Techniques for targeting information to users

• US 8,438,164 B2
• Filed: 07/05/2007
• Issued: 05/07/2013
• Est. Priority Date: 12/22/1997
• Status: Expired due to Fees

• Current Assignee: Ricoh Company Limited
• Original Assignee: Ricoh Company Limited
• Inventors: Hull, Jonathan J., Graham, Jamey, Hart, Peter, Piersol, Kurt
• Primary Examiner(s): Trujillo, James
• Assistant Examiner(s): Black, Linh
• Application Number:
  US11/773,894
• Publication Number:
  US 20080005102A1
• Time in Patent Office: 2,133 Days
• Field of Search: 707/101, 707/104.1, 707/749, 707/738
• US Class Current: 707/738
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: Y10S 707/913 Multimedia
• CPC Class Codes: Y10S 707/922 Communications
• CPC Class Codes: Y10S 707/99942 Manipulating data structure, e.g. compression, compaction, compilation
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

Techniques for providing relevant information to a user based on information or documents accessed or viewed by the user. The relevant information is provided automatically to the user without requiring user input. The information provided to the user is selected from information provided by various content provider systems. The present invention uses several techniques to determine relevancy between the contents of the document accessed by the user and between the information provided by the content provider systems. The relevancy information is used to select information to be provided to the user.

Claims

1. A method of providing information to a user based upon contents of a first document displayed to the user, the method comprising:

identifying, by a computer system, at least a first section of the first document;

extracting, by the computer system, a first set of one or more information objects from the first section of the first document;

applying, by the computer system, a first selection technique to generate a first set of relevancy scores for information objects in a second set of information objects distinct from the first set of information objects, the first set of relevancy scores indicating the relevancy of information objects in the second set of information objects to information objects in the first set of information objects calculated using the first selection technique, the first selection technique being based on relevance of information objects in the first and second sets of information objects to concepts of interest to the user;

applying, by the computer system, a second selection technique to generate a second set of relevancy scores for information objects in the second set of information objects, the second set of relevancy scores indicating the relevancy of information objects in the second set of information objects to information objects in the first set of information objects calculated using the second selection technique, the second selection technique being based on classes of information objects in the first and second sets of information objects, the classes of information objects including text, audio, or video; and

selecting, by the computer system, a third set of one or more information objects from information objects in the second set of information objects based upon the first set of relevancy scores generated using the first selection technique and the second set of relevancy scores generated using the second selection technique, wherein information objects in the third set of information objects store information to be output to the user when the first document is being displayed to the user.

2. The method of claim 1, wherein the first set of information objects comprises at least a first information object including information of a first type, and wherein the second set of information objects comprises at least one information object including information of a second type, wherein the second type is different from the first type.

3. The method of claim 1 wherein the first section of the first document corresponds to a section of the first document displayed to the user, wherein the section of the first document displayed to the user is less than the entire first document.

4. The method of claim 1 wherein extracting the first set of information objects from the first section of the first document comprises:

for each information object in the first set of information objects;

identifying a type of the information object based upon contents of the information object;

determining a first content recognition technique based upon the type of the information object; and

applying the first content recognition technique to the information object to determine information related to the contents of the information object.

5. The method of claim 1 wherein selecting the third set of one or more information objects from the second set of information objects based upon the first set of relevancy scores and the second set of relevancy scores comprises:

for each information object in the second set of information objects;

calculating an aggregate relevancy score for the information object by aggregating a relevancy score in the first set of relevancy scores generated for the information object by applying the first selection technique and a relevancy score in the second set of relevancy scores generated for the information object by applying the second selection technique; and

selecting the information object to be included in the third set of information objects if the aggregate relevancy score calculated for the information object is above a threshold value.

14. The method of claim 1 wherein applying the first selection technique to generate the first set of relevancy scores comprises:

determining a first degree of relevancy between a first information object in the first set of information objects and a concept of interest to the user;

determining a second degree of relevancy between a second information object in the second set of information objects and the concept of interest to the user; and

determining, based on the first degree of relevancy and the second degree of relevancy, the relevancy of the second information object to the first information object as it relates to the concept of interest to the user.

15. The method of claim 1 wherein applying the second selection technique to generate the second set of relevancy scores comprises:

determining a class of a first information object in the first set of information objects;

determining a class of a second information object in the second set of information objects;

determining, based on the class of the first information object and the class of the second information object, a comparison technique for comparing contents of the first and second information objects; and

applying the comparison technique to determine the relevancy of the second information object to the first information object.

16. The method of claim 15 wherein the comparison technique is selected from a group consisting of:

text comparison technique, image similarity comparison technique, sound similarity comparison technique, and video similarity comparison technique.

17. The method of claim 1 wherein the concepts of interest to the user are retrieved from a user profile associated with the user.

