Systems and methods for improved conversation translation

• US 10,635,754 B1
• Filed: 08/02/2019
• Issued: 04/28/2020
• Est. Priority Date: 08/02/2019
• Status: Active Grant

• Current Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Original Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Inventors: Pham, Vincent, Goodsitt, Jeremy Edward, Walters, Austin, Abad, Fardin Abdi Taghi
• Primary Examiner(s): Islam, Mohammad K
• Application Number:
  US16/529,950
• Time in Patent Office: 270 Days
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G06F 40/51 Translation evaluation
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation

Abstract

Systems and methods for improved conversation translation are disclosed. The system receives a first portion of a conversation in a first language. The system translates the first portion of the conversation to a second language. The system generates a predicted second portion of the conversation. The first portion and the predicted second portion are sent to a second user device as a predictive translation. The system then receives an actual second portion of the conversation, translates it to the second language, and sends the first portion and the actual second portion to the second user device as a batch translation. The system compares the batch translation to the predictive translation to identity any differences and generates a color-coded translation highlighting any differences between the batch translation and the predictive translation. The system sends the color-coded translation to the second user device for display on the second user device.

Claims

1. A method for improved conversation translation comprising:

receiving, by a processor, a first portion of a conversation in a first language from a first user device associated with a first user;

translating, by the processor, the first portion of the conversation from the first language to a second language with a translation algorithm;

generating, by the processor, a predicted second portion of the conversation in the second language with a predictive algorithm;

sending, by the processor, the first portion and the predicted second portion to a second user device as a predictive translation in the second language;

receiving, at the processor, an actual second portion of the conversation from the first user device in the first language;

translating, by the processor, the actual second portion of the conversation from the first language to the second language with the translation algorithm;

sending, by the processor, the first portion and the actual second portion of the conversation as a batch translation in the second language to the second user device;

comparing, by the processor, the predictive translation to the batch translation to identify any differences between the predictive translation and the batch translation;

generating, by the processor, a color-coded translation highlighting any differences between the batch translation and the predictive translation; and

sending, by the processor, the color-coded translation to the second user device to cause the second user device to display the predicative translation with any differences between the batch translation and the predictive translation highlighted in a first color.

2. The method of claim 1, further comprising:

identifying, by the processor, one or more sentiments from the color-coded translation based on at least one of;

tone, one or more pauses, one or more questions, pitch, negative wording, positive wording, or redundant wording; and

assigning, by the processor, a second color to each of the one or more sentiments in the color-coded translation; and

updating, by the processor, the color-coded translation to include the second color.

3. The method of claim 2, further comprising:

receiving, by the processor, a first response to at least one of the differences or the one or more sentiments from the second user device, the first response confirming or denying the at least one of the differences or the one or more sentiments.

4. The method of claim 3, further comprising:

updating, by the processor, the color-coded translation based on the first response; and

sending, by the processor, the color-coded translation to the second user device.

5. The method of claim 3, further comprising:

updating, by the processor, at least one of the translation algorithm or the predictive algorithm based on the first response.

6. The method of claim 1, wherein the first portion and the actual second portion include voice data or text data.

7. The method of claim 1, further comprising:

receiving, from the first user device, an address for the second user device;

wherein sending the batch translation to the second user device further comprises;

sending the batch translation to the address for the second user device; and

wherein sending the predictive translation to the second user device further comprises;

sending the predictive translation to the address for the second user device.

8. A method for improved conversation translation comprising:

sending, by a processor of a first user device, a first portion of a conversation in a first language to a computing device;

receiving, at the processor, a predictive translation, including a second portion of the conversation and a predicted third portion of the conversation, from a computing device in the first language, the second portion of the conversation sent to the computing device by a second user device in a second language, wherein the computing device translates the second portion of the conversation from a second language to the first language;

receiving, by the processor, a batch translation from the computing device including the second portion and an actual third portion of the conversation in the first language, the actual third portion of the conversation sent to the computing device by the second user device in the second language, wherein the computing device translates the actual third portion of the conversation from the second language to the first language;

comparing, with the processor, the batch translation and the predictive translation to identify any differences between the batch translation and the predictive translation;

displaying, on a first graphical user interface (GUI) located on a first portion of a screen of the first user device, the predictive translation with any differences between the batch translation and the predictive translation highlighted in a first color; and

displaying, on a second GUI located on a second portion of the screen of the first user device, the batch translation.

