Social Network Relevance-Based Interaction Recommendation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Social networks fail to provide relevance-based recommendations for improving existing connections and relationships, often treating events like birthdays as irrelevant or uniformly applicable, and do not consider the specific relevance of information to individual members based on their profiles and interactions.

Innovation Solution

A social network system and method that determines the relevance of events to members by considering factors such as elapsed time, social connection strength, and interaction history, and presents personalized recommended interactions based on these determinations, including notifications for reconnecting with entities that have moved closer geographically or achieved milestones.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If social networks provide uniform recommendations for all members, then the system complexity is reduced and ease of operation is improved, but the relevance and personalization of recommendations deteriorates

Engineering Contradiction:
Improveease of operationVSAvoidrelevance precision
Core Design Contradiction:
Ease of operationVSManufacturing precision

Solution Approach 1:

The patent applies local quality by determining relevance of events to members based on individual member characteristics including profile information, social connection strength, and interaction history. Each member receives personalized recommendations tailored to their specific context rather than uniform recommendations for all members, thereby improving relevance precision while maintaining operational simplicity through automated relevance determination.

Inventive Principle:
Principle #3Local quality

2Manufacturing precision

If social networks consider multiple factors for relevance determination, then the relevance and personalization of recommendations is improved, but the device complexity and processing requirements increase

Engineering Contradiction:
Improverelevance precisionVSAvoidsystem complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system performs self-service by automatically determining relevance of events to members based on their profiles and interaction history without requiring manual input or complex user configuration. The social network itself analyzes member characteristics, social connections, and past interactions to generate personalized recommendations, reducing the need for user involvement while maintaining high relevance precision.

Inventive Principle:
Principle #25Self-service

3Ease of manufacture

If social networks treat all events uniformly, then the ease of manufacture and system simplicity is improved, but the ability to highlight significant events and improve relationship maintenance deteriorates

Engineering Contradiction:
Improvesystem simplicityVSAvoidrelationship maintenance
Core Design Contradiction:
Ease of manufactureVSReliability

Solution Approach 1:

The patent applies parameter changes by dynamically adjusting recommendation parameters based on event types, member characteristics, and social connection strength. Different events are treated differently based on their relevance to individual members, with the system modifying recommendation parameters such as priority, personalization level, and delivery timing to optimize relationship maintenance while keeping the overall system simple and manageable.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS9619846B2System and method for relevance-based social network interaction recommendation
Publication Date: 2017.04.11 MICROSOFT TECHNOLOGY LICENSING LLC
  • US9619846B2 patent drawing
  • US9619846B2 patent drawing
  • US9619846B2 patent drawing

AI summary

System and method for recommending to a member of a social network an interaction with ones of a plurality of entities. Events related to individual ones of the plurality of entities are obtained. A relevance of ones of the events to the member is determined based on at least one characteristic of ones of the events and a trait of the member. Recommended interactions with ones of the plurality of entities individually related to the ones of the events based on the relevance for each of the events are presented to the user.