Website Rating System for Safe Advertising Placement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current advertising networks lack efficient methods to identify and control the placement of advertisements on websites containing objectionable content, leading to misalignment of brand image and advertising goals.
Innovation Solution
A system and method for rating websites based on probabilistic scores that assess the likelihood of containing objectionable content, using a combination of evidentiary sources and rating models to generate risk ratings, allowing for targeted and safe advertising.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If advertising networks use traditional ad-placement methods, then ad delivery is simple and fast, but brand safety is compromised due to inability to identify objectionable content
Solution Approach 1:
The system performs preliminary rating of websites and webpages before ad placement by analyzing multiple evidentiary sources and generating risk ratings in advance. This allows advertisers to pre-identify safe publishing venues, eliminating the need for complex real-time safety checks during ad delivery while maintaining brand safety.
Solution Approach 2:
The patent introduces an intermediary rating system that sits between the advertising network and publisher inventory. This rating application acts as a mediator that translates website content into standardized risk ratings, simplifying the ad-placement process by providing a clear safety metric without requiring advertisers to directly analyze content themselves.
2Measurement precision
If advertisers implement comprehensive content control, then brand appropriateness is ensured, but ad delivery efficiency decreases due to extensive content analysis requirements
Solution Approach 1:
The system pre-computes risk ratings for websites and webpages by analyzing multiple evidentiary sources before ad placement decisions are made. This preliminary assessment stores safety information in advance, allowing rapid ad delivery without repeating complex content analysis for each ad request.
Solution Approach 2:
The patent combines multiple evidentiary sources and rating models into a unified risk rating system. By merging diverse content signals into a single composite safety score, the system achieves comprehensive content assessment accuracy while simplifying the decision-making process and maintaining fast ad delivery speeds.
3Measurement precision
If multiple evidentiary sources are analyzed for each webpage, then rating accuracy improves, but processing time and computational resources increase
Solution Approach 1:
The system performs content analysis and generates risk ratings in advance before ad placement is needed. By pre-processing and storing rating information from multiple evidentiary sources, the system eliminates the need for time-consuming real-time analysis during ad delivery, maintaining both accuracy and speed.
Solution Approach 2:
The patent applies different levels of analysis depth to different websites based on their risk profiles. High-risk sites receive more intensive multi-source verification, while low-risk sites receive streamlined assessment. This localized quality approach maintains rating accuracy for problematic content while reducing processing time for safe content.
Data Source
AI summary
Systems, methods, and media for rating websites for safe advertising are provided. In accordance with some embodiments of the disclosed subject matter, the method comprises: receiving a uniform resource locator corresponding to a webpage; selecting a plurality of evidentiary sources for obtaining evidence relating to the uniform resource locator, wherein each piece of evidence corresponds to one of the plurality of evidentiary sources; converting each piece of evidence obtained from the plurality of evidentiary sources into a plurality of instances that describe the webpage; applying the plurality of instances to a plurality of rating models, wherein each of the plurality of rating models generates an ordinomial and wherein the ordinomial encodes a probability of membership in one or more severity classes of a category; combining the ordinomial from each of the plurality of rating models into a combined ordinomial probability estimate; and generating a rating for the webpage based at least in part on the combined ordinomial probability estimate, wherein the rating identifies whether the webpage is likely to contain objectionable content of the category.