Riding Tool Identification via Sensor Fusion and Voice Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices cannot accurately identify the category of a riding tool, such as a metro, high-speed railway, bus, or car, based solely on speed and location information, leading to difficulties in distinguishing between similar modes of transportation.
Innovation Solution
The method involves obtaining acceleration and magnetometer signals to extract features, combining them with voice signals to recognize voice broadcasts, and using artificial intelligence models to classify the riding tool, thereby improving identification accuracy by fusing multiple sensor data and voice recognition results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If only speed and location information are used for identification, then the device complexity is low, but the measurement precision of riding tool category identification is insufficient
Solution Approach 1:
The patent combines multiple sensor signals (acceleration signal from acceleration sensor, magnetometer signal from magnetometer sensor, and voice signal from microphone) to identify riding tool categories. By fusing these different types of signals, the system achieves higher identification accuracy for distinguishing between metro, high-speed railway, bus, and car, resolving the contradiction between using simple speed/location data and achieving precise category identification.
2Measurement precision
If multiple sensor signals and voice signals are fused for identification, then the measurement precision of riding tool category identification is improved, but the use of energy increases due to continuous microphone usage
Solution Approach 1:
The patent implements periodic action by controlling the microphone to operate only during specific periods when riding state is detected. The system first detects riding state using acceleration and magnetometer signals, and only activates the microphone during these periods for voice signal acquisition. This periodic operation mode maintains high identification accuracy while significantly reducing power consumption compared to continuous microphone operation.
Solution Approach 2:
The patent applies preliminary action by first detecting the riding state using acceleration and magnetometer signals before activating the microphone for voice signal acquisition. This preliminary detection mechanism ensures that the energy-intensive microphone operation is triggered only when necessary, i.e., when the device is in a riding state, thereby optimizing power consumption while maintaining identification accuracy.
3Measurement precision
If voice signal processing is continuously performed, then the measurement precision of voice broadcast recognition is improved, but the loss of time for processing increases
Solution Approach 1:
The patent implements periodic action by performing voice signal processing only during specific periods when riding state is detected, rather than continuously. The system activates the microphone and processes voice signals only when the device is in a riding state, as determined by acceleration and magnetometer signals. This approach maintains high voice broadcast recognition accuracy while reducing the time and computational resources wasted on processing during non-riding periods.
Data Source
AI summary
This application provides a riding tool identification method and a device. The method includes: obtaining at least one of an acceleration signal acquired by an acceleration sensor and a magnetometer signal acquired by a magnetometer sensor in an electronic device; identifying a riding tool based on at least one of an acceleration feature and a magnetometer feature, to obtain a riding classification result, where the acceleration feature is obtained based on the acceleration signal, and the magnetometer feature is obtained based on the magnetometer signal; obtaining a voice signal acquired by a microphone in the electronic device, and extracting a voice feature based on the voice signal; recognizing a voice broadcast during ride based on the voice feature, to obtain a voice broadcast recognition result; and determining a category of the riding tool based on the riding classification result and the voice broadcast recognition result.