Serendipity generating method, system, and device
A serendipity generating method, system, and device generates recommendations by identifying contrasting corresponding topic affinity values between users who more generally have a relatively high degree of similarity between corresponding topic affinity values. The topic affinity values may represent user interests with respect to topics and the topic affinity values may be inferred from usage behaviors, including geographic location information. Recommendations may be further in accordance with an assessment of the amount or quality of the usage behaviors from which the topic affinity values are derived and/or in accordance with the application of a probabilistic process. The recommendations may comprise computer-implemented objects that have relatively high affinities to topics associated with the contrasting corresponding topic affinity values.
1. A computer-implemented method, comprising:
selecting automatically a first affinity vector comprising a first plurality of topic affinity level values that are associated with a first user of a computer-implemented system, wherein a plurality of the first plurality of topic affinity level values are each based on an inference from a first one or more usage behaviors;
selecting automatically a second affinity vector comprising a second plurality of topic affinity level values that are associated with a second user of the computer-implemented system, wherein a plurality of the second plurality of topic affinity level values are each based on an inference from a second one or more usage behaviors, and wherein the selection of the second affinity vector is in accordance with a determination of a relatively high level of similarity between a plurality of the first plurality of topic affinity level values and a corresponding plurality of the second plurality of topic affinity level values;
identifying automatically one or more pairs of contrasting corresponding topic affinity level values by comparing topic affinity level values in the first affinity vector with topic affinity level values in the second affinity vector; and
generating automatically a recommendation for delivery to the first user, wherein the recommendation is generated in accordance with the one or more pairs of contrasting corresponding topic affinity level values.
2. The method of claim 1 , further comprising:
selecting automatically the first affinity vector comprising the first plurality of topic affinity level values that are associated with the first user of the computer-implemented system, wherein each of the first plurality of topic affinity level values is of an interest level of the first user with respect to a topic, wherein the topic is determined from an automatic analysis of content.
3. The method of claim 1 , further comprising:
determining the relatively high level of similarity between the plurality of the first plurality of topic affinity level values and the corresponding plurality of the second plurality of topic affinity level values, wherein the relatively high level of similarity is determined by performing a cosine similarity calculation.
4. The method of claim 1 , further comprising:
generating automatically the recommendation for delivery to the first user, wherein the recommendation is generated in accordance with the one or more pairs of contrasting corresponding topic affinity level values and an assessment of a relatively low inferential quality of the first one or more usage behaviors upon which the inference associated with one topic affinity level value of the one or more pairs of contrasting corresponding topic affinity level values is based.
5. The method of claim 1 , further comprising:
generating automatically the recommendation for delivery to the first user, wherein the recommendation is generated in accordance with the one or more pairs of contrasting corresponding topic affinity level values and an application of a probability distribution.
6. The method of claim 1 , further comprising:
generating automatically the recommendation for delivery to the first user, wherein the recommendation comprises a computer-implemented object that has a relatively high automatically determined affinity with at least one topic that is associated with the one or more pairs of contrasting corresponding topic affinity level values.
7. The method of claim 1 , further comprising:
generating automatically the recommendation for delivery to the first user, wherein the recommendation comprises a representation of the second user.
8. A system comprising one or more processor-based devices configured to:
select a first affinity vector comprising a first plurality of topic affinity level values that are associated with a first user of a computer-implemented system, wherein a plurality of the first plurality of topic affinity level values are each based on an inference from a first one or more usage behaviors;
select a second affinity vector comprising a second plurality of topic affinity level values that are associated with a second user of the computer-implemented system, wherein a plurality of the second plurality of topic affinity level values are each based on an inference from a second one or more usage behaviors, and wherein the selection of the second affinity vector is in accordance with a determination of a relatively high level of similarity between a plurality of the first plurality of topic affinity level values and a corresponding plurality of the second plurality of topic affinity level values;
identify one or more pairs of contrasting corresponding topic affinity level values by comparing topic affinity level values in the first affinity vector with topic affinity level values in the second affinity vector; and
generate a recommendation for delivery to the first user, wherein the recommendation is generated in accordance with the one or more pairs of contrasting corresponding topic affinity level values.
