Social Network Distance Estimation Using Profile Attributes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying third-degree connections in social network services is inefficient due to the large number of connections, making it costly and resource-intensive to maintain an index for quick identification.
Innovation Solution
A method to estimate the likelihood of a member being a third-degree connection by analyzing attributes in their profile, such as shared geographic location, job titles, and industry, generating a probability score that ranks search results in a people-search engine.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If an index is stored in memory to quickly identify third-degree connections, then search speed is improved, but computational resources and memory costs increase dramatically
Solution Approach 1:
The patent extracts only the essential attributes needed for distance estimation (profile attributes like job title, industry, geographic location) from the complete member data, storing these in a reduced form that enables estimation without requiring full indexes of all third-degree connections in memory
Solution Approach 2:
The system uses temporary, lightweight attribute data structures that can be created and discarded as needed for estimation queries, rather than maintaining permanent, expensive full indexes in memory. The normalized attribute representations serve as disposable computational objects for real-time estimation
2Measurement precision
If all member attributes are analyzed in detail to accurately determine third-degree connections, then identification accuracy is improved, but processing time increases
Solution Approach 1:
The patent applies local quality by analyzing only the specific profile attributes most relevant to connection likelihood (such as shared job titles, industries, and geographic locations) rather than examining all possible member attributes in detail, achieving sufficient accuracy with localized attribute analysis
Solution Approach 2:
The system changes the parameter representation by normalizing attributes into standardized formats and using probabilistic scoring instead of deterministic matching, enabling faster real-time estimation while maintaining practical identification accuracy
3Reliability
If real-time distance estimation is implemented, then search result relevance is improved, but computational complexity increases
Solution Approach 1:
The patent performs preliminary actions by pre-normalizing member attributes and pre-computing distance scores based on attribute comparisons, so that when a search is initiated, the system can quickly retrieve and use pre-processed data rather than performing complex computations in real-time
Solution Approach 2:
The system introduces an intermediary estimation layer that computes probability scores based on attribute analysis, serving as a mediator between the search query and the final connection identification. This intermediary scoring mechanism simplifies the overall computational complexity by breaking down the problem into manageable attribute-comparison steps
Data Source
AI summary
Techniques for estimating, in real time, the likelihood that any particular member of a social network service is a third degree connection of another member are described. Consistent with some embodiments, various member profile attributes of a member are used as a sort of proxy for determining the likelihood or probability that the member is a third degree connection of another member. For example, in some instances, the number of first-degree connections a member has is used to derive a probability score indicating the likelihood that the member is a third-degree connection of another member, such as a person performing a people-search. Once derived, the probability score for each member may be used in various applications, such as a people-search engine, to boost or increase a ranking score assigned to each search result and used to order the search results when presented to the user who has performed the search.