Knowledge Base Metadata Scoring for Issue Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Resource limitations in response management systems lead to inefficiencies in resolving customer-encountered issues, as existing systems rely on keyword searching that returns excessive and irrelevant results, overwhelming service agents and consuming excessive resources.
Innovation Solution
Implementing a two-part search strategy that includes keyword searching followed by ranking knowledge base articles based on metadata quality, utilization, and accuracy scores to prioritize relevant information for service agents, thereby streamlining the resolution process and updating metadata for future searches.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If keyword searching is used to find knowledge base articles, then the search process is simple and fast, but excessive and irrelevant results are returned overwhelming service agents
Solution Approach 1:
The patent introduces metadata quality scores as an intermediary filtering mechanism between the keyword search and the service agent. These scores act as a mediator that evaluates and ranks the relevance and quality of search results, allowing the system to maintain simple keyword-based search operation while effectively reducing the quantity of irrelevant results presented to agents.
Solution Approach 2:
The system changes the parameter of search result evaluation by introducing multiple scoring dimensions (quality score, utilization score, accuracy score) instead of relying solely on keyword matching. This parameter transformation allows the system to maintain operational simplicity while significantly improving result relevance and reducing overwhelming quantities of irrelevant articles.
2Loss of information
If all knowledge base articles are presented to service agents, then complete information is available, but resource expenditure increases and time to resolve issues increases
Solution Approach 1:
The patent applies local quality by differentiating between high-quality and low-quality knowledge base articles through metadata scoring. Instead of treating all articles equally, the system identifies and prioritizes locally superior articles (those with high quality, utilization, and accuracy scores), allowing service agents to access the most relevant information first while maintaining access to complete information when needed.
Solution Approach 2:
The system performs preliminary action by pre-calculating and storing metadata quality scores, utilization scores, and accuracy scores for all knowledge base articles before they are needed. This advance preparation allows the system to quickly rank and present relevant articles without time-consuming evaluations during actual issue resolution, thereby reducing time loss while maintaining information completeness.
3Measurement precision
If metadata quality scoring is implemented to rank articles, then relevant information is prioritized, but system complexity increases
Solution Approach 1:
The patent segments the article evaluation process into distinct, independent scoring components: quality score, utilization score, and accuracy score. Each component addresses a specific aspect of article relevance and can be calculated and stored separately. This segmentation reduces system complexity by breaking down the complex ranking task into manageable, modular scoring functions that can be independently maintained and updated.
4Reliability
If service agents review more knowledge base articles to ensure complete information, then accuracy of resolution improves, but productivity decreases
Solution Approach 1:
The system performs preliminary action by pre-calculating and storing metadata quality scores, utilization scores, and accuracy scores for all knowledge base articles before they are needed. This advance preparation allows the system to quickly rank and present relevant articles without time-consuming evaluations during actual issue resolution, thereby reducing time loss while maintaining information completeness.
Data Source
AI summary
Methods and systems for managing customer-encountered issues are disclosed. To manage the customer-encountered issues, service requests for the customer-encountered issues may be managed to reduce time to resolution. To do so, potential processes for remediating the customer-encountered issues may be searched using a two step procedure. The two step procedure may include both keyword searching to broadly identify relevant articles and ranking of the identified relevant articles. The ranking process may take into account both past history of resolution process success and availability of metadata for the resolution processes.