IP Library Granted Patent US 11,295,237
Granted Patent B2
US 11,295,237 · App. 16/220,518 · Granted Apr 5, 2022

Smart copy optimization in customer acquisition and customer management platforms

Inventors: Pavan Korada (San Mateo, CA); Sunpreet Singh Khanuja (Santa Clara, CA); Ao Li (New York, NY)
Assignee: Zeta Global Corp.
G06N20/00G06F16/958G06F16/9577G06K9/6201G06N3/0454G06N3/06G06N5/025G06N7/005G06N5/003
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 11,295,237
App. No.
16/220,518
Granted
Apr 5, 2022
Kind
B2
Abstract

In some examples, special-purpose machines are provided that facilitate smart copy optimization in a network service or publication system, including software-configured computerized variants of such special-purpose machines and improvements to such variants, and to the technologies by which such special-purpose machines become improved compared to other special-purpose machines that facilitate adding the new features. Such technologies can include special artificial-intelligence (AI), machine-learning (ML), and natural-language-processing (NLP) techniques.

Claims (69)

1. A copy optimization tool comprising:

a memory;

a neural network including:

a plurality of input nodes, wherein each input node includes a memory location for storing an input value;

a plurality of hidden nodes, wherein each hidden node is connected to each input node and includes computational instructions, implemented in machine code, for computing output values, respectively; and

a plurality of output nodes, wherein each of the output nodes includes a memory location for storing a respective output signal indicative of an output value or feature for a trained model;

one or more computer processors, configured to execute instructions programmed using a set of machine code, wherein the instructions, when executed by the one or more computer processors, cause the one or more computer processors to perform operations comprising:

extracting a text input from a candidate copy content;

using the trained model, accessing comparable historical copy content to generate historical comparison content;

profiling a historical performance of the historical comparison content in a context of CRM marketing, based on one or more of the following metrics:

a variance in the historical performance of the comparison content;

a frequency of use of a historical subject line or comparable copy content; and

a recency of use of a historical subject line or comparable copy content;

matching the text input from the candidate copy content with the comparable copy content based on one or more matching algorithms;

identifying historical matches of comparable copy content matching the text input of the candidate copy content;

ranking the historical matches based on one or more of the following rules:

a quality of a match;

a volume of historical subject lines or comparable copy content;

a word count; and

a recency or frequency of a historical subject line or comparable copy content; and

applying a weighting factor to the historical matches based on a past seasonality of historical matches.

2. The copy optimization tool of claim 1 , wherein the operations further comprise:

identifying a plurality of drivers in the extracted text using the trained model based on the profiled historical performance.

3. The copy optimization tool of claim 2 , wherein the plurality of drivers include positive and negative drivers.

4. The copy optimization tool of claim 3 , wherein the operations further comprise changing at least one of the negative drivers to a positive driver and transmitting a modified candidate copy content having the changed driver.

5. A method for copy optimization, comprising:

extracting, with a processor, a text input from a candidate copy content;

using a trained model of a neural network, accessing, with the processor, comparable historical copy content to generate historical comparison content; the neural network including

a plurality of input nodes, wherein each input node includes a memory location for storing an input value;

a plurality of hidden nodes, wherein each hidden node is connected to each input node and includes computational instructions, implemented in machine code, for computing output values, respectively; and

a plurality of output nodes, wherein each of the output nodes includes a memory location for storing a respective output signal indicative of an output value or feature for a trained model;

profiling, with the processor, a historical performance of the historical comparison content in a context of CRM marketing, based on one or more of the following metrics:

a variance in the historical performance of the comparison content;

a frequency of use of a historical subject line or comparable copy content; and

a recency of use of a historical subject line or comparable copy content;

matching, with the processor the text input from the candidate copy content with the comparable copy content based on one or more matching algorithms;

identifying, with the processor, historical matches of comparable copy content matching the text input of the candidate copy content; and

ranking, with the processor, the historical matches based on one or more of the following rules:

a quality of a match;

a volume of historical subject lines or comparable copy content;

a word count; and

a recency or frequency of a historical subject line or comparable copy content; and

applying, with the processor, a weighting factor to the historical matches based on a past seasonality of historical matches.

