ML-Based Remote Wake-Up for Mobile Driving Data Collection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Mobile devices experience delays in waking up to collect driving trip data, leading to inaccurate or sub-optimal computation of driving scores due to limited information available while asleep, resulting in missed data collection at the trip start.

Innovation Solution

A computing platform uses machine learning to predict trip start times by analyzing historical data from GPS, demographics, and other sensors, sending wake-up commands to the mobile device before the trip begins, ensuring timely data collection and minimizing battery drain by keeping the device asleep until needed.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the mobile device wakes up continuously to collect driving trip data, then data collection accuracy is improved, but battery consumption increases

Engineering Contradiction:

Improvedata collection accuracyVSAvoidbattery consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary actions by training a machine learning model with historical data to predict trip start times before actual trips occur. The model analyzes patterns from GPS data, accelerometer data, and other sensors to forecast when the device should wake up, allowing the device to remain asleep until just before the predicted trip begins, thus balancing data accuracy with battery conservation

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The mobile device serves itself by using its own historical sensor data and usage patterns to train a machine learning model that automatically determines optimal wake-up times. The device autonomously decides when to activate sensors and when to remain dormant based on predicted trip scenarios, eliminating the need for continuous manual monitoring or external control

Inventive Principle:

Principle #25Self-service

2Use of energy by moving object

If the mobile device remains asleep to conserve battery, then battery consumption is reduced, but data collection timeliness deteriorates

Engineering Contradiction:

Improvebattery consumptionVSAvoiddata collection delay

Core Design Contradiction:

Use of energy by moving objectVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of historical trip data and sensor patterns to predict future trip start times. By training the machine learning model in advance with labeled historical data, the system can accurately forecast when the device should wake up, ensuring timely data collection without requiring the device to remain continuously awake

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by continuously monitoring actual trip data and comparing it with predicted trip times. The machine learning model is dynamically updated using this feedback loop, improving its prediction accuracy over time. This allows the device to progressively wake up at more accurate times, reducing data collection delays while maintaining battery efficiency

Inventive Principle:

Principle #23Feedback

3Device complexity

If the mobile device uses limited sensor data while asleep to detect trip start, then device complexity is reduced, but measurement precision deteriorates

Engineering Contradiction:

Improvedevice simplicityVSAvoidtrip start detection accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system performs preliminary training of the machine learning model using extensive historical sensor data and labeled trip information before deployment. This pre-training phase allows the model to learn complex patterns and relationships in the data, enabling accurate trip start predictions even when the device later operates with limited real-time sensor data available during sleep mode

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The machine learning model acts as an intermediary between the limited sensor data available during sleep mode and the accurate trip start detection requirement. The model processes and interprets the limited input signals, translating them into accurate predictions of trip start times, thus bridging the gap between simple device operation and precise measurement

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20220051115A1Control Platform Using Machine Learning for Remote Mobile Device Wake Up

Publication Date: 2022.02.17 ALLSTATE INSURANCE COMPANY

AI summary

Aspects of the disclosure relate to using machine learning for remote wake up of a mobile device. A computing platform may receive historical data corresponding to driving trip patterns. The computing platform may train a machine learning model using the historical data corresponding to the driving trip patterns. The computing platform may receive initial data corresponding to a particular individual, and input the initial data into the machine learning model, which may cause output of a predicted trip start time of a driving trip of the particular individual. The computing platform may send, to a mobile device corresponding to the particular individual, one or more commands directing the mobile device to wake up prior to the predicted trip start time and to initiate collection of driving trip data corresponding to the driving trip, which may cause the mobile device to be configured for the collection of driving trip data.