Overview
Scholar9 is dedicated to empowering the global research community through technology and innovation. The platform provides visibility and credibility for scholars, enabling them to showcase their achievements to the world. Additionally, Scholar9 connects journal owners with a vast network of editors, reviewers, and article authors, streamlining the publication process.
Services
Data Collection & Data Analysis, GEN AI, Crawler
Industry
academic publishing
Business Type
Startup
BUILD YOUR IDEA
Our Project Challenges
The parent company of Scholar9, with years of experience in the publication industry, had accumulated a vast database of researchers. However, this data was unorganized and spread across various formats, such as PDFs, Word documents, and image files. The challenge was to import these past publication authors into the Scholar9 system by extracting and mapping the relevant information from their CVs to the platform’s profile fields.
Solution
Data Fetcher : We analyzed the CVs and implemented a data crawler capable of reading through PDFs and Word files. For image-based CVs, we used OCR technology to extract the text.
Data Extractor : We leveraged Google’s Gemini LLM to accurately extract the required fields from the CVs. This method achieved an impressive 97% accuracy rate.
Data Processor : The extracted data was mapped to the appropriate fields in the Scholar9 data structure, and the processed information was seamlessly integrated into the platform’s database.
Data Rectification : After importing the records, we executed data verification and cleaning scripts to identify any incorrect data, ensuring the imported records were accurate and relevant.
Impact
A 300% increase in platform traffic within 3 months of the data import.
A 2X increase in revenue in just 3 months, driven by increased engagement from researchers and journal owners.
Saved over 1000 man-hours of manual data processing.
300%
traffic increased within 3 months of data import
1000+
Man hours saved.
Client’s words
“We have always valued innovation, and working with XillenTech has reaffirmed this belief. Their approach to organizing our unstructured data has been transformational for our platform. The use of advanced technologies like data crawlers and LLM-based data extraction has saved us countless hours and helped us scale Scholar9 quickly. We highly recommend XillenTech for any data-driven development.”