Voice-controlled smart lift control method and system

By collecting and processing acoustic, structural vibration, and Hall pulse data of the height-adjustable desk, an estimated transfer function is constructed for adaptive filtering, which solves the problem of speech recognition failure and achieves high-accuracy voice control in mechanical noise environments, thus improving the safety and real-time performance of the intelligent height-adjustable desk.

CN122177100APending Publication Date: 2026-06-09SHAOXING CONTUO TRANSMISSION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
SHAOXING CONTUO TRANSMISSION TECH CO LTD
Filing Date
2026-02-11
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing voice-controlled smart height-adjustable desks may fail to recognize voice during movement due to mechanical noise interference, posing a safety hazard, especially in emergency scenarios where they could lead to equipment collisions and personnel injuries.

Method used

Acoustic, structural vibration, and Hall pulse data of the height-adjustable desk are collected. Through synchronous alignment and signal analysis, a predicted transfer function is constructed for adaptive cancellation filtering, a clean speech vector is extracted, and noise-resistant semantic feature extraction and intent decoding are performed to generate normalized control commands.

Benefits of technology

Maintaining high accuracy in command recognition while the motor is running at full speed significantly improves the real-time performance and safety of intelligent lifting interaction, avoiding the risk of collisions caused by voice interruption.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122177100A_ABST
    Figure CN122177100A_ABST
Patent Text Reader

Abstract

This application discloses a voice-controlled intelligent lifting control method and system. It synchronously collects acoustic, structural vibration, and Hall pulse data, uses Hall pulses to calculate the current height in real time, and uses this as an index to perform parameter interpolation in a pre-set mapping library, thereby constructing a predicted transfer function dynamically adapted to the current mechanical form. Based on this, the structural vibration attached to the frame is used as a reference signal, and adaptive cancellation filtering is used to restore a clean voice vector, effectively filtering out nonlinear mechanical noise generated by motor operation. In this way, the equipment can maintain extremely high command recognition accuracy even when the motor is running at full speed, fundamentally solving the collision risk caused by voice interruption failures, and significantly improving the real-time performance and physical safety of intelligent lifting interaction.
Need to check novelty before this filing date? Find Prior Art