METHOD AND SYSTEM FOR PRODUCING VARIABLE LENGTH CONTEXT MODELS

Patent №

US 7,624,009

Granted

2009-11-24

Filed 2004

Owner

HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.

Lab

AI components

4

ml · kr · planning · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

10933793

Various embodiments of the present invention provide methods and systems for determining, representing, and using variable-length contexts in a variety of different computational applications. In one embodiment of the present invention, a balanced tree is used to represent all possible contexts of a fixed length, where the depth of the balanced tree is equal to the fixed length of the considered contexts. Then, in the embodiment, a pruning technique is used to sequentially coalesce the children of particular nodes in the tree in order to produce an unbalanced tree representing a set of variable-length contexts. The pruning method is selected, in one embodiment, to coalesce nodes, and, by doing so, to truncate the tree according to statistical considerations in order to produce a representation of a variably sized context model suitable for a particular application.

AI classification

Machine learning1.00
Planning1.00
Knowledge representation0.98
AI hardware0.97
Vision0.12
Natural language0.01
Evolutionary computation0.00
Speech0.00

Ownership

HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.

assignment · 161260461

Assignors

SEROUSSI, GADIEL, VERDU, SERGIO, WEINBERGER, MARCELO, WIESSMAN, ITSCHAK, ORDENTLICH, ERIK

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC