[특허]Method and apparatus for performing plan-based dialog

[미국특허] Method and apparatus for performing plan-based dialog 원문보기

IPC분류정보
국가/구분	United States(US) Patent 등록
국제특허분류(IPC7판)	G10L-015/00
출원번호	US-0826858 (2004-04-16)
등록번호	US-7398211 (2008-07-08)
발명자 / 주소	Wang,Kuansan
출원인 / 주소	Microsoft Corporation
대리인 / 주소	Magee,Theodore M.
인용정보	피인용 횟수 : 7 인용 특허 : 20

초록 ▼

The present invention provides a dialog system in which the subsystems are integrated under a single technology model. In particular, each of the sub-systems uses stochastic modeling to identify a probability for its respective output. The combined probabilities identify a most probable action to be taken by the dialog system given the latest input from the user and the past dialog states. An additional aspect of the present invention is an embodiment in which the sub-systems communicate with one another through XML pages, thus allowing the sub-systems to be distributed across a distributed network.

대표청구항 ▼

What is claimed is: 1. A system for providing a computer-based dialog interface to a user, the system comprising: a dialog state engine that receives input from the user and that uses at least one stochastic model to generate at least one probability of a current dialog state given the user's input and a previous dialog state wherein the dialog state engine comprises: a recognition engine that uses a stochastic model to determine a probability of at least one surface semantic given the user input; and a discourse engine that uses a stochastic model to determine a probability of at least one current dialog state given the surface semantic from the recognition engine and a previous dialog state; and a rendering engine that uses a stochastic model to identify a probability of at least one action given a current dialog state. 2. The system of claim 1 wherein the current dialog state is represented by a discourse semantic structure. 3. The system of claim 2 wherein the discourse engine expands a discourse semantic structure based on the surface semantic before using a stochastic model to determine a probability for the discourse semantic structure. 4. The system of claim 3 wherein the dialog state engine further comprises a memory that is accessed by the discourse engine to resolve implicit references found in the user input. 5. The system of claim 4 wherein the memory comprises: a long-term memory containing values determined from previous user input; an explicit memory containing values taken from explicit references made in a current user input; and an implicit memory containing values that have been resolved from implicit references made in a current user input. 6. The system of claim 3 wherein the discourse semantic structure comprises semantic tokens that provide a general representation of specific entities and wherein the dialog state engine further comprises a database containing the specific entities that are represented by the semantic tokens. 7. The system of claim 1 wherein the rendering engine also receives an indication of the output interfaces that are available and wherein the rendering engine uses the stochastic model to identify a best action to take given the current dialog state, the probability of the current dialog state and the available output interface. 8. The system of claim 1 wherein the dialog state engine describes the current dialog state to the rendering engine by using a markup language. 9. A method of providing a dialog interface, the method comprising: receiving input generated by a user; determining a current dialog state based on the received input and a past dialog state; formatting the current dialog state into a markup language page; converting the markup language page into an output markup language page based on the current dialog state and an available output user interface; and passing the output markup language page to the available output user interface. 10. The method of claim 9 wherein formatting the current dialog state comprises formatting the current dialog state in an extensible markup language. 11. The method of claim 10 wherein formatting the current dialog state comprises formatting a discourse semantic structure into a markup language page. 12. The method of claim 11 wherein determining a current dialog state comprises: identifying a surface semantic in the input; formatting the surface semantic into a surface semantic markup language page; and identifying a discourse semantic structure from the surface semantic markup language page. 13. A system for providing a computer-based dialog interface to a user, the system comprising: a dialog state engine that receives input from the user and that generates a markup language page representing a current dialog state wherein the dialog state engine comprises: a recognition engine that receives user input and generates a markup language page representing surface semantics of the user input; and a discourse engine that converts the markup language page representing the surface semantics into the markup language page representing the dialog state; and a rendering engine that converts the markup language page representing the current dialog state into a markup language page representing an action.

