Ad Selection Using Subject Individual Representations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current web advertising technologies fail to effectively present targeted advertisements that leverage user interactions and trust relationships within social media platforms, leading to suboptimal engagement and relevance.
Innovation Solution
The system generates and displays advertisements featuring 'subject individuals' – friends and contributors – selected based on user interaction history, authoritativeness, and relevance, using a combination of databases and engines to compute user scores and ranks, ensuring that advertisements are more engaging and relevant to the target user.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional advertising ranking methods are used (based on bid eCPM and user scores), then advertising revenue can be generated, but user engagement and conversion rates remain suboptimal due to lack of personalization and trust factors
Solution Approach 1:
The patent segments the advertising system into multiple independent components: bid eCPM calculation module, user score calculation module, subject individual identification module, and advertisement selection module. Each module processes specific aspects independently, allowing the system to incorporate complex social media data and trust relationships without creating a monolithic complex system. This segmentation enables incremental implementation and maintenance of advertising effectiveness while managing system complexity.
Solution Approach 2:
The patent introduces subject individuals (friends and contributors) as intermediaries between advertisers and target users. These intermediaries serve as trust mediators whose interactions with advertisements influence the selection and presentation of ads. By incorporating these intermediary elements, the system enhances advertising effectiveness through social proof and trust relationships without directly complicating the core advertising delivery mechanism.
2Reliability
If advertisements include representations of subject individuals (friends and contributors), then user trust and engagement improve, but data processing and advertisement generation complexity increases
Solution Approach 1:
The patent performs preliminary actions by pre-identifying and ranking subject individuals (friends and contributors) based on their interactions with advertisements before the actual advertising delivery. User scores and subject individual rankings are calculated in advance, allowing the system to quickly select appropriate advertisements with representations during real-time operations. This preliminary processing reduces the complexity burden during critical ad delivery moments while maintaining high user trust through personalized content.
Solution Approach 2:
The patent uses representations (copies) of subject individuals such as profile pictures, names, or icons in advertisements rather than requiring full user data or direct user involvement. These simplified copies convey the trust and engagement benefits of featuring real users while minimizing data processing complexity and privacy concerns. The representation approach allows the system to leverage social relationships without the overhead of managing complete user profiles or obtaining extensive permissions.
3Measurement precision
If the system processes extensive user interaction data from social media platforms, then advertisement targeting precision improves, but computational requirements and processing time increase
Solution Approach 1:
The patent applies partial action by selectively processing only the most relevant user interaction data from social media platforms. Rather than analyzing all available data, the system focuses on key metrics such as advertisement interactions, friend relationships, and contributor ratings that directly impact targeting precision. This selective approach maintains high measurement precision for advertisement targeting while significantly reducing computational requirements and processing time compared to comprehensive data analysis.
Solution Approach 2:
The patent transforms complex social media interaction data into simplified scoring parameters (user scores, subject individual rankings, bid eCPM values) that can be efficiently processed and compared. By changing the parameter representation from raw interaction data to aggregated scores, the system achieves precise advertisement targeting through mathematical calculations rather than complex pattern recognition, thereby reducing computational time and resource requirements while maintaining or improving targeting accuracy.
Data Source
AI summary
Advertisements are generated and selected for display to users, wherein the advertisements include representations of subject individuals. These subject individuals can be friends with whom the user interacts on the Internet and/or any other contributors who may or may not have expertise with regard to the subject matter of the advertisement. A subject individual can be portrayed in an advertisement by including any type of representation of the individual.Ranks for the subject individuals are determined based on the subject individuals' interactions with advertisements and/or on other factors. An advertisement is selected and presented to a user based on a score derived from friends' and/or contributors' interactions with the advertisement. According to various embodiments of the invention, a method is provided for choosing which advertisement(s) to show to a user and which subject individuals to portray in the advertisements.