Adaptive pattern recognition based controller apparatus and method and human-factored interface therefore
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06F-017/00
G06F-015/00
G06F-015/18
H04N-007/10
H04N-007/025
G06Q-030/00
G06G-007/00
G06N-005/02
G06E-001/00
G06E-003/00
출원번호
US-0244152
(2011-09-23)
등록번호
US-8352400
(2013-01-08)
발명자
/ 주소
Hoffberg, Steven M.
Hoffberg-Borghesani, Linda I.
출원인 / 주소
Hoffberg, Steven M.
대리인 / 주소
Hoffberg, Steven M.
인용정보
피인용 횟수 :
9인용 특허 :
2
초록▼
A system and method of predicting items likely to appeal to a user, based on data received from a remote site. One or more local systems are provided, along with a remote system, said local systems communicating with said remote system over a network connection. Each local system maintains a set of
A system and method of predicting items likely to appeal to a user, based on data received from a remote site. One or more local systems are provided, along with a remote system, said local systems communicating with said remote system over a network connection. Each local system maintains a set of characterized items. A local processor predicts an appeal of an item to a user based on the comparison with the set of characterized items with, e.g., user preferences. The user may interact through graphical user interface. At least one user-preference predictive algorithm may be employed to present items predicted to appeal to the user.
대표청구항▼
1. A distributed system for predicting items likely to appeal to a user, comprising: a plurality of local systems each having a user interface, the user interface being configured to receive respective user input data;a remote system, communicating with said local systems over a communication networ
1. A distributed system for predicting items likely to appeal to a user, comprising: a plurality of local systems each having a user interface, the user interface being configured to receive respective user input data;a remote system, communicating with said local systems over a communication network connection to receive the user input data, producing a set of characterized items by an automated pattern recognition process, correlating at least previously received respective user input data from a respective local system with the set of characterized items, processing the received respective user input data with at least one predictive algorithm for predicting whether user input data is likely in error, and communicating information to the respective local system dependent on the correlation, to thereby predict an appeal to the respective user of items; anda local processor configured to present at least one item to a user based on the information received from the remote system. 2. The system of claim 1, wherein said items comprise items of media content. 3. The system of claim 2, wherein said items comprise any of network television programming, cable television programming, films, pay-per-view television programming and video. 4. The system of claim 1, said system being a component of a network-based video recording system. 5. A method of predicting items of media content most likely to appeal to a user and presenting said predictions through a graphical user interface, wherein said predictions are based on user preferences for specific media content, comprising: providing an interactive user interface for receiving user preference information;predicting whether a user input is likely in error with at least one predictive algorithm;predicting a user appeal of an item of media content according to at least one user-preference predictive algorithm executing on an automated processor which operates on the user preference information and characterizations of media content derived from an automated pattern recognition process and, predicts an appeal of respective items of media content to the user; anddisplaying items predicted to appeal to the user in said graphical user interface. 6. The method of claim 5, wherein the media content comprises video. 7. The method of claim 5, further comprising the step of evaluating features of the media content. 8. The method of claim 5, further comprising employing at least one correlator to predict the appeal of media content to a user. 9. The method of claim 5, wherein said media content comprises at least one type of programming selected from the group consisting of network television programming, cable television programming, pay-per-view television programming, movies and public-access television programming. 10. The method of claim 5, wherein preferences are expressed explicitly by the user. 11. The method of claim 5, wherein preferences are expressed implicitly by the user. 12. The method of claim 5, wherein preferences are expressed as a set of distinct factors relating to said media content. 13. The method of claim 5, wherein the user preference information is derived by at least automatically performing pattern recognition on media content previously presented to the user, wherein said predicting comprises determining at least one correlation of a user preference with characterizations of media. 14. The method of claim 5, wherein at least one predictive algorithm is based on an automated analysis of a pattern of user behavior over a course of time through experience of a plurality of media content. 15. The method of claim 5, wherein at least one predictive algorithm allows the user to provide feedback relating to an actual appeal of at least one media program. 16. The method of claim 5, wherein at least one predictive algorithm allows the user to provide feedback relating to at least the predicted appeal. 17. The method of claim 5, wherein said at least one predictive algorithm for predicting whether a user input is likely in error is dependent on user preferences. 18. A method for selecting content most likely to appeal to a user, wherein said selections represent predictions based on user preferences and context, comprising: providing an interactive user machine interface configured to define a context, and to receive preference information from a user based on an interaction of the user with the interactive user machine interface;predicting whether a user input is likely in error with at least one predictive algorithm;automatically predicting an appeal of an item of content to a user based on at least one user-preference predictive algorithm which employs machine pattern recognition to produce a characterization of a plurality of items of content, and compares the preference information with the characterizations; andpresenting context-appropriate items predicted to appeal to the user through said interactive user machine interface. 19. The method according to claim 18, wherein the content comprises multimedia, the preference information is received at least implicitly, and the context-appropriate items comprise a plurality of ranked items selected based on said predicting and the context. 20. The method according to claim 18, wherein said presenting comprises forming a hypertext link, linking text or information, the further comprising receiving a selection of the hypertext link by the user to select the text or information, and retrieving the selected text or information.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (2)
Hoffberg Steven M. ; Hoffberg-Borghesani Linda I., Human factored interface incorporating adaptive pattern recognition based controller apparatus.
Gaither Shawn A. (Saratoga CA) Shah Sunil C. (Mountain View CA), Method for operating a real-time expert system in a graphical programming environment.
Perlmutter, Keren O.; Perlmutter, Sharon M.; Wang, Eric; Klamer, Paul R.; Cookson, Christopher J.; Gasparri, Massimiliano, Registration of separations.
Perlmutter, Keren O.; Perlmutter, Sharon M.; Wang, Eric; Klamer, Paul R.; Cookson, Christopher J.; Gasparri, Massimiliano, Registration of separations.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.