IP Library Granted Patent US 12,731,056
Granted Patent B2
US 12,731,056 · App. 18/119,737 · Granted Sep 8, 2026

AI generated creative content based on shared memories

Inventors: James R. Kennedy (Glendale, CA); Douglas A. Fidaleo (Canyon Country, CA); Anthony P. Dohi (South Pasadena, CA); Komath Naveen Kumar (Los Angeles, CA); Prutsdom Jiarathanakul (Los Angeles, CA); Benjamin Hwang (New York, NY); Michael Barron (Burbank, CA)
Assignee: Disney Enterprises, Inc.
G06N7/01G10L25/63
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,731,056
App. No.
18/119,737
Granted
Sep 8, 2026
Kind
B2
Abstract

A system includes a computing platform having a hardware processor and a memory storing software code, a memory data structure storing memory features for an artificial intelligence interactive character (AIIC), and a trained machine learning (ML) model. The software code is executed to elicit, using the AIIC, a reminiscence from a user, predict, using the trained ML model and the reminiscence, one or more user memory feature(s) of the reminiscence, identify, using the memory data structure, one or more of the memory features for the AIIC as corresponding to the user memory feature(s), and determine, using the user memory feature(s), a mood modifier for a creative composition. The software code is further executed to produce, based on the mood modifier and the corresponding one or more of the plurality of memory features for the AIIC, the creative composition, and provide the creative composition to the AIIC.

Claims (46)

1 . A system comprising:

a computing platform having a hardware processor and a system memory;

the system memory storing a software code, a memory data structure storing a plurality of memory features for an artificial intelligence interactive character (AIIC), and a trained machine learning (ML) model;

the hardware processor configured to execute the software code to:

elicit, using the AIIC, a reminiscence from a user;

predict, using the trained ML model and the reminiscence, at least one user memory feature of the reminiscence;

identify, using the memory data structure, one or more memory features of the plurality of memory features for the AIIC as corresponding to the at least one user memory feature, by:

applying a weighted similarity calculation across a plurality of dimensions of the at least one user memory feature and the plurality of memory features for the AIIC, to produce a weighted overall similarity score; and

selecting the one or more memory features based on the weighted overall similarity score;

determine, using the at least one user memory feature, a mood modifier for a creative composition;

produce, based on the mood modifier and the one or more memory features, the creative composition; and

provide the creative composition to the AIIC.

2 . The system of claim 1 , wherein the plurality of memory features stored by the memory data structure comprise at least one of human generated memory features or synthesized memory features for the AIIC.

3 . The system of claim 1 , wherein the reminiscence comprises an utterance by the user, and wherein determining the mood modifier of the creative composition is based on a prosody of the utterance.

4 . The system of claim 1 , wherein the hardware processor is further configured to execute the software code to:

control the AIIC to perform the creative composition.

5 . The system of claim 1 , wherein the AIIC is implemented as a digital character or a machine.

6 . The system of claim 1 , wherein the creative composition comprises music or a choreography.

7 . The system of claim 1 , wherein the creative composition comprises a poem or lyrics.

8 . The system of claim 7 , wherein the hardware processor is further configured to execute the software code to:

utilize a large language ML model to generate the poem or the lyrics.

9 . The system of claim 1 , wherein the memory data structure comprises one of an undirected cyclic graph or an acyclic graph.

10 . The system of claim 1 , wherein the predicted at least one user memory feature comprises a plurality of predicted user memory features, and wherein the hardware processor is further configured to execute the software code to:

represent the plurality of predicted user memory features as a knowledge graph having a same data structure as the memory data structure; and

wherein identifying the one or more memory features as corresponding to the at least one user memory feature further uses the knowledge graph.

11 . The system of claim 1 , wherein the plurality of dimensions comprise people, places, concepts, or emotions.

12 . A method for use by a system including a computing platform having a hardware processor and a system memory, the system memory storing a software code, a memory data structure storing a plurality of memory features for an artificial intelligence interactive character (AIIC), and a trained machine learning (ML) model, the method comprising:

eliciting, by the software code executed by the hardware processor and using the AIIC, a reminiscence from a user;

predicting, by the software code executed by the hardware processor and using the trained ML model and the reminiscence, at least one user memory feature of the reminiscence;

identifying, by the software code executed by the hardware processor and using the memory data structure, one or more memory features of the plurality of memory features for the AIIC as corresponding to the at least one user memory feature, by:

applying a weighted similarity calculation across a plurality of dimensions of the at least one user memory feature and the plurality of memory features for the AIIC, to produce a weighted overall similarity score; and

selecting the one or more memory features based on the weighted overall similarity score;

determining, by the software code executed by the hardware processor and using the at least one user memory feature, a mood modifier for a creative composition;

producing, by the software code executed by the hardware processor based on the mood modifier and the one or more memory features, the creative composition; and

providing, by the software code executed by the hardware processor, the creative composition to the AIIC.

