Kyndryl, Inc.

International Business Machines Corporation

Aditya M Burli

Saravanan Devendran

Dennis Anthony Perpetua, Jr

Pritpal Arora

Subramanian Krishnan

Thangadurai Muthusamy

Nagarjuna Surabathina

Ramya Rajendiran

Nicola Jane Ankcorn McKenna

User input handling by a virtual assistant includes receiving a sequence of natural language statements provided by a user to a virtual assistant, applying a cognitive model to the sequence of statements and determining whether the sequence of statements provides a complete problem description, by the user, to which the virtual assistant is to respond in assisting the user address a problem that the user experiences, prompting the user to provide an additional one or more statements to complete the problem description, based on completing the problem description, formulating and providing a response to the user based on a determined intent of the complete problem description, and monitoring input by the user based on providing the response, the input informing feedback for further training of the cognitive model to identify whether statement sequences provide complete or incomplete problem descriptions.

Incomplete problem description determination for virtual assistant user input handling

An approach for securely accessing self-sovereign data via a bot-chain ledger may be provided. A bot may request access to a piece distributed data at a bot-chain client. A bot registry service may validate the requesting bot is registered with the bot-ledgering client. The bot-ledgering client may generate a token for the requesting bot and provide the identity of a data bot with permission to access the piece of distributed data. A data bot may request to read the piece of distributed data at the bot-ledgering client. The bot-ledgering client may verify the data bot is registered with the bot-chain. The bot-ledgering client may generate an access token and send it to the data bot.

Self-sovereign data access via bot-chain

Provided is a method, computer program product, and virtual conferencing system for automatically positioning a video thumbnail within an area on a display during a virtual conferencing session. A processor may receive a data stream of a virtual conferencing session. The data stream includes visual data associated with a presentation. The processor may analyze the visual data to identify a blank space area in the visual data. The processor may display the visual data to one or more users of the virtual conferencing session. The processor may display a video thumbnail of a presenter in the blank space area.

Automated video positioning during virtual conferencing

A generic connector module of an integration-platform system reconciles the system's application-independent canonical API with each application-specific API used by an endpoint application. The system generates a software library of application-specific configuration files each capable of enabling the connector to translate commands between one application-specific API format and the canonical-API format. Applications may be added to the system, removed, or updated without revising the connector. When the connector receives an application-specific request from an application or a canonical request from the integration platform, the connector selects an application-specific configuration file that lets the connector translate the received request into its complementary API format. The connector then forwards the translated request to its intended recipient. A converse process occurs when receiving an application-specific or canonical response to the translated request. Translations can be performed dynamically, in real time, without requiring a distinct connector module dedicated to each application.

Growing community of inventors

Bengaluru, India

Aditya M Burli