Visualized Compliance Estimation for Contact Center Scripts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for confirming whether an operator's utterance complies with a predetermined talk script in contact centers require manual setting of keywords, which is costly and inefficient, especially when the script is expressed in sentence format.
Innovation Solution
A visualized information generation apparatus that estimates compliance between an utterance text and a predetermined script by generating visualized information to distinguish between compliant and non-compliant ranges, using a processor to divide the utterance text and script into units, match them, and generate correspondence information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual keyword setting is used to confirm operator compliance with talk script, then compliance confirmation can be performed, but setting costs increase and efficiency decreases
Solution Approach 1:
The system automatically extracts keywords from the talk script and performs compliance matching without requiring manual keyword setting. The keyword extraction unit automatically identifies keywords from the script, and the compliance matching unit automatically compares utterance texts with extracted keywords, enabling the system to serve itself rather than requiring manual configuration.
Solution Approach 2:
The patent replaces manual mechanical keyword setting with automated computational keyword extraction and matching. Instead of manually configuring keywords, the system uses natural language processing techniques to automatically extract keywords from the talk script and perform compliance matching through algorithmic comparison of utterance texts with extracted keywords.
2Measurement precision
If manual keyword setting is used for compliance confirmation, then compliance can be assessed, but time consumption increases
Solution Approach 1:
The system performs preliminary keyword extraction from the talk script before compliance assessment. The keyword extraction unit processes the talk script in advance to extract keywords, so that when compliance matching occurs, the keywords are already prepared and available for immediate comparison with utterance texts, eliminating the need for manual keyword setting during the assessment process.
Solution Approach 2:
The patent replaces time-consuming manual keyword setting with automated computational extraction and matching processes. The system uses natural language processing algorithms to automatically identify and extract keywords from the talk script, and then automatically compares utterance texts with these extracted keywords, significantly reducing the time required for compliance assessment compared to manual methods.
3Adaptability or versatility
If sentence format talk scripts are used, then comprehensive communication guidance is provided, but keyword setting becomes challenging and less accurate
Solution Approach 1:
The system automatically extracts keywords from sentence format talk scripts without requiring manual intervention. The keyword extraction unit processes the natural language sentences of the talk script and automatically identifies relevant keywords, enabling the system to handle comprehensive sentence format scripts while maintaining accurate keyword identification for compliance assessment.
Solution Approach 2:
The patent replaces manual keyword setting with automated natural language processing techniques. The system uses computational methods to extract keywords from sentence format talk scripts, allowing comprehensive communication guidance to be maintained while automatically identifying accurate keywords for compliance matching, thereby resolving the challenge of manual keyword setting for sentence format scripts.
Data Source
AI summary
A visualized information generation apparatus according to an embodiment includes a visualized information generating part configured to generate visualized information in response to an input of information indicating compliance, non-compliance, or both between an utterance content expressed by an utterance text and an utterance content expressed by a predetermined script. The visualized information is for visualizing a range estimated to be in compliance in a manner that is different from a manner in which a range estimated to be in non-compliance is visualized. The range estimated to be in compliance and the range estimated to be in non-compliance are as defined herein.


