| CPC G06F 16/3344 (2019.01) [G06F 16/3326 (2019.01); G06F 16/338 (2019.01); G06F 16/35 (2019.01)] | 18 Claims |

|
1. A computer-implemented method comprising:
generating, by one or more processors, using a first machine learning model of a machine learning framework, and for a natural language query, an intent prediction that identifies a likelihood of a target query intent, wherein the intent prediction is based on a transformation of the natural language query into a query embedding;
generating, by the one or more processors, using a second machine learning model of the machine learning framework, and for the natural language query, an event prediction that identifies a likelihood of a target event that is associated with the target query intent, wherein the event prediction is based on a hidden state vector of a plurality of previous target events associated with an identifier corresponding to the natural language query;
generating, by the one or more processors, an intent classification for the natural language query based on the intent prediction and the event prediction; and
in response to the intent classification corresponding to the target query intent:
determining, by the one or more processors and based on the intent classification, a relevant data object from a plurality of candidate data objects based on a relevancy score between the relevant data object and the natural language query; and
providing, by the one or more processors and via a user interface, a natural language query result for the natural language query that identifies the relevant data object.
|