Jelajahi Sumber

fix(sgsc-时效性审查模型-xth): 修复编号识别错误bug

suhua31 2 minggu lalu
induk
melakukan
2f79340223

+ 6 - 2
core/construction_review/component/ai_review_engine.py

@@ -678,8 +678,12 @@ class AIReviewEngine(BaseReviewer):
                 'StandardCategoryTable.csv'
             )
             
-            # 创建轻量级审查器
-            checker = LightweightCompletenessChecker(csv_path)
+            # 创建轻量级审查器(传入model_client用于LLM生成建议)
+            # self.model_client 是从 BaseReviewer 继承的
+            checker = LightweightCompletenessChecker(
+                csv_path,
+                model_client=getattr(self, 'model_client', None)
+            )
             
             # 从state获取outline和原始chunks(如果有)
             outline = None

+ 373 - 64
core/construction_review/component/reviewers/completeness_reviewer.py

@@ -15,6 +15,9 @@ from typing import Dict, List, Optional, Set, Tuple, Any
 from dataclasses import dataclass, field
 from collections import defaultdict
 from pathlib import Path
+import json
+
+from foundation.observability.logger.loggering import review_logger as logger
 
 
 @dataclass
@@ -180,18 +183,42 @@ class TertiarySpecLoader:
 
 class LightweightCompletenessChecker:
     """轻量级完整性检查器"""
-    
-    def __init__(self, standard_csv_path: str):
+
+    def __init__(self, standard_csv_path: str, model_client=None, prompt_loader=None):
         """
         初始化检查器
-        
+
         Args:
             standard_csv_path: StandardCategoryTable.csv 文件路径
+            model_client: 模型客户端(可选),用于生成智能建议
+            prompt_loader: 提示词加载器(可选)
         """
         self.spec_loader = TertiarySpecLoader(standard_csv_path)
         self.tertiary_specs = self.spec_loader.get_tertiary_items()
         self.secondary_specs = self.spec_loader.get_secondary_items()
         self.secondary_names = self.spec_loader.get_secondary_names()
+
+        # 大模型客户端和提示词加载器(用于生成智能建议)
+        self.model_client = model_client
+        self.prompt_loader = prompt_loader
+
+        # 如果没有提供model_client,尝试从foundation导入
+        if self.model_client is None:
+            try:
+                from foundation.ai.agent.generate.model_generate import generate_model_client
+                self.model_client = generate_model_client
+            except ImportError:
+                logger.warning("无法导入generate_model_client,建议生成功能将使用简单拼接模式")
+                self.model_client = None
+
+        # 如果没有提供prompt_loader,尝试从当前模块导入
+        if self.prompt_loader is None:
+            try:
+                from .utils.prompt_loader import prompt_loader
+                self.prompt_loader = prompt_loader
+            except ImportError:
+                logger.warning("无法导入prompt_loader,建议生成功能将使用简单拼接模式")
+                self.prompt_loader = None
     
     def _normalize_chapter_code(self, code: str) -> str:
         """将章节分类码大小写归一化为与CSV一致(如 'management' -> 'management')"""
@@ -202,6 +229,198 @@ class LightweightCompletenessChecker:
                 return k
         return code
 
