User behavior monitoring on a computerized device
AssigneeMicrosoft Technology Licensing, LLC
InventorsElad Yom-Tov, Eric J. Horvitz, Ryen William White, Munmun De Choudhury, Scott J Counts
Life of this patent
Estimating the term…
Abstract
The subject disclosure is directed towards monitoring user behavior on a computerized device for any deviation from normal or acceptable behavior that is likely to affect the user's mental state. A prediction model corresponding to features of one or more mental states may be compared with features based upon current user behavior. If the user's current behavior presents a mental state indicative of an uncharacteristic deviation from the normal or acceptable behavior, descriptive data associated with that mental state may be presented to the user in addition to a trusted individual, such as a health care professional.
Claims20
A method performed at least in part on at least one processor comprising:
- establishing, by a monitoring component implemented on the at least one processor, a behavior baseline for a user;
- obtaining, by the monitoring component, user interaction data comprising one or more of search engine queries and social media postings of the user;
- accessing a predictive model corresponding to features of at least one mental state;
- comparing the predictive model with the obtained user interaction data to identify a current mental state of the user based on the features of the at least one mental state and the one or more of the search engine queries and social media postings of the user;
- and
- in response to identifying a deviation between the identified current mental state and the established behavior baseline, generating description data for the identified current mental state.
In a computing environment, a computerized device or a configuration of coupled computerized devices, comprising:
- a prediction model corresponding to at least one mental state;
- and
- a monitoring mechanism configured to:
- obtain user interaction data comprising one or more of search engine queries and social media postings of a user;
- extract features from the user interaction data using the prediction model;
- determine whether a psychological event is evident from the extracted features;
- responsive to a determination that the psychological event is evident, generate a secure alert corresponding to the psychological event.
One or more computer storage media having computer-executable instructions, which on execution by a computer cause the computer to perform operations, comprising:
- generating at least one classifier built from at least one prediction model associated with at least one mental state;
- configuring the at least one classifier to monitor user interaction data for a symptom of a mental illness, the user interaction data including data comprising one or more of search engine queries and social media postings of a user via a user device;
- and
- processing feedback from the user device to update the at least one prediction model based at least in part on the user interaction data, including the data comprising the one or more of the search engine queries and the social media postings of the user.
Dependencies are inferred from the claim text.