Microsoft Technology Licensing, LLC

AT&T Intellectual Property I, LP

Ovidiu Dan

Vaibhav Girish Parikh

Bernard S Renger

Hisao M Chang

Junlan Feng

Luciano De Andrade Barbosa

Siddhartha Cingh Arora

Maksym Bondarenko

Ryen William White

Paul Valentin Borza

Ryan Curtis Clark

Kumar Srinivasamurthy

Prateek Tiwari

Ambarish Chitnis

Ryan D Clark

Lin Tang

Pavel Dmitriev

Timothy Edgar

Rajanikanth Ageeru

Guilherme Iscaro De Godoy

Ondrej Starosta

Muhammad Saad Sadiq

Christopher Sedar

Michal Hanzlik

A computing system includes a processor; and memory storing instructions that, when executed by the processor, cause the processor to perform several acts. The acts include receiving multiple messages from multiple users in a messaging application that supports group conversations, where the multiple messages are included in a group conversation. The acts also include providing a prompt to a generative model, where the prompt includes the multiple messages. The acts additionally include receiving, from the generative model, an output generated by the generative model based upon the prompt and including the output as a turn in the group conversation.

Computer-implemented multi-user messaging application

Generating an improved/more accurate geolocation database is provided. Given a dataset of reverse DNS hostnames for IP addresses, ground truth information, and a hierarchical geographical database, a machine learning classifier can be trained to extract and disambiguate location information from the reverse DNS hostnames of IP addresses and to apply machine learning algorithms to determine location candidates and to select a most probable candidate for a reverse DNS hostname based on a confidence score. The classifier can be used to generate an accurate geolocation database, or to provide accurate geolocation information as a service.

Geolocation using reverse domain name server information

The act of setting up a user's device to participate in a meeting may be performed automatically, using location information and calendar information. With appropriate permission obtained from the user, the user's calendar and the location of the user's device are monitored. When the user's calendar indicates that the user is scheduled to be in a meeting and the user is in or approaching a conference room (or other type of room) associated with that meeting, the user's desktop, application, and meeting documents may be shared. The user's computer may be automatically connected to devices in the meeting room, and any audio/visual settings appropriate for the user's role in the meeting may be configured automatically. Alternatively, if the user is to participate in the meeting online, the online meeting may be joined automatically.

Automatic equipment configuration for meetings

A system that incorporates teachings of the present disclosure may operate, for example, obtaining a number of blogs including an initial set of annotated blogs and unannotated blogs. The initial set of annotated blogs are annotated as being either relevant to a selected media program or not relevant to the selected media program. A set of features is determined associating the selected media program with the unannotated blogs and a trained classifier is generated based on the set of features. The trained classifier is applied to the blogs to identify a subset of blogs relevant to the selected media program. An analysis is performed on the selected blogs to determine a trend related to the selected media program and a graphical user interface is presented that concurrently presents the selected blogs, the trend, and the selected media program. Other embodiments are disclosed.

Method and apparatus for associating micro-blogs with media programs

Architecture that improves the quality of RevIP databases using search engine query logs and other location information sources and finds IP addresses that share multiple locations (indicative of large Internet gateways). A ground truth dataset is generated with mappings of IP addresses to locations and IP ranges to locations which are known to be correct. Additionally, the architecture can determine which types of queries and SERP page blocks (page sections) are location aware. Location information can be extracted from user queries and the most-frequently-used locations aggregated per IP address. Dominant locations can be aggregated, mapped to existing RevIP database IP address ranges and replaced. The updated RevIP database can be evaluated against the ground truth dataset. RevIP IP address ranges can be split and combined to improve the overall performance of the RevIP database.

Reverse IP databases using data indicative of user location

A system that incorporates teachings of the present disclosure may operate, for example, according to a method for identifying subsets of blogs from a collection of blogs according to a relevance of each subset of blogs to one of a plurality of media programs deliverable to a plurality of subscriber devices, determining for each subset of blogs one or more trends, detecting a subscriber device from the plurality of subscriber devices, selecting a media program from the plurality of media programs, selecting one of the subsets of blogs that is relevant to the media program, and supplying the subscriber device the selected subset of blogs with the one or more trends determined for the select subset of blogs. Other embodiments are disclosed.

Embodiment described herein are generally directed to a toolbar extension of a web browser that grabs a user's search engine query and suggests a refined search query known to yield better search results. The toolbar recognizes the web page the user is on as being associated with a search engine and retrieves the user's search query. The toolbar interacts with a refinement component on a server, and the refinement component determines a refined search query based on confidence scores assigned to data mined from a data center affiliated with different search engine (one related to the toolbar). The refined search query is returned and displayed in a search field of the toolbar, allowing the user to easily run the refined search on the different search engine.

Query refinement in a browser toolbar

Growing community of inventors

Bethlehem, PA, United States of America

Ovidiu Dan