Interruption Response by an Artificial Intelligence Character

Number: 20260290345
Published: 2026-09-24
Filed: 2026-05-29
Assignee: Disney Enterprises, Inc.
Inventors: Kennedy; James R., Kantharaju; Reshmashree Bangalore, Paetzel-Pruesmann; Maike, Cumbal; Ronald, Kumar; Komath Naveen
CPC: G10L15/222; G06N3/006; G06N3/0455; G10L13/10; G10L15/1807
Verdict: Low Notable software
First reported: 2026-W39 (2026-09-25)
Source: Google Patents · FreePatentsOnline

The keeper's note

Gives a conversational AI character (think interactive droids/animatronics) the ability to notice when it's been interrupted mid-sentence and pick a smart way to respond instead of talking over people.

Abstract

There is provided a method that includes detecting, during a conversational turn by a first AI character in interaction with one of a human or a second AI character, sound produced by the human or the second AI character, classifying, using an ML model trained to detect an interruption to a conversation, the sound as an interruption to the interaction, identifying a response strategy for continuing the interaction based on one or more of (a) context of the interaction with the at least one of the human speaker or the second AI character, (b) a predicted importance of the conversational turn, or (c) a predicted importance of the interruption, and executing the response strategy by controlling playback of previously generated speech output of the first AI character based on a current playback position when the interruption is detected, controlling playback includes resuming, modifying, or terminating the previously generated speech output.

Background

BACKGROUND

A characteristic feature of most human interactions is spontaneity, including how individuals in conversation react to interruptions to their speech. In order for a non-human social agent, such as one embodied as an artificial intelligence (AI) interactive character, for example, to engage in conversation in a naturalistic human-like way, it is desirable to provide the non-human social agent with the ability to respond appropriately when interrupted.

Conventional solutions for providing speech for a non-human social agent may be unable to detect an interruption to that speech, or lack sophistication in their response when one is detected. For example, when the interruption goes undetected, it is simply ignored and the social agent continues its speech, i.e., “talking over” the interruption. Alternatively, a conventional response to an interruption to speech by a non-human social agent that is detected includes stopping the speech entirely when the interruption occurs. These responses may be appropriate in certain circumstances but not others. Unfortunately, both of those conversational scenarios may result in an awkward and unnatural experience for a human interacting with the social agent, and particularly in the case in which the interruption goes undetected and the social agent talks over the interruption, which may undesirably make the human feel ignored. Consequently, there is a need in the art for a solution enabling a non-human social agent to

Claims

21. A method for use by a system including a hardware processor and a system memory, the system memory storing a software code and a machine learning (ML) model trained to detect an interruption to a conversation by a participant in the conversation, the method comprising: detecting, by the software code executed by the hardware processor, during a conversational turn by a first artificial intelligence (AI) character in an interaction with at least one of a human or a second AI character, sound produced by the at least one of the human or the second AI character; classifying, by the software code executed by the hardware processor and using the ML model, the sound as an interruption to the interaction; identifying, by the software code executed by the hardware processor and using an interruption response strategy identification engine, a response strategy for continuing the interaction based on one or more of: (a) context of the interaction with the at least one of the human speaker or the second AI character, (b) a predicted importance of the conversational turn, or (c) a predicted importance of the interruption; and executing the response strategy by controlling playback of previously generated speech output of the first AI character based on a current playback position when the interruption is detected, wherein controlling playback comprises resuming, modifying, or terminating the previously generated speech output. || 34. A system comprising: a hardware processor; a system memory storing a software code and a machine learning (ML) model trained to detect an interruption to a conversation by a participant in the conversation; and the hardware processor configured to execute the software code to: detect during a conversational turn by a first artificial intelligence (AI) character in an interaction with at least one of a human or a second AI character, sound produced by the at least one of the human or the second AI character; classify, using the ML model, the sound as an interruption to the interaction; identify, using an interruption response strategy identification engine, a response strategy for continuing the interaction based on one or more of: (a) context of the interaction with the at least one of the human speaker or the second AI character, (b) a predicted importance of the conversational turn, or (c) a predicted importance of the interruption; and wherein the response strategy is executed by controlling playback of previously generated speech output of the first AI character based on a current playback position when the interruption is detected, wherein controlling playback comprises resuming, modifying, or terminating the previously generated speech output.