Unlock instant, AI-driven research and patent intelligence for your innovation.

System and method for data extraction for machine learning

A machine learning and data extraction technology, applied in machine learning, general control systems, control/regulation systems, etc., can solve problems such as low efficiency and difficult deployment

Pending Publication Date: 2022-02-18
GE GLOBAL SOURCING LLC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, deployment difficulties can arise based on the input type, and current transformation methods are inefficient in using or transforming different types of inputs

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • System and method for data extraction for machine learning
  • System and method for data extraction for machine learning
  • System and method for data extraction for machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] Embodiments of the subject matter described herein relate to systems and methods for transforming or converting information for artificial intelligence (AI) modeling based on received input configurations or input types. For example, given an incoming PNG file, the corresponding image can be reshaped, extracted, and reformatted to match the format used by the AI ​​model. In various embodiments, the front-end performs the conversion from a particular incoming file format to the corresponding intermediate n-dimensional array ("ND array") representation, while the back-end performs additional post-processing, such as reshaping, resizing, linear algebra methods execution and / or tasks such as channel alignment.

[0014] Various embodiments provide the technical effect of allowing the use of many different types of AI input data. Various embodiments provide the technical effect of improving the efficiency and convenience of developing and / or using AI models. Various embodim...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a data extraction system and method for machine learning. The system includes, for example, a maintenance system, a maintenance task input unit and one or more processors. The maintenance task input unit is configured to generate a plurality of input data sets corresponding to maintenance tasks. Each input data set adopts a corresponding format of a plurality of formats. The processor is coupled to the maintenance task input unit and is configured to obtain a plurality of input data sets from the maintenance task input unit; identify each input data set as a particular format of the plurality of formats; prepare an intermediate representation of the input data set based on the identified particular format; modify the intermediate representation corresponding to each input data set into a general format; and provide the model input to an artificial intelligence modeler of the maintenance system, and the artificial intelligence modeler is configured to use the model input for developing and / or using the model for vehicle maintenance.

Description

[0001] related application [0002] This application claims priority to U.S. Patent Application No. 63 / 062438, filed August 6, 2020, entitled "Data Extraction for Machine Learning Systems and Methods," the entire subject matter of which is hereby incorporated by reference. technical field [0003] The described subject matter relates to systems and methods used in conjunction with data extraction for machine learning, such as for developing and / or using artificial intelligence models to maintain components of vehicles. Background technique [0004] Machine learning and artificial intelligence (AI) models can receive input data for use in matrix format, however numeric matrix data may not be an allowed input. Therefore, transformations can be performed as a preprocessing step for many AI models. However, deployment difficulties may arise based on input types, and current transformation methods are inefficient in using or transforming different types of inputs. Contents of ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/15G06F30/27G06N20/00
CPCG06F30/15G06F30/27G06N20/00G05B23/0243G05B2219/2637G05B2219/25204G07C5/006G07C5/008G07C5/0825G07C5/0833
Inventor N·T·诺思
Owner GE GLOBAL SOURCING LLC