for constructing the training datasets for FFNN and RNN is consistent with the decision tree process and will not be elaborated upon. In some embodiments, the RNN records the temporal correlation coefficient sequence at each time step. .in, The time index represents the time interval. Since the reference signal is periodically subjected to time-domain correlation measurements, the time index represents each time-domain correlation measurement based on the reference signal. The sequence data containing the time index and the corresponding channel type label sequence serve as the training dataset for the RNN.

[0154] Determine the neural network structure (e.g., type, number of layers, width, non-linear activation function, loss function, optimizer, etc.), and optimize the neural network parameters based on the training dataset mentioned above.

[0155] Channel type determination is performed based on the trained neural network described above.

[0156] In some embodiments, the input to the FFNN is the time-domain correlation coefficient of a single reference signal measurement. Output the corresponding channel type determination.

[0157] In some embodiments, obtaining the channel type includes: acquiring channel characteristics of the reference signal at multiple time points. Based on the channel characteristics of the reference signal at multiple time points, the channel type of the channel at each of the multiple time points is determined using a channel type identification model. For example, the input to the RNN is a sequence of time-domain correlation coefficients from multiple past measurements of the reference signal. Supports output Channel type determination at multiple time points.

[0158] In this way, by using machine learning methods to accurately model the differences between different channel types in a data-driven manner, the performance of channel type judgment is improved, which has the advantage of high precision and high accuracy.

[0159] This application also provides a channel type identification device for performing the above-described channel type identification method.

[0160] Figure 10 This is a schematic diagram of the architecture of a channel type identification device provided in an embodiment of this application. Figure 10 As shown, in some embodiments, the channel type identification device includes a data processing unit 701 and a channel identification unit 702.

[0161] The data processing unit 701 is used to measure the reference signal in order to determine the channel characteristics of the channel corresponding to the reference signal.

[0162] The channel identification unit 702 is used to determine the channel type based on channel characteristics. The channel type is related to the number of dominant paths in the channel. The dominant path is used to characterize transmission paths in the channel whose signal power percentage is greater than a preset threshold.

[0163] In some embodiments, the data processing unit 701 is configured to: determine a first channel estimate based on a first signal; determine a second channel estimate based on a second signal; determine a first frequency domain channel inner product based on the first channel estimate and the second channel estimate; determine a first channel power normalization result for the first signal and the second signal based on the first channel estimate and the second channel estimate; and determine a time domain correlation coefficient based on the first frequency domain channel inner product and the first channel power normalization result.

[0164] In some embodiments, the data processing unit 701 is configured to determine, respectively, a first channel time-domain feature of the first signal and the second signal, a second channel time-domain feature of the first signal and the third signal, a third channel time-domain feature of the first signal and the fourth signal, a fourth channel time-domain feature of the second signal and the third signal, a fifth channel time-domain feature of the second signal and the fourth signal, and a sixth channel time-domain feature of the third signal and the fourth signal. Channel features are determined based on the first channel time-domain feature, the second channel time-domain feature, the third channel time-domain feature, the fourth channel time-domain feature, the fifth channel time-domain feature, and the sixth channel time-domain feature.

[0165] In some embodiments, the channel identification unit 702 is used to select all pairwise reference signal pairs from the reference signals and calculate the Orthogonal Frequency Division Multiplexing (OFDM) symbol spacing for each reference signal pair. For multiple sets of reference signal pairs with the same OFDM symbol spacing, the time-domain characteristics of the spacing of the multiple sets of reference signal pairs are determined based on the time-domain correlation coefficients of each reference signal pair in the multiple sets of reference signal pairs. For a single set of reference signal pairs with a unique OFDM symbol spacing, the time-domain correlation coefficient of the single set of reference signals is used as the time-domain characteristic of the single set of reference signals. Based on the time-domain characteristics of the multiple sets of reference signal pairs and the time-domain characteristics of the single set of reference signals, the set of channel time-domain characteristics is obtained.

[0166] In some embodiments, the channel identification unit 702 is configured to determine a first interval time-domain feature based on a first channel time-domain feature and a sixth channel time-domain feature when the interval between the OFDM symbols of the first signal and the second signal is equal to the interval between the OFDM symbols of the third signal and the fourth signal. When the interval between the OFDM symbols of the first signal and the third signal is equal to the interval between the OFDM symbols of the second signal and the fourth signal, the channel identification unit 702 determines a second interval time-domain feature based on a second channel time-domain feature and a fifth channel time-domain feature. When the interval between the OFDM symbols of the first signal and the second signal is different from the interval between the OFDM symbols of the second signal and the third signal, the channel identification unit 702 determines a third interval time-domain feature based on a third channel time-domain feature. The channel identification unit 702 also determines a fourth interval time-domain feature based on a fourth channel time-domain feature. Finally, the channel features are determined based on the first, second, third, and fourth interval time-domain features.

