A positioning method and apparatus, an electronic device, and a computer-readable storage medium

By utilizing recurrent neural networks and calibration algorithms to process the RSRP and TOA of base station signals, the impact of Tx-Rx delay error on positioning accuracy was resolved, thereby improving positioning accuracy without increasing hardware costs.

CN117177171BActive Publication Date: 2026-05-29BEIJING UNIV OF POSTS & TELECOMM
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING UNIV OF POSTS & TELECOMM
Filing Date
2023-08-31
Publication Date
2026-05-29

Smart Images

  • Figure CN117177171B_ABST
    Figure CN117177171B_ABST
Patent Text Reader

Abstract

Embodiments of the present application provide a positioning method and device, electronic equipment and computer readable storage medium, the method comprising: obtaining the RSRP and TOA of the signal received by the to-be-positioned device from a plurality of base stations at the current time, inputting the RSRP into a recurrent neural network trained in advance to obtain the first predicted position of the to-be-positioned device at the current time, determining the Tx-Rx delay error of each base station at the current time according to the first predicted position of the to-be-positioned device at the current time and the TOA; performing error elimination on the TOA according to the Tx-Rx delay error of each base station at the current time to obtain the TOA after error elimination of each base station at the current time; and determining the position coordinates of the to-be-positioned device at the current time based on the TOA after error elimination of each base station at the current time. The influence of the Tx-Rx delay error on the positioning result is reduced without increasing the reference terminal, thereby improving the positioning accuracy.
Need to check novelty before this filing date? Find Prior Art