+    def _build_llm_prompt_for_recommendation(
+        self,
+        level: str,
+        first_code: str,
+        first_name: str,
+        second_code: str = None,
+        second_name: str = None,
+        tertiary_items: List[TertiaryItem] = None,
+        outline_title: str = None
+    ) -> str:
+        """
+        构建用于LLM生成建议的prompt
+
+        Args:
+            level: 缺失级别(一级 / 二级 / 三级 / 一致性)
+            first_code: 一级分类代码
+            first_name: 一级分类名称
+            second_code: 二级分类代码(可选)
+            second_name: 二级分类名称(可选)
+            tertiary_items: 缺失的三级分类项列表(可选)
+            outline_title: 目录中的标题(用于一致性检查)
+
+        Returns:
+            str: 构建的prompt
+        """
+        # 构建问题上下文
+        if level == "一级":
+            context = f"""
+【问题类型】一级章节缺失
+【缺失章节】{first_name} ({first_code})
+【问题描述】文档中缺少'{first_name}'整个章节,这是专项施工方案中必须包含的一级章节。"""
+            # 获取该一级下的所有二级和三级信息作为参考
+            related_specs = []
+            for (fc, sc), sec_item in self.secondary_specs.items():
+                if fc == first_code:
+                    # 获取该二级下的所有三级
+                    tertiary_list = self.spec_loader.get_tertiary_by_secondary(fc, sc)
+                    tertiary_info = []
+                    for t_item in tertiary_list:
+                        tertiary_info.append(f"      - {t_item.third_cn}: {t_item.third_focus}")
+                    related_specs.append(f"""
+  【二级分类】{sec_item.second_cn}
+    【包含的三级内容要点】
+{chr(10).join(tertiary_info)}""")
+
+            reference = f"""
+【规范参考信息】
+根据《桥梁公司危险性较大工程管理实施细则(2025版)》,'{first_name}'章节应包含以下内容:
+{chr(10).join(related_specs)}
+"""
+
+        elif level == "二级":
+            context = f"""
+【问题类型】二级章节缺失
+【所属一级】{first_name} ({first_code})
+【缺失章节】{second_name} ({second_code})
+【问题描述】'{first_name}'下缺少'{second_name}'二级章节。"""
+            # 获取该二级下的所有三级信息
+            tertiary_list = self.spec_loader.get_tertiary_by_secondary(first_code, second_code)
+            tertiary_info = []
+            for t_item in tertiary_list:
+                tertiary_info.append(f"    - {t_item.third_cn}: {t_item.third_focus}")
+
+            reference = f"""
+【规范参考信息】
+根据《桥梁公司危险性较大工程管理实施细则(2025版)》,'{second_name}'章节应包含以下三级内容要点:
+{chr(10).join(tertiary_info)}
+"""
+
+        elif level == "三级":
+            context = f"""
+【问题类型】三级内容缺失
+【所属一级】{first_name} ({first_code})
+【所属二级】{second_name} ({second_code})
+【缺失内容】"""
+            missing_contents = []
+            for item in tertiary_items or []:
+                missing_contents.append(f"    - {item.third_cn}: {item.third_focus}")
+            context += "\n" + "\n".join(missing_contents)
+
+            reference = f"""
+【规范参考信息】
+以上缺失的内容要点是'{second_name}'章节下的标准内容要求,具体包括:
+{chr(10).join([f'  - {t.third_cn}: 应包含{t.third_focus}' for t in (tertiary_items or [])])}
+"""
+
+        elif level == "一致性":
+            context = f"""
+【问题类型】目录与正文不一致
+【涉及章节】{outline_title or second_name}
+【问题描述】目录页列有该章节,但正文中未发现对应内容。"""
+            reference = """
+【规范参考信息】
+根据文档一致性要求,目录中列出的章节应在正文中有对应的内容描述。若该章节确实不需要,应从目录中移除;若需要保留,则必须补充正文内容。
+"""
+        else:
+            context = "【问题类型】未知"
+            reference = ""
+
+        prompt = f"""你是一位资深的工程施工方案审查专家。请根据以下问题上下文和规范参考信息,生成专业的审查建议。
+
+{context}
+
+{reference}
+
+请用JSON格式输出审查建议,包含以下字段:
+- issue_point: 问题摘要(简洁明了,50字以内)
+- suggestion: 具体补充建议(详细可行,100-200字,包含具体应该补充的内容要点)
+- reason: 规范依据说明(引用具体规范要求,说明为什么需要补充)
+
+注意:
+1. suggestion应该具体、可操作,引用规范中的具体内容要求
+2. 使用专业的工程术语
+3. 语气应该是指导性的,帮助编制人员理解需要补充什么内容
+
+JSON输出:"""
+        return prompt
+
+    async def _generate_recommendation_with_llm(
+        self,
+        level: str,
+        first_code: str,
+        first_name: str,
+        second_code: str = None,
+        second_name: str = None,
+        tertiary_items: List[TertiaryItem] = None,
+        outline_title: str = None,
+        timeout: int = 30
+    ) -> Dict[str, str]:
+        """
+        使用大模型生成建议
+
+        Returns:
+            Dict[str, str]: 包含 issue_point, suggestion, reason 的字典
+        """
+        if not self.model_client:
+            return None
+
+        try:
+            prompt = self._build_llm_prompt_for_recommendation(
+                level=level,
+                first_code=first_code,
+                first_name=first_name,
+                second_code=second_code,
+                second_name=second_name,
+                tertiary_items=tertiary_items,
+                outline_title=outline_title
+            )
+
+            # 调用大模型
+            task_prompt_info = {
+                "task_prompt": prompt,
+                "task_name": f"completeness_suggestion_{level}"
+            }
+
+            # 生成唯一trace_id
+            import uuid
+            trace_id = f"completeness_llm_{uuid.uuid4().hex[:8]}"
+
+            model_response = await self.model_client.get_model_generate_invoke(
+                trace_id=trace_id,
+                task_prompt_info=task_prompt_info,
+                timeout=timeout,
+                model_name="qwen"  # 使用默认模型,可根据需要调整
+            )
+
+            # 解析模型返回的JSON
+            try:
+                # 尝试从返回文本中提取JSON
+                response_text = model_response.strip()
+                # 查找JSON块
+                if "```json" in response_text:
+                    json_str = response_text.split("```json")[1].split("```")[0].strip()
+                elif "```" in response_text:
+                    json_str = response_text.split("```")[1].split("```")[0].strip()
+                else:
+                    json_str = response_text
+
+                result = json.loads(json_str)
+                return {
+                    "issue_point": result.get("issue_point", ""),
+                    "suggestion": result.get("suggestion", ""),
+                    "reason": result.get("reason", "")
+                }
+            except (json.JSONDecodeError, IndexError) as e:
+                logger.warning(f"LLM建议生成结果解析失败: {e},返回: {model_response[:200]}")
+                return None
+
+        except Exception as e:
+            logger.warning(f"LLM建议生成失败: {e}")
+            return None
+
     async def check(
         self,
         chunks: List[Dict],
@@ -259,7 +478,7 @@ class LightweightCompletenessChecker:
 
