Microsoft Technology Licensing, LLC

Vladimir V Gvozdev

Dmitriy Meyerzon

John Michael Winn

Nikita Voronkov

Matteo Venanzi

Alexander Armin Spengler

Ivan Korostelev

John Guiver

Pavel Myshkov

Yordan Kirilov Zaykov

Elena Pochernina

Samuel Alexander Webster

Jeffrey L Wight

Jan-Ove Almli Karlberg

Åge Andre Kvalnes

Helge Grenager Solheim

Omar Zia Khan

Hui Li

Roberta Cannerozzi

Kjetil Krogvig Bergstrand

Thomas Minka

Anthony Arnold Wieser

Andrei-Alin Corodescu

Simon Thoresen Hult

Marius Bunescu

Thuy Thanh Duong

Kathrine Hammervold

Mircea Neagovici-Negoescu

Anund Lie

Niels Petter Rasch-Olsen

Chia-Jiun Tan

Martin Kukla

Kaixiang Miao

Liang Zheng

Omar Faruk

Andrei Razvan Popov

Sanil Rajput

Lars Kirkholt Melhus

Jørgen Løland

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 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

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

Examples described herein generally relate to a computer system including a knowledge graph storing a plurality of entities. The computer system compares source documents within an enterprise intranet to a plurality of templates defining potential entity attributes to identify extracts matching at least one of the plurality of templates. The computer system parses the extracts according to respective templates of the plurality of templates that match the extracts to determine instances. The computer system performs incremental clustering on a number of the instances to determine potential entity names. The computer system queries the knowledge graph with the potential entity names to obtain a set of candidate entity records. The computer system links the potential entity names with at least partial matching ones of the set of candidate entity records to define updated matching candidate entity records. The computer system updates the knowledge graph with the updated matching candidate entity records.

Incremental clustering for enterprise knowledge graph

Documents in a local computing system are parsed for indexing and sent to a cloud-based computing system. The cloud-based search service indexes documents that are parsed on the local computing system, as well as documents that reside in the cloud-based computing system. When a user launches a search, the search is executed against a single search index in the cloud-based computing system, which includes an index of content sources from both the local computing system and the cloud-based computing system.

Hybrid search connector

Growing community of inventors

Sammamish, WA, United States of America

Vladimir V Gvozdev