在線問診 Python、FastAPI、Neo4j — 構建問題分類器

將問題進行分析，和系統已有的分類進行關聯

構建字典數據

將構建的知識圖片字典化， 用於後面對問題的解析，下圖爲症狀的字典，其它字典同理

構建 Trie 字典樹

將建字典數據，組裝集合

cur_dir = '/'.join(os.path.abspath(__file__).split('/')[:-1])
# 　特徵詞路徑
self.disease_path = os.path.join(cur_dir, '../dict/disease.txt')
self.check_path = os.path.join(cur_dir, '../dict/examine.txt')
self.drug_path = os.path.join(cur_dir, '../dict/drug.txt')
self.food_path = os.path.join(cur_dir, '../dict/food.txt')
self.symptom_path = os.path.join(cur_dir, '../dict/symptom.txt')
self.deny_path = os.path.join(cur_dir, '../dict/deny.txt')
# 加載數據
self.disease_wds = [i.strip() for i in open(self.disease_path, encoding="utf-8") if i.strip()]   # ['乾眼', '右膝髕上囊及關節腔少量積液']
self.check_wds = [i.strip() for i in open(self.check_path, encoding="utf-8") if i.strip()]  # ['膝關節核磁', '視力', '砂眼', '辨色力', '角膜', '眼底']
self.drug_wds = [i.strip() for i in open(self.drug_path, encoding="utf-8") if i.strip()]
self.food_wds = [i.strip() for i in open(self.food_path, encoding="utf-8") if i.strip()]
self.symptom_wds = [i.strip() for i in open(self.symptom_path, encoding="utf-8") if i.strip()] # ['畏光','乾澀','看東西有時候清楚有時候不清楚']

# 讀出所有 dict 裏面的字典數據，並拼接成一個大而全的 集合
# ['乾眼', '右膝髕上囊及關節腔少量積液','膝關節核磁', '視力', '砂眼', '辨色力', '角膜', '眼底','畏光','乾澀','看東西有時候清楚有時候不清楚']
self.region_words = set(self.disease_wds + self.check_wds + self.drug_wds + self.food_wds + self.symptom_wds)

構建 Trie 字典樹
Trie字典樹：https://www.cnblogs.com/vipsoft/p/17722820.html
Aho-Corasick 算法 AC自動機實現：https://www.cnblogs.com/vipsoft/p/17722761.html

# 目的是爲了將來對用戶提的問題，進行關鍵詞快速提取
def build_actree(self, word_list):
    """
    構造actree，加速過濾
    :param word_list:
    :return:
    """
    actree = ahocorasick.Automaton()
    for index, word in enumerate(word_list):
        actree.add_word(word, (index, word))  # 向trie樹中添加單詞
    actree.make_automaton()
    return actree

按實體組裝字典

# 將 ['乾眼', '右膝髕上囊及關節腔少量積液','膝關節核磁', '視力', '砂眼', '辨色力', '角膜', '眼底']，進行分類，組裝成不同類型的字典
def build_wdtype_dict(self):
    """
    構造詞對應的類型
    :return:
    """
    wd_dict = dict()
    for wd in self.region_words:
        wd_dict[wd] = []
        if wd in self.disease_wds:
            wd_dict[wd].append('disease')
        if wd in self.check_wds:
            wd_dict[wd].append('check')
        if wd in self.drug_wds:
            wd_dict[wd].append('drug')
        if wd in self.food_wds:
            wd_dict[wd].append('food')
        if wd in self.symptom_wds:
            wd_dict[wd].append('symptom')
    return wd_dict

問題分析

通過AC算法，過濾關鍵詞

# "請問最近看東西有時候清楚有時候不清楚是怎麼回事"
def check_medical(self, question):
    """
    問句過濾
    :param question:
    :return:
    """
    region_wds = []
    for i in self.region_tree.iter(question):  # 從問題中，找出關鍵詞
        wd = i[1][1]  # 看東西有時候清楚有時候不清楚
        region_wds.append(wd)
    stop_wds = []
    for wd1 in region_wds:
        for wd2 in region_wds:
            if wd1 in wd2 and wd1 != wd2:
                stop_wds.append(wd1)
    final_wds = [i for i in region_wds if i not in stop_wds]  # '看東西有時候清楚有時候不清楚'
    medical_dict = {i: self.wdtype_dict.get(i) for i in final_wds}  # {'看東西有時候清楚有時候不清楚': ['symptom']}
    return medical_dict

解析出問題的類型

data['args'] = medical_dict
# 若沒有查到相關的外部查詢信息，那麼則將該疾病的描述信息返回
if question_types == [] and 'symptom' in types:
   question_types = ['symptom_disease']
# 將多個分類結果進行合併處理，組裝成一個字典
data['question_types'] = question_types

輸出字典

question = "請問最近看東西有時候清楚有時候不清楚是怎麼回事"
# 最終輸出
data = {'args': {'看東西有時候清楚有時候不清楚': ['symptom']}, 'question_types': ['symptom_disease']}

question = "乾眼常用藥有哪些"
# 最終輸出
data = {'args': {'乾眼': ['disease']}, 'question_types': ['disease_drug']}

question = "乾眼哪些不能喫"
data = {'args': {'乾眼': ['disease']}, 'question_types': ['disease_not_food']}

後面根據 question_types 生成 CQL語句

源代碼地址：https://gitee.com/VipSoft/VipQA