         # 7. 生成分级建议
         actual_first = {cat1 for cat1, _ in actual_secondary}
-        recommendations = self._generate_recommendations(
+        recommendations = await self._generate_recommendations(
             tertiary_result, catalogue_result, outline_result,
             actual_first, actual_secondary, actual_tertiary,
             chapter_classification
@@ -636,7 +855,7 @@ class LightweightCompletenessChecker:
         else:
             return "incomplete"
     
-    def _generate_recommendations(
+    async def _generate_recommendations(
         self,
         tertiary_result: Dict,
         catalogue_result: Dict,
@@ -653,8 +872,8 @@ class LightweightCompletenessChecker:
           level        : 缺失级别(一级 / 二级 / 三级 / 一致性)
           issue_point  : 问题摘要(含级别标识)
           location     : 问题定位路径
-          suggestion   : 补充建议
-          reason       : 规范依据说明
+          suggestion   : 补充建议(使用LLM生成)
+          reason       : 规范依据说明(使用LLM生成)
         """
         recommendations: List[Dict[str, Any]] = []
 
@@ -679,17 +898,36 @@ class LightweightCompletenessChecker:
 
             # ── 一级缺失 ──────────────────────────────────────────────
             if first_code not in actual_first:
-                recommendations.append({
-                    "level": "一级",
-                    "issue_point": f"【一级章节缺失】'{first_name}'整个章节不存在",
-                    "location": first_name,
-                    "suggestion": f"请添加'{first_name}'章节及其下全部子章节内容",
-                    "reason": (
-                        f"根据规范要求,文档必须包含'{first_name}'一级章节,"
-                        f"当前正文中未发现该章节任何内容"
-                    ),
-                    "first_seq": first_seq,
-                })
+                # 尝试使用LLM生成建议
+                llm_result = await self._generate_recommendation_with_llm(
+                    level="一级",
+                    first_code=first_code,
+                    first_name=first_name,
+                    first_seq=first_seq
+                )
+
+                if llm_result:
+                    recommendations.append({
+                        "level": "一级",
+                        "issue_point": llm_result.get("issue_point", f"【一级章节缺失】'{first_name}'整个章节不存在"),
+                        "location": first_name,
+                        "suggestion": llm_result.get("suggestion", f"请添加'{first_name}'章节及其下全部子章节内容"),
+                        "reason": llm_result.get("reason", f"根据规范要求,文档必须包含'{first_name}'一级章节,当前正文中未发现该章节任何内容"),
+                        "first_seq": first_seq,
+                    })
+                else:
+                    # 回退到简单拼接
+                    recommendations.append({
+                        "level": "一级",
+                        "issue_point": f"【一级章节缺失】'{first_name}'整个章节不存在",
+                        "location": first_name,
+                        "suggestion": f"请添加'{first_name}'章节及其下全部子章节内容",
+                        "reason": (
+                            f"根据规范要求,文档必须包含'{first_name}'一级章节,"
+                            f"当前正文中未发现该章节任何内容"
+                        ),
+                        "first_seq": first_seq,
+                    })
                 continue
 
