IP Library › Granted Patent US 11,288,158
Granted Patent B2
US 11,288,158 · App. 16/973,137 · Granted Mar 29, 2022

Device identification device and device identification method

Inventors: Hirofumi Noguchi (Tokyo, JP); Yoji Yamato (Tokyo, JP); Misao Kataoka (Tokyo, JP); Tatsuya Demizu (Tokyo, JP)
Assignee: Nippon Telegraph and Telephone Corporation
G06F11/3051G06F17/15H04L41/0869
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,288,158
App. No.
16/973,137
Granted
Mar 29, 2022
Kind
B2
Abstract

A device identification device ( 100 ) includes: a device feature value extractor ( 1 - 1, 1 - 2 ) to routinely extract one or more device feature values of an unknown device; a model identifier ( 6 ) to identify a model of the unknown device; a change pattern generator ( 2 ) to generate one or more change patterns of the extracted one or more device feature values; and a device similarity calculator ( 3 ) to compare each of the generated one or more change patterns with each of change patterns of known devices, to calculate a device similarity therebetween, and identify the unknown device, when the maximum value of the calculated device similarities is equal to or greater than a first threshold, as the known device indicating the maximum value.

Claims (22)

1. A device identification device for identifying an unknown device connected to a network, comprising:

a device feature value extractor, including one or more processors, configured to routinely extract one or more device feature values of the unknown device from a signal received from the unknown device;

a model identifier, including one or more processors, configured to identify a model of the unknown device from the signal received from the unknown device;

a change pattern generator, including one or more processors, configured to generate one or more change patterns of the extracted one or more device feature values, wherein the change patterns are prepared, using one or more predetermined calculation logics, for respective types of the one or more device feature values changing with time; and

a device similarity calculator, including one or more processors, configured to compare each of the generated one or more change patterns to each of change patterns of known devices, belonging to the identified model, among a plurality of kinds of known devices stored in a storage unit of the device identification device, to calculate a device similarity between the unknown device and each of the known devices, belonging to the identified model, and identify the unknown device, when a maximum value of the calculated device similarities is equal to or greater than a first threshold, as the known device indicating the maximum value of the calculated device similarities.

2. The device identification device as claimed in claim 1 , further comprising:

a type similarity calculator, including one or more processors, configured to calculate a type similarity for every device type, when the model identifier has failed to identify the model of the unknown device, with respect to the one or more change patterns of the unknown device, and determine, when a maximum value of the calculated type similarities is equal to or greater than a second threshold, that a type of the unknown device is the type indicating the maximum value of the calculated type similarities.

3. A device identification method executed in a device identification device for identifying an unknown device connected to a network, comprising:

routinely extracting one or more device feature values of the unknown device from a signal received from the unknown device;

identifying a model of the unknown device from the signal received from the unknown device;

generating one or more change patterns of the extracted one or more device feature values, wherein the change patterns are prepared, using one or more predetermined calculation logics, for respective types of the one or more device feature values changing with time;

comparing each of the generated one or more change patterns to each of change patterns of known devices, belonging to the identified model, among a plurality of kinds of known devices stored in a storage unit of the device identification device, to calculate a device similarity between the unknown device and each of the known devices, belonging to the identified model; and

identifying the unknown device, when a maximum value of the calculated device similarities is equal to or greater than a first threshold, as the known device indicating the maximum value of the calculated device similarities.

4. The device identification method executed in the device identification device as claimed in claim 3 , further including:

calculating a type similarity for every device type, when identifying the model of the unknown device has been failed, with respect to the one or more change patterns of the unknown device; and

determining, when a maximum value of the calculated type similarities is equal to or greater than a second threshold, that a type of the unknown device is the type indicating the maximum value of the calculated type similarities.

5. A device identification device for identifying an unknown device connected to a network, comprising:

one or more processors for executing computer-readable code, the computer-readable code causing the one or more processors to:

routinely extract one or more device feature values of the unknown device from a signal received from the unknown device;

identify a model of the unknown device from the signal received from the unknown device;

generate one or more change patterns of the extracted one or more device feature values, wherein the change patterns are prepared, using one or more predetermined calculation logics, for respective types of the one or more device feature values changing with time; and

compare each of the generated one or more change patterns to each of change patterns of known devices, belonging to the identified model, among a plurality of kinds of known devices stored in a storage unit of the device identification device, to calculate a device similarity between the unknown device and each of the known devices, belonging to the identified model, and identify the unknown device, when a maximum value of the calculated device similarities is equal to or greater than a first threshold, as the known device indicating the maximum value of the calculated device similarities.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 16, 2020
From: NOGUCHI, HIROFUMI; YAMATO, YOJI; KATAOKA, MISAO; DEMIZU, TATSUYA
To: NIPPON TELEGRAPH AND TELEPHONE CORPORATION
Reel/Frame 054661/0796 →
Priority Claims (1)
JP JP2018-110116 · Jun 8, 2018 · national
Continuity (1)
Related Publication 20210255943A1 · Aug 19, 2021