Mark Entry Portal With AI

The document outlines a project for developing an AI-powered mark entry portal aimed at automating the error-prone and time-consuming manual mark entry process. The proposed system intends to reduce manual entry errors by 95% and integrate with existing college systems, utilizing technologies such as OCR and NLP for data extraction. Key benefits include increased accuracy, efficiency, and scalability, with future plans for integration with learning management systems and personalized feedback generation.

Uploaded by

shreyshelar096

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PPTX, PDF, TXT or read online on Scribd

0% found this document useful (0 votes)

1 views8 pages

Mark Entry Portal With AI

Uploaded by

shreyshelar096

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PPTX, PDF, TXT or read online on Scribd

You are on page 1/ 8

Mark Entry Portal with AI

Streamlining mark entry and analysis using AI. This is a project for
[Course Name], [Professor's Name]. Presented by: [Your Name(s)].

by Shrey Shelar
Problem Statement
Manual Mark Entry Motivation

Manual mark entry is error-prone and time-consuming. Automate mark entry to improve accuracy and save
The average error rate in manual data entry is 5%. time. Automation can save 80% of processing time.

Objectives
Develop an AI-powered portal for efficient and accurate mark entry. Reduce manual entry errors by 95% and
integrate with existing college systems.
Literature Review
Existing Systems Key Papers

Existing mark entry systems lack AI integration. A Key research papers on OCR and NLP techniques.
survey of 5 college systems revealed no AI. Research Tesseract OCR engine accuracy benchmarked at 85%.
shows AI grading reduces instructor time by 40%. Stanford NLP library used for data extraction.
Proposed System
AI-Powered Portal Key Modules
AI-powered mark entry Modules: Document Upload,
portal with automatic data AI Processing, Validation,
extraction from scanned Database Storage. AI
documents. Accuracy module expected
>90% accuracy.

Benefits
Accuracy, Efficiency, Scalability, and Security are the key
benefits of this approach.
System Architecture
Three-Tier Architecture Technologies Used

Presentation, Application, and Data tiers. Clear diagram Frontend: React.js, Material UI. Backend: Python (Flask),
of data flow and component interaction. TensorFlow/PyTorch. Database: PostgreSQL. OCR:
Tesseract. Cloud Deployment on AWS: EC2, S3, RDS.
Key Modules
Document Upload
Supports PDF, JPG, handles 1000 documents per batch.

AI Processing
Extracts marks using OCR and NLP. OCR extraction time:
less than 2 seconds.

Validation
Allows manual review, correction of extracted data.
Displays confidence scores.

Database Storage
Secure PostgreSQL storage. Scalable to 1 million+ records.
Advantages & Limitations
Advantages Limitations

• Increased accuracy • Document quality dependence

• Reduced errors • AI bias potential
• Time savings • Initial costs
• Improved security
• Automated reporting

Future Scope
Integration with LMS, AI-driven performance prediction, and personalized feedback generation.
Conclusion
AI-powered mark entry portal offers significant improvements. It
has the potential to revolutionize mark entry. Future work focuses
on expanding features and addressing limitations. Thank you!