             # ── 一级存在,检查二级 ─────────────────────────────────────
@@ -703,20 +941,41 @@ class LightweightCompletenessChecker:
 
                 # ── 二级缺失 ──────────────────────────────────────────
                 if (cat1, cat2) not in actual_secondary:
-                    recommendations.append({
-                        "level": "二级",
-                        "issue_point": (
-                            f"【二级章节缺失】{first_name} > '{second_name}'整个章节不存在"
-                        ),
-                        "location": f"{first_name} > {second_name}",
-                        "suggestion": f"请在'{first_name}'下添加'{second_name}'章节内容",
-                        "reason": (
-                            f"根据规范要求,'{first_name}'下应包含'{second_name}'二级章节,"
-                            f"当前正文中未发现该章节内容"
-                        ),
-                        "first_seq": first_seq,
-                        "second_seq": second_seq,
-                    })
+                    # 尝试使用LLM生成建议
+                    llm_result = await self._generate_recommendation_with_llm(
+                        level="二级",
+                        first_code=cat1,
+                        first_name=first_name,
+                        second_code=cat2,
+                        second_name=second_name
+                    )
+
+                    if llm_result:
+                        recommendations.append({
+                            "level": "二级",
+                            "issue_point": llm_result.get("issue_point", f"【二级章节缺失】{first_name} > '{second_name}'整个章节不存在"),
+                            "location": f"{first_name} > {second_name}",
+                            "suggestion": llm_result.get("suggestion", f"请在'{first_name}'下添加'{second_name}'章节内容"),
+                            "reason": llm_result.get("reason", f"根据规范要求,'{first_name}'下应包含'{second_name}'二级章节,当前正文中未发现该章节内容"),
+                            "first_seq": first_seq,
+                            "second_seq": second_seq,
+                        })
+                    else:
+                        # 回退到简单拼接
+                        recommendations.append({
+                            "level": "二级",
+                            "issue_point": (
+                                f"【二级章节缺失】{first_name} > '{second_name}'整个章节不存在"
+                            ),
+                            "location": f"{first_name} > {second_name}",
+                            "suggestion": f"请在'{first_name}'下添加'{second_name}'章节内容",
+                            "reason": (
+                                f"根据规范要求,'{first_name}'下应包含'{second_name}'二级章节,"
+                                f"当前正文中未发现该章节内容"
+                            ),
+                            "first_seq": first_seq,
+                            "second_seq": second_seq,
+                        })
                     continue
 
                 # ── 二级存在,检查三级缺失 ────────────────────────────
@@ -734,40 +993,82 @@ class LightweightCompletenessChecker:
                 if not missing_t_items:
                     continue
 
