B

AI Battery Research Paper Parser

2.80

Derivation Chain

Step 1 Gachon University & Korea University AI-based battery electrolyte design
→
Step 2 Surge in AI + materials research papers
→
Step 3 Automated experimental condition extraction tool for materials Startups' AI papers

Problem

R&D researchers at next-generation battery and materials Startups (5–20 employees) need to read 50–100 AI + materials-related papers per week, but experimental conditions (electrolyte composition, temperature, cycle count, performance metrics) are described in different formats across papers, making comparison impossible. Each researcher spends over 10 hours per week extracting experimental conditions, and when missing conditions cause reproduction experiments to fail, millions of won (~$750–$3,750) in reagent and equipment costs are wasted.

Solution

Upload battery/materials research PDFs and an LLM automatically extracts experimental conditions (composition, temperature, pressure, cycle count) and performance metrics (capacity, charge/discharge efficiency, lifespan) into structured tables. The extracted data is organized into a standardized format for cross-paper comparison and merged with in-house experimental data to support optimal condition discovery.

Target: Researchers at next-generation battery/materials R&D Startups (5–20 employees), university battery research labs
Revenue Model: SaaS Monthly Subscription at 79,000 KRW (~$59)/account, including 100 papers/month. Overage at 500 KRW (~$0.38)/paper. Enterprise plan at 290,000 KRW (~$218)/month (unlimited)
Ecosystem Role: Supplier
MVP Estimate: 2_weeks

NUMR-V Scores

N Novelty
4.0/5
U Urgency
3.0/5
M Market
2.0/5
R Realizability
3.0/5
V Validation
2.0/5
NUMR-V Scoring System
N Novelty1-5How uncommon the service is in market context.
U Urgency1-5How urgently users need this problem solved now.
M Market1-5Market size and growth potential from proxy indicators.
R Realizability1-5Buildability for a small team with realistic constraints.
V Validation1-5Validation signal quality from competition and demand data.
Each dimension is scored 1-5 and weighted into grade S/A/B/C/D.
SaaS N=.15 U=.20 M=.15 R=.30 V=.20 Senior N=.25 U=.25 M=.05 R=.30 V=.15

Feasibility (70%)

Tech Complexity
29.3/40
Data Availability
20.8/25
MVP Timeline
20.0/20
API Bonus
0.0/15
Feasibility Breakdown
Tech Complexity/ 40Difficulty of core implementation stack.
Data Availability/ 25Practical availability and cost of required data.
MVP Timeline/ 20Expected time to ship a usable MVP.
API Bonus/ 15Bonus for viable public API leverage.
Total 100 points; below 50% is filtered out.

Market Validation (51/100)

Competition
8.0/20
Market Demand
3.8/20
Timing
14.0/20
Revenue Signals
7.5/15
Pick-Axe Fit
10.5/15
Solo Buildability
7.0/10
Validation Breakdown
Competition/ 20Signal quality from competitor landscape.
Market Demand/ 20Demand proxies from search and mention patterns.
Timing/ 20Fit with current shifts in tech, behavior, and regulation.
Revenue Signals/ 15Reference evidence for monetization viability.
Pick-Axe Fit/ 15How well the concept serves participants in a trend.
Solo Buildability/ 10Practicality for lean-team implementation.
Total 100 points; below 50 is filtered out.

Technical Requirements

AI/ML [medium] Backend [medium] Frontend [low]
Dashboard