Issue Graphs for Analyzing Organizational Influence
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current software tools are inadequate for automatically analyzing vast quantities of disparate data related to policymaking processes across various governmental jurisdictions, as they often focus on either structured or unstructured data, lack the ability to derive structured data from unstructured data, and require significant manual inputs to update information, making it impractical to monitor and analyze the impact of policymaking processes effectively.
Innovation Solution
The development of systems and methods that utilize machine-trained models and automated data aggregation techniques to construct issue-based knowledge graphs, allowing for the analysis of both structured and unstructured data, and enabling the calculation of complex relationships between entities within a policy intelligence platform.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis of policymaking data is performed, then detailed understanding of policy documents and relationships can be achieved, but significant time and financial resources are required and consistency is difficult to maintain
Solution Approach 1:
The patent replaces manual mechanical analysis with automated software systems that use natural language processing and machine learning algorithms to analyze policy documents, extract entities, and identify relationships automatically, eliminating the need for human analysts to manually review each document while maintaining or improving analysis accuracy
Solution Approach 2:
The system enables self-service automated analysis where the software autonomously collects data from multiple sources, processes unstructured text, identifies policymakers and organizations, and generates insights without requiring human intervention at each step, allowing continuous operation without manual resource allocation
2Productivity
If automated software tools are used to analyze policymaking data, then time and resource efficiency improve, but existing tools are limited to one or two data types and require significant manual inputs
Solution Approach 1:
The patent creates a universal platform that handles multiple data types including unstructured policy documents, structured databases, news articles, and social media content within a single system, eliminating the need for separate tools for different data types and reducing manual data preparation requirements
Solution Approach 2:
The system introduces an intermediary layer of natural language processing and entity recognition technology that bridges unstructured text data and structured analysis outputs, automatically extracting meaningful information from diverse sources and transforming them into a unified format that can be analyzed without manual intervention
3Reliability
If existing information services systems are used, then document tracking capability is provided, but they lack context for relating documents and ignore people and organizational data
Solution Approach 1:
The patent merges document tracking functionality with entity relationship analysis by combining policy document data with policymaker profiles, organizational information, and interaction data into a unified knowledge graph that preserves document tracking reliability while adding rich contextual information about people and organizations involved in policymaking processes
Data Source
AI summary
A system for generating and analyzing organizational influence data is disclosed. In one embodiment, at least one processor is configured to access first data associated with a plurality of policymakers; generate first nodes representing the plurality of policymakers within an issue graph model; generate a second node representing an organization; receive a selection of an agenda issue of interest to the organization; access second data associated with the organization; generate links within the issue graph model representing relationships between the first nodes and the second node; determine an organizational influence factor comprising a measure of how likely the second node is to affect a property of each of the first nodes; identify at least one node of the first nodes associated with the selected agenda issue based on the organizational influence factor; and output node properties associated with the identified node.