International Business Machines Corporation

Stephanie Huston

Corville O Allen

Laura Janet Rodriguez

Techniques for content augmentation and assist are provided. A textual conversation between a first user and a plurality of recipients is analyzed to determine a first intent of the first user. A set of relationships is determined between the first user and the plurality of recipients, and a set of historical intents corresponding to each of the plurality of recipients is evaluated to identify similar intents to the first intent. A plurality of predefined messages is identified based on one or more similar intents that overlap between two or more of the plurality of recipients. A first predefined message is selected, from the plurality of predefined messages, based on the first intent and the determined set of relationships, and suggested content is provided based on the first predefined message.

Context-aware dynamic content assist

In automatically modifying message signatures, a system extract message content from the message text from a sender to a recipient. Using at least the message content, the system determines: a relationship context capturing a nature of the relationship between the sender and the recipient, a temporal context capturing temporal features of the message content, a historical context capturing a nature of electronic interactions between the sender and the recipient over time, and a tone category capturing a primary tone and strength of the primary tone of the message content. The system selects a signature template associated with contextual data that includes the relationship, temporal, and historical contexts and the tone category. The signature template includes a set of sections where a signature is modified by inserting section values associated with the contextual data into the set of sections. The modified signature is inserted into the message text.

Growing community of inventors

Durham, NC, United States of America

Stephanie Huston