US 11,875,241 B2
Aspect pre-selection using machine learning
Farah Abdallah, Seattle, WA (US); Robert Enyedi, Santa Clara, CA (US); Amit Srivastava, San Jose, CA (US); Elaine Lee, Fremont, CA (US); Braddock Craig Gaskill, Alhambra, CA (US); Tomer Lancewicki, Jersey City, NJ (US); Xinyu Zhang, San Jose, CA (US); Jayanth Vasudevan, Fremont, CA (US); and Dominique Jean Bouchon, Cupertino, CA (US)
Assigned to eBay Inc., San Jose, CA (US)
Filed by eBay Inc., San Jose, CA (US)
Filed on Aug. 31, 2021, as Appl. No. 17/462,465.
Application 17/462,465 is a continuation of application No. 15/859,239, filed on Dec. 29, 2017, granted, now 11,144,811.
Claims priority of provisional application 62/588,868, filed on Nov. 20, 2017.
Prior Publication US 2021/0390365 A1, Dec. 16, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 3/006 (2023.01); G06F 16/50 (2019.01); G06Q 30/0601 (2023.01); G06Q 30/0251 (2023.01); G06F 16/9032 (2019.01); G06Q 10/10 (2023.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01); G06F 16/248 (2019.01)
CPC G06N 3/006 (2013.01) [G06F 16/248 (2019.01); G06F 16/50 (2019.01); G06F 16/90332 (2019.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01); G06Q 10/10 (2013.01); G06Q 30/0256 (2013.01); G06Q 30/0601 (2013.01); G06Q 30/0625 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving a search query from a user;
extracting a category of the search query;
locating, based on the category, a model from a plurality of models specific for the user, each of the plurality of models corresponding to a particular category and trained using machine learning and previous data received from the user that is specific to the particular category;
identifying additional text describing at least one aspect associated with the category of the search query by processing the search query using the model;
automatically adding, without user intervention, the additional text to the search query responsive to the identifying;
initiating, by a computing device, a search using the search query that includes the additional text;
outputting, by the computing device, a result of the search and an indication in a user interface that the additional text is added to the search query; and
adjusting the model based on user interaction with the result of the search.