Social media recommendation engine

• US 9,679,338 B2
• Filed: 11/13/2012
• Issued: 06/13/2017
• Est. Priority Date: 11/13/2012
• Status: Active Grant

• Current Assignee: Nautilus True LLC
• Original Assignee: Quantum Capital Fund, LLC
• Inventors: Magcale, Arnold, Iracleous, Dane, Johns, Justin
• Primary Examiner(s): Bashore, William
• Assistant Examiner(s): CHOWDHURY, RAYEEZ R
• Application Number:
  US13/675,969
• Publication Number:
  US 20140136992A1
• Time in Patent Office: 1,673 Days
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/904 Browsing; Visualisation therefor for navigating the web G06F16/954; browsing optimisation for the web G06F16/957
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06F 40/117 Tagging; Marking up details of markup languages G06F40/143; Designating a block; Setting of attributes style sheets, e.g. eXtensible Stylesheet Language Transformation [XSLT], G06F40/154
• CPC Class Codes: G06F 40/177 of tables; using ruled lines
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Embodiments disclose a recommendation engine that implements a system and method for classifying users and media content, and for determining which media items a particular user will most likely enjoy. By organizing users and media content in a 3 dimensional virtual space and assigning x, y, and z coordinates to each, their relationship and affiliation with/to one another is defined by their distances from each other. When a user rates a media item highly, both that user and that media item move closer together. When a user gives a negative rating to a media item, they move farther apart. Further multiple users who rate the same media item similarly move closer together to form clusters of similar interest groups. This terraforms the virtual space into a natural attraction/separation of like-minded/different-minded users and similar/dissimilar media content.

Claims

1. A method for organizing and classifying users and user associated media content in a virtual space, comprising:

tagging all content in the virtual space;

assigning co-ordinates to the tagged content in the said space;

assigning every user a coordinate in the virtual space; and

determining user affiliation with the content in the virtual space, wherein said determining further comprises;

causing the said user and the said content item to travel with respect to each other through the same virtual space, wherein the said travel with respect to each other is based on the user rating of the content such that a high user rating causes the user and the rated content item to move closer together in the virtual space and a low user rating causes the user and the rated content item to move farther apart in the virtual space; and

maintaining number of ratings each media content item receives, wherein the greater the number of ratings received, the less the rated content item is caused to travel with each subsequent rating.

2. The method of claim 1 wherein assigning an initial user coordinate is determined based upon user response to a series of interactive queries presented to the user.

3. The method of claim 1 wherein the user coordinates are repeatedly altered in the virtual space, which alteration is determined by user interaction with the content.

4. The method of claim 1 wherein the said determining of user affiliation further comprises creating a vector between a user selected content item and the assigned user coordinates.

5. The method of claim 1 wherein determining the user affiliation further comprises receiving user rating of the user selected content item in the virtual space, and wherein the user affiliation with the content item is determined according to the user rating of the said content item.

6. The method of claim 5 wherein the user affiliation is at least one of a positive and a negative affiliation.

7. The method of claim 5 wherein a positive user rating causes the content item rated and the user'"'"'s coordinates to travel towards one another along their vector in the virtual space.

8. The method of claim 5 wherein a negative user rating received causes the content item rated and the user'"'"'s coordinates to travel away from one another along their vectors in the virtual space.

9. The method of claim 1 further comprising aggregating the ratings of the content items rated, identifying the users'"'"' rating the content items, and creating a single or plurality of user interest group clusters based on content items rated by the said users.

10. The method of claim 1 wherein the virtual space comprises multiple dimensions.

11. The method of claim 1 wherein the virtual space comprises three dimensions.

26. The method of claim 1 further comprising:

intelligently assigning a coordinate to each user and each content item in the virtual dimension;

adaptively determining the user affiliation with the said content item;

wherein said adaptively determining user affiliation comprises;

user rating of the content such that highly rated content is caused to move closer to the user in the virtual dimension, and lowly rated content is caused to move further away from the user in said virtual dimension;

calculating a vector between the content item and the user; and

determining how the content item should be positioned in relation to the user;

wherein the said determining comprises determining how close or far the content item should be moved from the user, which determining is further based on the rating by the user and at least one of the number of times it has been rated by that user and the number it has been rated by any user.

12. A computer automated system for organizing and classifying users and user associated media content in a virtual space, comprising a processing unit and a memory element, and having instructions encoded thereon, wherein the encoded instructions cause the system to:

assign a coordinate to each user in the virtual space;

assign a coordinate to each content item in the virtual space;

allow the user to rate a single or plurality of content items in the virtual space;

determine user affiliation based on their rating of the content;

wherein a high user rating causes the user and the rated content item to move closer together in the virtual space and a low user rating causes the user and the rated content to move farther apart in the virtual space; and

maintain the number of ratings each media content item receives, wherein the greater the number of ratings received, the less the rated content item is caused to travel through the virtual space.

