• 首先安裝pyltp
  pytlp項目首頁

• 單例類（第一次調用時加載模型）

class Singleton(object):
    def __new__(cls, *args, **kwargs):
        if not hasattr(cls, ‘_the_instance‘):
            cls._the_instance = object.__new__(cls, *args, **kwargs)
        return cls._the_instance

• 使用pyltp提取地址

import os
from pyltp import Segmentor, Postagger, NamedEntityRecognizer
from
 
 main.models.Singleton import Singleton

class address_extract_model(Singleton):
    print(‘load ltp model start...‘)

    pwd = os.getcwd()
    project_path = os.path.abspath(os.path.dirname(pwd) + os.path.sep + ".")

    LTP_DATA_DIR = project_path + ‘\AlarmClassification\main\ltp\model‘  # ltp模型目錄的路徑
 

    cws_model_path = os.path.join(LTP_DATA_DIR, ‘cws.model‘)
    pos_model_path = os.path.join(LTP_DATA_DIR, ‘pos.model‘)  # 詞性標註模型路徑，模型名稱為`pos.model`
    ner_model_path = os.path.join(LTP_DATA_DIR, ‘ner.model‘)  # 命名實體識別模型路徑，模型名稱為`ner.model`

    print(‘path‘ + cws_model_path)

    segmentor = Segmentor()  # 初始化實例
 

    segmentor.load(cws_model_path)  # 加載模型

    postagger = Postagger() # 初始化實例
    postagger.load(pos_model_path)  # 加載模型

    recognizer = NamedEntityRecognizer() # 初始化實例
    recognizer.load(ner_model_path)  # 加載模型


    def get_model(self):
        return self.segmentor, self.postagger, self.recognizer


def get_address_prediction(alarm_content):
    model = address_extract_model()
    segmentor, postagger, recognizer = model.get_model()

    words = segmentor.segment(alarm_content)  # 分詞
    postags = postagger.postag(words)  # 詞性標註
    netags = recognizer.recognize(words, postags)  # 命名實體識別

    result = ‘‘
    for i in range(0, len(netags)):
        print(words[i] + ‘: ‘ + netags[i])
        # 地名標簽為 ns
        if ‘s‘ in netags[i]:
            result += words[i] + ‘,‘
    if len(result) < 1:
        result = ‘No address!‘
    print(result)
    return result


def get_address(alarm_content):
    print("start get_address...")
    result = "Exception"
    try:
        result = get_address_prediction(alarm_content)
    except Exception as ex:
        print(ex)

    print("Output is " + result)
    return result

# segmentor.release()  # 釋放模型
# postagger.release()
# recognizer.release()

• 運行效果

• 項目源碼 ( 命名實體提取代碼位於main/ltp， 模型文件需要到pyltp下載 )
  https://github.com/haibincoder/AlarmClassification

使用pyltp提取文本中的地址