US 11,854,544 B1
Entity resolution of product search filters
Gary Weiss, Givatayim (IL); and David Shamouilian, Netanya (IL)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Jun. 11, 2021, as Appl. No. 17/345,734.
Int. Cl. G06F 16/00 (2019.01); G06F 16/245 (2019.01); G06F 16/2455 (2019.01); G06F 16/248 (2019.01); G10L 15/08 (2006.01); G10L 15/22 (2006.01); G10L 15/183 (2013.01); G06F 16/242 (2019.01); G06N 20/00 (2019.01); G06F 16/22 (2019.01)
CPC G10L 15/22 (2013.01) [G06F 16/2246 (2019.01); G06F 16/2425 (2019.01); G06N 20/00 (2019.01); G10L 15/183 (2013.01); G10L 2015/223 (2013.01)] 20 Claims
OG exemplary drawing
 
5. A computer-implemented method, comprising:
receiving first input data associated with a first search query comprising search terms to search an item catalog of a resource provider;
determining a set of potential departments of the item catalog to search based on the first search query;
receiving voice input data and processing the voice input data using a natural language processing algorithm to produce second input data, the second input data comprising an attribute;
determining, based on the attribute, a structured graph corresponding to each of the potential departments, the structured graph comprising subsets of items within each potential department divided into trees based on item attributes and filters;
accessing, based on the structured graph, a predefined set of filters for each of the potential departments;
matching the attribute to a subset of the predefined set of filters; and
refining the first search query based on the subset of the predefined set of filters.