Microsoft Technology Licensing, LLC

Other

Aidan C Crook

Peter Bailey

Nick Craswell

William Ramsey

Ohil Krishnamurthy Manyam

Ahmed Hassan Awadallah

Imed Zitouni

Sarthak D Shah

Nikhil Dandekar

Filip Andrzej Radlinski

Daniel T Schwartz

Avneesh Sud

Sarvesh Nagpal

Sebastian De La Chica

Justin Ormont

Toby H Walker

Daniel Robert Schwartz

Kyle Mark Williams

Xiaoyuan Cui

Yunling Wang

Likhita Krishnamurthy

Bradley Wethington

Systems and methods of automated machine learning for modeling a data set according to a modeling intent are presented. A modeling service receives a data set from a submitting party as well as a set of constraints. A pipeline generator generates a set of pipelines according to a modeling intent of a data set and in view of the set of constraints. A machine learned trained judge conducts an analysis of the pipelines to identify an optimal pipeline to train. Optimal results are generated according to the optimal pipeline and the optimal results are provided to the submitting party in response to receiving the data set and constraints.

Machine learning for automated model generation with constraints

Systems, methods, and computer-readable storage media are provided for capturing a state of a user interface. A state of the user interface presented by an application is identified, the user interface comprising a plurality of user interface elements. An indication of a modification to the user interface or an indication of user activity is received, where the indication of user activity is associated with one of the plurality of user interface elements. The state of the user interface is modified based on at least one of the indication of a modification to the user interface or user activity.

Capturing user interactions

Examples of the present disclosure describe systems and methods of identifying good and bad abandonment using gesture movement. In aspects, user feedback signals may be received by a client device in response to the viewing and/or navigation of query results. The feedback signals may be provided to a framework for determining and/or analyzing query abandonment. The framework may identify gesture data in the feedback signals and extract feature data from the gesture data. The feature data may be provided to a metrics component to determine metrics and/or satisfaction values for the feature data. The metrics and/or feature data may be used to train a predictive model to identify good abandonment in query results.

Identifying Abandonment Using Gesture Movement

Simplified collaborative searching is provided by pattern recognition such as facial recognition, motion recognition, and the like to provide handsfree functionality. Users join a collaborative search by placing themselves within the field of view of a camera communicationally coupled to a computing device that performs facial recognition and identifies the users, thereby adding them to the collaboration. Users also join by performing simple movements with a portable computing device, such as the ubiquitous mobile phone. A collaboration component tracks the users in the collaboration and identifies them to a search engine, thereby enabling the search engine to perform a collaborative search. The collaboration component also disseminates the collaborative recommendations, either automatically or based upon explicit requests triggered by pattern recognition, including motion recognition and touch recognition. The collaboration component can utilize heuristics to identify individual collaborative sessions, or can utilize existing collaborative infrastructure.

Simplified collaborative searching through pattern recognition

Methods are provided for re-ranking documents based on user-specific features. Search results are received from a non-contextual ranking system such that the search results are not specific toward a particular user, such as the user who submitted the search query. Contextual signals are received and provide user-specific features that are used to re-rank documents so that the most important and relevant documents are listed at the top of the list of search results. Each of the user-specific features are evaluated and compared to determine a new position of each document. A set of contextual search results is then generated based on the new positions.

Ranking contextual signals for search personalization

Methods and computer-readable media are provided for improving the efficiency of the interleaving process. Once it is determined that a search query is to be used in an interleaving experiment, a primary ranking system and a secondary ranking system are analyzed to determine whether their respective search results for that search query would be identical. If the search results would be identical, the search query is routed only to the primary ranking system and not the secondary ranking system. If, however, it is determined that the search results would not be identical, both the primary ranking system and the secondary ranking system receive the search query for processing.

Efficient use of computational resources for interleaving

Growing community of inventors

Los Altos, CA, United States of America

Aidan C Crook