Bridging NL2SQL for CAN Signal Analytics at NIO: From Externalized Schemas to CTE Pipelines

Abstract

Large Language Models (LLMs) promise natural-language access to data, yet applying them to Controller Area Network (CAN) signal SQL analytics in the automotive industry is challenging. First, CAN data warehouses store tens of thousands of signals as opaque numeric columns. Multiple signals are often packed into a single column as bit segments, requiring external Database CAN (DBC) files beyond the native database schema for proper definitions. Second, engineers' natural-language queries often use terms that map to multiple signals in the DBC files, with little direct indication of which signals are being referenced. Finally, signal analysis in production involves multi-step SQL pipelines using layered Common Table Expressions (CTEs) for tasks such as temporal alignment, more complex than those handled by existing NL2SQL methods. To address these, we present NIO-Weaver, an end-to-end CAN signal analytics system within a graph-augmented multi-agent framework. First, to uncover signals hidden in opaque numeric columns, we introduce an automated graph-construction pipeline that leverages DBC files to build a domain-knowledge graph, associating signals with potential high-level terms. Second, to bridge the semantic gap between natural-language queries and multiple signals, we propose an optimized retrieval method that extracts terms from queries and performs hybrid retrieval. We combine regex matching, embedding search, and constrained graph traversal to identify candidate signals for further processing. Finally, to simplify the generation of multi-step CTE-based pipelines, we introduce a hierarchical generation paradigm. We decompose queries into plans, incrementally generating executable CTEs, while self-correction mechanisms refine missing signals and incorrect SQL. Experiments on the real-world industrial CAN warehouse at NIO demonstrate that NIO-Weaver outperforms baselines by up to 67.2%.