Method and system using keyword vectors and associated metrics for learning and prediction of user correlation of targeted content messages in a mobile environment
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06F-015/18
G06F-017/21
H04L-029/08
G06N-003/00
G06Q-030/02
H04L-012/18
H04L-012/58
H04M-003/487
H04W-008/18
H04W-004/12
H04W-004/20
출원번호
US-0268945
(2008-11-11)
등록번호
US-9705998
(2017-07-11)
발명자
/ 주소
Krishnaswamy, Dilip
Verma, Nakul
Bychkovsky, Vladimir
출원인 / 주소
QUALCOMM Incorporated
대리인 / 주소
Cole, Nicholas A.
인용정보
피인용 횟수 :
0인용 특허 :
99
초록▼
Methods and systems for determining a suitability for a mobile client to display information are disclosed. A particular exemplary method includes receiving a plurality of sets of one or more first keywords on a mobile client, each set of first keywords associated with one or more respective first m
Methods and systems for determining a suitability for a mobile client to display information are disclosed. A particular exemplary method includes receiving a plurality of sets of one or more first keywords on a mobile client, each set of first keywords associated with one or more respective first messages, monitoring user interaction of the respective first messages on the mobile client, performing learning operations on the mobile client with the first keywords based on monitored user interaction to estimate a set of keyword interest weights, receiving a set of target keywords associated with a target message, and displaying the target message on the mobile client based on the estimated keyword interest weights.
대표청구항▼
1. A method for determining display information on a mobile client, comprising: receiving a plurality of sets of one or more first keywords on the mobile client, each set of first keywords associated with one or more respective first messages;monitoring user interaction of the respective first messa
1. A method for determining display information on a mobile client, comprising: receiving a plurality of sets of one or more first keywords on the mobile client, each set of first keywords associated with one or more respective first messages;monitoring user interaction of the respective first messages on the mobile client;performing learning operations on the mobile client with the first keywords based on monitored user interaction to estimate a set of keyword interest weights;receiving a set of target keywords associated with a target message;receiving the target message over a wireless link if the estimated set of keyword interest weights indicates a desirability of the target message; anddisplaying the target message on the mobile client based on the estimated set of keyword interest weights. 2. The method according to claim 1, further comprising: performing a prediction routine based on the set of target keywords and the estimated set of keyword interest weights to determine an estimated user interest of the target message,wherein the target message is displayed when the estimated user interest is favorable compared to other estimated user interests of other messages. 3. The method according to claim 2, wherein the step of performing a prediction routine includes performing a correlation operation R={circumflex over (P)}·A, where {circumflex over (P)} is a current estimate of user interest weights and A is a vector representation of the target message. 4. The method according to claim 1, wherein the step of monitoring user interaction includes monitoring click-through-rates for the first messages. 5. The method according to claim 1, wherein performing learning operations includes using at least one steepest descent algorithm to estimate at least one keyword interest weight. 6. The method according to claim 1, wherein performing learning operations includes using at least one Newtonian algorithm to estimate at least one keyword interest weight. 7. The method according to claim 1, wherein the set of target keywords is specified from a keyword dictionary. 8. The method according to claim 7, wherein a rate of learning is determined based on at least one of information-space sparseness, rate of presentation of information, value of initial seed, and aspects of a user profile. 9. The method according to claim 7, wherein the set of target keywords is specified from a specified hierarchical keyword dictionary, wherein a hierarchy of the specified hierarchical keyword dictionary has two or more levels. 10. The method according to claim 7, wherein the set of target keywords is specified from a specified flat keyword dictionary. 11. The method according to claim 7, wherein the set of target keywords is not associated with semantics of a specific language. 12. The method according to claim 7, wherein the step of learning incorporates random or pseudo-random noise. 13. The method according to claim 7, wherein a cardinality of the set of target keywords is sparse relative to a size of the keyword dictionary. 14. The method according to claim 1, wherein one or more learning parameters used for the step of learning operations are incorporated into at least one received message. 15. The method according to claim 14, wherein the one or more learning parameters include at least one decay constant. 16. The method according to claim 1, wherein only a subset of the set of target keywords is used to display the target message on the mobile client. 17. The method according to claim 16, wherein the subset of keywords is determined based upon a threshold interest value. 18. The method according to claim 16, wherein the subset of keywords is determined by using those keywords from the set of target keywords having the respective top keyword interest weights. 19. A mobile client configured to display information, comprising: means for receiving a plurality of sets of one or more first keywords on a mobile client, each set of first keywords associated with one or more respective first messages, the means for receiving further configured to receive a set of target keywords associated with a target message;means for monitoring user interaction of the respective first messages on the mobile client;means for performing learning operations on the mobile client with the first keywords based on monitored user interaction to estimate a set of keyword interest weights;means for receiving the target message over a wireless link if the estimated set of keyword interest weights indicate a desirability of the target message; andmeans for displaying the target message on the mobile client based on the estimated set of keyword interest weights. 