摘要：安全关键型心理健康支持系统必须区分：何时适合进行支持性对话，何时应阻止自由形式生成。本文提出 Anian，这是一套面向围产期心理健康支持和正念干预分流的安全门控多模态 AI 后端。Anian 不旨在诊断精神疾病，也不替代临床照护或危机干预。其模块化流水线将生成式 AI 置于结构化状态表示、保守风险融合和响应门控之后。用户文本或由语音导出的 ASR 转录文本会被映射到四个相互关联的层级：L1 情绪状态、L2 心理社会构念、L3 安全风险，以及 L4 干预路径。本地基于文本和规则的安全证据，会通过最高风险优先规则与外部语音衍生证据相融合，即 S_fusion = max(S_local, S_external)。当融合风险处于中等或高等级时，系统会阻止普通 AI 生成回复和文本转语音交付，改以固定安全内容及寻求人工支持的提示取代。内部原型评估在弱标签和规则衍生框架下，使用了来自公开情绪、对话、心理健康相关及中文对话语料库的约 858,295 条归一化记录。L1 情绪分类的 Micro-F1 为 0.9604，L2 心理社会构念识别为 0.9144，L4 路由为 0.9742。在包含 233 个样本的受控安全压力测试中，L3 规则引擎在预定义场景内实现了 1.0000 的高风险召回率。这些发现支持该标签框架和门控逻辑在内部层面的可行性，但并未确立其临床有效性、诊断准确性、真实世界安全性或干预效果。本文报告了该架构、本体、安全融合机制、原型评估、误差分析计划，以及接受专家审查和真实世界验证的路线图。

Abstract:Safety-critical mental-health support systems must distinguish when supportive conversation is appropriate from when free-form generation should be blocked. This paper presents Anian, a safety-gated multimodal AI backend for perinatal mental-health support and mindfulness-intervention routing. Anian is not intended to diagnose psychiatric conditions or replace clinical care or crisis intervention. Its modular pipeline places generative AI downstream of structured state representation, conservative risk fusion, and response gating. User text or voice-derived ASR transcripts are mapped into four linked layers: L1 emotion states, L2 psychosocial constructs, L3 safety risk, and L4 intervention routes. Local text- and rule-based safety evidence is fused with external voice-derived evidence using a highest-risk-priority rule, S_fusion = max(S_local, S_external). At moderate or high fused risk, ordinary AI-generated responses and text-to-speech delivery are blocked and replaced by fixed safety content and prompts for human support. An internal prototype evaluation used approximately 858,295 normalized records from public emotion, dialogue, mental-health-related, and Chinese dialogue corpora within a weak-label and rule-derived framework. Micro-F1 scores were 0.9604 for L1 emotion classification, 0.9144 for L2 psychosocial constructs, and 0.9742 for L4 routing. In a controlled safety stress test of 233 samples, the L3 rule engine achieved high-risk recall of 1.0000 within predefined scenarios. These findings support the internal feasibility of the label framework and gating logic but do not establish clinical validity, diagnostic accuracy, real-world safety, or effectiveness. We report the architecture, ontology, safety-fusion mechanism, prototype evaluation, error-analysis plan, and roadmap for expert-reviewed and real-world validation.