Facebook
Senior Engineering Manager
Sumo Logic Feb 1, 2015 - Jun 2019
Engineering Manager at Sumo Logic
Twitter May 2013 - Dec 2014
Engineering Manager
Groupon Apr 2011 - May 2013
Member of Technical Staff
Microsoft Jul 2008 - Apr 2011
Applied Researcher
Education:
University of Illinois at Urbana - Champaign 2004 - 2008
Doctorates, Doctor of Philosophy, Computer Science
University of Illinois at Urbana - Champaign 2002 - 2004
Master of Science, Masters, Computer Science
University of Illinois at Urbana - Champaign 1999 - 2002
Bachelors, Bachelor of Science, Computer Science
Skills:
Data Mining Machine Learning Scalability Information Retrieval Data Analysis Personalization Algorithms Distributed Systems Business Intelligence Mapreduce Big Data Hadoop Agile Methodologies Collaborative Filtering Mobile Devices Anomaly Detection
LINGFENG WU - Beijing, CN WENJUN DAI - Beijing, CN XIAO WU - Beijing, CN XIAOLEI LI - Kirkland WA, US VU ANH HA - Kirkland WA, US WEIBIN ZHU - Beiging, CN
Assignee:
MICROSOFT CORPORATION - REDMOND WA
International Classification:
G06F 17/30
US Classification:
707748, 707771, 707777, 707E17089, 707E17061
Abstract:
Systems and methods for assigning a product category and/or classification to user data based on a taxonomy of makes and models is provided. User data is received and converted to plain text. A taxonomy is provided, having a plurality of categories corresponding with product descriptions based on product makes and models. Rules are associated with the categories in the taxonomy and used to generate a category score for categories in the taxonomy. The category scores are used to assign at least one category from the taxonomy to the user data. A product class may also be assigned to the user data based on the assigned product category.
Selecting Advertisements For Presentation With Search Results
Xiaolei Li - Kirkland WA, US Raman Chandrasekar - Seattle WA, US Dou Shen - Redmond WA, US
Assignee:
Microsoft Corporation - Redmond WA
International Classification:
G06Q 30/00
US Classification:
705 1442, 705 1454
Abstract:
This patent application pertains to selecting advertisements for presentation with search results. One example includes receiving a user's search query. This example also includes selecting an advertisement that is relevant for presentation to the user with search results for the search query. The advertisement is selected from a set of advertisements by comparing a semantic context of individual advertisements to a semantic context of the user's search query.
JEREMY TANTRUM - SHORELINE WA, US JUNXIAN WANG - BELLEVUE WA, US XIAOLEI LI - KIRKLAND WA, US
Assignee:
MICROSOFT CORPORATION - REDMOND WA
International Classification:
G06Q 30/00 G06Q 10/00
US Classification:
705 1442, 705 1443
Abstract:
Systems, methods, and computer storage media having computer-executable instructions embodied thereon that utilize relevance judgments to estimate a discounted cumulative gain. In embodiments, a query:ad pair including a search query and at least one advertisement is identified. The at least one advertisement is identified as having not been previously associated with the search query and not as not having associated therewith a relevance judgment. An estimated relevance judgment is calculated and utilized to calculate an estimated discounted cumulative gain for the search query.
Generating Proactive Reminders For Assistant Systems
- Menlo Park CA, US Jivko Dobrev - Kirkland WA, US Honglei Liu - San Mateo CA, US Xiaolei Li - Los Altos CA, US
International Classification:
H04L 67/55 H04L 67/53
Abstract:
In one embodiment, a method includes receiving a user request from a first user to create a reminder at a client system, wherein the user request does not specify an activation-condition for the reminder, determining proactive activation-conditions for the reminder, determining whether the proactive activation-conditions for the reminder are satisfied based on user context associated with the first user, and presenting the reminder to the first user at the client system responsive to determining the proactive activation-conditions are satisfied.
Proactive In-Call Content Recommendations For Assistant Systems
- Menlo Park CA, US Xiaolei Li - Los Altos CA, US Yuan Chang - Sunnyvale CA, US Ting Chen Leo Hsu - San Jose CA, US
International Classification:
H04N 7/14 H04L 29/06 H04N 7/15 G06F 16/9536
Abstract:
In one embodiment, a method includes establishing a video call between a plurality of client systems, sending, to a first client system of the plurality of client systems while maintaining the video call between the plurality of client systems, instructions for presenting a first content recommendation comprising one or more selected content items, wherein the first content recommendation comprises a prompt to share the selected content items with one or more second client systems of the plurality of client systems, receiving, from the first client system responsive to the prompt, a request to share the selected content items, and sending, to the one or more second client systems responsive to receiving the request and while maintaining the video call between the plurality of client systems, instructions for presenting the selected content items within the video call.
- Chicago IL, US Amit Aggarwal - Sunnyvale CA, US Xiaolei Li - Sunnyvale CA, US David Thacker - Burlingame CA, US Kevin Chang - Mountain View CA, US
International Classification:
G06Q 30/02
Abstract:
In a promotion offering system, a promotion offering may be presented to a consumer on more than one occasion. The previous presentation of the promotion to the consumer may affect a subsequent presentation of the same promotion to the same consumer. The present invention provides an apparatus and method for analyzing the effect a previous presentation of a promotion may have on a consumer when the promotion is presented to the consumer at a subsequent time.
Proactive In-Call Content Recommendations For Assistant Systems
- Menlo Park CA, US Xiaolei Li - Los Altos CA, US Yuan Chang - Menlo Park CA, US Ting Chen Leo Hsu - Menlo Park CA, US
International Classification:
H04N 7/14 H04N 7/15 H04L 29/06 G06F 16/9536
Abstract:
In one embodiment, a method includes establishing a video call between multiple client systems and determining user identifiers of users associated with the video call. Whether to provide content recommendations during the video call may then be determined based on a current context of that video call, and one or more content items to recommend may be selected based on the determined user identifiers. Finally, in response to determining to provide content recommendations during the video call, a first content recommendation with the selected content items may be sent to one or more of the client systems while maintaining the video call between those client systems.
Method, Apparatus, And Computer Program Product For Suppressing Content From Ranked Positioning In Electronic Correspondence Based On Rules-Based Scoring
Provided herein are systems, methods and computer readable media for determining whether to suppress presentation of a promotion from a promotion program in an electronic correspondence to a consumer. An example system may performing operations comprising receiving a set of promotions selected for presentation to the consumer in the electronic correspondence, each promotion respectively associated with a promotion score representing an estimated acceptance of the associated promotion by the consumer, determining, using a rules-based filter comprising a set of rules, whether to modify the promotion score, including geofencing data and the consumer's previous promotion purchasing history, in an instance in which the promotion score is modified, determining whether to suppress presentation of the promotion in the electronic correspondence based at least in part on the modified promotion score.