IP Library › Granted Patent US 12,726,311
Granted Patent B2
US 12,726,311 · App. 18/513,470 · Granted Sep 1, 2026

Channel estimation method and apparatus, device, and readable storage medium

Inventors: Jianming Wu (Dongguan, CN); Ang Yang (Dongguan, CN)
Assignee: VIVO MOBILE COMMUNICATION CO., LTD.
H04L5/0051H04B17/328H04L25/023H04W72/232
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,726,311
App. No.
18/513,470
Granted
Sep 1, 2026
Kind
B2
Abstract

The present application discloses a channel estimation method and apparatus, a device, and a readable storage medium. The channel estimation method includes: receiving, by a communication device, a pilot signal and a data signal; determining, by the communication device, a linear feature according to the pilot signal; determining, by the communication device, a nonlinear feature according to the data signal; and performing, by the communication device, channel estimation according to the linear feature and the nonlinear feature.

Claims (60)

1 . A method of channel estimation, comprising:

receiving, by a communication device, a pilot signal and a data signal;

determining, by the communication device, a linear feature according to the pilot signal;

determining, by the communication device, a nonlinear feature according to the data signal; and

performing, by the communication device, channel estimation according to the linear feature and the nonlinear feature.

2 . The method according to claim 1 , wherein performing, by the communication device, the channel estimation according to the linear feature and the nonlinear feature comprises:

performing, by the communication device, channel estimation through artificial intelligence according to the linear feature and the nonlinear feature.

3 . The method according to claim 2 , wherein determining, by the communication device, the nonlinear feature according to the data signal comprises:

when using multiple-input multiple-output transmission, determining, by the communication device, the nonlinear feature according to the data signal by training a neural network.

4 . The method according to claim 3 , wherein receiving, by the communication device, the pilot signal and the data signal comprises:

receiving, by the communication device, the pilot signal and the data signal via a resource element; and

determining, by the communication device, the nonlinear feature according to the data signal by training the neural network comprises:

training, by the communication device according to the pilot signal and the data signal, a nonlinear feature associated with the resource element; and

training, by the communication device by using the trained nonlinear feature and the pilot signal, a channel associated with the resource element.

5 . The method according to claim 1 , wherein determining, by the communication device, the nonlinear feature according to the data signal comprises:

performing, by the communication device, de-noising processing on the data signal; and

determining, by the communication device, the nonlinear feature by using the denoised data signal.

6 . The method according to claim 5 , wherein performing, by the communication device, the de-noising processing on the data signal comprises:

determining, by the communication device, a noise reduction channel block; and

performing, by the communication device, de-noising processing on the data signal through the noise reduction channel block.

7 . The method according to claim 6 , wherein determining, by the communication device, the noise reduction channel block comprises:

determining, by the communication device, a size of the noise reduction channel block according to one or more of a manner of receiving a signal, channel fading frequency selectivity, and a moving speed of the communication device; and

the manner of receiving a signal comprises: receiving a signal in different consecutive time slots, or receiving a signal in an independent time slot.

8 . The method according to claim 7 , wherein in response to a determination that the communication device is a terminal, the method further comprises:

receiving downlink control information; and

determining the manner of receiving a signal according to the downlink control information.

9 . The method according to claim 7 , before determining, by the communication device, the size of the noise reduction channel block, further comprising:

determining, by the communication device, channel fading frequency selectivity or the moving speed of the communication device.

10 . The method according to claim 5 , wherein performing, by the communication device, the de-noising processing on the data signal comprises:

obtaining, by the communication device, a measured reference signal received power (RSRP) or a received signal strength indicator (RSSI);

determining, by the communication device, a noise power spectral density according to the RSRP or the RSSI; and

performing de-noising processing on the data signal according to the noise power spectral density.

11 . The method according to claim 1 , wherein the nonlinear feature comprises an amplitude feature of the data signal.

