Affinity Score Calculation for New Users via Mutual Contacts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In social networks, determining the affinity or engagement between users, especially when a new user joins with limited interaction data, is challenging due to the lack of available information about their interactions with other members.
Innovation Solution
Calculating affinity coefficients based on the new user's connections, using their contact list to establish initial affinities, and applying forward and bilateral affinity calculations to determine connectedness and kinship, ensuring mutual affinities for effective recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional affinity calculation methods are used based on user interactions, then affinity accuracy is improved for established users, but new users cannot have their affinity determined due to lack of interaction data
Solution Approach 1:
The patent uses mutual contacts as an intermediary to determine affinity between users. Instead of directly measuring interaction between two users, the system identifies common contacts in both users' contact lists and uses the strength of those mutual contacts as a proxy measure of affinity. This mediator approach enables affinity calculation for new users who lack direct interaction history.
Solution Approach 2:
The system performs preliminary affinity calculations using contact list data before actual user interactions occur. By pre-calculating affinity scores based on mutual contacts upon user registration or when contact lists are updated, the system establishes initial affinity values that can later be refined as users interact, solving the problem of having no affinity data for new users.
2Adaptability or versatility
If mutual contacts are used to calculate affinity, then affinity can be determined for new users, but the calculation complexity increases
Solution Approach 1:
The patent segments the affinity calculation process into distinct components: identifying mutual contacts, calculating individual contact strengths, summing strengths, and applying the formula. This segmentation allows the complex task to be broken down into manageable steps that can be implemented efficiently and maintained easily.
Solution Approach 2:
The system uses readily available contact list data that users already provide to the service for other purposes. By leveraging this existing data structure and the users' own contact information, the system performs affinity calculations without requiring additional complex data collection infrastructure or external resources.
3Loss of information
If contact list data is used for affinity calculation, then data availability is improved for new users, but data privacy concerns increase
Solution Approach 1:
The patent extracts only the necessary information from contact lists - specifically the presence and strength of mutual contacts - without accessing or processing the full content of users' contact data. This extraction approach minimizes privacy exposure by using only what is strictly needed for the calculation while leaving sensitive contact information untouched and private.
Data Source
AI summary
Exemplary embodiments relate to techniques for determining social networking or messaging user affinity and engagement coefficients (e.g., a measure of the connectedness between two people in a network). The described techniques are particularly well-suited to cases in which only limited information is available, such as when a new user joins a network and only the user's contacts list is available. The available information may be used to determine a group of existing users to which the new user is connected. Some embodiments relate to calculating scores among these existing users in order to infer an affinity for the new user to the existing users. Other embodiments involve calculating bilateral scores that reflect a degree of mutual affinity between two users.