Nuisance Call Detection via Dynamic Voice Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing nuisance call detection methods face challenges in accurately identifying nuisance calls, especially when call times are short or voice information is limited, leading to increased erroneous determinations due to insufficient data for analysis.
Innovation Solution
A nuisance call detection device that analyzes voice signals by dividing them into frames, calculating determination information such as stress evaluation and keyword detection, and adjusts weighting factors based on conversation length to determine the likelihood of a nuisance call through a nuisance call evaluation value.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If voice recognition is performed during a telephone call to detect keywords or analyze speech patterns, then nuisance call detection capability is improved, but detection accuracy deteriorates when call time is short or voice information is limited
Solution Approach 1:
The patent applies preliminary action by calculating conversation length information during the call and using it to adjust weighting factors before final nuisance call determination. The system prepares adaptive weighting factors based on the accumulated conversation data, allowing accurate detection even when voice information is limited. This preliminary preparation of weighting parameters ensures that the detection system can handle short calls effectively by adjusting the importance of different determination information based on conversation duration.
2Reliability
If multiple pieces of determination information are calculated and analyzed, then detection comprehensiveness is improved, but computational complexity increases
Solution Approach 1:
The patent applies dynamics by making the weighting factors adaptive rather than fixed. The weighting factors are dynamically adjusted based on conversation length information, allowing the system to optimize the contribution of different determination information pieces according to the actual call conditions. This dynamic adjustment mechanism enables comprehensive detection while managing computational complexity by focusing resources on the most relevant parameters for each specific call scenario.
Data Source
AI summary
A nuisance call detection device that determines whether a telephone call in which a connection is established between a first telephone and a second telephone is a nuisance call and detects the nuisance call, analyzes a voice signal for one telephone call to calculate a plurality of pieces of determination information used for determination as to whether the telephone call is a nuisance call, simultaneously calculates information on a length of a conversation for the one telephone call, further calculates each weighting factor of the plurality of pieces of determination information in accordance with a length of the conversation, then calculates a nuisance call evaluation value based on a value obtained by multiplying each of the plurality of pieces of determination information by the weighting factor, and determines based on the nuisance call evaluation value whether the telephone call is a nuisance call.