AI Generated Creative Content Based on Shared Memories

Number: 20260330272
Published: 2026-10-22
Filed: 2026-06-29
Assignee: Disney Enterprises, Inc.
Inventors: Kennedy; James R., Fidaleo; Douglas A., Dohi; Anthony P., Kumar; Komath Naveen, Jiarathanakul; Prutsdom, Hwang; Benjamin, Barron; Michael
CPC: G06N7/01; G10L25/63
Verdict: Low Notable software
First reported: 2026-W43 (2026-10-23)
Source: Google Patents · FreePatentsOnline

The keeper's note

The same AI-character memory system turned toward storytelling: it pulls a guest's shared memory and generates new creative content, like a song or tale, out of it.

Abstract

There is provided a system including a computing platform having a hardware processor and a system memory storing a software code and a memory data structure storing memory features for an artificial intelligence interactive character (AIIC). The hardware processor is configured to execute the software code to elicit, using the AIIC, a reminiscence from a user, predict, using a trained machine learning model and the reminiscence, at least one user memory feature, identify, using the memory data structure, one or more of the memory features for the AIIC based on a similarity between the predicted at least one user memory feature and the memory features for the AIIC, determine a mood modifier based on emotion information of the identified one or more of the memory features for the AIIC, and generate a creative composition for performance by the AIIC based on the mood modifier.

Background

BACKGROUND

Creative compositions, such as instrumental and lyrical music for example, are closely associated with human memories. Such memories are often emotional memories (i.e., how a person emotionally reacted while hearing particular music) or intellectual (i.e., where a person was or who they were with while hearing particular music). This close association of music with memories often triggers or evokes pleasant memories of past emotions, people, and places when a piece of music is played.

There is evidence in the psychology literature that sharing memories creates a sense of relationship closeness between individuals. The emotional closeness engendered by the sharing of memories is often enhanced when these memories are relatable between the individuals, i.e., the individuals seem to have similar experiences or interpretations of those experiences. In the context of music, this closeness generally is felt when the lyrics, harmony, rhythm or melody performed by an artist trigger an emotional response or evoke memories in a listener.

Artificial intelligence (AI) is now being used to create original music. However, until now, AI generated music has had only crude ability to mimic traditionally composed music and may be off-putting rather than enjoyable. Thus, there exists a need in the art for systems and methods for generating music using AI in a manner that is responsive to the memories of its listeners.

Claims

1. A system comprising: a computing platform having a hardware processor and a system memory; the system memory storing a software code and a memory data structure storing a plurality of memory features for an artificial intelligence interactive character (AIIC); the hardware processor configured to execute the software code to: elicit, using the AIIC, a reminiscence from a user; predict, using a trained machine learning (ML) model and the reminiscence, at least one user memory feature; identify, using the memory data structure, one or more of the plurality of memory features for the AIIC based on a similarity between the predicted at least one user memory feature and the plurality of memory features for the AIIC; determine a mood modifier based on emotion information of the identified one or more of the plurality of memory features for the AIIC; and generate a creative composition for performance by the AIIC based on the mood modifier. || 13. A method comprising: eliciting, using an artificial intelligence interactive character (AIIC), a reminiscence from a user; predicting, using a trained machine learning (ML) model and the reminiscence, at least one user memory feature; identifying, using a memory data structure storing a plurality of memory features for the AIIC, one or more of the plurality of memory features for the AIIC based on a similarity between the at least one user memory feature and the plurality of memory features for the AIIC; determining a mood modifier based on emotion information of the identified one or more of the plurality of memory features for the AIIC; and generating a creative composition for performance by the AIIC based on the mood modifier. || 19. A non-transitory computer-readable medium storing software code that, when executed by a hardware processor of a computing platform, causes the hardware processor to: elicit, using an artificial intelligence interactive character (AIIC), a reminiscence from a user; predict, using a trained machine learning (ML) model and the reminiscence, at least one user memory feature; identify, using a memory data structure storing a plurality of memory features for the AIIC, one or more of the plurality of memory features for the AIIC based on a similarity between the at least one user memory feature and the plurality of memory features for the AIIC; determine a mood modifier based on emotion information of the identified one or more of the plurality of memory features for the AIIC; and generate a creative composition for performance by the AIIC based on the mood modifier.