Automatically assisting conversations using graph database

Patent metadata

Field	Value
Publication number	US-11580305-B2
Application number	US-201715636066-A
Country	US
Kind code	B2
Filing date	Jun 28, 2017
Priority date	Jun 28, 2017
Publication date	Feb 14, 2023
Grant date	Feb 14, 2023

Abstract

Examples of the present disclosure describe systems and methods for automatically assisting conversations using a graph database. In order to minimize misunderstanding of words and phrases used by participants during a conversation, phrases from the conversation may be received by conversation assistance application as the conversation takes place. Entities may be extracted from the phrase based on natural language recognition according to a domain context of the participant being assisted. One or more tags may be looked up from a graph database, and may be provided to the participant as a list of hashtags related to the conversation. Links to documents may be extracted based on the tags for the participant for viewing during the conversation.

First claim

What is claimed is:

1. A system, comprising:
at least one processor; and
a memory storing instructions that when executed by the at least one processor perform operations for assisting conversations, the operations comprising:
receiving at least one phrase from a conversation between a first participant and a second participant;
extracting a tag based on the at least one received phrase, wherein extracting the tag comprises:
extracting at least one entity from the received at least one phrase based on natural language recognition, wherein the natural language recognition is based on at least one of a first domain of the first participant or a second domain of the second participant; and
based on the extracted at least one entity, retrieving the tag from at least one graph database;

retrieving a first set of links to a first subset of documents for the first participant from the at least one graph database based on: the tag, the first domain, and access privileges for the first participant to the documents;
retrieving a second set of links to a second subset of the documents for the second participant from the at least one graph database based on: the tag, the second domain, and access privileges for the second participant to the documents; and
providing the first set of links to the first participant and the second set of links to the second participant.

2. The system of claim 1 , wherein retrieving the first set of links to the first subset of the documents for the first participant and the second set of links to the second subset of the documents for the second participant comprises:
retrieving tag nodes from the at least one graph database;
based on the retrieved tag nodes, retrieving at least one link to at least one of the documents associated with the retrieved tag nodes; and
ranking the retrieved at least one link to the at least one of the documents based on relevance to the extracted at least one entity.

3. The system of claim 1 , wherein the tag is associated with at least one document.

4. The system of claim 1 , wherein the operations further comprise identifying at least one common domain context among the first participant and the second participant to the conversation, wherein the natural language recognition is based on the at least one common domain context.

5. The system of claim 1 , wherein the at least one graph database comprises a tag graph, and wherein the tag graph comprises a tag node and an edge originating from the tag node to a document link node.

6. The system of claim 1 , wherein the at least one graph database comprises a document link graph, the document link graph comprising a document link node, at least one edge from the document link node to a document node, and at least one edge from the document link node to an access control node.

7. A method for automatically assisting conversation among participants using a graph database, the method comprising:
receiving identities of participants of a conversation, wherein one of the participants is a requesting participant;
receiving a phrase from the conversation;
extracting a tag from the phrase;
receiving a selection of the tag from the requesting participant;
based on the tag and the identity of the requesting participant, retrieving a set of links to at least a subset of electronic files for the requesting participant from a plurality of graph databases, wherein the plurality of the graph databases comprise:
a first graph database comprising organizational information about the participants that includes access control information regarding access to the electronic files;
a second graph database comprising relationships between the tag and other tags; and
a third graph database comprising links to the at least the subset of electronic files, wherein the second graph database further comprises relationships between at least the tag and the links in the third graph database; and

based on access control information for the requesting participant, providing the set of links to the at least the subset of electronic files to the requesting participant.

8. The method of claim 7 , the method further comprising:
receiving identity of a participant of the conversation, wherein extracting the tag comprises:
extracting at least one entity from the received phrase based on natural language recognition; and
based on the extracted at least one entity, retrieving the tag from at least one graph database.

9. The method of claim 8 , the method further comprising:
receiving identity of a participant of the conversation, wherein retrieving the set of links to electronic files comprises:
retrieving tag nodes from the at least one graph database;
based on the retrieved tag nodes, retrieving at least one link to the at least the subset of the electronic files associated with the retrieved tag nodes; and
ranking the retrieved at least one link to the at least the subset of the electronic files based on relevance to the extracted at least one entity.

10. The method of claim 8 , wherein the tag is associated with at least one of the set of links to the at least the subset of electronic files, and wherein the requesting participant is accessible to the electronic files through the set of links to electronic files.

11. The method of claim 8 , wherein the natural language recognition is based on a domain context of the requesting participant.

12. The method of claim 8 , further comprising:
receiving identities of all participants of the conversation; and
identifying at least one common domain context among the all participants of the conversation, wherein the natural language recognition is based on the common domain context of the requesting participant.

13. The method of claim 8 , wherein the at least one graph database comprises a tag graph comprising a tag node and an edge originating from the tag node to a document link node.

14. The method of claim 8 , wherein the at least one graph database comprises a document link graph comprising a document link node, at least one edge from the document link node to at least one of the electronic files, and at least one edge from the document link node to an access control node.

15. A computer-readable storage device with a memory storing computer executable instructions which, when connected to and executed by at least one processor, perform a method for automatically assisting conversations among participants using graph database, the method comprising:
receiving a phrase from a conversation between a first participant and a second participant;
transcoding the phrase to at least one text phrase;
extracting a tag from the at least one text phrase, wherein extracting the tag comprises:
extracting at least one entity from the received phrase based on natural language recognition, wherein the natural language recognition is based on at least one of a first domain of the first participant or a second domain of the second participant; and
based on the extracted at least one entity, retrieving the tag from at least one graph database;

receiving a selection of the tag from at least one of the first participant or the second participant;
retrieving a first set of links to a first subset of documents for the first participant from the at least one graph database based on: the tag, the first domain for the first participant, and access privileges for the first participant to the documents;
retrieving a second set of links to a second subset of the documents for the second participant from the at least one graph database based on the tag, the second domain for the second partic

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Olsen Bernt Ivar
• Elsebø Kristian
• Meling Jon

Classifications

• G06F40/169

  Annotation, e.g. comment data or footnotes · CPC title

• G06F16/9024

  Graphs; Linked lists (G06F16/9027 takes precedence) · CPC title

• G06F17/00

  Digital computing or data processing equipment or methods, specially adapted for specific functions (information retrieval, database structures or file system structures therefor G06F16/00) · CPC title

• G06F16/93

  Document management systems · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title