Method for identifying external device by registering features of EM signal and electronic device applying said method

Patent metadata

Field	Value
Publication number	US-11768233-B2
Application number	US-201917421156-A
Country	US
Kind code	B2
Filing date	Dec 17, 2019
Priority date	Jan 9, 2019
Publication date	Sep 26, 2023
Grant date	Sep 26, 2023

Abstract

A method by which an electronic device interworks with an external device may be disclosed, the method comprising the operations of: obtaining an EM signal from the external device; extracting feature data by passing the obtained EM signal through a feature extraction model; receiving information related to the external device; generating registration information on the basis of the extracted feature data and the information related to the external device; and storing the generated registration information in a database of a memory, wherein the operation of receiving the information related to the external device provides an input interface for inputting information related to the external device, or shows at least one piece of pre-stored information related to the external device. In addition, other various embodiments identified through the specification are also possible.

First claim

The invention claimed is:

1. A method for interworking with an external device in an electronic device, the method comprising:
obtaining an electromagnetic (EM) signal from the external device;
passing the obtained EM signal through a feature extraction model to extract feature data;
comparing a similarity between the extracted feature data and feature data of an EM signal obtained from a plurality of external devices;
displaying candidate devices, among the plurality of external devices, similar to the extracted feature data based on the similarity;
receiving an input for selecting one of the candidate devices associated with the external device;
generating registration information based on the extracted feature data and the selected candidate device associated with the external device; and
storing the generated registration information in a database of a memory.

2. The method of claim 1 , wherein the input for selecting one of the candidate information associated with the external device includes a selection window capable of selecting the external device, a quick menu of displaying external devices recently interworking, a notification window of notifying a user of information to be input, and/or an input window capable of inputting the external device.

3. The method of claim 1 , wherein the generating of the registration information includes:
receiving context information including information associated with a situation, a location, and/or an environment where the registration information is generated.

4. The method of claim 1 , further comprising:
generating the feature extraction model,
wherein the generating of the feature extraction model includes:
previously collecting an EM signal of at least one external device and constructing learning data, and
wherein the learning data includes type 1 in a form where there is information about the EM signal and where there is a tag displaying whether the EM signal is generated from a certain external device or type 2 where there is only the information about the EM signal.

5. The method of claim 4 , wherein the feature extraction model is generated based on a supervised learning method, and
wherein the supervised learning method includes a CNN classifier model.

6. The method of claim 4 , wherein the feature extraction model is generated based on an unsupervised learning method, and
wherein the unsupervised learning method includes an autoencoder model.

7. An electronic device, comprising:
an input device;
a display device;
a communication module;
an electromagnetic (EM) sensing circuit configured to obtain an EM signal;
at least one processor operationally connected with the input device, the display device, the communication module, and the EM sensing circuit;
a memory operationally connected with the processor; and
a device registering unit operationally connected with the memory,
wherein the memory stores instructions, when executed, causing the at least one processor to:
obtain an EM signal from an external device, using the EM sensing circuit;
apply the obtained EM signal to a feature extraction model to extract feature data;
store information mapping the external device and the electronic device in a database included in the memory;
register an associated service with an external device identified based on the feature data
store the extracted feature data together with information associated with the external device;
identify the external device based on feature data with the highest similarity with the feature data of the EM signal between the extracted feature data; and
display candidate devices, similar to the extracted feature data.

8. The electronic device of claim 7 , wherein the instructions cause the at least one processor to:
receive the feature extraction model from an external server, via the communication module.

9. The electronic device of claim 7 , wherein the EM sensing circuit generates EM signal data based on the EM signal, and
wherein the EM signal data includes information about a waveform of the EM signal or information about a type of the external device of emitting the EM signal.

10. The electronic device of claim 7 , wherein the instructions cause the at least one processor to:
transmit the obtained EM signal to an EM server having information associated with the external device, via the communication module; and
receive feature data extracted from the EM signal from the EM server.

11. The electronic device of claim 10 , wherein the instructions cause the processor to:
receive the information associated with the external device together with the feature data from the EM server, via the communication module.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Lee Yuwon
• Min Hwangki
• Choi Shunghyun
• Kang Doosuk
• Kim Seungnyun

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0455

  Auto-encoder networks; Encoder-decoder networks · CPC title

• G06N3/088

  Non-supervised learning, e.g. competitive learning · CPC title

• G06F18/24133

  Distances to prototypes · CPC title