System for generation of object profiles for a system for customized ...

1. A method for cataloging a plurality of target objects that are stored on an electronic storage media, where users are connected via user terminals and bidirectional data communication connections to a target server that accesses said electronic storage media, said method comprising the steps of:

storing on said electronic storage media each target object;

automatically generating in said target server, target profiles for each of said target objects that are stored on said electronic storage media, each of said target profiles being generated from the contents of an associated one of said target objects and their associated target object characteristics comprising:

automatically generating a hierarchical menu that directs said users to at least a subset of said plurality of target objects stored on said electronic media, comprising:

sorting all target objects in said subset into a plurality of clusters of target objects based on an empirical measure of similarity of content of said target objects, and

generating a hierarchical menu that identifies the content in common of target objects sorted into each of said plurality of clusters, to enable said identified user to identify ones of said plurality of target objects stored on said electronic storage media that are likely to be of interest to said identified user.

2. The method of claim 1 wherein said step of automatically generating a hierarchical menu further comprises:

ascribing a cluster profile to each of said plurality of clusters.

3. The method of claim 1 wherein said step of sorting comprises:

dividing said plurality of target objects into at least two clusters based upon said empirical measure of similarity of content of said target objects;

subdividing each of said at least two clusters into at least two subclusters based upon said empirical measure of similarity of content of said target objects contained in each said cluster; and

repeating said step of subdividing to produce a multi-level hierarchy of identified clusters.

4. The method of claim 3 wherein said step of generating a hierarchical menu comprises:

ascribing a cluster profile to each cluster produced by all steps of dividing and subdividing in said step of sorting.

5. The method of claim 4 wherein said step of ascribing comprises:

identifying at least one term in said generated target profiles produced for ones of said plurality of target objects sorted into a cluster that is indicative of the target content of said ones of said plurality of target objects sorted into said cluster.

6. The method of claim 4 wherein said step of ascribing comprises:

selecting at least one target object of said ones of said plurality of target objects sorted into said cluster that are closest to the center of the cluster, and

ascribing a cluster profile that is indicative of a content of said ones of said plurality of target objects sorted into said cluster, said cluster profile comprising elements of at least one of: a title of said selected at least one target object, and a set of words contained in the target profile of said selected at least one target object cluster which have the highest relative frequency.

7. A method for cataloging a plurality of target objects that are stored on an electronic storage media, where users are connected via user terminals and bidirectional data communication connections to a target server that accesses said electronic storage media, and wherein said sets of target object characteristics comprise sets of user interest characteristics for a virtual community of users, said method comprising the steps of:

storing on said electronic storage media each target object;

automatically generating in said target server, target profiles for each of said target objects that are stored on said electronic storage media, each of said target profiles being generated from the contents of an associated one of said target objects and their associated target object characteristics comprising:

automatically generating a hierarchical menu that directs a requesting one of said users to at least a subset of said sets of user interest characteristics for a virtual community of users stored on said electronic media, comprising:

sorting all sets of user interest characteristics for a virtual community of users in said subset into a plurality of clusters of target sets of user interest characteristics for a virtual community of users based on an empirical measure of similarity of content of said target sets of user interest characteristics for a virtual community of users, and

generating a hierarchical menu that identifies the content in common of target sets of user interest characteristics for a virtual community of users sorted into each of said plurality of clusters, to enable said requesting user to identify ones of said plurality of target sets of user interest characteristics for a virtual community of users stored on said electronic storage media that are likely to be of interest to said requesting user.

8. The method of claim 7 wherein said step of automatically generating a hierarchical menu further comprises:

ascribing a cluster profile to each of said plurality of clusters.

9. The method of claim 7 wherein said step of sorting comprises:

dividing said plurality of target sets of user interest characteristics for a virtual community of users into at least two clusters based upon said empirical measure of similarity of content of said target sets of user interest characteristics for a virtual community of users;

subdividing each of said at least two clusters into at least two subclusters based upon said empirical measure of similarity of content of said target sets of user interest characteristics for a virtual community of users contained in each said cluster; and

repeating said step of subdividing to produce a multi-level hierarchy of identified clusters.

10. The method of claim 9 wherein said step of generating a hierarchical menu comprises:

ascribing a cluster profile to each cluster produced by all steps of dividing and subdividing in said step of sorting.

11. The method of claim 10 wherein said step of ascribing comprises:

identifying at least one term in said generated target profiles produced for ones of said plurality of target sets of user interest characteristics for a virtual community of users sorted into a cluster that is indicative of the target content of said ones of said plurality of target sets of user interest characteristics for a virtual community of users sorted into said cluster.

12. The method of claim 10 wherein said step of ascribing comprises:

selecting at least one target set of user interest characteristics for a virtual community of users of said ones of said plurality of target sets of user interest characteristics for a virtual community of users sorted into said cluster that are closest to the center of the cluster, and

ascribing a cluster profile that is indicative of a content of said selected target set of user interest characteristics for a virtual community of users sorted into said cluster, said cluster profile comprising elements of at least one of: a characteristic of said selected at least one target user interest characteristics for a virtual community of users, and a set of words contained in the target profile of said selected at least one target object cluster which have the highest relative frequency.

