| CPC G06F 16/3323 (2019.01) [G06F 16/334 (2019.01); G06N 5/02 (2013.01)] | 20 Claims |
|
1. A system for generating content based on dual-pathway models, the system comprising:
one or more processors; and
one or more non-transitory, computer-readable media comprising instructions recorded thereon that, when executed by the one or more processors, cause operations comprising:
receiving first user data;
determining, based on the first user data, a first prediction count that a user has a first intent of a plurality of available intents using a first model of a dual-pathway model, wherein the first model comprises a deterministic word graph model;
comparing the first prediction count to a first threshold count for using a second model of the dual-pathway model, wherein the second model comprises a semantic autocomplete model, and wherein the first threshold count comprises a required number of potential user inputs to be generated for display that have a threshold confidence;
in response to the first prediction count equaling or exceeding the first threshold count, selecting the first model from the dual-pathway model;
determining, using the first model, a first response for the first intent;
generating for display, on a user interface, a first potential user input corresponding to the first intent, wherein the first potential user input comprises a first text string for entry into a search field of the user interface;
receiving a first user input into the search field, wherein the first user input comprises a first textual character;
determining whether the first textual character corresponds to the first text string;
in response to determining that the first textual character corresponds to the first text string, continuing to generate for display the first potential user input;
determining, based on second user data, a second prediction count that the user has a second intent of the plurality of available intents using the first model of the dual-pathway model;
comparing the second prediction count to the first threshold count for using the second model of the dual-pathway model;
in response to the first prediction count not equaling or exceeding the first threshold count, selecting the second model from the dual-pathway model;
determining, using the second model, a second response for the second intent; and
generating for display, on the user interface, a second potential user input corresponding to the second response.
|