Autonomous semantic labeling of physical locations

Patent metadata

Field	Value
Publication number	US-9781575-B1
Application number	US-201615084799-A
Country	US
Kind code	B1
Filing date	Mar 30, 2016
Priority date	Mar 30, 2016
Publication date	Oct 3, 2017
Grant date	Oct 3, 2017

Abstract

A portable electronic device may generate a (RF) radio frequency fingerprint that includes information representative of at least a portion of RF signals received at a given physical location. The RF fingerprint may include, for example, a unique identifier and a signal strength that are both logically associated with at least a portion of the received RF signals. The portable electronic device may also receive data representative of a number of environmental parameters about the portable electronic device. These environmental parameters may be measured using sensors carried by the portable electronic device. Considered in combination, these environmental parameters provide an environmental signature for a given location. When combined into a data cluster, the RF fingerprint and the environmental signature may provide an indication of the physical subdivision where the portable electronic device is located. The portable electronic device may then generate a proposed semantic label for the physical subdivision.

First claim

What is claimed:

1. A semantic labeling controller, comprising:
a transceiver to receive a plurality of radio frequency (RF) signals within a defined portion of the RF spectrum;
a sensor to generate a signal that includes data or information indicative of an ambient environment in a physical subdivision external to the controller;
RF fingerprint generator circuitry coupled to the transceiver, the RF fingerprint generator circuitry to receive a plurality of RF signals and selectively generate an RF fingerprint that includes data indicative of at least one parameter associated with each of the received RF signals;
environmental signature generator circuitry coupled to the sensor, the environmental signature generator circuitry to receive the signal that includes data or information indicative of the ambient environment in the physical subdivision and selectively generate an environmental signature that includes data indicative of the ambient environment external to the controller;
data grouping circuitry coupled to the RF fingerprint generator circuitry and to the environmental signal generator circuitry to selectively group the RF fingerprint and the environmental signature into a data cluster responsive to the RF fingerprint meeting at least one threshold condition; and
semantic labeling circuitry coupled to the data grouping circuitry to autonomously generate a proposed semantic label for logical association with the physical subdivision based at least in part on the RF fingerprint and the environmental signature included in the data cluster.

2. The semantic labeling controller of claim 1 wherein the transceiver, in operation, receives RF signals within at least a portion of an RF spectrum defined by Bluetooth® or Near Field Communication (NFC) standards.

3. The semantic labeling controller of claim 1 wherein the transceiver, in operation, receives RF signals within at least a portion of an RF spectrum defined by IEEE 802.11 (WiFi) standards.

4. The semantic labeling controller of claim 3 wherein the RF fingerprint generator circuitry selectively generates the RF fingerprint using at least a unique identifier and a signal strength logically associated with each respective one of the plurality of received RF signals.

5. The semantic labeling controller of claim 4 wherein the semantic labeling circuitry further:
generates a human perceptible output that includes data indicative of the proposed semantic label;
receives input indicative of a confirmation of the proposed semantic label; and
responsive to receipt of the input indicative of the confirmation of the proposed semantic label, logically associates the confirmed semantic label with the physical subdivision.

6. The semantic labeling controller of claim 5 wherein the sensor comprises at least one of: an audio input sensor, an ambient light sensor, an accelerometer, or an image sensor.

7. The semantic labeling controller of claim 6 , further comprising device profile selection circuitry coupled to the semantic labeling circuitry to select a device profile based at least in part on the identified physical subdivision.

8. The semantic labeling controller of claim 6 , further comprising device detection circuitry coupled to the semantic labeling circuitry and to the data grouping circuitry, the device detection circuitry to:
detect a presence of at least one other local portable electronic device;
receive a signal from the at least one other local portable electronic device, the signal including data representative of a semantic label and an identified data cluster logically associated with the semantic label;
compare the received data representative of the identified data cluster with the data cluster generated by the data grouping circuitry; and
responsive to a favorable comparison, logically associate the received semantic label with the physical subdivision.

9. The semantic labeling controller of claim 1 wherein the data grouping circuitry selectively determines an RF signal sampling rate based at least in part on at least one of data or information included in the output signal from the sensor.

10. The semantic labeling controller of claim 9 wherein the data grouping circuitry selectively reduces the RF signal sampling rate responsive to data or information included in the output signal of the sensor indicative of the sensor being stationary.

11. The semantic labeling controller of claim 9 wherein the data grouping circuitry further selectively halts RF signal sampling responsive to data or information included in the output signal of the sensor indicative of the sensor being in motion.

12. The semantic labeling controller of claim 1 wherein the data grouping circuitry selectively groups the RF fingerprint and the environmental signature into a data cluster responsive to the RF fingerprint remaining within an RF fingerprint threshold for greater than a defined temporal threshold period.

13. A semantic labeling method, comprising:
selectively generating, by radio frequency (RF) fingerprint generator circuitry, an RF fingerprint that includes data indicative of at least one parameter associated with each of the received RF signals;
generating, by a sensor, a signal that includes data or information indicative of an ambient environment in a physical subdivision external to the controller;
generating, by environmental signature generating circuitry coupled to the sensor, an environmental signature that includes data indicative of the ambient environment external to the sensor;
selectively grouping, by data grouping circuitry coupled to the RF fingerprint generator circuitry and to the environmental signal generator circuitry, the RF fingerprint and the environmental signature into a data cluster responsive to the RF fingerprint meeting at least one threshold condition; and
autonomously generating, by semantic labeling circuitry coupled to the data grouping circuitry, a proposed semantic label for logical association with the physical subdivision based at least in part on the RF fingerprint and the environmental signature included in the data cluster.

14. The method of claim 13 wherein selectively generating an RF fingerprint that includes data indicative of at least one parameter associated with each of the received RF signals comprises:
selectively generating, by the RF fingerprint generator circuitry, an RF fingerprint using at least one parameter from each of the plurality of received RF signals, each of the plurality of received RF signals within at least a portion of an RF spectrum that includes at least one of: a Bluetooth® RF spectrum or Near Field Communication (NFC) RF spectrum.

15. The method of claim 13 wherein selectively generating an RF fingerprint that includes data indicative of at least one parameter associated with each of the received RF signals comprises:
selectively generating, by the RF fingerprint generator circuitry, an RF fingerprint using at least one parameter from each of the plurality of received RF signals, each of the plurality of received RF signals within at least a portion of an RF spectrum that includes an IEEE 802.11 (WiFi) RF spectrum.

16. The method of claim 15 wherein selectively generating at least one RF fingerprint using at least one parameter from each of the plurality of received RF signals comprises:
selectively generating, by the RF fingerprint generator circuitry, at least one RF fingerprint using at least a unique identifier and a signal strength logically associated with each respective one of the plurality of received RF signals.

17. The method of

Assignees

• Intel Corp

Inventors

• Wan Chieh-Yih
• Yang Lei
• Huang Jonathan J
• Lu Hong
• Shah Rahul C
• Nachman Lama

Classifications

• H04W4/005

  Electricity · mapped topic

• H04L67/303

  Terminal profiles · CPC title

• H04W4/04 Primary

  Electricity · mapped topic

• H04W4/023 Primary

  using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds · CPC title

• H04W4/008

  Electricity · mapped topic