Systems and methods for detecting unauthorized broadband internet access sharing
AssigneeRovi Guides, Inc.
InventorsSerhad Doken, Dhananjay Lal
Life of this patent
Estimating the term…
Abstract
Data describing broadband internet usage is collected from a user equipment device associated with each respective user account. The data are then input into a machine learning model that is trained on broadband internet usage data of a plurality of user accounts in a single geographic area. An n-dimensional metric for each user account is then obtained as output from the machine learning model. Using the n-dimensional metric, at least one candidate user account suspected of being engaged in broadband internet access sharing is identified, and a list of candidate user accounts is generated.
Claims24
A method for identifying user accounts engaged in broadband internet access sharing, the method comprising:
- collecting, from a respective user equipment device associated with each respective user account of a plurality of user accounts, data describing broadband internet usage;
- inputting the data into a machine learning model trained on broadband internet usage data of a plurality of user accounts in a single geographic area;
- obtaining, as output from the machine learning model, an n-dimensional metric for each respective user account;
- identifying, based on the n-dimensional metric of each respective user account of the plurality of user accounts, at least one candidate user account suspected of being engaged in broadband internet access sharing;
- and
- generating a list of candidate accounts suspected of being engaged in broadband internet access sharing.
A system for identifying user accounts engaged in broadband internet access sharing, the system comprising:
- input/output circuitry;
- and
- control circuitry configured to:
- collect, using the input/output circuitry, from a respective user equipment device associated with each respective user account of a plurality of user accounts, data describing broadband internet usage;
- input the data into a machine learning model trained on broadband internet usage data of a plurality of user accounts in a single geographic area;
- obtain, as output from the machine learning model, an n-dimensional metric for each respective user account;
- identify, based on the n-dimensional metric of each respective user account of the plurality of user accounts, at least one candidate user account suspected of being engaged in broadband internet access sharing;
- and
- generate a list of candidate accounts suspected of being engaged in broadband internet access sharing.
Dependencies are inferred from the claim text.