Capacitive Face-Proximity Detection for Faster Assistant Invocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated assistants require explicit user interface inputs for invocation, which can cause delays and failures due to environmental conditions or user limitations, such as noise or wearing gloves, leading to inefficient interactions.
Innovation Solution
Utilizing capacitive touch sensors to detect non-tactile inputs, like a user holding a device near their face, to implicitly invoke automated assistants, leveraging machine learning models to distinguish between tactile and non-tactile inputs and reduce the need for explicit invocation phrases.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If explicit user interface input is required to invoke automated assistant, then user privacy and resource consumption are controlled, but interaction duration is extended and responsiveness is reduced
Solution Approach 1:
The system performs preliminary detection of facial features near the display using capacitive sensors before the user actually intends to interact. By detecting the presence of facial features (mouth, nose, eyes) in proximity to the display area, the system prepares for potential interaction in advance, reducing the time required when the user actually wants to invoke the assistant.
Solution Approach 2:
The system dynamically adjusts the invocation mechanism based on real-time detection. When facial features are detected near the display, the system transitions from requiring explicit invocation (static state) to enabling implicit invocation through facial gestures (dynamic state). This dynamic adaptation allows the system to optimize between privacy control and responsiveness based on current context.
2Reliability
If explicit user interface input is required to invoke automated assistant, then false positive invocations are reduced, but invocation reliability fails in noisy environments or when user dexterity is limited
Solution Approach 1:
The capacitive touch sensor array serves as an intermediary between the user and the automated assistant invocation. Instead of directly detecting voice commands (which fail in noisy environments) or touch inputs (which fail when wearing gloves), the system uses capacitive sensors to detect facial features near the display as an intermediate signal that reliably indicates invocation intent across various environmental conditions.
Solution Approach 2:
The system changes the detection parameter from acoustic (voice recognition) or tactile (touch input) to capacitive (electrical field detection near the display). This parameter change allows the system to detect facial features through the display surface without requiring direct contact or clear audio, thereby maintaining invocation reliability across diverse environmental conditions including noise, gloves, and face masks.
3Adaptability or versatility
If capacitive touch sensors are used for both tactile and non-tactile input detection, then invocation versatility is improved, but input detection precision may be compromised
Solution Approach 1:
The system segments the capacitive sensor array into different functional zones: tactile input areas for direct touch interaction and facial detection areas for non-tactile facial feature detection. By spatially segmenting the sensor array and applying different detection algorithms to different zones, the system maintains high precision for both tactile and non-tactile input modes simultaneously.
Solution Approach 2:
The system applies different detection characteristics to different regions of the capacitive sensor array. Facial feature detection is performed with specific sensitivity thresholds and pattern recognition algorithms optimized for facial geometries, while tactile input detection uses different thresholds for direct contact. This local quality differentiation ensures that each input mode maintains high detection precision despite using the same underlying sensor technology.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables efficient and reliable invocation of automated assistants without explicit user input, reducing interaction delays and improving responsiveness in various environments.
Implementation Method 1
The touch display interface can include an array of capacitive touch sensors that can operate by being responsive to static charge and/or changes in charge of nearby surfaces.
Implementation Method 2
capacitive touch sensors that can operate by being responsive to static charge and/or changes in charge of nearby surfaces
Data Source
AI summary
Implementations set forth herein relate to controlling invocation of an automated assistant according to whether a capacitive touch sensor array has detected a particular input that indicates a user has positioned an assistant-enabled device near their face. The capacitive touch sensor array can be part of a touch display interface of a portable computing device that provides access to an automated assistant. When the interface is positioned near the face of the user, input data from the interface can be processed to determine whether the input data indicates the display interface is near their face or whether the user is providing some other input to the display interface. When the input data indicates the user is positioning the display interface near their face or mouth, the automated assistant can be invoked in lieu of the user providing any other invocation input.