US 2021/0232971 A1 · DATA META-MODEL BASED FEATURE VECTOR SET GENERATION FOR TRAINING MACHINE LEARNING MODELS

Abstract

This disclosure relates generally to data meta model and meta file generation for feature engineering and training of machine learning models thereof. Conventional methods do not facilitate appropriate relevant data identification for feature engineering and also do not implement standardization for use of solution across domains. Embodiments of the present disclosure provide systems and methods wherein datasets from various sources/domains are utilized for meta file generation that is based on mapping of the dataset with a data meta model based on the domains, the meta file comprises meta data and information pertaining to action(s) being performed. Further functions are generated using the meta file and the functions are assigned to corresponding data characterized in the meta file. Further functions are invoked to generate feature vector set and machine learning model(s) are trained using the features vector set. Implementation of the generated data meta-model enables re-using of feature engineering code.

Claims12

Dependent claims

A processor implemented method, comprising:

obtaining, via one or more hardware processors, a plurality of datasets from a plurality of sources, wherein the plurality of datasets corresponding to one or more domains;
generating, via the one or more hardware processors, a meta file based on a mapping of the plurality of datasets obtained from the plurality of sources to a data meta model that is identified based on the one or more domains, wherein the meta file comprises meta data and information pertaining to one or more specific actions being performed;
generating, via the one or more hardware processors, one or more functions using the generated meta file and assigning the generated one or more functions to one or more corresponding data characterized in the generated meta file;
invoking, via the one or more hardware processors, the generated one or more functions to generate a feature vector set specific to the one or more corresponding data comprised in the plurality of datasets;
and
training, via the one or more hardware processors, one or more machine learning models using the features vector set.

3 more elements

One or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause data meta-model-based feature vector set generation for training machine learning models by:

obtaining a plurality of datasets from a plurality of sources, wherein the plurality of datasets corresponding to one or more domains;
generating a meta file based on a mapping of the plurality of datasets obtained from the plurality of sources to a data meta model that is identified based on the one or more domains, wherein the meta file comprises meta data and information pertaining to one or more specific actions being performed;
generating one or more functions using the generated meta file and assigning the generated one or more functions to one or more corresponding data characterized in the generated meta file;
invoking the generated one or more functions to generate a feature vector set specific to the one or more corresponding data comprised in the plurality of datasets;
and
training one or more machine learning models using the features vector set.

3 more elements

Dependencies are inferred from the claim text.

Data meta-model based feature vector set generation for training machine learning models

Life of this patent

Data meta-model based feature vector set generation for training machine learning models

Life of this patent

Abstract

Claims12