Response prediction for electronic communications

Patent metadata

Field	Value
Publication number	US-12450502-B2
Application number	US-202418407892-A
Country	US
Kind code	B2
Filing date	Jan 9, 2024
Priority date	Jun 4, 2020
Publication date	Oct 21, 2025
Grant date	Oct 21, 2025

Abstract

Systems, methods, and apparatuses are described herein for performing sentiment analysis on electronic communications relating to one or more image-based communications methods, such as emoji. Message data may be received. The message data may correspond to a message that is intended to be sent but has not yet been sent to an application. Using a first machine learning model, one or more subsets of the plurality of emoji may be determined. The one or more subsets of the plurality of emoji may comprise one or more different types and quantities of emoji, and may each correspond to the same or a different sentiment. Using a second machine learning model, one or more emojis may be selected from the one or more subsets. The one or more emojis selected may correspond to responses to the message.

First claim

What is claimed is:

1. A first computing device comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the first computing device to:
before sending a first message to a second computing device:
process, using a first trained machine learning model configured to determine subsets comprising at least two text elements of a plurality of text elements, the first message to determine one or more subsets comprising at least two different text elements of the plurality of text elements, wherein at least one of the one or more subsets corresponds to at least two different text element types, and wherein the first trained machine learning model was trained by modifying using first training data, one or more first weights of a first artificial neural network;
select, using a second trained machine learning model configured to select text elements of the plurality of text elements that correspond to one or more predicted responses to one or more messages and based on the first message, one or more second text elements from the one or more subsets of the plurality of text elements, wherein the second trained machine learning model was trained by modifying, using second training data different from the first training data, one or more second weights of a second artificial neural network; and
transmit the one or more second text elements.

2. The first computing device of claim 1 , wherein the second computing devices executes an application, wherein the application is a messaging application, and wherein the first message is intended to be posted in the messaging application.

3. The first computing device of claim 1 , wherein the instructions, when executed by the one or more processors, cause the first computing device to process the first message by causing the first computing device to:
weight each of the plurality of text elements based on:
a quantity of the plurality of text elements that correspond to an text element type; and
a sentiment corresponding to the text element type.

4. The first computing device of claim 1 , wherein a first text element type of the at least two different text element types corresponds to a positive reaction, and wherein a second text element type of the at least two different text element types corresponds to a negative reaction.

5. The first computing device of claim 1 , wherein at least one of the one or more subsets further corresponds to:
a first quantity of a first text element type of the at least two different text element types, and
a second quantity of a second text element type of the at least two different text element types.

6. The first computing device of claim 1 , wherein the first trained machine learning model is trained using first training data that comprises a history of messages in one or more of a plurality of applications that each comprise a plurality of different text element corresponding to one or more different sentiments.

7. The first computing device of claim 1 , wherein the second trained machine learning model was trained using second training data that comprises a history of responses to one or more past messages of a history of messages in one or more of a plurality of applications.

8. The first computing device of claim 1 , wherein the instructions, when executed by the one or more processors, cause the first computing device to transmit the one or more second text elements by transmitting a confidence value associated with each of the one or more second text elements.

9. The first computing device of claim 1 , wherein the instructions, when executed by the one or more processors, cause the first computing device to process the first message by causing the first computing device to:
determine that a first text element of the plurality of text elements belongs to a first subset of the one or more subsets based on one or more second text elements of the plurality of text elements.

10. The first computing device of claim 1 , wherein the instructions, when executed by the one or more processors, cause the first computing device to transmit the one or more second text elements by causing the first computing device to:
transmit a count of the one or more second text elements.

11. The first computing device of claim 1 , wherein the message comprises one or more text elements.

12. A method comprising:
before sending, by a first computing device, a first message to a second computing device:
processing, by the first computing device and using a first trained machine learning model configured to determine subsets comprising at least two text elements of a plurality of text elements, the first message to determine one or more subsets comprising at least two different text elements of the plurality of text elements, wherein at least one of the one or more subsets corresponds to at least two different text element types, and wherein the first trained machine learning model was trained by modifying using first training data, one or more first weights of a first artificial neural network;
selecting, by the first computing device, using a second trained machine learning model configured to select text elements of the plurality of text elements that correspond to one or more predicted responses to one or more messages, and based on the first message, one or more second text elements from the one or more subsets of the plurality of text elements, wherein the second trained machine learning model was trained by modifying, using second training data different from the first training data, one or more second weights of a second artificial neural network; and
transmitting, by the first computing device, the one or more second text elements.

13. The method of claim 12 , wherein the second computing device executes a first application, wherein the first application is a messaging application, and wherein the first message is intended to be posted in the first application.

14. The method of claim 12 , wherein processing the first message comprises:
weighting each of the plurality of text elements based on:
a quantity of the plurality of text elements that correspond to an text element type; and
a sentiment corresponding to the text element type.

15. The method of claim 12 , wherein a first text element type of the at least two different text element types corresponds to a positive reaction, and wherein a second text element type of the at least two different text element types corresponds to a negative reaction.

16. The method of claim 12 , wherein at least one of the one or more subsets further corresponds to:
a first quantity of a first text element type of the at least two different text element types, and
a second quantity of a second text element type of the at least two different text element types.

17. The method of claim 12 , wherein transmitting the one or more second text elements comprises transmitting a confidence value associated with each of the one or more second text elements.

18. A method comprising:
before sending, by a first computing device, textual content of a first message to a second computing device;
processing, by the first computing device and using a first trained machine learning model configured to determine subsets comprising at least two text elements of a plurality of text elements, the textual content of the first message to determine one or more subsets comprising at least two different text elements of the plurality of text elements, and wherein the first trained machine learning model was trai

Assignees

• Capital One Services Llc

Inventors

• Osborn Kevin
• Loucks Eric
• Edwards Joshua
• Bergeron George
• Johnson Kyle
• Lee Brian

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title

• H04L51/10

  Multimedia information · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title