Personalized Search Query Generation in Social Networks

Solution Overview

Problem

Social networking systems face challenges in providing users with engaging and relevant search queries within their social graphs, as existing methods lack personalized suggestions based on user engagement factors and social-graph attributes.

Innovation Solution

The system generates personalized structured queries by scoring nodes based on engagement factors, identifying common nodes, and creating queries that reference these nodes and edges, thereby providing users with more relevant search results.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the system provides generic search queries, then the system complexity is low, but user engagement and relevance of search results deteriorate

Engineering Contradiction:

Improveuser engagementVSAvoidsystem complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The system pre-generates structured queries based on social-graph elements (users, groups, pages, events) and stores them for later use. When a user searches, the system retrieves and personalizes these pre-generated queries rather than creating them from scratch, reducing real-time computational complexity while maintaining high relevance and engagement

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts query parameters based on user profile attributes, social connections, and engagement history. By changing parameters such as query weighting, prioritization of certain social-graph elements, and personalization factors, the system delivers highly relevant results without fundamentally changing the underlying query structure, thus managing complexity

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If the system generates personalized structured queries based on social-graph elements, then search result relevance improves, but the time to generate queries increases

Engineering Contradiction:

Improvesearch result relevanceVSAvoidquery generation time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system pre-generates structured queries based on social-graph elements (users, groups, pages, events) and stores them for later use. When a user searches, the system retrieves and personalizes these pre-generated queries rather than creating them from scratch, reducing real-time computational complexity while maintaining high relevance and engagement

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates template queries that can be copied and adapted for different users based on their profiles and social connections. These template queries are generated once and then instantiated multiple times with personalized parameters, significantly reducing query generation time while maintaining relevance

Inventive Principle:

Principle #26Copying

3Measurement precision

If the system analyzes user engagement factors and social-graph attributes, then query personalization quality improves, but computational resources required increase

Engineering Contradiction:

Improvequery personalization qualityVSAvoidcomputational resources

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system dynamically adjusts query parameters based on user profile attributes, social connections, and engagement history. By changing parameters such as query weighting, prioritization of certain social-graph elements, and personalization factors, the system delivers highly relevant results without fundamentally changing the underlying query structure, thus managing complexity

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system focuses on analyzing only the most relevant user engagement factors and social-graph attributes rather than processing all available data. By selecting key parameters such as recent interactions, close social connections, and explicitly stated interests, the system achieves high personalization quality with reduced computational overhead

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS9633121B2Personalizing default search queries on online social networks

Publication Date: 2017.04.25 META PLATFORMS INC

AI summary

In one embodiment, a method includes accessing a social graph that includes a plurality of nodes and edges. A first node corresponds to a first user associated with an online social network and second nodes correspond to a concept or a second user. The method further comprises scoring a first set of nodes of the second nodes based on user-engagement factors. The method further comprises identifying common nodes that are connected by edges to nodes of the first set of nodes that have a score greater than a threshold score. The method further comprises generating structured queries and sending the structured queries to the user, the sent structured queries being a personalized query.