#命名实体识别(NER)：从文本中精准提取关键信息的完整指南

class NERDataProcessor:
    """
    中文NER预处理器：字符级BIO标注与实体恢复
    """
    def __init__(self, entity_types: list = ["PER", "ORG", "LOC"]):
        self.entity_types = entity_types

    def text_to_bios(self, text: str, entities: list) -> tuple:
        """
        文本转字符级BIO标签
        entities格式：[(start_char, end_char, label), ...]
        """
        char_labels = ["O"] * len(text)
        # 按起始位置排序实体避免覆盖
        for s, e, l in sorted(entities, key=lambda x: x[0]):
            if 0 <= s < e <= len(text) and l in self.entity_types:
                char_labels[s] = f"B-{l}"
                for i in range(s+1, e):
                    char_labels[i] = f"I-{l}"
        return list(text), char_labels

    def bios_to_entities(self, chars: list, labels: list) -> list:
        """
        字符级BIO标签恢复完整实体
        返回格式：[(实体文本, 标签, 起始位置, 结束位置), ...]
        """
        entities, curr = [], None
        for i, (c, l) in enumerate(zip(chars, labels)):
            if l.startswith("B-"):
                if curr: entities.append(("".join(curr[0]), curr[1], curr[2], i))
                curr = ([c], l[2:], i)
            elif l.startswith("I-") and curr and curr[1] == l[2:]:
                curr[0].append(c)
            else:
                if curr: entities.append(("".join(curr[0]), curr[1], curr[2], i))
                curr = None
        if curr: entities.append(("".join(curr[0]), curr[1], curr[2], len(chars)))
        return entities

from transformers import pipeline

# 推荐的中文开源模型：ckiplab/bert-base-chinese-ner
ner_pipeline = pipeline(
    task="token-classification",
    model="ckiplab/bert-base-chinese-ner",
    aggregation_strategy="simple"  # 自动聚合相邻的同类型实体
)

# 推理示例
text = "雷军在北京小米科技园发布了小米15"
results = ner_pipeline(text)

# 格式化输出
print("识别结果：")
for res in results:
    print(f"[{res['entity_group']}] {res['word']} (置信度：{res['score']:.2f})")

from seqeval.metrics import f1_score, classification_report

# 示例真实标签与预测标签（token级）
y_true = [["B-PER", "I-PER", "O", "B-ORG", "I-ORG", "I-ORG"]]
y_pred = [["B-PER", "O", "O", "B-ORG", "I-ORG", "I-ORG"]]

# 评估
print(f"实体级F1分数：{f1_score(y_true, y_pred):.2f}")
print("\n分类报告：")
print(classification_report(y_true, y_pred))

class EcomNER:
    def __init__(self):
        # 加载预微调的电商NER模型（可替换为自己训练的）
        self.ner = pipeline("token-classification", model="your-finetuned-ecom-ner", aggregation_strategy="simple")
    
    def extract_slots(self, query: str) -> dict:
        """
        从用户查询中提取电商核心槽位
        """
        slots = {"product": [], "order_id": [], "time": [], "amount": []}
        results = self.ner(query)
        for res in results:
            eg = res["entity_group"].lower()
            if eg in slots: slots[eg].append(res["word"])
        return slots

# 演示
ecom_ner = EcomNER()
query = "帮我查下订单号AB123456的退款，昨天付的999元"
print("用户查询：", query)
print("提取槽位：", ecom_ner.extract_slots(query))