Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020264518 - APPARATUS OF A KNOWLEDGE GRAPH TO ENHANCE THE PERFORMANCE AND CONTROLLABILITY OF NEURAL RANKING ENGINES

Publication Number WO/2020/264518
Publication Date 30.12.2020
International Application No. PCT/US2020/040176
International Filing Date 29.06.2020
IPC
G06F 19/00 2018.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
19Digital computing or data processing equipment or methods, specially adapted for specific applications
G06F 16/00 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
G06N 5/02 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
02Knowledge representation
CPC
G06F 16/9027
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
901Indexing; Data structures therefor; Storage structures
9027Trees
G06F 16/9032
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
G06N 5/02
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
02Knowledge representation
Applicants
  • SCHEINBERG, Michael [US]/[US] (TT)
  • PORTER, Tim [GB]/[GB]
  • SAMA, Michele [IT]/[CH]
  • PEDDER, Christopher [GB]/[CH]
  • DA PALMA, Andre [PT]/[GB]
  • TANDIROGLU, Ozgun [GB]/[GB]
Inventors
  • PORTER, Tim
  • SAMA, Michele
  • PEDDER, Christopher
  • DA PALMA, Andre
  • TANDIROGLU, Ozgun
Agents
  • SCHEINBERG, Michael
Priority Data
62/868,20228.06.2019US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) APPARATUS OF A KNOWLEDGE GRAPH TO ENHANCE THE PERFORMANCE AND CONTROLLABILITY OF NEURAL RANKING ENGINES
(FR) APPAREIL D'UN GRAPHE DE CONNAISSANCES PERMETTANT D'AMÉLIORER LA PERFORMANCE ET LA CONTRÔLABILITÉ DE MOTEURS DE CLASSEMENT NEURONAL
Abstract
(EN)
This invention allows the semi-automated creation and curation of a knowledge graph based on a query-atom IR ranking engine. This invention cooperates with a domain expert to smoothly and semi-automatically incorporate or restructure textual data in the knowledge graph when a suitable high-confidence response to a query cannot be found. The invention extends the conventional information retrieval approach to consumer interaction by building a structured knowledge graph. Using graph exploration the invention augments the ranking made by the underlying neural model in order to stay in sync with the constantly-changing domain of application. The ultimate goal of this invention is to allow the consistent, cognitive, consumer- driven incorporation and restructuring of relevant unstructured data in a knowledge graph which is generated by mimicking users behaviours.
(FR)
L'invention permet la création et la conservation semi-automatisées d'un graphe de connaissances sur la base d'un moteur de classement de récupération d'informations (IR) atome- interrogation. Ce système coopère avec un expert de domaine pour incorporer ou restructurer sans à-coups et semi-automatiquement des données textuelles dans le graphe de connaissances lorsqu'une réponse de confiance élevée appropriée à une interrogation ne peut pas être trouvée. L'invention étend l'approche de récupération d'informations classique à une interaction de consommateur par construction d'un graphe de connaissances structuré. À l'aide d'une exploration graphique, l'invention augmente le classement effectué par le modèle neuronal sous-jacent afin de rester en synchronisation avec le domaine d'application changeant constamment. Le but final de ce système est de permettre l'incorporation et la restructuration cohérente, cognitive, entraînée par le consommateur de données non structurées pertinentes dans un graphe de connaissances qui est généré par imitation de comportements d'utilisateurs.
Latest bibliographic data on file with the International Bureau