Social learning inferencing engine for intelligent agent environment
First Claim
1. A social learning inferencing engine implemented as a computer process on a distributed data base to predict a user'"'"'s score for objects on the distributed data base, said process comprising the steps of:
- establishing a user class containing member fields that identify the user, specify configuration values specific to the user, and links to objects that the user has scored or referenced;
establishing an object class containing member fields that identify an object and links to user objects that have scored or referenced the object;
associating user object links to actual scores given by the user for the objects, a comment given by the user and associated with the score, and a number of references made by the user to the objects;
calculating similarity measures for each user class to every other user class and similarity measures for each object class to every other object class based on the scores and the number of references associated with the user object links;
using the similarity measures of the user classes and the similarity measures of the object classes to predict a score that the user would give the object; and
displaying objects to the user that have a predicted score above a threshold set by the user.
1 Assignment
0 Petitions
Accused Products
Abstract
A social learning inferencing engine for a wide range of information searching applications is generally applicable to a wide range of applications due to the engine'"'"'s interfaces and the objects involved in these interfaces. The basic interfaces are a record of a user'"'"'s score of a object, a count of the number of times a user references an object, and a prediction of a user'"'"'s score of a object given the user has not previously scored the object. The scores of this user and other users strongly similar or strongly dissimilar to this user for this object and other objects strongly similar or strongly dissimilar to this object are used in making this prediction. The two central object classes in the system are the users and the objects. The user object class contains member fields that identify the user, specify configuration values specific to this user (these configuration values being used in predicting the scores of the objects for this user), and links to objects that the user has scored or referenced. The object class contains member fields that identify the object and links to user objects that have scored or referenced this object.
-
Citations
10 Claims
-
1. A social learning inferencing engine implemented as a computer process on a distributed data base to predict a user'"'"'s score for objects on the distributed data base, said process comprising the steps of:
-
establishing a user class containing member fields that identify the user, specify configuration values specific to the user, and links to objects that the user has scored or referenced; establishing an object class containing member fields that identify an object and links to user objects that have scored or referenced the object; associating user object links to actual scores given by the user for the objects, a comment given by the user and associated with the score, and a number of references made by the user to the objects; calculating similarity measures for each user class to every other user class and similarity measures for each object class to every other object class based on the scores and the number of references associated with the user object links; using the similarity measures of the user classes and the similarity measures of the object classes to predict a score that the user would give the object; and displaying objects to the user that have a predicted score above a threshold set by the user. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A social learning inferencing engine implemented as a computer process on a distributed data base to predict a user'"'"'s score for objects on the distributed data base, said process comprising the steps of:
-
establishing a user class containing member fields that identify the user, specify configuration values specific to the user, and links to objects that the user has scored or referenced; establishing an object class containing member fields that identify an object and links to user objects that have scored or referenced the object; associating user object links to actual scores given by the user for the objects, a comment given by the user and associated with the score, and a number of references made by the user to the objects; calculating similarity measures for each user class to every other user class and similarity measures for each object class to every other object class based on the scores and the number of references associated with the user object links; using the similarity measures of the user classes and the similarity measures of the object classes to predict a score that the user would give the object; displaying objects to the user that have a predicted score above a threshold set by the user, wherein the distributed data base is the Internet, and the computer process is a proxy application on a server in the Internet, wherein the objects are Uniform Resource Locators (URLs) on the World Wide Web (WWW) allowing the user to assign scores for URLs displayed; and highlighting URLs displayed by the user that have a predicted score higher or lower than thresholds set by the user.
-
-
10. A social learning inferencing engine implemented as a computer process on a distributed data base to predict a user'"'"'s score for objects on the distributed data base, said process comprising the steps of:
-
establishing a user class containing member fields that identify the user, specify configuration values specific to the user, and links to objects that the user has scored or referenced; establishing an object class containing member fields that identify an object and links to user objects that have scored or referenced the object; associating user object links to actual scores given by the user for the objects, a comment given by the user and associated with the score, and a number of references made by the user to the objects; calculating similarity measures for each user class to every other user class and similarity measures for each object class to every other object class base on the scores and the number of references associated with the user object links; using the similarity measures of the user classes and the similarity measures of the object classes to predict a score that the user would give the object; displaying objects to the user that have a predicted score above a threshold set by the user, wherein the distributed data base is the Internet, and the computer process is a proxy application on a server in the Internet, wherein the objects are Uniform Resource Locators (URLs) on the World Wide Web (WWW) allowing the user to assign scores for URLs displayed, wherein the scores assignable by the user are within a predefined range, and wherein the predefined range includes negative scores and the step of predicting includes predicting negative scores.
-
Specification