Indoor telephone traffic accurate location method based on machine learning in cellular network

Abstract

The invention discloses an indoor telephone traffic accurate location method based on machine learning in a cellular network. The method comprises the steps that a cellular network base station system uses idle resources to acquire the signal parameters of user equipment UE step by step; the data are used to design a hybrid location algorithm; information fusion is carried out to acquire preliminary position estimation; residual analysis decision is used for non-line-of-sight identification; a Kalman filter algorithm is used for multi-path suppression; a position estimated by the hybrid location algorithm is corrected to acquire an estimated position; priori information which comprises the habits of a user and the position of a building is used to correct the estimated position, and a reliable sample is extract; a machine learning algorithm is used to train data to acquire the location model of the combination of different parameters; a model trained in the off-line phase is used to estimate the position of the UE; and a particle filter algorithm is used to track the position in real time.

Description

technical field [0001] The invention belongs to the field of positioning technology, and relates to a precise positioning method for indoor traffic in a cellular network, in particular to a machine learning-based precise positioning method for indoor traffic in a cellular network. Background technique [0002] In recent years, the demand for location-based services has increased, and wireless location technology has been extensively studied. At present, with the development of the cellular network mobile communication system, the location of the base station near the user, the angle of arrival (Angle of Arrival, AOA) of the signal of the user equipment (UE), the time of arrival of the signal (Time of Arrival, TOA), and the The parameters such as Time Difference of Arrival (TDOA), Received Signal Strength (RSS) and other parameters are used for location estimation to obtain the specific location of the UE. [0003] Common cellular network positioning technologies include: (1...

AI Technical Summary

Problems solved by technology

[0004] Although there are a variety of positioning technologies, in indoor or urban areas with dense buildings, due to the influence of non-line-of-sight (NLOS), multipath fading, and shadow effects on signal propagation, the positioning accuracy is greatly affected. Impact

Even if some non-line-of-sight discrimination methods and multipath suppression methods are adopted, it is still difficult to obtain high-precision positioning in complex environments

In addition, obtaining a higher-precision positioning often requires paying a greater price, such as using more base stations and additional hardware devices to obtain more signal parameters. However, in actual cellular networks, it is often difficult for multiple base stations to simultaneously receive UE's Information such as signals and angles may not be available, so that traditional positioning methods are difficult to obtain good positioning results in practical applications

[0005] The indoor traffic positioning in the urban cellular network has the following characteristics. The difficulty lies in: (1) The middle and high-rise buildings in the urban area are densely populated, and non-line-of-sight, multipath fading, and shadow effects are seriously affected

(2) The type and number of parameters of the UE signal that the base station system can obtain are not fixed, there may be redundant parameters sometimes, and sometimes insufficient parameters, the traditional deterministic geometric method is often not applicable

Images