Online site prediction and mitigation
AssigneeInternational Business Machines Corporation
InventorsKelley Anders, Liam S. Harpur, Al Chakra, Robert H. Grant
Life of this patent
Estimating the term…
Abstract
Using natural language analysis of content at URLs accessed by a user, content metadata is generated. From the content metadata and from activity information associated with a set of URLs accessed by the user, a class model is generated that represents a probability that content referenced by a URL will distract the user. Using the class model to analyze content referenced by a received URL, a probability is forecasted that the content referenced by the received URL will distract the user.
Claims20
A method comprising:
- generating, using natural language analysis of content at URLs accessed by a user, content metadata;
- constructing, from the content metadata and from activity information associated with a set of URLs accessed by the user, a class model, the class model representing a probability that content referenced by a URL will distract the user;
- and
- forecasting, using the class model to analyze content referenced by a received URL, a probability that the content referenced by the received URL will distract the user.
A computer usable program product comprising one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices, the stored program instructions comprising:
- program instructions to generate, using natural language analysis of content at URLs accessed by a user, content metadata;
- program instructions to construct, from the content metadata and from activity information associated with a set of URLs accessed by the user, a class model, the class model representing a probability that content referenced by a URL will distract the user;
- and
- program instructions to forecast, using the class model to analyze content referenced by a received URL, a probability that the content referenced by the received URL will distract the user.
A computer system comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:
- program instructions to generate, using natural language analysis of content at URLs accessed by a user, content metadata;
- program instructions to construct, from the content metadata and from activity information associated with a set of URLs accessed by the user, a class model, the class model representing a probability that content referenced by a URL will distract the user;
- and
- program instructions to forecast, using the class model to analyze content referenced by a received URL, a probability that the content referenced by the received URL will distract the user.
Dependencies are inferred from the claim text.