Organization Profile Inference via Trust Graph Mediation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Incomplete or unreliable data sources for organizations pose challenges in inferring missing data and determining data reliability, affecting the accuracy of organization profiles in social networks.
Innovation Solution
A platform that enriches organization data using member data, web content mining, and machine learning to automatically infer and retrieve attributes, including name, URL, and logo enrichment, and clusters similar records to create a unified organization profile.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data from multiple sources is collected to enrich organization profiles, then the quantity of organization data increases, but the reliability and consistency of the data decreases due to incomplete or unreliable sources
Solution Approach 1:
The patent introduces a trust graph as an intermediary data structure that mediates between multiple data sources and the final organization profile. The trust graph stores trust scores that represent the reliability of each data source, allowing the system to weigh and combine data from multiple sources while accounting for their varying levels of reliability. This resolves the contradiction by enabling quantity expansion through multi-source collection while maintaining reliability through the trust-based mediation mechanism.
Solution Approach 2:
The patent changes the parameter of data reliability from a binary (trusted/not trusted) state to a continuous trust score parameter. By computing and storing trust scores for each data source based on historical accuracy, completeness, and consistency metrics, the system can dynamically adjust the weight given to each source. This parameter transformation allows the system to incorporate data from multiple sources (increasing quantity) while differentiating their reliability levels (maintaining overall reliability).
2Loss of information
If data from multiple sources is collected to enrich organization profiles, then the completeness of organization data improves, but the difficulty of detecting and measuring data accuracy increases
Solution Approach 1:
The trust graph serves as an intermediary that pre-processes and evaluates data from multiple sources before integration. It computes trust scores based on measurable criteria such as data completeness, consistency across sources, and historical reliability. This intermediary layer transforms the complex task of accuracy detection into a systematic evaluation process, allowing the system to achieve comprehensive data collection while maintaining manageable accuracy assessment through standardized trust score computation.
Solution Approach 2:
The patent replaces manual or ad-hoc data accuracy verification with an automated computational system. The trust graph uses algorithmic processes to automatically compute trust scores by analyzing data patterns, source reliability history, and cross-validation results. This substitution of mechanical verification methods with computational automation reduces the difficulty of detecting and measuring data accuracy while enabling comprehensive multi-source data integration.
Data Source
AI summary
In an example embodiment, a member profile corresponding to a member of a social networking service is obtained. Usage information for the member is then obtained, and one or more member metrics are calculated based on the member profile and usage information for the corresponding member. A plurality of features are extracted from the member profile and the one or more member metrics. The plurality of features is inserted into an organization name confidence score model to obtain a confidence score for an organization name in the member profile.