Retailmenot, Inc.

Symantec Corporation

Lipphei Adam

David John Reese

Annette M Taberner-Miller

Sankalp Acharya

Nicholas James Shiffert

Chandrasekhar Cidambi

Rowan Trollope

Caskey L Dickson

Rachel Renee Bell

Provided is a process, including: obtaining a set of historical geolocations; segmenting the historical geolocations into a plurality of temporal bins; determining pairwise transition probabilities between a set of geographic places based on the historical geolocations; configuring a compute cluster by assigning subsets of the transition probabilities to computing devices in the compute cluster; receiving a geolocation stream indicative of current geolocations of individuals; selecting a computing device in the compute cluster in response to determining that the computing device contain transition probabilities for the received respective geolocation; selecting transition probabilities applicable to the received respective geolocation from among the subset of transition probabilities assigned to the selected computing device; predicting a subsequent geographic place based on the selected transition probabilities.

Scalable complex event processing with probabilistic machine learning models to predict subsequent geolocations

Provided is a process of selectively providing content to computing devices based on geographic proximity to dynamically detected events drawing crowds, the process including: obtaining, with one or more computers, data indicative of current geolocations of more than 5,000 mobile computing devices based on information reported by an application executing on the mobile computing devices; inferring, with one or more computers, that an event with a crowd is occurring based on the data indicative of the geolocations indicating an amount of people and a proximity of the people; selecting, with one or more computers, content in response to the inference; and sending, with one or more computers, the selected content to one or more user computing devices for presentation based on proximity between the one or more user computing devices and a geographic location of the event with the crowd.

Geotargeting of content by dynamically detecting geographically dense collections of mobile computing devices

Techniques for providing protection against unsafe links on a social networking website are disclosed. In one particular exemplary embodiment, the techniques may be realized as a method for providing protection against unsafe links on a social networking website comprising: receiving, from the social networking website, user profile data associated with a user of the social networking website, scanning, from the user profile data, a plurality of links, accessing a safety rating for each of the plurality of links, and outputting, to a client device associated with the user, a link analysis report that indicates the safety rating of one or more of the plurality of links.

Techniques for providing protection against unsafe links on a social networking website

Growing community of inventors

Austin, TX, United States of America

Lipphei Adam