Activity Stream-Based Recommendations System and Method
AssigneeManyWorlds, Inc.
InventorsSteven Dennis Flinn, Naomi Felina Moneypenny
Life of this patent
Estimating the term…
Abstract
A computer-implemented activity stream-based recommendations system delivers recommendations in accordance with a selected item of an activity stream, inferences of interests based on usage behaviors, and a contextual neighborhood of objects. In addition, or alternatively, the recommendations may be generated in accordance with an inference of expertise. The contents of the objects in the activity stream may be generated by humans or automatically by a processor-based device. Explanations for the recommendations may be delivered to recommendation recipients.
Claims20
A computer-implemented method, comprising:
- using a first computer-implemented system to receive an activity stream, wherein the activity stream comprises a first plurality of computer-implemented objects, wherein the objects are temporally sequenced;
- selecting an object of the first plurality of objects as a context for a recommendation;
- and
- receiving a recommendation of a computer-implemented object, wherein the recommendation is generated by a recommender function executed on a processor-based computing device, wherein the recommender function generates the recommendation based, at least in part, on an inference of the recommendation recipient's interests from a plurality of usage behaviors and a contextualization, wherein the contextualization comprises affinities between the selected object and a second plurality of objects.
A computer-implemented system, comprising:
- a computer-implemented activity stream function that delivers to a user an activity stream comprising a first plurality of objects originating from a first system, wherein the first plurality of objects are temporally sequenced;
- and
- a recommender function executed on a processor-based computing device, wherein the recommender function generates the recommendation for delivery to the user responsive to a user-selected object of the activity stream and based, at least in part, on an inference of the user's interests from a plurality of usage behaviors and a contextualization, wherein the contextualization comprises affinities between the selected object and a second plurality of objects.
A computer-implemented system, comprising:
- an activity stream function executed on a processor-based device, wherein the activity stream function displays a plurality of temporally sequenced objects;
- and
- a computer-implemented recommender that generates a recommendation of a first user for delivery to a second user in response to a selection of an object of the plurality of objects, wherein the recommendation is generated in accordance with the selected object and an inference of a level of expertise.
Dependencies are inferred from the claim text.