Predicted Viewing Time Ad Selection for User Recall

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional online systems prioritize sponsored content selection based on interaction likelihood, limiting the presentation of sponsored content to users who may view it for extended periods without interacting, thereby reducing the effectiveness of advertising revenue generation.

Innovation Solution

An online system selects advertisements for presentation based on predicted viewing time, using models that analyze user characteristics and past viewing durations to identify optimal ad placement, increasing the likelihood of user recall and subsequent action.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If conventional online systems select sponsored content based on interaction likelihood, then the number of users capable of providing compensation increases, but the effectiveness of advertising revenue generation decreases due to limited presentation to users who may view content for extended periods without interacting

Engineering Contradiction:

Improveadvertising revenue generation effectivenessVSAvoidsponsored content selection criteria

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent changes the selection parameter from interaction likelihood to predicted viewing duration. The system calculates expected viewing time based on user characteristics and content attributes, then selects sponsored content that maximizes viewing duration within a threshold range. This parameter change directly addresses the contradiction by shifting focus from immediate interaction to sustained viewing, thereby improving revenue effectiveness while expanding content selection versatility.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system dynamically adjusts sponsored content selection by continuously evaluating predicted viewing durations and updating selections based on user behavior patterns. The selection process is not static but adapts to individual user characteristics and contextual factors, allowing the system to optimize for both revenue effectiveness and content diversity simultaneously.

Inventive Principle:

Principle #15Dynamics

2Quantity of substance

If online systems present sponsored content to maximize interaction, then compensation from users who interact increases, but revenue from users who view content for long periods without interacting is lost

Engineering Contradiction:

Improvetotal compensation receivedVSAvoidrevenue generation reliability

Core Design Contradiction:

Quantity of substanceVSReliability

Solution Approach 1:

The system incorporates feedback loops where actual viewing durations are measured and used to refine predicted viewing duration models. This feedback mechanism allows the system to learn from real user behavior, improving the accuracy of predictions and thereby increasing both the quantity of compensation received and the reliability of revenue generation from non-interacting viewers.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary analysis of user characteristics and content attributes to predict viewing duration before content presentation. By pre-calculating expected viewing times and selecting content accordingly, the system proactively optimizes for both compensation quantity and revenue reliability, rather than relying solely on post-interaction data.

Inventive Principle:

Principle #10Preliminary action

3Device complexity

If sponsored content is selected based on interaction likelihood, then the selection process remains simple, but the system fails to capture value from extended viewing without interaction

Engineering Contradiction:

Improvecontent selection process complexityVSAvoidadvertising revenue effectiveness

Core Design Contradiction:

Device complexityVSProductivity

Solution Approach 1:

The patent segments the content selection process into distinct components: user characteristic analysis, content attribute evaluation, predicted viewing duration calculation, and final selection. This segmentation allows the complex process to be managed systematically while capturing value from extended viewing. Each segment can be optimized independently, balancing complexity and effectiveness.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces predicted viewing duration as an intermediary metric between user characteristics and content selection. This intermediary simplifies the decision-making process by providing a single predictive measure that captures the essence of extended viewing potential, reducing overall system complexity while improving revenue effectiveness.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS10108983B2Selecting content for presentation to an online system user to increase likelihood of user recall of the presented content

Publication Date: 2018.10.23 META PLATFORMS INC

AI summary

An online system selects content items for a user to increase probabilities of the user remembering the content items after presentation. The online system generates one or more models based on information describing amounts of time users have viewed previously presented content items. Hence, a model associated with a user predicts an amount of time the user will view a content item. When selecting content items for the user, the online system selects one or more content items that the user is predicted to view for an amount of time within a specific range, which may be based on amounts of times other users have viewed the content item or content items similar to the content item. For example, the online system increases a probability of selecting a content item the user is predicted to view for an amount of time within the specific range.