Notification Targeting via Downstream User Engagement Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Content sharing platforms face challenges in effectively targeting notifications to users due to the difficulty in gauging user interest when notifications are not directly accessed through the initial device, leading to irrelevant or excessive notifications that may deter users from engaging with the platform.

Innovation Solution

The system analyzes downstream user behavior to increase affinity scores for notifications, even if the user accessed the media content item through a different device or after the notification was generated, ensuring relevant notifications are targeted based on user interest.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the system sends notifications to users about media content items, then users are informed about content availability, but users may receive excessive or irrelevant notifications that deter engagement

Engineering Contradiction:
Improvenotification relevanceVSAvoiduser disengagement
Core Design Contradiction:
ReliabilityVSObject-generated harmful factors

Solution Approach 1:

The system uses downstream user engagement behavior as feedback to adjust notification targeting. By monitoring whether users interact with media content items after receiving notifications, the system learns user preferences and refines future notification targeting, creating a closed-loop feedback mechanism that improves relevance over time

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system dynamically changes notification parameters (such as affinity scores) based on observed user engagement patterns. By adjusting these parameters according to downstream behavior, the system adapts notification delivery to match actual user interests, transforming static notification rules into dynamic, data-driven decisions

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If the system tracks user interaction with notifications on the initial device, then notification delivery can be monitored, but the system cannot accurately gauge user interest when access occurs on different devices or after notification generation

Engineering Contradiction:
Improveuser interest measurementVSAvoidcross-device tracking
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The system implements universal tracking across multiple devices and time points by monitoring downstream engagement behavior regardless of which device or when the user accesses the media content. This multi-functional approach allows the system to measure user interest universally, not just within the constraints of a single device or immediate notification interaction

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

Solution Approach 2:

The system shifts from tracking only direct notification interactions (single dimension) to monitoring downstream engagement behavior across multiple dimensions including different devices, time periods, and interaction types. This dimensional expansion enables comprehensive user interest measurement beyond the initial notification context

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentEP3289786B1Notification targeting based on downstream user engagement
Publication Date: 2021.05.26 GOOGLE LLC
  • EP3289786B1 patent drawingFigure 1
  • EP3289786B1 patent drawingFigure 2
  • EP3289786B1 patent drawingFigure 3

AI summary

A notification that has been generated for a user may be identified. The notification may pertain to a media content item. A determination may be made as to whether the user interacted with the media content item, and a further determination may be made as to whether the user has interacted with the notification. In response to determining that the user has interacted with the media content item and has not interacted with the notification pertaining to the media content item, an affinity score of the user with respect to the notification may be calculated. A condition associated with providing a subsequent notification to the user may be determined based on the affinity score of the user.