Automated Linguistic Personalization for Marketing Campaigns

Solution Overview

Problem

Manual production of multiple personalized advertising messages for different audience segments is resource-intensive and time-consuming, requiring significant effort and expense in conventional techniques.

Innovation Solution

Techniques for linguistic personalization involve extracting dependencies between keywords and modifiers from segment-specific and product-specific texts to build language models, identifying transformation points, and inserting modifiers into a message skeleton to create personalized messages for targeted marketing campaigns.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If manual production of multiple personalized advertising messages is used, then message personalization quality is improved, but time consumption and resource expenditure increase significantly

Engineering Contradiction:

Improvemessage personalization qualityVSAvoidtime consumption

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical message production with an automated computational system that uses language models to generate personalized messages. The system extracts dependencies between keywords and modifiers from segment-specific texts, builds language models, and automatically generates personalized messages without human intervention, thereby eliminating the time-consuming manual process while maintaining personalization quality

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the parameters of message generation by using statistical language models that process textual data at a computational level. Instead of manual crafting, the system uses probabilistic language models trained on segment-specific texts to automatically generate messages, transforming the generation process from manual to automated while preserving the personalized characteristics

Inventive Principle:

Principle #35Parameter changes

2Manufacturing precision

If manual production of multiple personalized advertising messages is used, then message personalization quality is improved, but resource expenditure increases significantly

Engineering Contradiction:

Improvemessage personalization qualityVSAvoidresource expenditure

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The patent replaces manual mechanical message production with an automated computational system that uses language models to generate personalized messages. The system extracts dependencies between keywords and modifiers from segment-specific texts, builds language models, and automatically generates personalized messages without human intervention, thereby eliminating the time-consuming manual process while maintaining personalization quality

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-service by automatically extracting dependencies, building language models, and generating personalized messages without requiring manual human effort. The computational system serves itself by processing segment-specific texts and product-specific texts to automatically create customized messages, eliminating the need for human resources in the message production process

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS11055745B2Linguistic personalization of messages for targeted campaigns

Publication Date: 2021.07.06 ADOBE INC

AI summary

Techniques for linguistic personalization of messages for targeted campaigns are described. In one or more implementations, dependencies between keywords and modifiers are extracted, from one or more segment-specific texts and a product-specific text, to build language models for the one or more segment specific texts and the product specific text. Modifiers with a desired sentiment are extracted from the product specific text and transformation points are identified in a message skeleton. Then one or more of the extracted modifiers are inserted to modify one or more identified keywords in the message skeleton to create a personalized message for a target segment of the targeted marketing campaign.