Tata Consultancy Services Limited

Sumiran Naman

Ashim Roy

Nikhil Girish Patwardhan

Anantha Desik Puranam Hosudurg

Ashish Diwan

Pranit Reke

Prachi Shastri

Venkata Bala Tripura Sundari Nallamreddy

As discussed earlier, labelling techniques that are available for labelling of unlabelled tabular data use some semi supervised models for identification purposes. However, they require sample labeled data for training purposes. Further, the same labelling model/technique cannot be used for all data types. Present disclosure provides method and system for identifying labels of unlabeled column data. The system uses a hybrid approach i.e., it uses language models, regular expressions and known dictionaries for labelling of unlabelled tabular data. For performing labelling, system first classifies received unlabelled tabular data into one or more data buckets. The system then uses appropriate techniques, based on data types, for identification of labels of unlabeled data present in data buckets. Thereafter, system uses feedback mechanism which will impart maturity to system over time. Finally, once system is matured, system can identify labels for all types of data.

Method and system for identifying labels of unlabelled column data

Existing systems provide data selection for one differential technique considering an analytical problem or synthetic data but not an arrangement for selection of one or more techniques together. The embodiments herein provide a method and system for differential privacy enabled service with hybrid rule management and similarity metrics to select data. The system generates a query table called universal data from the associates tables and databases. The system further based on query on the universal table of single columns or selected columns with different parameters using different privacy rules generates differential private data stored in temp tables/views. The system retrieves queried data of different techniques and parameters interactively viewing the privacy and similarity of each data types of retrieved data with universal data using different metrics like bar charts, Histograms, average, std. and correlation to select right different privacy data of the universal data based on Privacy and similarity tolerances.

System and method for enabling differential privacy techniques

Growing community of inventors

Pune, India

Sumiran Naman