Strategies for providing novel recommendations

A system comprising:

• one or more processors;
• memory;
• and
• a recommendation-generating module, stored in the memory and executable on the one or more processors, the recommendation-generating module comprising:
• logic configured to generate a set of original recommendations based at least in part on at least one source of information;
• logic configured to generate a set of novel recommendations from the set of original recommendations based at least in part on repulsion force analysis applied to the set of original recommendations, wherein the repulsion force analysis ensures that at least one recommendation is separated from a reference by at least a sufficient amount to provide a desired degree of variation between said at least one recommendation and the reference;
• and
• logic configured to provide the set of novel recommendations to a user,
• wherein the reference is known information that identifies at least one known interest of the user, such that the repulsion force analysis ensures that said at least one recommendation is separated from the known information by the sufficient amount.

A method for generating novel recommendations, the method implemented at least in part by a computing device and comprising:

• receiving a set of original recommendations which have been generated based at least in part on at least one source of information;
• generating a set of novel recommendations from the set of original recommendations based at least in part on repulsion force analysis applied to the set of original recommendations, wherein the repulsion force analysis ensures that at least one recommendation is separated from a reference by at least a sufficient amount to provide a desired degree of variation between said at least one recommendation and the reference;
• and
• providing the set of novel recommendations to a user;
• wherein the reference is known information that identifies at least one known interest of the user, such that the repulsion force analysis ensures that said at least one recommendation is separated from the known information by the sufficient amount.

A method for generating novel recommendations, the method implemented at least in part by a computing device and comprising:

• receiving a set of original recommendations which have been generated based at least in part on at least one source of information;
• generating a set of novel recommendations which improve novelty in the set of original recommendations by:
• determining known items concerning which the user is presumed to have prior knowledge;
• expanding the known items to include a collection of items which are determined to be related to the known items, to provide an expanded set of items;
• identifying whether any members of the expanded set of items are present in the set of original recommendations to define obvious original recommendations;
• and
• reducing he concentration of the obvious original recommendations in the set of original recommendations, to yield the set the novel recommendations;
• and
• providing the set of novel recommendations to a user.

A method for generating novel recommendations, the method implemented at least in part by a computing device and comprising:

• receiving a set of original recommendations which have been generated based at least in part on at least one source of information;
• generating a set of novel recommendations from the set of original recommendations through the use of cluster analysis, wherein the generating ensures that at lest one recommendation is separated from a reference by at least a sufficient amount to provide a desired degree of variation between said at least one recommendation and the reference;
• and
• providing the set of novel recommendations to a user,
• wherein the reference is known information that identifies at least one known interest of the user, such that the cluster analysis ensures that said at least one recommendation is separated from the known information by the sufficient amount.

A method comprising:

• under control of one or more computer systems configured with executable instructions,
• providing at least one source of information from which to generate recommendations;
• generating a first set of recommendations based at least in part on said at least one source of information;
• generating a second set of recommendations from the first set of recommendations based at least in part on repulsion force analysis applied to the first set of recommendations, wherein the repulsion force analysis ensures that at least one recommendation is separated from a reference by at least a sufficient amount to provide a desired degree of variation between said at least one recommendation and the reference;
• and
• providing the second set of recommendations to a user,
• wherein the reference is known information that identifies at least one known interest of the user, such that the repulsion force analysis ensures that said at least one recommendation is separated from the known information by the sufficient amount.