CN-119785859-B - Codeword information decoding method, apparatus and storage medium

CN119785859BCN 119785859 BCN119785859 BCN 119785859BCN-119785859-B

Abstract

The application relates to the technical field of memories, and discloses a decoding method, equipment and a storage medium of codeword information, which relate to the technical field of memories and comprise the steps of determining the number of error bits in codeword information when the codeword information is read, re-reading the codeword information and performing overturning operation on the codeword information according to a re-reading result if the number of error bits is larger than the error-correctable number, and performing hard decoding on the overturning result based on an iterative algorithm to obtain a corresponding decoding result. Aiming at improving the decoding capability.

Inventors

Zeng Chuangyuan
LIU SHANG
GUO ZICHENG

Assignees

得一微电子股份有限公司

Dates

Publication Date: 20260508
Application Date: 20241118

Claims (8)

1. A method of decoding codeword information, the method comprising: when the codeword information is read, determining the number of error bits in the codeword information; If the number of the error bits is larger than the error-correctable number, adjusting the voltage according to a preset adjustment amount, and collecting re-reading results under each voltage; performing exclusive OR calculation on all the re-reading results, and determining bits to be flipped in the codeword information according to the calculation results; detecting a decoding record of a hierarchical structure where the codeword information is located; if the decoding record is empty, performing turning operation on all the bits to be turned; If the decoding record is not empty, screening the bits to be turned over according to the average number of error bits in the decoding record, and turning over the screened bits to be turned over; And performing hard decoding on the turnover result based on an iterative algorithm to obtain a corresponding decoding result.
2. The method of claim 1, wherein the step of determining the number of error bits in the codeword information when the codeword information is read comprises: when the codeword information is read, dividing the codeword information based on a generator polynomial to obtain a corresponding accompanying polynomial; And determining the number of the error bits according to the syndrome coefficients of the syndrome polynomial.
3. The method of claim 1, wherein the step of screening the bits to be flipped comprises: determining a correlation coefficient between the bit to be flipped and a historical error bit in the decoding record; And sequencing all the bits to be flipped according to the correlation coefficient to generate a sequence, and screening the sequence according to the average number.
4. The method of claim 3, wherein said step of ordering all said bits to be flipped according to said correlation coefficient to generate a sequence and screening said sequence according to said average further comprises, prior to said step of: Determining the fault mode of the bit to be flipped according to the fault mode of the historical error bit matched with the bit to be flipped; And weighting the correlation coefficient according to the severity of the fault mode.
5. The method of claim 1, wherein the step of determining the number of erroneous bits in the codeword information further comprises, when the codeword information is read: And if the number of the error bits is smaller than or equal to the error-correctable number, decoding the codeword information based on an iterative algorithm to obtain a corresponding decoding result.
6. The method of claim 1, wherein the step of hard decoding the flipped result based on the iterative algorithm to obtain a corresponding decoded result comprises: if the number of error bits in the turnover result is smaller than or equal to the error-correctable number, hard decoding is carried out on the turnover result based on an iterative algorithm, and a corresponding decoding result is obtained; The step of hard decoding the turnover result based on the iterative algorithm to obtain a corresponding decoding result further comprises the following steps: And if the number of error bits in the turnover result is larger than the error-correctable number, decoding the turnover result based on a low-density parity check algorithm to obtain a corresponding decoding result.
7. A decoding device for codeword information, characterized in that the device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the decoding method for codeword information according to any of claims 1 to 6.
8. A storage medium, characterized in that the storage medium is a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method of decoding codeword information according to any of claims 1 to 6.

Description

Codeword information decoding method, apparatus and storage medium Technical Field The present application relates to the field of memory technologies, and in particular, to a method, an apparatus, and a storage medium for decoding codeword information. Background NAND FLASH (Not AND Flash, NAND Flash) is a very important non-volatile memory, AND is widely used in various portable electronic devices. Although NAND FLASH has advantages of high density and low cost, it is prone to various errors during data storage. To improve the reliability of NAND FLASH, ECC (Error Correction Cod e ) techniques are generally used to detect and correct errors generated during storage. A common algorithm, such as BCH (Bose Chaudhuri Hocquenghem), BCH code is a linear cyclic code that can locate and correct the erroneous bits by computing the syndrome polynomial and applying a specific algorithm, thereby recovering the original information. However, for a specific BCH code, the number of correctables is already determined at design time, and decoding performance will be severely affected once the number of errors actually occurring exceeds this threshold. The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present application and is not intended to represent an admission that the foregoing is prior art. Disclosure of Invention The application mainly aims to provide a decoding method, equipment and a storage medium for codeword information, and aims to solve the technical problem of insufficient decoding capability. In order to achieve the above object, the present application provides a method for decoding codeword information, the method comprising: when the codeword information is read, determining the number of error bits in the codeword information; If the number of error bits is larger than the error-correctable number, re-reading the codeword information, and performing overturn operation on the codeword information according to the re-reading result; And performing hard decoding on the turnover result based on an iterative algorithm to obtain a corresponding decoding result. In one embodiment, when the codeword information is read, the step of determining the number of error bits in the codeword information comprises: when the codeword information is read, dividing the codeword information based on the generator polynomial to obtain a corresponding accompanying polynomial; the number of erroneous bits is determined based on the syndrome coefficients of the syndrome polynomial. In one embodiment, the step of re-reading the codeword information and performing the flipping operation on the codeword information according to the re-reading result includes: Adjusting the voltage according to a preset adjustment amount, and collecting re-reading results under each voltage; performing exclusive OR calculation on all re-reading results, and determining bits to be flipped in the codeword information according to the calculation results; And performing flipping operation on the bit to be flipped. In one embodiment, the step of flipping the bits to be flipped includes: Detecting decoding records of a hierarchical structure where codeword information is located; If the decoding record is empty, performing turning operation on all bits to be turned; And if the decoding record is not empty, screening the bits to be flipped according to the average number of error bits in the decoding record, and flipping the screened bits to be flipped. In one embodiment, the step of screening the bits to be flipped includes: Determining the correlation coefficient between the bit to be flipped and the historical error bit in the decoding record; and sequencing all bits to be flipped according to the correlation coefficient to generate a sequence, and screening the sequence according to the average number. In an embodiment, before the step of sorting all bits to be flipped according to the correlation coefficient to generate a sequence and screening the sequence according to the average number, the method further includes: determining the fault mode of the bit to be flipped according to the fault mode of the historical error bit matched with the bit to be flipped; and weighting the correlation coefficient according to the severity of the fault mode. In an embodiment, when the codeword information is read, the step of determining the number of error bits in the codeword information further comprises: If the number of error bits is smaller than or equal to the error-correctable number, decoding the codeword information based on an iterative algorithm to obtain a corresponding decoding result. In one embodiment, the step of hard decoding the flipped result based on the iterative algorithm to obtain a corresponding decoded result includes: If the number of error bits in the turnover result is smaller than or equal to the error correction number, hard decoding is carried out on the turnover resu