Back to results
US 2026/0268359 A1Published application
Systems and methods for features engineering
AssigneeKinaxis Inc.
InventorsSebastien Ouellet, Zhen Lin, Christopher Wang, Chantal Bisson-Krol
Life of this patent
Estimating the term…
Abstract
Systems and methods for features engineering, in which internal and external signals are received and fused. The fusing is based on meta-data of each of the one or more internal signals and each of the one or more external signals. A set of features is generated based on one or more valid combinations that match a transformation input, the transformation forming part of library of transformations. Finally, a set of one or more features is selected from the plurality of features, based on a predictive strength of each feature. The set of selected features can be used to train and select a machine learning model.
Claims20
A computer-implemented method comprising:
- engineering, by a processor, one or more features based on fused signal data from signal data comprising a data file and a meta-data file that defines content of the data file, wherein the data file contains columns and values for a given signal, and the meta-data file associated with the data file contains column names and associated types;
- wherein engineering one or more features comprises:
- receiving, by the processor, internal signal data;
- receiving, by the processor, external signal data;
- determining if a range is present for the internal signal data or the external signal data or both, and if so, expanding the signal data and generating meta-data for the expanded signal data;
- fusing, by the processor, the signal data into a fused signal data based on internal signal meta-data and external signal meta-data;
- generating, by the processor, a plurality of features from the fused signal data based on one or more valid combinations that match a transformation input, the transformation forming part of a library of transformations;
- selecting, by the processor, one or more features from the plurality of features, based on a predictive strength of each feature, to provide a set of selected features;
- and
- training, by the processor, one or more machine learning models, using the set of selected features.
7 more elements
A system comprising:
- a processor;
- and
- a memory storing instructions that, when executed by the processor, configure the system to:
- engineer, by the processor, one or more features based on fused signal data from signal data comprising a data file and a meta-data file that defines content of the data file, wherein the data file contains columns and values for a given signal, and the meta-data file associated with the data file contains column names and associated types;
- and
- wherein when engineering the one or more features, the system is configured to:
- receive, by the processor, internal signal data;
- receive, by the processor, external signal data;
- determine if a range is present for the internal signal data or the external signal data or both, and if so, expand the signal data and generate meta-data for the expanded signal data;
- fuse, by the processor, the signal data into a fused signal data based on internal signal meta-data and external signal meta-data;
- generate, by the processor, a plurality of features from the fused signal data based on one or more valid combinations that match a transformation input, the transformation forming part of a library of transformations;
- select, by the processor, one or more features from the plurality of features, based on a predictive strength of each feature, to provide a set of selected features;
- and
- train, by the processor, one or more machine learning models, using the set of selected features.
11 more elements
A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to:
- engineer, by a processor, one or more features based on fused signal data from signal data comprising a data file and a meta-data file that defines content of the data file, wherein the data file contains columns and values for a given signal, and the meta-data file associated with the data file contains column names and associated types;
- and
- wherein when engineering the one or more features, the system is configured to:
- receive, by the processor, internal signal data;
- receive, by the processor, external signal data;
- determine if a range is present for the internal signal data or the external signal data or both, and if so, expand the signal data and generate meta-data for the expanded signal data;
- fuse, by the processor, the signal data into a fused signal data based on internal signal meta-data and external signal meta-data;
- generate, by the processor, a plurality of features from the fused signal data based on one or more valid combinations that match a transformation input, the transformation forming part of a library of transformations;
- select, by the processor, one or more features from the plurality of features, based on a predictive strength of each feature, to provide a set of selected features;
- and
- train, by the processor, one or more machine learning models, using the set of selected features.
8 more elements
Dependencies are inferred from the claim text.