20. The mobile client according to claim 19, further comprising: means for performing a prediction routine based on the set of target keywords and the estimated set of keyword interest weights to determine an estimated user interest of the target message,wherein the target message is displayed when the estimated user interest is favorable compared to other estimated user interests of other messages. 21. The mobile client according to claim 20, wherein the means for performing a prediction routine performs at least a correlation operation R={circumflex over (P)}·A, where {circumflex over (P)} is a current estimate of user interest weights and A is a vector representation of the target message. 22. The mobile client according to claim 19, wherein the means for performing uses at least one steepest descent algorithm to estimate at least one keyword interest weight. 23. The mobile client according to claim 19, wherein the means for performing uses at least one Newtonian algorithm to estimate at least one keyword interest weight. 24. The mobile client according to claim 19, wherein the means for performing incorporates random or pseudo-random noise in the learning operations. 25. The mobile client according to claim 19, wherein a cardinality of the set of target keywords is sparse relative to a size of a keyword dictionary. 26. The mobile client according to claim 19, wherein one or more learning parameters used for the learning operations are incorporated into at least one received message. 27. The mobile client according to claim 26, wherein the one or more learning parameters include at least one decay constant. 28. The mobile client according to claim 19, wherein only a subset of the set of target keywords is used to display the target message on the mobile client. 29. The mobile client according to claim 28, wherein the subset of keywords is determined based upon a threshold interest value. 30. The mobile client according to claim 29, wherein the subset of keywords is determined by using those keywords from the set of target keywords having the respective top keyword interest weights. 31. A mobile client configured to display information, comprising: a receiving circuit configured to receive a plurality of sets of one or more first keywords on a mobile client, each set of first keywords associated with one or more respective first messages, the receiving circuit further configured to receive a set of target keywords associated with a target message;monitoring means for monitoring user interaction of the respective first messages on the mobile client;learning means for performing learning operations on the mobile client with the first keywords based on monitored user interaction to estimate a set of keyword interest weights, wherein the receiving circuit is further configured to receive the target message over a wireless link if the estimated set of keyword interest weights indicate a desirability of the target message; anda display configured to display the target message on the mobile client based on the estimated set of keyword interest weights. 32. The mobile client according to claim 31, further comprising: means for performing a prediction routine based on the set of target keywords and the estimated set of keyword interest weights to determine an estimated user interest of the target message;wherein the target message is displayed when the estimated user interest of the target message is favorable compared to other estimated user interests of other messages. 33. The mobile client according to claim 32, wherein the prediction means performs a prediction routine by performing at least a correlation operation R={circumflex over (P)}·A, where {circumflex over (P)} is a current estimate of user interest weights and A is a vector representation of the target message. 34. The mobile client according to claim 31, wherein the learning means performs at least one steepest descent algorithm to estimate at least one keyword interest weight. 35. The mobile client according to claim 31, wherein the learning means incorporates random or pseudo-random noise in the learning operations. 36. The mobile client according to claim 31, wherein a cardinality of the set of target keywords is sparse relative to a size of a keyword dictionary. 37. The mobile client according to claim 31, wherein only a subset of the set of target keywords is used to display the target message on the mobile client. 38. The mobile client according to claim 37, wherein the subset of keywords is determined based upon a threshold interest value. 39. A non-transitory computer-readable medium comprising instructions for the following operations: instructions for receiving a plurality of sets of one or more first keywords on a mobile client, each set of first keywords associated with one or more respective first messages;instructions for monitoring user interaction of the respective first messages on the mobile client;instructions for performing learning operations on the mobile client with the first keywords based on monitored user interaction to estimate a set of keyword interest weights;instructions for receiving a set of target keywords associated with a target message;instructions for receiving the target message over a wireless link if the estimated set of keyword interest weights indicate a desirability of the target message; andinstructions for displaying the target message on the mobile client based on the estimated set of keyword interest weights.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (99)
Landsman Rick W. ; Lee Wei-Yeh, Ad controller for use in implementing user-transparent network-distributed advertising and for interstitially displaying an advertisement so distributed.
