Information Classification System Confidence Calculation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information classification systems cannot accurately determine the probability of correctly classifying unclassified information into a true group, preventing the execution of processes tailored to this probability.
Innovation Solution
An information classification system that includes a classified information storing means and a confidence calculating means to determine the confidence value based on the probability that a group specified for unclassified information is the true group, using static and dynamic confidence calculations to select appropriate reference information and adjust processes accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If an information classification system classifies information based on entropy and selects reference information, then the classification process can be executed, but it is impossible to acquire a value depending on the probability that the specified group is a true group
Solution Approach 1:
The patent performs preliminary actions by storing multiple classified information items with different group specifications in advance (offline phase). When classifying unclassified information, the system selects reference information from these pre-stored items and calculates confidence values before final classification, enabling probability assessment of the true group.
Solution Approach 2:
The patent introduces a feedback mechanism where the system calculates confidence values based on the selected reference information and the specified group. This confidence value represents the probability that the specified group is the true group, providing feedback on classification reliability and enabling different processes according to this probability.
2Productivity
If the system selects reference information from stored classified information, then classification can proceed, but no confidence value indicating the probability of correct classification can be obtained
Solution Approach 1:
The patent introduces confidence calculation as an intermediary step between selecting reference information and final classification. The confidence value serves as a mediator that quantifies the reliability of the classification, allowing the system to maintain productivity while assessing reliability through this intermediate confidence metric.
3Ease of operation
If the system specifies a group for unclassified information based on reference information, then classification is completed, but no mechanism exists to execute different processes based on the probability of correct classification
Solution Approach 1:
The patent makes the classification system dynamic by enabling different processes to be executed based on the calculated confidence value. When confidence is high, the system can confidently assign the specified group; when confidence is low, alternative processes can be triggered, making the system adaptable to different situations based on classification probability.
Data Source
AI summary
An information classification system 100 includes: a classified information storing part 101 for storing classified information having already been classified into a certain group and group specification information for specifying the group, in association with each other; and a confidence calculating part 102 for calculating confidence having a value depending on a probability that a group which is specified based on unclassified information as a target to be classified and classified information selected as reference information from among the stored classified information and into which the unclassified information should be classified is a true group.