Rule Prioritization by Question Frequency for Customer Care Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current customer care systems for electronic devices are inefficient and costly due to lengthy diagnostic processes, manual data gathering, and high Mean Time-to-Resolution (MTTR), which leads to increased support costs and customer frustration.
Innovation Solution
A codified knowledgebase system that uses rules to diagnose and fine-tune device performance by matching device profiles with relevant rules, applying natural language processing, and prioritizing rule creation based on question frequency and MTTR, enabling automated handling of common issues and reducing human intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual data gathering and diagnostic processes are used by CSRs, then device information can be obtained for problem diagnosis, but the process becomes extensive, time-consuming, and complex
Solution Approach 1:
The system enables self-service by automatically gathering device information and diagnostics without requiring CSR intervention. The device itself provides diagnostic data through automated interactions, eliminating the need for manual information gathering by support representatives.
Solution Approach 2:
The patent replaces the mechanical manual process of CSR questioning and data gathering with an automated electronic system. The automated diagnostic system electronically collects device information, replaces the manual mechanical interaction between CSR and customer with an automated electronic diagnostic process.
2Reliability
If CSRs are required to be experts on many types of devices and applications, then accurate problem diagnosis can be achieved, but support costs increase
Solution Approach 1:
The automated diagnostic system acts as an intermediary between the customer's device and the support infrastructure. This intermediary automatically collects device information, performs diagnostics, and prepares problem data, replacing the need for highly skilled human CSRs while maintaining diagnostic accuracy.
Solution Approach 2:
The system creates automated copies of the diagnostic expertise that would otherwise reside in human CSRs. By encoding diagnostic logic and device knowledge into automated systems, the patent replicates expert-level diagnostic capabilities without the associated human resource costs.
3Loss of information
If users spend increased time on the telephone to receive support, then complex diagnostic questions can be answered, but overall frustration increases
Solution Approach 1:
The system enables users to self-diagnose and self-report device issues without requiring lengthy phone conversations. The automated system guides users through necessary diagnostic interactions at their own pace, collecting complete diagnostic information while maintaining user convenience.
4Measurement precision
If the majority of time is taken in identifying the root cause of the problem, then accurate diagnosis can be achieved, but Mean Time-to-Resolution (MTTR) increases
Solution Approach 1:
The system performs preliminary diagnostic actions automatically before human intervention is needed. By pre-collecting device information, pre-running diagnostics, and pre-identifying potential issues, the system eliminates the time-consuming root cause identification phase that previously required extensive manual investigation.
Solution Approach 2:
The patent replaces the manual mechanical process of step-by-step troubleshooting with an automated electronic diagnostic system. This substitution enables rapid identification of root causes through automated analysis of device data, significantly reducing MTTR while maintaining diagnostic accuracy.
Data Source
AI summary
A method is provided for prioritizing rule creation for computer-assisted customer care. When a question from a user of a device is received by a customer care analytics engine for which no rule is automatically fired, the question and a related device profile of the device are added to an unfired questions list. The analytics engine parses the question to match terms in other questions in the list. The question is also added to an appropriate category in the list based on the device profile. A prioritization algorithm is used to rank the question among other questions within the list or the category, ranking the question more highly according to the frequency of those terms in the category or the list. According to its rank-wise order, the question is directed for creation of a rule to permit automatic handling of questions having the same or similar terms in the future.