-                # 为每个缺失的三级项创建单独的 recommendation
-                for t_item in missing_t_items:
-                    recommendations.append({
-                        "level": "三级",
-                        "issue_point": (
-                            f"【三级内容缺失】{first_name} > {second_name} > '{t_item.third_cn}'"
-                        ),
-                        "location": f"{first_name} > {second_name}",
-                        "suggestion": f"请补充'{second_name}'下的'{t_item.third_cn}'内容",
-                        "reason": f"'{second_name}'下缺失规范要求的'{t_item.third_cn}'内容要点",
-                        "first_seq": first_seq,
-                        "second_seq": second_seq,
-                        "third_seq": t_item.third_seq,
-                    })
+                # 尝试使用LLM批量生成三级缺失建议
+                llm_result = await self._generate_recommendation_with_llm(
+                    level="三级",
+                    first_code=cat1,
+                    first_name=first_name,
+                    second_code=cat2,
+                    second_name=second_name,
+                    tertiary_items=missing_t_items
+                )
+
+                if llm_result:
+                    # LLM生成了整体建议,为每个缺失项添加相同建议(但位置不同)
+                    for t_item in missing_t_items:
+                        recommendations.append({
+                            "level": "三级",
+                            "issue_point": f"【三级内容缺失】{first_name} > {second_name} > '{t_item.third_cn}'",
+                            "location": f"{first_name} > {second_name}",
+                            "suggestion": llm_result.get("suggestion", f"请补充'{second_name}'下的'{t_item.third_cn}'内容"),
+                            "reason": llm_result.get("reason", f"'{second_name}'下缺失规范要求的'{t_item.third_cn}'内容要点"),
+                            "first_seq": first_seq,
+                            "second_seq": second_seq,
+                            "third_seq": t_item.third_seq,
+                        })
+                else:
+                    # 回退到简单拼接
+                    for t_item in missing_t_items:
+                        recommendations.append({
+                            "level": "三级",
+                            "issue_point": (
+                                f"【三级内容缺失】{first_name} > {second_name} > '{t_item.third_cn}'"
+                            ),
+                            "location": f"{first_name} > {second_name}",
+                            "suggestion": f"请补充'{second_name}'下的'{t_item.third_cn}'内容",
+                            "reason": f"'{second_name}'下缺失规范要求的'{t_item.third_cn}'内容要点",
+                            "first_seq": first_seq,
+                            "second_seq": second_seq,
+                            "third_seq": t_item.third_seq,
+                        })
 
         # ── 一致性审查:目录有列但正文无内容 ─────────────────────────────
         if outline_result:
             for e in outline_result.get("empty_sections", []):
                 f_name = e.get("first_name", "")
-                # 优先用目录页原始标题,回退到标准名称
                 sec_title = e.get("outline_title") or e.get("secondary_name", "")
                 location = f"{f_name} > {sec_title}" if f_name else sec_title
-                recommendations.append({
-                    "level": "一致性",
-                    "issue_point": f"【目录正文不一致】'{location}'目录已列但正文无内容",
-                    "location": location,
-                    "suggestion": (
-                        f"请补充'{sec_title}'章节的正文内容,或从目录中移除该章节"
-                    ),
-                    "reason": (
-                        f"目录页列有'{sec_title}'章节,但正文中未发现对应内容,"
-                        f"存在目录与正文不一致的问题"
-                    ),
-                })
+
+                # 尝试使用LLM生成建议
+                llm_result = await self._generate_recommendation_with_llm(
+                    level="一致性",
+                    first_code="",
+                    first_name=f_name,
+                    second_name=sec_title,
+                    outline_title=sec_title
+                )
+
+                if llm_result:
+                    recommendations.append({
+                        "level": "一致性",
+                        "issue_point": llm_result.get("issue_point", f"【目录正文不一致】'{location}'目录已列但正文无内容"),
+                        "location": location,
+                        "suggestion": llm_result.get("suggestion", f"请补充'{sec_title}'章节的正文内容,或从目录中移除该章节"),
+                        "reason": llm_result.get("reason", f"目录页列有'{sec_title}'章节,但正文中未发现对应内容,存在目录与正文不一致的问题"),
+                    })
+                else:
+                    recommendations.append({
+                        "level": "一致性",
+                        "issue_point": f"【目录正文不一致】'{location}'目录已列但正文无内容",
+                        "location": location,
+                        "suggestion": (
+                            f"请补充'{sec_title}'章节的正文内容,或从目录中移除该章节"
+                        ),
+                        "reason": (
+                            f"目录页列有'{sec_title}'章节,但正文中未发现对应内容,"
+                            f"存在目录与正文不一致的问题"
+                        ),
+                    })
 
         if not recommendations:
             recommendations.append({
@@ -785,16 +1086,20 @@ class LightweightCompletenessChecker:
 async def check_completeness_lightweight(
     chunks: List[Dict],
     outline: Optional[List[Dict]] = None,
-    standard_csv_path: Optional[str] = None
+    standard_csv_path: Optional[str] = None,
+    model_client=None,
+    prompt_loader=None
 ) -> LightweightCompletenessResult:
     """
     轻量级完整性审查入口函数
-    
+
     Args:
         chunks: 文档分块列表,每个chunk需包含tertiary_category_code
         outline: 目录结构(可选)
         standard_csv_path: 三级标准CSV文件路径,默认为doc_worker/config/StandardCategoryTable.csv
-    
+        model_client: 模型客户端(可选),用于生成智能建议
+        prompt_loader: 提示词加载器(可选)
+
     Returns:
         LightweightCompletenessResult
     """
@@ -802,8 +1107,12 @@ async def check_completeness_lightweight(
         # 默认路径
         default_path = Path(__file__).parent.parent.parent.parent.parent / "doc_worker" / "config" / "StandardCategoryTable.csv"
         standard_csv_path = str(default_path)
-    
-    checker = LightweightCompletenessChecker(standard_csv_path)
+
+    checker = LightweightCompletenessChecker(
+        standard_csv_path,
+        model_client=model_client,
+        prompt_loader=prompt_loader
+    )
     return await checker.check(chunks=chunks, outline=outline)
 
