Interactive calligraphic character K approaching search method
A query method and k-nearest neighbor technology, which is applied in the fields of electrical digital data processing, special data processing applications, instruments, etc., can solve the problems of complexity, query accuracy is not very ideal, and styles are different, and achieve the effect of improving query efficiency.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0046] The specific implementation steps of interactive calligraphy word k nearest neighbor query method are as follows:
[0047] (1) Local distance map index:
[0048] In order to support efficient and accurate content-based calligraphic character similarity query, an interactive high-dimensional index structure for the characteristics of calligraphic character retrieval—Partial Distance Map (PDM)—is proposed. By combining relevant feedback information from users, the query space can be more effectively reduced, and the query efficiency can be improved while ensuring a high precision rate. The basic idea of PDM index is that for a query word V q , with the help of its nearest neighbor (most similar) word V p and a pre-generated local distance map to complete the query.
[0049] According to the observation of calligraphy character retrieval results, for any given calligraphy character V i , words with a distance value of less than 150 (defined as MAX_VDT below) are very...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com