Content augmentation based on personal profiles
(19)AUSTRALIAN PATENT OFFICE(54) Title Content augmentation based on personal profiles(51)6 International Patent Classification(s) H04N 007/173(21) Application No: 2003228068 (22) Application Date: 2003.05.19(87) WIPO No: WO03/105463(30) Priority Data (31) Number (32) Date 10/165,904 2002.06.10 (33) Country US 200510277 (43) Publication Date : 2003.12.22(43) Publication Journal Date : 2004 .02.19(71) Applicant(s) KONINKLIJKE PHILIPS ELECTRONICSN.V(72) Inventor(s) Jasinschi, Radu; Dimitrova, Nevenka; Zi mmerman, John (-|-|) Application No AU 2003228068 A8(19)AUSTRALIAN PATENT OFFICE(54) Title Content augmentation based on personal profiles(51)6 International Patent Classification(s) H04N 007/173(21) Application No: 2003228068 (22) Application Date: 2003.05.19(87) WIPO No: WO03/105463(30) Priority Data (31) Number (32) Date 10/165,904 2002.06.10 (33) Country US 200510277 (43) Publication Date : 2003.12.22(43) Publication Journal Date : 2004 .02.19(71) Applicant(s) KONINKLIJKE PHILIPS ELECTRONICSN.V(72) Inventor(s) Jasinschi, Radu; Dimitrova, Nevenka; Zi mmerman, John-1- A method, process and system for performing content augmentation of personal profiles includes (a) building a user history of a plurality of augmented content information of relevant TV programs; (b) analyzing user queries and determining a degree to which the user queried for additional content information; (c) inferring values about the user from user queries for additional content information so as to augment the additional content information; (d) updating the augmented content information to at least one of the user history, Internet and specialized databases; (e) linking individual ones of the plurality of augmented content information to each other; and (f) determining inferences about the user's interests and preferences based on the linkage of the plurality of augmented content information. The updating of the augmented content information includes segmenting and indexing of multimedia content. A feedback system is created where user queries for more information and purchases from the Internet and specialized databases will result in additional augmented content information about the particular user. CLAIMS:1. A method for performing content augmentation of personal profiles comprising: (a) building a user history (105) of a plurality of augmented content information of relevant TV programs; (b) analyzing user queries (110) and determining a degree to which the user queried for additional content information; (c) inferring values (115) about the user from the user queries for additional content information in step (b) so as to augment the additional content information; (d) updating the augmented content information (120) to at least one of the user history, Internet and specialized databases; and (e) linking (125) individual ones of the plurality of augmented content information to each other; (f) determining inferences about the user's interests and preferences based on the linkage of the plurality of augmented content information.
2. The method according to claim 1, further comprising: (g) creating a feedback system by updating the user history in step (a) with the determination about user's interests and preferences from step (f).
3. The method according to claim 1, wherein the updating of the augmented content information in step (d) includes segmenting and indexing of the plurality of augmented content information, and wherein the segmenting and indexing is performed on multimedia. <Desc/Clms Page number 17> 4. The method according to claim 3, further comprising prompting the user in a push mode to engage in communication with one of the Internet and specialized databases updated in step (d) with the augmented content information.
5. The method according to claim 3, further comprising prompting the user in a push mode to purchase items associated with said one of the Internet and specialized databases updated in step (d) with the augmented content information.
6. The method according to claim 1, wherein the determining of the degree to which the user queried for additional content information includes categorizing superficial queries for a first particular subject relative to a second particular subject by counting a number of superficial queries for each of the first and second particular subjects.
7. The method according to claim 1, wherein the determining of the degree to which the user queried for additional content information in step (b) includes determining a depth of the queries based on a predetermined correlation of a particular user query and a value of the depth assigned to the particular user query.
8. The method according to claim 1, wherein the inferred values include designation of at least one user trait selected from the group consisting of curiosity, knowledge, frugality, quantity, fashion, and false pretenses.
9. The method according to claim 6, wherein the segmenting and indexing of the multimedia includes: <Desc/Clms Page number 18> (i) automatic feature extraction from at least one of a visual stream, an audio stream, and a transcript stream by determining low-level, mid-level, and high level features; and (ii) automatic audio classification that corresponds to predetermined categories including more than one of silence, noise, speech, music, speech plus noise, speech plus speech, speech plus music.
10. The method according to claim 9, wherein the lower level features comprise pixel-based color, shape and edge attributes, the mid-level features include keyframes, faces and videotext including audio features, and the high level features are classified according to topics, and wherein the automatic audio classification 11. The method according to claim 3, wherein the segmenting and indexing is performed by combining cepstral- based features, frequency-domain operations and temporal-domain operations to extract acoustical features, spectral and temporal features.
12. A content augmentation system comprising: a processor (210); means for storing content information (215,220) comprising viewing history and query history of a viewer, said means for storing being in communication with the processor; means for analyzing (225) a degree to which a viewer queried for additional content information; <Desc/Clms Page number 19> means for segmenting and indexing multimedia content (230) watched by a viewer to provide augmented content information; means for storage (235) of the augmented contented information; a viewer profile (240) identifying a viewer and associated augmented content information that has been linked to each other;STDC0272 means for linking (212) the viewer profile with one of the Internet and specialized databases and for updating the viewer profile with information from the Internet and specialized databases regarding the viewing of the Internet and specialized database by the viewer.
13. The system according to claim 12, wherein the means for segmenting and indexing multimedia uses cepstral-based features.
14. The system according to claim 13, wherein the cepstral-based features include MFCC and LPC.
15. The system according to claim 12, wherein the means for segmenting and indexing includes a'combination of cepstral- based features, frequency-domain operations and temporal-domain operations to extract acoustical features, spectral and temporal features.
16. The system according to claim 13, further comprising means for prompting a viewer (213) in a push mode to engage in communication with one of the Internet and specialized databases. <Desc/Clms Page number 20> 17. The system according to claim 13, further comprising means for combining (242) explicit viewer preferences with the segmenting and indexing.
18. The system according to claim 13, wherein the means for analyzing (225) includes means for updating a viewer profile with quantitative values associated with the additional content information queried by a viewer and the degree to which the additional content information is queried.
19. A content augmentation device comprising: a processor (210); a first storage area for storing content information (215,220) comprising viewing history and query history of a viewer, said means for storing being in communication with the processor; means for analyzing (225) a degree to which a viewer queried for additional content information; means for segmenting and indexing multimedia content (230) watched by a viewer to provide augmented content information; a second storage area for storage of the augmented contented information; a viewer profile (240) identifying a viewer and associated augmented content information that has been linked to each other;STDC0305 means for linking (212) the viewer profile with one of the Internet and specialized databases and for updating the viewer profile with information from the Internet and <Desc/Clms Page number 21> specialized databases regarding the viewing of the Internet and specialized database by the viewer.
20. The device according to claim 19, wherein the means for segmenting and indexing multimedia uses cepstral-based features.
21. The device according to claim 19, wherein the cepstral-based features include MFCC and LPC.
22. The device according to claim 19, wherein the means for segmenting and indexing includes a combination of cepstralbased features, frequency-domain operations and temporal-domain operations to extract acoustical features, spectral and temporal features.
23. The device according to claim 20, further comprising means for prompting a viewer (213) in a push mode to engage in communication with one of the Internet and specialized databases.
24. The device according to claim 19, further comprising means for combining (242) explicit viewer preferences with the segmenting and indexing.