US 11,941,044 B2
Automatic personalized image-based search
Kannan Achan, Saratoga, CA (US); Sushant Kumar, Sunnyvale, CA (US); Kaushiki Nag, Santa Clara, CA (US); and Venkata Syam Prakash Rapaka, Cupertino, CA (US)
Assigned to WALMART APOLLO, LLC, Bentonville, AR (US)
Filed by Walmart Apollo, LLC, Bentonville, AR (US)
Filed on Jan. 28, 2019, as Appl. No. 16/259,822.
Claims priority of provisional application 62/622,543, filed on Jan. 26, 2018.
Prior Publication US 2019/0236095 A1, Aug. 1, 2019
Int. Cl. G06F 16/56 (2019.01); G06F 16/21 (2019.01); G06F 16/50 (2019.01); G06F 16/535 (2019.01); G06F 16/9535 (2019.01); G06N 3/08 (2023.01)
CPC G06F 16/535 (2019.01) [G06F 16/214 (2019.01); G06F 16/50 (2019.01); G06F 16/56 (2019.01); G06F 16/9535 (2019.01); G06N 3/08 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform:
training a recurrent neural network model to create a trained model based at least on: (a) first images associated with first items on a website, (b) first search terms used by users of the website to search for the first items on the website, and (c) personal features of the users, wherein an output term of the recurrent neural network model at a first time step is used as an input term at a immediately subsequent time step in the recurrent neural network model;
receiving an input image that was uploaded by a current user, the input image comprising a depiction of one or more items;
obtaining a user encoded representation vector for the current user based on a set of personal features of the current user;
generating an image encoded representation vector for the input image;
deriving search terms that are personalized to the current user for the one or more items depicted in the input image, using the trained model and based on the user encoded representation vector for the current use rand the image encoded representation vector for the input image, wherein the search terms comprise one or more item names for the one or more items and one or more features for the one or more items that are personalized to the current user based on the set of personal features; and
executing a search of items on the website based on the input image using the search terms derived that are personalized to the current user,
wherein training the recurrent neural network model comprises:
generating a respective user encoded representation vector for each user of the users based on a respective set of personal features of the each user using an autoencoder neural network.