Generating document edit requests for electronic documents managed by a third-party document management service using artificial intelligence

Patent metadata

Field	Value
Publication number	US-2020293606-A1
Application number	US-201916355160-A
Country	US
Kind code	A1
Filing date	Mar 15, 2019
Priority date	Mar 15, 2019
Publication date	Sep 17, 2020
Grant date	—

Abstract

Artificial intelligence is introduced into document review to identify content suggestions from input to generate suggested annotations for the reviewed document. An approach is provided for receiving an electronic document that contains original content from an original electronic document for review and electronic mark-ups provided by a first user. One or more electronic mark-ups that represent content suggestions proposed by the first user are identified from the electronic document. For each electronic mark-up of the one or more electronic mark-ups identified a document portion of the original content that corresponds to the electronic mark-up is identified, and an annotation is generated for the electronic mark-up comprising the electronic mark-up and a first user ID for the first user and associating the annotation to the document portion identified. The original content with one or more annotations generated from the one or more electronic mark-ups is displayed, in electronic form, within a display window.

First claim

What is claimed is:

1 . An apparatus comprising:
one or more processors; and one or more memories storing instructions which, when processed by the one or more processors, cause:
receiving content input that represents content suggestions for content within an electronic document managed by a third-party management system;
identifying one or more content suggestions from the content input;
for each content suggestion of the one or more content suggestions from the content input:
identifying a document portion of the electronic document that corresponds to the content suggestion;
generating a document suggestion request for the content suggestion, wherein the document suggestion request comprises the content suggestion, a content suggestion type, an associated user ID of the user associated with the content suggestion, and an electronic document location based on the identified document portion; and

sending, to the third-party management system, one or more generated document suggestion requests.

2 . The apparatus of claim 1 , wherein the content input is one of a marked-up physical document, a marked-up electronic document, an audio file, a video file, a captured screenshot, or an interactive whiteboard file that contains a series of coordinates corresponding to received input representing generated marks on an interactive whiteboard.

3 . The apparatus of claim 1 , wherein identifying the one or more content suggestions from the content input, comprises:
determining that the content input is a media content item; and using a machine-learning model, identifying the one or more content suggestions that correspond to phrases indicating suggestions for the electronic document, wherein the machine-learning model has been trained using an input data set of media content items that have identified content suggestion speech.

4 . The apparatus of claim 3 , wherein the associated user ID of the user associated with the content suggestion is determined using the machine-learning model to identify the associated user ID based upon matching speech characteristics of speech within the media content item to speech characteristics of the associated user ID.

5 . The apparatus of claim 1 , wherein identifying the one or more content suggestions from the content input, comprises:
determining that the content input is one of a marked-up electronic document or a marked-up physical document; identifying original content within the electronic document; and identifying the one or more content suggestions as mark-ups within the electronic document by identifying content that is separate from the original content identified in the electronic document.

6 . The apparatus of claim 1 , wherein for each content suggestion of the one or more content suggestions from the content input, further cause:
using a machine-learning model, determining a meaning of the content suggestion by analyzing combinations of text characters within the content suggestion; and using the machine-learning model, determining the content suggestion type for the content suggestion based upon the meaning of the content suggestion, wherein the content suggestion type is one of a comment or a suggested edit.

7 . The apparatus of claim 1 , the one or more memories store additional instructions which, when processed by the one or more processors, cause:
determining that the content input is a media content item; sending the media content item to the third-party management system; and wherein the generated document suggestion request further comprises an electronic link to the media content item.

8 . One or more non-transitory computer-readable media storing instructions which, when processed by one or more processors, cause:
receiving content input that represents content suggestions for content within an electronic document managed by a third-party management system; identifying one or more content suggestions from the content input; for each content suggestion of the one or more content suggestions from the content input:
identifying a document portion of the electronic document that corresponds to the content suggestion;
generating a document suggestion request for the content suggestion, wherein the document suggestion request comprises the content suggestion, a content suggestion type, an associated user ID of the user associated with the content suggestion, and an electronic document location based on the identified document portion; and
sending, to the third-party management system, one or more generated document suggestion requests.

9 . The one or more non-transitory computer-readable media of claim 8 , wherein the content input is one of a marked-up physical document, a marked-up electronic document, an audio file, a video file, a captured screenshot, or an interactive whiteboard file that contains a series of coordinates corresponding to received input representing generated marks on an interactive whiteboard.

10 . The one or more non-transitory computer-readable media of claim 8 , wherein identifying the one or more content suggestions from the content input, comprises:
determining that the content input is a media content item; and using a machine-learning model, identifying the one or more content suggestions that correspond to phrases indicating suggestions for the electronic document, wherein the machine-learning model has been trained using an input data set of media content items that have identified content suggestion speech.

11 . The one or more non-transitory computer-readable media of claim 10 , wherein the associated user ID of the user associated with the content suggestion is determined using the machine-learning model to identify the associated user ID based upon matching speech characteristics of speech within the media content item to speech characteristics of the associated user ID.

12 . The one or more non-transitory computer-readable media of claim 8 , wherein identifying the one or more content suggestions from the content input, comprises:
determining that the content input is one of a marked-up electronic document or a marked-up physical document; identifying original content within the electronic document; and identifying the one or more content suggestions as mark-ups within the electronic document by identifying content that is separate from the original content identified in the electronic document.

13 . The one or more non-transitory computer-readable media of claim 8 , wherein for each content suggestion of the one or more content suggestions from the content input, further comprising:
using a machine-learning model, determining a meaning of the content suggestion by analyzing combinations of text characters within the content suggestion; and using the machine-learning model, determining the content suggestion type for the content suggestion based upon the meaning of the content suggestion, wherein the content suggestion type is one of a comment or a suggested edit.

14 . The one or more non-transitory computer-readable media of claim 8 , wherein identifying the one or more electronic mark-ups that represent the content suggestions proposed by the first user, comprises:
determining that the content input is a media content item; sending the media content item to the third-party management system; and wherein the generated document suggestion request further comprises an electronic link to the media content item.

15 . A computer-implemented method comprising:
receiving content input that represents content suggestions for content within an electronic document mana

Assignees

• Nelson Steven A
• Kitada Hiroshi
• Wong Lana
• Ricoh Co Ltd

Inventors

• Nelson Steven A
• Kitada Hiroshi
• Wong Lana

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/08

  Learning methods · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F40/30

  Semantic analysis · CPC title