Systems and methods for improving business communications using natural language processing

Patent metadata

Field	Value
Publication number	US-2020410055-A1
Application number	US-201916455122-A
Country	US
Kind code	A1
Filing date	Jun 27, 2019
Priority date	Jun 27, 2019
Publication date	Dec 31, 2020
Grant date	—

Abstract

Systems and methods for improving business communication are provided. The system includes a processor, a memory, and a user interface coupled to each of the processor, and the memory. The processor is configured to receive and read the text of a business communication; identify one or more words in the text of the business communication for evaluation of objectivity, apply an objectivity rule and generate an objectivity score for the one or more identified words. The method further determines whether the objectivity score is low using a control table and provides a replacement word for an identified word having a low objectivity score.

First claim

What is claimed is:

1 . A system for improving business communication, the system comprising:
a processor; a memory; and a user interface coupled to each of the processor, and the memory, wherein the processor is configured to: receive, from a client device, a text of a business communication; read the text of a business communication; identify one or more words in the text of the business communication for evaluation of objectivity; apply an objectivity rule; and generate an objectivity score for the one or more identified words.

2 . The system of claim 1 , wherein the one or more words identified in the business communication is assigned an objectivity score.

3 . The system of claim 1 , wherein the one or more words identified in the business communication is compared with a library comprised of one or more replacement words based on semantic properties of the word, and assigned a score based on the objectivity.

4 . The system of claim 1 , wherein the algorithm is a natural language processing algorithm.

5 . The system of claim 4 , wherein the natural language processing algorithm is an unsupervised algorithm.

6 . The system of claim 4 , wherein the natural language processing algorithm is a supervised algorithm.

7 . The system of claim 4 , wherein the natural language processing algorithm is a semi-supervised algorithm.

8 . A method for improving business communication, the method comprising the steps of:
reading a text of a business communication; identifying one or more words in the text of the business communication for evaluation of objectivity; applying an objectivity rule; generating an objectivity score for the one or more identified words; comparing the objectivity score with a score control table; and identifying a replacement word for an identified word with a low objectivity score.

9 . The method of claim 8 , wherein, the business communication comprises of an email, a report, a news article, a press release, a newsletter, or a letter.

10 . A system for improving business communication, the system comprising:
a processor; a memory; and a user interface coupled to each of the processor, and the memory, wherein the processor is configured to: receive, from a client device, a text of a business communication; read the text of a business communication; identify one or more words in the text of the business communication for evaluation of objectivity; apply an objectivity rule; generate an objectivity score for the one or more identified words; compare the objectivity score with a control table; determine whether the objectivity score is low; and identify a replacement word in a library for a word with a low objectivity score.

11 . The system of claim 10 , wherein the one or more words identified in the business communication is assigned an objectivity score.

12 . The system of claim 10 , wherein the one or more words identified in the business communication is compared with a library comprised of one or more replacement words based on semantic properties of the word, and assigned a score based on the objectivity.

13 . The system of claim 10 , wherein the algorithm is a natural language processing algorithm.

14 . The system of claim 13 , wherein the natural language processing algorithm is an unsupervised algorithm.

15 . The system of claim 13 , wherein the natural language processing algorithm is a supervised algorithm.

16 . The system of claim 13 , wherein the natural language processing algorithm is a semi-supervised algorithm.

Assignees

• Jpmorgan Chase Bank Na

Inventors

• Backis Lukas
• Tucker Greg
• Alker Elliot

Classifications

• G06F18/2113

  by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0895

  Weakly supervised learning, e.g. semi-supervised or self-supervised learning · CPC title

• G06Q10/10

  Office automation; Time management · CPC title

• G06N20/00

  Machine learning · CPC title