International Business Machines Corporation

Sumeet Surendra Kapoor

Snehal U Pansare

Girish Padmanabhan

Rachana Vishwanathula

Manoj Panda

According to one embodiment, a method, computer system, and computer program product for evaluating a data request is provided. The embodiment may include receiving a request to share data of a user during an interaction between an intelligent virtual assistant (IVA) representing the user and a requesting entity. The request is sent from the requesting entity to the IVA. The embodiment may include calculating an overall data sharing confidence score based on an evaluation of the request. The embodiment may include determining whether the overall data sharing confidence score is above a data sharing threshold value. In response to determining that the overall data sharing confidence score is above the data sharing threshold value, the embodiment may include instructing the IVA to share the data of the user with the requesting entity.

Artificial intelligence enabled data privacy for virtual assistants

A computer-implemented method, according to one embodiment, includes collecting user data associated with a first user's thoughts and/or experience with a first activity, and receiving, from a neural device paired with the first user, cognitive information about the first activity. The method further includes generating, based on the collected user data and the cognitive information, a scene set in a training environment based on the first activity. The generated scene is output to a hologram device for displaying the scene for the first user. A computer program product, according to another embodiment, includes a computer readable storage medium having program instructions embodied therewith. The program instructions are readable and/or executable by a computer to cause the computer to perform the foregoing method.

Using collected user data and cognitive information to generate a scene set in a training environment

Embodiments are disclosed for a method. The method includes determining a context of a data access request for a data virtualization engine. The method also includes determining data sources that are relevant to the data access request by using a governance machine learning model trained to predict the data sources based on the request and the context. Additionally, the method includes determining data governance rules-policies that are relevant to the request, by using the governance machine learning model, further trained to predict the data governance rules-policies based on the data sources and the context. Further, the method includes generating, by using a query machine learning model, a data access command executable by the data virtualization engine and configured to retrieve data from the data sources and apply the data governance rules-policies.

Growing community of inventors

Pune, India

Sumeet Surendra Kapoor