Mobile Terminal Reception Testing with AI-Predicted Signal Levels
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile terminal testing devices face challenges in significantly shortening the Equivalent Isotropic Sensitivity (EIS) search time due to the need for numerous measurements, especially when using methods that linearly or non-linearly change the output level of the test signal, and the CP determination process, which limits further reduction in measurement numbers.
Innovation Solution
A mobile terminal testing device and method utilizing AI prediction to dynamically set the output level and step level of the test signal based on machine learning, allowing for efficient and rapid setting of the test signal to a testable level by reducing the number of measurements through AI-predicted adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the output level of the test signal is changed linearly or non-linearly through multiple measurements, then the reception sensitivity test can be performed systematically, but the EIS search time becomes excessively long
Solution Approach 1:
The system performs preliminary actions by predicting the EIS value and determining an appropriate starting output level before beginning the actual reception sensitivity test. This preliminary prediction step allows the test to start closer to the target EIS value, significantly reducing the number of measurements needed and thus the EIS search time while maintaining measurement precision
Solution Approach 2:
The system uses feedback by continuously monitoring the measured EIS value during the test and comparing it with the target value. Based on this feedback, the output level is dynamically adjusted to converge faster to the target EIS value, reducing the number of measurements required compared to fixed linear or non-linear step methods
2Productivity
If the number of measurements is reduced to shorten EIS search time, then testing efficiency improves, but measurement precision may be compromised
Solution Approach 1:
By performing preliminary prediction of the EIS value and determining an optimal starting output level before the actual test, the system reduces the measurement range that needs to be covered. This allows fewer measurements to achieve the same precision that would otherwise require many more measurements in traditional systematic approaches
Solution Approach 2:
The system dynamically adjusts the output level based on real-time measurement results and prediction algorithms, rather than following a fixed linear or non-linear sequence. This dynamic adaptation allows the test to converge to the target EIS value with fewer measurements while maintaining precision
3Ease of manufacture
If a fixed starting output level is used for EIS search, then the test setup is simple, but the search time cannot be significantly reduced
Solution Approach 1:
The system performs preliminary prediction of the appropriate starting output level based on predicted EIS values before beginning the actual test sequence. This preliminary action maintains the simplicity of the test setup while dramatically reducing the EIS search time by starting the measurements much closer to the target value
Solution Approach 2:
The system changes the starting output level parameter dynamically based on predicted EIS values rather than using a fixed predetermined value. This parameter adaptation allows the system to maintain setup simplicity while achieving faster convergence to the target EIS value
Data Source
AI summary
A reception sensitivity test control unit 18 provided in a measurement device 1 and configured to execute a reception sensitivity test by repeatedly transmitting and receiving a test signal to a mobile terminal includes a test condition setting unit 18a that initially sets a test condition including an initial step level SL0 and a starting output level OL0 of the test signal at a start of the reception sensitivity test, and an AI prediction test condition change setting unit 18b that sets an AI prediction output level OL01, which is AI-predicted in advance by an AI prediction model based on the test condition set by the test condition setting unit 18a, as a first output level instead of the output level OL0.