公开(公告)号：US11526512B1

公开(公告)日：2022-12-13

申请号：US16452363

申请日：2019-06-25

Applicant: Amazon Technologies, Inc.

Inventor： Nissim Halabi ,  Natali Arieli ,  Sagi Bernstein ,  Iftah Gamzu ,  Marina Haikin ,  Yochai Zvik

IPC: G06F16/2453 ,  G06F16/2452 ,  G06K9/62 ,  G10L15/16 ,  G06N20/00 ,  G10L15/22 ,  G06F40/289

Abstract: Systems and methods are described for mitigating errors introduced during processing of user input such as voice input. A query may be derived from processed user input. A performance predictor analyzes the query and uses historical data to predict whether the query will return relevant results if executed. If the query's predicted performance is below a threshold, a query rewriter may identify potential alternatives to the query from a library of “known good” queries. Different analyzers may be applied to identify different sets of alternatives, and machine learning models may be applied to rank the outputs of the analyzers. The best-matching alternatives from each analyzer may then be provided as inputs to a further machine learning model, which assesses the probability that each of the identified alternatives reflects the intent of the user. A most likely alternative may then be selected to execute in place of the original query.