HEADER-TOKEN DRIVEN AUTOMATIC TEXT SEGMENTATION

Patent №

US 9,529,862

Granted

2016-12-27

Filed 2015

Owner

EBAY INC.

+1 more

Lab

AI components

6

ml · nlp · vision · speech · kr · planning

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

14724269

A method and a system to automatically segment text based on header tokens is described. A relevance value and an irrelevance value are determined for each token in a description, assuming no tokens are left out of computations. The irrelevance value is based on occurrences of a token in a sample set of descriptions. The relevance value is an estimated probability of relevance based on the header of the description being segmented.

AI classification

Natural language1.00
Machine learning1.00
Knowledge representation1.00
Planning1.00
Speech0.99
Vision0.88
AI hardware0.03
Evolutionary computation0.01

Ownership

EBAY INC.

assignment · 357350546

PAYPAL, INC.

assignment · 392610378

Assignors

SARWAR, BADRUL M., MOUNT, JOHN A.

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

© 2026 NYSGPT2525 LLC