13 . The method of claim 12 , wherein the plurality of memory features stored by the memory data structure comprise at least one of human generated memory features or synthesized memory features for the AIIC.

14 . The method of claim 12 , wherein the reminiscence comprises an utterance by the user, and wherein determining the mood modifier of the creative composition is based on a prosody of the utterance.

15 . The method of claim 12 , further comprising:

controlling the AIIC, by the software code executed by the hardware processor, to perform the creative composition.

16 . The method of claim 12 , wherein the AIIC is implemented as a digital character or a machine.

17 . The method of claim 12 , wherein the creative composition comprises a poem, lyrics, music or a choreography.

18 . The method of claim 17 , the method further comprising: utilizing, by the software code executed by the hardware processor, a large language ML model to generate the poem or the lyrics.

19 . The method of claim 12 , wherein the memory data structure comprises one of an undirected cyclic graph or an acyclic graph.

20 . The method of claim 12 , wherein the predicted at least one user memory feature comprises a plurality of predicted user memory features, the method further comprising:

representing, by the software code executed by the hardware processor, the plurality of predicted user memory features as a knowledge graph having a same data structure as the memory data structure; and

wherein identifying the one or more memory features as corresponding to the at least one user memory feature further uses the knowledge graph.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 9, 2023
From: KENNEDY, JAMES R.; FIDALEO, DOUGLAS A.; DOHI, ANTHONY P.; KUMAR, KOMATH NAVEEN; JIARATHANAKUL, PRUTSDOM; HWANG, BENJAMIN; BARRON, MICHAEL
To: DISNEY ENTERPRISES, INC.
Reel/Frame 062938/0295 →
Continuity (2)
Provisional Application 63380268 · Oct 20, 2022
Related Publication 20240135212A1 · Apr 25, 2024
References Cited (32)
US 9721551B2 · Silverstein · 2017 [cited by examiner]
US 10163429B2 · Silverstein · 2018 [cited by examiner]
US 10713289B1 · Mishra · 2020 [cited by examiner]
US 11024276B1 · Dabby · 2021 [cited by examiner]
US 11410653B1 · Mahar · 2022 [cited by examiner]
US 11442992B1 · Moon · 2022 [cited by examiner]
US 11461952B1 · Bosnak · 2022 [cited by examiner]
US 20150179157A1 · Chon · 2015 [cited by examiner]
US 20150286709A1 · Sathish · 2015 [cited by examiner]
US 20160148605A1 · Minamitaka · 2016 [cited by examiner]
US 20180190249A1 · Roblek · 2018 [cited by examiner]
US 20180322854A1 · Ackerman · 2018 [cited by examiner]
US 20190138923A1 · Jacobs · 2019 [cited by examiner]
US 20190224853A1 · Gewecke · 2019 [cited by examiner]
US 20190369957A1 · Spector · 2019 [cited by examiner]
US 20190370398A1 · He · 2019 [cited by examiner]
US 20200035209A1 · Luan · 2020 [cited by examiner]
US 20200105244A1 · Kuramitsu · 2020 [cited by examiner]
US 20200380940A1 · Abdallah · 2020 [cited by examiner]
US 20210149887A1 · Marchese · 2021 [cited by examiner]
US 20210312897A1 · Ackerman · 2021 [cited by examiner]
US 20210350776A1 · O'Brien · 2021 [cited by examiner]
US 20210350777A1 · Nordin · 2021 [cited by examiner]
US 20220014352A1 · Shillingford · 2022 [cited by examiner]
US 20220230628A1 · Zhu · 2022 [cited by examiner]
US 20220245352A1 · Nivarthi · 2022 [cited by examiner]
US 20220374130A1 · Pu · 2022 [cited by examiner]
US 20220406280A1 · Kishi · 2022 [cited by examiner]
US 20230229639A1 · McCreary · 2023 [cited by examiner]
US 20230260531A1 · Srivastava · 2023 [cited by examiner]
US 20230281467A1 · Eavy · 2023 [cited by examiner]
U.S. Appl. No. 18/119,716, filed Mar. 9, 2023. [cited by applicant]