IP Library › Granted Patent US 12,731,082
Granted Patent B2
US 12,731,082 · App. 17/560,159 · Granted Sep 8, 2026

Smart copy optimization in customer acquisition and customer management platforms

Inventors: Pavan Korada (San Rafael, CA); Sunpreet Singh Khanuja (San Jose, CA); Ao Li (Cliffside, NJ)
Assignee: Zeta Global Corp.
G06N20/10G06F16/9577G06F16/958G06F18/22G06N3/045G06N3/06G06N5/025G06N7/01G06N20/00G06N5/01
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 12,731,082
App. No.
17/560,159
Filed
Dec 22, 2021
Granted
Sep 8, 2026
Kind
B2
Examiner
CHEN, ALAN S
Art Unit
2125
USPC
707/748
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 (61)

1 . A copy optimization tool comprising:

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

profiling a historical performance of the historical comparison content based on one or more of following metrics:

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

a recency of use of a historical subject line and 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 following rules:

a quality of a match;

a volume of historical subject lines and comparable copy content;

a word count; and

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

applying a weighting factor to the historical matches based on past seasonal performance patterns of the comparable copy content associated with the ranked historical matches;

determining a confidence range of the performance of the candidate copy content based on a weight-adjusted standard deviation interval of the ranked historical matches; and

transmitting, based on the determined confidence range of the performance of the candidate copy content, the candidate copy content over a network for deployment in a marketing campaign.

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 a text input from a candidate copy content;

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

profiling a historical performance of the historical comparison content based on one or more of following metrics:

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

a recency of use of a historical subject line and 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 following rules:

a quality of a match;

a volume of historical subject lines and comparable copy content;

a word count; and

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

applying a weighting factor to the historical matches based on past seasonal performance patterns of the comparable copy content associated with the ranked historical matches;

determining a confidence range of the performance of the candidate copy content based on a weight-adjusted standard deviation interval of the ranked historical matches; and

transmitting, based on the determined confidence range of the performance of the candidate copy content, the candidate copy content over a network for deployment in a marketing campaign.

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 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, accessing comparable historical copy content to generate historical comparison content;

profiling a historical performance of the historical comparison content based on one or more of following metrics:

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

a recency of use of a historical subject line and 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 following rules:

a quality of a match;

a volume of historical subject lines and comparable copy content;

a word count; and

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

applying a weighting factor to the historical matches based on past seasonal performance patterns of the comparable copy content associated with the ranked historical matches;

determining a confidence range of the performance of the candidate copy content based on a weight-adjusted standard deviation interval of the ranked historical matches; and

transmitting, based on the determined confidence range of the performance of the candidate copy content, the candidate copy content over a network for deployment in a marketing campaign.

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 (4)
RELEASE OF SECURITY INTEREST Recorded Jul 27, 2026
From: BANK OF AMERICA, N.A., AS ADMINISTRATIVE AGENT
To: ZETA GLOBAL CORP.; ZSTREAM ACQUISTION LLC
Reel/Frame 076066/0332 →
SECURITY INTEREST Recorded Jul 24, 2026
From: ZETA GLOBAL CORP.; ZSTREAM ACQUISITION LLC; LIVECLICKER INC.; MARIGOLD USA, INC.; LIVEINTENT, INC.; SAILTHRU, INC.
To: BANK OF AMERICA, N.A., AS ADMINISTRATIVE AGENT
Reel/Frame 076062/0611 →
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 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 23, 2023
From: KORADA, PAVAN; KHANUJA, SUNPREET SINGH; LI, AO
To: ZETA GLOBAL CORP.
Reel/Frame 062781/0144 →
Continuity (2)
Continuation 16220518 · Dec 14, 2018
Related Publication 20220114497A1 · Apr 14, 2022
References Cited (24)
US 6029139A · Cunningham et al. · 2000 [cited by applicant]
US 10091140B2 · Galley et al. · 2018 [cited by applicant]
US 20110313865A1 · Sinyagin et al. · 2011 [cited by applicant]
US 20120215640A1 · Ramer et al. · 2012 [cited by applicant]
US 20170262878A1 · Cetintas et al. · 2017 [cited by applicant]
US 20180108066A1 · Kale et al. · 2018 [cited by applicant]
US 20200007934A1 · Ortiz et al. · 2020 [cited by applicant]
US 20200021873A1 · Swaminathan et al. · 2020 [cited by applicant]
US 20200034887A1 · Hamedi et al. · 2020 [cited by applicant]
US 20200193322A1 · Korada et al. · 2020 [cited by applicant]
WO WO2020123949A1 · 2020 [cited by applicant]
Charlin et al., A Framework for Optimizing Paper Matching; In Proceedings of the Twenty-Seventh Conference on Uncertainty in Artificial Intelligence (UAI'11). AUAI Press, Arlington, Virginia, USA; 2011; Total pp. 10 (Ye… [cited by examiner]
Yang et al., Unsupervised Text Style Transfer using Language Models as Discriminators; arXiv:1805.11749v1 [cs.CL] May 30, 2018; Total pp. 13 (Year: 2018). [cited by examiner]
“U.S. Appl. No. 16/220,518, Non Final Office Action mailed Aug. 27, 2021”, 15 pgs. [cited by applicant]
“U.S. Appl. No. 16/220,518, Notice of Allowance mailed Dec. 3, 2021”, 6 pgs. [cited by applicant]
“U.S. Appl. No. 16/220,518, Preliminary Amendment filed Nov. 5, 2019”, 8 pgs. [cited by applicant]
“U.S. Appl. No. 16/220,518, Response filed Nov. 9, 2021 to Non Final Office Action mailed Aug. 27, 2021”, 9 pgs. [cited by applicant]
“International Application Serial No. PCT/US2019/066244, International Preliminary Report on Patentability mailed Jun. 24, 2021”, 9 pgs. [cited by applicant]
“International Application Serial No. PCT/US2019/066244, International Search Report mailed May 4, 2020”, 5 pgs. [cited by applicant]
“International Application Serial No. PCT/US2019/066244, Written Opinion mailed May 4, 2020”, 7 pgs. [cited by applicant]
“Natural Language Toolkit”, https://www.nltk.org/, 2 pgs. [cited by applicant]
“Stanford Log-linear Part-Of-Speech Tagger”, https://nlp.stanford.edu/software/tagger.html, 18 pgs. [cited by applicant]
Toutanova, Kristina, et al., “Enriching the Knowledge Sources Used in a Maximum Entropy Part-of-Speech Tagger”, Proceedings of the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Lar… [cited by applicant]
Toutanova, Kristina, et al., “Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network”, Proceedings of HLT-NAACL, (2003), 252-259. [cited by applicant]