Microsoft Technology Licensing, LLC

Kishor Chamua

Shveta Verma

Amit Dangwal

Saksham Saxena

Sushil Kumar Chordia

Manish Gupta

Puneet Agrawal

Deepak Achuthan Menon

Rajendra Bhimsen Shinde

Anuska Nandy

Biju Venugopal

Tezan Sahu

Karthik Rg

Thuli Nitoshe Chishi

Deepanjali Singh

Akash Shivaji Padmane

Harendra Prasad Baji

Srishti Srivastava

Aditi Gulati

This disclosure describes a query gateway system that provides an efficient and flexible framework for providing context-retained autosuggest queries from an autosuggest query system (e.g., a search engine query experience) to a generative language model system (e.g., an AI chat experience). For instance, the query gateway system establishes a framework to leverage the features and services of the autosuggest query system and automatically provides context-retained queries to the generative language model system using separate user interfaces that do not disrupt user navigation or require manual duplicative user input. Additionally, the query gateway system incorporates additional enhancements, including an AI chat eligibility model and a query reformulation model, to improve the computational efficiency and accuracy of the AI chat system.

Generating narrative query responses utilizing generative language models from search-based autosuggest queries

Methods, computer systems, computer-storage media, and graphical user interfaces are provided for providing an interactive search exploration tool. In embodiments, an interactive search exploration tool is presented via a graphical user interface. The tool may include a primary topic, indicating the search query, that is positioned at a center of the interactive search exploration tool. The tool may also include distance indicators indicating extents of relatedness to the primary topic. The distance indicators can be represented as concentric shapes positioned around the primary topic at varying distances. The tool can also include a related topic(s) positioned around the primary topic. The related topic is positioned in proximity to a distance indicator that corresponds with an extent of relatedness of the related topic to the primary topic. Thereafter, in response to a selection of the related topic, a topic content snippet that provides a representation of the related topic is presented.

Interactive search exploration

A method for multi-intent searching includes surfacing, via a web browser provided through a network, a search engine UI in a first browser tab, where the search engine UI includes a search box for specifying a search query. The method includes, responsive to user input, entering keystrokes into the search box, surfacing an autocomplete menu adjacent to the search box, and populating the autocomplete menu with suggested search queries related to the entered keystrokes. The method also includes surfacing a pop-out icon corresponding to each suggested search query within the autocomplete menu and, responsive to additional user input including a selection of the pop-out icon corresponding to one of the suggested search queries, launching a second browser tab including search results for the suggested search query, where the autocomplete menu with the suggested search queries is maintained within the first browser tab after the launching of the second browser tab.

Surfacing automatically-suggested search query results in separate browser tabs for improved multi-intent searching

Systems and methods are directed to providing multi-level rich autosuggestions for multi-intent search queries. The system receives a query prefix entered in a search box and accesses a database of machine-learning derived intent clusters. Based on the query prefix, a top-ranking machine-learning derived intent cluster is identified, and the search user interface is updated to provide a plurality of first level autosuggestions in an autosuggestion box including a smart suggestion. The smart suggestion is a first level suggestion of the top-ranking machine-learning derived intent cluster. The system receives a selection of the smart suggestion and, in response, replaces the plurality of first level autosuggestions in the autosuggestion box with second level autosuggestions. The second level autosuggestions comprise one or more intent categories that are subsets of the smart suggestion, whereby each intent category comprises a plurality of subcategory suggestions.

Multi-level rich autosuggestions for multi-intent search query

Growing community of inventors

Hyderabad Telangana, India

Kishor Chamua