Heterogeneous Graph Embedding for Talent Search Queries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional methods for talent search on social networks require manual effort and multiple trials to translate hiring position criteria into effective search queries, as they need to consider various factors like required skills, alternative skills, company presence, and educational backgrounds, which can be time-consuming and inefficient.
Innovation Solution
The system employs machine learning techniques to learn affinity levels between standardized entities, representing skills, titles, industries, and locations in a heterogeneous graph, allowing for the calculation of affinity scores and generating optimized search queries by embedding entities into a vector space and using node similarity models to suggest relevant search terms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual querying methods are used to translate hiring criteria into search queries, then recruiters can perform talent searches, but the process requires multiple trials and significant time investment
Solution Approach 1:
The system pre-computes affinity scores and relationships between entities (skills, titles, companies, schools) before actual search queries are executed. This preliminary structuring of data relationships enables rapid query generation without requiring recruiters to manually iterate through multiple search attempts, directly reducing the time loss while maintaining search productivity.
2Measurement precision
If standardized entity representation learning is implemented, then query structuring is optimized, but the system complexity increases due to machine learning models and heterogeneous graph structures
Solution Approach 1:
The patent introduces standardized entities as intermediary representations that bridge raw data and search queries. These standardized entities (skills, titles, companies, schools) with learned affinity scores act as mediators that simplify the complex relationships in the data, enabling precise search results while abstracting away the underlying system complexity from the recruiter interface.
Data Source
AI summary
In an example, a plurality of user profiles in a social networking service are accessed. A heterogeneous graph structure having a plurality of nodes connected by edges is generated, each node corresponding to a different entity in the social networking service, each edge representing a co-occurrence of entities represented by nodes on each side of the edge in at least one of the user profiles. Weights are calculated for each edge of the heterogeneous graph structure, the weights being based on co-occurrence counts reflecting a number of user profiles in the plurality of user profiles in which corresponding nodes co-occurred. The heterogeneous graph structure is embedded into a d-dimensional space. A machine-learned model is then used to calculate a similarity score between a first node and second node by computing distance between the first node and the second node in the d¬-dimensional space.