US-20260127638-A1 - MACHINE LEARNING BASED APPROACH FOR OPTIMIZING TARGETED MESSAGING BASED ON PERSONA CLUSTER IN AN ENTERPRISE APPLICATION

Abstract

Methods, system, and non-transitory processor-readable storage medium for email targeting system are provided herein. An example method includes receiving by an email server system, from an email client system, an email campaign intended for a plurality of recipients. The email targeting system categorizes each of the plurality of recipients into recipient behavior classifications based on previous recipient behavior responding to previous email campaigns. The email targeting system generates a personalized templated email communication for each of recipient behavior classifications, to replace the email campaign, where the email targeting system uses the email campaign, a large language model, and the recipient behavior classifications to generate the personalized templated email.

Inventors

• Abhishek Mishra
• Dev Kathuria
• David Sydow
• Vivek Bhargava
• Ajith Navada

Assignees

• DELL PRODUCTS L.P.

Dates

Publication Date

20260507

Application Date

20241105

Claims (20)

1. 1 . A method comprising: intercepting, in real-time by distributed email targeting system architecture, by an email server system, from an email client system, an email campaign intended for a plurality of recipients before transmission to the recipients wherein the intercepting comprises monitoring email transmission queues and redirecting identified email campaigns to the email targeting system while maintaining original transmission timing parameters; categorizing, by an email targeting system executing machine learning algorithms in real-time during the interception process, each of the plurality of recipients into recipient behavior classifications based on previous recipient behavior responding to previous email campaigns wherein the categorizing comprises executing machine learning algorithms that analyze behavioral patterns and generate classifications, wherein the categorizing comprises compiling user data including geographic location data and average email reading time associated with the previous email campaigns; dynamically generating, by the email targeting system in real-time during a single intercept-analyze-generate cycle, a personalized templated email communication for each of recipient behavior classifications, to replace the email campaign, wherein the email targeting system simultaneously uses the email campaign, a large language model, and the recipient behavior classifications to generate the personalized templated email communication, wherein the dynamically generating comprises: providing the large language model with the email campaign; prompting the large language model to generate a more concise email campaign; prompting the large language model to generate a more verbose email campaign; prompting the large language model to generate a strongly worded email header for the email campaign; and prompting the large language model to generate a general email header for the email campaign; and transmitting the personalized templated email communications to the recipients within a predetermined time threshold of the original email campaign transmission schedule, wherein the method is performed by at least one processing device comprising a processor coupled to a memory and wherein the email targeting system comprises distributed processing components including a real-time interception module, a behavioral analysis engine, and a large language model interface that operate concurrently.
2. 2 . The method of claim 1 wherein the previous recipient behavior is associated with the plurality of recipients.
3. 3 . The method of claim 1 wherein intercepting in real-time by the email server system, from the email client system, the email campaign comprises: monitoring email transmission queues in real-time; identifying email campaigns based on predetermined criteria before transmission initiation; and redirecting identified email campaigns to the email targeting system for processing while maintaining original transmission timing parameters.
4. 4 . The method of claim 1 wherein categorizing, by the email targeting system, each of the plurality of recipients into the recipient behavior classifications comprises: compiling, by the email targeting system, message analytics, wherein the message analytics comprise at least one of read receipts and sent receipts associated with the previous email campaigns.
5. 5 . The method of claim 1 wherein categorizing, by the email targeting system, each of the plurality of recipients into the recipient behavior classifications comprises: compiling, by the email targeting system, user data, wherein the user data comprises at least one of geographic location data and average email reading time associated with the previous email campaigns.
6. 6 . The method of claim 1 wherein categorizing, by the email targeting system, each of the plurality of recipients into the recipient behavior classifications comprises: identifying, by the email targeting system, unique footprints in metadata associated with the previous email campaigns.
7. 7 . The method of claim 1 wherein categorizing, by the email targeting system, each of the plurality of recipients into the recipient behavior classifications comprises: compiling, by the email targeting system, historical data associated with the previous email campaigns.
8. 8 . The method of claim 1 wherein categorizing, by the email targeting system, each of the plurality of recipients into the recipient behavior classifications comprises: categorizing the plurality of recipients according to at least one of an opening classification and a reading classification.
9. 9 . The method of claim 1 wherein categorizing, by the email targeting system, each of the plurality of recipients into the recipient behavior classifications comprises: categorizing, by the email targeting system, the plurality of recipients according to an opening classification, wherein the opening classification indicates how likely a recipient is to open an email relative to other recipients, wherein the opening classification comprises a mostly-ignores-email classification, a sometimes-ignores-email classification, and a usually-opens-email classification.
10. 10 . The method of claim 9 further comprising: for each email in a plurality of email campaigns received by a recipient, wherein the plurality of recipients comprises the recipient: determining whether the recipient opened the each email; determining a percentage of opened emails for recipients receiving email from the plurality of email campaigns, based on geographical data associated with the recipient; determining how much time the recipient spent reading the each email; determining an average time spent reading the each email by the recipients receiving email from the plurality of email campaigns; and recording a non-opened-email value if the recipient did not open the each email.
11. 11 . The method of claim 10 further comprising: classifying the recipient as having ignored the each email based on whether the recipient opened the each email and the percentage of opened emails for the recipients receiving email from the plurality of email campaigns, based on the geographical data associated with the recipient.