13. Apparatus for cataloging a plurality of target objects that are stored on an electronic storage media, where users are connected via user terminals and bidirectional data communication connections to a target server that accesses said electronic storage media, said apparatus comprising:

means for storing on said electronic storage media each target; and

means for automatically generating in said target server, target profiles for each of said target objects and that are stored on said electronic storage media, each of said target profiles being generated from the contents of an associated one of said target objects their associated target object characteristics, comprising:

means for automatically generating a hierarchical menu that directs said users to at least a subset of said plurality of target objects stored on said electronic media, comprising:

means for sorting all target objects in said subset into a plurality of clusters of target objects based on an empirical measure of similarity of content of said target objects, and

means for generating a hierarchical menu that identifies the content in common of target objects sorted into each of said plurality of clusters, to enable said identified user to identify ones of said plurality of target objects stored on said electronic storage media that are likely to be of interest to said identified user.

14. The apparatus of claim 13 wherein said means for automatically generating a hierarchical menu further comprises:

means for ascribing a cluster profile to each of said plurality of clusters.

15. The apparatus of claim 13 wherein said means for sorting comprises:

means for dividing said plurality of target objects into at least two clusters based upon said empirical measure of similarity of content of said target objects;

means for subdividing each of said at least two clusters into at least two subclusters based upon said empirical measure of similarity of content of said target objects contained in each said cluster; and

means for repeating said cluster subdividing to produce a multi-level hierarchy of identified clusters.

16. The apparatus of claim 15 wherein said means for generating a hierarchical menu comprises:

means for ascribing a cluster profile to each cluster produced by all steps of dividing and subdividing in said step of sorting.

17. The apparatus of claim 16 wherein said means for ascribing comprises:

means for identifying at least one term in said generated target profiles produced for ones of said plurality of target objects sorted into a cluster that is indicative of the target content of said ones of said plurality of target objects sorted into said cluster.

18. The apparatus of claim 17 wherein said means for ascribing comprises:

means for selecting at least one target object of said ones of said plurality of target objects sorted into said cluster that are closest to the center of the cluster, and

means for ascribing a cluster profile that is indicative of a content of said ones of said plurality of target objects sorted into said cluster, said cluster profile comprising elements of at least one of: a title of said selected at least one target object, and a set of words contained in the target profile of said selected at least one target object cluster which have the highest relative frequency.

19. Apparatus for cataloging a plurality of target objects that are stored on an electronic storage media, where users are connected via user terminals and bidirectional data communication connections to a target server that accesses said electronic storage media, said apparatus comprising:

means for storing on said electronic storage media each target; and

means for automatically generating in said target server, target profiles for each of said target objects and that are stored on said electronic storage media, each of said target profiles being generated from the contents of an associated one of said target objects their associated target object characteristics, comprising:

means for automatically generating a hierarchical menu that directs a requesting one of said users to at least a subset of said sets of user interest characteristics for a virtual community of users stored on said electronic media, comprising:

means for sorting all sets of user interest characteristics for a virtual community of users in said subset into a plurality of clusters of target sets of user interest characteristics for a virtual community of users based on an empirical measure of similarity of content of said target sets of user interest characteristics for a virtual community of users, and

means for generating a hierarchical menu that identifies the content in common of target sets of user interest characteristics for a virtual community of users sorted into each of said plurality of clusters, to enable said requesting user to identify ones of said plurality of target sets of user interest characteristics for a virtual community of users stored on said electronic storage media that are likely to be of interest to said requesting user.

20. The apparatus of claim 19 wherein said means for automatically generating a hierarchical menu further comprises:

means for ascribing a cluster profile to each of said plurality of clusters.

21. The apparatus of claim 19 wherein said means for sorting comprises:

means for dividing said plurality of target sets of user interest characteristics for a virtual community of users into at least two clusters based upon said empirical measure of similarity of content of said target sets of user interest characteristics for a virtual community of users;

means for subdividing each of said at least two clusters into at least two subclusters based upon said empirical measure of similarity of content of said target sets of user interest characteristics for a virtual community of users contained in each said cluster; and

means for repeating said step of subdividing to produce a multi-level hierarchy of identified clusters.

22. The apparatus of claim 21 wherein said means for generating a hierarchical menu comprises:

means for ascribing a cluster profile to each cluster produced by all steps of dividing and subdividing in said step of sorting.

23. The apparatus of claim 22 wherein said means for ascribing comprises:

means for identifying at least one term in said generated target profiles produced for ones of said plurality of target sets of user interest characteristics for a virtual community of users sorted into a cluster that is indicative of the target content of said ones of said plurality of target sets of user interest characteristics for a virtual community of users sorted into said cluster.

24. The apparatus of claim 22 wherein said means for ascribing comprises:

means for selecting at least one target set of user interest characteristics for a virtual community of users of said ones of said plurality of target sets of user interest characteristics for a virtual community of users sorted into said cluster that are closest to the center of the cluster, and

means for ascribing a cluster profile that is indicative of a content of said selected target set of user interest characteristics for a virtual community of users sorted into said cluster, said cluster profile comprising elements of at least one of: a characteristic of said selected at least one target user interest characteristics for a virtual community of users, and a set of words contained in the target profile of said selected at least one target object cluster which have the highest relative frequency.