Task/domain segmentation in applying feedback to command control
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06F-007/00
G06F-017/30
출원번호
US-0451465
(2012-04-19)
등록번호
US-8849842
(2014-09-30)
발명자
/ 주소
Reisman, Richard
출원인 / 주소
RPX Corporation
대리인 / 주소
Berkeley Law & Technology Group, LLP
인용정보
피인용 횟수 :
0인용 특허 :
61
초록▼
An apparatus for responding to a current user command associated with one of a plurality of task/domains. The apparatus comprises: a digital storage device that stores cumulative feedback data gathered from multiple users during previous operations of the apparatus and segregated in accordance with
An apparatus for responding to a current user command associated with one of a plurality of task/domains. The apparatus comprises: a digital storage device that stores cumulative feedback data gathered from multiple users during previous operations of the apparatus and segregated in accordance with the plurality of task/domains; a first digital logic device that determines the current task/domain with which the current user command is associated; a second digital logic device that determines a current response to the current user command on the basis of that portion of the stored cumulative feedback data associated with the current task/domain; a first communication interface that communicates to the user the current response; and a second communication interface that receives from the user current feedback data regarding the current response. The current feedback data is added to the cumulative feedback data stored in the digital storage device and associated with the current task/domain.
대표청구항▼
1. A method for responding to a current user command initiated by a user, comprising: storing cumulative feedback data provided by a plurality of users in a memory of a computing platform, said cumulative feedback data relating to individual items provided in a plurality of responses to a plurality
1. A method for responding to a current user command initiated by a user, comprising: storing cumulative feedback data provided by a plurality of users in a memory of a computing platform, said cumulative feedback data relating to individual items provided in a plurality of responses to a plurality of previous user commands, said cumulative feedback data heuristically organized with regard to respective ones of the plurality of previous user commands, with regard to respective ones of the plurality of users, and with regard to task-domain;determining one or more subsets of the plurality of users;determining, utilizing at least in part a processor of the computing platform, a current response to the current user command based at least in part on a portion of the cumulative feedback data related to one or more of the plurality of previous responses to one or more of the plurality of previous user commands related to the current user command and associated with other users of the one or more subsets of users;communicating to the user the current response comprising one or more results weighted at least in part according a factor related to said one or more of the plurality of previous responses associated with the other users;receiving from the user current feedback data regarding the current response; andadding the current feedback data to a portion of the stored cumulative feedback data associated with the current user. 2. The method of claim 1, wherein the one or more subsets of the plurality of users are determined based at least in part on a parameter indicative of a relative similarity between individual ones of the plurality of users and the current user. 3. The method of claim 2, wherein the factor corresponds at least in part to respective ones of the one or more subsets of users of which the other users are a member. 4. The method of claim 2, wherein the factor is based at least in part on an explicit specification by the user. 5. The method of claim 2, wherein the factor is based at least in part on an implicit specification by the user. 6. The method of claim 2, wherein said storing the cumulative feedback comprises storing explicit feedback data provided by one or more of the plurality of users. 7. The method of claim 2, wherein said storing the cumulative feedback comprises storing implicit feedback data provided by one or more of the plurality of users. 8. The method of claim 1, wherein the current user command comprises a search query and wherein the individual items comprise items responsive to the search query. 9. The method of claim 8, wherein the search query comprises a Boolean query. 10. The method of claim 8, wherein the search query comprises a natural language query. 11. A server computing system, comprising: a memory to store cumulative feedback data provided by a plurality of users, said cumulative feedback data relating to individual items provided in a plurality of responses to a plurality of previous user commands, said cumulative feedback data heuristically organized with regard to respective ones of the plurality of previous user commands and with regard to respective ones of the plurality of users, and with regard to task-domain; anda processor to determine one or more subsets of the plurality of users, the processor further to determine a current response to a current user command initiated by a user based at least in part on a portion of the cumulative feedback data related to one or more of the plurality of previous responses to one or more of the plurality of previous user commands related to the current user command and associated with other users of the one or more subsets of users, the processor to communicate to the user the current response comprising one or more results weighted at least in part according a factor related to said one or more of the plurality of previous responses associated with the other users, the processor further to receive from the user current feedback data regarding the current response, and to add the current feedback data to a portion of the stored cumulative feedback data associated with the current user. 12. The server computing system of claim 11, the processor to determine one or more subsets of the plurality of users based at least in part on a parameter indicative of a relative similarity between individual ones of the plurality of users and the current user. 13. The server computing system of claim 12, wherein the factor corresponds at least in part to respective ones of the one or more subsets of users of which the other users are a member. 