Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020109946 - PARTITIONING KNOWLEDGE GRAPH

Publication Number WO/2020/109946
Publication Date 04.06.2020
International Application No. PCT/IB2019/060059
International Filing Date 22.11.2019
IPC
G06F 16/35 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
30of unstructured textual data
35Clustering; Classification
CPC
G06F 16/2425
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
2425Iterative querying; Query formulation based on the results of a preceding query
G06F 16/285
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
20of structured data, e.g. relational data
28Databases characterised by their database models, e.g. relational or object models
284Relational databases
285Clustering or classification
G06F 16/9024
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
9024Graphs; Linked lists
G06F 16/906
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
906Clustering; Classification
Applicants
  • INTERNATIONAL BUSINESS MACHINES CORPORATION [US]/[US]
  • IBM (CHINA) INVESTMENT COMPANY LTD. [CN]/[CN] (MG)
  • IBM DEUTSCHLAND GMBH [DE]/[DE] (MG)
Inventors
  • SCHEIDELER, Tim
  • RUEGER, Erik
  • RAVIZZA, Stefan
  • FLOETHER, Frederik
Agents
  • KLETT, Peter
Priority Data
16/200,75727.11.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) PARTITIONING KNOWLEDGE GRAPH
(FR) GRAPHE DE CONNAISSANCES DE PARTITIONNEMENT
Abstract
(EN)
A method for partitioning a knowledge graph is provided. The method analyzes past searches and determines an access frequency of a plurality of edges. The method marks, as intermediate cluster cores, edges having the highest access frequencies, sorts the marked 5intermediate cluster cores according to their access frequencies, and selects a first cluster core having the highest access frequency. The method assigns first edges in a first radiusaround the first cluster core to build the first cluster. The method selects a second cluster core having the highest access frequency apart from edges of the first cluster, and assignssecond edges in a second radius around second cluster core to build the second cluster. The 0method partitions the knowledge graph into a first sub-knowledge-graph comprising the first cluster and a second sub-knowledge-graph comprising the second cluster.
(FR)
L'invention concerne un procédé de partitionnement d'un graphe de connaissances. Le procédé analyse des recherches antérieures et détermine une fréquence d'accès d'une pluralité de bords. Le procédé marque, en tant que noyaux de grappe intermédiaires, des bords ayant les fréquences d'accès les plus élevées, trie les 5 noyaux de grappe intermédiaires marqués selon leurs fréquences d'accès, et sélectionne un premier noyau de grappe ayant la fréquence d'accès la plus élevée. Le procédé attribue des premiers bords dans un premier rayon autour du premier noyau de grappe pour construire la première grappe. Le procédé sélectionne un second noyau de grappe ayant la fréquence d'accès la plus élevée à l'exception des bords de la première grappe, et attribue des seconds bords dans un second rayon autour du second noyau de grappe pour construire la seconde grappe. Le procédé partitionne le graphe de connaissances en un premier sous-graphe de connaissances comprenant la première grappe et un second sous-graphe de connaissances comprenant la seconde grappe.
Also published as
Latest bibliographic data on file with the International Bureau