| CPC G06F 16/3344 (2019.01) | 20 Claims |
|
9. A computing system, comprising:
one or more processors; and
a memory storing computer-executable instructions that, when executed by the one or more processors, causes the computing system to:
generate a semantically-related search query for a document based at least in part on providing document data corresponding to the document to a machine-learning model as input, the semantically-related search query comprising at least one token that lexically differs from the document data, the machine-learning model being previously trained to generate semantically-related search queries that lexically differ from input data;
associate the document with the semantically-related search query generated by the machine-learning model;
receive a subsequent search query;
match the document to the subsequent search query based at least in part on determining a lexical match between a first portion of the subsequent search query and a second portion of the semantically-related search query with which the document is associated; and
add the document to a search result set that is generated in response to receiving the subsequent search query.
|