US 11,960,555 B2
Attentive pseudo-relevance feedback network for query categorization
Ali Ahmadvand, Atlanta, GA (US); Sayyed M. Zahiri, Atlanta, GA (US); Simon Hughes, Atlanta, GA (US); Khalifeh Al Jadda, Atlanta, GA (US); Surya Kallumadi, Atlanta, GA (US); and Eugene Agichtein, Atlanta, GA (US)
Assigned to Home Depot Product Authority, LLC, Atlanta, GA (US)
Filed by Home Depot Product Authority, LLC, Atlanta, GA (US)
Filed on Mar. 2, 2022, as Appl. No. 17/685,130.
Claims priority of provisional application 63/155,903, filed on Mar. 3, 2021.
Prior Publication US 2022/0284066 A1, Sep. 8, 2022
Int. Cl. G06F 16/9535 (2019.01); G06F 16/906 (2019.01); G06F 16/9532 (2019.01); G06F 16/9538 (2019.01)
CPC G06F 16/9535 (2019.01) [G06F 16/906 (2019.01); G06F 16/9532 (2019.01); G06F 16/9538 (2019.01)] 18 Claims
OG exemplary drawing
 
1. A method of providing results from a search engine, the method comprising:
generating an initial set based on a query received from a user, the initial set corresponding to documents from the search engine;
determining, by a computing device, a vector representative of each document in the initial set of the query;
deriving, by the computing device, one or more fields corresponding to each document of the initial set;
determining, by a model of the computing device, field embeddings representative of each of the one or more fields corresponding to each document of the initial set comprising:
determining, by the model of the computing device, a word-level embeddings and character-level embeddings for each word in the field,
adjusting, by the model of the computing device, the word-level embeddings based on the character-level embeddings, and
determining, by the model of the computing device, the field embeddings based on the adjusted word-level embeddings,
wherein the adjusted word-level embeddings refine the field embeddings to compensate for morphological errors in the documents;
generating, by the model of the computing device, an attention value based on the vector representative of each document in the query and on the refined field embeddings of the initial set;
applying, by the computing device, the attention value to the initial set to generate a first set of results;
determining, by the computing device, a category based on an application of the attention value; and
presenting, by the computing device, a second set of results in response to the query;
wherein the second set of results comprises one or more documents of the initial set determined based on the attention values and on the refined field embeddings.