Social Affinity Computation via Weighted Graph Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to effectively compute and utilize numeric affinity scores between social connections on online platforms, which are crucial for improving information retrieval and search result ranking based on social relationships.
Innovation Solution
The method involves creating a weighted graph structure from public social data using XFN or FOAF markup, cleaning the graph to remove errors, and calculating affinity scores through various measures such as path length, edge weights, and vertex importance to determine the strength of social connections between users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If social connection data is collected from multiple public social sites using markup annotations, then the quantity of social connection information is improved, but the complexity of processing and computing affinity scores increases
Solution Approach 1:
The patent segments the social connection data processing by creating a structured weighted graph representation where social connections are divided into discrete edges with specific weights, and users are represented as distinct vertices. This segmentation allows the system to handle large quantities of social data from multiple sources by breaking it down into manageable graph components that can be processed systematically for affinity score computation.
2Measurement precision
If all social connection paths between user pairs are explored to compute affinity scores, then the precision of social affinity measurement is improved, but the computational time and resources increase
Solution Approach 1:
The patent applies parameter changes by assigning different weights to various types of social connections (e.g., direct friends versus friends of friends) and by transforming the exploration of all paths into a weighted graph computation problem. This allows the system to compute affinity scores by evaluating path weights rather than exhaustively analyzing each connection path, significantly reducing computational time while maintaining measurement precision through the weighted aggregation of multiple connection paths.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on computer storage devices, for determining social affinities from public data. In one aspect, a method computes numeric affinity scores or weights between pairs of network identities, e.g., identities made public by users of social web sites on the Internet, where the pairs of identities appear to represent pairs of individual people, using explicit and inferred social connections obtained from public user data on the Internet. Some of the system and methods explore all social connections (paths) between any given pair of vertices X and Y in the weighted graph data structure of such social connections and aggregates information about their number and relative strength to produce the affinity score from X to Y.