# US 2023/0155905 A1 · Artificial intelligence based device identification

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0155905 A1
- Document ID: US20230155905A1
- Status: Published application
- Kind: A1
- Application number: 17/997,851
- Filed: 2020-05-28
- Published: 2023-05-18
- Earliest claimed: 2020-05-28
- Assignees: Siemens Canada Limited
- Applicants: Siemens Canada Limited
- Inventors: Johannes Riedl; Mirjana Zafirovic-Vukotic; Anas Hawari; Axel Gruner
- Web page: https://patentgrep.com/patent/US20230155905A1

## CPC

- G06F 21/44: Program or device authentication
- H04L 43/062: related to network traffic
- H04L 41/0853: by actively collecting configuration information or by backing up configuration information
- H04L 41/16: using machine learning or artificial intelligence
- H04L 43/045: for graphical visualisation of monitoring data
- G05B 23/024: {Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks}
- H04W 4/70: Services for machine-to-machine communication [M2M] or machine type communication [MTC]
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A system for obtaining information about an Internet of Things (IoT) device connected to a network includes a data traffic collection point, a data processing module and an artificial intelligence module. The data traffic collection point collects data units communicated to or from a specified IoT device of a plurality of IoT devices connected to a network. The data processing module processes quantitative information pertaining to the data units communicated to or from the specified IoT device collected over a defined time interval, to create a temporal data traffic fingerprint of the specified IoT device. The artificial intelligence module utilizes a machine learning model to deduce device identifying information of the specified IoT device from the temporal data traffic fingerprint of the specified IoT device.

## Claims

### Claim 1

A system for obtaining information about an Internet of Things (IoT) device connected to a network, the system comprising:
a data traffic collection point configured to collect data units communicated to or from a specified IoT device of a plurality of IoT devices connected to a network,
a data processing module configured to process quantitative information pertaining to the data units communicated to or from the specified IoT device collected over a defined time interval, to create a temporal data traffic fingerprint of the specified IoT device, and
an artificial intelligence module configured to utilize a machine learning model to deduce device identifying information of the specified IoT device from the temporal data traffic fingerprint of the specified IoT device.

### Claim 2 (depends on 1)

The system according to claim 1, wherein the data traffic collection point is configured to collect data units communicated to or from the specified IoT device based on a device address or identifier of the specified IoT device.

### Claim 3 (depends on 1)

The system according to claim 1, wherein the data traffic collection point is configured to collect data units communicated via a physical port linked to the specified IoT device, or via a virtual interface linked to the specified IoT device, or via a circuit comprising a combination of physical ports and/or virtual interfaces linked to the specified IoT device.

### Claim 4 (depends on 1)

The system according to claim 1, wherein the data traffic collection point is selected from the group consisting of: the specified IoT device, a node of the network via which data units communicated to or from the specified IoT device passes, and a port of a network component linked to the specified IoT device.

### Claim 5 (depends on 1)

The system according to claim 1, wherein the data processing module is configured to process the quantitative information to create statistical information pertaining to the data units communicated to or from the specified IoT device over the defined time interval.

### Claim 6 (depends on 5)

The system according to claim 5, wherein the statistical information includes number of data units per time interval per protocol or per a selected set of protocols.

### Claim 7 (depends on 6)

The system according to claim 6, wherein:
the data units comprise Ethernet frames, and
the statistical information includes number of Ethernet frames per time interval per EtherType value, the EtherType value being indicative of an encapsulated protocol.

### Claim 8 (depends on 5)

The system according to claim 5, wherein the statistical information includes number of data units per time interval per data prioritization class.

### Claim 9 (depends on 5)

The system according to claim 5, wherein the statistical information includes data unit length distribution per time interval.

### Claim 10 (depends on 5)

The system according to claim 5, wherein the statistical information comprises statistics on selected contents of payload of the data units per time interval.

### Claim 11 (depends on 1)

The system according to claim 1, wherein:
the data processing module is configured to create a graphical image from the quantitative information, the graphical image representing the temporal data traffic fingerprint of the specified IoT device, and
the artificial intelligence module is configured to classify the graphical image representing the temporal data traffic fingerprint into one of a plurality of learned data traffic fingerprint types, to deduce the device identifying information of the specified IoT device.

### Claim 12 (depends on 1)

The system according to claim 1, wherein the device identifying information comprises information on device type.

### Claim 13 (depends on 12)

The system according to claim 12, wherein the device identifying information further comprises information on device type variant.

### Claim 14 (depends on 1)

The system according to claim 1, wherein the system is embedded in a router-switch.

### Claim 15 (depends on 1)

The system according to claim 1, wherein the system is distributed across of a plurality of computing devices.

### Claim 16

A computer-implemented method for obtaining information about an Internet of Things (IoT) device connected to a network, the method comprising:
receiving a collection of data units communicated to or from a specified IoT device of a plurality of IoT devices connected to a network,
processing quantitative information pertaining to the data units communicated to or from the specified IoT device collected over a defined time interval, to create a temporal data traffic fingerprint of the specified IoT device, and
deducing device identifying information of the specified IoT device from the temporal data traffic fingerprint of the specified IoT device using a machine learning model.

### Claim 17 (depends on 16)

The method according to claim 16, wherein the processing of the quantitative information comprises creating statistical information pertaining to the data units communicated to or from the specified IoT device over the defined time interval.

### Claim 18 (depends on 17)

The method according to claim 17, wherein the statistical information comprises one or more of:
number of data units per time interval per protocol or per a selected set of protocols,
number of data units per time interval per data prioritization class,
data unit length distribution per time interval, and
statistics on selected contents of payload of the data units per time interval.

### Claim 19 (depends on 16)

The method according to claim 16, comprising:
creating a graphical image from the quantitative information, the graphical image representing the temporal data traffic fingerprint of the specified IoT device, and
classifying the graphical image representing the temporal data traffic fingerprint into one of a plurality of learned data traffic fingerprint types using the machine learning model, to deduce the device identifying information of the specified IoT device.

### Claim 20 (depends on 16)

The method according to claim 16, wherein the device identifying information comprises information on device type.

### Claim 21 (depends on 16)

A non-transitory computer-readable storage medium including instructions that, when processed by a computer, configure the computer to perform the method according to claim 16.

### Claim 22

(canceled)
