Contextual-based knowledge entity suggestions

Patent metadata

Field	Value
Publication number	US-2024185093-A1
Application number	US-202218075284-A
Country	US
Kind code	A1
Filing date	Dec 5, 2022
Priority date	Dec 5, 2022
Publication date	Jun 6, 2024
Grant date	—

Abstract

A data processing system implements receiving a textual context inserted into a user interface element; receiving an indicator inserted into the user interface element after the textual context, the indicator indicating a desire to tag a topic from a plurality of topics included in a knowledge base; receiving one or more textual character inserted into the user interface element after the indicator; encoding, using a machine-learning (ML) model, the received textual context to generate at least one representation reflecting one or more meanings of the received textual context; decoding, using the ML model, the at least one representation to generate a plurality of tokens in response to the one or more meanings of the received textual context, the plurality of tokens corresponding with the at least one textual character and at least one of the topics of the plurality of topics; identifying one or more topics from the plurality of topics as recommended topics; and providing the identified recommended topics for display in a topic selection user interface element that enables selection of one recommended topic for insertion as the tag in the user interface element.

First claim

What is claimed is:

1 . A data processing system comprising:
a processor; and a machine-readable medium storing executable instructions that, when executed, cause the processor to perform operations comprising:
receiving a textual context inserted into a user interface element;
receiving an indicator inserted into the user interface element after the textual context, the indicator indicating a desire to tag a topic from a plurality of topics included in a knowledge base;
receiving at least one textual character inserted into the user interface element after the indicator;
encoding, using a machine-learning (ML) model, the received textual context to generate at least one representation reflecting one or more meanings of the received textual context;
decoding, using the ML model, the at least one representation to generate a plurality of tokens in response to the one or more meanings of the received textual context, the plurality of tokens corresponding with the at least one textual character and at least one of the topics of the plurality of topics;
identifying one or more topics from the plurality of topics as recommended topics; and
providing the identified recommended topics for display in a topic selection user interface element that enables selection of one recommended topic for insertion as the tag in the user interface element.

2 . The data processing system of claim 1 , wherein generating the plurality of tokens includes utilizing a prefix tree data structure representing the plurality of topics in the knowledge base.

3 . The data processing system of claim 2 , wherein generating the plurality of tokens further includes generating tokens that match the at least one textual characters.

4 . The data processing system of claim 2 , wherein the prefix tree is divided into sub-areas.

5 . The data processing system of claim 4 , wherein the knowledge base comprises an organization-based knowledge base associated with a user utilizing the user interface element.

6 . The data processing system of claim 5 , wherein the knowledge base is stored in a storage medium associated with the organization.

7 . The data processing system of claim 6 , wherein at least one of the sub-areas is transferred between the storage medium and one or more computing devices that execute the ML model as processing requires.

8 . A method implemented in a data processing system for providing topic recommendations, the method comprising:
receiving a textual context inserted into a user interface element; receiving an indicator inserted into the user interface element after the textual context, the indicator indicating a desire to tag a topic from a plurality of topics included in a knowledge base; receiving at least one textual character inserted into the user interface element after the indicator; providing the textual context, the at least one character and a prefix tree data structure representing the plurality of topics as inputs to a trained machine-learning (ML) model; receiving as an output of the trained ML model one or more topics from the plurality of topics as identified recommended topics; and providing the identified recommended topics for display in a topic selection user interface element that enables selection of one recommended topic for insertion as the tag in the user interface element.

9 . The method of claim 8 , wherein the ML model performs functions of:
encoding the received textual context to generate at least one representation reflecting one or more meanings of the received textual context; decoding the at least one representation to generate a plurality of tokens in response to the one or more meanings of the received textual context, the plurality of tokens corresponding with the at least one textual character and at least one of the topics of the plurality of topics; and identifying one or more topics from the plurality of topics as recommended topics.

10 . The method of claim 9 , wherein generating the plurality of tokens includes utilizing the prefix tree data structure representing the plurality of topics in the knowledge base.

11 . The method of claim 10 , wherein generating the plurality of tokens further includes generating tokens that match the at least one textual characters

12 . The method of claim 8 , wherein the knowledge base comprises an organization-based knowledge base associated with a user utilizing the user interface element.

13 . The method of claim 12 , wherein the prefix tree is divided into sub-areas.

14 . The method of claim 13 , wherein the knowledge base is stored in a storage medium associated with the organization.

15 . The method of claim 14 , wherein at least one of the sub-areas is transferred between the storage medium and one or more computing devices that execute the ML model as processing requires.

16 . A machine-readable medium on which are stored instructions that, when executed, cause a processor of a programmable device to perform functions of:
receiving a textual context inserted into a user interface element; receiving an indicator inserted into the user interface element after the textual context, the indicator indicating a desire to tag a topic from a plurality of topics included in a knowledge base; receiving at least one textual character inserted into the user interface element after the indicator; encoding, using a machine-learning (ML) model, the received textual context to generate at least one representation reflecting one or more meanings of the received textual context; decoding, using the ML model, the at least one representation to generate a plurality of tokens in response to the one or more meanings of the received textual context, the plurality of tokens corresponding with the at least one textual character and at least one of the topics of the plurality of topics; identifying one or more topics from the plurality of topics as recommended topics; and providing the identified recommended topics for display in a topic selection user interface element that enables selection of one recommended topic for insertion as the tag in the user interface element.

17 . The machine-readable medium of claim 16 , wherein generating the plurality of tokens includes utilizing a prefix tree data structure representing the plurality of topics in the knowledge base.

18 . The machine-readable medium of claim 16 , wherein generating the plurality of tokens further includes generating tokens that match the at least one textual characters.

19 . The machine-readable medium of claim 16 , where the ML model is a bidirectional encoder representations from transformers (BERT) model.

20 . The machine-readable medium of claim 16 , wherein the knowledge base comprises an organization-based knowledge base associated with a user utilizing the user interface element.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Blohm Sebastian Johannes
• Li Xiao
• Voronkov Nikita
• Kotaich Hadi
• Xu Wenjin
• Piao Kun
• Ong Dion Stephan Javellana

Classifications

• G06N5/022 Primary

  Knowledge engineering; Knowledge acquisition · CPC title

• G06F40/284

  Lexical analysis, e.g. tokenisation or collocates · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G06F16/353 Primary

  into predefined classes · CPC title

• G06F16/345

  Summarisation for human users · CPC title