Auto-Solution Advisor for IT Help Desk Text Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual diagnosis and solution identification by help desk personnel for customer IT issues are slow and ineffective due to the need for manual processing of customer descriptions in lay language.
Innovation Solution
An automated solution advisor system that uses text analysis and machine learning to categorize customer problem descriptions and match them with known solutions by filtering stop words, stemming, and employing Latent Dirichlet Allocation (LDA) and Kullback-Leibler distance measures to determine textual similarity between current and previous help requests.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual diagnosis and solution identification by help desk personnel is used, then human judgment and flexibility are maintained, but the process becomes slow and less effective
Solution Approach 1:
The patent introduces an automated solution advisor as an intermediary system between the customer's help request and the final solution. This advisor uses text analysis and machine learning to automatically categorize problems and match them with known solutions, acting as a mediator that handles routine cases without human intervention while maintaining solution quality
Solution Approach 2:
The system performs preliminary actions by pre-categorizing help requests and matching them with solutions before human personnel become involved. The automated advisor analyzes the problem description, determines the category, and identifies potential solutions in advance, allowing human technicians to only handle cases that require their expertise
2Measurement precision
If manual processing of customer descriptions is used, then nuanced understanding is achieved, but productivity decreases
Solution Approach 1:
The patent replaces the mechanical process of manual text analysis with automated text analysis and machine learning algorithms. The system uses computational methods to categorize help requests and identify solutions, substituting human cognitive processing with automated electronic systems that can handle multiple cases simultaneously
Solution Approach 2:
The automated solution advisor enables self-service by allowing the system to independently analyze problem descriptions, categorize issues, and identify solutions without requiring human personnel for every case. The advisor serves itself by using its own automated processes to resolve routine help requests
3Adaptability or versatility
If multiple levels of help desk support are maintained, then complex issues are handled effectively, but device complexity increases
Solution Approach 1:
The automated solution advisor serves multiple functions within a single system: it categorizes help requests, matches them with solutions, and can escalate complex cases. This multi-functional approach replaces the need for separate manual processes at multiple support levels, consolidating capabilities into one automated system
Data Source
AI summary
A system includes a processor that executes instructions stored in a memory to implement an auto-solution advisor on a server. The auto-solution advisor receives a current help request describing in lay language text a problem with a computer application or computing device, and determines whether the current help request is textually similar to a previous help request for a previous problem. Based on the similarity of the current help request to the previous help request, the auto-solution advisor assigns a known solution for the previous problem as the suggested solution for the current help request.