[0167] In some embodiments, the data processing unit 701 is configured to determine a first power delay spectrum of a first signal based on a first channel estimate. Based on a second channel estimate, it determines a second power delay spectrum of a second signal. The coefficients of regions other than the target region in the first power delay spectrum are set to zero to obtain a third power delay spectrum. The target region includes at least one spectral peak region. The coefficients of regions other than the target region in the second power delay spectrum are set to zero to obtain a fourth power delay spectrum. A first frequency domain channel inner product is determined based on the third and fourth power delay spectra.

[0168] In some embodiments, the channel identification unit 702 includes a channel type identification model, used to obtain the channel type based on channel characteristics. The channel type identification model is trained based on multiple samples. Each sample corresponds to a different channel type label, and each sample includes channel characteristics corresponding to multiple Orthogonal Frequency Division Multiplexing (OFDM) symbol intervals.

[0169] In some embodiments, the channel identification unit 702 is used to determine the channel type based on the channel characteristics and the decision tree depth threshold by means of a channel type identification model when the OFDM symbol spacing of the channel characteristics is greater than the OFDM symbol spacing threshold.

[0170] In some embodiments, the channel identification unit 702 is used to acquire the channel characteristics of the reference signal at multiple time points. Based on the channel characteristics of the reference signal at multiple time points, the channel type of the channel at each of the multiple time points is determined by a channel type identification model.

[0171] This embodiment also provides an electronic device for performing the above-described channel type identification method. Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 11 As shown, the electronic device 800 includes at least one processor 820; and a memory 804 communicatively connected to the at least one processor 820; wherein the memory 804 stores instructions executable by the at least one processor 820, which, when executed by the at least one processor 820, enable the at least one processor to perform a channel type identification method.

[0172] Electronic device 800 can be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0173] 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.

[0174] 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 methods 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.

[0175] Memory 804 is configured to store various types of data to support the operation of electronic device 800. Examples of such 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.

[0176] 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.

[0177] Multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen 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 the touch or swipe action 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 the electronic device 800 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the 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.

[0178] 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.

[0179] 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.

[0180] 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 a light sensor, such as a CMOS or 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.

[0181] 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, 3G, 4G, 5G, other communication standards, or combinations thereof. In some embodiments of this application, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In some embodiments of this application, communication component 816 further includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0182] In some embodiments of this application, 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 methods described above.

[0183] In some embodiments of this application, a non-transitory computer-readable storage medium storing computer instructions is also provided, such as a memory 804 including instructions that can be executed by a processor 820 of an electronic device 800 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0184] In some embodiments of this application, a computer program product is also provided, including a computer program and computer instructions for causing a computer to perform the method described in any one of the first aspects.

[0185] Some embodiments of this application also provide a chip system, such as Figure 12 As shown, the chip system includes at least one processor 601 and at least one interface circuit 602. The processor 601 and the interface circuit 602 are interconnected via a line. For example, the interface circuit 602 can be used to receive signals from other devices (e.g., the memory of an electronic device). As another example, the interface circuit 602 can be used to send signals to other devices (e.g., the processor 601). Exemplarily, the interface circuit 602 can read instructions stored in memory and send those instructions to the processor 601. When the instructions are executed by the processor 601, the communication device can perform the steps in the above embodiments. Of course, the chip system may also include other discrete components, and some embodiments of this application do not specifically limit this.

[0186] In some embodiments of this application, the interface circuit 602 can obtain data, program instructions and / or information from the internal storage area of ​​the chip system; it can also obtain data, program instructions and / or information from outside the chip system.

[0187] Optionally, the chip system may also include memory for storing necessary computer programs and data.

[0188] Those skilled in the art will also understand that the various illustrative logical blocks and steps listed in the embodiments of this application can be implemented by electronic hardware, computer software, or a combination of both. Whether such functionality is implemented through hardware or software depends on the specific application and the overall system design requirements. Those skilled in the art can implement the described functionality using various methods for each specific application.

