Ambience-Aware Digital Assistant Response Generation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current digital assistants lack the ability to consider the privacy and sensitivity of content and the user's ambience when generating responses, leading to undesirable experiences, such as embarrassment in public spaces or disruption during physical activities.

Innovation Solution

A digital assistant system that determines the ambience and sensitivity of content using parameters like noise, location, and user state to generate appropriate responses, allowing user interaction for confirming whether to reveal sensitive information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the digital assistant recites all responses without filtering, then the response delivery is fast and straightforward, but the user experiences embarrassment in public spaces or disruption during physical activities

Engineering Contradiction:
Improveresponse deliveryVSAvoiduser embarrassment and disruption
Core Design Contradiction:
Ease of operationVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary analysis of the response content and ambience before delivering the response. The ambience awareness module analyzes the current environment and the response content analysis module evaluates the response content in advance to determine appropriate delivery methods, preventing harmful outcomes before they occur

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary processing layer between the NLG system and the response delivery mechanism. This intermediary includes the ambience awareness module and response content analysis module that mediate between the generated response and its delivery, selecting appropriate delivery methods based on analyzed parameters

Inventive Principle:
Principle #24Intermediary (Mediator)

2Object-affected harmful factors

If the digital assistant analyzes privacy and sensitivity of content and determines ambience before generating responses, then the user experience is improved by avoiding embarrassment and disruptions, but the system complexity increases

Engineering Contradiction:
Improveuser embarrassment and disruptionVSAvoidsystem complexity
Core Design Contradiction:
Object-affected harmful factorsVSDevice complexity

Solution Approach 1:

The system is segmented into distinct functional modules: ambience awareness module that analyzes environment, response content analysis module that evaluates content privacy and sensitivity, and a response delivery mechanism that selects appropriate delivery methods. This segmentation allows each module to handle specific tasks independently

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The digital assistant system is enhanced with multi-functional capabilities that allow it to perform both traditional voice assistant functions and new ambience-aware response analysis functions using the same core architecture, reducing the need for entirely separate systems

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS11887591B2Methods and systems for enabling a digital assistant to generate an ambient aware response
Publication Date: 2024.01.30 SAMSUNG ELECTRONICS CO LTD
  • US11887591B2 patent drawing
  • US11887591B2 patent drawing
  • US11887591B2 patent drawing

AI summary

Embodiments herein disclose methods and systems for providing a digital assistant in a device, which can generate responses to commands from a user based on ambience of the user. On receiving a command from the user of the device to perform an action, content stored in the device can be extracted. The embodiments include determining degree of privacy and sensitivity of the content. The embodiments include determining ambience of the user based on ambient noise, location of the device, presence of other humans, emotional state of the user, application parameters, user activity, and so on. The embodiments include generating a response and revealing the response based on the determined ambience and the degree of privacy and sensitivity of the extracted content. The embodiments include facilitating dialog with the user for generating appropriate responses based on the ambience of the user.