欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

菜哥学知识图谱(通过“基于医疗知识图谱的问答系统”)(六)(代码分析3)

程序员文章站 2022-03-04 13:06:45
...

上接菜哥学知识图谱(通过“基于医疗知识图谱的问答系统”)(五)(neo4j的cql语言)
本节继续进行代码分析。
7.answer_search.py。该类的classify()方法,将问题提取了关键字,并对问题进行了分类。下面对代码进行注释。

#!/usr/bin/env python3
# coding: utf-8
# File: question_classifier.py
# Author: lhy<[email protected],https://huangyong.github.io>
# Date: 18-10-4

import os
import ahocorasick  #ahocorasick实现快速的关键字匹配

class QuestionClassifier:
    def __init__(self):
        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.department_path = os.path.join(cur_dir, 'dict/department.txt')
        self.check_path = os.path.join(cur_dir, 'dict/check.txt')
        self.drug_path = os.path.join(cur_dir, 'dict/drug.txt')
        self.food_path = os.path.join(cur_dir, 'dict/food.txt')
        self.producer_path = os.path.join(cur_dir, 'dict/producer.txt')
        self.symptom_path = os.path.join(cur_dir, 'dict/symptom.txt')
        self.deny_path = os.path.join(cur_dir, 'dict/deny.txt')
        # 加载特征词
        self.disease_wds= [i.strip() for i in open(self.disease_path, encoding='utf-8') if i.strip()]  #把词取出,放入list #疾病名称
        self.department_wds= [i.strip() for i in open(self.department_path, encoding='utf-8') if i.strip()] #科室名称
        self.check_wds= [i.strip() for i in open(self.check_path, encoding='utf-8') if i.strip()] #检查项目
        self.drug_wds= [i.strip() for i in open(self.drug_path, encoding='utf-8') if i.strip()] #药品
        self.food_wds= [i.strip() for i in open(self.food_path, encoding='utf-8') if i.strip()] #食物
        self.producer_wds= [i.strip() for i in open(self.producer_path, encoding='utf-8') if i.strip()] #药品大类
        self.symptom_wds= [i.strip() for i in open(self.symptom_path, encoding='utf-8') if i.strip()] #症状
        self.region_words = set(self.department_wds + self.disease_wds + self.check_wds + self.drug_wds + self.food_wds + self.producer_wds + self.symptom_wds)   #所有的关键字放在一起,去重
        self.deny_words = [i.strip() for i in open(self.deny_path, encoding='utf-8') if i.strip()]   #否定词
        # 构造领域actree
        self.region_tree = self.build_actree(list(self.region_words))   #建立一个AC自动机,方法在后面。AC制动机的目的是加速匹配。
        # 构建词典
        self.wdtype_dict = self.build_wdtype_dict()  #词的类型的字典,{'百日咳':'disease',....}
        # 问句疑问词,把所有的问句形式穷举
        self.symptom_qwds = ['症状', '表征', '现象', '症候', '表现'] #症状关键词
        self.cause_qwds = ['原因','成因', '为什么', '怎么会', '怎样才', '咋样才', '怎样会', '如何会', '为啥', '为何', '如何才会', '怎么才会', '会导致', '会造成']  #原因关键词
        self.acompany_qwds = ['并发症', '并发', '一起发生', '一并发生', '一起出现', '一并出现', '一同发生', '一同出现', '伴随发生', '伴随', '共现'] #并发症关键词
        self.food_qwds = ['饮食', '饮用', '吃', '食', '伙食', '膳食', '喝', '菜' ,'忌口', '补品', '保健品', '食谱', '菜谱', '食用', '食物','补品'] 
        self.drug_qwds = ['药', '药品', '用药', '胶囊', '口服液', '炎片']
        self.prevent_qwds = ['预防', '防范', '抵制', '抵御', '防止','躲避','逃避','避开','免得','逃开','避开','避掉','躲开','躲掉','绕开',
                             '怎样才能不', '怎么才能不', '咋样才能不','咋才能不', '如何才能不',
                             '怎样才不', '怎么才不', '咋样才不','咋才不', '如何才不',
                             '怎样才可以不', '怎么才可以不', '咋样才可以不', '咋才可以不', '如何可以不',
                             '怎样才可不', '怎么才可不', '咋样才可不', '咋才可不', '如何可不']
        self.lasttime_qwds = ['周期', '多久', '多长时间', '多少时间', '几天', '几年', '多少天', '多少小时', '几个小时', '多少年']
        self.cureway_qwds = ['怎么治疗', '如何医治', '怎么医治', '怎么治', '怎么医', '如何治', '医治方式', '疗法', '咋治', '怎么办', '咋办', '咋治']
        self.cureprob_qwds = ['多大概率能治好', '多大几率能治好', '治好希望大么', '几率', '几成', '比例', '可能性', '能治', '可治', '可以治', '可以医']
        self.easyget_qwds = ['易感人群', '容易感染', '易发人群', '什么人', '哪些人', '感染', '染上', '得上']
        self.check_qwds = ['检查', '检查项目', '查出', '检查', '测出', '试出']
        self.belong_qwds = ['属于什么科', '属于', '什么科', '科室']
        self.cure_qwds = ['治疗什么', '治啥', '治疗啥', '医治啥', '治愈啥', '主治啥', '主治什么', '有什么用', '有何用', '用处', '用途',
                          '有什么好处', '有什么益处', '有何益处', '用来', '用来做啥', '用来作甚', '需要', '要']