12 . The method according to claim 11 , wherein determining, by the communication device, the nonlinear feature by using the denoised data signal comprises:

obtaining, by the communication device, a sum of squared values of amplitudes of all transmit antennas; and

determining, by the communication device, the sum of the square values of the amplitudes as the amplitude feature of the denoised data signal.

13 . The method according to claim 1 , wherein the pilot signal comprises: a demodulation reference signal, a phase tracking reference signal, a channel state information reference signal, or a sounding reference signal.

14 . A communications device, comprising: a memory storing a computer program; and a processor coupled to the memory and configured to execute the computer program to perform operations comprising:

receiving a pilot signal and a data signal;

determining a linear feature according to the pilot signal;

determining a nonlinear feature according to the data signal; and

performing channel estimation according to the linear feature and the nonlinear feature.

15 . The communications device according to claim 14 , wherein performing the channel estimation according to the linear feature and the nonlinear feature comprises:

performing channel estimation through artificial intelligence according to the linear feature and the nonlinear feature.

16 . The communications device according to claim 15 , wherein determining the nonlinear feature according to the data signal comprises:

when using multiple-input multiple-output transmission, determining the nonlinear feature according to the data signal by training a neural network.

17 . The communications device according to claim 16 , wherein receiving the pilot signal and the data signal comprises:

receiving the pilot signal and the data signal via a resource element; and

determining the nonlinear feature according to the data signal by training the neural network comprises:

training, by the communication device according to the pilot signal and the data signal, a nonlinear feature associated with the resource element; and

training, by the communication device by using the trained nonlinear feature and the pilot signal, a channel associated with the resource element.

18 . A non-transitory computer-readable storage medium, storing a computer program, when the computer program is executed by a processor, causes the processor to perform operations comprising:

receiving a pilot signal and a data signal;

determining a linear feature according to the pilot signal;

determining a nonlinear feature according to the data signal; and

performing channel estimation according to the linear feature and the nonlinear feature.

19 . The non-transitory computer-readable storage medium according to claim 18 , wherein performing the channel estimation according to the linear feature and the nonlinear feature comprises:

performing channel estimation through artificial intelligence according to the linear feature and the nonlinear feature.

20 . The non-transitory computer-readable storage medium according to claim 19 , wherein determining the nonlinear feature according to the data signal comprises:

when using multiple-input multiple-output transmission, determining the nonlinear feature according to the data signal by training a neural network.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 18, 2023
From: WU, JIANMING; YANG, ANG
To: VIVO MOBILE COMMUNICATION CO., LTD.
Reel/Frame 065608/0070 →
Priority Claims (1)
CN 202110546723.1 · May 19, 2021 · national
Continuity (2)
Continuation PCTCN2022092497 · May 12, 2022
Related Publication 20240097853A1 · Mar 21, 2024
References Cited (11)
US 20040248541A1 · Park · 2004 [cited by examiner]
US 20120094709A1 · Ogawa · 2012 [cited by examiner]
US 20140036984A1 · W. Charbonneau et al. · 2014 [cited by applicant]
CN 110430150A · 2019 [cited by applicant]
CN 111464465A · 2020 [cited by applicant]
CN 111555990A · 2020 [cited by applicant]
CN 112398505A · 2021 [cited by applicant]
WO 2020199066A1 · 2020 [cited by applicant]
International Search Report issued in corresponding International Application No. PCT/CN2022/092497, mailed Aug. 10, 2022, 4 pages. [cited by applicant]
First Office Action issued in related Chinese Application No. 202110546723.1 , mailed Aug. 29, 2023, 7 pages. [cited by applicant]
Ziyu Zhou et al.,“Analysis of the theoretical upper limit of uplink spectrum efficiency based on superimposed pilots in cell-free massive MIMO systems”, Signal Processing, vol. 37, Issue 4, Apr. 30, 2021, ISSN:1003-0530. [cited by applicant]