US 12,353,382 B2
Management of indexed data to improve content retrieval processing
Saurabh Sanjay Deshpande, Sammamish, WA (US); Mina Mikhail, Bothell, WA (US); Matthew Francis Hurst, Seattle, WA (US); and Riham Hassan Abdel-Moneim Mansour, Redmond, WA (US)
Assigned to MICROSOFT TECHNOLOGY LICENSING, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Dec. 7, 2022, as Appl. No. 18/062,991.
Application 18/062,991 is a continuation of application No. 16/721,652, filed on Dec. 19, 2019, granted, now 11,544,502.
Prior Publication US 2023/0096647 A1, Mar. 30, 2023
Int. Cl. G06K 9/62 (2022.01); G06F 16/22 (2019.01); G06F 16/2453 (2019.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01)
CPC G06F 16/2228 (2019.01) [G06F 16/22 (2019.01); G06F 16/2272 (2019.01); G06F 16/24549 (2019.01); G06F 18/2148 (2023.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
pre-loading, into a memory, data shards comprising a plurality of indexes from indexing file content representative of a randomized sampling of the file content;
receiving a search query for searching the file content from a user via a user interface of a cloud-based service;
processing the search query with a trained artificial intelligence classifier trained to search indexing across the data shards to retrieve content responsive to the search query;
reading, from the memory, the data shards during the processing the search query by the trained artificial intelligence classifier; and
providing the content responsive to the search query.