Microsoft Technology Licensing, LLC

Rahul Lal

Marcelo Medeiros De Barros

Abinash Sarangi

Hariharan Ragunathan

Xia Song

Dena Natalie Saunders

Marcelo M Debarros

John Michael Guthmann

Nathan Novielli

Ling Lu

Shantanu Sharma

Benjamin David Brubaker

Sarah Jiaxuan Liu

Saksham Singhal

Ankit Kumar

Saulo Santos

Nick Peine

Zhun Liu

Alexander Verge

Abuzer Mirac Ozcan

Hazim Macky

A computing system is disclosed that includes a processor and memory. The memory stores instructions that, when executed by the processor, cause the processor to perform several acts. The acts include receiving, by a generative model, input set forth by a user of a client computing device that is in network communication with the computing system. The acts also include generating, by the generative model, a query based upon the input set forth by the user; providing the query to a search engine. The acts further include receiving, by the generative model and from the search engine, content identified by the search engine based upon the query. The acts additionally include generating, by the generative model, an output based upon a prompt, where the prompt includes the content identified by the search engine based upon the query. The acts also include transmitting the output to the client computing device for presentment to the user.

Informational grounding with respect to a generative model

A 'while away' canvas is described herein. A client computing device detects that a page that comprises search results is displayed on a display of the client computing device, wherein the search results were identified based upon a query received from the client computing device. The client computing device subsequently detects that focus of the user has left the page. Upon detecting that focus of the user has returned to the page, the client computing device updates the page to include the “while away” canvas, which identifies additional search results (based upon the query) that were published after the page that comprises the search results was initially displayed.

Updating a search page upon return of user focus

Systems, methods, and computer-executable instructions for verifying a chat bot. Registration information for the chat bot is received that includes keywords. Queries are submitted to the chat bot and responses to the queries are received. The responses are classified using a classifier. Verification that the responses are classified as approved responses are done. The registration information is stored and the registration of the chat bot is completed based upon the verified responses. A search query that includes a search keyword is received. The search keyword is matched to the keywords associated with the chat bot. Search results that include a link to the chat bot that are based upon the search query are provided.

Chat bot registration with search results integration

Representative embodiments disclose mechanisms to increase readability and/or engagement of search results on a mobile device while minimizing the bandwidth consumed by transferring search results from the search system to the mobile device. A search results page comprises a plurality of containers adapted to hold content of a content type such as text, rich media, hidden content, and so forth. When the search results page is downloaded to the mobile device, only content that is visible through a viewport on the screen on the mobile device is downloaded. The content that is visible can be adjusted to enhance readability and/or engagement based on the type of content displayed such as by adjusting size, spacing, color/highlights, animations, and so forth. Content that is not visible in the viewport is not downloaded until it becomes visible in the viewport or is predicted to become visible in the viewport.

Real time search enhancement using mobile viewport

Systems and methods for responding to a user query are provided. More specifically, the systems and methods provide static search results along with a relevant chat bot user interface for combined display on a browser interface in response to a user query. As such, the systems and methods utilize a conversation layer to communicate with a selected chat bot service. Additionally, the systems and methods may update the static search results and other related content displayed in the browser interface in response to user chat bot inputs and/or chat bot responses provided on the chat bot user interface in the combined display. Accordingly, the systems and methods for responding to a user query provide a more efficient and better search engine when compared to previously utilized search engines that did not provide access to a chat bot interface on the same browser interface as the search results.

Systems and methods for responding to an online user query

Technologies are provided for protecting nonintrusive content of a web page presented on a user device. A web page is received on a user device including instructions to monitor the web page for changes to the web page, and instructions to restore and freeze content of the web page when a modification has been detected. A content filter filters content on the web page. The filtering is detected on the user device, and the web page is restored with the original content of the web page and the content is frozen on the web page, preventing further modification of the web page.

Web page nonintrusive content protection on user device

Aspects of the technology described herein can detect visual regressions in a computer-generated document, such as a web page, caused by programming errors. The technology can be used to detect errors in programs coded in a variety of different languages and used in a variety of applications that generate user interfaces. In one aspect, the technology is used to validate an updated program module prior to replacing a production version of the program module with the updated version. The technology described herein can compare a baseline version of a user interface with a test version of the user interface generated using the updated program module. In an aspect, a visual parity analysis is run to detect a visual regression.

Visual regression analysis

Growing community of inventors

Redmond, WA, United States of America

Rahul Lal