- Number
- 12333257
- Published
- 2025-06-17
- Filed
- 2021-06-11
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Fidaleo; Douglas A.
- CPC
- G06N5/04; G06F40/174; G06F40/186; G06F40/216; G06F21/6245; G06F40/35
- Verdict
- Set aside data-security/privacy patent, applies to social agent context but core claim is security plumbing
- Source
- Google Patents · FreePatentsOnline
Abstract
A social agent system includes a computing platform having processing hardware and a system memory storing a social agent software code. The processing hardware is configured to execute the social agent software code to receive, from a client system, input data provided by a user of the client system when the user is interacting with the social agent system using the client system, and to select, using the input data, a dialogue template for responding to the user. The dialogue template includes one or more placeholder fields to be filled by the client system to create a personalized dialogue for responding to the user. The processing hardware is further configured to execute the social agent software code to deliver, to the client system, the dialogue template including the one or more placeholder fields to be filled by the client system to create the personalized dialogue for responding to the user.
Background
BACKGROUND (1) A characteristic feature of human social interaction is personalization. For example, when two people interact repeatedly in a similar manner, such as greeting one another, a variety of different expressions may be used despite the fact that a generic “hello” would be adequate in almost every instance. Instead, a human speaker may select expressions for use in an interaction with another person based on whether that person is a child, a teenager, or an adult, as well as based on their personal history of interactions with the other person. In order for a non-human social agent to engage in a realistic interaction with a user, it is desirable that the social agent also be capable of varying its form of expression in a personalized and seemingly natural way. (2) Personalizing the responsiveness of a social agent during an interaction with a particular user has typically required the system providing the social agent to acquire and store user data as part of an overall user profile including demographic and geographic details describing the user, as well as a history of previous interactions with the user. However, concerns regarding personal privacy, data security, and liability for data breaches make it increasingly advantageous, for users and system administrators alike, to provide users with the ability to restrict access to their personal user data while continuing to enable use of such data to personalize their interactions with a social agent.
Claims
1. A social agent system comprising: a computing platform including a processing hardware and a system memory; a social agent software code stored in the system memory, the social agent software code including a machine learning predictive model; the processing hardware configured to execute the social agent software code to: receive, from a client system storing a social agent client application of the social agent software code, input data provided by a user of the client system, the input data including a non-verbal vocalization by the user while the user is interacting with a social agent provided by the social agent system, wherein the social agent is embodied as one of a physical machine configured to be wirelessly controlled by the client system or a virtual character comprising an avatar or an animation rendered on a display of the client system, and wherein the social agent appears to watch and listen to the user in order to respond to the user based on the input data provided by the user; infer, using the machine learning predictive model and the input data, a goal of the user; select, using the input data and the goal of the user, a dialogue template for responding to the user, the dialogue template including at least one placeholder field configured to be filled by the client system to create a personalized dialogue, using the dialogue template, for responding to the user; deliver, to the client system, the dialogue template; wherein a user data used to fill the at least one placeholder field is inaccessible to the social agent system based on a user data access restriction selected by the user using the social agent client application; and wherein the social agent is configured to execute the personalized dialogue accompanied by a haptic effect activated by a haptic actuator of the client system or the physical machine. ||
6. A method for use by a social agent system including a computing platform having a processing hardware and a system memory storing a social agent software code, the social agent software code including a machine learning predictive model, the method comprising: receiving from a client system storing a social agent client application of the social agent software code, by the social agent software code executed by the processing hardware, input data provided by a user of the client system, the input data including a non-verbal vocalization by the user while the user is interacting with the social agent, wherein the social agent is embodied as one of a physical machine configured to be wirelessly controlled by the client system or a virtual character comprising an avatar or an animation rendered on a display of the client system, and wherein the social agent appears to watch and listen to the user in order to respond to the user based on the input data provided by the user; inferring, by the social agent software code executed by the processing hardware and using the machine learning predictive model and the input data, a goal of the user; selecting, by the social agent software code executed by the processing hardware and using the input data and the goal of the user, a dialogue template for responding to the user, the dialogue template including at least one placeholder field configured to be filled by the client system to create a personalized dialogue, using the dialogue template, for responding to the user; delivering to the client system, by the social agent software code executed by the processing hardware, the dialogue template; wherein a user data used to fill the at least one placeholder field is inaccessible to the social agent system based on a user data access restriction selected by the user using the social agent client application; and wherein the social agent is configured to execute the personalized dialogue accompanied by a haptic effect activated by a haptic actuator of the client system or the physical machine. ||
11. A computer-readable non-transitory medium having stored thereon a social agent client application, which when executed by a hardware processor of a client system, instantiates a method comprising: sending, to a social agent system including a social agent software code including a machine learning predictive model, input data provided by a user of the client system when the user is interacting with a social agent provided by the social agent system, the input data including a non-verbal vocalization by the user during the interacting, wherein the social agent is embodied as one of a physical machine configured to be wirelessly controlled by the client system or a virtual character comprising an avatar or an animation rendered on a display of the client system, and wherein the social agent appears to watch and listen to the user in order to respond to the user based on the input data provided by the user; receiving, from the social agent system, a dialogue template for responding to the user, the dialogue template including at least one placeholder field configured to be filled by the client system wherein the dialogue template is selected by the social agent software code using at least one of the input data or-a goal of the user inferred by the social agent software code using the machine learning predictive model based on the input data; identifying user data stored on the client system for filling the at least one placeholder field, the user data being inaccessible to the social agent system based on a user data access restriction selected by the user using the social agent client application; filling the at least one placeholder field using the user data to create a personalized dialogue, using the dialogue template, for responding to the user; and executing the personalized dialogue; wherein the personalized dialogue is accompanied by a haptic effect, and wherein executing the personalized dialogue comprises activating a haptic actuator of the client system or the physical machine.