US 12,261,809 B2
Context-aware conversational assistant
Vinayak Kamat, Overland Park, KS (US); and Roman Breslav, Newton, MA (US)
Assigned to HRB Innovations, Inc., Wilmington, DE (US)
Filed by HRB Innovations, Inc., Las Vegas, NV (US)
Filed on Apr. 28, 2017, as Appl. No. 15/581,177.
Prior Publication US 2018/0316636 A1, Nov. 1, 2018
Int. Cl. H04L 51/046 (2022.01); G06Q 30/016 (2023.01); H04L 51/02 (2022.01); H04L 51/216 (2022.01)
CPC H04L 51/046 (2013.01) [H04L 51/02 (2013.01); H04L 51/216 (2022.05); G06Q 30/016 (2013.01)] 20 Claims
OG exemplary drawing
 
1. One or more non-transitory computer-storage media storing computer executable instructions that, when executed by at least one processor, perform a method of providing a context-aware conversational assistant, the method comprising:
presenting, by a first user interface on a user computing device, messages between a user and a human agent and an inbox configured to receive a message from the user;
requesting a biometric scan to be obtained by a sensor associated with the user computing device;
obtaining biometric data from the user by the sensor associated with the user computing device and authenticating an identity of the user by comparing the biometric data to stored identity data associated with a user history data store;
obtaining historic data associated with the user history data store comprising a past query and a past response to the past query;
receiving, by the inbox on the first user interface, the message from the user, the message comprising a query;
analyzing the query to determine a query meaning,
wherein the query meaning has a first interpretation and a second interpretation;
analyzing the past query and determining a higher likelihood that the query meaning is indicative of the first interpretation based on the past response to the past query,
wherein the past response to the past query is indicative of the first interpretation;
obtaining sentiment data from the sensor associated with the user computing device;
analyzing the sentiment data and the historic data associated with the user to determine a mood of the user based on the sentiment data and comparing the message to the past query;
selecting a set of info cards from a plurality of info cards based on the query, the past response, and the mood of the user,
wherein the set of info cards include a recommended response to the query based on the first interpretation;
presenting, by a second user interface and by an agent computing device, the messages between the user and the human agent, and the set of info cards;
receiving an info card selection by the human agent; and
presenting a query response by the first user interface to the user based on the info card selection by the human agent.