- Number
- 12443822
- Published
- 2025-10-14
- Filed
- 2021-06-10
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Scanlon; Raymond J. et al.
- CPC
- G06F40/35; G06N3/006; G06T13/40; G06T19/006; G06T19/20
- Verdict
- Low Notable software
- Source
- Google Patents · FreePatentsOnline
The keeper's note
Context-based interactive social-agent (character) interaction technique (granted).
Abstract
A system for performing context-based management of social agent interactions includes processing hardware and a memory storing a software code. The processing hardware executes the software code to detect the presence of an interaction partner, identify a present state of an interaction with the interaction partner, and to determine, based on the present state, a first score for each of multiple interactive expressions for use in initiating or continuing the interaction. The processing hardware further executes the software code to predict a state change of the interaction based on each of the interactive expressions to provide multiple predicted state changes corresponding respectively to the multiple interactive expressions, to determine, using the predicted state changes, a second score for each of the interactive expressions, and to select, using the first scores and the second scores, at least one of the interactive expressions to initiate or continue the interaction.
Background
BACKGROUND (1) Advances in artificial intelligence have led to the development of a variety of devices providing dialogue-based interfaces that simulate social agents. However, conventional dialogue interfaces typically project a single synthesized persona that tends to lack character and naturalness. In addition, 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 social agent interactions, natural communications between human beings are more nuanced, varied, and dynamic. That is to say, typical shortcomings of conventional social agents include their inability to engage in natural, fluid interactions, their inability to process more than one statement or question concurrently, and their inability to repair a flaw in an interaction, such as a miscommunication or other conversation breakdown. Moreover, although existing social agents offer some degree of user personalization, for example tailoring responses to an individual user's characteristics or preferences, that personalization remains limited by their fundamentally transactional design, which makes it unnecessary for conventional social agents to remember more than a limited set of predefined keywords, such as user names and basic user preferences.
Claims
1. A system for performing context-based social agent interactions with human beings, the system comprising: a processing hardware; a memory storing a software code; a social agent instantiated as a robot, a virtual character, or a tabletop or wall-mounted device, the social agent comprising an output unit configured to effectuate an interactive expression of the social agent, the output unit comprising a display, a speaker, a mechanical actuator, or a haptic actuator; at least one detector comprising at least one sensor or at least one microphone; the processing hardware configured to execute the software code to: detect, using the at least one detector, presence of a human being; identify a present state of an interaction with the human being based on a first expression of the human being; determine, based on scoring criteria and the present state, a first score for each of a plurality of interactive expressions for one of initiating or continuing the interaction to provide a plurality of first scores corresponding respectively to the plurality of interactive expressions, each of the plurality of interactive expressions being potential responses to be provided by the social agent in response to the first expression of the human being; predict a state change of the interaction based on use of each of the plurality of interactive expressions in response to the first expression of the human being to determine a plurality of predicted state changes corresponding respectively to the plurality of interactive expressions; determine, using the plurality of predicted state changes, a second score for each of the plurality of interactive expressions to determine a plurality of second scores corresponding respectively to the plurality of interactive expressions, wherein the second score is determined based on a desirability of a predicted state change resulting from use of each of the plurality of interactive expressions in response to the first expression of the human being; and select, using the plurality of first scores and the plurality of second scores, at least one of the plurality of interactive expressions to initiate or continue the interaction; and initiate or continue the interaction with the human being by providing, using the output unit of the social agent, the selected at least one of the plurality of interactive expressions to the human being. ||
8. A method of performing context-based social agent interactions with human beings by a system having a processing hardware, and a memory storing a software code, a social agent instantiated as a robot, a virtual character, or a tabletop or wall-mounted device, the social agent comprising an output unit configured to effectuate an interactive expression of the social agent, the output unit comprising a display, a speaker, a mechanical actuator, or a haptic actuator, and at least one detector comprising at least one sensor or at least one microphone, the method comprising: detecting, by the software code executed by the processing hardware and using the at least one detector, presence of a human being; identifying, by the software code executed by the processing hardware, a present state of an interaction with the human being based on a first expression of the human being; determining, by the software code executed by the processing hardware, based on scoring criteria and the present state, a first score for each of a plurality of interactive expressions for one of initiating or continuing the interaction to provide a plurality of first scores corresponding respectively to the plurality of interactive expressions, each of the plurality of interactive expressions being potential responses to be provided by the social agent in response to the first expression of the human being; predicting, by the software code executed by the processing hardware, a state change of the interaction based on use of each of the plurality of interactive expressions in response to the first expression of the human being to determine a plurality of predicted state changes corresponding respectively to the plurality of interactive expressions; determining, by the software code executed by the processing hardware and using the plurality of predicted state changes, a second score for each of the plurality of interactive expressions to determine a plurality of second scores corresponding respectively to the plurality of interactive expressions, wherein the second score is determined based on a desirability of a predicted state change resulting from use of each of the plurality of interactive expression s in response to the first expression of the human being; selecting, by the software code executed by the processing hardware and using the plurality of first scores and the plurality of second scores, at least one of the plurality of interactive expressions to initiate or continue the interaction; and initiating or continuing the interaction with the human being, by the software code executed by the processing hardware, by providing, using the output unit of the social agent, the selected at least one of the plurality of interactive expressions to the human being.