Microsoft Technology Licensing, LLC

Steven Fox

Zijian Zheng

Kuldeep Karnawat

Thomas Dale White

Mark B Mydland

Thomas A Taylor

Susan Theresa Dumais

Ying Zhang

Pyungchul Kim

Zhenbin Xu

Takeshi Shimizu

Frederic Behr

Lu Wang

Methods for updating an information retrieval system are disclosed. In one embodiment, search terms affiliated with mappings or associations that represent a connection of relevancy between a query and an asset are pushed as content updates to a client system (e.g., as new updates or utilized to replace older data). The search terms are inserted (e.g., inserted as metadata) into corresponding content (the content associated with the asset). In this manner, content-searching data can be updated (e.g., remotely updated) as frequently as desired, even periodically, or selectively as new manually and/or automatically derived data becomes available. In another embodiment, the update data is already built into the content when it is delivered to a client machine. Other disclosed embodiments pertain to methods for generating a data mining classification model that is a blended representation of associations (e.g., query-asset associations) having different characteristics and/or different originating sources.

Generation of a blended classification model

A search authoring tool for mapping queries to assets for use in an information retrieval system has a query-to-asset mappings database, a search authoring engine, and a search evaluation engine. The query-to-asset mappings database is built from search author input and user mappings. The search authoring engine is adapted to receive operator input and to generate one or more new query-to-asset mappings based on the received operator input. The search evaluation engine is adapted to compare the one or more new query-to-asset mappings to the existing mappings to determine if the one or more new query-to-asset mappings will cause performance degradation of the information retrieval system.

Search authoring metrics and debugging

Systems and methods for measuring and improving search result relevance based on user satisfaction are disclosed. An event log is preferably scanned to determine the start and the end of a session. User behaviors within the session are preferably identified. User satisfaction is preferably estimated based on the user behaviors. User satisfaction is preferably a measure of the user's perception of the extent to which a result correlates to his intent based on his behaviors. User satisfaction is preferably estimated to be one of three satisfaction levels: satisfied, partially-satisfied, and dissatisfied. Symptoms, which are indications of a need for improvement within a search system, are preferably observed based on the user behaviors and the user satisfaction. Diagnostics, which are conditions that prevent a search system from performing optimally, are preferably derived based on the symptoms. A performance report for the search system based, at least in part, on the user satisfaction and the diagnostics may be generated. Such a report may be analyzed to determine methods for improving the relevance of results generated by the search system.

System and method for measuring and improving search result relevance based on user satisfaction

Context-based user feedback is gathered regarding searches performed on a search mechanism. The search mechanism is monitored for user behavior data regarding an interaction of a user with the search mechanism. The response data provided by the search mechanism is also monitored. Context data (describing the search) and user feedback data (the user's feedback on the search&#x2014;either explicit or implicit) are determined. This can be used, for example, to evaluate a search mechanism or to check a relevance model.

Search system using user behavior data

Growing community of inventors

Bothell, WA, United States of America

Steven Fox