Techniques to embed a data object into a multidimensional frame
AssigneeCapital One Services, LLC
InventorsAustin Grant Walters, Jeremy Edward Goodsitt, Mark Louis Watson, Anh Truong
Life of this patent
Estimating the term…
Abstract
Various embodiments are generally directed to techniques for embedding a data object into a multidimensional frame, such as for training an autoencoder to generate latent space representations of the data object based on the multidimensional frame, for instance. Additionally, in one or more embodiments latent space representations of data objects may be classified, such as with a machine learning algorithm. Some embodiments are particularly directed to embedding a data object comprising a plurality of object entries into a three-dimensional (3D) frame.
Claims19
An apparatus, comprising:
- a processor;
- and
- memory comprising instructions that, when executed by the processor, cause the processor to:
- access a data object comprising a set of object entries, wherein each object entry in the set of object entries comprises a row value, a column value, and at least one cell contents entry, wherein the object entry corresponds to a data table entry, and wherein the row value and the column value indicate a location of the data table entry in a data table;
- generate a multidimensional frame based on the data object, the multidimensional frame comprising a row dimension, a column dimension, and a content dimension, wherein at least one row value is mapped onto the row dimension, at least one column value is mapped onto the column dimension, and the at least one cell contents entry is mapped along the contents dimension to generate the multidimensional frame;
- and
- utilize a trained encoder to embed the multidimensional frame into a latent space representation of the multidimensional frame.
A method comprising:
- accessing a data object comprising a set of object entries, wherein each object entry in the set of object entries comprises a row value, a column value, and at least one cell contents entry wherein the object entry corresponds to a data table entry, and wherein the row value and the column value indicate a location of the data table entry in a data table;
- generating a multidimensional frame based on the data object, the multidimensional frame comprising a row dimension, a column dimension, and a content dimension, wherein at least one row value is mapped onto the row dimension, at least one column value is mapped onto the column dimension, and the at least one cell contents entry is mapped along the contents dimension to generate the multidimensional frame;
- and
- utilizing a trained encoder to embed the multidimensional frame into a latent space representation of the multidimensional frame.
A non-transitory computer-readable storage medium having executable instructions stored thereon, which when executed by a processing circuit, cause the processing circuit to:
- access a data object comprising a set of object entries, wherein each object entry in the set of object entries comprises a row value, a column value, and at least one cell contents entry wherein the object entry corresponds to a data table entry, and wherein the row value and the column value indicate a location of the data table entry in a data table;
- generate a multidimensional frame based on the data object, the multidimensional frame comprising a row dimension, a column dimension, and a content dimension, wherein at least one row value is mapped onto the row dimension, at least one column value is mapped onto the column dimension, and the at least one cell contents entry is mapped along the contents dimension to generate the multidimensional frame;
- and
- utilize a trained encoder to embed the multidimensional frame into a latent space representation of the multidimensional frame.
Dependencies are inferred from the claim text.