Skills Ontology Creation via Hierarchical Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Social networking services face challenges in organizing and categorizing skills data, as users predominantly list granular skills rather than broad categories, making it difficult for advertisers and search functionalities to target relevant skills effectively.
Innovation Solution
The implementation of a machine learning-based approach to create a skills hierarchy by training a classifier using feature data and pre-existing hierarchy information, which identifies parent-child relationships between skills, allowing for the organization of skills into a structured category system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users list granular skills on their profiles, then the detail and precision of skill information is improved, but the ability to perform broad category targeting and classification deteriorates
Solution Approach 1:
The patent implements a hierarchical skill classification system where granular skills (e.g., specific programming languages) are nested within broader skill categories (e.g., programming skills). This nested structure allows the system to simultaneously preserve detailed skill information and enable broad category targeting by organizing skills in parent-child relationships across multiple levels of abstraction.
2Ease of manufacture
If a hierarchical skill structure is created, then the organization and classification of skills is improved, but the complexity of the system increases
Solution Approach 1:
The patent employs machine learning models to automatically classify skills into hierarchical categories before advertising or search operations occur. By pre-processing and organizing skills into a structured hierarchy in advance, the system reduces the complexity of real-time classification tasks and enables efficient querying without requiring complex runtime processing.
3Productivity
If machine learning classification is used to create skill hierarchies, then the automation and efficiency of skill organization is improved, but the computational resources and processing time increase
Solution Approach 1:
The patent implements skill classification selectively rather than processing all skills uniformly. The machine learning models focus on classifying skills that are relevant to current advertising or search queries, performing partial classification only when needed. This approach maintains high productivity for relevant tasks while reducing overall computational resource consumption by avoiding unnecessary classification of unrelated skills.
Data Source
AI summary
Disclosed in some examples are systems, methods, and machine readable mediums which allow for the automatic creation of a skills hierarchy. The skills hierarchy comprises an organization of a standardized list of skills into a hierarchy that describes category relationships between the skills in the hierarchy. The category relationships may include no relationships, parent relationships, and child relationships. A skill may be considered a parent of another skill if the parent skill describes a broader category of skill that includes the child. Other relationships such as grandparent (e.g., a parent's parent), great-grandparent, grandchild, great grandchild and so on may be defined inferentially as well. In some examples, the constructed hierarchy may be organized with broader skills at higher levels and narrower skills at lower levels.