Indoor room-localization system and method therof

Patent metadata

Field	Value
Publication number	US-10481239-B2
Application number	US-201716066566-A
Country	US
Kind code	B2
Filing date	Jan 2, 2017
Priority date	Dec 31, 2015
Publication date	Nov 19, 2019
Grant date	Nov 19, 2019

Abstract

A processor-based client device may be localized in an indoor area based on Received Signal Strength Indication (RSSI) values from different access points is provided. A general geographic area in which the processor-based client device is located. A position of the processor-based client device on the identified area is determined. A context-aware information is displayed on the processor-based client device once the identified area is determined.

First claim

What is claimed is:

1. An indoor room localization system comprising:
a memory including training data and response data;
a processor coupled to the memory, the processor for carrying or having computer-executable instructions to collect WiFi RSSI data corresponding to various sites, the instructions causing a machine to:
classify the collected WiFi RSSI data into an array of RSSI patterns;
transmit the classified RSSI patterns to the memory for storing into training data;
transmit response data identifying classifications of the collected WiFi RSSI data to the memory for storage;
generate observation vectors from the response data identifying classifications of the collected WiFi RSSI data; and
update categorical distribution parameters using the generated observation vectors to specify a probability that the machine is within a predetermined region; and
wherein a dirichlet distribution is used to classify the collected WiFi RSSI data into an array of RSSI patterns and a mode of the dirichlet distribution is used to specify the probability that the machine is within the predetermined region.

2. The indoor room localization system of claim 1 wherein the instructions further causing the machine to use the response data stored in the memory to specify the probability that the machine is within the predetermined region.

3. The indoor room localization system of claim 1 , wherein the processor is integrated into a client device.

4. The indoor room localization system of claim 2 , wherein the memory is located on a cloud network.

5. The indoor room localization system of claim 1 wherein a support vector machine (SVM) is used to classify the collected WiFi RSSI data into an array of RSSI patterns.

6. The indoor room localization system of claim 5 , wherein the processor is integrated into a client device.

Assignees

• Bosch Gmbh Robert

Inventors

• Das Samarjit
• De Sousa Joao Pedro

Classifications

• H04W4/33

  for indoor environments, e.g. buildings · CPC title

• G01S11/06

  using intensity measurements · CPC title

• H04W4/021

  Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences · CPC title

• G01S5/0252 Primary

  Radio frequency fingerprinting · CPC title

• H04W64/00 Primary

  Locating users or terminals {or network equipment} for network management purposes, e.g. mobility management · CPC title