6. The method of claim 5 , further comprising:

identifying, with the processor, a plurality of drivers in the extracted text using the trained model based on the profiled historical performance.

7. The method of claim 6 , wherein the plurality of drivers include positive and negative drivers.

8. The method of claim 7 , further comprising changing, with the processor, at least one of the negative drivers to a positive driver and transmitting a modified candidate copy content having the changed driver.

9. A non-transitory computer-readable medium storing instructions that, when executed by one or more computer processors of a computer, cause the computer to perform operations comprising:

extracting a text input from a candidate copy content;

using a trained model of a neural network, accessing comparable historical copy content generate historical comparison content; the neural network including

a plurality of input nodes, wherein each input node includes a memory location for storing an input value;

a plurality of hidden nodes, wherein each hidden node is connected to each input node and includes computational instructions, implemented in machine code, for computing output values, respectively; and

a plurality of output nodes, wherein each of the output nodes includes a memory location for storing a respective output signal indicative of an output value or feature for a trained model;

profiling a historical performance of the historical comparison content in a context of CRM marketing, based on one or more of the following metrics:

a variance in the historical performance of the comparison content;

a frequency of use of a historical subject line or comparable copy content; and

a recency of use of a historical subject line or comparable copy content;

matching the text input from the candidate copy content with the comparable copy content based on one or more matching algorithms;

identifying historical matches of comparable copy content matching the text input of the candidate copy content; and

ranking the historical matches based on one or more of the following rules:

a quality of a match;

a volume of historical subject lines or comparable copy content;

a word count; and

a recency or frequency of a historical subject line or comparable copy content; and

applying a weighting factor to the historical matches based on a past seasonality of historical matches.

10. The computer-readable medium of claim 9 , wherein the operations further comprise:

identifying a plurality of drivers in the extracted text using the trained model based on the profiled historical performance.

11. The computer-readable medium of claim 10 , wherein the plurality of drivers include positive and negative drivers.

12. The computer-readable medium of claim 11 , wherein the operations further comprise changing at least one of the negative drivers to a positive driver and transmitting a modified candidate copy content having the changed driver.

Assignments (6)
NOTICE OF GRANT OF SECURITY INTEREST IN PATENTS Recorded Aug 30, 2024
From: ZETA GLOBAL CORP.; ZSTREAM ACQUISITION LLC
To: BANK OF AMERICA, N.A., AS ADMINISTRATIVE AGENT
Reel/Frame 068822/0154 →
TERMINATION AND RELEASE OF SECURITY INTEREST IN PATENTS RECORDED AT REEL 055212, FRAME 0964 Recorded Aug 30, 2024
From: BANK OF AMERICA, N.A., AS ADMINISTRATIVE AGENT
To: ZETA GLOBAL CORP.
Reel/Frame 068822/0167 →
RELEASE OF SECURITY INTEREST Recorded Feb 11, 2021
From: FIRST EAGLE PRIVATE CREDIT, LLC, AS SUCCESSOR TO NEWSTAR FINANCIAL, INC
To: ZBT ACQUISITION CORP.; ZETA GLOBAL CORP.; 935 KOP ASSOCIATES, LLC
Reel/Frame 055282/0276 →
NOTICE OF GRANT OF SECURITY INTEREST IN PATENTS Recorded Feb 3, 2021
From: ZETA GLOBAL CORP.
To: BANK OF AMERICA, N.A.
Reel/Frame 055212/0964 →
SECURITY INTEREST Recorded Dec 3, 2020
From: ZETA GLOBAL CORP.
To: FIRST EAGLE PRIVATE CREDIT, LLC
Reel/Frame 054585/0770 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 13, 2019
From: KORADA, PAVAN; KHANUJA, SUNPREET SINGH; LI, AO
To: ZETA GLOBAL CORP.
Reel/Frame 051271/0410 →
Continuity (1)
Related Publication 20200193322A1 · Jun 18, 2020