Sap Se

Prateek Bajaj

Prajesh K

Sumaiya P K

Somanathan Ramanathan

Interactions between organizations occur through multiple channels such as textual communication (e.g., emails) and voice communication (e.g., telephone conversations). All such interaction data collated together constitutes a large amount of unstructured data. A framework is provided for collating the unstructured interaction data and creating a machine-legible structure from it using machine learning models. The machine learning models may generate a variety of generic as well as business-context-relevant insights, with the usage and application of custom-built machine learning model pipelines that generate an overall business insight record that can then be published back into a customer relationship management (CRM) system. Multiple data types are used for the interactions. For example, a voice call may be recorded and stored as an audio file, whereas an email may be stored as a text file. Multiple such formats may also be used to store interaction data.

Machine learning for multi-channel interaction workflows

Example methods and systems are directed to determining topics of data objects. A machine learning model may be trained and used to determine topics of data objects. After topics for data objects are determined by the trained machine learning model, data objects having similar topics can be automatically related. A semantic web approach relies upon the metadata of the data objects being generated along with the metadata of the insights being generated (such as topic groups). Such a semantic association between various objects (using metadata) forms a metadata driven network of analytical representation of business entities/objects. A data-stream comprising the semantic web, indicating the relationships between the metadata of the data objects and the metadata for the topics, may be pushed continuously into a central tool or repository to allow users to generate seamless analytical dashboards with minimal efforts.

Intelligent entity relation detection

Technologies are provided for iterative machine learning and relearning. A training dataset can be divided into a plurality of training data blocks which can be used to generate separate machine learning models. The accuracy of the machine learning models can be assessed using a test dataset. Training data blocks which result in models with good accuracy can be combined into larger training data blocks which can then be used to generate new machine learning models. The process of combining training data blocks can be repeated as long as the resulting machine learning model has acceptable accuracy. However, if a model for a combined training data block has a poorer accuracy than the machine learning models for its component training data blocks, then the combined training data block and its machine learning model can be forgotten and its component training data blocks (and their associated machine learning models) can be relearned.

Iterative machine learning and relearning

A method of simplifying automated testing within an integrated development environment (IDE) for a user having a visual impairment is disclosed. An access mechanism is provided for selecting automated testing scripts from within the IDE by responding to audio communications describing one or more access commands. An execution mechanism is provided to the user for executing one or more of the selected automated testing scripts. A result mechanism is provided to the user, the result mechanism including a summary of a result of the executing of the one or more selected testing scripts, the summary based on an analysis of console output of the IDE, the analysis including performing feature extraction and natural language processing on the console output to generate a natural language description of the result. An action mechanism is provided to perform an additional action that is selected based on the type of the result.

Growing community of inventors

New Delhi, India

Prateek Bajaj