Microsoft Technology Licensing, LLC

Scott Joseph Counts

Jordan L K Schwartz

Shelly D Farnham

Julia Schwarz

Asta Jane Roseway

Meredith June Morris

Justin Brooks Cranshaw

Curtis N Von Veh

Roberta Rene Moeur

Anthony Lee Carbary

Stevie Nicole Chancellor

Eric J Horvitz

Lili Cheng

John Charles Krumm

Ryen William White

William L Portnoy

Elad Yom-Tov

Andrew W Jacobs

Peter Bailey

Michael Ching

Steve Glenner

Nikhil Dandekar

Chad Carson

Marc A Smith

Shubha Umesh Nabar

Reid Andersen

Ho John Lee

Sujay Kumar Jauhar

Chirag Deepakkumar Shah

Aaron C Hoff

Paul Johns

Longqi Yang

Mengting Wan

Paul Alexander Dow

Hyun-Ju Seo

Sathish Kumar Manivannan

Shuang Guo

Siddharth Suri

Jennifer Lynay Neville

Georg Ludwig Wilhelm Buscher

Tara Lynn Safavi

Xiaochuan Ni

Munmun De Choudhury

Aditya Pal

Various embodiments discussed herein relate to prompting a model, such as a Large Language Model (LLM), to ingest natural language clustering instructions and generate corresponding natural language clustering information, such as a cluster description and/or a cluster label without the need to generate any numeric text embeddings.

Dataset clustering via language model prompts

A user interface (UI) for visualizing search data provides techniques for grouping and organizing aggregate data that shows the categories of topics included in search queries from a large number of individual users. Raw search queries are categorized into one of a number of topical categories. The search queries are assigned to a geographic location based on geolocations of computing devices generating the search queries. The UI presents a map that shows the number of search queries per topical category for each geographic location displayed in the current UI view. As a result of this UI design, a user can easily understand the interaction between geographic location and frequency of search query topics. Trends in the geographic distribution of searches and in the categories of topics searched are also easily understood from this UI design by changing the time range of the search queries displayed.

User interface for visualizing search data

Described herein are various technologies pertaining to presenting search results to a user, wherein the search results are messages generated by way of social networking applications. An interactive graphical object is presented together with retrieved messages, and messages are filtered responsive to interactions with the interactive graphical object. Additionally, a graphical object that is indicative of credibility of a message is presented together with the message.

Interactive search results page

The subject disclosure is directed towards monitoring user behavior on a computerized device for any deviation from normal or acceptable behavior that is likely to affect the user's mental state. A prediction model corresponding to features of one or more mental states may be compared with features based upon current user behavior. If the user's current behavior presents a mental state indicative of an uncharacteristic deviation from the normal or acceptable behavior, descriptive data associated with that mental state may be presented to the user in addition to a trusted individual, such as a health care professional.

User behavior monitoring on a computerized device

The author ranking technique described herein is a technique to rank authors in social media systems along various dimensions, using a variety of statistical methods for utilizing those dimensions. More particularly, the technique ranks authors in social media systems through a combination of statistical techniques that leverage usage metrics, and social and topical graph characteristics. In various exemplary embodiments, the technique can rank author authority by the following: 1) temporal analysis of link sharing in which authority is computed based on a user's propensity to provide early links to web pages that subsequently become popular; 2) topical authority based on the author's links and content updates in specific topic areas; and 3) popularity and influence based on nodal properties of authors.

Ranking authors in social media systems

A unique system and method that facilitates group-based mobile communication around external feed content is provided. The system and method involve adding external feed content to content generated within a group. Both types of content can be viewed on the mobile devices of the group. Updates to the feed content can be obtained and communicated to the group. When multiple feeds are subscribed to by a group, one or more group members can display such feed content in a selective manner. For example, splinter groups can be formed off of the original group for members who wish to receive a subset of feeds (feed content) to assist them in focusing on a topic of interest. Group members can also employ display filters to restrict feed content displayed on their mobile devices. Users can also search for available feeds and form new groups around such content or join an existing group.

Implicit group formation around feed content for mobile devices

As described herein, mobile device games may be constructed via a website from customizable atomic rule-based units, and also supports the reuse and remixing of game components by a game creator, members of an online community, or by any other user. Once composed, the game can be played via player mobile devices, which send content to a server or a peer device that hosts the game rule statements, and can trigger distribution of new content, rules, or other information.

Game builder for mobile device-based games

A system and method for generating a highlight view of electronic interactions, such as, emails, instant messages, audio messages and/or video messages is provided. The highlight view can facilitate a user's understanding of the electronic interactions. The electronic interactions can comprise emails associated with conversation threads of a discussion list posted and/or received by a plurality of users. The highlight view system can include, for a given period of time, a list of participants in the discussion list, a list of conversation threads and/or a linear progression of one or more of the conversation threads. The linear progression of one or more conversation threads can include signal word(s), such as, 'stated, 'asked', &#x201c;responded', &#x201c;wrapped up&#x201d;, &#x201c;disagreed&#x201d;, &#x201c;agreed&#x201d; etc. that facilitate a user's comprehension of the individual e-mails which form the conversation thread. An electronic interactions highlight system can include an input component that receives electronic interactions (e.g., emails associated with conversation thread(s) of a discussion list) and an analysis component that analyzes the electronic interactions and automatically generates a highlight view of the electronic interactions.

Automatically generated highlight view of electronic interactions

A system that facilitates computation of a time-dependent variability value is described herein. The system includes a receiver component that receives a plurality of items, wherein each item has a timestamp corresponding thereto. The system further includes a value generator component that outputs a time-dependent variability value for an item in the plurality of items, wherein the time-dependent variability value is indicative of a recent frequency of use of the item in comparison to a frequency of use of the item over a defined period of time.

Computing a time-dependent variability value

A rules-based physical-virtual world game builder architecture. Mobile device games can be constructed via a website from customizable atomic rule-based units, and also supports the reuse and remixing of game components by the game creator, members of an online community, or by any other user. Once composed, the game can be played via player mobile devices, which send content to a server or peer device that hosts the game rule statements, and can trigger distribution of new content, rules, or other information. The architecture can comprise an interface component for providing access, a build component for constructing a rule/rule unit for execution during game play, and an execution component for executing the rule/rule units based on data received during game play. Game creation and play can occur via any number of different client types, on any number of clients, and can be via client/server and/or peer-to-peer architectures.

The subject disclosure pertains to systems and methods for determining locations of mobile devices. In particular, a set of regions is defined based upon the relative strength of signals received from one or more base stations within the region. Each region has associated location information (e.g., latitude and longitude). The location of a mobile device can be determined by analyzing the strength of received signals, identifying base stations and generating an ordered list of base stations based upon signal strength. The ordered list can be compared to the set of regions to determine the region in which the mobile device is located. The location information for the retrieved region can be used to estimate the location of the mobile device.

Determining physical location based upon received signals

Growing community of inventors

Seattle, WA, United States of America

Scott Joseph Counts