[0189] In the above detailed description, reference has been made to the accompanying drawings, which illustrate specific aspects of how this application can be practiced. In this regard, terms indicating direction or positional relationship, such as “center,” “longitudinal,” “lateral,” “length,” “width,” “thickness,” “upper,” “lower,” “front,” “rear,” “left,” “right,” “vertical,” “horizontal,” “top,” “bottom,” “inner,” “outer,” “clockwise,” “counterclockwise,” “axial,” “radial,” and “circumferential,” can be used with reference to the orientation of the described figures. Since components of the described device can be positioned in multiple different orientations, directional terms are used for illustrative purposes and are not restrictive. It should be understood that other aspects can be utilized and structural or logical changes can be made without departing from the concept of this application. Therefore, the following detailed description should not be considered limiting.

[0190] It should be understood that, unless otherwise specifically indicated, features of various embodiments of this application described herein can be combined with each other. As used herein, the term “and / or” includes any one of the relevant listed items and any combination of any two or more; similarly, “at least one of…” includes any one of the relevant listed items and any combination of any two or more.

[0191] It should be understood that, unless otherwise expressly specified and limited, the terms "joining," "attaching," "installing," "connecting," "linking," and "fixing," as used in the embodiments of this application, should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between them; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms herein based on the specific circumstances.

[0192] Furthermore, the term "above" as used herein with respect to components, elements, or material layers formed or located "above" a surface may be used to indicate that the component, element, or material layer is "indirectly" positioned (e.g., placed, formed, deposited, etc.) on the surface such that one or more additional components, elements, or layers are arranged between the surface and the component, element, or material layer. However, the term "above" as used with respect to components, elements, or material layers formed or located "above" a surface may also optionally have a specific meaning: that the component, element, or material layer is "directly" positioned (e.g., placed, formed, deposited, etc.) on the surface, for example, in direct contact with the surface.

[0193] Although terms such as “first,” “second,” and “third” may be used herein to describe various components, parts, regions, layers, or sections, these components, parts, regions, layers, or sections are not limited to these terms. Rather, these terms are used only to distinguish one component, part, region, layer, or section from another. Therefore, without departing from the teachings of the examples described herein, the first component, part, region, layer, or section mentioned in the examples may also be referred to as the second component, part, region, layer, or section. 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 indicated technical features. Thus, a feature defined as “first” or “second” may explicitly or implicitly include at least one of that feature. In the description herein, “a plurality” means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0194] It should be understood that spatial relative terms, such as “above,” “upper,” “below,” and “lower,” are used herein to describe the relationship between one element and another shown in the figures. In addition to the orientation depicted in the figures, these spatial relative terms are also intended to encompass different orientations of the device in use or operation. For example, if the device in the figures is flipped, an element described as “above” or “upper” relative to another element would be “below” or “lower” relative to that other element. Thus, depending on the spatial orientation of the device, the term “above” encompasses both above and below orientations. Devices may have other orientations (e.g., rotated 90 degrees or in other orientations), and the spatial relative terms used herein should be interpreted accordingly.

[0195] Furthermore, the term “exemplary” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as advantageous compared to other aspects or designs. Rather, the use of the term “exemplary” is intended to present the concept in a concrete manner. As used herein, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from the context, “X applies A or B” is intended to mean any of the natural inclusive arrangements. That is, “X applies A or B” satisfies any of the foregoing instances if X applies A; X applies B; or both X applies A and B. Additionally, unless otherwise specified or clear from the context to refer to the singular form, the articles “a” and “an” as used in this application and the appended claims are generally understood to mean “one or more.”

[0196] Similarly, although this application has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding the specification and drawings. This application includes all such modifications and variations and is limited only by the scope of the claims. In particular, with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terminology used to describe such components is intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if structurally not equivalent to the disclosed structure. Furthermore, although a particular feature of this application may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations, as may be desired and advantageous to any given or particular application. Moreover, with regard to the terms “comprising,” “owning,” “having,” “having,” or variations thereof as used in the Detailed Description or the claims, such terms are intended to be inclusive in a manner similar to the term “including.”

[0197] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0198] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A channel type identification method, characterized in that, include: The reference signal is measured to determine the channel characteristics of the channel corresponding to the reference signal; Based on the channel characteristics, the channel type is determined; the channel type is associated with the number of dominant paths in the channel; the dominant path is used to characterize the transmission path in the channel whose signal power ratio is greater than a preset threshold.

