Processing

Please wait...

Settings

Settings

Goto Application

1. WO2018023106 - SYSTEM AND METHOD OF DISAMBIGUATING NATURAL LANGUAGE PROCESSING REQUESTS

Publication Number WO/2018/023106
Publication Date 01.02.2018
International Application No. PCT/US2017/044610
International Filing Date 31.07.2017
IPC
G06F 17/27 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
20Handling natural language data
27Automatic analysis, e.g. parsing, orthograph correction
CPC
G06F 16/219
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
20of structured data, e.g. relational data
21Design, administration or maintenance of databases
219Managing data history or versioning
G06F 16/243
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
20of structured data, e.g. relational data
24Querying
242Query formulation
243Natural language query formulation
G06F 16/24575
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
20of structured data, e.g. relational data
24Querying
245Query processing
2457with adaptation to user needs
24575using context
G06F 16/90332
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
90Details of database functions independent of the retrieved data types
903Querying
9032Query formulation
90332Natural language query formulation or dialogue systems
G06F 16/9535
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
90Details of database functions independent of the retrieved data types
95Retrieval from the web
953Querying, e.g. by the use of web search engines
9535Search customisation based on user profiles and personalisation
G06F 40/295
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
40Handling natural language data
20Natural language analysis
279Recognition of textual entities
289Phrasal analysis, e.g. finite state techniques or chunking
295Named entity recognition
Applicants
  • VOICEBOX TECHNOLOGIES CORPORATION [US]/[US]
  • SWART, Erik [US]/[US]
  • DROUIN, Emilie [US]/[US]
Inventors
  • SWART, Erik
  • DROUIN, Emilie
Agents
  • RUGGIERO, Charles N.J.
Priority Data
62/368,97529.07.2016US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SYSTEM AND METHOD OF DISAMBIGUATING NATURAL LANGUAGE PROCESSING REQUESTS
(FR) SYSTÈME ET PROCÉDÉ DE DÉSAMBIGUÏSATION DE DEMANDES DE TRAITEMENT DE LANGAGE NATUREL
Abstract
(EN)
A system and method is provided of disambiguating natural language processing requests based on smart matching, request confirmations that are used until ambiguities are resolved, and machine learning. Smart matching may match entities (e.g., contact names, place names, etc.) based on user information such as call logs, user preferences, etc. If multiple matches are found and disambiguation has not yet been learned by the system, the system may request that the user identify the intended entity. On the other hand, if disambiguation has been learned by the system, the system may execute the request without confirmations. The system may use a record of confirmations and/or other information to continuously learn a user's inputs in order to reduce ambiguities and no longer prompt for confirmations.
(FR)
L'invention concerne un système et un procédé destinés à désambiguïser des demandes de traitement de langage naturel (NLP) d'après une mise en correspondance intelligente, à demander des confirmations qui sont utilisées jusqu'à ce que les ambiguïtés soient résolues, et à réaliser un apprentissage automatique. La mise en correspondance intelligente peut mettre en correspondance des entités (p. ex. des noms de contacts, des noms de lieux, etc.) d'après des informations d'utilisateurs comme des journaux d'appels, des préférences d'utilisateurs, etc. Si des correspondances multiples sont trouvées et si la désambiguïsation n'a pas encore été apprise par le système, le système peut demander à l'utilisateur d'identifier l'entité souhaitée. En revanche, si la désambiguïsation a été apprise par le système, le système peut exécuter la demande sans confirmations. Le système peut utiliser une consignation des confirmations et/ou d'autres informations pour apprendre de façon continue les saisies d'un utilisateur afin de réduire les ambiguïtés et de ne plus solliciter de confirmations.
Also published as
Latest bibliographic data on file with the International Bureau