公开(公告)号：US11250041B2

公开(公告)日：2022-02-15

申请号：US16147444

申请日：2018-09-28

Applicant: Apple Inc.

Inventor： Vivek Kumar Rangarajan Sridhar ,  Xingwen Xu ,  Vignesh Jagadeesh

IPC: G06F16/33 ,  G06F16/13 ,  G06F16/35 ,  G06F16/31

Abstract: A device implementing a system for expanded search includes a processor configured to identify plural words, and generate, for each word of the plural words, a word vector based on a proximity of the word relative to other words of the plural words, the word vector comprising plural dimensions. The processor is further configured to create a compressed word vector structure comprising clusters of subsets of the plural dimensions across the word vectors, each cluster including similar values of the respective dimensions, convert the word vectors to points on at least one plane, and partition the at least one plane into nested groupings of the points based on a threshold number of points per nested grouping. The processor is further configured to create a tree look-up structure of the nested groupings, and provide the compressed word vector structure and the tree look-up structure to a client device.

公开(公告)号：US20190340255A1

公开(公告)日：2019-11-07

申请号：US16147233

申请日：2018-09-28

Applicant: Apple Inc.

Inventor： Killian Huyghe ,  Eric Circlaeys ,  Guillaume Vergnaud ,  Sabrine Rekik ,  Lee A. Morgan ,  Elliot C. Liskin ,  Vivek Kumar Rangarajan Sridhar ,  Xingwen Xu ,  Kevin Bessiere ,  Patrick H. Kelly ,  Timothy J. Allen ,  Benedikt M. Hirmer

IPC: G06F17/30 ,  G06F17/27

Abstract: Embodiments of the present disclosure present devices, methods, and computer readable medium for enabling a user to quickly and easily filter and search a digital asset collection. The disclosed techniques allow for rapid recall of desired digital assets, linking assets into logical collections, and an overall improved user experience. The zero keyword/contextual keyword feature presents multimedia content icons and searchable keywords to allow a user to search the digital asset collection simply by tapping on one of these keywords. The top auto completion feature auto-completes suggestions in the search field based on various heuristics to ensure the method produces diverse and relevant results. The next keyword suggestion feature predicts a next search term based on learned properties about the digital asset collection. The semantical synonym and syntax synonym features expand an indexed vocabulary to allow broader searching. The fast/limited property feature loads only those needed properties required for a search.