 

+ 5 - 5
core/construction_review/component/reviewers/timeliness_content_reviewer.py

@@ -46,14 +46,14 @@ class StandardExtractor:
 
     # 规范编号正则模式(匹配类似 GB 50010-2010、JTG B01-2014、GB/T 50502-2020 等格式)
     STANDARD_NUMBER_PATTERNS = [
-        # 中国国家标准:GB 50010-2010、GB/T 50502-2020
-        r'GB(?:/T)?\s*\d{4,5}(?:\.\d+)?\s*-\s*\d{4}',
+        # 中国国家标准:GB 50010-2010、GB/T 50502-2020、GB 51-2001
+        r'GB(?:/T)?\s*\d{1,5}(?:\.\d+)?\s*-\s*\d{4}',
         # 中国行业标准:JTG B01-2014、JTG D60-2015、JTG/T 3650-2020
-        r'[A-Z]{2,3}(?:/T)?\s*[A-Z]?\s*\d{2,4}(?:\.\d+)?\s*-\s*\d{4}',
+        r'[A-Z]{2,3}(?:/T)?\s*[A-Z]?\s*\d{1,5}(?:\.\d+)?\s*-\s*\d{4}',
         # 地方标准:DB11/T 1234-2020
-        r'DB\d{2}(?:/T)?\s*\d{4,5}\s*-\s*\d{4}',
+        r'DB\d{2}(?:/T)?\s*\d{1,5}\s*-\s*\d{4}',
         # 团体标准:T/CECS 123-2020
-        r'T/\w+\s*\d{3,5}\s*-\s*\d{4}',
+        r'T/\w+\s*\d{1,5}\s*-\s*\d{4}',
     ]
 
     # 规范名称与编号组合的正则模式

+ 87 - 28
core/construction_review/component/reviewers/utils/reference_matcher.py

@@ -283,13 +283,16 @@ async def validate_and_generate_number(
     if existing_number:
         logger.info(f"[时效性验证] 验证编号: 《{regulation_name}》 {existing_number}")
         
-        # 先进行本地标准化比较:检查参考候选中是否有编号完全匹配(忽略括号差异)的
-        normalized_existing = _normalize_text(existing_number)
+        # 先进行本地标准化比较:检查参考候选中是否有名称和编号都完全匹配(忽略括号差异)的
+        normalized_existing_number = _normalize_text(existing_number)
+        normalized_regulation_name = _normalize_text(regulation_name)
         for candidate in reference_candidates:
-            # 从候选中提取编号
-            _, candidate_number = _extract_regulation_info(candidate)
-            if candidate_number and _normalize_text(candidate_number) == normalized_existing:
-                logger.info(f"[时效性验证] 本地验证通过(编号匹配): 《{regulation_name}》 {existing_number}")
+            # 从候选中提取名称和编号
+            candidate_name, candidate_number = _extract_regulation_info(candidate)
+            if (candidate_name and candidate_number and
+                _normalize_text(candidate_name) == normalized_regulation_name and
+                _normalize_text(candidate_number) == normalized_existing_number):
+                logger.info(f"[时效性验证] 本地验证通过(名称和编号都匹配): 《{regulation_name}》 {existing_number}")
                 return ValidationMatchResult(
                     review_item=review_item,
                     reference_candidates=reference_candidates,
@@ -297,6 +300,21 @@ async def validate_and_generate_number(
                     validated_number=existing_number,
                     status="验证通过"
                 )
+
+        # 【关键】检查是否有编号相同但名称不同的情况(规范名称错误)
+        for candidate in reference_candidates:
+            candidate_name, candidate_number = _extract_regulation_info(candidate)
+            if (candidate_name and candidate_number and
+                _normalize_text(candidate_number) == normalized_existing_number and
+                _normalize_text(candidate_name) != normalized_regulation_name):
+                logger.info(f"[时效性验证] 编号相同但名称不同: 《{regulation_name}》-> 应为《{candidate_name}》")
+                return ValidationMatchResult(
+                    review_item=review_item,
+                    reference_candidates=reference_candidates,
+                    is_valid=False,
+                    validated_number=existing_number,
+                    status="规范名称错误"
+                )
         