        print('model init finished ......')

        return

    '''分类主函数'''
    def classify(self, question):
        data = {}
        medical_dict = self.check_medical(question)  #从问句中匹配出的,{'百日咳':'disease',....}
        if not medical_dict:
            return {}
        data['args'] = medical_dict
        #收集问句当中所涉及到的实体类型
        types = []
        for type_ in medical_dict.values(): 
            types += type_    #所有的类型,如['disease','food',......]
        question_type = 'others'

        question_types = []

        # 症状
        if self.check_words(self.symptom_qwds, question) and ('disease' in types):  #如果symptom_qwds(症状词) 在 question中,且有类型为'disease'的词,即知道疾病名称,则:
            question_type = 'disease_symptom'  #问句类型为:已知疾病询问症状
            question_types.append(question_type)

        if self.check_words(self.symptom_qwds, question) and ('symptom' in types): #如果症状词在question中,且有症状词
            question_type = 'symptom_disease'  #已知症状问疾病
            question_types.append(question_type)

        # 原因
        if self.check_words(self.cause_qwds, question) and ('disease' in types):  
            question_type = 'disease_cause'  #已知疾病问病因
            question_types.append(question_type)
        # 并发症
        if self.check_words(self.acompany_qwds, question) and ('disease' in types):
            question_type = 'disease_acompany'  #已知疾病问并发症
            question_types.append(question_type)

        # 推荐食品
        if self.check_words(self.food_qwds, question) and 'disease' in types:
            deny_status = self.check_words(self.deny_words, question)
            if deny_status:
                question_type = 'disease_not_food'  #已知疾病问忌口
            else:
                question_type = 'disease_do_food'  #已知疾病问食补
            question_types.append(question_type)

        #已知食物找疾病
        if self.check_words(self.food_qwds+self.cure_qwds, question) and 'food' in types:
            deny_status = self.check_words(self.deny_words, question)
            if deny_status:
                question_type = 'food_not_disease'
            else:
                question_type = 'food_do_disease'
            question_types.append(question_type)

        # 推荐药品
        if self.check_words(self.drug_qwds, question) and 'disease' in types:
            question_type = 'disease_drug'
            question_types.append(question_type)

