- Number
- 11748558
- Published
- 2023-09-05
- Filed
- 2020-10-27
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Tiwari; Sanchita et al.
- CPC
- G06F40/20; G06F40/30; G06F40/35; G06N3/0442; G06N3/045; G06N3/08; G06N3/09; G06V10/82; G06V40/174; G06V40/20
- Verdict
- Low Notable software
- Source
- Google Patents · FreePatentsOnline
The keeper's note
Multi-persona interactive social agent AI (granted).
Abstract
A system providing a multi-persona social agent includes a computing platform having a hardware processor, a system memory storing a software code, and multiple neural network (NN) based predictive models accessible by the software code. The hardware processor executes the software code to receive input data corresponding to an interaction with a user, determine a generic expression for use in the interaction, and identify one of the character personas as a persona to be assumed by the multi-persona social agent. The software code also generates, using the generic expression and one of the NN based predictive models corresponding to the persona to be assumed by the multi-persona social agent, a sentiment driven personified response for the interaction with the user based on a vocabulary, phrases, and one or more syntax rules idiosyncratic to the persona to be assumed, and renders the sentiment driven personified response using the multi-persona social agent.
Background
BACKGROUND (1) Advances in artificial intelligence have led to the development of a variety of devices providing one of several dialogue-based interfaces, such as GOOGLE HOME™, AMAZON ALEXA™, and others. However, the dialogue interfaces provided by these and similar devices each typically project a single synthesized persona that tends to lack character and naturalness. Moreover, these devices and the dialog interfaces provided by the conventional art are typically transactional, and indicate to a user that they are listening for a communication from the user by responding to an affirmative request by the user. (2) In contrast to conventional transactional device interactions, natural communications between human beings are more nuanced and varied, and include the use of non-verbal, as well as verbal expressions, some of which may be idiosyncratic to a particular individual's personality. Consequently, there is a need in the art for an interactive social agent that is capable of assuming a variety of different personas each having unique personality characteristics and patterns of expression.
Claims
1. A system providing a multi-persona social agent, the system comprising: a computing platform including a hardware processor and a system memory; a software code stored in the system memory; a plurality of neural network (NN) based predictive models accessible by the software code, each of the plurality of NN based predictive models being trained to predict an interactive behavior of a respective one of a plurality of character personas; the hardware processor configured to execute the software code to: receive an input data corresponding to an interaction with a user; determine, in response to receiving the input data, a generic expression for use in the interaction with the user; identify, based on a location of the multi-persona social agent, one of the plurality of character personas as a persona to be assumed by the multi-persona social agent; generate, using the generic expression and a respective one of the plurality of NN based predictive models corresponding to the persona to be assumed by the multi-persona social agent, a sentiment driven personified response for the interaction with the user based on a vocabulary, a plurality of phrases, and at least one syntax rule that are idiosyncratic to the persona to be assumed by the multi-persona social agent; and render the sentiment driven personified response using the multi-persona social agent. ||
7. A method for use by a system providing a multi-persona social agent, the system including a computing platform having a hardware processor, a system memory storing a software code, and a plurality of neural network (NN) based predictive models accessible by the software code, each of the plurality of NN based predictive models being trained to predict an interactive behavior of a respective one of a plurality of character personas, the method comprising: receiving, by the software code executed by the hardware processor, an input data corresponding to an interaction with a user; determining, by the software code executed by the hardware processor in response to receiving the input data, a generic expression for use in the interaction with the user; identifying, by the software code executed by the hardware processor, based on a location of the multi-persona social agent, one of the plurality of character personas as a persona to be assumed by the multi-persona social agent; generating, by the software code executed by the hardware processor and using the generic expression and a respective one of the plurality of NN based predictive models corresponding to the persona to be assumed by the multi-persona social agent, a sentiment driven personified response for the interaction with the user based on a vocabulary, a plurality of phrases, and at least one syntax rule that are idiosyncratic to the persona to be assumed by the multi-persona social agent; and rendering, by the software code executed by the hardware processor, the sentiment driven personified response using the multi-persona social agent. ||
17. A multi-persona robot comprising: a computing platform including a hardware processor and a system memory; a software code stored in the system memory; a plurality of neural network (NN) based predictive models accessible by the software code, each of the plurality of NN based predictive models being trained to predict an interactive behavior of a respective one of a plurality of character personas; the hardware processor configured to execute the software code to: receive an input data corresponding to an interaction with a user; determine, in response to receiving the input data, a generic expression for use in the interaction with the user; identify, based on a location of the robot, one of the plurality of character personas as a persona to be assumed by the multi-persona robot; generate, using the generic expression and a respective one of the plurality of NN based predictive models corresponding to the persona to be assumed by the multi-persona robot, a sentiment driven personified response for the interaction with the user based on a vocabulary, a plurality of phrases, and at least one syntax rule that are idiosyncratic to the persona to be assumed by the multi-persona robot; and render the sentiment driven personified response to the user.