Offline fingerprint database construction method, position fingerprint positioning method and system
A construction method and fingerprint library technology, applied in offline fingerprint library construction method, position fingerprint positioning method and system field, can solve the problems of increasing fingerprint matching calculation delay, etc., to reduce transmission delay, improve positioning accuracy, and high security Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0060] Embodiment 1: a method for constructing an offline fingerprint library, including: in the offline stage, before the mobile device end transmits a plurality of sampling values at the current reference point to the MEC server, it first completes the split operation of the fingerprint data through a clustering algorithm, That is, the reference point sampling data is transmitted to different MEC servers according to the clustering rules. The construction principle of the offline fingerprint library is as follows: image 3 As shown, the number of sub-databases of the fingerprint database is c, and the number of reference points of each sub-database is {n 1 ,n 2 ,...,n c}and
[0061] In the positioning model after the clustering operation is added, a new clustering operation is added to the task list of the MEC server to complete the classification and storage of fingerprint data. The specific process of building an offline fingerprint database is as follows:
[0062]...
Embodiment 2
[0076] Implementation 2: On the basis of Embodiment 1, this embodiment adopts the K-means clustering algorithm to obtain the clustering center of the sub-fingerprint library. K-means clustering, that is, K-means clustering. In the location fingerprint, the K-means algorithm uses the Euclidean distance as the standard of similarity, and divides the reference points into k classes. The similarity of reference points of different classes is low. . Assume that there are m reference points in the current entire area, respectively {L 1 , L 2 ,...,L m}, the number of APs used to create the fingerprint offline fingerprint library is n, respectively {AP 1 ,AP 2 ,...,AP n}. Reference point L i The coordinates are (xi,y i ), and its corresponding fingerprint is RSS i ={rss 1,i ,rss 2,i ,...,rss n,i}. The specific process of K-means clustering is as follows:
[0077]Input: the number of classes k (1
[0078] Output: k clusters a...
Embodiment 3
[0089] Implementation 3: a location fingerprint positioning method, including: adopting the off-line fingerprint library construction method described in the above embodiments to construct a sub-library of the off-line fingerprint library;
[0090] Each mobile edge computing server performs matching based on the RSS vector of the target point and its stored sub-database for constructing the offline fingerprint database, and weights the matching results of each mobile edge computing server to obtain the final estimated position of the target point. The specific processing logic is as follows:
[0091] Input: Maximum weight threshold T high , the minimum weighted threshold T low .
[0092] Step1: After the preprocessing of the sampling data of the target point is completed, the RSS vector of the target point is R={rss 1 ,rss 2 ,...,rss n}, the RSS vector of the cluster center of the i (i=1,2,...,n) class is RSS c i ={rss c i,1 ,rss c i,2 ,...,rss c i,n}, the similar...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com