Flash memory decoding method and device and computer storage medium
By dynamically updating the correction factors alpha and beta in the LDPC software decoder, the software decoding process of the flash memory system is optimized, which solves the problem of limited error correction performance in the prior art and improves data reliability and error correction capability.
CN122220143AActive Publication Date: 2026-06-16HUIYIWEI (SHANGHAI) TECHNOLOGY CO LTD
10 Cites 0 Cited by
Patent Information
- Application Number
- CN202610550443.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-24
- Publication Date
- 2026-06-16
- Estimated Expiration
- 2046-04-24
AI Technical Summary
Technical Problem
Existing LDPC soft decoding algorithms offer limited improvement in error correction performance in flash memory systems and cannot effectively address the problem of high raw bit error rates.
Method used
By dynamically updating the correction factors alpha and beta based on the hard decision results, the node update steps in the LDPC soft decoder are optimized, thereby enhancing the error correction performance of soft decoding.
Benefits of technology
It improves the data reliability of the flash memory system and the error correction performance of the software decoder, reduces the bit error rate, and accelerates the convergence speed of the software decoder.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention provides a flash memory decoding method and device and a computer storage medium. The flash memory decoding method comprises the following steps: in response to hard decision failure, updating a correction factor according to a current hard decision result; using the updated correction factor to update the posterior information of the variable node; and performing hard decision again according to the updated posterior information of the variable node. According to the flash memory decoding method, the dynamic correction factor is introduced, the error correction performance of soft decoding is improved, and soft decoding convergence is accelerated.
Need to check novelty before this filing date? Find Prior Art