Indoor location method and system

Abstract

The embodiment of the invention provides an indoor location method and system. The method comprises: obtaining the current signal intensity value of a terminal to be detected monitored by each monitoring terminal; matching the fingerprints in a pre-built fingerprint database based on the current signal intensity value and the identity identification of the monitoring terminal corresponding to the current signal intensity value, and obtaining the probability density function and coordinates corresponding to the current signal intensity value at each monitoring points covered by each monitoring terminal; substituting the current signal intensity value into the corresponding probability density function, and calculating the corresponding probability density; and calculating the position where the terminal to be detected is located based on the probability density and the coordinates corresponding to the current signal intensity value at each monitoring point covered by each monitoring terminal through adoption of a pre-built weight position solution formula. According to the embodiment of the invention, the training time and the location cost are reduced while the indoor location precision is improved.

Description

technical field [0001] The present invention relates to the technical field of positioning, in particular to an indoor positioning method and system. Background technique [0002] At present, wireless networks are widely used in indoor positioning, and the positioning accuracy of indoor positioning is increasingly required. Among them, the representative indoor positioning scheme is the positioning scheme based on the naive Bayesian positioning algorithm. [0003] However, due to the complexity of the indoor environment and the interference of many signals in the same frequency band around the indoor environment, there are two problems in the following two aspects when adopting the naive Bayesian positioning algorithm: First, due to the geographical fingerprint matching in the offline stage Due to the volatility of the collected signal strength values, only using the Naive Bayesian positioning algorithm to construct the fingerprint database makes it difficult to establish a ...

AI Technical Summary

Problems solved by technology

[0003] However, due to the complexity of the indoor environment and the interference of many signals in the same frequency band around the indoor environment, there are two problems in the following two aspects when adopting the naive Bayesian positioning algorithm: First, due to the geographical fingerprint matching in the offline stage Due to the volatility of the collected signal strength values, only using the Naive Bayesian positioning algorithm to construct the fingerprint database makes it difficult to establish a fingerprint database; second, using the Naive Bayesian positioning algorithm and combining the regression algorithm to form a Bayesian regression algorithm will cause The training time is longer, which increases the cost of positioning

Images