knowledge_search/tools/analyze_feature_matches.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
统计 how 解构文件中所有原始特征匹配到的分类/标签及其路径
"""

import json
from collections import defaultdict
from typing import Dict, List, Set, Any


def build_classification_path(classification_list: List[str]) -> str:
    """构建分类路径字符串"""
    if not classification_list:
        return ""
    return "/".join(classification_list)


def analyze_feature_matches(json_file_path: str) -> Dict[str, Any]:
    """
    分析文件中所有原始特征的匹配情况

    返回结构：
    {
        "原始特征1": {
            "匹配的分类标签": [
                {
                    "名称": "...",
                    "类型": "标签/分类",
                    "路径": "...",
                    "层级": "...",
                    "相似度": 0.xxx
                }
            ],
            "统计": {
                "总匹配数": xxx,
                "高相似度匹配数(>0.8)": xxx,
                "中等相似度匹配数(0.5-0.8)": xxx,
                "低相似度匹配数(<0.5)": xxx
            }
        }
    }
    """

    # 读取JSON文件
    with open(json_file_path, 'r', encoding='utf-8') as f:
        data = json.load(f)

    # 存储结果
    feature_matches = defaultdict(lambda: {
        "匹配的分类标签": [],
        "统计": {
            "高相似度匹配数(>=0.8)": 0
        }
    })

    # 遍历 how解构结果
    how_result = data.get('how解构结果', {})

    # 处理三种列表：灵感点列表、目的点列表、关键点列表
    for level_name in ['灵感点列表', '目的点列表', '关键点列表']:
        level_list = how_result.get(level_name, [])

        for item in level_list:
            # 遍历how步骤列表
            for step in item.get('how步骤列表', []):
                # 遍历每个步骤中的特征
                for feature in step.get('特征列表', []):
                    feature_name = feature.get('特征名称', '')
                    matches = feature.get('匹配结果', [])

                    if not feature_name:
                        continue

                    # 处理每个匹配结果
                    for match in matches:
                        persona_feature_name = match.get('人设特征名称', '')
                        feature_type = match.get('特征类型', '')
                        classification_list = match.get('特征分类', [])
                        feature_level = match.get('人设特征层级', '')
                        similarity = match.get('匹配结果', {}).get('相似度', 0)

                        # 只保留相似度>=0.8的匹配
                        if similarity < 0.8:
                            continue

                        # 构建路径
                        path = build_classification_path(classification_list)

                        # 添加到结果
                        match_info = {
                            "名称": persona_feature_name,
                            "类型": feature_type,
                            "路径": path,
                            "层级": feature_level,
                            "相似度": round(similarity, 3)
                        }

                        feature_matches[feature_name]["匹配的分类标签"].append(match_info)

                        # 更新统计
                        stats = feature_matches[feature_name]["统计"]
                        stats["高相似度匹配数(>=0.8)"] += 1

    # 对每个原始特征的匹配结果按相似度降序排序
    for feature_name in feature_matches:
        feature_matches[feature_name]["匹配的分类标签"].sort(
            key=lambda x: x["相似度"],
            reverse=True
        )

    return dict(feature_matches)


def print_summary(results: Dict[str, Any]):
    """打印统计摘要"""
    print("=" * 80)
    print("原始特征匹配统计摘要（仅相似度>=0.8）")
    print("=" * 80)

    total_features = len(results)
    # 统计有匹配的特征数
    features_with_matches = sum(1 for data in results.values() if data["统计"]["高相似度匹配数(>=0.8)"] > 0)

    print(f"\n总原始特征数: {total_features}")
    print(f"有高相似度匹配的特征数: {features_with_matches}")
    print(f"无匹配的特征数: {total_features - features_with_matches}")

    # 统计总体数据
    total_matches = 0

    for feature_name, data in results.items():
        stats = data["统计"]
        total_matches += stats["高相似度匹配数(>=0.8)"]

    print(f"\n总高相似度匹配数(>=0.8): {total_matches}")

    print("\n" + "=" * 80)
    print("各原始特征详细匹配情况")
    print("=" * 80)


def print_detailed_results(results: Dict[str, Any], top_n: int = None):
    """打印详细结果"""

    for idx, (feature_name, data) in enumerate(results.items(), 1):
        stats = data["统计"]
        matches = data["匹配的分类标签"]
        match_count = stats['高相似度匹配数(>=0.8)']

        # 跳过没有匹配的特征
        if match_count == 0:
            continue

        print(f"\n[{idx}] 原始特征: {feature_name}")
        print(f"    高相似度匹配数(>=0.8): {match_count}")

        # 显示所有匹配（如果指定了top_n则只显示前N个）
        display_matches = matches[:top_n] if top_n else matches
        print(f"    匹配列表（共{len(display_matches)}个）:")
        for i, match in enumerate(display_matches, 1):
            print(f"      {i}. {match['名称']} ({match['相似度']:.3f})")
            print(f"         类型: {match['类型']}, 层级: {match['层级']}")
            if match['路径']:
                print(f"         路径: {match['路径']}")
            else:
                print(f"         路径: (顶级分类)")


def save_results(results: Dict[str, Any], output_file: str):
    """保存结果到JSON文件"""
    with open(output_file, 'w', encoding='utf-8') as f:
        json.dump(results, f, ensure_ascii=False, indent=2)
    print(f"\n详细结果已保存到: {output_file}")


def main():
    # 输入文件路径
    input_file = "/Users/liulidong/project/pattern相关文件/optimization/690d977d0000000007036331_how.json"

    # 输出文件路径
    output_file = "/Users/liulidong/project/pattern相关文件/optimization/feature_matches_analysis.json"

    print("开始分析特征匹配...")

    # 分析
    results = analyze_feature_matches(input_file)

    # 打印摘要
    print_summary(results)

    # 打印详细结果（显示所有匹配，不限制数量）
    print_detailed_results(results, top_n=None)

    # 保存结果
    save_results(results, output_file)

    print("\n分析完成！")


if __name__ == "__main__":
    main()