Hyper video: information retrieval using text from multimedia

• US 6,757,866 B1
• Filed: 10/29/1999
• Issued: 06/29/2004
• Est. Priority Date: 10/29/1999
• Status: Expired due to Term

• Current Assignee: Verizon Laboratories Incorporated (Verizon Communications Inc.)
• Original Assignee: Verizon Laboratories Incorporated (Verizon Communications Inc.)
• Inventors: Dey, Jayanta Kumar, Ponte, Jay Michael
• Primary Examiner(s): Feild, Joseph
• Assistant Examiner(s): NGUYEN, CHAU T
• Application Number:
  US09/430,597
• Time in Patent Office: 1,705 Days
• Field of Search: 715/500.1, 715/501.1, 709/219, 707/3, 707/6, 707/4, 345/716, 345/717, 345/721
• US Class Current: 715/256
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

Disclosed is a method and device for selecting documents, such as Web pages or sites, for presentation to a user, in response to a user expression of interest, during the course of presentation to the user of a document, such as a video or audio selection, whose content varies with time. The method takes advantage of information retrieval techniques to select documents related to the portion of the temporal document in which the user has expressed interest. The method generates the search query to use to select documents by reference to text associated with the portion of the temporal document in which the user has expressed interest, as by using the closed caption test associated with the video, or by using speech recognition techniques.

Claims

1. A method for finding documents which relate to a portion of a temporal document wherein the temporal document is video or audio material, comprising:

(a) in response to a signal of interest at a particular time during the temporal document, identifying a portion of the temporal document for which related documents are to be found;

(b) selecting text associated with the portion of the temporal document identified;

(c) finding the related document by use of information retieval techniques as applied to the selected text,

wherein the related documents are accessed through the Internet and are selected from a collection of documents according to scores associated with the documents, said scores based on a ratio between the number of documents in the collection and, for a term in the selected text, the number of documents in the collection containing the term; and

(d) selecting the related documents from among a collection of documents which may be accessed through the Internet, by utilizing databases comprising information about the collection, wherein a score S_D of a document D in the collection may be determined by crediting the document D, for each term T in the temporal portion of the document identified which occurs in the document D, with an amount proportional to Robertson'"'"'s term frequency TF_TD and to IDF_T where

2. The method of claim 1, wherein the video material is stored on a video server.

3. The method of claim 1, wherein the selected text is determined by application of speech recognition techniques to the audio component of the portion of the temporal document identified.

4. The method of claim 1, wherein the selected text is the closed-captioned text associated with the portion of the temporal document identified.

5. The method of claim 1, wherein the temporal document includes text.

6. The method of claim 5, wherein the document text appearing to the user varies with time and the selected text is that portion of the temporal document identified.

7. The method of claim 6, wherein the document text includes news bulletins, weather, sports scores or stock transaction or pricing information.

8. The method of claim 1, wherein a predetermined number of documents, 1000, are selected.

9. The method of claim 1, wherein K₁ is 0.5, K₂ is 1.5, K₃ is 0.5, and K₄ is 1.0.

10. The method of claim 1, wherein evaluating documents in the collection includes accessing compressed document surrogates.

11. The method of claim 1, wherein related documents are selected from the collection by a server which is distinct from the server which receives the signal of interest.

12. A device for finding documents which relate to a portion of a temporal document wherein the temporal document is video or audio material, comprising:

(a) means for identifying a portion of the temporal document for which related documents are to be found, in response to a signal of interest at a particular time during the temporal document;

(b) means for selecting text associated with the portion of the temporal document identified;

(c) means for finding thee related documents by use of information retrieval techniques as applied to the selected text,

wherein the related documents are accessed through the Internet and are selected from a collection of documents according to scores associated with the documents, said scores based on a ratio between the number of documents in the collection and, for a term in the selected text, the number of documents in the collection containing the term;

(d) means for selecting the related documents from among a collection of documents which may be accessed through the Internet, by utilizing databases comprising information about the collection wherein a score S_D of document D in the collection may be determined by crediting the document D, for each term T in the temporal portion of the document identified which occurs in the document D, with an amount proportional to Robertson'"'"'s term frequency TF_TD and to IDF_T where

 

TF_TD=N_TD/(N_TD+K₁+K₂*(L_D/L₀)), and

N_TD is the number of times the term T occurs in document D,

L_D is the length of document D,

L₀ is the average length of a document in the collection of documents indexed,

K₁ and K₂ are constants, and

13. The device of claim 12, wherein the video material is stored on a video server.

14. The device of claim 12, wherein the selected text is determined by application of speech recognition techniques to the audio component of the portion of the temporal document identified.

15. The device of claim 12, wherein the selected text is the closed-captioned text associated with the portion of the temporal document identified.

16. The device of claim 12, wherein the temporal document includes text.

17. The device of claim 16, wherein the document text appearing to the user varies with time and the selected text is that portion of the temporal document identified.

18. The device of claim 17, wherein the document text includes news bulletins, weather, sports scores or stock transaction or pricing information.

19. The device of claim 12, wherein a predetermined number of documents, 1000, are selected.

20. The device of claim 12, wherein K₁ is 0.5, K₂ is 1.5, K₃ is 0.5, and K₄ is 1.0.

21. The device of claim 12, wherein evaluating documents in the collection includes accessing compressed document surrogates.

22. The device of claim 12, wherein related documents are selected from the collection by a server which is distinct from the server which receives the signal of interest.