将构建的知识图片字典化, 用于后面对问题的解析,下图为症状的字典,其它字典同理
将建字典数据,组装集合
cur_dir = '/'.join(os.path.abspath(__file__).split('/')[:-1])
# 特征词路径
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')
# 加载数据
self.disease_wds = [i.strip() for i in open(self.disease_path, encoding="utf-8") if i.strip()] # ['干眼', '右膝髌上囊及关节腔少量积液']
self.check_wds = [i.strip() for i in open(self.check_path, encoding="utf-8") if i.strip()] # ['膝关节核磁', '视力', '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','干涩','看东西有时候清楚有时候不清楚']
# 读出所有 dict 里面的字典数据,并拼接成一个大而全的 集合
# ['干眼', '右膝髌上囊及关节腔少量积液','膝关节核磁', '视力', '砂眼', '辨色力', '角膜', '眼底','畏光','干涩','看东西有时候清楚有时候不清楚']
self.region_words = set(self.disease_wds + self.check_wds + self.drug_wds + self.food_wds + self.symptom_wds)
构建 Trie 字典树
Trie字典树:https://www.cnblogs.com/vipsoft/p/17722820.html
Aho-Corasick 算法 AC自动机实现:https://www.cnblogs.com/vipsoft/p/17722761.html
# 目的是为了将来对用户提的问题,进行关键词快速提取
def build_actree(self, word_list):
"""
构造actree,加速过滤
:param word_list:
:return:
"""
actree = ahocorasick.Automaton()
for index, word in enumerate(word_list):
actree.add_word(word, (index, word)) # 向trie树中添加单词
actree.make_automaton()
return actree
# 将 ['干眼', '右膝髌上囊及关节腔少量积液','膝关节核磁', '视力', '砂眼', '辨色力', '角膜', '眼底'],进行分类,组装成不同类型的字典
def build_wdtype_dict(self):
"""
构造词对应的类型
: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
通过AC算法,过滤关键词
# "请问最近看东西有时候清楚有时候不清楚是怎么回事"
def check_medical(self, question):
"""
问句过滤
:param question:
:return:
"""
region_wds = []
for i in self.region_tree.iter(question): # 从问题中,找出关键词
wd = i[1][1] # 看东西有时候清楚有时候不清楚
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] # '看东西有时候清楚有时候不清楚'
medical_dict = {i: self.wdtype_dict.get(i) for i in final_wds} # {'看东西有时候清楚有时候不清楚': ['symptom']}
return medical_dict
解析出问题的类型
data['args'] = medical_dict
# 若没有查到相关的外部查询信息,那么则将该疾病的描述信息返回
if question_types == [] and 'symptom' in types:
question_types = ['symptom_disease']
# 将多个分类结果进行合并处理,组装成一个字典
data['question_types'] = question_types
输出字典
question = "请问最近看东西有时候清楚有时候不清楚是怎么回事"
# 最终输出
data = {'args': {'看东西有时候清楚有时候不清楚': ['symptom']}, 'question_types': ['symptom_disease']}
question = "干眼常用药有哪些"
# 最终输出
data = {'args': {'干眼': ['disease']}, 'question_types': ['disease_drug']}
question = "干眼哪些不能吃"
data = {'args': {'干眼': ['disease']}, 'question_types': ['disease_not_food']}
后面根据 question_types 生成 CQL语句