Microsoft Technology Licensing, LLC

Microsoft Corporation

Dmitriy Meyerzon

Nikita Voronkov

Victor Poznanski

Vladimir Tankovich

Yauhen Shnitko

Aninda Ray

John Michael Winn

Kyle G Peltonen

David Mowatt

John Guiver

Hugo Zaragoza

Matteo Venanzi

Ryan Antoine Nakhoul

Vladimir V Gvozdev

Alexander Armin Spengler

Ivan Korostelev

Mihai Petriuc

Jessica Anne Alspaugh

Jeffrey L Wight

Dirk H Groeneveld

Hang Li

Kenji C Obata

Nicolai Bodd

Pavel Myshkov

Sankrant Sanu

David M Cohen

Yordan Kirilov Zaykov

Elena Pochernina

Welly Sugiarto Lee

Ashok Kuppusamy

Omar Zia Khan

Michael James Taylor

Charles Reeves Little, Ii

Christopher Russell Kehler

Hui Li

David J Lee

Oleg Melnychuk

Boxin Li

Stephen Robertson

Joshua Stickler

Zheng Chen

Jun Yan

Vidya Srinivasan

Srikanth Shoroff

Lei Ji

F Soner Terek

Samuel Alexander Webster

Ravi Kumar Bikkula

Andrew Haon

Michael B Taylor

Junyi Chai

Zhongyuan Wang

Chadd Creighton Merrigan

Nicholas Anthony Buelich, Ii

Mircea Neagovici-Negoescu

Knut Kristian Johansen

Sebastian Blohm

Denise Michele Trabona

Jun Xu

Jan-Ove Almli Karlberg

Åge Andre Kvalnes

Yunbo Cao

Helge Grenager Solheim

Viktoriya Taranov

Ruihua Song

Jason Glenn Silvis

Jeremy Mazner

John Lincoln DeMaris

Nathaniel Terrell Clinton

Johannes Gehrke

Puneet Narula

Pedro Dantas DeRose

Fredrik Holm

Naresh Kannan

Scott Norin

Adri Verlaan

Uppinakuduru Raghavendra Udupa

Manfred Nysted Berry

Thomas Minka

Kjetil Krogvig Bergstrand

Age Kvalnes

Manish Garg

Guangping Gao

Anthony Arnold Wieser

Andrei-Alin Corodescu

Kristen Kamath

Chris J C Burges

Janet Longhurst

Zhihua Dong

Simon Thoresen Hult

Xin Zou

Karthik Tangirala

Ping Jiang

Dennis Joel David Myren

Marius Bunescu

Melissa Torres

Thuy Thanh Duong

Sebastian Johannes Blohm

Chia-Jiun Tan

In various examples there is a computer-implemented method of database construction. The method comprises storing a knowledge graph comprising nodes connected by edges, each node representing a topic. Accessing a topic type hierarchy comprising a plurality of types of topics, the topic type hierarchy having been computed from a corpus of text documents. One or more text documents are accessed and the method involves labelling a plurality of the nodes with one or more labels, each label denoting a topic type from the topic type hierarchy, by, using a deep language model; or for an individual one of the nodes representing a given topic, searching the accessed text documents for matches to at least one template, the template being a sequence of words and containing the given topic and a placeholder for a topic type; and storing the knowledge graph comprising the plurality of labelled nodes.

Knowledge base with type discovery

Examples of the present disclosure describe systems and methods for cross-provider topic conflation. In aspects, a request relating to one or more topics may be received by a content surfacing platform. One or more data sources of multiple content providers may be searched for documents relating to the topic(s). Document content (e.g., document metadata and sentences, phrases, and other word content within the document) relating to the topic(s) may be extracted from the documents of the various content providers. The document content may be classified and/or separated into subparts. The subparts may be clustered and/or conflated by topic, thereby removing duplicated data while preserving the unique information in each subpart. The conflated topics may be stored in a single knowledge base, such as an enterprise knowledge graph, and/or presented in response to the request.

Cross-provider topic conflation

Examples described herein generally relate to a computer system including a knowledge graph storing a plurality of entities. A mining of a set of enterprise source documents within an enterprise intranet is performed, by a user-based mining system, to determine a plurality of entity names. An entity record is generated within a knowledge graph for a mined entity name from the linked entity names based on an entity schema and ones of the set of enterprise source documents associated with the mined entity name. The entity record includes attributes aggregated from the ones of the set of enterprise source documents associated with the mined entity name.

Enterprise knowledge graphs using user-based mining

Examples described herein generally relate to a computer system including a knowledge graph storing a plurality of entities. A mining of a set of enterprise source documents within an enterprise intranet is performed, by an enterprise named entity recognition (ENER) model, to determine a plurality of entity names. An entity record is generated within a knowledge graph for a mined entity name from the linked entity names based on an entity schema and ones of the set of enterprise source documents associated with the mined entity name. The entity record includes attributes aggregated from the ones of the set of enterprise source documents associated with the mined entity name.

Enterprise knowledge graphs using enterprise named entity recognition

Techniques for establishing a network connection with a client device and responding to composite requests from the client device. For a composite request identifying a first action associated with a first data plugin component and a second action associated with a different second data plugin component, the first action is performed by executing a first portion of the data plugin component and transmitting corresponding response data in a first transmission to the client device via the network connection, and the second action is performed by executing a second portion of the data plugin component and transmitting corresponding response data in a second transmission separate from the first transmission to the client device via the network connection.

