Perception method, apparatus, and storage medium
By acquiring and processing the distance and Doppler feature information of two-dimensional surface echo signals from multiple network devices, and combining the signal-to-noise ratio and eigenvectors, the sensing capability is evaluated using the Fisher information matrix. This solves the problem of low accuracy in existing sensing technologies and enables more accurate determination of the position and velocity of the sensed object.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HONOR DEVICE CO LTD
- Filing Date
- 2026-02-10
- Publication Date
- 2026-06-12
AI Technical Summary
Existing sensing technologies have low sensing accuracy in the field of communications, especially when multiple network devices are sensing in a coordinated manner, making it difficult to accurately determine the position and speed of the sensed object.
By sending configuration information to multiple network devices, distance and Doppler feature information based on two-dimensional surface echo signals are obtained. Combining signal-to-noise ratio and feature vectors, the error is quantized using the Fisher information matrix, and the sensing capabilities of each network device are dynamically evaluated, thereby improving sensing accuracy and robustness.
It enables more accurate determination of the position and velocity of the sensed object, improves the sensing accuracy and robustness, reduces the computational burden, and enhances the overall accuracy of collaborative sensing among multiple network devices.
Smart Images

Figure CN121692095B_ABST
Abstract
Citation Information
Patent Citations
Perception processing method and device, terminal and network side equipment
CN120434815A
Information processing apparatus, sensing apparatus, mobile object, method for processing information, and information processing system
US20230048222A1