9. The method of claim 8, further comprising:

identifying, by the processor, one or more sentiments from the predictive translation based on at least one of;

tone, one or more questions, pitch, negative wording, positive wording, or redundant wording; and

displaying, on the first GUI, the second GUI, or both, the one or more sentiments highlighted in a second color.

10. The method of claim 9, further comprising:

sending, by the first user device, a first response to the computing device indicating confirmation or denial of the differences or the one or more sentiments.

11. The method of claim 10, further comprising:

receiving, by the first user device, an updated translation based on the predictive translation, the batch translation, and the first response from the computing device.

12. The method of claim 11, further comprising:

sending, by the first user device, an instruction to transmit the updated translation to the second user device.

13. The method of claim 11, further comprising:

sending, by the first user device, the updated translation to the second user device.

14. The method of claim 13, wherein the first user device and the second user device communicate through Bluetooth®

communication or near field communication (NFC).

15. A first user device comprising:

a processor;

a screen comprising a first graphical user interface (GUI) and a second GUI, the first GUI and the second GUI displayed concurrently on the screen; and

memory, in communication with the processor and the screen, and storing instructions that, when executed, cause the first user device to;

receive, by the processor, a first portion of a conversation in a first language from a user of the first user device;

translate, by the processor, the first portion of the conversation from the first language to a second language with a translation algorithm;

generate, by the processor, a predicted second portion of the conversation in the second language with a predictive algorithm;

send, by the processor, a first predictive translation, including the first portion and the predicted second portion, in the second language to a second user device;

receive, by the processor, an actual second portion of the conversation in a first language from the user of the first user device;

translate, by the processor, the actual second portion of the conversation from the first language to the second language with the translation algorithm;

send, by the processor, a first batch translation including the first portion and the actual second portion in the second language to the second user device;

receive, by the processor, a second predictive translation in the first language including a third portion of the conversation and a fourth predicted portion of the conversation, the third portion received in the second language from the second user device;

display, in the first GUI, the second predictive translation in the first language;

receive, by the processor, a second batch translation in the first language including the third portion of the conversation and an actual fourth portion of the conversation, the actual fourth portion received in the second language from the second user device;

display, in the second GUI, the second batch translation;

compare, by the processor, the second predictive translation to the second batch translation to identify any differences between the second predictive translation and the second batch translation; and

highlight, in the first GUI, the second GUI, or both, any differences between the second predictive translation and the second batch translation in a first color.

16. The first user device of claim 15, further configured to:

determine, by the processor, one or more sentiments in the second predictive translation based on at least one of;

tone, one or more pauses, one or more questions, pitch, negative wording, positive wording, or redundant wording;

assign, by the processor, a second color to each of the one or more sentiments; and

highlight, in the first GUI, the second GUI, or both, each of the one or more sentiments in the second color.

17. The first user device of claim 16, further configured to:

receive, at the processor, a first response to at least one of the differences or at least one of the one or more sentiments from the first user device, the first response confirming or denying the at least one of the differences or at least one of the one or more sentiments.

18. The first user device of claim 17, further configured to:

update, the first GUI, the second GUI, or both, based on the first response.

19. The first user device of claim 17, further comprising:

update, by the processor, the translation algorithm, the predictive algorithm, or both based on the first response.

20. The first user device of claim 15, wherein the first portion, the actual second portion, the predicted second portion, the third portion, the actual fourth portion, and the predicted fourth portion include voice data or text data.