Recommendation network

• US 9,514,236 B2
• Filed: 11/15/2011
• Issued: 12/06/2016
• Est. Priority Date: 08/19/2005
• Status: Active Grant

• Current Assignee: SitNet LLC
• Original Assignee: Resource Consortium Limited
• Inventors: Evans, Matthew R., Salgado, Daniel L.
• Primary Examiner(s): Hill, Stanley K
• Assistant Examiner(s): Traktovenko, Ilya
• Application Number:
  US13/373,501
• Publication Number:
  US 20120221505A1
• Time in Patent Office: 1,848 Days
• Field of Search: 706/55, 706/46, 706/45, 706/62
• US Class Current: 1/1
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
• CPC Class Codes: G06Q 10/10 Office automation; Time management

Abstract

A recommendation network is described. In some embodiments, the recommendation network includes recommenders that explicitly or implicitly recommend, rate or refer items and recommendation receivers that receive the recommendations. In some embodiments, the recommenders can be recommendation receivers, and vice versa. In some embodiments, recommendation receivers assign rust ratings to recommenders. The recommendation receiver can assign separate trust ratings to individual topics for which the recommendation receiver trusts the recommender. The separate trust ratings represent the recommendation receiver'"'"'s amount of trust in the recommender to makes valuable recommendations for the specific topic. The recommendation network can use the separate trust ratings, along with ratings provided by the recommender, to rank recommendations per the separate topics. The recommendation receiver can assign the recommender to different bundles, topics, channels, etc. to which other recommendation receivers can subscribe.

Claims

1. A system comprising:

one or more processors; and

one or more modules configured to store instructions, which when executed by at least one of the one or more processors, cause the system to perform operations to;

detect a recommendation, by a recommendation source to a receiver of the recommendation, of digital content hosted by a digital content host, wherein the digital content host is distinct from the recommendation source and the recommendation of the digital content is associated with a topic,

detect a first value that relates the recommendation source to the receiver of the recommendation specifically for prior recommendations of digital content, from a plurality of digital content hosts, that is associated with the topic, and

calculate a second value associated with the digital content based on the first value.

2. The system of claim 1, wherein the operation to calculate the second value includes an operation to compute the first value with a third value that represents degree of one or more of recommendation of, preference for, dislike of, knowledge of, use of, and interaction with the digital content by the source and wherein the third value is one or more of implied and non-implied.

3. The system of claim 1, wherein the one or more modules are configured to store instructions, which when executed by at least one of the one or more processors, cause the system to further perform an operation to assign the first value based on one or more of a default value to assign to recommendations for the topic when the recommendations for the topic have not been assigned a rating that indicates a degree of recommendation, a value proportional to the first value, an average rating by the source for previously recommended digital content on the topic, a value equivalent to ratings associated with a network address from which the recommendation originates, a value based on a degree of preference for additional digital content on the topic previously recommended by the source, and rating for the digital content provided by an additional source with a trust rating that is greater than or equal to the first value.

4. The system of claim 1, wherein the one or more modules are configured to store instructions, which when executed by at least one of the one or more processors, cause the system to further perform an operation to determine a location within a user interface on which to place a reference for the digital content based on one or more of first value, the second value, and a third value that indicates a relationship between the source and the digital content.

5. The system of claim 1, wherein the first value is assigned to the source based on information from one or more user accounts socially interrelated with the source within a social network, wherein the receiver of the recommendation is one of the one or more user accounts.

6. The system of claim 5, wherein the one or more modules are configured to store instructions, which when executed by at least one of the one or more processors, cause the system to further perform an operation modify the first value based on one or more of an indication of approval of the digital content by at least one of one or more user accounts, an additional recommendation of the digital content by the receiver of the recommendation to an additional one of the one or more user accounts, a duration of time that the first value has been assigned to the source, an amount of trust ratings assigned to the source for the topic by the one or more user accounts, and a degree of social networking interaction between the source and the one or more user accounts.

7. The system of claim 1, wherein the one or more modules are configured to store instructions, which when executed by at least one of the one or more processors, cause the system to further perform operations to:

detect an indication of opinion by the receiver of the recommendation regarding the digital content,

generate a proposed degree of modification to the first value in response to detection of the indication of opinion, and

provide, for presentation via a user interface associated with the receiver of the recommendation, the proposed degree of modification.

8. The system of claim 1, wherein the one or more modules are configured to store instructions, which when executed by at least one of the one or more processors, cause the system to further perform operations to:

detect possession by the source of a token that originated from the receiver of the recommendation, wherein the token indicates a third value that specifies a preference by the receiver for one or more of the source and the topic, and

one or more of calculate the second value based on the first value and the third value and modify the first value according to the third value.

9. A computer-implemented method, comprising:

detecting a recommendation to digital content, wherein the digital content is hosted by a digital content host and the digital content host is not a source of the recommendation;

detecting a rating associated, via a user account, with the source of the recommendation;

detecting via one or more processors, user input regarding one or more of the digital content and the recommendation, wherein the user input is associated with the user account, and

modifying, via at least one of the one or more processors, the rating associated with the source based on the user input.

10. The computer-implemented method of claim 9, wherein the detecting the user input regarding the one or more of the digital content and the recommendation comprises detecting one or more of an indication of approval of the one or more of the digital content and the recommendation via the user account, an indication of disapproval of the one or more of the digital content and the recommendation via the user account, an assignment of a digital content rating via the user account, a forwarding of the recommendation via the user account and detecting a purchase associated with the digital content via the user account.

11. The computer-implemented method of claim 9, wherein the modifying the rating associated with the source based on the user input comprises:

computing a degree of modification to make to the rating based on a value associated with the user input; and

modifying the rating according to the degree of modification.

12. The computer-implemented method of claim 11, wherein the value associated with the user input is associated with one or more of a degree of approval of the one or more of the digital content and the recommendation via the user account, a degree of disapproval of the one or more of the digital content and the recommendation via the user account, a degree of difference between a first content rating made by the source of the recommendation and a second digital content rating made via the user account, a degree of forwarding of the recommendation via the user account, an amount of a purchase associated with the digital content via the user account, and a degree of social networking interaction between the source of the recommendation and the user account concerning the one or more of the recommendation and the digital content.

13. The computer-implemented method of claim 9 further comprising:

determining a digital content rating;

performing a computation of the digital content rating and the rating associated with the source;

calculating a score for the one or more of the digital content and the recommendation in response to the performing the computation and,

providing the score to use for presentation of one or more of the digital content and the recommendation.

14. The computer-implemented method of claim 13 wherein the determining the digital content rating comprises one or more of:

receiving the digital content rating with the recommendation to the digital content, wherein the digital content rating is a representation of a degree of preference for the digital content by the source of the recommendation; and

generating the digital content rating subsequent to receiving the recommendation wherein the digital content rating represents an implied degree of preference that the source has for the digital content.

15. A system comprising:

one or more processors; and

one or more modules configured to store instructions, which when executed by at least one of the one or more processors, cause the system to perform operations to;

detect a recommendation, by a recommendation source to a receiver of the recommendation, of digital content hosted by a digital content host, wherein the recommendation source is distinct from the digital content host and the recommendation of the digital content is associated with a topic,

detect a first value that relates the recommendation source to the receiver of the recommendation specifically for prior recommendations of digital content, from a plurality of digital content hosts, that is associated with the topic, and,

calculate a second value associated with the digital content based on the first value.