Multi-objective Notification Ranking System for Message Prioritization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional notification systems fail to optimize message delivery effectively across multiple sources due to independent spacing algorithms and priority scoring systems that do not account for messages from other systems, leading to overwhelming recipients and prioritization issues.

Innovation Solution

Implementing a multi-objective notification ranking system that analyzes notification events from multiple sources using machine-learned models to assign scores based on desired performance objectives, determining whether to send, queue, or drop messages, and routing them based on priority, thereby optimizing delivery across systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If independent notification systems send messages based on their own spacing algorithms, then each system can optimize its message delivery, but recipients receive too many notification messages and become overwhelmed

Engineering Contradiction:
Improvenotification delivery efficiencyVSAvoidmessage overload to recipients
Core Design Contradiction:
ProductivityVSObject-affected harmful factors

Solution Approach 1:

The patent combines multiple independent notification systems into a unified notification system that centrally manages message delivery. The unified system aggregates notification events from multiple sources, applies a single multi-objective optimization algorithm, and coordinates message timing across all sources to prevent overwhelming recipients while maintaining delivery efficiency.

Inventive Principle:
Principle #5Merging (Combining)

2Productivity

If independent notification systems prioritize messages based on their own scoring systems, then each system can optimize its message selection, but the recipient does not receive the overall highest priority messages

Engineering Contradiction:
Improvemessage selection efficiencyVSAvoidpriority information accuracy
Core Design Contradiction:
ProductivityVSLoss of information

Solution Approach 1:

The patent implements a universal priority scoring mechanism that handles multiple objectives simultaneously. The multi-objective optimization algorithm evaluates messages against multiple criteria (engagement likelihood, user preferences, timing) and produces a single prioritized ranking that reflects overall message importance, enabling the system to select the highest priority messages across all notification sources.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Ease of operation

If notification systems use separate spacing algorithms, then each system can independently control message timing, but the spacing algorithms are not effective when systems are unaware of each other's messages

Engineering Contradiction:
Improveindependent system operationVSAvoidspacing algorithm effectiveness
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent introduces a central notification management system that acts as an intermediary between multiple notification sources. This intermediary receives notification events from all sources, applies coordinated spacing logic that considers messages from all systems, and schedules message delivery to optimize timing while preventing recipient overload. The intermediary maintains awareness of all incoming messages and adjusts spacing dynamically.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS10977096B1Multi-objective, multi-input, efficient decoupling holistic platform for communication selection
Publication Date: 2021.04.13 MICROSOFT TECHNOLOGY LICENSING LLC
  • US10977096B1 patent drawing
  • US10977096B1 patent drawing
  • US10977096B1 patent drawing

AI summary

Technologies for determining whether to send notification messages, from different sources, to a target user are provided. The disclosed techniques include receiving a first notification event from a first notification service and receiving a second notification event from a second notification service. The first and second notification services are different services. Using a machine-learned model to assign a first score to the first notification event and a second score to the second notification event. Based on the first score, a determination is made to generate a first notification message for the first notification event. The first notification message is then sent to a target user. Based on the second score, a determination is made not to generate a second notification message for the second notification event.