Search International and National Patent Collections

1. (WO2018182093) METHOD FOR ENCODING ON BASIS OF MIXTURE OF VECTOR QUANTIZATION AND NEAREST NEIGHBOR SEARCH (NNS) METHOD USING SAME

Pub. No.:    WO/2018/182093    International Application No.:    PCT/KR2017/006450
Publication Date: Fri Oct 05 01:59:59 CEST 2018 International Filing Date: Wed Jun 21 01:59:59 CEST 2017
IPC: G06F 17/30
Applicants: ODD CONCEPTS INC.
오드컨셉 주식회사
Inventors: ZHAO, Wan Lei
짜오완 레이
MOON, Sang Whan
문상환
Title: METHOD FOR ENCODING ON BASIS OF MIXTURE OF VECTOR QUANTIZATION AND NEAREST NEIGHBOR SEARCH (NNS) METHOD USING SAME
Abstract:
The present invention relates to a method for encoding on the basis of a mixture of vector quantization and a nearest neighbor search (NNS) method using the same. The present invention relates to a method for encoding a candidate vector for searching for a neighbor that is nearest to a query in a candidate dataset, the method comprising: a normalization step of normalizing an input vector (wherein a first input vector is the candidate vector) to obtain a direction vector and vector energy; a quantization step of quantizing the direction vector to obtain a code word and a residual vector; a step of repeating the normalization step and the quantization step, as many times as a predetermined number of encoding times, by using the residual vector as an input vector; and a step of encoding the candidate vector by using one or more code words and energy of one or more vectors resulting from the repetition. According to the present invention, a dataset having a very wide range of energy values can be effectively approximated and higher precision thereof can be obtained.