US 12,271,987 B2
Preprocessor system for natural language avatars
Dan German, Bristol (GB); Michelle Collins, Chicago, IL (US); Tyler W. Chase-Nason, Grand Junction, CO (US); and Navroz J. Daroga, Bayside, WI (US)
Assigned to Codebaby, Inc., Milwaukee, WI (US)
Filed by CodeBaby, Inc., Milwaukee, WI (US)
Filed on Jan. 13, 2023, as Appl. No. 18/154,099.
Claims priority of provisional application 63/266,748, filed on Jan. 13, 2022.
Prior Publication US 2023/0222723 A1, Jul. 13, 2023
Int. Cl. G06T 13/40 (2011.01); G06F 40/35 (2020.01); G06T 13/20 (2011.01); G10L 13/033 (2013.01); G10L 13/08 (2013.01); G10L 15/18 (2013.01); G10L 15/22 (2006.01)
CPC G06T 13/40 (2013.01) [G06F 40/35 (2020.01); G06T 13/205 (2013.01); G10L 13/033 (2013.01); G10L 13/08 (2013.01); G10L 15/1815 (2013.01); G10L 15/22 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A natural language avatar system comprising:
a response file providing query intents linked to response packages having text interspersed with avatar control data; and
a natural language processor operating to:
(1) receive a user query from a browser computer connected to the Internet;
(2) map the received user query to an intent and access the response file using the intent to obtain an associated response package; and
(3) convert the text of the response package to speech together with avatar control data interspersed in the speech at times based on locations of the avatar control data tags with respect to the text of the response package for output at the browser computer;
further including a preprocessor receiving the query from the browser computer and forwarding it to the natural language processor and receiving the speech and avatar control data from the natural language processor and forwarding it to the browser computer;
wherein the preprocessor includes a response cache holding previously received speech and avatar control data and operating to transmit the previously received speech and avatar control data in lieu of the speech and avatar control data developed by the natural language processor in response to the query when the previously received speech and avatar control data match the query;
wherein the natural language processor may receive a speech query to extract speech text as the user query and wherein the preprocessor monitors the speech text from the natural language processor to determine an end of speech time and trigger a transmission of the previously received speech and avatar to control data in lieu of the speech and avatar control data developed by the natural language processor in response to the query.