Expert Ranking via Topic Graph Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for identifying and ranking subject matter experts on social networks are limited by their reliance on precise skill definitions, which can lead to missing qualified candidates due to broad, narrow, or incorrectly worded search terms.
Innovation Solution
A system that uses an ordered list of topics to define a subject matter area, incorporating similarity weights based on a topic graph, to generate queries that account for both listed and similar skills, ensuring more accurate matching and ranking of experts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If simple search methods using basic skill keywords are used, then the search process is fast and easy to operate, but the search accuracy deteriorates because qualified candidates are missed due to broad, narrow, or incorrectly worded search terms
Solution Approach 1:
The patent introduces a topic graph as an intermediary structure between the user's simple search queries and the complex skill profiles of candidates. The topic graph expands basic search terms into related skill concepts, acting as a mediator that translates simple queries into comprehensive search criteria without requiring users to manually define complex search terms.
Solution Approach 2:
The system changes the search parameters from simple keyword matching to a multi-dimensional evaluation that includes topic graph relationships, skill proficiency levels, and relevance weighting. This transforms the search process from binary match/no-match to a graded assessment that captures nuanced skill alignments.
2Productivity
If search results are ranked solely by the number of skills matched, then the ranking process is simple and fast, but the quality of results deteriorates because candidates with higher proficiency in fewer skills may be undervalued
Solution Approach 1:
The patent applies local quality by differentiating the evaluation of different skills based on their specificity and relevance to the job. Not all matched skills are treated equally - the system weights skills differently according to their importance in the topic graph and their specificity to the search query, ensuring that highly relevant skills carry more weight than generic ones.
Solution Approach 2:
The ranking system transitions from counting the number of matched skills to evaluating a weighted sum of skill proficiencies. This parameter change allows the system to capture the quality and relevance of skill matches rather than merely quantifying them, producing more reliable rankings that reflect actual candidate suitability.
3Device complexity
If the search relies on explicitly listed skills in user profiles, then the system complexity is low, but the adaptability deteriorates because implicit or related skills are not captured
Solution Approach 1:
The topic graph is pre-computed and stored before actual search operations. This preliminary action of building the graph structure with pre-established relationships between topics and skills allows the system to quickly expand search queries without performing complex real-time analysis, thus adding adaptability while keeping operational complexity manageable.
Solution Approach 2:
The topic graph serves multiple functions: it expands search queries, identifies related skills, determines skill relationships, and weights search results. This multi-functionality allows a single data structure to handle various matching scenarios, improving adaptability without proportionally increasing system complexity.
Data Source
AI summary
Embodiments of the present invention allow a system to use data gathered from social networks and other systems to determine an ordered list of desired topics or skills to define a subject matter area and incorporate the order of the topics or skills into a search. To define this subject matter area, embodiments can consider not just the topics or skills that are listed, but those topics or skills that are similar based on a pre-computed topic graph. These considerations can be incorporated into a generated query, so that the query itself accounts for similarity of topics via the topic graph and the order of desired terms. The query generation process can include a claimed skills veracity model that provides differential weighting to claimed skills, based on the skill-sets of users who are deemed to be similar to the user being evaluated.