Invention Grant
- Patent Title: Feature extraction for machine learning
-
Application No.: US15161867Application Date: 2016-05-23
-
Publication No.: US10565520B2Publication Date: 2020-02-18
- Inventor: Janardan Misra , Shubhashis Sengupta , Sanjay Podder , Karthik Acharyulu
- Applicant: Accenture Global Solutions Limited
- Applicant Address: IE Dublin
- Assignee: Accenture Global Solutions Limited
- Current Assignee: Accenture Global Solutions Limited
- Current Assignee Address: IE Dublin
- Agency: Harrity & Harrity, LLP
- Priority: IN6492/CHE/2015 20150312
- Main IPC: G06F17/27
- IPC: G06F17/27 ; G06F17/00 ; G06F17/30 ; G06F17/21 ; G06F3/048 ; G06N99/00 ; G06F19/00 ; G06N20/00 ; G06F16/23 ; G06F16/31

Abstract:
A device may receive a first command, included in a set of commands, to set a configuration parameter associated with performing feature extraction. The device may receive a second command, included in the set of commands, to set a corresponding value for the configuration parameter. The configuration parameter and the corresponding value may correspond to a particular feature metric that is to be extracted. The device may configure, based on the configuration parameter and the corresponding value, feature extraction for a corpus of documents. The device may perform, based on configuring feature extraction for the corpus, feature extraction on the corpus to determine the particular feature metric. The device may generate a feature vector based on performing the feature extraction. The feature vector may include the particular feature metric. The feature vector may include a feature identifier identifying the particular feature metric. The device may provide the feature vector.
Public/Granted literature
- US20170161637A1 FEATURE EXTRACTION FOR MACHINE LEARNING Public/Granted day:2017-06-08
Information query