IP Library Granted Patent US 11,741,484
Granted Patent B2
US 11,741,484 · App. 16/431,584 · Granted Aug 29, 2023

Customer interaction and experience system using emotional-semantic computing

Inventor: Alan McCord (Wakatipu Queenstown, NZ)
Assignee: VONAGE BUSINESS LIMITED
G06Q30/0201G06F16/248G06F16/24578G06F16/9535G06F40/237G06N20/00G10L15/1815G10L15/22G10L15/26G10L25/63
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 11,741,484
App. No.
16/431,584
Granted
Aug 29, 2023
Kind
B2
Abstract

A system and method for customer interaction and experience enhancement which automatically gathers direct and indirect customer communications about products and services, converts them to text where necessary, and analyzes the communications for sentiment and emotional content, and scores and displays the information in a manner conducive to making business decisions based on the customer sentiment and emotion, such as making changes to products or services, troubleshooting customer service interactions, and better marketing.

Claims (31)

1. A system for enhancing customer relations through automated analysis of the conversational distance in direct and indirect customer communications, comprising:

a web search engine for gathering indirect customer communications about products and services from online sources;

an automated speech recognition engine for converting audio to text transcriptions;

a sentiment and emotion analyzer for:

receiving direct and indirect customer communications, each communication being associated with a product or service and each communication comprising either text content or audio content, the text content and audio content comprising an expression of an emotion or a sentiment;

converting any audio content to text content using the automated speech recognition engine;

receiving text content from each of the direct and indirect customer communications;

analyzing the received text content using a machine learning algorithm to determine a conversational distance between an agent and a customer for each of the direct and indirect customer communications, wherein:

the conversational distance is determined at least in part by the emotion or the sentiment;

the conversational distance for the direct customer communications is determined using the agent's interactions with the customer, and

the conversational distance for the indirect customer communications is determined using the agent's history of interactions with other customers;

cumulatively assigning similarity scores to the products or services associated with the direct or indirect customer communications based on the determined conversational distance; and

generating a recommended response for the agent to each direct or indirect communication based on the assigned similarity score for that direct or indirect communication.

2. The system of claim 1 wherein the sentiment and emotion analyzer uses vector clustering to segment similar content.

3. The system of claim 1 wherein the sentiment and emotion analyzer uses linear transformation to translate between the language of product-specific or service-specific domains.

4. The system of claim 1 wherein the sentiment and emotion analyzer uses vector algebra to determine sentiment.

5. The system of claim 1 wherein the sentiment and emotion analyzer uses vector calculus to understand and predict time evolution in sentiment by calculating rates of change of vectors and time dynamics, and the predictions are applied to the cumulatively assigned similarity scores.

6. A method for enhancing customer relations through automated analysis of conversational distance in direct and indirect customer communications, comprising:

gathering indirect customer communications from online sources using a web search engine operating on a computing device;

receiving direct and indirect customer communications at a sentiment and emotion analyzer operating on the computing device, each communication being associated with a product or service and each communication comprising either text content or audio content the text content and audio content comprising an expression of an emotion or a sentiment;

converting any audio content to text content using an automated speech recognition engine operating on the computing device;

analyzing text content from each of the direct and indirect customer communications using a machine learning algorithm to determine a conversational distance between an agent and a customer for each of the direct and indirect customer communications, wherein:

the conversational distance is determined at least in part by the emotion or the sentiment;

the conversational distance for the direct customer communications is determined using the agent's interactions with the customer, and

the conversational distance for the indirect customer communications is determined using the agent's history of interactions with other customers;

cumulatively assigning similarity scores to the products or services associated with the direct or indirect customer communications based on the determined conversational distance; and

generating a recommended response for the agent to each direct or indirect communication based on the assigned similarity score for that direct or indirect communication.

7. The method of claim 6 comprising the additional step of using vector clustering to segment similar content.

8. The method of claim 6 comprising the additional step of using linear transformation to translate between the language of product-specific or service-specific domains.

9. The method of claim 6 comprising the additional step of using vector algebra to determine sentiment.

10. The method of claim 6 comprising the additional step of using vector calculus to understand and predict time evolution in emotion and meaning by calculating rates of change of vectors and time dynamics, and applying the predictions to the cumulatively assigned similarity scores.

Assignments (2)
CHANGE OF NAME Recorded Feb 3, 2022
From: NEWVOICEMEDIA LIMITED
To: VONAGE BUSINESS LIMITED
Reel/Frame 058879/0481 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 13, 2020
From: MCCORD, ALAN
To: NEWVOICEMEDIA LTD.
Reel/Frame 053185/0477 →
Continuity (4)
Continuation 16163482 · Oct 17, 2018
Continuation In Part 15675420 · Aug 11, 2017
Provisional Application 62523733 · Jun 22, 2017
Related Publication 20200160356A1 · May 21, 2020
Cited By (1)
US 12,712,970