Adaptive Huffman coding system and method

By constructing a Huffman binary tree and optimizing node data mapping, the problem of high memory bandwidth usage of adaptive Huffman coding on hardware is solved, and efficient coding storage and memory optimization are achieved, which is suitable for edge model inference.

CN114900193BActive Publication Date: 2025-10-03BOLIU INTELLIGENT TECH (NANJING) CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202210366617.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-04-08
Publication Date
2025-10-03
Estimated Expiration
2042-04-08

AI Technical Summary

Technical Problem

Existing adaptive Huffman coding suffers from hardware issues such as high memory bandwidth usage, a tree-like data structure that is not conducive to memory storage, and high computational costs, making it difficult to efficiently perform lossless data compression during edge model inference.

Method used

By constructing a Huffman binary tree and using fixed address access to optimize node data mapping, configuring continuous memory to store internal node and leaf node information, dynamically updating node weights and swapping nodes, and using binary tree memory address remapping technology, memory usage is optimized and bandwidth usage is reduced.

Benefits of technology

It achieves efficient access to encoded data structures on hardware, optimizes storage space and provides memory flexibility, reduces memory bandwidth usage per unit time, and is suitable for hardware environments with memory constraints.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention discloses an adaptive Huffman coding system and method. The adaptive Huffman coding system includes: a data acquisition module for acquiring data to be encoded and a Huffman binary tree encoding module. The data acquisition module is used to acquire data to be encoded; the Huffman binary tree encoding module is used to construct a Huffman binary tree based on the data to be encoded acquired by the data acquisition module. Each node of the Huffman binary tree is indexed with memory. When constructing the Huffman binary tree, the memory index value of the target node is calculated based on the unique path from the root node to the target node. The adaptive Huffman coding system and method proposed by the present invention can efficiently access the encoding data structure on hardware and optimize the encoding storage space, while providing the flexibility of configurable memory.
Need to check novelty before this filing date? Find Prior Art