Generating item recommendations
AssigneeAmazon Technologies, Inc.
InventorBharath Kumar
Life of this patent
Estimating the term…
Abstract
Disclosed are various embodiments of systems, methods, and programs embodied in computer readable mediums for generating item purchase recommendations. To provide such a recommendation, first data is accessed using a server, the first data comprising an interaction history of an entity with respect to at least one network site. Also, second data is accessed using the server, the second data comprising a record of use of media by the entity on at least one media device remote to the server. An item recommendation is generated in the server for the entity based on the first and second data.
Claims20
A system, comprising:
- at least one server;
- and
- recommendation logic executable on the at least one server, the recommendation logic comprising:
- logic that generates a recommendation for a plurality of items for an entity based on first data and second data, the first data comprising an interaction history of the entity with respect to at least one network site, and the second data comprising a record of use of a media by the entity on at least one media device remote to the at least one server;
- logic that identifies a category of use of the media associated with the entity in the record of use of the media by the entity;
- logic that draws an association between the category of use of the media and a current interaction with the at least one network site by the entity, wherein the recommendation is further generated based upon the category of use of the media;
- and
- an electronic commerce application executable on the at least one server in conjunction with the at least one network site, the electronic commerce application being configured to accept a compensation from the entity in exchange for the media through the at least one network site, where the electronic commerce application is configured to serve up the recommendation to a client associated with the entity.
A system, comprising:
- at least one server;
- and
- recommendation logic executable on the at least one server, the recommendation logic comprising:
- logic that generates a recommendation for a plurality of items for an entity based on first data and second data;
- the first data comprising an interaction history of the entity with respect to an electronic commerce application executable on the at least one server, the electronic commerce application being configured to accept a compensation from the entity through at least one network site;
- and
- the second data comprising a record of use of a media by the entity on at least one media device remote to the at least one server.
A non-transitory computer-readable medium embodying an application executable in a computing device, comprising:
- code that generates a recommendation for a plurality of items for an entity based at least upon an interaction history of the entity with respect to at least one network site and a record of use of a media by the entity on at least one media device remote to at least one server;
- code that identifies a category of use of the media associated with the entity in the record of use of the media by the entity;
- and
- code that draws an association between the category of use and a current interaction with the at least one network site by the entity, wherein the recommendation is further generated based upon the category of use associated with the entity.
Dependencies are inferred from the claim text.