摘要：大语言模型能够理解自然语言化学问题，但其内部推理过程难以检查、约束和验证。本文提出 ChemOntoRule，这是一个用于 AI 辅助中学阶段化学问题求解的概念验证型符号核心。其核心设计选择是以任务为中心的本体工程：本体围绕一组已定义化学问题所需的概念、属性、关系和可执行程序构建，而非将其作为化学知识的通用表示。实现的系统将以 JSON 和 RDF/Turtle 序列化的轻量级本体，与针对电子结构、周期性趋势、氧化态、氧化物与氢化物行为及其他中学阶段推理模式的确定性 Python 规则相结合。对于尚未由通用规则表示的问题类别，系统另设独立的专家编码回退机制。研究在 300 道由人工编写并手工验证的化学题目上检验了该系统。完整系统与 300 个参考答案中的 296 个相匹配（98.67%）。本体驱动的规则子集覆盖 269 道题目，并与其中 266 个参考答案匹配（98.88%）；另有 31 道题目由任务特定的专家编码回退机制处理，其中 30 道匹配。由于同一题集同时用于指导本体构建和评估，这些结果衡量的是已实现的覆盖度与内部一致性，而非独立泛化能力。本文分析了 4 个不匹配案例，区分了结构验证与化学正确性，并定义了一种未来架构：语言模型主要充当从用户语言到标准化本体任务框架的翻译器。Token 效率被提出为未来受控研究中可检验的假设，而非本研究的当前结论。

Abstract:Large language models can interpret natural-language chemistry questions, but their internal reasoning is difficult to inspect, constrain, and validate. This paper presents ChemOntoRule, a proof-of-concept symbolic core for AI-assisted school-level chemistry problem solving. The central design choice is task-centric ontology engineering: the ontology is constructed around the concepts, properties, relations, and executable procedures required by a defined collection of chemistry problems, rather than as a universal representation of chemistry. The implemented artifact combines a lightweight ontology serialized in JSON and RDF/Turtle with deterministic Python rules for electronic structure, periodic trends, oxidation states, oxide and hydride behavior, and related school-level reasoning patterns. A separate expert-coded fallback handles problem families not yet represented by general rules. The system was examined on 300 human-authored and manually validated chemistry problems. The complete system matched 296 of 300 reference answers (98.67%). The ontology-driven rule subset covered 269 problems and matched 266 references (98.88%); 31 problems were handled by task-specific expert-coded fallbacks, with 30 matches. Because the same collection informed ontology construction and evaluation, these results measure implemented coverage and internal consistency, not independent generalization. We analyze the four mismatches, distinguish structural validation from chemical correctness, and define a future architecture in which a language model acts primarily as a translator from user language into a normalized ontological task frame. Token efficiency is presented as a testable hypothesis for future controlled studies, not as a result of the current work.