Content element recommendation system

Patent metadata

Field	Value
Publication number	US-11790165-B2
Application number	US-202117214518-A
Country	US
Kind code	B2
Filing date	Mar 26, 2021
Priority date	Jan 26, 2021
Publication date	Oct 17, 2023
Grant date	Oct 17, 2023

Abstract

A system and method for identifying relevant content from other documents and presenting candidate documents/content in a document authoring application is described. A computer-implemented method includes performing an analysis of text of a document being authored by a user with a document authoring application, searching a document library for content elements and documents based on the analysis of the text, identifying candidate documents and candidate content based on the searching, presenting a list of candidate documents or candidate content with the document authoring application, receiving a selection of a candidate document or candidate content from the list in the document authoring application, and including an instance of the selected candidate document or candidate content in the document.

First claim

What is claimed is:

1. A computer-implemented method comprising:
monitoring content in a document a user is typing in a document authoring application of a client device;
identifying a last predefined number of words or phrases authored in the document by the user typing in the document authoring application;
performing an analysis of the last predefined number of words or phrases authored in the document by the user typing in the document authoring application;
searching a document library for content elements and documents based on the analysis of the last predefined number of words or phrases authored in the document;
identifying candidate documents and candidate content based on the searching;
identifying user's interactions with the document authoring application and determining whether to display, based on the user's interactions, a candidate graphical user interface that includes the candidate documents and the candidate content, the user's interactions comprising a combination of predefined keywords and predefined key triggers;
generating a suggestion indicator in a graphical user interface generated by the document authoring application in response to identifying the candidate documents and candidate content based on the searching;
detecting a selection of the suggestion indicator by the user of the document authoring application;
in response to detecting the selection of the suggestion indicator, visually identifying key phrases in the document in the document authoring application;
presenting a list of the candidate documents or candidate content in a pane of the graphical user interface;
receiving a selection of a candidate document or candidate content from the list in the document authoring application;
identifying a portion of the candidate document or candidate content, the portion being relevant to the last predefined number of words or phrases of the document; and
including the portion of the candidate document or candidate content in a body of the document.

2. The computer-implemented method of claim 1 , further comprising:
detecting a predefined trigger at the document authoring application,
wherein the identifying candidate documents and candidate content is in response to detecting the predefined trigger.

3. The computer-implemented method of claim 1 , wherein including the portion of the candidate document or candidate content further comprises:
identifying a location, in the body of the document, based on the last predefined number of words or phrases authored in the document by the user; and
adding the portion of the candidate document or candidate content at the location in the body of the document.

4. The computer-implemented method of claim 1 , wherein the candidate content comprises a dynamic element that is updated near real-time based on changes to the dynamic element by other users having access to the dynamic element.

5. The computer-implemented method of claim 1 , further comprising:
identifying a user profile of the user operating the document authoring application; and
training a machine learning model based on the user profile and a pattern of events from the document authoring application.

6. The computer-implemented method of claim 5 , wherein the user profile of the user indicates an enterprise profile of the user, collaborators of the user, a group within an enterprise to which the user belongs, an operating system of the client device, and a time and day of document authoring application activities of the user.

7. The computer-implemented method of claim 1 , further comprising:
training a machine learning model based on a pattern of events from the document authoring application.

8. The computer-implemented method of claim 7 , wherein the pattern of events comprises:
features of the document present in the document authoring application;
features of a first candidate document selected by the user; and
features of a second candidate document not selected by the user.

9. The computer-implemented method of claim 7 , further comprising:
computing a relevance score for each candidate document in the document library based on the machine learning model,
the relevance score for each candidate document being indicative of a relevance of each candidate document to the document present in the document authoring application.

10. The computer-implemented method of claim 9 , further comprising:
ranking each candidate document based on their corresponding relevance score; and
identifying top candidate documents from the ranked candidate documents, a set of candidate documents including the top candidate documents.

11. The computer-implemented method of claim 9 , wherein the relevance score is based on a current document feature inputs and candidate document feature inputs,
the current document feature inputs comprising a filename, a title, and a preset character neighborhood around an insertion point in the document present in the document authoring application, and
the candidate document feature inputs comprising a filename, a title, and a summary of a corresponding candidate document.

12. The computer-implemented method of claim 1 , further comprising:
identifying relevant content from the candidate documents, the relevant content being pertinent to the content in the document present in the document authoring application,
wherein providing the candidate documents in the user interface element of the document authoring application further comprises: identifying the relevant content from a set of candidate documents in the user interface element of the document authoring application.

13. The computer-implemented method of claim 1 , wherein the document library includes documents authored, read, edited, and shared by the user of the document authoring application, and documents shared to or from the user.

14. The computer-implemented method of claim 1 , further comprising:
causing a display of a first user interface element of the document authoring application adjacent to a second user interface element of the document authoring application,
the first user interface element comprising the document being formed by the document authoring application,
the second user interface element comprising one or more candidate documents from a set of candidate documents.

15. A computing apparatus comprising:
a processor; and
a memory storing instructions that, when executed by the processor, configure the apparatus to:
monitor content of a document a user is typing in a document authoring application of a client device;
identify a last predefined number of words or phrases authored in the document by the user typing in the document authoring application;
perform an analysis of the last predefined number of words or phrases authored in the document by the user typing in the document authoring application;
search a document library for content elements and documents based on the analysis of the last predefined number of words or phrases authored in the document;
identify candidate documents and candidate content based on the searching;
identify a combination of predefined keywords typed by the user in the document authoring application, predefined key triggers typed by the user in the document authoring application, and long-detected pauses by the user in the document authoring application, and determine whether to display, based on the combination of predefined keywords and predefined key triggers, a candidate graphical user interface that includes the candidate documents and the candidate content;
generate a suggestion indicator in a gra

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Wilde Benjamin Gustav
• Richardson Ransom Lloyd
• Banks Richard Malcolm
• Sharma Manoj
• Wu Zeyu
• Howard Matthew Stephen
• Sundar Sudarshan
• Stopa Lyndsy Marie
• Zheng Yi
• Sanchez Jacob Lee
• Polyakov Aleksandr
• Campoli Jason Peter
• Howard Gregory Alan
• Scudieri Paul Anthony

Classifications

• G06F40/205 Primary

  Parsing · CPC title

• G06F16/3344

  using natural language analysis · CPC title

• G06F3/0482

  Interaction with lists of selectable items, e.g. menus · CPC title

• G06F16/335 Primary

  Filtering based on additional data, e.g. user or group profiles (filtering in web context G06F16/9535, G06F16/9536) · CPC title

• G06F3/04842

  Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) · CPC title