         # 调用3模型验证
         validation = await validate_reference_number(
@@ -432,28 +450,34 @@ async def match_reference_files(reference_text: str, review_text: str) -> str:
         exact_info = raw_item.get("exact_match_info", "")
         same_name_current = raw_item.get("same_name_current", "")
         
-        # 【校正逻辑】如果LLM判断has_exact_match=false,但本地比较发现编号相同(忽略括号差异),则校正为true
+        # 【校正逻辑】如果LLM判断has_exact_match=false,但本地比较发现名称和编号相同(忽略括号差异),则校正为true
         if not has_exact and exact_info:
-            _, review_number = _extract_regulation_info(review_item)
-            _, exact_number = _extract_regulation_info(exact_info)
-            if review_number and exact_number and _normalize_text(review_number) == _normalize_text(exact_number):
-                logger.info(f"[规范匹配校正] review_item='{review_item}' 编号实质相同,校正has_exact_match为true")
+            review_name, review_number = _extract_regulation_info(review_item)
+            exact_name, exact_number = _extract_regulation_info(exact_info)
+            if (review_name and exact_name and
+                _normalize_text(review_name) == _normalize_text(exact_name) and
+                review_number and exact_number and
+                _normalize_text(review_number) == _normalize_text(exact_number)):
+                logger.info(f"[规范匹配校正] review_item='{review_item}' 名称和编号都相同,校正has_exact_match为true")
                 has_exact = True
         
-        # 【第一步】先检查向量搜索候选中是否有精确匹配(编号完全相同)
+        # 【第一步】检查向量搜索候选中的匹配情况
         # ref_candidates 是 List[List[str]],需要获取当前项对应的候选列表
         current_candidates = ref_candidates[i] if i < len(ref_candidates) else []
-        _, review_number = _extract_regulation_info(review_item)
-        
-        if review_number and current_candidates:
+        review_name, review_number = _extract_regulation_info(review_item)
+
+        if review_name and review_number and current_candidates:
+            normalized_review_name = _normalize_text(review_name)
             normalized_review_number = _normalize_text(review_number)
-            exact_match_found = False
-            
+
+            # 先检查是否有完全匹配(名称和编号都相同)
             for candidate in current_candidates:
                 if isinstance(candidate, str):
-                    _, candidate_number = _extract_regulation_info(candidate)
-                    if candidate_number and _normalize_text(candidate_number) == normalized_review_number:
-                        # 向量库中找到精确匹配,直接使用,不需要AI投票
+                    candidate_name, candidate_number = _extract_regulation_info(candidate)
+                    if (candidate_name and candidate_number and
+                        _normalize_text(candidate_name) == normalized_review_name and
+                        _normalize_text(candidate_number) == normalized_review_number):
+                        # 向量库中找到精确匹配(名称和编号都相同)
                         logger.info(f"[规范匹配] 向量库中找到精确匹配: '{review_item}' -> '{candidate}'")
                         final_results.append({
                             "review_item": review_item,
@@ -462,11 +486,34 @@ async def match_reference_files(reference_text: str, review_text: str) -> str:
                             "exact_match_info": candidate,
                             "same_name_current": candidate
                         })
-                        exact_match_found = True
+                        has_exact = True
                         break
-            
-            # 如果找到了精确匹配,跳过本次循环
-            if exact_match_found:
+
+            if has_exact:
+                continue
+
+            # 【关键】检查是否有编号相同但名称不同的情况(规范名称错误)
+            for candidate in current_candidates:
+                if isinstance(candidate, str):
+                    candidate_name, candidate_number = _extract_regulation_info(candidate)
+                    if (candidate_name and candidate_number and
+                        _normalize_text(candidate_number) == normalized_review_number and
+                        _normalize_text(candidate_name) != normalized_review_name):
+                        # 编号相同但名称不同 - 判定为规范名称错误
+                        logger.info(f"[规范匹配] 编号相同但名称不同: '{review_item}' -> '{candidate}'")
+                        final_results.append({
+                            "review_item": review_item,
+                            "has_related_file": True,
+                            "has_exact_match": False,
+                            "exact_match_info": "",
+                            "same_name_current": candidate,
+                            "name_mismatch": True,  # 标记为名称不匹配
+                            "correct_name": candidate_name  # 正确的名称
+                        })
+                        has_exact = True  # 标记为已处理,跳过后续逻辑
+                        break
+
+            if has_exact:
                 continue
         
