Xianshi Wei

Title: Xianshi Wei and Machine-Learning-Based Search Suggestions.

Introduction

Xianshi Wei is an inventor associated with Bayside, New York, and Optum, Inc. His patent work includes a machine-learning approach to personalizing and ranking typeahead search suggestions using historical search activity and user click feedback.

Latest Patents

The provided information identifies one patent associated with Wei: “Machine learning techniques for predicting and ranking typeahead query suggestion keywords based on user click feedback.” The invention describes generating feature vectors for candidate keywords and personalized feature vectors based on a user’s search-session data. It then predicts the likelihood that the user will select each keyword, ranks the suggestions according to those predictions, and presents typeahead keywords based on the resulting rankings. Wei is credited with 1 patent in the supplied data.

Career Highlights

Wei’s listed work connects machine learning with search technology, focusing on making query suggestions more relevant to individual users. The patent describes using historical search data and click feedback to inform the selection and ordering of suggested keywords.

Collaborations

The supplied information names Chenwei Liu and Ayush Tomar as Wei’s coworkers. Their inclusion indicates a professional connection, but the provided details do not specify their roles in the patent or the extent of their collaboration.

Conclusion

Xianshi Wei’s listed patent presents a personalized, data-driven method for ranking typeahead suggestions, reflecting an application of machine learning to improve search experiences.