Leading the construction of the company's big data platform products, covering data collection, master data management, data warehouse, data services, and labels.
Master Data Management: Established the 100Doc master data management system, mainly supporting manual editing and review of hospitals, doctors, drugs, conference posters, and data dictionaries.
Data Warehouse: Adopted dimensional modeling paradigm, provided OneID product logic for "individuals" and "institutions", and defined data models for HCP, HCO, medical knowledge, and academia.
Indicator System: Established an indicator system with 58 atomic indicators and 70+ dimensions.

Establish a macroeconomic database and AI economist to enhance internal macro investment research efficiency and provide automated macroeconomic interpretation to the public. Macroeconomic Database: A proprietary macroeconomic database owned by the company, covering data categories such as China's macroeconomics, regional macroeconomics, global macroeconomics, and industrial economics. Macroeconomic Analysis Dashboard: Targeted at government and corporate senior decision-making departments, it provides analysis, interpretation, and forecasts of global, Chinese, and even regional macroeconomics.

In 2019, federated learning, as an emerging technology for data collaboration, began to spread in China. I studied and researched it, and applied it to JD's Data Federation and Mu Media Data Platform.

Traditional Data Integration: Integrate feature or label data into one party, and use data from both parties to train and obtain a model. This poses risks of privacy data leakage and data asset outflow.

Federated Learning: Data owners can conduct joint training (exchange encrypted training parameters) and obtain an adequately accurate model (with a small gap compared to traditional data integration model) without disclosing their original data. The training target is either non-individual information or is authorized by users, and no party can infer the other's original data.

JD Mu Media Data Platform is the data marketplace of the Digital Marketing Ecosystem department, integrating the group's internal and external offline unique data capabilities. The goal is to drive offline marketing business development with data intelligence at its core and empower advertisers.

iZone Product: An offline commercial geographic big data analysis system. Through over 1 billion+ active user data coverage, it makes the site selection, operation, marketing, insight, and decision-making processes of offline physical businesses more scientific and efficient. Clients span industries including supermarkets, real estate, automobiles, tourism, exhibitions, and more.

XFlora is an online community for gardening, offering features such as a plant library, flower event records, group discussions, gardening manuals, and personal homepages to gardening enthusiasts. The vision is to popularize gardening and infuse city life with greenery. Together with entrepreneurial partners, we started with an initial idea and went through user research, needs analysis, product design, and development, successively launching web-based product features and operating content across multiple channels.

The demand side operates offline entertainment small theaters and hopes to develop applications for online live streaming, interaction, and review, in order to retain audiences and maximize the efficiency of offline entertainment.