Voice Search System for Call Center Audio Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for identifying problematic calls in call centers require listening to entire recordings to determine customer anger, making it inefficient to find and check specific issues within large volumes of voice data.
Innovation Solution
A voice search system that creates a database associating voice section sequences with keywords and time information, allowing for efficient retrieval of relevant playback start positions within recorded calls by searching for specific keywords and determining the start time of adjacent voice sections for playback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the entire recorded call is listened to in order to check at which part and why a customer was angry, then the accuracy of identifying problematic calls is improved, but the time required to check the content of the problem increases significantly
Solution Approach 1:
The patent extracts and separates the voice sections containing keywords from the entire recorded call. By using keyword search to identify specific voice sections and their appearance times, the system extracts only the relevant portions that contain problematic content, allowing supervisors to check only necessary segments rather than listening to entire calls.
Solution Approach 2:
The patent divides the recorded call into multiple voice sections with distinct time information. Each voice section is associated with specific keywords and appearance times, enabling segmented playback and inspection of problematic portions while maintaining the ability to identify the exact location and context of customer anger.
2Quantity of substance
If multiple parts-to-elicit are identified in a recorded call, then the coverage of problematic areas is improved, but the complexity of determining which part to check first increases
Solution Approach 1:
The patent performs preliminary organization of voice sections by storing them in a database with associated keywords and appearance times before the actual search. This preliminary structuring allows the system to quickly retrieve and present multiple problematic parts in an organized manner, reducing the complexity of selecting which part to check first.
Data Source
AI summary
Provided is a voice search technology that can efficiently find and check a problematic call. To this end, a voice search system of the present invention includes a call search database that stores, for each of a reception channel and a transmission channel of each of a plurality of pieces of recorded call voice data, voice section sequences in association with predetermined keywords and time information. The call search database is searched based on an input search keyword, so that a voice section sequence that contains the search keyword is obtained. More specifically, the voice search system obtains, as a keyword search result, a voice section sequence that contains the search keyword and the appearance time thereof from the plurality of pieces of recorded call voice data, and obtains, based on the appearance time in the keyword search result, the start time of a voice section sequence of another channel immediately before the voice section sequence obtained as the keyword search result, and thus determines the start time as the playback start position for playing back the recorded voice. Then, the playback start position is output as a voice search result.