        # 药品治啥病
        if self.check_words(self.cure_qwds, question) and 'drug' in types:
            question_type = 'drug_disease'
            question_types.append(question_type)

        # 疾病接受检查项目
        if self.check_words(self.check_qwds, question) and 'disease' in types:
            question_type = 'disease_check'
            question_types.append(question_type)

        # 已知检查项目查相应疾病
        if self.check_words(self.check_qwds+self.cure_qwds, question) and 'check' in types:
            question_type = 'check_disease'
            question_types.append(question_type)

        # 症状防御
        if self.check_words(self.prevent_qwds, question) and 'disease' in types:
            question_type = 'disease_prevent'
            question_types.append(question_type)

        # 疾病医疗周期
        if self.check_words(self.lasttime_qwds, question) and 'disease' in types:
            question_type = 'disease_lasttime'
            question_types.append(question_type)

        # 疾病治疗方式
        if self.check_words(self.cureway_qwds, question) and 'disease' in types:
            question_type = 'disease_cureway'
            question_types.append(question_type)

        # 疾病治愈可能性
        if self.check_words(self.cureprob_qwds, question) and 'disease' in types:
            question_type = 'disease_cureprob'
            question_types.append(question_type)

        # 疾病易感染人群
        if self.check_words(self.easyget_qwds, question) and 'disease' in types :
            question_type = 'disease_easyget'
            question_types.append(question_type)

        # 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 'disease' in types:
            question_types = ['disease_desc']

        # 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

        return data

    '''构造词对应的类型'''
    def build_wdtype_dict(self):
        wd_dict = dict()  #创建一个空字典
        for wd in self.region_words:   #所有的关键字
            wd_dict[wd] = []
            if wd in self.disease_wds:
                wd_dict[wd].append('disease')  #如果该关键字属于 疾病,则wd_dict[wd] = ['disease'],下同
            if wd in self.department_wds:
                wd_dict[wd].append('department')
            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')
            if wd in self.producer_wds:
                wd_dict[wd].append('producer')
        return wd_dict   #返回了一个字典,里面的内容是{'百日咳':'disease',....}

    '''构造actree,加速过滤'''  #输入list,输出一个AC树
    def build_actree(self, wordlist):
        actree = ahocorasick.Automaton() 
        for index, word in enumerate(wordlist):
            actree.add_word(word, (index, word))
        actree.make_automaton()
        return actree

    '''问句过滤'''
    def check_medical(self, question):  
        region_wds = []
        for i in self.region_tree.iter(question):   #快速匹配,匹配的结果是一个双重元组序列,形如('百日咳',(3324,'百日咳')),就是前面的actree.add_word(word, (index, word))给加进来成tree的。这个index是在前面所有关键字加在一起之后的region_words中的***
            wd = i[1][1]  #把'百日咳'这个关键字给挑出来了
            region_wds.append(wd)  #把所有的关键字列入列表region_wds
        stop_wds = []   					   #下面这几句做了这么一件事:
        for wd1 in region_wds:                 #1.如果一个问句里面挑出了两个词
            for wd2 in region_wds:
                if wd1 in wd2 and wd1 != wd2:  #2.如果其中一个词包含另一个词
                    stop_wds.append(wd1)       #3.则把短的词写入stop_wds
        final_wds = [i for i in region_wds if i not in stop_wds]  #4.final_wds中是把region_wds去掉stop_wds。就是说如果问句中一个词包含另外一个词,则以长词为准。
        final_dict = {i:self.wdtype_dict.get(i) for i in final_wds}  #类似于{'百日咳':'disease',....},其中'百日咳'在问句中,且不在stop_wds中。

        return final_dict  

    '''基于特征词进行分类'''
    def check_words(self, wds, sent):
        for wd in wds:
            if wd in sent:
                return True
        return False


if __name__ == '__main__':
    handler = QuestionClassifier()
    while 1:
        question = input('input an question:')
        data = handler.classify(question)
        print(data)