Cloud-based composable data layer

Aggregation of content based on user-generated topics is provided. Users may associate one or more topics with content items stored across various workloads and repositories. A topic may be a word or phrase of the user's choice, and may be utilized for discoverability of information and aggregation of content items. Topics and content items associated with topics may be acted on (e.g., a user may add or delete topics to associate with a content item, associate or disassociate content items with a topic, embed a set of content items or a stream of content items associated with a topic into other experiences, follow topics, etc.). Content items identified as related to a specific topic may be automatically suggested as possible content items of interest to the user. Additionally, when a user follows a topic, the user may be notified of any changes that occur to the topic.

Aggregating enterprise graph content around user-generated topics

Examples described herein generally relate to a computer system for generating a knowledge graph storing a plurality of entities and to displaying a topic page for an entity in the knowledge graph. The computer system performs a mining of source documents within an enterprise intranet to determine a plurality of entity names. The computer system generates an entity record within the knowledge graph for a mined entity name based on an entity schema and the source documents. The entity record includes attributes aggregated from the source documents. The computer system receives a curation action on the entity record from a first user. The computer system updates the entity record based on the curation action. The computer system displays an entity page including at least a portion of the attributes to a second user based on permissions of the second user to view the source documents.

Enterprise knowledge graph

A data processing system implements receiving a request for user-centric topic recommendations from a computing device of a user in response to a user input in an application indicating that the user is attempting to assign a tag to a first content item in the application; obtaining a first set of user-centric topic recommendations from a first topic datastore based on a relevance ranking assigned to each of the topic recommendations; providing the first set of user-centric topic recommendations to the computing device; causing the computing device to display the first set of user-centric topic recommendations; receiving one or more second requests for user-centric topic recommendations; obtaining one or more second sets of user-centric topic recommendations from the first topic datastore based on the query string and the relevance ranking; and causing the computing device of the user to display the one or more second sets of user-centric topic recommendations.

User centric topics for topic suggestions

A computing system comprises, in one example, a display system, a user profile update system configured to update a user profile for a given user, a data extraction system configured to analyze a data source and to extract, from the data source, at least one work attribute associated with the given user, and a surfacing system. The surfacing system comprises a suggestion generator component configured to generate a user profile suggestion based on the at least one work attribute, and a display system controller configured to control the display system to generate a user interface display, with user input mechanisms, that displays the user profile suggestion and to detect a user interaction with the user input mechanisms. The user profile update system updates the user profile based on the detected user interaction.

Extracting and surfacing user work attributes from data sources

Systems and methods for providing notification delivery based on utilization of bloom filters are provided. A collaboration system obtains subscriber information for each user of a collaboration system, whereby the subscriber information corresponds to one or more features of content that are relevant to each user. The collaboration system hashes the subscriber information to generate a bloom filter for each user. The collaboration system receives an article to be published, whereby the article comprises a set of features. The set of features is hashed to obtain a hash set. The hashing of the set of features is performed using same hashing functions as that used to generate the bloom filter. The collaboration system compares the hash set to the bloom filter to identify a match, whereby the match indicates a feature of the article matches the subscriber information. The collaboration system generates a list of recipients based on the match.

System of mobile notification delivery utilizing bloom filters

Extracting and surfacing information corresponding to individual logical topics from enterprise data stores that are separated across multiple geographic regions. A clustering service creates, by utilizing machine learning toolkits that are agnostic to the region in which data is stored, individual topics that have references to multiple shards of data that are stored in different geographic regions. The clustering service also shards the knowledge base state according to the regions from which pieces of data for the particular logical topic was extracted. For example, a first shard containing information extracted from a first document may be stored in a first region whereas a second shard containing information extracted from a second document may be stored in a second region. Responsive to user activity associated with the topic, a serving platform may identify and reconstitute these shards that are stored in different regions so as to surface the regionally extracted and sharded information on that topic to a user.

Extracting and surfacing topic descriptions from regionally separated data stores

Examples described herein generally relate to a computer system including a knowledge graph storing a plurality of entities. A mining of a set of enterprise source documents within an enterprise intranet is performed, by a plurality of knowledge mining toolkits, to determine a plurality of entity names. The plurality of entity names are linked based on entity metadata by traversing various relationships between people, files, sites, groups, associated with entities. An entity record is generated within a knowledge graph for a mined entity name from the linked entity names based on an entity schema and ones of the set of enterprise source documents associated with the mined entity name. The entity record includes attributes aggregated from the ones of the set of enterprise source documents associated with the mined entity name.

Enterprise knowledge graphs using multiple toolkits

Mining of a set of enterprise source documents within an enterprise intranet is performed, by a plurality of knowledge mining toolkits, to determine a plurality of entity names. A plurality of entity records are generated within a knowledge graph for mined entity names from the entity names based on an entity schema and ones of the set of enterprise source documents associated with the mined entity names. Pattern recognition is applied to an active document using an enterprise named entity recognition (ENER) system to identify potential entity names within the document that match a respective one of a plurality of entity records in the knowledge graph. One or more matching entity names are annotated within the document with information from the knowledge graph for the respective ones of the plurality of entity records. The annotated information is displayed with the active document.

Annotations for enterprise knowledge graphs using multiple toolkits

A system may include a processor; and a memory storing instructions that, when executed by the processor, configure the processor to: receive, from a computing device, a request for a set of content, the request associated with a user identifier; query a cached data store to determine that a set of audiences for the user identifier is stale; in response to the determination that the set of audiences is stale: access user properties for the user identifier; and generate the set of audiences for the user identifier based on the user properties; and serve the set of content according to the generated set of audiences.

Scalable system for dynamic user audience determination

Growing community of inventors

Bellevue, WA, United States of America

Dmitriy Meyerzon