2. The channel type identification method according to claim 1, characterized in that, The channel type includes at least one of the following: The first non-line-of-sight NLOS channel; the number of dominant paths in the first non-line-of-sight NLOS channel is zero; Line-of-sight (LOS) channel; the number of dominant paths in the line-of-sight (LOS) channel is one; Dynamic point selection of channels; The number of dominant paths in the dynamic point selection channel is one; The second non-line-of-sight NLOS channel; the number of dominant paths in the second non-line-of-sight NLOS channel is one; A single-frequency network channel; the single-frequency network channel includes at least two dominant paths.

3. The channel type identification method according to claim 1, characterized in that, The channel characteristics include channel time-domain characteristics and / or channel frequency-domain characteristics.

4. The channel type identification method according to claim 3, characterized in that, The channel time-domain characteristics include a time-domain correlation coefficient; the reference signal includes a first signal and a second signal transmitted at different times, and the measurement of the reference signal to determine the channel characteristics of the channel corresponding to the reference signal includes: Based on the first signal, determine the first channel estimate; Based on the second signal, determine the second channel estimate; Based on the first channel estimate and the second channel estimate, determine the first frequency domain channel inner product; Based on the first channel estimate and the second channel estimate, determine the first channel power normalization result of the first signal and the second signal; The time-domain correlation coefficient is determined based on the first frequency-domain channel inner product and the first channel power normalization result.

5. The channel type identification method according to claim 4, characterized in that, The first signal and the second signal are configured on the first subframe; the reference signal further includes a third signal and a fourth signal configured on the second subframe, and the first subframe and the second subframe are non-overlapping temporal resources; The measurement of the reference signal to determine the channel characteristics of the channel corresponding to the reference signal includes: The first channel time-domain characteristics of the first signal and the second signal, the second channel time-domain characteristics of the first signal and the third signal, the third channel time-domain characteristics of the first signal and the fourth signal, the fourth channel time-domain characteristics of the second signal and the third signal, the fifth channel time-domain characteristics of the second signal and the fourth signal, and the sixth channel time-domain characteristics of the third signal and the fourth signal are determined respectively. The channel features are determined based on the first channel time-domain features, the second channel time-domain features, the third channel time-domain features, the fourth channel time-domain features, the fifth channel time-domain features, and the sixth channel time-domain features.

6. The channel type identification method according to claim 5, characterized in that, The channel time-domain characteristics include a time-domain correlation coefficient; determining the channel type includes: Select two pairs of reference signals from the reference signals and calculate the orthogonal frequency division multiplexing (OFDM) symbol spacing for each pair of reference signals. For multiple sets of reference signal pairs with the same OFDM symbol spacing, the time-domain characteristics of the interval of the multiple sets of reference signal pairs are determined based on the time-domain correlation coefficient of each reference signal pair in the multiple sets of reference signal pairs. For a single set of reference signals with a unique OFDM symbol interval, the time-domain correlation coefficient of the single set of reference signals is used as the time-domain feature of the interval of the single set of reference signals. Based on the time-domain characteristics of the multiple sets of reference signal pairs and the time-domain characteristics of the single set of reference signals, the channel time-domain characteristic set of the channel is obtained.

7. The channel type identification method according to claim 4, characterized in that, Determining the first frequency domain channel inner product based on the first channel estimate and the second channel estimate includes: Based on the first channel estimate, determine the first power delay spectrum of the first signal; Based on the second channel estimate, determine the second power delay spectrum of the second signal; The coefficients of the regions other than the target region in the first power delay spectrum are set to zero to obtain the third power delay spectrum; the target region includes at least one spectral peak region. The coefficients of the regions other than the target region in the second power delay spectrum are set to zero to obtain the fourth power delay spectrum. The first frequency domain channel inner product is determined based on the third power delay spectrum and the fourth power delay spectrum.

8. The channel type identification method according to claim 1, characterized in that, Determining the channel type based on the channel characteristics includes: Based on the channel characteristics, the channel type is obtained through a channel type identification model; The channel type identification model is trained based on multiple samples; each sample corresponds to a different channel type label, and each sample includes channel features corresponding to multiple orthogonal frequency division multiplexing (OFDM) symbol intervals.

9. The channel type identification method according to claim 8, characterized in that, The channel type obtained from the channel includes: If the OFDM symbol spacing of the channel feature is greater than the OFDM symbol spacing threshold, the channel type is determined by the channel type identification model based on the channel feature and the decision tree depth threshold.

