US 12,469,010 B2
Virtual business assistant AI engine for multipoint communication
Srivatsan Laxman, Palo Alto, CA (US); and Supriya A Rao, Palo Alto, CA (US)
Filed by Srivatsan Laxman, Palo Alto, CA (US); and Supriya A Rao, Palo Alto, CA (US)
Filed on Oct. 26, 2020, as Appl. No. 17/080,037.
Application 17/080,037 is a continuation in part of application No. 16/917,882, filed on Jun. 30, 2020, abandoned.
Claims priority of provisional application 62/869,160, filed on Jul. 1, 2019.
Prior Publication US 2021/0142291 A1, May 13, 2021
Int. Cl. G06N 5/025 (2023.01); G06F 16/22 (2019.01); G06F 16/28 (2019.01); G06Q 10/107 (2023.01)
CPC G06Q 10/107 (2013.01) [G06F 16/22 (2019.01); G06F 16/285 (2019.01); G06N 5/025 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A computerized method comprising:
receiving a dialog session, wherein the dialog session comprises a set of new inbound messages;
feeding the dialog session into tokenizer;
with the tokenizer, generating a set of tokens by breaking the new inbound messages into a sequence of tokens;
providing the tokens to a DAG frame labeler cascade;
with the DAG frame labeler cascade, using a sequence of tokens to generate a set of token labels, wherein the input to the DAG frame labeler cascade is then passed to a set of levels, wherein a number of levels is dependent on a desired depth of the DAG frame, and wherein each entity group has its own level;
passing, with the DAG frame labeler cascade, the token labels and tokens to an entity interpreter;
with the entity interpreter, generating a DAG frame, wherein the entity interpreter implements an entity group alignment, wherein the entity group alignment associates a specified set of services with one or more customers from the set of new inbound messages, wherein entity interpreter implements a pronoun resolution operation;
with the DAG frame, outputting a structured information from a multiturn dialogue; and
with multitask learning framework:
receiving the DAG frame,
subject the DAG frame to a multi-task layer processing, wherein the multi-task layer processing infer a response to an incoming messages,
using the multi-task layer processing to predict various class label, wherein each prediction comes with a score that is associated with a confidence level in preparation for a set of messages that is constructed in a response, and
augmenting the DAG frame with class labels to enhance the structured annotated dialog session.