12. 12 . The method of claim 10 further comprising: classifying the recipient in one of the opening classifications based on whether the recipient opened the each email and the percentage of opened emails for the recipients receiving email from the plurality of email campaigns, based on the geographical data associated with the recipient.
13. 13 . The method of claim 1 wherein categorizing, by the email targeting system, each of the plurality of recipients into the recipient behavior classifications comprises: categorizing by the email targeting system, the plurality of recipients according to a reading classification, wherein the reading classification indicates how much time a recipient typically spends reading an email relative to other recipients, wherein the reading classification comprises a minimal time reading classification, an average time reading classification, and an extra time reading classification.
14. 14 . The method of claim 13 wherein categorizing by the email targeting system, the plurality of recipients according to a reading classification comprises: determining a standard deviation associated with the recipient's reading time for the each email in a plurality of email campaigns opened by the recipient; and classifying the recipient into the reading classification according to the standard deviation.
15. 15 . (canceled)
16. 16 . The method of claim 1 further comprising: for each recipient in the plurality of recipient categorized by the email targeting system with an opening classification of mostly-ignores-email classification, append the strongly worded email header; and for each recipient in the plurality of recipient categorized by the email targeting system with an opening classification of sometimes-ignores-email classification, or usually-opens-email classification, append the general email header.
17. 17 . The method of claim 1 further comprising: for each recipient in the plurality of recipient categorized by the email targeting system with a reading classification of minimal time reading classification, append the more concise email campaign; and for each recipient in the plurality of recipient categorized by the email targeting system with a reading classification of extra time reading classification, append the more verbose email campaign.
18. 18 . The method of claim 1 further comprising: transmitting, by the email targeting system, the personalized templated email communications back to the email client system for review by at least one author of the email campaign.
19. 19 . A system comprising: at least one processing device comprising a processor coupled to a memory; the at least one processing device being configured: to intercept, in real-time by distributed email targeting system architecture, by an email server system, from an email client system, an email campaign intended for a plurality of recipients before transmission to the recipients wherein the intercepting comprises monitoring email transmission queues and redirecting identified email campaigns to the email targeting system while maintaining original transmission timing parameters; to categorize, by an email targeting system executing machine learning algorithms in real-time during the interception process, each of the plurality of recipients into recipient behavior classifications based on previous recipient behavior responding to previous email campaigns wherein the categorizing comprises executing machine learning algorithms that analyze behavioral patterns and generate classifications, wherein the categorizing comprises compiling user data including geographic location data and average email reading time associated with the previous email campaigns; to dynamically generate, by the email targeting system in real-time during a single intercept-analyze-generate cycle, a personalized templated email communication for each of recipient behavior classifications, to replace the email campaign, wherein the email targeting system simultaneously uses the email campaign, a large language model, and the recipient behavior classifications to generate the personalized templated email communication, wherein the dynamically generating comprises: providing the large language model with the email campaign; prompting the large language model to generate a more concise email campaign; prompting the large language model to generate a more verbose email campaign; prompting the large language model to generate a strongly worded email header for the email campaign; and prompting the large language model to generate a general email header for the email campaign; and to transmit the personalized templated email communications to the recipients within a predetermined time threshold of the original email campaign transmission schedule, wherein the email targeting system comprises distributed processing components including a real-time interception module, a behavioral analysis engine, and a large language model interface that operate concurrently.
20. 20 . A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes said at least one processing device: to intercept, in real-time by distributed email targeting system architecture, by an email server system, from an email client system, an email campaign intended for a plurality of recipients before transmission to the recipients wherein the intercepting comprises monitoring email transmission queues and redirecting identified email campaigns to the email targeting system while maintaining original transmission timing parameters; to categorize, by an email targeting system executing machine learning algorithms in real-time during the interception process, each of the plurality of recipients into recipient behavior classifications based on previous recipient behavior responding to previous email campaigns wherein the categorizing comprises executing machine learning algorithms that analyze behavioral patterns and generate classifications, wherein the categorizing comprises compiling user data including geographic location data and average email reading time associated with the previous email campaigns; to dynamically generate, by the email targeting system in real-time during a single intercept-analyze-generate cycle, a personalized templated email communication for each of recipient behavior classifications, to replace the email campaign, wherein the email targeting system simultaneously uses the email campaign, a large language model, and the recipient behavior classifications to generate the personalized templated email communication, wherein the dynamically generating comprises: providing the large language model with the email campaign; prompting the large language model to generate a more concise email campaign; prompting the large language model to generate a more verbose email campaign; prompting the large language model to generate a strongly worded email header for the email campaign; and prompting the large language model to generate a general email header for the email campaign; and to transmit the personalized templated email communications to the recipients within a predetermined time threshold of the original email campaign transmission schedule, wherein the email targeting system comprises distributed processing components including a real-time interception module, a behavioral analysis engine, and a large language model interface that operate concurrently.