10. The channel type identification method according to claim 8, characterized in that, The channel type obtained from the channel includes: Obtain the channel characteristics of the reference signal at multiple time points; Based on the channel characteristics of the reference signal at the multiple time points, the channel type of the channel at each of the multiple time points is determined by the channel type identification model.

11. A channel type identification device, characterized in that, include: A data processing unit is used to measure a reference signal to determine the channel characteristics of the channel corresponding to the reference signal; A channel identification unit is used to determine the channel type based on the channel characteristics; the channel type is associated with the number of dominant paths in the channel; the dominant path is used to characterize the transmission path in the channel whose signal power ratio is greater than a preset threshold.

12. The channel type identification device according to claim 11, characterized in that, The data processing unit is used for A first channel estimate is determined based on the first signal in the reference signal; The second channel estimate is determined based on the second signal in the reference signal; Based on the first channel estimate and the second channel estimate, determine the first frequency domain channel inner product; Based on the first channel estimate and the second channel estimate, determine the first channel power normalization result of the first signal and the second signal; The time-domain correlation coefficient is determined based on the first frequency-domain channel inner product and the first channel power normalization result.

13. The channel type identification device according to claim 12, characterized in that, The data processing unit is used for The first channel time-domain characteristics of the first signal and the second signal, the second channel time-domain characteristics of the third signal in the first signal and the reference signal, the third channel time-domain characteristics of the fourth signal in the first signal and the reference signal, the fourth channel time-domain characteristics of the second signal and the third signal, the fifth channel time-domain characteristics of the second signal and the fourth signal, and the sixth channel time-domain characteristics of the third signal and the fourth signal are determined respectively. The channel features are determined based on the first channel time-domain features, the second channel time-domain features, the third channel time-domain features, the fourth channel time-domain features, the fifth channel time-domain features, and the sixth channel time-domain features.

14. The channel type identification device according to claim 13, characterized in that, The channel identification unit is used for Select two pairs of reference signals from the reference signals and calculate the orthogonal frequency division multiplexing (OFDM) symbol spacing for each pair of reference signals. For multiple sets of reference signal pairs with the same OFDM symbol spacing, the time-domain characteristics of the interval of the multiple sets of reference signal pairs are determined based on the time-domain correlation coefficient of each reference signal pair in the multiple sets of reference signal pairs. For a single set of reference signals with a unique OFDM symbol interval, the time-domain correlation coefficient of the single set of reference signals is used as the time-domain feature of the interval of the single set of reference signals. Based on the time-domain characteristics of the multiple sets of reference signal pairs and the time-domain characteristics of the single set of reference signals, the channel time-domain characteristic set of the channel is obtained.

15. The channel type identification device according to claim 12, characterized in that, The data processing unit is used for Based on the first channel estimate, determine the first power delay spectrum of the first signal; Based on the second channel estimate, determine the second power delay spectrum of the second signal; The coefficients of the regions other than the target region in the first power delay spectrum are set to zero to obtain the third power delay spectrum; the target region includes at least one spectral peak region. The coefficients of the regions other than the target region in the second power delay spectrum are set to zero to obtain the fourth power delay spectrum. The first frequency domain channel inner product is determined based on the third power delay spectrum and the fourth power delay spectrum.

16. The channel type identification device according to claim 11, characterized in that, The channel identification unit includes a channel type identification model, used for Based on the channel characteristics, the channel type is obtained through a channel type identification model; The channel type identification model is trained based on multiple samples; each sample corresponds to a different channel type label, and each sample includes channel features corresponding to multiple orthogonal frequency division multiplexing (OFDM) symbol intervals.

17. The channel type identification device according to claim 16, characterized in that, The channel identification unit is used for If the OFDM symbol spacing of the channel feature is greater than the OFDM symbol spacing threshold, the channel type is determined by the channel type identification model based on the channel feature and the decision tree depth threshold.

18. The channel type identification device according to claim 16, characterized in that, The channel identification unit is used for Obtain the channel characteristics of the reference signal at multiple time points; Based on the channel characteristics of the reference signal at the multiple time points, the channel type of the channel at each of the multiple time points is determined by the channel type identification model.

19. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method of any one of claims 1-10.

20. A computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-10.

21. A program product, characterized in that, Includes computer instructions for causing a computer to perform the method of any one of claims 1 to 10.

22. A chip system, characterized in that, The chip system includes a processing unit and interface circuitry; The processing unit obtains program instructions through the interface circuit, and the program instructions are executed by the processing unit. The processing unit is used to execute the method described in any one of claims 1-10.

Images