Legislation Revision Prediction System Using Influence Indices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing legal information processing systems fail to accurately predict the revision of legislation and regulations due to the lack of direct involvement of non-process-related information, such as economic scales and revision speeds, which are crucial for manufacturers to prepare and negotiate effectively.
Innovation Solution
A prediction system that collects relevant information, performs conversion processing to create indices related to the degree of influence on revision, and uses these indices to predict the stage of revision or negotiation timing, incorporating machine learning models trained with labeled data to enhance prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If relevant information including economic scale and revision speed is directly entered into the inference system, then the prediction system can utilize more information types, but the prediction accuracy does not improve because the information is not directly involved with the revision process
Solution Approach 1:
The patent introduces an intermediary conversion process that transforms non-directly-involved information (economic scale, revision speed) into an index representing degree of influence on revision. This intermediary index serves as a bridge between indirect information and the revision prediction process, allowing the system to utilize diverse information types while maintaining prediction accuracy through the mediating conversion step.
Solution Approach 2:
The patent applies parameter transformation by converting raw information parameters (economic scale, revision speed) into a different parameter format (index of degree of influence). This parameter change enables the information to be meaningfully integrated into the prediction system, transforming unrelated data into relevant predictive input through systematic conversion rules.
2Measurement precision
If only information directly involved with the revision process is used, then the prediction accuracy is high, but the system cannot utilize indirect information such as economic scale and revision speed
Solution Approach 1:
The conversion to an index of degree of influence acts as an intermediary that allows indirect information to be incorporated without compromising prediction accuracy. The index serves as a standardized interface that translates diverse indirect information into a form that can be meaningfully combined with direct revision process information.
Solution Approach 2:
The patent creates a universal index format that can accommodate multiple types of indirect information (economic scale, revision speed, and potentially other indirect factors). This universal conversion mechanism enables the system to handle diverse information types through a single standardized process, achieving multi-functionality in information processing.
3Productivity
If various types of indirect information are collected and used without conversion, then the system can process more information, but the prediction result becomes inaccurate due to lack of direct involvement with revision process
Solution Approach 1:
The patent systematically changes the parameters of indirect information through conversion into an index of degree of influence. This parameter transformation maintains the information processing capacity to handle diverse data types while ensuring the converted parameters are suitable for accurate prediction by the inference system.
Solution Approach 2:
The index conversion process serves as an intermediary filtering and transformation stage that processes various indirect information types before they reach the inference system. This intermediary step maintains high information processing capacity while ensuring only properly transformed, prediction-relevant data is passed to the prediction engine.
Data Source
AI summary
An information collection server obtains relevant information relating to legislation, regulations, or standards (vehicle emissions control) from an external server group and a local server and provides the obtained relevant information to an information processing server. When the information processing server receives the relevant information from the information collection server, it performs conversion processing on each piece of information included in the relevant information in accordance with each piece of information to convert each piece of information into an index relating to a degree of influence on revision of the emissions control. The information processing server provides each resultant index to a prediction creation server. When the prediction creation server receives each resultant index from the information processing server, it predicts a stage of revision of the emissions control based on each index.