Automated Matter Assignment via Vector Similarity Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In large organizations, particularly in the legal field, it is challenging to properly match employees with the correct new matters due to the difficulty in identifying the optimal personnel with the necessary experience and skills for specific projects.
Innovation Solution
A system and method that automatically assigns matters by generating new matter vectors from matter information, comparing them to historical matter vectors, selecting similar historical matters, determining associated employees, applying rules to generate scores, and assigning the matter to the employee with the highest score based on similarity and workload considerations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual matching of employees to matters is performed, then employees can be assigned based on expertise and skills, but the process becomes time-consuming and inefficient in large organizations
Solution Approach 1:
The patent replaces the manual mechanical process of matching employees to matters with an automated computer-based system. The system uses natural language processing to extract matter information from emails or documents, generates matter vectors, compares them to historical matter vectors, and automatically assigns matters to employees based on similarity scores and employee availability, eliminating the need for manual review and assignment
Solution Approach 2:
The system enables self-service by automatically performing the entire matter assignment process without human intervention. The automated system extracts matter information, classifies matters, identifies suitable employees, and completes assignments autonomously, allowing the organization to benefit from continuous operation without requiring dedicated personnel for this task
2Productivity
If automated matter assignment is implemented, then efficiency and speed improve, but the complexity of the system increases
Solution Approach 1:
The system achieves multi-functionality by combining multiple capabilities into a single automated platform: natural language processing to extract matter information from various sources, vector generation and comparison for similarity assessment, employee availability checking, and automatic assignment. This consolidates what would otherwise require multiple separate systems into one unified solution
Solution Approach 2:
The patent introduces matter vectors as an intermediary representation that bridges the gap between unstructured matter information and structured employee matching. By converting matter descriptions into comparable vector formats, the system enables automated similarity assessment without requiring complex direct analysis of raw text, simplifying the overall process
3Measurement precision
If historical matter data is used for assignment, then assignment accuracy improves through learning from past patterns, but data privacy and security concerns increase
Solution Approach 1:
The system extracts only the essential features and characteristics needed for matching from historical matter data, storing them as matter vectors rather than retaining complete historical records. This extraction approach captures the necessary information for accurate matching while minimizing the storage and handling of sensitive detailed information, thereby reducing privacy risks
Data Source
AI summary
In one embodiment, a method of automatically assigning a matter includes receiving matter information, generating one or more new matter vectors from the matter information, comparing the one or more new matter vectors to historical matter vectors of historical matter information relating to historical matters, selecting a plurality of historical matters from the historical matters, where each historical matter of the plurality of historical matters has a similarity between the one or more new matter vectors and one or more historical matter vectors that is above a threshold, determining a subset of employees associated with the plurality of historical matters, where the subset of employees is a subset of a plurality of employees, applying one or more rules to the subset of employees to generate a score for each employee of the subset of employees, and assigning the matter to an assigned employee having a highest score.