Method for encoding based on mixture of vector quantization and nearest neighbor search using thereof
US11436228B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 20, 2017 |
| Grant date | Sep 6, 2022 |
| Priority date | — |
| Expiry date | Jan 26, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F16/24
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
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 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.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.