- Number
- 20200184306
- Published
- 2020-06-11
- Filed
- 2018-12-05
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Buhmann; Jakob, Fidaleo; Douglas A., Shvo; Maayan, Kapadia; Mubbasir, Lehman; Jill Fain, Wulfeck; Sarah K., Gibbens; Rylan, Poulakos; Steven, Wiseman; John
- CPC
- G06N3/006; G06F3/011
- Verdict
- Low Notable software
- Source
- Google Patents · FreePatentsOnline
The keeper's note
ML-driven affect behavior for a virtual/interactive agent.
Abstract
A system for simulating human-like affect-driven behavior includes a hardware processor and a system memory storing software code providing a virtual agent. The hardware processor executes the software code to identify a character assumed by the virtual agent and having a personality, a target state of motivational fulfillment, a baseline mood, and emotions. The software code identifies current physical and motivational fulfillment states, and currently active emotions of the character, and determines a current mood of the character based on the baseline mood and the currently active emotions. The software code further detects an experience by the character and plans multiple behaviors including a first behavior based on the experience and the current physical state, the second behavior based on the experience, the personality, the current mood, and the currently active emotions, and a third behavior based on the target and current states of motivational fulfillment.
Background
BACKGROUND
Providing a virtual social agent capable of engaging in a human-like interaction with a human user is a challenging task, at least in part because human interactions occur around a wide range of contexts. Conventional examples of interactive agents include conversational agents provided on smart electronic devices, which are able to sustain question-and-answer type conversations. However, because those conventional conversational agents are designed for the very specific function of responding to questions or requests, they omit many of the properties that a real human would offer in an interaction that make that interaction not only informative but also enjoyable or entertaining. For example, an interaction between two humans may be influenced or shaped by the personalities of those human participants, as well as the history or storyline of their previous interactions. Thus, there remains a need in the art for a virtual agent capable of engaging in an extended interaction with a human user that simulates human-like affect-driven behavior.SUMMARY
There are provided systems and methods for simulating human-like affect-driven behavior by a virtual agent, substantially as shown in and/or described in connection with at least one of the figures, and as set forth more completely in the claims.
Claims
1. A system for simulating human-like affect-driven behavior, the system comprising: a computing platform including a hardware processor and a system memory; a software code stored in the system memory, the software code configured to provide a virtual agent; wherein the hardware processor is configured to execute the software code to control the virtual agent to: identify a character assumed by the virtual agent, the character having a personality, a target state of motivational fulfillment, a baseline mood, and a plurality of emotions; identify a current physical state, a current state of motivational fulfillment, and currently active emotions of the character; determine a current mood of the character based on the baseline mood and the currently active emotions; receive an input corresponding to one of an interaction and an event experienced by the character; and plan a plurality of behaviors including at least a first behavior, a second behavior, and a third behavior for the character, the first behavior being based on the input and the current physical state of the character, the second behavior being based on the input, the personality, the current mood, and the currently active emotions of the character, and the third behavior being based on a difference between the target state of motivational fulfillment and the current state of motivational fulfillment.
8. A method for use by a system for simulating human-like affect-driven behavior, the system comprising a computing platform having a hardware processor and a system memory storing a software code configured to provide a virtual agent, the method comprising: identifying, by the software code executed by the hardware processor, a character assumed by the virtual agent, the character having a personality, a target state of motivational fulfillment, a baseline mood, and a plurality of emotions; identifying, by the software code executed by the hardware processor, a current physical state, a current state of motivational fulfillment and currently active emotions of the character; determining, by the software code executed by the hardware processor, a current mood of the character based on the baseline mood and the currently active emotions; receiving, by the software code executed by the hardware processor, an input corresponding to one of an interaction and an event experienced by the character; and planning, by the software code executed by the hardware processor, a plurality of behaviors including at least a first behavior, a second behavior, and a third behavior for the character, the first behavior being based on the input and the current physical state of the character, the second behavior being based on the input, the personality, the current mood, and the currently active emotions of the character, and the third behavior being based on a difference between the target state of motivational fulfillment and the current state of motivational fulfillment.
15. A computer-readable non-transitory medium having stored thereon instructions, which when executed by a hardware processor, instantiate a method comprising: identifying a character assumed by the virtual agent, the character having a personality, a target state of motivational fulfillment, a baseline mood, and a plurality of emotions; identifying a current physical state, a current state of motivational fulfillment, and currently active emotions of the character; determining a current mood of the character based on the baseline mood and the currently active emotions; receiving an input corresponding to one of an interaction and an event experienced by the character; and planning a plurality of behaviors including at least a first behavior, a second behavior, and a third behavior for the character, the first behavior being based on the input and the current physical state of the character, the second behavior being based on the input, the personality, the current mood, and the currently active emotions of the character, and the third behavior being based on a difference between the target state of motivational fulfillment and the current state of motivational fulfillment.