9. The system of claim 8 , further comprising the one or more processor-based devices configured to:
select the first affinity vector comprising the first plurality of topic affinity level values that are associated with the first user of the computer-implemented system, wherein each of the first plurality of topic affinity level values is of an interest level of the first user with respect to a topic.
10. The system of claim 9 , further comprising the one or more processor-based devices configured to:
generate the recommendation for delivery to the first user, wherein the recommendation comprises a computer-implemented object that is selected for the recommendation in accordance with the computer-implemented object having a relatively high automatically determined affinity with at least one topic that is associated with the one or more pairs of contrasting corresponding topic affinity level values.
11. The system of claim 8 , further comprising the one or more processor-based devices configured to:
generate the recommendation for delivery to the first user, wherein the recommendation is generated in response to a search request by the first user.
12. The system of claim 8 , further comprising the one or more processor-based devices configured to:
generate the recommendation for delivery to the first user, wherein the recommendation is generated in accordance with the one or more pairs of contrasting corresponding topic affinity level values and an assessment of a relatively low amount of the first one or more usage behaviors upon which the inference associated with one topic affinity level value of the one or more pairs of contrasting corresponding topic affinity level values is based.
13. The system of claim 12 , further comprising the one or more processor-based devices configured to:
generate a communication for delivery to the first user that comprises one or more words that convey a level of confidence in the recommendation, wherein the level of confidence is in accordance with the assessment of the relatively low amount of the first one or more usage behaviors.
14. The system of claim 8 , further comprising the one or more processor-based devices configured to:
generate the recommendation for delivery to the first user, wherein the recommendation is generated in accordance with the one or more pairs of contrasting corresponding topic affinity level values and an application of a probability distribution.
15. The system of claim 14 , further comprising the one or more processor-based devices configured to:
generate the recommendation for delivery to the first user, wherein the recommendation is generated in accordance with the one or more pairs of contrasting corresponding topic affinity level values and the application of the probability distribution, wherein the application of the probability distribution is tunable by the first user.
16. The system of claim 8 , further comprising the one or more processor-based devices configured to:
generate the recommendation for delivery to the first user, wherein the recommendation is generated in accordance with the one or more pairs of contrasting corresponding topic affinity level values and an expected learning value that could be derived from usage behaviors exhibited by the first user in response to the recommendation.
17. A portable processor-based device comprising:
geographic location monitoring hardware; and
one or more processors configured to:
receive geographic location information from the location monitoring hardware;
provide the geographic location information to an affinity vector function that generates a topic affinity vector comprising a first plurality of topic affinity level values that are associated with a user of the portable processor-based device, wherein a plurality of the first plurality of topic affinity level values are each derived from one or more usage behaviors, wherein at least one of the one or more usage behaviors comprises the geographic location information; and
receive a recommendation, wherein the recommendation is generated in accordance with an identification of one or more pairs of contrasting corresponding topic affinity level values that are determined by comparing the first topic affinity vector and a second topic affinity vector comprising a second plurality of topic affinity level values that is associated with another user of a computer-implemented system, wherein the second topic affinity vector is selected for the comparing based upon a determination of a relatively high level of similarity between a plurality of the first plurality of topic affinity level values and a corresponding plurality of the second plurality of topic affinity level values.
18. The system of claim 17 , further comprising the one or more processors configured to:
receive the recommendation, wherein at least one of the second plurality of topic affinity level values is derived from a geographic location that is associated with the other user.
19. The system of claim 18 , further comprising the one or more processors configured to:
receive the recommendation, wherein the recommendation is generated in accordance with the identification of the one or more pairs of contrasting corresponding topic affinity level values, wherein at least one value of the one or more pairs of contrasting corresponding topic affinity level values is derived from the geographic location that is associated with the other user.
20. The system of claim 19 , further comprising the one or more processors configured to:
receive the recommendation, wherein the recommendation comprises a reference to a physical object that is proximal to the geographic location that is associated with the other user.