Disney patents method for training AI characters to speak in character


Disney describes a system that trains artificial intelligence models to create digital characters that can hold conversations. The process involves multiple steps to ensure the character stays true to its specific personality and avoids saying incorrect or inappropriate things.
In the filing’s own words
A system includes a hardware processor configured to execute a machine learning (ML) model training pipeline to train an ML model using data relevant to a world of a digital persona to provide a dialogue model, generate, using the dialogue model, first conversational outputs, train the dialogue model, based on the first conversational outputs, to avoid hallucinations and/or undesirable expressions to provide a guardrailed dialogue model, generate, using the guardrailed dialogue model, second conversational outputs, train the guardrailed dialogue model, based on the second conversational outputs and persona data identifying interaction characteristics of the digital persona to provide a persona-specific model, generate, using the persona-specific model, a response to a scripted question, determine a quality score for the response, and further train the persona-specific model or validate the persona-specific model for human interaction, depending upon whether the quality score fails to satisfy or satisfies a quality criterion.
What exactly they claim (claim 1)
1. A system comprising: a hardware processor, and a memory storing a machine learning (ML) model training pipeline; the hardware processor configured to execute the ML model training pipeline to: train an ML model using a dataset including data relevant to a world of a predetermined digital persona, to provide a dialogue model; generate, using the dialogue model, a plurality of first conversational outputs; train the dialogue model, based on the plurality of first conversational outputs, to avoid at least one of hallucinations or undesirable expressions, to provide a guardrailed dialogue model; generate, using the guardrailed dialogue model, a plurality of second conversational outputs; train the guardrailed dialogue model, based on the plurality of second conversational outputs and persona data identifying interaction characteristics of the predetermined digital persona, to provide a persona-specific model; generate, using the persona-specific model, a response to a scripted question; determine a quality score for the response; further train the persona-specific model, when the quality score fails to satisfy a quality criterion, or validate the persona-specific model for human interaction when the quality score satisfies the quality criterion.
Facts
- Company
- Disney (Disney Enterprises, Inc.)
- Official title
- Machine learning model-based generation of digital personas
- Patent number
- US12792969B2
- Application number
- 18650796
- Filed
- Apr 30, 2024
- Granted
- Nov 10, 2026
- Inventors
- 1
- Claims
- 20
Classified under
G06N 20/00 Physics & computingMore from Disney in AI & software
- Disney patents AI character that creates art from your shared memories Sep 8, 2026
- Disney patents AI that lets actors speak in a character's voice Nov 3, 2026
- Disney patents video compression using generative models to cut file sizes Sep 3, 2026
- Disney patents AI characters that create art from shared memories Oct 22, 2026
- Disney patents tech to sync translated speech with body gestures Sep 17, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.