Notification Timing Prediction Using ML for Higher User Interaction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional content transmission systems often fail to effectively serve their purpose due to fixed or random delivery methods, leading to low interaction rates with users.

Innovation Solution

Utilizing machine learning to predict optimal transmission times based on individual user characteristics, such as age and device usage patterns, to improve the likelihood of user interaction with notifications or content.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If machine learning is used to predict optimal transmission times, then user interaction probability is improved, but device complexity increases

Engineering Contradiction:

Improveuser interaction probabilityVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

A machine learning model is introduced as an intermediary component between the content transmission system and user characteristics data. The model processes user characteristics (age, device usage patterns) and predicts optimal transmission times, thereby improving interaction probability without requiring the entire system to become complex - only the prediction module needs the ML capability.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The conventional mechanical approach of fixed or random transmission scheduling is replaced with an intelligent prediction system. Instead of using simple timers or random generators, the patent substitutes a machine learning model that learns from historical data to predict optimal transmission moments, achieving higher reliability through data-driven decisions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If notifications are transmitted more frequently to ensure user engagement, then interaction probability is improved, but network resource consumption increases

Engineering Contradiction:

Improveuser engagementVSAvoidnetwork resource consumption

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The system performs preliminary analysis of user characteristics and historical interaction data to predict the optimal moment for transmission before actually sending the notification. By preparing the transmission timing in advance based on learned patterns, the system avoids both premature and delayed transmissions, ensuring engagement while minimizing unnecessary network resources consumption.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent changes the parameter of transmission timing from fixed or random values to dynamically predicted optimal times based on user characteristics. This parameter optimization allows the system to transmit notifications at the most effective moments, improving engagement probability while reducing overall transmission frequency and associated network resource consumption.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20250384998A1Machine learning to select transmission timing

Publication Date: 2025.12.18 MANIFOLD INC

AI summary

Techniques for improved machine learning are provided. A notification to be provided to a user engaged in a therapeutic treatment is identified, and a set of user characteristics associated with the user is determined. A target time to provide the notification to the user is identified by processing the set of user characteristics using a machine learning model, and the notification is transmitted to the user at the target time.