US 12,136,159 B2
Contextually oriented behavior of artificial intelligence characters
Ilya Gelfenbeyn, Palo Alto, CA (US); Mikhail Ermolenko, Mountain View, CA (US); Kylan Gibbs, San Francisco, CA (US); Evgenii Shingarev, Mountain View, CA (US); Ilya Platonov, Mountain View, CA (US); and Kirill Ryzhov, Mountain View, CA (US)
Assigned to Theai, Inc., Mountain View, CA (US)
Filed by Theai, Inc., Mountain View, CA (US)
Filed on Dec. 30, 2023, as Appl. No. 18/401,416.
Claims priority of provisional application 63/436,489, filed on Dec. 31, 2022.
Prior Publication US 2024/0221269 A1, Jul. 4, 2024
Int. Cl. G06T 13/40 (2011.01); G06F 40/40 (2020.01); G06V 20/50 (2022.01)
CPC G06T 13/40 (2013.01) [G06V 20/50 (2022.01); G06F 40/40 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A method for providing contextually oriented behavior of artificial intelligence (AI) characters, the method comprising:
receiving, by at least one processor, a description of a plurality of scenes associated with an AI environment, the description including a list of AI objects and a list of AI character models present in a scene of the plurality of scenes, the description including a natural language received from a user via a user interface;
pre-processing, by the at least one processor, the natural language to generate text;
passing, by the at least one processor, the text through a plurality of machine learning models to produce intermediate outputs of the plurality of machine learning models, the intermediate outputs including parameters associated with the list of AI character models present in the scene of the plurality of scenes;
generating, by the at least one processor and based on the parameters associated with the list of AI character models, a plurality of AI scene models corresponding to the plurality of scenes, the plurality of AI scene models including an AI scene model corresponding to the scene;
presenting, by the at least one processor, the AI scene model in the AI environment to the user, the presenting including rendering the list of AI objects and the list of AI character models in the scene associated with the AI scene model on a client-side computing device associated with the user, the scene being associated with parameters of the scene, wherein:
the AI character models of the list of AI character models are associated with a knowledge store;
the knowledge store stores a plurality of versions of information, the plurality of versions of information being assigned with priority scores; and
the priority scores are based on the parameters of the scene; and
adjusting, by the at least one processor and based on the parameters of the scene, behavioral characteristics of an AI character model of the list of AI character models, wherein the adjusting the behavioral characteristics of the AI character model includes:
selecting, based on the priority scores, a version of information from the plurality of versions of information stored in the knowledge store; and
configuring the AI character model to share the version of information during an interaction between the user and the AI character model.