IP Library › Granted Patent US 12,153,893
Granted Patent B2
US 12,153,893 · App. 17/583,909 · Granted Nov 26, 2024

Automatic tone detection and suggestion

Inventors: Tomasz Lukasz Religa (Seattle, WA); Zhang Li (Bellevue, WA); Christine Lauren Mayer (Seattle, WA); Max Wang (Seattle, WA); Huitian Jiao (Redmond, WA); Weixin Cai (Kirkland, WA); Cheng Yang (Bellevue, WA); Christie Chan (Los Angeles, CA); Siqing Chen (Bellevue, WA)
Assignee: Microsoft Technology Licensing, LLC
G06F40/35G06F40/253G06F40/284G06N20/00
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,153,893
App. No.
17/583,909
Filed
Jan 25, 2022
Granted
Nov 26, 2024
Kind
B2
Art Unit
2681
USPC
704/9
Abstract

A method and system for providing tone detection for a content may include receiving a request to detect a tone for a content, retrieving user data and data about the content, detecting a content environment for the content based on at least one of the user data and the data about the content, detecting the tone for the content based on the content and the content environment, inputting the content and the detected tone into a machine-learning (ML) model for modifying the tone from the detected tone to a modified tone, obtaining at least one rephrased content segment as an output from the ML model, the rephrased content segment modifying the tone of the content from the detected tone to the modified tone, and providing at least one of the detected tone or the at least one rephrased content segment for display.

Claims (62)

1. A data processing system comprising:

a processor; and

a memory in communication with the processor, the memory comprising executable instructions that, when executed by, the processor, cause the data processing system to perform functions of:

receiving a request to detect a tone for a content;

retrieving user data and data about the content;

detecting a content environment for the content based on at least one of the user data and the data about the content;

calculating a prediction score for a likelihood of the content being associated with a given tone;

comparing the calculated prediction score to a threshold requirement for the detected content environment;

when the calculated prediction score meets the threshold requirement for the detected content environment, identifying the given tone as a detected tone for the content;

inputting the content and the detected tone into a machine-learning (ML) model for modifying the tone from the detected tone to a modified tone;

obtaining at least one rephrased content segment as an output from the ML model, the rephrased content segment modifying the tone of the content from the detected tone to the modified tone; and

providing at least one of the detected tone or the at least one rephrased content segment for display.

2. The data processing system of claim 1 , wherein the instructions further cause the processor to cause the data processing system to perform functions of:

identify a portion of the content that is likely responsible for the detected tone; and

providing display data about the identified portion for display.

3. The data processing system of claim 2 , wherein the identified portion is identified in a user interface screen as the portion responsible for the detected tone.

4. The data processing system of claim 3 , wherein upon selection of the identified portion in the user interface screen, the at least one rephrased content segment is displayed.

5. The data processing system of claim 1 , wherein the instructions further cause the processor to cause the data processing system to perform functions of providing the detected content environment for display.

6. The data processing system of claim 1 , wherein the detected content environment includes a detected audience for the content.

7. The data processing system of claim 1 , wherein detecting the tone is done via a plurality of ML models for each of a plurality of tones.

8. A method for providing tone detection for a content, comprising:

receiving a request to detect a tone for the content;

retrieving user data and data about the content;

detecting a content environment for the content based on at least one of the user data and the data about the content;

calculating a prediction score for a likelihood of the content being associated with a given tone;

comparing the calculated prediction score to a threshold requirement for the detected content environment;

when the calculated prediction score meets the threshold requirement for the detected content environment, identifying the given tone as a detected tone for the content;

inputting the content and the detected tone into a machine-learning (ML) model for modifying the tone from the detected tone to a modified tone;

obtaining at least one rephrased content segment as an output from the ML model, the rephrased content segment modifying the tone of the content from the detected tone to the modified tone; and

providing at least one of the detected tone or the at least one rephrased content segment for display.

9. The method of claim 8 , further comprising:

parsing the content into a plurality of smaller segments;

detecting a separate tone for one or more of the smaller segments;

determining the tone for the content based on the separate tone for the one or more smaller segments.

10. The method of claim 8 , further comprising:

collecting user feedback information relating to at least one of the detected tone or a user's selection of the rephrased content segment;

ensuring that the user feedback information is privacy compliant; and

storing the user feedback information for use in improving the ML model.

11. The method of claim 8 , further comprising:

identify a portion of the content that is likely responsible for the detected tone; and

providing display data about the identified portion for display.

12. The method of claim 8 , further comprising:

determining if the detected tone conveys an improper tone; and

upon determining that the detected tone conveys the improper tone, providing a notification of the improper tone for display.

13. The method of claim 11 , wherein the identified portion is identified in a user interface screen as the portion responsible for the detected tone.

14. The method of claim 13 , wherein upon selection of the identified portion in the user interface screen, the at least one rephrased content segment is displayed.

15. The method of claim 8 , further comprising providing the detected content environment for display.

16. A non-transitory computer readable medium on which are stored instructions that, when executed, cause a programmable device to perform functions of:

receiving a request to detect a tone for a content;

retrieving user data and data about the content;

detecting a content environment for the content based on at least one of the user data and the data about the content;

calculating a prediction score for a likelihood of the content being associated with a given tone;

comparing the calculated prediction score to a threshold requirement for the detected content environment;

when the calculated prediction score meets the threshold requirement for the detected content environment, identifying the given tone as a detected tone for the content;

inputting the content and the detected tone into a machine-learning (ML) model for modifying the tone from the detected tone to a modified tone;

obtaining at least one rephrased content segment as an output from the ML model, the rephrased content segment modifying the tone of the content from the detected tone to the modified tone; and

providing at least one of the detected tone or the at least one rephrased content segment for display.

17. The non-transitory computer readable medium of claim 16 , wherein the instructions further cause the programmable device to perform functions of:

identify a portion of the content that is likely responsible for the detected tone; and

providing display data about the identified portion for display.

18. The non-transitory computer readable medium of claim 17 , wherein the identified portion is identified in a user interface screen as the portion responsible for the detected tone.

19. The non-transitory computer readable medium of claim 16 , wherein the instructions further cause the programmable device to perform functions of providing the detected content environment for display.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 31, 2022
From: LI, ZHANG
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 058825/0773 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 25, 2022
From: RELIGA, TOMASZ LUKASZ; MAYER, CHRISTINE LAUREN; WANG, MAX; JIAO, HUITIAN; CAI, WEIXIN; YANG, CHENG; CHAN, CHRISTIE; CHEN, SI-QING
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 058762/0658 →
Continuity (1)
Related Publication 20230259713A1 · Aug 17, 2023