Biometric Identification Preprocessing via Group Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current biometric feature-based identification systems are inefficient due to the need to compare a collected biometric feature with a large set of registration biometric features, leading to long identification times and reduced accuracy from comparing similar features.
Innovation Solution
Classifying users into groups based on a predetermined rule, where a biometric feature collection device broadcasts a radio signal to determine the user's group identifier, allowing the identification server to pre-select a screening feature set for comparison, reducing the number of features to match.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the identification server compares the collection biometric feature with each registration biometric feature in the registration biometric feature set one by one, then the identification can be performed, but the identification efficiency is very low
Solution Approach 1:
The patent segments the registration biometric feature set into multiple subsets based on user groups. Each user is assigned to a specific user group, and the system only compares the collection biometric feature with registration biometric features within the same user group subset. This segmentation dramatically reduces the comparison scope from the entire registration biometric feature set to a smaller, targeted subset, thereby improving identification efficiency and reducing identification time.
Solution Approach 2:
The patent performs preliminary actions by pre-classifying users into different user groups and pre-organizing registration biometric features into corresponding subsets before the actual identification process. This preliminary organization allows the system to quickly narrow down the comparison range during identification, avoiding the need to search through the entire registration biometric feature set, thus improving productivity and reducing time loss.
2Measurement precision
If the identification server compares the collection biometric feature with each registration biometric feature, then identification can be performed, but the accuracy is reduced due to comparing similar features
Solution Approach 1:
The patent segments users into distinct user groups based on predetermined rules (such as device type, usage scenario, or other distinguishing characteristics). By organizing registration biometric features into separate subsets corresponding to each user group, the system ensures that only features from the appropriate group are compared during identification. This segmentation prevents the comparison of similar but unrelated features from different user groups, thereby improving identification accuracy while maintaining efficiency.
Solution Approach 2:
The patent applies local quality by tailoring the comparison process to the specific characteristics of each user group. Instead of uniformly comparing all registration biometric features, the system adjusts the comparison scope and criteria based on the local characteristics of the user group to which the user belongs. This localized approach ensures that only relevant and distinguishable features are compared, improving accuracy by eliminating misleading similarities between different user groups.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach significantly improves identification efficiency by reducing the number of features to compare and enhances accuracy by narrowing the comparison range, allowing users to wait less time for identification results while protecting user privacy.
Implementation Method 1
a biometric feature collection device broadcasts a radio signal to a predetermined surrounding area of the biometric feature collection device
Data Source
AI summary
This disclosure relates to identification preprocessing. In one aspect, a method includes receiving at an identification server, and from a mobile computing device that has entered a predetermined area surrounding a biometric feature collection device, a group identifier of a user group to which a user of the mobile computing device belongs. The group identifier is transmitted by the mobile computing device in response to the mobile computing device receiving a radio signal broadcast to the predetermined area. The user group is one of multiple user groups. Based on the group identifier, the identification server selects, from a stored registration biometric feature set, a registration biometric feature associated with each user in the user group. The identification server adds the registration biometric feature to a screening feature set established for the biometric feature collection device. Biometric feature-based identification is performed on the user using the screening feature set.