Siemens Aktiengesellschaft

Siemens Schweiz Ag

Swathi Shyam Sunder

Tobias Aigner

Martin Ringsquandl

Mitchell Joblin

Prithvi Raj Ramakrishnaraja

Yogesh Kamath

Yogesh Borkhade

Nataliia Rümmele

Rani Joseph

Aneta Koleva

A system and method for data management is provided. The method includes obtaining a dataset from a data source by a processing unit. The dataset includes a plurality of datapoints, and each of the datapoints belongs to a column among a plurality of columns. Further, an ontology label for at least one column in the dataset is predicted using a machine learning model. The predicted ontology label is associated with an ontology comprising a plurality of ontology labels. Further, a mapping between the dataset and the ontology is generated based on the relation between the predicted ontology label and the column. Furthermore, the datapoints are classified with respect to the ontology labels based on the mapping generated. The classified datasets are outputted on a user interface.

System and method for data management

A solution for automated column type annotation maps each column contained in a table to a column annotation class. A pre-processor transforms the table into a numerical tensor representation by outputting a sequence of cell tokens for each cell in the table. A table encoder encodes the sequences of cell tokens and a column annotation label for each column into body cell embeddings. A body pooling component processes the body cell embeddings to provide column representations. A classifier classifies the column representations to provide for each column, confidence scores for each column annotation class. The method concludes with comparing the highest confidence score for each column with a threshold, and, if the highest confidence score for each column is above the threshold, annotating each column with the respective column annotation class.

Method and system for automated column type annotation

Various embodiments of the teachings herein include a computer-aided method for transforming data in a relational database, containing sensor measurements, into RDF data blocks of a graph database. The method may include: providing a R2RML mapping file; breaking down and converting the data using the mapping file and a first mapping parser; generating a generation of RDF data blocks; and storing the generation as a database. After the data have been broken down and converted, checking a quality of the obtained R2RML mapping and creating a second R2RML mapping file, on the basis of which the relational data are broken down and converted into RDF data blocks. The second R2RML mapping, during the preparation of the relational data into RDF data blocks, automatically stops the processing of relational data that are not to be resolved and thus optimizes the energy efficiency of the preparation.

Device and method for preparing data

Growing community of inventors

Bengaluru, India

Swathi Shyam Sunder