Exploring the Development of Chinese Digital Resources under Lightweight Deep Learning.

Area of Science:

• Digital Economy
• Data Science
• Artificial Intelligence

Background:

• COVID-19 pandemic negatively impacted global economies.
• Digital economy emerged as a crucial driver for economic recovery.
• Urban Big Data (UBD) presents challenges in classification and security due to high dimensionality and lack of standards.

Purpose of the Study:

• To propose a novel Urban Big Data (UBD) classification and grading method.
• To enhance the security and value of high-value datasets.
• To analyze the development status and identify problems in China's digital economy and data resources.

Main Methods:

• Lightweight (LWT) deep learning (DL) clustering algorithm for data classification (DC).
• Semi-intelligent approach for creating hierarchical thesaurus, corpus, rule base, and model base.
• Big data analysis system integrating DL, spatiotemporal correlation, and big data technologies.
• Data visualization using Tableau for analysis of China's digital resources.

Main Results:

• A UBD classification and grading method was developed.
• Analysis revealed China's advanced digital infrastructure but underdeveloped trading infrastructure (41.65%).
• Low scores for China's digital economy in accounting (2.4), privacy (5.1), and security (11).

Conclusions:

• China's digital economy has significant growth potential in distribution and trading.
• Urgent need to improve data accounting, privacy, and security.
• Recommendations provided to promote data sharing, quality management, market activation, and security to enhance economic vitality.