Microsoft Technology Licensing, LLC

Bernt Ivar Olsen

Jon Meling

Kristian Elsebø

Amund Kronen Johansen

Tali Roth

Scott M Stiles

Nithya Ramkumar

Knut Kristian Johansen

Selva Nalliah

Examples of the present disclosure describe systems and methods for automatically assisting conversations using a graph database. In order to minimize misunderstanding of words and phrases used by participants during a conversation, phrases from the conversation may be received by conversation assistance application as the conversation takes place. Entities may be extracted from the phrase based on natural language recognition according to a domain context of the participant being assisted. One or more tags may be looked up from a graph database, and may be provided to the participant as a list of hashtags related to the conversation. Links to documents may be extracted based on the tags for the participant for viewing during the conversation.

Automatically assisting conversations using graph database

Examples of the present disclosure describe systems and methods relating to hierarchical contextual search suggestions. In an example, search suggestions may be provided to a user searching for content of a content management platform. In some examples, the content management platform may manage hierarchical content, such that search suggestions provided to the user for a search query may be associated with content at a level of the hierarchical content accessed by the user. If there is not a sufficient number of search suggestions to provide to the user at the current level of the hierarchy, additional and/or alternative search suggestions may be generated for the user based on content from a different level of the hierarchy. As a result, the user may continue to receive relevant search suggestions, while reducing the amount of computing overhead and analysis used to generate such search suggestions.

Hierarchical contextual search suggestions

Relevance based dynamic navigation is provided. A communication application searches communications to identify hashtags associated with the communications. A relevance score is computed for each hashtag based on a relevance criteria associated with the hashtags. The hashtags are ranked based on the relevance score. Next, the ranked hashtags are presented in a navigation user interface.

Providing relevance based dynamic hashtag navigation

Growing community of inventors

Tromso, Norway

Bernt Ivar Olsen