6. A computer readable storage medium having stored thereon program code executable by a computer system, the program code comprising:

code for identifying at least a first section of a first document;

code for extracting a first set of one or more information objects from the first section of the first document;

code for applying a first selection technique to generate a first set of relevancy scores for information objects in a second set of information objects distinct from the first set of information objects, the first set of relevancy scores indicating the relevancy of information objects in the second set of information objects to information objects in the first set of information objects calculated using the first selection technique, the first selection technique being based on relevance of information objects in the first and second sets of information objects to concepts of interest to the user;

code for applying a second selection technique to generate a second set of relevancy scores for information objects in the second set of information objects, the second set of relevancy scores indicating the relevancy of information objects in the second set of information objects to information objects in the first set of information objects calculated using the second selection technique, the second selection technique being based on classes of information objects in the first and second sets of information objects, the classes of information objects including text, audio, or video; and

code for selecting a third set of one or more information objects from information objects in the second set of information objects based upon the first set of relevancy scores generated using the first selection technique and the second set of relevancy scores generated using the second selection technique, wherein information objects in the third set of information objects store information to be output to a user when the first document is being displayed to the user.

7. The computer readable storage medium of claim 6, wherein the first set of information objects comprises at least a first information object comprising including information of a first type, and wherein the second set of information objects comprises at least one information object including information of a second type, wherein the second type is different from the first type.

8. The computer readable storage medium of claim 6 wherein the code for extracting the first set of information objects from the first section of the first document comprises:

for each information object in the first set of information objects;

code for identifying a type of the information object based upon contents of the information object;

code for determining a first content recognition technique based upon the type of the information object; and

code for applying the first content recognition technique to the information object to determine information related to the contents of the information object.

9. The computer readable storage medium of claim 6 wherein the code for selecting the third set of one or more information objects from the second set of information objects based upon the first set of relevancy scores and the second set of relevancy scores comprises:

for each information object in the second set of information objects;

code for calculating an aggregate relevancy score for the information object by aggregating a relevancy score in the first set of relevancy scores generated for the information object by applying the first selection technique and a relevancy score in the second set of relevancy scores generated for the information object by applying the second selection technique; and

code for selecting the information object to be included in the third set of information objects if the aggregate relevancy score calculated for the information object is above a threshold value.

10. A system for providing information to a user based upon contents of a first document displayed to the user, the system comprising:

a processor;

a memory coupled to the processor, the memory configured to store a plurality of code modules for execution by the processor, the plurality of code modules comprising;

a code module for identifying at least a first section of the first document;

a code module for extracting a first set of one or more information objects from the first section of the first document;

a code module for applying a first selection technique to generate a first set of relevancy scores for information objects in a second set of information objects distinct from the first set of information objects, the first set of relevancy scores indicating the relevancy of information objects in the second set of information objects to information objects in the first set of information objects calculated using the first selection technique, the first selection technique being based on relevance of information objects in the first and second sets of information objects to concepts of interest to the user;

a code module for applying a second selection technique to generate a second set of relevancy scores for information objects in the second set of information objects, the second set of relevancy scores indicating the relevancy of information objects in the second set of information objects to information objects in the first set of information objects calculated using the second selection technique, the second selection technique being based on classes of information objects in the first and second sets of information objects, the classes of information objects including text, audio, or video; and

a code module for selecting a third set of one or more information objects from information objects in the second set of information objects based upon the first set of relevancy scores generated using the first selection technique and the second set of relevancy scores generated using the second selection technique, wherein information objects in the third set of information objects store information to be output to the user when the first document is being displayed to the user.

11. The system of claim 10, wherein the first set of information objects comprises at least a first information object including information of a first type, and wherein the second set of information objects comprises at least one information object including information of a second type, wherein the second type is different from the first type.

12. The system of claim 10 wherein the code module for extracting the first set of information objects from the first section of the first document comprises:

for each information object in the first set of information objects;

a code module for identifying a type of the information object based upon contents of the information object;

a code module for determining a first content recognition technique based upon the type of the information object; and

a code module for applying the first content recognition technique to the information object to determine information related to the contents of the information object.

13. The system of claim 10 wherein the code module for selecting the third set of one or more information objects from the second set of information objects based upon the first set of relevancy scores and the second set of relevancy scores comprises:

for each information object in the second set of information objects;

a code module for calculating an aggregate relevancy score for each information object in the second set of information objects by aggregating a relevancy score in the first set of relevancy scores generated for the information object by applying the first selection technique and a relevancy score in the second set of relevancy scores generated for the information object by applying the second selection technique; and

a code module for selecting an information object from the second set of information objects to be included in the third set of information objects if the aggregate relevancy score calculated for the information object is above a threshold value.