Description

FIELD The field relates generally to optimizing email campaigns by optimizing and targeting the messaging. BACKGROUND Large enterprise companies typically receive various types of communications that are daily sent either for internal communication or is intended for customer communication. SUMMARY Illustrative embodiments provide techniques for implementing an email targeting system in a storage system. For example, in illustrative embodiments, an email server system receives from an email client system, an email campaign intended for a plurality of recipients. An email targeting system categorizes each of the plurality of recipients into recipient behavior classifications based on previous recipient behavior responding to previous email campaigns. The email targeting system generates a personalized templated email communication for each of recipient behavior classifications, to replace the email campaign, where the email targeting system uses the email campaign, a large language model, and the recipient behavior classifications to generate the personalized templated email communication. Other types of processing devices can be used in other embodiments. These and other illustrative embodiments include, without limitation, apparatus, systems, methods and processor-readable storage media. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 shows an information processing system including an email targeting system, in an illustrative embodiment. FIG. 2 shows a flow diagram of a process for an email targeting system, in an illustrative embodiment. FIG. 3 illustrates an email delivery report, in an illustrative embodiment. FIG. 4 illustrates business unit email delivery report, in an illustrative embodiment. FIG. 5 illustrates a demography email report, in an illustrative embodiment. FIG. 6 illustrates an email open rate report, in an illustrative embodiment. FIGS. 7 and 8 show examples of processing platforms that may be utilized to implement at least a portion of an email targeting system embodiments. DETAILED DESCRIPTION Illustrative embodiments will be described herein with reference to exemplary computer networks and associated computers, servers, network devices or other types of processing devices. It is to be appreciated, however, that these and other embodiments are not restricted to use with the particular illustrative network and device configurations shown. Accordingly, the term “computer network” as used herein is intended to be broadly construed, so as to encompass, for example, any system comprising multiple networked processing devices. Described below is a technique for use in implementing an email targeting system, which technique may be used to generate targeted messaging for recipients of an email campaign. An email server system receives from an email client system, an email campaign intended for a plurality of recipients. An email targeting system categorizes each of the plurality of recipients into recipient behavior classifications based on previous recipient behavior responding to previous email campaigns. The email targeting system generates a personalized templated email communication for each of recipient behavior classifications, to replace the email campaign, where the email targeting system uses the email campaign, a large language model, and the recipient behavior classifications to generate the personalized templated email communication. Prior to sending out email campaigns, there are validations processes such as proof reading, localization, and message content review that need to be completed. In addition, there are major stakeholders involved in the end-to-end process. These stakeholders include the marketing and communication teams, who are responsible for content generation and review, the communication development team who is responsible for triggering the communication, and the end-user (i.e., the recipient) who will receive the email campaign. The most critical problem that can hinder the generation of succinct, relevant, and targeted email campaigns is that there are many siloed layers of approval and guidelines required for content generation. For example, the addition of company messaging templates and guidelines (color schemes, font, verbiage, etc.) into the communication, and the generation of layered user context may have thousands of patterns that require the right content to be sent according to specific behavior patterns for a user. Conventional technologies that manually create and maintain mass emailing lists are not scalable and lead to cluttered inboxes for the recipients, with the possibility that the email recipients will ignore potentially relevant and important emails. Conventional technologies that send out email campaigns do not target email campaigns based on the previous recipient behavior to prior email campaigns. Conventional technologies do not provide a machine learning based approach for identifying and rating critical messaging and verbiage in a messagin