이 특허에 인용된 특허 (20) 인용/피인용 타임라인 분석

Bigus Joseph Phillip ; Cragun Brian John ; Delp Helen Roxlo, Apparatus and method for optimizing the performance of computer tasks using multiple intelligent agents having varied degrees of domain knowledge.
상세보기
Wang, Huei-Ming; Lin, Yi-Chung; Chiang, Tung-Hui, Apparatus and method for portable dialogue management using a hierarchial task description table.
상세보기
Vassiliadis Stamatis (Vestal NY) Triantafyllos George (Vestal NY) Kobrosly Walid (Vestal NY), Clustering fuzzy expected value system.
상세보기
Echensperger Heimo,DEX ; Eibach Wolfgang,DEX ; Fox Michael,DEX ; Harz Hans H.,DEX ; Schaefer Rolf,DEX ; Streit Ralf,DEX, Computer system and method for performing multiple tasks.
상세보기
Eric Horvitz ; Timothy S. Paek, Computer-based representations and reasoning methods for engaging users in goal-oriented conversations.
상세보기
Chirico Neil F. (Charlotte NC), Expert system wtih a plurality of independent knowledge bases.
상세보기
Alimpich Claudia C. ; Goddard Joan Stagaman ; Neuhard Deborah E. ; Steinmeyer Cheryl ; Vo Minh Trong ; Wittig James Philip ; Yang Rachel Youngran, Graphical interface method, apparatus and application for creating a list from pre-defined and user-defined values.
상세보기
Johnson, David E.; Oles, Frank J.; Goetz, Thilo W., Interactive automated response system.
상세보기
David Ladd ; Gregory Johnson, Markup language for interactive services and methods thereof.
상세보기
Nicolas Chapados CA; Peter R. Stubley CA; Claudia Pateras CA; Real R. Tremblay CA, Method and apparatus for discourse management.
상세보기
Abella Alicia ; Gorin Allen Louis, Method and apparatus for generating sematically consistent inputs to a dialog manager.
상세보기
Ganesh N. Ramaswamy ; Upendra V. Chaudhari, Method and system for non-intrusive speaker verification using behavior models.
상세보기
Lagarde Konrad Charles ; Rogers Richard Michael, Method for distributed task fulfillment of web browser requests.
상세보기
Abella Alicia ; Brown Michael Kenneth ; Buntschuh Bruce Melvin, Methods and apparatus object-oriented rule-based dialogue management.
상세보기
Johnson David Edward, Multimodal natural language interface for cross-application tasks.
상세보기
Morin Philippe R. ; Applebaum Ted H. ; Junqua Jean-Claude, Multimodal voice dialing digital key telephone with dialog manager.
상세보기
Richards Jonathan B. ; Guthridge ; III Joseph W. ; Jones William H., Natural language help interface.
상세보기
Papineni Kishore A. ; Roukos Salim ; Ward Robert T., Natural language task-oriented dialog manager and method.
상세보기
Takebayashi Yoichi (Kanagawa JPX) Tsuboi Hiroyuki (Hyogo JPX) Sadamoto Yoichi (Chiba JPX) Yamashita Yasuki (Hyogo JPX) Nagata Yoshifumi (Kanagawa JPX) Seto Shigenobu (Kanagawa JPX) Shinchi Hideaki (K, Speech dialogue system for facilitating improved human-computer interaction.
상세보기
Marx Matthew T. ; Carter Jerry K. ; Phillips Michael S. ; Holthouse Mark A. ; Seabury Stephen D. ; Elizondo-Cecenas Jose L. ; Phaneuf Brett D., System and method for developing interactive speech applications.
상세보기

이 특허를 인용한 특허 (7) 인용/피인용 타임라인 분석

Gorin, Allen Louis; Parker, Barry Allen; Scherer, James B.; Wilpon, Jay Gordon, Automated task classification system.
상세보기
Gorin, Allen Louis; Parker, Barry Allen; Scherer, James B.; Wilpon, Jay Gordon, Automated task classification system.
상세보기
Sarikaya, Ruhi, Contextual language generation by leveraging language understanding.
상세보기
Dahlmeier, Daniel; Moser, Gerd; Suleiman, Basem; Roy, Marcus; Schrank, Dominik, Enhancing speech recognition with domain-specific knowledge to detect topic-related content.
상세보기
Weng, Fuliang; Ai, Hua, System and method for automated testing of complicated dialog systems.
상세보기
Kanungo,Tapas; Rhodes,James J., System and method for extracting entities of interest from text using n-gram models.
상세보기
Boyer, Stephen Kane; Breyta, Gregory; Kanungo, Tapas; Kreulen, Jeffrey Thomas; Rhodes, James J., System and method for identifying similar molecules.
상세보기

활용도 분석정보

상세보기

다운로드

내보내기

활용도 Top5 특허

해당 특허가 속한 카테고리에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다.
더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.

내보내기 메뉴

내보내기 구분

파일저장
인쇄
메일전송

구성항목

기본정보
상세정보

관리번호, 국가코드, 자료구분, 상태, 출원번호, 출원일자, 공개번호, 공개일자, 등록번호, 등록일자, 발명명칭(한글), 발명명칭(영문), 출원인(한글), 출원인(영문), 출원인코드, 대표IPC

저장형식

Text(ASCII format)
Excel format
PIAS분석(.xls)

메일정보

받는사람 (필수): @
보내는사람 (선택): @
제목
내용: KISTI 검색결과 이메일 서비스

안내

총 건의 자료가 검색되었습니다.

다운받으실 자료의 인덱스를 입력하세요. (1-10,000)

검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다.

데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요)

다운로드 파일은 UTF-8 형태로 저장됩니다.
파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오.

Text(ASCII format)
Excel format

AI-Helper ※ AI-Helper는 을 사용합니다.

AI-Helper

안녕하세요, AI-Helper입니다. 좌측 "선택된 텍스트"에서 텍스트를 선택하여 요약, 번역, 용어설명을 실행하세요.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.

IPC	Description
A	생활필수품
A62	인명구조; 소방(사다리 E06C)
A62B	인명구조용의 기구, 장치 또는 방법(특히 의료용에 사용되는 밸브 A61M 39/00; 특히 물에서 쓰이는 인명구조 장치 또는 방법 B63C 9/00; 잠수장비 B63C 11/00; 특히 항공기에 쓰는 것, 예. 낙하산, 투출좌석 B64D; 특히 광산에서 쓰이는 구조장치 E21F 11/00)
A62B-1/08	.. 윈치 또는 풀리에 제동기구가 있는 것

연합인증

[미국특허] Method and apparatus for performing plan-based dialog 원문보기