Identifying works for initiating a work-based action, such as an action on the internet

• US 20020032698A1
• Filed: 09/13/2001
• Published: 03/14/2002
• Est. Priority Date: 09/14/2000
• Status: Active Grant

• Current Assignee: Network-1 Technologies, Inc.
• Original Assignee: Dr. Ingemar J Cox
• Inventors: Cox, Ingemar J.
• Granted Patent: US 7,058,223 B2
• Time in Patent Office: Days
• US Class Current: 715/501.1
• CPC Class Codes: G06F 16/41 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A system is described for linking traditional media works, such as print and broadcast media for example, to a more interactive media conduit, such as the Internet. The system avoids the need to modify the media work in anyway. Instead, it employs a passive recognition system that uniquely identifies the specific work, such as a particular television or radio broadcast or printed commercial. The identification may be based in intra-work and/or extra-work information. Several different embodiments/environments are described. The best embodiment may depend, at least in part, on costs of hardware and communication. These costs can change over time. In one embodiment, all of the databases and computation are performed at the user'"'"'s premises. In another embodiment, all of the databases and computation occur at remote sites that user premise equipment can query using uniquely identifying extra-work information, such as the time, place and station on which the work was broadcast. This second embodiment is most suitable for content that is published, e.g. magazines, newspapers, etc., or broadcasted, e.g. cable, satellite and terrestrial television and radio. Alternative embodiments, in which various operations are performed at both the user'"'"'s premises and remote locations are also possible.

Claims

1. A method for associating extra work information with an identification of a work, the method comprising:

a) accepting a work and extra-work information associated with the work;

b) identifying the work as one of a predetermined number of known works, each of the predetermined number of known works having an identifier; and

c) associating the identifier of the one of the predetermined number of known works with the extra-work information.

2. The method of claim 1 wherein the extra-work information includes at least one of (A) a channel over which the work is or was broadcast, (B) a station which broadcast the work, (C) a time that the work broadcast is or was received, (D) a time that the work is or was broadcast, and (E) a geographic region in which the work is or was broadcast.

3. The method of claim 1 wherein the act of identifying the work as one of a predetermined number of known works includes:

a) extracting features from the work;

b) comparing the extracted features with stored sets of feature vectors, wherein each of the stored sets of feature vectors includes an associated work identifier.

4. The method of claim 3 wherein the work is a video work and wherein the features extracted from the work are selected from a group consisting of (A) a pseudo-random sample of pixels from a frame of the video work, (B) a pseudo-random sample of pixels from a low-resolution copy of a frame from the video work, (C) intensities of blocks of pixels, (D) a frequency-based decomposition of a signal of the video work, (E) frequencies from a signal of the video work, and (F) information from some or all pixels of the video work.

5. The method of claim 3 wherein the work is an audio work and wherein the features extracted from the work are selected from a group consisting of (A) a frequency decomposition of a signal of the audio work, (B) information samples of the audio work, (C) average intensities of sampled windows of the audio work, and (D) information from frequencies of the audio work.

6. The method of claim 1 wherein the act of associating the identifier of the one of the predetermined number of known works with the extra-work information uses a monitoring of the works and uses a comparison technique selected from a group consisting of (A) linear correlation, (B) statistical correlation, (C) mutual information, (D) Euclidean distance, (E) Lp-norms, (F) clustering, (G) kd-trees, (H) vantage point trees, and (I) excluded middle vantage point forest.

7. The method of claim 1 further comprising:

d) storing the associated the identifier of the one of the predetermined number of known works and the extra-work information in a database.

8. The method of claim 7 further comprising:

e) accepting a client query including extra-work information; and

f) using the accepted extra-work information to lookup an identifier in the database.

9. The method of claim 8 further comprising:

g) using an identifier found in the database to lookup a work-related action.

10. The method of claim 9 wherein the work-related action is transiting the client sourcing the client query to an Internet web site.

11. The method of claim 1, wherein if the work is not identified as one of a predetermined number of known works, then d) assigning a new work identifier to the work;

and e) storing the identifier and work as a known work.

13. The one or more machine readable medium of claim 12 wherein the extra-work information includes at least one of (A) a channel over which the work is or was broadcast, (B) a station which broadcast the work, (C) a time that the work broadcast is or was received, (D) a time that the work is or was broadcast, and (E) a geographic region in which the work is or was broadcast.

15. The monitoring apparatus of claim 14 wherein the extra-work information includes at least one of (A) a channel over which the work is or was broadcast, (B) a station which broadcast the work, (C) a time that the work broadcast is or was received, (D) a time that the work is or was broadcast, and (E) a geographic region in which the work is or was broadcast.

16. The monitoring apparatus of claim 14 wherein the means for identifying include:

a) means for extracting features from the work; and

b) means for comparing the extracted features with stored sets of feature vectors, wherein each of the stored sets of feature vectors includes an associated work identifier.

17. The monitoring apparatus of claim 14 further comprising:

d) a database for storing records, one of the records including the associated the identifier of the one of the predetermined number of known works and the extra-work information.

18. The monitoring apparatus of claim 14 further comprising means for assigning an identifier to a previously unknown work, wherein if the means for identifying does not identify the work as one of a predetermined number of known works, then providing the work to the means for assigning.

20. The method of claim 19 wherein the media work is a video work and wherein the features extracted from the work are selected from a group consisting of (A) a pseudo-random sample of pixels from a frame of the video work, (B) a pseudo-random sample of pixels from a low-resolution copy of a frame from the video work, (C) intensities of blocks of pixels, (D) a frequency-based decomposition of a signal of the video work, (E) frequencies from a signal of the video work, and (F) information from some or all pixels of the video work.

21. The method of claim 19 wherein the media work is an audio work and wherein the features extracted from the work are selected from a group consisting of (A) a frequency decomposition of a signal of the audio work, (B) information samples of the audio work, (C) average intensities of sampled windows of the audio work, and (D) information from frequencies of the audio work.

22. The method of claim 19 wherein the act of determining an identification of the media work based on the features extracted uses a comparison technique selected from a group consisting of (A) linear correlation, (B) statistical correlation, (C) mutual information, (D) Euclidean distance, (E) Lp-norms, (F) clustering, (G) kd-trees, (H) vantage point trees, and (I) excluded middle vantage point forests.

12. One or more machine-readable storage medium having stored thereon:

a) a first plurality of records, each of said first plurality of records including;

i) a first field for storing features of a first work;

ii) a second field for storing an identifier of the first work; and

b) a second plurality of records, each of said second plurality of recording including;

i) a first field for storing extra-work information associated with the first work; and

ii) a second field for storing an identifier of the first work.

14. A monitoring apparatus, the monitoring apparatus comprising:

a) in input for accepting a work and extra-work information associated with the work;

b) means for identifying the work as one of a predetermined number of known works, each of the predetermined number of known works having an identifier; and

c) means for associating the identifier of the one of the predetermined number of known works with the extra-work information.

19. A method for linking a media work to an action, the method comprising:

a) extracting features from the media work;

b) determining an identification of the media work based on the features extracted;

c) determining an action based on the identification of the media work determined.