Human-Presence Detection Model Training With Distance-Temperature Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for human presence detection in computers consume high power and are prone to misjudgment due to the use of multiple distance sensors and potential interference from nearby objects.
Innovation Solution
A training system and method using a distance sensor and a temperature sensor to generate a human-presence detection model by clustering training samples based on distance and temperature data, reducing power consumption and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple distance sensors are installed on display screen and keyboard to detect human presence, then detection coverage is improved, but power consumption increases significantly
Solution Approach 1:
The patent extracts the distance sensing function from multiple distributed sensors and consolidates it into a single distance sensor positioned at a specific location. This extraction approach maintains detection capability while dramatically reducing power consumption by eliminating the need to operate multiple sensors simultaneously.
Solution Approach 2:
The patent merges the functions of multiple distance sensors into a single integrated detection system that uses both distance sensor and temperature sensor data together. This combination allows the system to achieve reliable human presence detection without the power consumption penalty of operating multiple independent sensors.
2Measurement precision
If multiple distance sensors are used to determine user presence, then detection accuracy is improved, but misjudgment occurs when nearby objects are detected
Solution Approach 1:
The patent introduces temperature sensor data as an intermediary factor to distinguish between actual human presence and false detections from nearby objects. By combining temperature information with distance measurements, the system can accurately identify whether a detected object is a human body, preventing misjudgment while maintaining detection accuracy.
Solution Approach 2:
The patent changes the detection parameters from purely distance-based measurements to a combined parameter system incorporating both distance and temperature. This parameter transformation enables the system to differentiate between human presence and nearby objects based on temperature characteristics, thereby reducing misjudgment.
3Reliability
If distance sensors work simultaneously to detect human presence, then detection reliability is improved, but power consumption increases
Solution Approach 1:
The patent employs periodic sampling of sensor data rather than continuous operation of multiple sensors. The system periodically collects distance and temperature data, processes them through the machine learning model, and updates detection results only when necessary, maintaining reliability while reducing overall power consumption.
Solution Approach 2:
The patent replaces the mechanical approach of using multiple active distance sensors with a computational approach that uses a single distance sensor combined with temperature sensing and machine learning processing. This substitution achieves reliable detection through algorithmic processing rather than through the power-intensive operation of multiple hardware sensors.
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
The system provides more accurate human presence detection with reduced power consumption by utilizing single pixel distance data and temperature data for training, enhancing detection model performance.
Implementation Method 1
a distance between an object under test and a computer can be accurately determined
Implementation Method 2
a temperature sensor and a host device, wherein the host device obtains a plurality of training samples by the distance sensor and the temperature sensor
Data Source
AI summary
A training system and a training method for a human-presence detection model are provided. The training method includes: obtaining, by a distance sensor and a temperature sensor, a plurality of training samples; dividing the plurality of training samples into a first data cluster and a second data cluster according to whether or not an input interface of the host device is in a used state; marking the first data cluster as a human-presence cluster; selecting a sub-cluster from the second data cluster; marking the sub-cluster as a human-absence cluster; and performing machine learning for the human-presence cluster and the human-absence cluster to generate the human-presence detection model. The first data cluster corresponds to the used state. A center point of the sub-cluster corresponds to a maximum distance value and a minimum temperature value.