Treatment Recommendation Engine Using Embeddings for Personalized Display

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Businesses fail to effectively engage consumers on digital platforms due to a lack of personalized interaction based on consumer data analysis, resulting in inefficient communication strategies.

Innovation Solution

A system utilizing a treatment selection engine that employs machine learning techniques to analyze user data and generate personalized treatment recommendations, including the use of deep learning and transformer models to create user and treatment embeddings, which are then scored for likelihood of user engagement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If businesses use standardized templated emails and notifications for all consumers, then the implementation complexity and cost are reduced, but consumer engagement and personalization effectiveness deteriorate

Engineering Contradiction:

Improveease of treatment implementationVSAvoidpersonalization effectiveness

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The system dynamically selects treatments based on real-time analysis of consumer data, user behavior patterns, and contextual factors. The treatment selection engine continuously adapts the type, timing, and content of communications to match individual consumer preferences and behaviors, transforming static templated approaches into dynamic personalized interactions without requiring manual customization for each consumer

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system automatically generates and selects appropriate treatments for each consumer without human intervention. The treatment selection engine autonomously processes consumer data, evaluates multiple treatment options, and determines the optimal treatment to deliver, enabling the business to scale personalized communications without proportionally increasing operational complexity or costs

Inventive Principle:

Principle #25Self-service

2Productivity

If businesses analyze consumer data to create personalized treatments, then consumer engagement and treatment effectiveness are improved, but system complexity and computational requirements increase

Engineering Contradiction:

Improveconsumer engagement effectivenessVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system segments consumer data into distinct features and characteristics that can be independently analyzed. The treatment selection engine breaks down complex consumer profiles into manageable data elements such as purchase history, browsing behavior, demographic attributes, and engagement patterns, allowing for systematic processing and evaluation of multiple treatment options based on specific consumer segments

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The treatment selection engine serves as an intermediary layer between raw consumer data and treatment delivery. This intermediary component processes, analyzes, and transforms complex consumer data into actionable treatment selections, shielding the rest of the system from direct complexity while enabling data-driven personalization through structured data processing and treatment evaluation

Inventive Principle:

Principle #24Intermediary (Mediator)

3Ease of operation

If businesses send treatments at predetermined intervals to all consumers, then the operational process is simplified, but treatment timing optimization and consumer response rates deteriorate

Engineering Contradiction:

Improveoperational simplicityVSAvoidtreatment timing optimization

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system changes the timing parameter of treatment delivery based on individual consumer characteristics and behavior patterns. Instead of using fixed predetermined intervals for all consumers, the treatment selection engine dynamically adjusts when treatments are delivered to each consumer based on their optimal response times, engagement patterns, and contextual factors, maximizing treatment effectiveness while maintaining automated operational simplicity

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20260073292A1Systems And Methods for Automatic Treatment Recommendation For Digital Platform Display Using Machine Learning Techniques

Publication Date: 2026.03.12 AUXIA INC

AI summary

Disclosed herein is a computerized method including operations of obtaining user attributes and user event data, generating user embeddings and aggregated user features from the user event data and the user attributes, obtaining treatment attributes and a set of treatments corresponding to the treatment attributes, generating treatment embeddings and aggregated treatment features from the set of treatments and the treatment attributes, and generating a trained machine learning model by processing the user embeddings, the aggregated user features, the treatment embeddings, and the aggregated treatment features by a machine learning algorithm, wherein the trained machine learning machine is configured to generate a score for each treatment of the set of treatments indicative of a likelihood that serving of a particular treatment will result in performance of an objective. The user event data may include event sequence data indicating a sequence of user input actions corresponding to one or more treatments.