US 11,687,803 B2
Response prediction for electronic communications
Kevin Osborn, Newton Highlands, MA (US); Eric Loucks, Tysons, VA (US); Joshua Edwards, Philadelphia, PA (US); George Bergeron, Falls Church, VA (US); Kyle Johnson, Washington, DC (US); and Brian Lee, South Riding, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jun. 4, 2020, as Appl. No. 16/892,705.
Prior Publication US 2021/0383251 A1, Dec. 9, 2021
Int. Cl. G06N 5/04 (2023.01); H04L 51/10 (2022.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01)
CPC G06N 5/04 (2013.01) [G06F 40/30 (2020.01); G06N 20/00 (2019.01); H04L 51/10 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A first computing device comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the first computing device to:
determine a first trained machine learning model, wherein the first trained machine learning model was trained, using first training data comprising a history of messages in one or more of a plurality of applications that each comprise a plurality of different emoji corresponding to one or more different sentiments, to determine subsets comprising at least two different emojis of a plurality of emojis by modifying, based on the first training data, one or more first weights of first nodes of a first artificial neural network;
determine a second trained machine learning model, wherein the second trained machine learning model was trained, using second training data comprising a history of responses to one or more past messages of the history of messages in the one or more of the plurality of applications, to select emojis, from the plurality of emojis, that correspond to one or more predicted responses to one or more messages by modifying, based on the second training data, one or more second weights of second nodes of a second artificial neural network;
receive data corresponding to a message, wherein the message is intended to be sent but has not yet been sent to an application executing on a second computing device;
process, using the first machine learning model, the message to determine one or more subsets comprising at least two different emojis of the plurality of emojis, wherein at least one of the one or more subsets corresponds to at least two different emoji types;
select, using the one or more second machine learning models and based on the message, one or more second emojis from the one or more subsets of the plurality of emojis, wherein the one or more second emojis comprise predicted responses to the message; and
transmit the one or more second emojis.