Microsoft Technology Licensing, LLC

John P Moore

Chencheng Wu

Hardik Bati

Haifeng Zhao

Jiashuo Wang

Haowen Cao

Liang Zhang

Yang Chen

Daniel Francis

Xiang Yu

Ankit Gupta

Souvik Ghosh

Jing Wang

Thomas Michael Lee

Haiyan Luo

Christos Koufogiannakis

Xiaojing Chen

Swetha Nagabhushan Karthik

Steven Kaplan

Wenjun Wu

Aparna Krishnan

Anand Kishore

Henry Heyburn Pistell

Keyi Yu

Mira Thambireddy

Techniques for a flexible data security and machine learning system for merging third-party data are provided. In one technique, the system receives a data set from a third-party entity and receives selection data that indicates that the third-party entity selected a set of data security policies that includes an encryption option and a data mixing option from among multiple data mixing options. In response to receiving the selection data, the system stores data that associates the set of data security policies with the data set, encrypts the data set according to the encryption option, and persistently stores the encrypted data set. Later, the system decrypts the encrypted data set in volatile memory, generates, based on the data mixing option, training data based on the decrypted version of the data set, trains a machine-learned model based on the training data, and stores the machine-learned model in association with the data set.

Flexible data security and machine learning system for merging third-party data

Entity resolution techniques for matching entity records from different data sources are provided. In one technique, an entity record from a source database is identified along with multiple data items included therein. Each data item corresponds to an attribute of multiple source attributes. For one of the data items that corresponds to a first source attribute, multiple target attributes are identified. A first query is generated that includes the data items and associates the data item with each of the multiple target attributes. A second query that is different than the first query is also generated. Two searches are performed of a target database: one based on the first query and the other based on the second query. A scoring model generates multiple scores, one for each search result. It is determined whether the entity record matches an entity record in the target database based on the set of scores.

Entity resolution techniques for matching entity records from different data sources

Techniques are provided for server-to-server interaction for content item selection. A system receives a request for one or more content items from a client device. In response to receiving the request, the system generates multiple content requests. Each content request is sent to a different content provider of multiple content providers. At least one of the content requests is transmitted over a network to a content provider that is remote relative to the system. The system receives multiple responses, each of which is from a different content provider of the multiple content providers. Each response identifies a different content item. The system makes a determination that at least one content item is associated with a particular web domain. The system selects, based on the determination, a particular content item of the plurality of content items and causes the particular content item to be transmitted to the client device.

Server to server interaction in content item selection events

Techniques for managing multiple computing systems are provided. A system comprises a content delivery system (CDS) and an entity identification system (EIS). The CDS causes a content item that is associated with a content delivery campaign to be delivered over a computer network to a computing device of a user. The CDS detects that the user performed an action relative to the content item and, in response, creates an action record that indicates a particular entity associated with the user and that indicates an account that is associated with the content item and causes the action record to be made available to the EIS. The EIS, based on the account indicated in the action record, identifies a particular account from among multiple accounts indicated in an account database and searches the particular account for an entity (if any) that matches the particular entity.

Signal generation for one computer system based on online activities of entities with respect to another computer system

Techniques for responding to content requests that originate from remote computing devices are provided. In one technique, a content request that includes a viewer identifier of a user that requested web content and a contextual entity identifier of an entity that is referenced in the web content is received. In response to receiving the content request, based on the viewer identifier, first profile data about a viewer associated with the viewer identifier is retrieved. Also, based on the contextual entity identifier, second profile data about the entity is retrieved. Based on the first profile data and the second profile data, a content delivery campaign is identified. Particular content to deliver is determined based on the content delivery campaign. The particular content is sent to a computing device that initiated the content request.

Contextual entity analysis for electronic content delivery across a computer network

Growing community of inventors

San Francisco, CA, United States of America

John P Moore