Context Sensing Offload Engine for Mobile Power Reduction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Context algorithms running continuously on mobile computing devices consume excessive power, leading to rapid battery drain, as they constantly sense ambient environments and device status without distinguishing between meaningful and meaningless data.

Innovation Solution

Implementing a context-based trigger mechanism that offloads context sensing from the main processor to dedicated offload engines, such as a sensor hub engine and DSP engine, allowing only meaningful context data to be captured at specified intervals, reducing unnecessary power consumption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If context algorithms run continuously on the main processor to maintain context awareness, then the device can always be aware of the latest ambient environment or device status, but power consumption increases significantly causing rapid battery drain

Engineering Contradiction:

Improvecontext awarenessVSAvoidpower consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent divides the context sensing system into two segments: a low-power sensor hub engine that continuously monitors sensors and a main processor that handles complex computations only when needed. This segmentation allows continuous context monitoring while minimizing power consumption by keeping the main processor in sleep mode during idle periods.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The sensor hub engine performs periodic sampling of sensor data at configurable intervals, transitioning from continuous monitoring to periodic monitoring. This reduces power consumption while maintaining context awareness by only activating the main processor when significant context changes are detected during these periodic sampling cycles.

Inventive Principle:

Principle #19Periodic action

2Loss of information

If continuous sensing is performed to capture all context data, then complete context information is available, but meaningless data is captured increasing processing overhead and power consumption

Engineering Contradiction:

Improvecontext data completenessVSAvoidpower consumption

Core Design Contradiction:

Loss of informationVSLoss of energy

Solution Approach 1:

The sensor hub engine extracts only meaningful context changes from sensor data by comparing current readings against previous states and predefined thresholds. This extraction process filters out meaningless repetitive data before transmitting to the main processor, reducing processing overhead and power consumption while maintaining context information completeness.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system dynamically adjusts sampling rates and trigger thresholds based on context importance and current power conditions. For stable contexts, sampling intervals are increased or monitoring is suspended, while for changing contexts, sampling frequency increases. This parameter adaptation reduces energy loss by matching data capture intensity to actual context variability.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS9568977B2Context sensing for computing devices

Publication Date: 2017.02.14 INTEL CORP

AI summary

A method and system for context sensing is described herein. The method includes determining if sensor data obtained via a number of sensors exceed a predetermined threshold. The method also includes increasing a sampling rate of any of the sensors to obtain context data corresponding to a computing device if the sensor data exceed the threshold. The method further includes analyzing the context data to classify a context of the computing device.