System and method for combining voice annotation and recognition search criteria with traditional search criteria into metadata

• US 20020184196A1
• Filed: 06/04/2001
• Published: 12/05/2002
• Est. Priority Date: 06/04/2001
• Status: Abandoned Application

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Lehmeier, Michelle R., Sobol, Robert E., Beeman, Edward S.
• Application Number:
  US09/873,687
• Publication Number:
  US 20020184196A1
• Time in Patent Office: Days
• US Class Current: 707/3
• CPC Class Codes: G06F 16/38 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Abstract

The present invention is directed to a system and method which uses metadata to create an association between key words in textual files or files containing text; key objects in image files or pictures; and key names associated with textual files, files containing text, image files and picture files and the files or their file names. Key words in textual files or files containing text can be identified by the user or through semantics processing. Key objects in image and picture files can be identified by the user or through object recognition software. Key names in textual files, files containing text, image files and picture files are identified by a narrative or other spoken words given by the user to the processing system with respect to specific pictures.

Claims

1. A document retrieval system comprising:

a document processing engine configured to extract search keys from a data file to identify internal characteristics of said data file;

a speech recognition engine configured to convert spoken characteristics associated with certain said files to spoken characteristic data; and

a data structure which associates said internal characteristics of a file and any said spoken characteristics of a file with said file in a memory.

2. The document retrieval system of claim 1 further comprising:

a search engine configured to search for said internal characteristics and any said spoken characteristics within said memory so as to identify files associated with said internal characteristics and any said spoken characteristics.

3. The document retrieval system of claim 1 wherein at least some of said files contain textual information.

4. The document retrieval system of claim 2 further comprising a character recognition engine configured to provide said textual information.

5. The document retrieval system of claim 1 wherein at least some of said files contain image data.

6. The document retrieval system of claim 4 wherein the document processing engine includes an object recognition system.

8. The method of claim 6 further including the step of:

searching said metadata to identify said file.

9. The method of claim 6 wherein said internal characteristics of a file include textual information.

10. The method of claim 8 further comprising the step of recognizing print characters to provide said textual information.

11. The method of claim 6 wherein said file contains an image.

12. The method of claim 10 further comprising the step of recognizing and classifying at least one object depicted in said image.

14. The image storage system of claim 13 further comprising:

a microphone providing spoken information.

15. The image storage system of claim 12 further comprising:

an object recognizer providing identification of objects within said captured images.

16. The images storage system of claim 12 further comprising a speech recognition engine configured to convert said spoken information to spoken characteristic data.

17. The image storage system of claim 12 further comprising:

a plurality of text files, each with a corresponding file name;

a document processing engine configured to extract search keys from each of said files; and

said metadata further providing an association between said search keys and said file names.

18. The image storage system of claim 15 further comprising:

an object recognizer providing identification of objects within said captured images.

19. The images storage system of claim 15 further comprising a speech recognition engine configured to convert said spoken information to spoken characteristic data.

20. The image storage system of claim 15 further comprising a character recognition engine configured to provide the textual information.

22. The system of claim 19 further comprising:

means for retrieving stored ones of said documents based upon receipt of a data tag associated with said document to be retrieved.

7. A method of identifying documents comprising the steps of:

identifying internal characteristics of a file;

converting spoken words associated with said file into spoken characteristics associated with said file; and

creating metadata associating said internal characteristics and said spoken characteristics with said file.

13. An image storage system comprising:

an image capture platform providing captured images;

a memory storing image data captured by said image capture platform together with said spoken information relating to said image data; and

a metadata providing an association between said captured images and said spoken information.

21. A system for storing documents in an electronic storage media, said system comprising:

means for obtaining from each said document to be stored, data tags pertaining to certain characteristics of said document, said data tags selected from the list of character recognition, semantics processing, object recognition, and voice recognition; and

means for associating said data tags with each said document.