14. The server computing system of claim 12, wherein the factor is based at least in part on an explicit specification by the user. 15. The server computing system of claim 12, wherein the factor is based at least in part on an implicit specification by the user. 16. The server computing system of claim 12, the memory to store the cumulative feedback at least in part by storing explicit feedback data provided by one or more of the plurality of users. 17. The server computing system of claim 12, the memory to store the cumulative feedback at least in part by storing implicit feedback data provided by one or more of the plurality of users. 18. The server computing system of claim 11, wherein the current user command comprises a search query and wherein the individual items comprise items responsive to the search query. 19. The server computing system of claim 18, wherein the search query comprises a Boolean query. 20. The server computing system of claim 18, wherein the search query comprises a natural language query. 21. An article, comprising′ a non-transitory computer readable storage medium having stored thereon instructions executable by a processing unit of a computer system to: store cumulative feedback data provided by a plurality of users in a memory of the computing platform, said cumulative feedback data relating to individual items provided in a plurality of responses to a plurality of previous user commands, said cumulative feedback data heuristically organized with regard to respective ones of the plurality of previous user commands and with regard to respective ones of the plurality of users, and with regard to task-domain;determine one or more subsets of the plurality of users;determine a current response to a current user command initiated by a user based at least in part on a portion of the cumulative feedback data related to one or more of the plurality of previous responses to one or more of the plurality of previous user commands related to the current user command and associated with other users of the one or more subsets of users;communicate to the user the current response comprising one or more results weighted at least in part according a factor related to said one or more of the plurality of previous responses associated with the other users;receive from the user current feedback data regarding the current response; andadd the current feedback data to a portion of the stored cumulative feedback data associated with the current user. 22. The article of claim 21, wherein the computer readable storage medium has stored thereon further instructions executable by the processor to determine the one or more subsets of the plurality of users based at least in part on a parameter indicative of a relative similarity between individual ones of the plurality of users and the current user. 23. The article of claim 22, wherein the factor corresponds at least in part to respective ones of the one or more subsets of users of which the other users are a member. 24. The article of claim 22, wherein the factor is based at least in part on an explicit specification by the user. 25. The article of claim 22, wherein the factor is based at least in part on an implicit specification by the user. 26. The article of claim 22, wherein the computer readable storage medium has stored thereon further instructions executable by the processor to store the cumulative feedback at least in part by storing explicit feedback data provided by one or more of the plurality of users. 27. The article of claim 22, wherein the computer readable medium has stored thereon further instructions executable by the processor to store the cumulative feedback at least in part by storing implicit feedback data provided by one or more of the plurality of users. 28. The article of claim 21, wherein the current user command comprises a search query and wherein the individual items comprise items responsive to the search query. 29. The article of claim 28, wherein the search query comprises a Boolean query. 30. The article of claim 28, wherein the search query comprises a natural language query.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (61)
Kleindienst, Jan; Ramaswamy, Ganesh N.; Gopalakrishnan, Ponani; Coffman, Daniel M., Adaptive emotion and initiative generator for conversational systems.
Lang Andrew K. ; Kosak Donald M., Information system and method for filtering a massive flow of information entities to meet user information classificat.
Boyles Ray W. (Apex NC) Gierlach Michael F. (Raleigh NC) Gopal Prabandham M. (Wayne NJ) Sultan Robert (Richterswil NC CHX) Vacek Gary M. (Raleigh NC), Locating resources in computer networks having cache server nodes.
Davis Owen ; Jain Vidyut, Method and apparatus for tracking client interaction with a network resource and creating client profiles and resource database.
Dinkin Joel E. (Raleigh NC) Harter Johnathan L. (Raleigh NC) Henderson Julie M. (Durham NC) Kramer Dirk K. (Raleigh NC) Lerner Michael A. (Raleigh NC) Sandick Haldon J. (Durham NC), Method of combining architecturally dissimilar computing networks into a single logical network.
Agrawal Rakesh ; Chakrabarti Soumen ; Dom Byron Edward ; Raghavan Prabhakar, Multilevel taxonomy based on features derived from training documents classification using fisher values as discrimination values.
Beall Christopher W. ; Motycka John D. ; Pendleton Samuel S. ; Terpening Brooke E. ; Appelbaum Matthew A. ; Neal Michael R., Search engine for remote access to database management systems.
Jois Suresh Krishna ; Stankovic Alex ; Stankovic William ; Dressel Arthur, System and method for dynamic data interaction in a hypertext data processing system.
Davis Darren J. ; Derer Matthew ; Garcia Johann ; Greco Larry ; Kurt Tod E. ; Kwong Thomas ; Lee Jonathan C. ; Lee Ka Luk ; Pfarner Preston ; Skovran Steve, System and method for influencing a position on a search result list generated by a computer network search engine.
Hill William Colyer ; Terveen Loren Gilbert, System and method for locating resources on a network using resource evaluations derived from electronic messages.
Eves, David A.; Allen, Richard J.; Timms, Allan R., System and method for providing appropriate hyperlink based on identified keywords from text messages sent between users.
Kaplan Craig A. (Santa Cruz CA) Chen James R. (Saratoga CA) Fallside David C. (San Jose CA) Fenwick Justine R. (Santa Cruz CA) Forcier Mitchell D. (Walnut Creek CA) Wolff Gregory J. (Mountain View CA, System for adjusting hypertext links with weighed user goals and activities.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.