Microsoft Technology Licensing, LLC

Other

Jeremy Grubaugh

Jon Meling

Ashok Kuppusamy

Berit Herstad

Roberta Cannerozzi

Andreas Eide

Adam D Troy

Reid Maker

Maya Angele Pelichet

Roman Werpachowski

Alexander Primo Lopez

Aaron John Cronin

Livani Pillay

Wei-Han Chang

Daniel Duarte

Graham Kent

Yaw Oduro Amoateng

Åsmund Grammeltvedt

David Dupree Harris

Ola Natvig

The disclosed technology is generally directed to a personalized feed. In one example of the technology, selected key-value pairs from a profile associated with a user are provided. Based on a prompt that includes natural-language text instructions, the selected key-value pairs, and ranked content, a large language model is used to generate: pill prompts associated with the ranked content, such that the pill prompts are information requests that are unique and personalized to have particular relevance to the user based on selected key-value pairs, and a response to each pill prompt such that the response includes content corresponding to the requested information. A content feed is displayed to the user, including displaying selectable pills to the user as part of the displayed content feed such that each selectable pill includes a corresponding pill prompt. The response to the pill prompt that corresponds to the selection is displayed to the user.

User interface including personalized feed with dynamically generated prompts

Techniques of electronic message generation using organizational data are disclosed herein. One example technique includes recognizing a contact a user previously communicated with in an input to an address field of a draft email in the email client. The technique can then include determining whether the input also contains a preset keyword or key phrase indicating an intention of the user to send the draft email to a related entity of the contact. In response to determining that the input also contains a preset keyword or key phrase, the technique includes querying a relationship map corresponding to the contact for an identity and email address of the related entity of the contact and surface the identity and email address in the email client as a suggested destination address for selection by the user.

Message generation using organizational data

A method comprising: accessing a record of past emails or IM messages between a first user and a plurality of other users; from amongst a set of entities (e.g. other users, user groups or folders), identifying a subset as preferred entities of the first user, wherein at least some of the preferred entities are identified automatically based on at least a frequency of interaction between the first user and each of the entities; independently of receiving any search queries, causing a graphical user interface to display a list of the preferred entities; and based on the first user selecting one of the entities from the list, causing the graphical user interface to display to the first user a filtered-down list of emails and IM messages, being some or all of the emails or IM messages communicated between the first user and the selected entity.

Filtering communications

Growing community of inventors

Redmond, WA, United States of America

Jeremy Grubaugh