Yalamanchili, Kishore; Nagaraj, Yogeshwar Narayanan; Keshava Iyengar, Rashmi; Krishnaswamy, Dilip; Beraha, Rodolfo Giacomo, Adaptive hardware reconfiguration of configurable co-processor cores for hardware optimization of functionality blocks based on use case prediction, and related methods, circuits, and computer-readable media.
Nakano Hirohiko (Yokohama JPX) Domyo Seiichi (Yokohama JPX) Kuroda Takaki (Yokohama JPX) Shouji Naofumi (Yokohama JPX) Kobayashi Atsushi (Machida JPX), Distributed file system permitting each user to enhance cache hit ratio in file access mode.
Bergh Christopher P. ; Metral Max E. ; Ritter David Henry ; Sheena Jonathan Ari ; Sullivan James J., Distributed system for facilitating exchange of user information and opinion using automated collaborative filtering.
Imai Toru,JPX ; Shimokawa Toshihiko,JPX ; Yoshida Hideki,JPX ; Fujii Hiroku,JPX, File reading method and file requesting client device in client-server information communication system.
Sullivan David J. ; Gauvin William Joseph ; Taranto Edward James, Method and apparatus for accessing copies of documents using a web browser request interceptor.
Singer, Howard; Popkin, Laird; Sadan, Yariv, Method and device for the wireless exchange of media content between mobile devices based on content preferences.
O'Toole, James; Morris, Stephen; Lapolito, Anthony, Method and system for dynamically pre-positioning content in a network based detecting or predicting user presence.
Krishnaswamy, Dilip; Aggarwal, Pooja; Daley, Robert S; Renschler, Martin; Lundqvist, Patrik, Method and system for message value calculation in a mobile environment.
Krishnaswamy, Dilip; Aggarwal, Pooja, Method and system for using a cache miss state match indicator to determine user suitability of targeted content messages in a mobile environment.
R. Russell Caldwell ; Michael C. Merrill ; Michael L. Greene ; Roy G. Wells, Method for mapping applications and or attributes in a distributed network environment.
Bharat Krishna Asur ; Henzinger Monika R., Method for ranking documents in a hyperlinked environment using connectivity and selective content analysis.
Stringer Calvert,David W. J.; Dawson,Steven Mark; Lincoln,Patrick D., Methods and apparatus for scalable, distributed management of virtual private networks.
Elbaz, Gilad Israel; Bronson, Kenneth, Methods and systems for providing relevant advertisements or other content for inactive uniform resource locators using search queries.
Jean Charpentier FR; Edouard Issenmann FR; Roger Larousse FR; Patrick Lohat FR, Mobile telephony method and system using signaling messages with priority levels.
Horvitz,Eric J.; Kadie,Carl M., Multi-attribute specification of preferences about people, priorities and privacy for guiding messaging and communications.
Pradhan, Salil; McDonnell, James Thomas Edward; Waters, John Deryk; Macer, Peter J., Profiles for information acquisition by devices in a wireless network.
Herz Frederick S. M. ; Eisner Jason M. ; Salganicoff Marcos, Pseudonymous server for system for customized electronic identification of desirable objects.
Gabber Eran ; Gibbons Phillip P. ; Matias Yossi ; Mayer Alain J., System and method for providing anonymous personalized browsing by a proxy system in a network.
Peters, Jr.,Robert Yaeger; Samarasinghe,Harish, System and method for providing multi-media services to communication devices over a communications network.
Herz Frederick S. M. ; Eisner Jason M. ; Ungar Lyle H. ; Marcus Mitchell P., System for generation of user profiles for a system for customized electronic identification of desirable objects.
Rose Daniel E. ; Bornstein Jeremy J. ; Tiene Kevin ; Ponceleon Dulce B., System for ranking the relevance of information objects accessed by computer users.
Alexander Ronald ; Dias Stephen ; Hancock Kenneth S. ; Leung Elsie Y. ; Macrae Douglas ; Ng Arthur Y. ; O'Neil Shawn ; Schoaff Peter Christopher ; Sutton Jonathon ; Ward ; III Thomas Edward ; Westber, Systems and methods for displaying and recording control interface with television programs, video, advertising information and program scheduling information.
Bell,David; Bygrave,Chris; Dineen,Oliver; Norton,Philip, Systems and methods for generating pattern keys for use in navigation systems to predict user destinations.
Andreasson, Måns Folke Markus; Bengtsson, Henrik; Cronström, David Sebastian; Stavenow, Bengt Gunnar; Baard, Henrik, Using personal data for advertisements.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.