People Graph
The People Graph platform is an artificial intelligence-based system that analyzes the communication graph of social network users. The People Graph platform uses graph edges between user nodes, weighted by various analyses. The dependency between users and the classification of communication is also extracted. This system was designed to analyze the entire social network, manage the Network, identify critical users and use them in promotions, user engagement, use in recommender engines, and marketing purposes.
Feature List
Analysis And Weighting Of Relationships Between Users
Detecting Persona Of Each User
Usable output for recommender systems
Sentiment Analysis
Approach Analysis
Thematic Analysis
Activity Analysis
Duration of technical development
9 Months
Any certification or proof of product testing
We tested the product both with a standard test dataset and in real environments. Our system achieved up to 90% mAP in a laboratory environment and up to 80% in real environments. For more details,
a Tensor board document is available.
Count of concurrent users in peak
Based on the fully asynchronous architecture used in the microservices design, it is easily scalable. The current production server with limited resources can serve about 10,000 requests for the end user and 500 requests for GPU-based processing simultaneously.
Tech Stack
AI: Python with TensorFlow Framework, OpenCV, BentoML Backend: Python with FastAPI Framework Data Base: MongoDB, Redis Frontend: Pure Web Application
Maintenance and development team
Ali Sobhani, Senior Developer of Artificial Intelligence and Backend