Method and system for locating mobile terminal

Abstract

The invention discloses a method and system for locating a mobile terminal, and belongs to the field of wireless service supporting in mobile communication. The method integrates the advantages of a support vector machine and a K-nearest neighbor algorithm, and through the stages of off-line drive test sampling and model training, two layers of SVM locating models and KNN locating models are constructed. In an on-line locating stage, the two layer of the SVM locating models and the KNN locating models are combined, so that the locating precision of the mobile terminal is greatly improved. The method achieves compromise and balance between the algorithm complexity and the locating precision, and compared with a traditional locating method, the method effectively improves the locating precision, greatly reduces calculated amount and improves the locating speed.

Description

technical field [0001] The invention relates to the field of wireless service support in the field of mobile communication, in particular to a positioning method and system for a mobile terminal based on a support vector machine and a K-nearest neighbor algorithm. Background technique [0002] The positioning method of the mobile station in the mobile communication network is an emerging technology in recent years. With the increase in the number of mobile communication users and the continuous expansion of user needs, fast, accurate, effective and practical positioning methods have become one of the key technologies urgently needed in the communication field. . The positioning technology of mobile terminals in mobile communication cellular network has broad application prospects, such as emergency rescue, intelligent transportation, dynamic resource management and so on. The mobile communication network transmits and receives information to the mobile station through secto...

AI Technical Summary

Problems solved by technology

However, GPS positioning requires mobile terminals to have GPS positioning functions, which are generally only met by smart phones, and ordinary mobile phones cannot; Even if the data of the third-party software is obtained, it still involves steps such as data decryption, which is difficult to apply

[0009] (2) Through signal time of arrival (TOA), time difference of arrival, signal angle of arrival (AOA) or hybrid positioning methods, the positioning error is generally more than 200 meters, which cannot meet the high-precision positioning requirements

[0010] (3) Use the cell ID + timing advance (CellID + TA) positioning method, that is, use the location information of the serving cell occupied by the mobile station and the TA of the serving cell to perform positioning. This method increases the burden on the communication network less, but the positioning accuracy lower

In addition, there is also a positioning technology by measuring the signal strength and then using the propagation model to calculate the distance. However, due to the different wireless propagation environments, this method also has the problem of relatively large errors.

[0011] In general, the existing positioning methods cannot achieve a good balance in terms of positioning accuracy and positioning efficiency.

Images