Content Item Placement in Online Documents

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional techniques for presenting online documents with embedded content items often result in a poor client experience, leading to fewer interactions and lower membership in online systems, as the placement of content items can distract users and make content difficult to follow.

Innovation Solution

An online system uses a machine learning model to evaluate the layout of augmented online documents by extracting features and generating scores based on client interactions, selecting optimal layouts for content item placement within online documents to enhance user engagement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If content items are embedded within an online document using conventional techniques, then the document includes media content items, but the client experience deteriorates due to distracting placements and difficulty following content

Engineering Contradiction:

Improvecontent items embeddedVSAvoidclient experience

Core Design Contradiction:

Quantity of substanceVSEase of operation

Solution Approach 1:

The system performs preliminary analysis of the online document structure, client preferences, and content item characteristics before embedding. It pre-determines optimal placement positions by evaluating multiple potential locations and selecting the best one, thereby avoiding distracting placements and improving client experience from the outset

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system applies different placement strategies to different regions of the online document based on local characteristics. It analyzes specific document sections, client device properties, and content item types to determine the most appropriate placement location for each content item, rather than using a uniform embedding approach

Inventive Principle:

Principle #3Local quality

2Quantity of substance

If content items are placed within online documents, then media content is provided to clients, but client interactions decrease due to poor placement causing distraction

Engineering Contradiction:

Improvecontent items providedVSAvoidclient interactions

Core Design Contradiction:

Quantity of substanceVSProductivity

Solution Approach 1:

The system implements a feedback mechanism that monitors client interactions with content items and uses this data to refine placement decisions. By analyzing interaction patterns, the system learns which placements lead to engagement and which cause distraction, continuously improving content item placement to maximize client interactions

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system pre-evaluates potential content item placements by simulating their impact on client behavior. It uses historical data and machine learning models to predict which placements will maximize interactions before actually embedding the content items, thereby improving productivity from the beginning

Inventive Principle:

Principle #10Preliminary action

3Quantity of substance

If conventional embedding techniques are used, then content items are included in documents, but user engagement and membership decrease due to difficult-to-follow content

Engineering Contradiction:

Improvecontent items includedVSAvoiduser engagement

Core Design Contradiction:

Quantity of substanceVSReliability

Solution Approach 1:

The system tailors content item placement to local document characteristics and user preferences. It analyzes the semantic content, visual layout, and reading flow of different document sections to determine optimal insertion points that maintain narrative coherence and make content easy to follow, thereby improving user engagement and retention

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system performs preliminary optimization of content placement by evaluating multiple candidate positions and selecting the one that best maintains document flow and readability. It pre-processes the document structure to identify optimal insertion points that minimize disruption to the reading experience, ensuring content is easy to follow from the outset

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS10303743B2Automatic placement of electronic media content items within an online document

Publication Date: 2019.05.28 META PLATFORMS INC

AI summary

An online system stores online documents, where each online document has a layout. The system creates augmented online documents by combining the online documents with one or more content items. The system stores client interactions with the content items, responsive to presenting the augmented online documents via a client device. The system receives a new online document. The system creates new augmented online documents by combining the new online document with one or more new content items. For each new augmented online document, the system generates a score based on one or more features describing the layout of the new augmented online document. The system selects a new augmented online document based on the generated scores and sends the selected new augmented online document for presentation via a client device.