Back to results
US 11,902,328 B2Granted
Network device identification
AssigneeOrdr Inc.
InventorsVivekanandan Vinayagam, Gnanaprakasam Pandian, Sheausong Yang, Vijayaraghavan Doraiswami
Life of this patent
Estimating the term…
Abstract
Machine learning techniques are described for analyzing information network traffic to identify different devices connected to a network. Transmitted network packets may be passively collected and analyzed. In some cases the described techniques may be used to identify distinct devices connected to a network even though the collected and analyzed packets may lack a unique device identifier, such as a media access control (MAC) identifier, corresponding to a device that originated the packets.
Claims21
A non-transitory computer readable medium comprising instructions which, when executed by one or more hardware processors, cause performance of operations comprising:
- training a machine learning model to determine a device type of a device based on communications transmitted by the device and/or communications received by the device, the training comprising:
- obtaining training data sets of historical data, each training data set of historical data comprising:
- a set of communications transmitted to or transmitted by a particular device;
- a device type of the particular device;
- training the machine learning model based on the training data sets;
- obtaining a first plurality of data packets transmitted within a first communication session corresponding to a first device on a network;
- applying the machine learning model to the first plurality of data packets to determine a first device type corresponding to the first device;
- generating a first device profile corresponding to the first device of the first device type, wherein the first device profile is associated with a first device identifier;
- obtaining a second plurality of data packets transmitted within a second communication session corresponding to a second device on the network;
- applying the machine learning model to the second plurality of data packets to determine a second device type corresponding to the second device;
- generating a second device profile corresponding to the second device of the second device type, wherein the second device profile is associated with a second device identifier that is different from the first device identifier;
- responsive at least to determining that the first device type and the second device type are identical, determining that the first device is the same as the second device;
- responsive to determining that the first device and the second device are the same device:
- merging the first device profile and the second device profile into a single device profile based on the first plurality of data packets and the second plurality of data packets, wherein the single device profile is associated with the first device identifier and not associated with the second device identifier;
- and
- presenting at least a portion of the single device profile.
13 more elements
A method comprising:
- training a machine learning model to determine a device type of a device based on communications transmitted by the device and/or communications received by the device, the training comprising:
- obtaining training data sets of historical data, each training data set of historical data comprising:
- a set of communications transmitted to or transmitted by a particular device;
- a device type of the particular device;
- training the machine learning model based on the training data sets;
- obtaining a first plurality of data packets transmitted within a first communication session corresponding to a first device on a network;
- applying the machine learning model to the first plurality of data packets to determine a first device type corresponding to the first device;
- generating a first device profile corresponding to the first device of the first device type, wherein the first device profile is associated with a first device identifier;
- obtaining a second plurality of data packets transmitted within a second communication session corresponding to a second device on the network;
- applying the machine learning model to the second plurality of data packets to determine a second device type corresponding to the second device;
- generating a second device profile corresponding to the second device of the second device type, wherein the second device profile is associated with a second device identifier that is different from the first device identifier;
- responsive at least to determining that the first device type and the second device type are identical, determining that the first device is the same as the second device;
- responsive to determining that the first device and the second device are the same device:
- merging the first device profile and the second device profile into a single device profile based on the first plurality of data packets and the second plurality of data packets, wherein the single device profile is associated with the first device identifier and not associated with the second device identifier;
- and
- presenting at least a portion of the single device profile.
13 more elements
A system comprising:
- at least one device including a hardware processor;
- the system being configured to perform operations comprising:
- training a machine learning model to determine a device type of a device based on communications transmitted by the device and/or communications received by the device, the training comprising:
- obtaining training data sets of historical data, each training data set of historical data comprising:
- a set of communications transmitted to or transmitted by a particular device;
- a device type of the particular device;
- training the machine learning model based on the training data sets;
- obtaining a first plurality of data packets transmitted within a first communication session corresponding to a first device on a network;
- applying the machine learning model to the first plurality of data packets to determine a first device type corresponding to the first device;
- generating a first device profile corresponding to the first device of the first device type, wherein the first device profile is associated with a first device identifier;
- obtaining a second plurality of data packets transmitted within a second communication session corresponding to a second device on the network;
- applying the machine learning model to the second plurality of data packets to determine a second device type corresponding to the second device;
- generating a second device profile corresponding to the second device of the second device type, wherein the second device profile is associated with a second device identifier that is different from the first device identifier;
- responsive at least to determining that the first device type and the second device type are identical, determining that the first device is the same as the second device;
- responsive to determining that the first device and the second device are the same device:
- merging the first device profile and the second device profile into a single device profile based on the first plurality of data packets and the second plurality of data packets, wherein the single device profile is associated with the first device identifier and not associated with the second device identifier;
- and
- presenting at least a portion of the single device profile.
15 more elements
Dependencies are inferred from the claim text.