Graph-Based Contact Suggestion Ranking Using Shared Time Weights
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for generating contact suggestions in social networks are limited in their ability to provide relevant suggestions, as they do not effectively account for the amount of time users spend together, leading to inefficient user interaction and connection requests.
Innovation Solution
A system that builds a user graph based on relationship weights, including the amount of time users spend together, and uses a machine learning model to rank contact suggestions, predicting the probability of a user sending a connection request, thereby optimizing the display of contact suggestions on a user interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional methods are used to generate contact suggestions, then the system is simple to implement, but the relevance of contact suggestions deteriorates
Solution Approach 1:
The system segments the contact suggestion generation process into multiple components: building a user graph from social network data, computing first scores using graph algorithms, and computing second scores using machine learning models. This segmentation allows each component to specialize in specific tasks, improving overall suggestion relevance while managing system complexity through modular architecture.
Solution Approach 2:
The system performs preliminary actions by pre-building a user graph that captures relationships between users before generating contact suggestions. This pre-computed graph structure with weighted edges representing interaction strength provides a foundation for more accurate suggestion ranking, improving relevance without repeating computationally intensive operations during suggestion generation.
2Manufacturing precision
If time spent together is incorporated into relationship weights, then contact suggestion relevance improves, but computational complexity increases
Solution Approach 1:
The system changes parameters by incorporating time spent together as a weighting factor in the user graph edges. Instead of treating all social relationships equally, the system assigns different weights based on interaction duration, which improves the accuracy of contact suggestions by prioritizing users with stronger temporal relationships while managing computational load through efficient graph algorithms.
3Manufacturing precision
If machine learning models are used to rank contact suggestions, then suggestion quality improves, but processing time increases
Solution Approach 1:
The system extracts and separates the machine learning scoring component from the overall contact suggestion pipeline. By computing second scores using ML models independently from the graph-based first scores, the system can optimize each component separately, using approximate nearest neighbor search and other efficient techniques to reduce processing time while maintaining suggestion quality.
Data Source
AI summary
Methods, systems, and devices for generating contact suggestions for a user of a social network. A first score is computed for each one of the plurality of users, the first score being computed using an edge-weighted ranking algorithm based on the user graph. A second score is computed, using a machine learning model, for each user of the plurality of users, the second score of each user being, at least partially, based on the first score of said user, with the second score of each user being representative of a probability of a first user sending a connection request to said user. A ranked contact suggestion list of one or more users of the plurality of users is generated, the one or more users being ranked based on their respective second score.