Weighted Semantic Graph for Social Network Content Targeting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current social network services face challenges in accurately identifying target audiences for content delivery, as cookie-based profiling often results in users receiving irrelevant content, despite their interests not being aligned with the content's associated concepts.

Innovation Solution

The method involves using a weighted semantic graph to quantify semantic relations between user interests and content tags, dynamically adjusting similarity values based on user actions, and employing crowdsourcing to improve content delivery by identifying and targeting users with higher probabilities of interest.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If cookie-based profiling is used to identify target users, then content delivery can be automated and scaled, but the accuracy of user interest identification deteriorates

Engineering Contradiction:

Improvecontent delivery automationVSAvoiduser interest identification accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent introduces a semantic graph as an intermediary layer between user profiles and content items. This semantic graph contains concepts and their relationships, serving as a mediator that translates user interests into meaningful content recommendations without requiring direct cookie-based tracking of user behavior

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical cookie-based tracking system with a semantic analysis system. Instead of mechanically tracking user interactions through cookies, the system uses semantic relationships and concept matching to identify user interests, thereby improving accuracy while maintaining automation

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Device complexity

If traditional content delivery methods are used, then system complexity remains low, but content relevance to users deteriorates

Engineering Contradiction:

Improvesystem complexityVSAvoidcontent relevance

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent segments the content delivery system into distinct components: user profiles with interest concepts, a semantic graph with structured knowledge, and content items with associated concepts. This segmentation allows for more precise matching while keeping each component relatively simple and manageable

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent changes the parameter space from simple cookie-based user identifiers to semantic concept vectors. By representing users and content in terms of semantic concepts and their relationships, the system achieves higher relevance through meaningful parameter transformations rather than complex processing

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS9946798B2Identification of target audience for content delivery in social networks by quantifying semantic relations and crowdsourcing

Publication Date: 2018.04.17 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A mechanism is provided in a data processing system for content delivery. The mechanism identifies a candidate user of a social networking service. The candidate user has an associated profile including at least one concept of interest. The mechanism determines a probability that the candidate user is interested in an item of content based on a semantic similarity of the at least one concept of interest and at least one concept tag associated with the item of content using a weighted semantic graph. Responsive to the probability exceeding a probability threshold, the mechanism delivers the item of content to the candidate user. Responsive to receiving feedback comprising at least one action taken by the candidate user with respect to the item of content, the mechanism adjusts weights in the weighted semantic graph.