Decoder Output Correction for Reliable Polar Code Decoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional polar code decoding methods face challenges in achieving high decoding performance while maintaining a simple interconnection structure, with existing modes either compromising on complexity or reliability.
Innovation Solution
A decoding method and apparatus that involves training a correction model using training data to correct decoding results from a first decoder, allowing iterative decoding and correction across multiple decoders to improve performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If soft output subcode decoding unit performs SCL decoding or SCAN decoding, then decoding performance is improved, but decoding kernel area increases and interconnection cable becomes complex
Solution Approach 1:
The decoding system is divided into multiple independent subcode decoding units, each handling specific subcodes. This segmentation allows parallel processing while maintaining simple interconnections within each unit, resolving the contradiction between performance and complexity.
Solution Approach 2:
A result processing unit acts as an intermediary that collects decoding results from multiple subcode decoding units and performs final synthesis. This mediator approach allows simple individual units to achieve high overall performance through coordinated processing.
2Device complexity
If hard output subcode decoding unit performs successive cancellation decoding, then interconnection cable remains simple, but decoding performance deteriorates due to lack of reliability information
Solution Approach 1:
Multiple hard output subcode decoding units are merged in parallel, with their results combined by the result processing unit. This combining approach achieves high decoding performance through ensemble processing while each individual unit maintains simple interconnection structure.
Solution Approach 2:
The result processing unit provides feedback by synthesizing results from multiple decoding units and potentially iteratively refining the overall decoding outcome, thereby improving performance without increasing individual unit complexity.
Data Source
AI summary
A decoding method includes: decoding first to-be-decoded information based on a first decoder to obtain a first decoding result that includes first soft information or a first hard output; and correcting the first decoding result based on a first correction model to obtain a corrected first decoding result of the first to-be-decoded information. The first correction model is obtained through training based on training data that includes a training decoding result and a corrected training decoding result. The training decoding result is a decoding result obtained after the first decoder decodes training to-be-decoded information, and the corrected training decoding result is a corrected decoding result corresponding to the training decoding result. In this way, after a decoder performs decoding, a decoding result can be corrected based on a correction model.