Automated Industry Classification for Startup Companies

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Manually identifying the industry and products/services of startup companies is labor-intensive and limited by human capacity, making it inefficient for performing industry analysis.

Innovation Solution

A system and method for generating custom industry classifications using a computer program that receives standard and custom industry classifications, converts descriptions to vector representations, performs similarity matching, and trains a supervised classifier to automate the classification of startup companies into industries and products/services.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual review of startup company details is performed to identify industry and products/services, then classification accuracy can be maintained, but labor intensity and time consumption increase significantly

Engineering Contradiction:
Improveclassification accuracyVSAvoidclassification speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces the mechanical manual review process with an automated computer program that uses vector representations and similarity matching algorithms to classify startup companies into industries and identify their products/services, thereby eliminating manual labor while maintaining classification quality

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates vector representations (digital copies) of startup company descriptions and compares them against vector representations of industry definitions and product/service descriptions, enabling automated classification through computational similarity assessment rather than human review

Inventive Principle:
Principle #26Copying

2Reliability

If manual classification is performed to ensure accurate industry identification, then classification quality is maintained, but the process is limited by human capacity and scalability

Engineering Contradiction:
Improveclassification qualityVSAvoidscalability
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent creates a universal classification system that can process any startup company description through the same automated vector-based approach, making the system scalable and adaptable to different industries and company types without requiring additional human resources or manual adjustments

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Loss of information

If comprehensive information about startup companies is reviewed manually, then complete industry analysis is achieved, but the amount of labor and time required becomes unsustainable

Engineering Contradiction:
Improveinformation completenessVSAvoidanalysis time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The patent replaces manual information review with automated text processing that extracts and analyzes relevant features from startup company descriptions, maintaining information completeness while dramatically reducing the time required for analysis through computational efficiency

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20240028921A1Systems and methods for generating custom industry classifications
Publication Date: 2024.01.25 JPMORGAN CHASE BANK NA
  • US20240028921A1 patent drawing
  • US20240028921A1 patent drawing
  • US20240028921A1 patent drawing

AI summary

A method for generating custom industry classifications may include a classification computer program receiving standard industry classifications, standard industry descriptions, custom industry classifications, custom industry descriptions, and a mapping of the custom industry classifications to the standard industry classifications; generating a dataset comprising standard industry descriptions as inputs and custom industry classifications as outputs; converting the standard industry descriptions and unmapped portions of the custom industry descriptions to vector representations; performing similarity matching on the vector representations of the standard industry descriptions and the vector representations of the unmapped portions; assigning each of the unmapped portions of the custom industry descriptions to one of the standard industry descriptions based on the similarity matching; training a supervised classifier using the dataset and a plurality of startup company descriptions for a plurality of startup companies as inputs; and outputting a custom classification for each of the plurality of startup companies.