Search Result Ranking Using Social Activity Affinity

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional techniques for personalizing search results in social network services face limitations, such as sparseness of social network activity data and reliance on user search history, which can lead to irrelevant results for new users or those expressing new interests.

Innovation Solution

The system calculates a user's affinity to search results based on correlations between their social activity data and that of historical users who clicked or skipped similar results, using aggregated social activity data to rank results and provide personalized recommendations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional techniques use social network activity data to personalize search results, then search result personalization is improved, but the sparseness of data leads to limited effectiveness for many users

Engineering Contradiction:

Improvesearch result personalization effectivenessVSAvoidsocial network activity data quantity

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The patent merges social network activity data with search query data and user profile data to create a comprehensive personalization system. By combining multiple data sources, the system overcomes the sparseness issue in social network data alone and achieves better personalization effectiveness for a broader range of users.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system applies multi-functionality by using the personalization mechanism for diverse user scenarios including new users, users with limited social network data, and users with diverse interests. The unified approach handles multiple personalization needs through a single framework that leverages multiple data types.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Reliability

If the system relies on user search history for personalization, then search result relevance is improved for returning users, but new users or users with new interests receive irrelevant results

Engineering Contradiction:

Improvesearch result relevanceVSAvoidadaptability to new users and new interests

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary action by pre-establishing user profiles and social network relationships before the user performs searches. This allows the system to provide personalized results to new users based on their social network data and inferred preferences, without requiring extensive search history.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary mechanism that uses social network activity data and user profile data as mediators between the search query and the search results. This intermediary layer enables the system to infer user preferences and provide relevant results even when direct search history is insufficient or unrelated.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Adaptability or versatility

If the system uses only social network activity data for personalization, then personalization for new users is improved, but the system cannot capture user preferences for new interests effectively

Engineering Contradiction:

Improvepersonalization for new usersVSAvoidaccuracy of interest-based personalization

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system implements dynamics by continuously updating user profiles and preferences based on evolving social network activity and search behavior. This allows the system to adapt to changing user interests and provide accurate personalization for new interests as they emerge, while maintaining accuracy for established preferences.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS8972399B2Ranking based on social activity data

Publication Date: 2015.03.03 BRITISH COLUMBIA TRANSMISSION CORP

AI summary

Various technologies described herein pertain to using social activity data to personalize ranking of results returned by a computing operation for a user. For each of the results returned by the computing operation, a respective first affinity of the user to a corresponding result and a respective second affinity of the user to the corresponding result can be calculated and used for ranking the results. The respective first affinity of the user to the corresponding result can be calculated based on correlations between social activity data of the user and social activity data of a first group of historical users that clicked the corresponding result. Moreover, the respective second affinity of the user to the corresponding result can be calculated based on correlations between the social activity data of the user and social activity data of a second group of historical users that skipped the corresponding results.