- Number
- 20250252341
- Published
- 2025-08-07
- Filed
- 2024-02-05
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Paetzel-Pruesmann; Maike et al.
- CPC
- G06N5/022; G06N20/00; G06N3/006
- Verdict
- Low Notable software
- Source
- Google Patents · FreePatentsOnline
The keeper's note
Multi-sourced ML AI-character training and development technique.
Abstract
A system includes a hardware processor configured to execute software code to receive interaction data identifying an action and personality profiles corresponding respectively to multiple participant cohorts in the action, generate, using the interaction data, an interaction graph of behaviors of the participant cohorts in the action, simulate, using a behavior model, participation of each of the participant cohorts in the action to provide a predicted interaction graph, and compare the predicted and generated interaction graphs to identify a similarity score for the predicted interaction graph relative to the generated interaction graph. When the similarity score satisfies a similarity criterion, the software code is executed to train, using the behavior model, an artificial intelligence character for interactions. When the similarity score fails to satisfy the similarity criterion, the software code is executed to modify the behavior model based on one or more differences between the predicted and generated interaction graphs.
Background
BACKGROUND
Advances in artificial intelligence (AI) have led to the development of a variety of systems providing AI characters that simulate social agents. However, composing dialogue for an AI character requires an understanding of not only what the AI character should say or do, but also anticipating how one or more human users will respond during a particular interaction. Given the variability of language, personality profiles, demographics, and the context in which an interaction may take place, generating realistic interactive behavior by an AI character during a single interaction may require the processing of hundreds or thousands of data points. As a result, it is impossible for human being to verify all of the possible interaction scenarios without reliance on one or more sophisticated computational models. Consequently, there is a need in the art for a multi-sourced machine learning model-based solution for AI character training and development.
Claims
1. A system comprising: a hardware processor and a memory storing a software code; the hardware processor configured to execute the software code to: receive interaction data, the interaction data identifying an action and a plurality of personality profiles corresponding respectively to a plurality of participant cohorts in the action; generate, using the interaction data, an interaction graph of behaviors of the plurality of participant cohorts in the action; simulate, using a behavior model, participation of each of the plurality of participant cohorts in the action to provide a predicted interaction graph for the plurality of participant cohorts; compare the predicted interaction graph and the generated interaction graph to identify a similarity score for the predicted interaction graph relative to the generated interaction graph; when the similarity score satisfies a similarity criterion, train, using the behavior model, an artificial intelligence (AI) character for interactions; and when the similarity score fails to satisfy the similarity criterion, modify the behavior model based on one or more differences between the predicted interaction graph and the generated interaction graph. ||
8. A method for use by a system having hardware processor and a memory storing a software code, the method comprising: receiving, by the software code executed by the hardware processor, interaction data, the interaction data identifying an action and a plurality of personality profiles corresponding respectively to a plurality of participant cohorts in the action; generating, by the software code executed by the hardware processor and using the interaction data, an interaction graph of behaviors of the plurality of participant cohorts in the action; simulating, by the software code executed by the hardware processor and using a behavior model, participation of each of the plurality of participant cohorts in the action to provide a predicted interaction graph for the plurality of participant cohorts; comparing, by the software code executed by the hardware processor, the predicted interaction graph and the generated interaction graph to identify a similarity score for the predicted interaction graph relative to the generated interaction graph; when the similarity score satisfies a similarity criterion, training, by the software code executed by the hardware processor and using the behavior model, an artificial intelligence (AI) character for interactions; and when the similarity score fails to satisfy the similarity criterion, modifying the behavior model, by the software code executed by the hardware processor based on one or more differences between the predicted interaction graph and the generated interaction graph. ||
15. A computer-readable non-transitory medium having stored thereon instructions, which when executed by a hardware processor, instantiate a method comprising: receiving interaction data, the interaction data identifying an action and a plurality of personality profiles corresponding respectively to a plurality of participant cohorts in the action; generating, using the interaction data, an interaction graph of behaviors of the plurality of participant cohorts in the action; simulating, using a behavior model, participation of each of the plurality of participant cohorts in the action to provide a predicted interaction graph for the plurality of participant cohorts; comparing the predicted interaction graph and the generated interaction graph to identify a similarity score for the predicted interaction graph relative to the generated interaction graph; when the similarity score satisfies a similarity criterion, training, using the behavior model, an artificial intelligence (AI) character for interactions; when the similarity score fails to satisfy the similarity criterion, modifying the behavior model based on one or more differences between the predicted interaction graph and the generated interaction graph.