         # 如果有精确匹配(由LLM判断),直接接受
@@ -492,12 +539,24 @@ async def match_reference_files(reference_text: str, review_text: str) -> str:
                 if validation_result.validated_number:
                     # 【关键逻辑】检查生成的编号与原始编号是否属于同一规范家族
                     is_same_family = _is_same_regulation_family(
-                        review_number or "", 
+                        review_number or "",
                         validation_result.validated_number
                     )
-                    
-                    if not is_same_family:
-                        # 生成的编号与原始编号完全不同,说明参考库中找到的文件实际上不相关
+
+                    # 【特殊处理】检查参考候选中是否有名称完全匹配的文件
+                    # 如果名称相同但编号不同(如 GB 51-2001 vs GB 50021-2001),应接受生成的编号
+                    has_same_name_in_candidates = False
+                    for candidate in current_candidates:
+                        if isinstance(candidate, str):
+                            candidate_name, _ = _extract_regulation_info(candidate)
+                            if (candidate_name and
+                                _normalize_text(candidate_name) == _normalize_text(review_name)):
+                                has_same_name_in_candidates = True
+                                break
+
+                    if not is_same_family and not has_same_name_in_candidates:
+                        # 生成的编号与原始编号完全不同,且参考库中没有名称匹配的文件
+                        # 说明参考库中找到的文件实际上不相关
                         logger.info(f"[规范匹配] '{review_item}' 生成的编号({validation_result.validated_number})"
                                   f"与原始编号({review_number})不属于同一规范家族,判定为无相关文件")
                         final_results.append({

+ 11 - 5
core/construction_review/component/reviewers/utils/timeliness_determiner.py

@@ -55,22 +55,28 @@ HUMAN = """
    - 原因:在参考规范库中完全找不到相关文件
    - 建议:当前引用未在参考规范库中发现,建议人工核实其有效性
 
-2. **规范编号错误**(高风险)
-   - 条件:has_related_file = true 且 has_exact_match = false
+2. **规范名称错误**(高风险)
+   - 条件:name_mismatch = true(编号相同但名称不同)
+   - 原因:规范编号正确,但规范名称错误。审查引用的是《错误名称》(编号),参考库中应为《正确名称》(编号)
+   - 建议:建议将规范名称更正为《正确名称》(编号)
+   - **重要**:必须从 correct_name 字段获取正确的规范名称
+
+3. **规范编号错误**(高风险)
+   - 条件:has_related_file = true 且 has_exact_match = false 且 name_mismatch 不存在或不为true
    - 原因:与参考文件XXX编号不一致(注意:仅当编号实质性不同时才算不一致,忽略括号格式差异)
    - 建议:建议核实并更正为参考库中的正确编号XXX
 
-3. **规范编号正确**(无风险)
+4. **规范编号正确**(无风险)
    - 条件:has_exact_match = true 且 exact_match_info 中状态为"现行"
    - 原因:与参考文件XXX名称编号一致,且文件状态为现行
    - 建议:引用规范为现行有效版本,无需调整
 
-4. **引用已废止的规范**(高风险)
+5. **引用已废止的规范**(高风险)
    - 条件:has_exact_match = true 且 exact_match_info 中状态为"废止" 且 same_name_current 为空
    - 原因:参考文件显示XXX已废止,且无明确替代版本
    - 建议:建议删除该引用或咨询最新替代规范
 
-5. **引用已被替代的规范**(高风险)
+6. **引用已被替代的规范**(高风险)
    - 条件:has_exact_match = true 且 exact_match_info 中状态为"废止" 且 same_name_current 不为空
    - 原因:参考文件显示《规范名称》(原编号)已废止,存在现行版本《规范名称》(新编号)
    - 建议:建议更新为现行版本《规范名称》(新编号),并核实其适用性