---
title: Project Digital-Customer-Hub-Prototype
emoji: 🏢
colorFrom: indigo
colorTo: pink
sdk: gradio
sdk_version: 6.2.0
app_file: app.py
pinned: false
short_description: Automating Lead Scoring & CRM Integration for Global Sales O
---

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference


Here is a comprehensive GitHub README structure tailored to the Molex Project Engineer role. This is designed to show a hiring manager that you understand the intersection of Data Engineering, AI, and Business Value.

Project: Sales-Ops Intelligence Hub (DCH Prototype)
Automating Lead Scoring & CRM Integration for Global Sales Operations
1. Project Overview
This is a Proof of Concept Digital Customer Hub intelligence layer focused on sales lead triaging and customer interaction understanding.

Automation: Eliminates manual data entry and lead categorization.

Lead Scoring: Implements an AI-driven priority matrix.

Data Integration: Generates structured JSON outputs ready for SAP and Salesforce ingestion.

2. Technical Architecture
The system is built using a modern data engineering stack:

Intelligence Engine: Hugging Face BART-Large-MNLI (Zero-Shot Classification).

UI/Interface: Gradio (for stakeholder demonstration and feedback).

Data Processing: Python (Pandas/JSON).

Environment: Google Colab.

3. Implementation Details
A. Intent Classification & Lead Scoring
The model identifies four specific business intents without requiring a pre-labeled dataset:

Urgent RFQ (High Priority)

Sales Opportunity (High Priority)

Technical Support (Medium Priority)

General Inquiry (Low Priority)

B. Data Pipeline Logic
The system performs a Clean-Score-Structure workflow:

Ingestion: Receives raw text from Sales/Customer Service logs.

AI Analysis: Calculates a confidence score for the detected intent.

Prioritization: A logic-based script assigns a "System Priority" based on the AI's confidence and the intent type.

Output: Produces a standardized JSON object to maintain Data Integrity across global systems.

4. Business Impact (Projected)
Efficiency: Estimated 90% reduction in time spent by sales teams on manual lead qualification.

Accuracy: Improved lead routing through a synchronized "Intelligence Engine."

Scalability: Modular Python code allows for rapid deployment as an API or cloud-based microservice (AWS/Azure).

5. How to Run
Open the Google Colab Notebook.

Install dependencies: pip install transformers torch gradio pandas.

Run the final cell to launch the Gradio interactive dashboard.

Input a sample customer email (e.g., "I need a technical quote for the new connector series ASAP") to see real-time lead scoring.