US 11,893,795 B2
Interacting with visitors of a connected home environment
William Alexander Finlayson, San Mateo, CA (US); Liana Kong, Redwood City, CA (US); John Jordan Nold, Longmont, CO (US); Sahana Mysore, Menlo Park, CA (US); and Ruiyi Song, Sunnyvale, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Dec. 9, 2020, as Appl. No. 17/116,662.
Claims priority of provisional application 62/945,724, filed on Dec. 9, 2019.
Prior Publication US 2021/0174095 A1, Jun. 10, 2021
Int. Cl. G06V 20/52 (2022.01); G08B 13/196 (2006.01); G06F 3/16 (2006.01); G06V 20/40 (2022.01); G06V 40/10 (2022.01); G06V 40/20 (2022.01)
CPC G06V 20/52 (2022.01) [G06F 3/165 (2013.01); G06V 20/41 (2022.01); G06V 40/10 (2022.01); G06V 40/20 (2022.01); G08B 13/196 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining video data captured by a camera of a visitor interaction system;
determining an approach of a person toward the visitor interaction system;
determining, based on an analysis of the video data and the approach of the person, an identity of the person;
determining, based on the identity of the person, that the person belongs to a respective predefined visitor group of a plurality of predefined visitor groups, each of the plurality of predefined visitor groups corresponding to a respective predefined response model of a plurality of predefined response models, one or more predefined response model of the plurality of predefined response models including at least one response action of a plurality of response actions, a respective response action of the plurality of response actions being executable by the visitor interaction system without requiring intervention of a user of the visitor interaction system;
identifying a respective predefined response model of the plurality of predefined response models corresponding to the respective predefined visitor group of the plurality of predefined visitor groups, one or more respective predefined response model of the plurality of predefined response models for each of the predefined visitor groups being modifiable using one or more previous response actions, the one or more previous response actions including one or more user selected response actions, one or more user rejected response actions, one or more user defined response actions, or one or more repeated response actions;
initiating, by the visitor interaction system, a first autonomous action of a plurality of respective autonomous actions based on the respective predefined response model; and
sending a first report message to the user via a client device, the first report message including at least one of a representation of the video data, data relating to the approach of the person, data relating to the identity of the person, the first autonomous action, or a summary of the first message.