Neural Network-based Recommender Method and System
A neural network-based recommender method and system applies computer-implemented neural networks to match information within computer-implemented content objects that contain, for example, text and/or images. The matching of the information is combined with an evaluation of the computer-implemented objects based upon user behaviors to generate computer-implemented topics. Affinities among the topics or among users and the topics are generated based on the matching of the information and the evaluation of the computer-implemented objects. Recommendations are generated for delivery to users based upon the generated topics and affinities. The topics and/or affinities may be based upon inferences of expertise levels.
1 . A computer-implemented method, comprising:
matching automatically information that is within a plurality of computer-implemented content objects, wherein the matching is performed by application of a computer-implemented neural network;
evaluating automatically the plurality of computer-implemented content objects, wherein the evaluating is based upon user behavioral information;
generating automatically a plurality of computer-implemented topics in accordance with the matching of the information and the evaluating of the plurality of computer-implemented content objects;
generating automatically affinities among the computer-implemented topics in accordance with the matching of the information and the evaluating of the plurality of computer-implemented content objects; and
generating automatically a recommendation for delivery to a user, wherein the recommendation is based on the plurality of computer-implemented topics and the affinities among the computer-implemented topics.
2 . The method of claim 1 , further comprising:
matching automatically the information that is within the plurality of computer-implemented content objects, wherein the information comprises text.
3 . The method of claim 1 , further comprising:
matching automatically the information that is within a plurality of computer-implemented content objects, wherein the information comprises images.
4 . The method of claim 1 , further comprising:
matching automatically the information that is within the plurality of computer-implemented content objects, wherein the matching is based upon an inference of an expertise level.
5 . The method of claim 1 , further comprising:
evaluating automatically the plurality of computer-implemented content objects, wherein the evaluating is based upon an expertise level that is inferred from the user behavioral information.
6 . The method of claim 1 , further comprising:
generating automatically the recommendation for delivery to the user, wherein the recommendation is further based on affinities among the plurality of the computer-implemented topics and the plurality of content objects.
7 . The method of claim 1 , further comprising:
generating a communication that comprises an explanation for the recommendation, wherein the explanation references an expertise level.
8 . A computer-implemented system comprising one or more processor-based devices configured to:
match automatically information that is within a plurality of computer-implemented content objects, wherein the match is performed by application of a computer-implemented neural network;
evaluate automatically the plurality of computer-implemented content objects, wherein the evaluation is based upon user behavioral information;
generate automatically a plurality of computer-implemented topics in accordance with the match of the information and the evaluation of the plurality of computer-implemented content objects;
generate automatically affinities among the computer-implemented topics in accordance with the match of the information and the evaluation of the plurality of computer-implemented content objects; and
generate automatically a recommendation for delivery to a user, wherein the recommendation is based on the plurality of computer-implemented topics and the affinities among the computer-implemented topics.
9 . The system of claim 8 , further comprising the one or more processor-based devices configured to:
match automatically the information that is within the plurality of computer-implemented content objects, wherein the information comprises text.
10 . The system of claim 8 , further comprising the one or more processor-based devices configured to:
match automatically the information that is within the plurality of computer-implemented content objects, wherein the information comprises images.
11 . The system of claim 10 , further comprising the one or more processor-based devices configured to:
match automatically the information that is within the plurality of computer-implemented content objects, wherein the information comprises the images, wherein the images are elements of videos.
12 . The system of claim 8 , further comprising the one or more processor-based devices configured to:
evaluate automatically the plurality of computer-implemented content objects, wherein the evaluation is based upon an expertise level that is inferred from the user behavioral information.
13 . The system of claim 8 , further comprising the one or more processor-based devices configured to:
generate automatically the recommendation for delivery to the user, wherein the recommendation is further based on affinities among the plurality of the computer-implemented topics and the plurality of content objects.
14 . The system of claim 8 , further comprising the one or more processor-based devices configured to:
generating a communication that comprises an explanation for the recommendation, wherein the explanation references an expertise level.
15 . A computer-implemented system comprising one or more processor-based devices configured to:
match automatically information that is within a plurality of computer-implemented content objects, wherein the match is performed by application of a computer-implemented neural network;
evaluate automatically the plurality of computer-implemented content objects, wherein the evaluation is based upon user behavioral information;
generate automatically a plurality of computer-implemented topics in accordance with the match of the information and the evaluation of the plurality of computer-implemented content objects;
generate automatically affinities among a plurality of users of the computer-implemented system and the computer-implemented topics in accordance with the match of the information and the evaluation of the plurality of computer-implemented content objects; and
generate automatically a recommendation for delivery to a user, wherein the recommendation is based on the plurality of computer-implemented topics and the affinities among the plurality of users of the computer-implemented system and the computer-implemented topics.
16 . The system of claim 15 , further comprising the one or more processor-based devices configured to:
match automatically the information that is within the plurality of computer-implemented content objects, wherein the information comprises text.
17 . The system of claim 15 , further comprising the one or more processor-based devices configured to:
match automatically the information that is within the plurality of computer-implemented content objects, wherein the information comprises images.
18 . The system of claim 15 , further comprising the one or more processor-based devices configured to:
match automatically the information that is within the plurality of computer-implemented content objects, wherein the information comprises content that is published by users of the computer-implemented system.
19 . The system of claim 15 , further comprising the one or more processor-based devices configured to:
generate automatically the affinities among the plurality of users of the computer-implemented system and the computer-implemented topics based upon automatic inferences of user preferences from the user behavioral information.
20 . The system of claim 15 , further comprising the one or more processor-based devices configured to:
generate automatically the affinities among the plurality of users of the computer-implemented system and the computer-implemented topics based upon automatic inferences of expertise levels from the user behavioral information.