13. The system of claim 12 wherein the instructions further cause the system to:

assign an initial user coordinate based upon user response to a series of interactive queries presented to the user.

14. The system of claim 12 wherein the instructions further cause the system to:

aggregate the ratings of the content items rated, identify the user'"'"'s rating the content items, and create a single or plurality of user interest group clusters based on content items rated by the said users.

15. The system of claim 12 wherein the virtual space comprises multiple dimensions.

16. The system of claim 12 wherein the virtual space comprises three dimensions.

27. The computer automated system of claim 12 wherein the system is further caused to, in the virtual space:

calculate a vector between the user and a consumed content item;

receive a user rating of the content item;

determine, based on the received rating, whether the user and the content item should move toward each other or away from each other in the virtual space;

determine, based on the rating received by the user, the amount that the user and the content item should shift in either direction in the virtual space;

wherein the greater the number of times that the content item has been rated, the lesser the severity of the shift for the content item for each subsequent rating; and

wherein the user'"'"'s movement is not hindered by that severity.

28. The computer automated of claim 12 wherein the system is further caused to:

intelligently assign a coordinate to each user and each content item in the virtual space;

adaptively determine the user affiliation with the said content item;

wherein the said adaptive determination of user affiliation comprises;

user rating of the content such that highly rated content is caused to move closer to the user in the virtual space, and lowly rated content is caused to move further away from the user in said virtual space;

calculating a vector between a consumed content item and the user; and

determine how the piece of content should be positioned in relation to the user;

wherein the said determining comprises determining how close or far the piece of content should be moved from the user, which determining is further based on the rating by the user and at least one of the number of times it has been rated by that user and the number it has been rated by any user.

17. A system for classifying and organizing users and media content in a multi-dimensional virtual space, and for determining which content a user will most likely enjoy, comprising:

a processing unit;

assigning a location to all content in the virtual space;

assigning a location to all users in the virtual space;

causing the said user and the said content item to travel with respect to each other through the same virtual space, wherein the said travel with respect to each other is based on the user rating of the content such that a high user rating causes the user and the rated content item to move closer together in the virtual space and a low user rating causes the user and the rated content item to move farther apart in the virtual space;

causing a user and the content to travel through the virtual space with respect to each other based on the user rating of a content item; and

maintain the number of ratings each media content item receives, wherein the greater the number of ratings received, the less the rated content item is caused to travel through the virtual space.

18. The system of claim 17 wherein assigning an initial user location is determined via user response to a series of interactive queries presented to the user.

19. The system of claim 17 wherein user location is repeatedly altered in the virtual space, and is determined by user interaction with the content.

20. The system of claim 17 wherein the user rating is at least one of a positive and a negative rating.

21. The system of claim 17 wherein a positive user rating causes the content item rated and the user'"'"'s coordinates to travel towards one another along their vector in the virtual space.

22. The system of claim 17 wherein a negative user rating causes the content item rated and the user'"'"'s coordinates to travel away from one another along their vector in the virtual space.

23. The system of claim 17 wherein the multi-dimensional virtual space is a three dimensional virtual space.

24. A method for intuitively organizing and classifying users and user associated content within a virtual dimension, comprising:

intelligently assigning a coordinate to each user and each piece of content in the virtual dimension;

adaptively determining the user affiliation with the said piece of content;

wherein said adaptively determining user affiliation comprises;

user rating of the content such that highly rated content is caused to move closer to the user in the virtual dimension, and lowly rated content is caused to move further away from the user in said virtual dimension;

calculating a vector between a user-viewed piece of content and the user; and

determining how the piece of content should be positioned in relation to the user;

wherein said determining comprises determining how close or far the piece of content should be moved from the user, which determining is further based on the rating by the user and at least one of the number of times it has been rated by that user and the number it has been rated by any user; and

maintaining number of ratings each media content item receives, wherein the greater the number of ratings received, the less the rated content item is caused to travel with each subsequent rating.

25. A system for intuitively organizing and classifying users and user associated content within a virtual dimension, comprising a processing unit and a memory element, and having thereon encoded instructions which cause the system to:

intelligently assign a coordinate to each user and each piece of content in the virtual dimension;

adaptively determine the user affiliation with the said piece of content;

wherein said adaptive determination of user affiliation comprises;

user rating of the content such that highly rated content is caused to move closer to the user in the virtual dimension, and lowly rated content is caused to move further away from the user in said virtual dimension;

calculating a vector between a user-viewed piece of content and the user; and

determine how the piece of content should be positioned in relation to the user;

wherein said determining comprises determining how close or far the piece of content should be moved from the user, which determining is further based on the rating by the user and at least one of the number of times it has been rated by that user and the number it has been rated by any user; and

maintaining number of ratings each media content item receives, wherein the greater the number of ratings received, the less the rated content item is caused to travel with each subsequent rating.