Invention Grant
US09351117B2 Use of a trained classifier to predict distance based on a pair of wireless scans
有权
使用训练有素的分类器来基于一对无线扫描来预测距离
- Patent Title: Use of a trained classifier to predict distance based on a pair of wireless scans
- Patent Title (中): 使用训练有素的分类器来基于一对无线扫描来预测距离
-
Application No.: US13972738Application Date: 2013-08-21
-
Publication No.: US09351117B2Publication Date: 2016-05-24
- Inventor: Mohammed Waleed Kadous , Brian Patrick Williams , Etienne Le Grand
- Applicant: Google Inc.
- Applicant Address: US CA Mountain View
- Assignee: Google Inc.
- Current Assignee: Google Inc.
- Current Assignee Address: US CA Mountain View
- Agency: McDonnell Boehnen Hulbert & Berghoff LLP
- Main IPC: H04W64/00
- IPC: H04W64/00 ; H04W4/02

Abstract:
The present disclosure describes methods, systems, and apparatuses for determining the distance between two wireless scans of a mobile computing device. The distance is determined by scanning for wireless networks with a computing device. The scanning includes a receiving a plurality of network attributes for each wireless networks within the range of the mobile computing device. Further, the distance is determined by comparing the plurality of network attributes from the scanning with a reference set of network attributes. The comparing of network attributes is used to determine an attribute comparison. Finally, the distance between a position associated with the reference set of network attributes and the computing device, based on the attribute comparison, determines a position associated with the network.
Public/Granted literature
- US20150057014A1 Use of a Trained Classifier to Predict Distance Based on a Pair of Wireless Scans Public/Granted day:2015-02-26
Information query