PRODUCT · StarPlex Pharmaceutical AI Agent Platform

One intelligent foundation, four native capabilities, data-driven decision support across multiple workflows.

StarPlex is a pharmaceutical AI agent platform independently developed by Weiming Penguin. It deeply integrates four core AI technologies—knowledge graphs, dynamic ontology modeling, large-model cognition, and multi-agent collaboration—to create an AI-native solution spanning data collection → real-time cleansing → decision support → business execution, delivering intelligent data capabilities across multiple workflows for the pharmaceutical industry.

01
StarLink
Intelligent Multimodal Data Collection
02
StarFlow
Real-Time Data Cleansing
03
StarCore
Industry Databases with Unified Semantics
04
StarRealm
Cross-Domain Relational Reasoning
01 · Product Portfolio

Four products. One shared semantic framework.

01 StarLink
Intelligent Multimodal Data Collection

Take control of your data at the source

Intelligent multimodal data collection covers 12 types of heterogeneous data sources, including direct DDI connections, shipments, traceability codes, distribution flow data, e-commerce, DTP, and O2O, with AI-driven real-time collection and governance. Collect data without stationing staff on-site.

Dynamic ontologies Multimodal collection Remote operations and maintenance Semantic alignment
KEY METRICS · Key Outcomes
High
AI capability share
Numerous
Direct connections to distributors / chains
Large-scale
Real-time processing
02 StarFlow
Real-time data cleansing · Tiangong™ engine

Significantly improve cleansing accuracy

The Tiangong™ pharmaceutical matching engine continues to advance through six generations, from “Manual · Zero Start” to “Tiangong · Sixfold,” improving cleansing rates and accuracy with morphological matching, dynamic scoring, pharmaceutical small models, LLM Embedding, and RAG Rerank.

Tiangong™ LLM Embedding RAG Rerank Real-time governance
KEY METRICS · Key Outcomes
High
Cleansing accuracy
Sixfold
Tiangong Generation 6
Real-time
Governance frequency
03 StarCore
Industry Databases with Unified Semantics

Turn data from a “silent asset” into productive value

An enterprise-grade data asset workspace that consolidates pharmaceutical master data, with broad coverage of HCOs, HCPs, and scholarly literature resources. Build an intelligent closed loop of “data → analysis → prediction → decisions → action.”

Knowledge graphs Ontologies Industry databases Decision support
KEY METRICS · Core Databases
Broad
HCO healthcare organizations
Extensive
HCP pharmaceutical experts
Continuously updated
Scholarly literature
04 StarRealm
Cross-domain relational reasoning · Central AI orchestration engine

An enterprise-grade, AI-native operational hub

Four-layer architecture: AI data foundation → AI monitoring and alerts → AI analysis and decision support → AI-automated execution. Integrates GeoAI, GNN, NL2SQL, generative AI, and multimodal perception.

GeoAI GNN NL2SQL Generative AI
KEY MODULES · Core Modules
4 layers
Complete architecture
Multi-agent
Collaboration framework
Closed loop
From data to execution
02 · Core Technologies

Four core AI technologies, one pharmaceutical-specific semantic framework.

01
Knowledge graph
Knowledge Graph
Build pharmaceutical knowledge graphs and align semantics across domains, moving from “standardized fields” to “intelligent data assets.”
02
Dynamic ontology modeling
Dynamic Ontology
Adapt to heterogeneous data from multiple sources with self-evolving collection patterns, connecting new data sources with less custom development.
03
Cross-Domain Relational Reasoning
Cross-domain Reasoning
Connect nodes across multiple workflows and identify hidden contributions to value, moving from “fragmentation” to “reasoning across multiple workflows.”
04
Decision support
Decision Intelligence
Multi-agent collaboration: advance alerts → in-process tracking → retrospective attribution, moving from “human decision-making” to “AI-assisted decision-making.”

Ready to put data back at the heart of decision-making?

View Customer Stories