US 11,928,430 B2
Detecting unrelated utterances in a chatbot system
Crystal C. Pan, Palo Alto, CA (US); Gautam Singaraju, Dublin, CA (US); Vishal Vishnoi, Redwood City, CA (US); and Srinivasa Phani Kumar Gadde, Belmont, CA (US)
Assigned to Oracle International Corporation, Redwood Shores, CA (US)
Filed by Oracle International Corporation, Redwood Shores, CA (US)
Filed on Sep. 10, 2020, as Appl. No. 17/017,076.
Claims priority of provisional application 62/899,700, filed on Sep. 12, 2019.
Prior Publication US 2021/0083994 A1, Mar. 18, 2021
Int. Cl. G06F 40/284 (2020.01); G06F 18/23213 (2023.01); G06F 18/24 (2023.01); G06F 40/216 (2020.01); G06F 40/35 (2020.01); G06N 20/00 (2019.01); H04L 51/02 (2022.01)
CPC G06F 40/284 (2020.01) [G06F 18/23213 (2023.01); G06F 18/24 (2023.01); G06F 40/216 (2020.01); G06F 40/35 (2020.01); G06N 20/00 (2019.01); H04L 51/02 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
a training system configured to perform operations comprising:
accessing training utterances associated with skill bots, the training utterances comprising respective training utterances associated with each skill bot of the skill bots, wherein each skill bot of the skill hots is configured to provide a dialog with a user;
generating training feature vectors from the training utterances, the training feature vectors comprising respective training feature vectors associated with each skill bot of the skill hots;
generating multiple set representations of the training feature vectors, wherein each set representation of the multiple set representations corresponds to a subset of the training feature vectors; and
configuring a classifier model to determine whether an utterance is related or unrelated to the skill bots; and
a master bot configured to perform operations comprising:
accessing an input utterance as a user input;
generating an input feature vector from the input utterance;
determining, using the classifier model and based on the input feature vector, that the input utterance is unrelated to the skill bots; and
in response to determining that the input utterance is unrelated to the skills bots, outputting an indication that the user input cannot be handled by the skill bots.