Systems and methods for combining and summarizing emoji responses to generate a text reaction from the emoji responses

Patent metadata

Field	Value
Publication number	US-11444894-B2
Application number	US-202117478438-A
Country	US
Kind code	B2
Filing date	Sep 17, 2021
Priority date	Jun 10, 2020
Publication date	Sep 13, 2022
Grant date	Sep 13, 2022

Abstract

Example embodiments of messaging systems and methods are provided. An example system includes a database containing a plurality of messages, a plurality of emoji responses, and a plurality of text reactions. The system further includes a predictive model trained using the plurality of messages and the plurality of emoji responses as inputs and the plurality of text reactions as outputs to determine a mapping relationship between the inputs and the outputs. The predictive model receives a message and one or more emoji responses to the message, combines and summarizes the one or more emoji responses to a text reaction to the message based on the mapping relationship, and transmits the text reaction to a user who initiates the message.

First claim

What is claimed is:

1. A non-transitory computer-accessible medium comprising for execution by a computer hardware arrangement comprising a processor and a memory, wherein, upon execution by the processor, the processor is configured to perform procedures comprising:
receiving, by a predictive model, a first message;
receiving, by the predictive model, an emoji response to the first message;
combining, by the predictive model, the emoji response to the first message based on a mapping relationship to generate at least one selected from the group of words and phrases;
summarizing, by the predictive model, the emoji response to the first message based on the mapping relationship to generate a text sentiment reaction;
generating, by the predictive model, a text reaction to the first message by integrating the text sentiment reaction with the generated at least one selected from the group of words, and phrases; and
transmitting, by the predictive model, the text reaction to the first message.

2. The non-transitory computer-accessible medium of claim 1 , wherein the procedures further comprise training the predictive model using a plurality of messages and a plurality of emoji responses as inputs and a plurality of text reactions as outputs to determine a mapping relationship between the inputs and the outputs.

3. The non-transitory computer-accessible medium of claim 2 , wherein:
at least one of the plurality of emoji responses corresponds to each of the plurality of messages, and
at least one of the plurality of text reactions corresponds to each of the plurality of messages.

4. The non-transitory computer-accessible medium of claim 3 , wherein each of the plurality of text reactions is generated by combining corresponding emoji responses of the plurality of emoji responses.

5. The non-transitory computer-accessible medium of claim 2 , wherein:
each message of the plurality of messages comprises one or more selected from the group of text and emoji,
each of the plurality of text reactions comprises one or more selected from the group of a word and a phrase, and
the word and phrase each is generated by combining one or more of the corresponding emoji responses.

6. The non-transitory computer-accessible medium of claim 2 , wherein:
each of the plurality of text reactions comprises a text sentiment reaction that is generated by summarizing one or more of the corresponding emoji responses.

7. The non-transitory computer-accessible medium of claim 1 , wherein:
the first message is received from a first user application comprising instructions for execution on a first user device,
the emoji response to the first message is received from a second user application comprising instructions for execution on a second user device, and
the text reaction is transmitted to the first user application.

8. The non-transitory computer-accessible medium of claim 1 , wherein combining the emoji response to the first message based on the mapping relationship comprises:
converting, by the predictive model, the emoji response to corresponding individual characters, and
combining, by the predictive model, the corresponding individual characters to generate the at least one selected from the group of words and phrases.

9. The non-transitory computer-accessible medium of claim 1 , wherein:
the text sentiment reaction to the first message is generated by the predictive model via a sentiment analysis algorithm.

10. A messaging system, comprising:
a processor;
a memory; and
a predictive model, wherein the predictive model is configured to:
receive a first message,
receive an emoji response to the first message,
combine the emoji response to the first message based on a mapping relationship to generate at least one selected from the group of words and phrases,
summarize the emoji response to the first message based on the mapping relationship to generate a text sentiment reaction,
generate a text reaction to the first message by integrating the text sentiment reaction with the generated at least one selected from the group of words and phrases, and
transmit the text reaction t.

11. The system of claim 10 , wherein combining the emoji response to the first message based on the mapping relationship comprises:
converting the emoji response to corresponding individual characters; and
combining the corresponding individual characters to generate the at least one selected from the group of words and phrases.

12. The system of claim 10 , wherein:
the predictive model is trained using a plurality of messages and a plurality of emoji responses as inputs and a plurality of text reactions as outputs, and
the predictive model is further configured to determine the mapping relationship between the inputs and the outputs.

13. The system of claim 12 , wherein:
each message of the plurality of messages comprises one or more selected from the group of text and emoji,
each of the plurality of text reactions comprises one or more selected from the group of a word and a phrase, and
the word and phrase each is generated by combining one or more of the corresponding emoji responses.

14. The system of claim 12 , wherein:
at least one of the plurality of emoji responses corresponds to each of the plurality of messages,
at least one of the plurality of text reactions corresponds to each of the plurality of messages, and
each of the plurality of text reactions is generated by combining corresponding emoji responses of the plurality of emoji responses.

15. The system of claim 10 , wherein:
the first message is received from a first user application comprising instructions for execution on a first user device,
the emoji response to the first message is received from a second user application comprising instructions for execution on a second user device, and
the text reaction is transmitted to the first user application.

16. A method, comprising:
receiving, by a predictive model, a first message;
receiving, by the predictive model, an emoji response to the first message;
combining, by the predictive model, the emoji response to the first message based on a mapping relationship to generate at least one selected from the group of words and phrases;
summarizing, by the predictive model, the emoji response to the first message based on the mapping relationship to generate a text sentiment reaction;
generating, by the predictive model, a text reaction to the first message by integrating the text sentiment reaction with the generated at least one selected from the group of words, and phrases; and
transmitting, by the predictive model, the text reaction to the first message.

17. The method of claim 16 , further comprising:
training the predictive model using a plurality of messages and a plurality of emoji responses as inputs and a plurality of text reactions as outputs to determine a mapping relationship between the inputs and the outputs,
wherein at least one of the plurality of emoji responses corresponds to each of the plurality of messages, and
wherein at least one of the plurality of text reactions corresponds to each of the plurality of messages.

18. The method of claim 17 , further comprising generating, by the predictive model, an overall sentiment based on the mapping relationship.

19. The method of claim 18 , further comprising assigning, by the predictive model, a sentiment score to the overall sentiment.

20. The method of claim 16 , wherein the text reaction to the first message is transmit

Assignees

• Capital One Services Llc

Inventors

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

Classifications

• H04L51/02 Primary

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• H04L51/10 Primary

  Multimedia information · CPC title