一、pyahocorasick
1.安装 pyahocorasick 包：
pip install pyahocorasick -i https://pypi.tuna.tsinghua.edu.cn/simple/
-
pip install pyahocorasick：安装名为 pyahocorasick 的第三方库👉 这个库是一个 Aho-Corasick 多模匹配算法 的 Python 实现，常用于高效的多关键词搜索。
-
-i https://pypi.tuna.tsinghua.edu.cn/simple/：指定 pip 使用 清华镜像源，下载会更快、更稳定，尤其是在国内网络环境下。
2.介绍
✅ pyahocorasick 是 Python 的一个第三方库，
实现了 Aho--Corasick 多模式串匹配算法（自动机算法）。
👉 简单理解：
如果你有 很多关键词 ，想要在 一段文本 里 一次性高效匹配出所有关键词的位置 ，用普通的 for 循环挨个匹配会很慢，而 Aho--Corasick 算法可以用 O(n + m + k) 的时间（接近线性时间）搞定，非常高效。
二、创建医疗知识图谱
python
#选材自开源项目(刘焕勇，中国科学院软件研究所)，数据集来自互联网爬虫数据
import os
import json
from py2neo import Graph,Node
class MedicalGraph:
def __init__(self):
cur_dir = '/'.join(os.path.abspath(__file__).split('/')[:-1])
self.data_path = os.path.join(cur_dir, 'data/medical2.json')
self.g = Graph("bolt://localhost:7687", auth=("neo4j", "weixuanlv0304"))
'''读取文件'''
def read_nodes(self):
# 共７类节点
drugs = [] # 药品
foods = [] # 食物
checks = [] # 检查
departments = [] #科室
producers = [] #药品大类
diseases = [] #疾病
symptoms = []#症状
disease_infos = []#疾病信息
# 构建节点实体关系
rels_department = [] # 科室－科室关系
rels_noteat = [] # 疾病－忌吃食物关系
rels_doeat = [] # 疾病－宜吃食物关系
rels_recommandeat = [] # 疾病－推荐吃食物关系
rels_commonddrug = [] # 疾病－通用药品关系
rels_recommanddrug = [] # 疾病－热门药品关系
rels_check = [] # 疾病－检查关系
rels_drug_producer = [] # 厂商－药物关系
rels_symptom = [] #疾病症状关系
rels_acompany = [] # 疾病并发关系
rels_category = [] # 疾病与科室之间的关系
count = 0
for data in open(self.data_path):
disease_dict = {}
count += 1
print(count)
data_json = json.loads(data)
disease = data_json['name']
disease_dict['name'] = disease
diseases.append(disease)
disease_dict['desc'] = ''
disease_dict['prevent'] = ''
disease_dict['cause'] = ''
disease_dict['easy_get'] = ''
disease_dict['cure_department'] = ''
disease_dict['cure_way'] = ''
disease_dict['cure_lasttime'] = ''
disease_dict['symptom'] = ''
disease_dict['cured_prob'] = ''
if 'symptom' in data_json:
symptoms += data_json['symptom']
for symptom in data_json['symptom']:
rels_symptom.append([disease, symptom])
if 'acompany' in data_json:
for acompany in data_json['acompany']:
rels_acompany.append([disease, acompany])
if 'desc' in data_json:
disease_dict['desc'] = data_json['desc']
if 'prevent' in data_json:
disease_dict['prevent'] = data_json['prevent']
if 'cause' in data_json:
disease_dict['cause'] = data_json['cause']
if 'get_prob' in data_json:
disease_dict['get_prob'] = data_json['get_prob']
if 'easy_get' in data_json:
disease_dict['easy_get'] = data_json['easy_get']
if 'cure_department' in data_json:
cure_department = data_json['cure_department']
if len(cure_department) == 1:
rels_category.append([disease, cure_department[0]])
if len(cure_department) == 2:
big = cure_department[0]
small = cure_department[1]
rels_department.append([small, big])
rels_category.append([disease, small])
disease_dict['cure_department'] = cure_department
departments += cure_department
if 'cure_way' in data_json:
disease_dict['cure_way'] = data_json['cure_way']
if 'cure_lasttime' in data_json:
disease_dict['cure_lasttime'] = data_json['cure_lasttime']
if 'cured_prob' in data_json:
disease_dict['cured_prob'] = data_json['cured_prob']
if 'common_drug' in data_json:
common_drug = data_json['common_drug']
for drug in common_drug:
rels_commonddrug.append([disease, drug])
drugs += common_drug
if 'recommand_drug' in data_json:
recommand_drug = data_json['recommand_drug']
drugs += recommand_drug
for drug in recommand_drug:
rels_recommanddrug.append([disease, drug])
if 'not_eat' in data_json:
not_eat = data_json['not_eat']
for _not in not_eat:
rels_noteat.append([disease, _not])
foods += not_eat
do_eat = data_json['do_eat']
for _do in do_eat:
rels_doeat.append([disease, _do])
foods += do_eat
recommand_eat = data_json['recommand_eat']
for _recommand in recommand_eat:
rels_recommandeat.append([disease, _recommand])
foods += recommand_eat
if 'check' in data_json:
check = data_json['check']
for _check in check:
rels_check.append([disease, _check])
checks += check
if 'drug_detail' in data_json:
drug_detail = data_json['drug_detail']
producer = [i.split('(')[0] for i in drug_detail]
rels_drug_producer += [[i.split('(')[0], i.split('(')[-1].replace(')', '')] for i in drug_detail]
producers += producer
disease_infos.append(disease_dict)
return set(drugs), set(foods), set(checks), set(departments), set(producers), set(symptoms), set(diseases), disease_infos,\
rels_check, rels_recommandeat, rels_noteat, rels_doeat, rels_department, rels_commonddrug, rels_drug_producer, rels_recommanddrug,\
rels_symptom, rels_acompany, rels_category
'''建立节点'''
def create_node(self, label, nodes):
count = 0
for node_name in nodes:
node = Node(label, name=node_name)
self.g.create(node)
count += 1
print(count, len(nodes))
return
'''创建知识图谱中心疾病的节点'''
def create_diseases_nodes(self, disease_infos):
count = 0
for disease_dict in disease_infos:
node = Node("Disease", name=disease_dict['name'], desc=disease_dict['desc'],
prevent=disease_dict['prevent'] ,cause=disease_dict['cause'],
easy_get=disease_dict['easy_get'],cure_lasttime=disease_dict['cure_lasttime'],
cure_department=disease_dict['cure_department']
,cure_way=disease_dict['cure_way'] , cured_prob=disease_dict['cured_prob'])
self.g.create(node)
count += 1
print(count)
return
'''创建知识图谱实体节点类型schema'''
def create_graphnodes(self):
Drugs, Foods, Checks, Departments, Producers, Symptoms, Diseases, disease_infos,rels_check, rels_recommandeat, rels_noteat, rels_doeat, rels_department, rels_commonddrug, rels_drug_producer, rels_recommanddrug,rels_symptom, rels_acompany, rels_category = self.read_nodes()
self.create_diseases_nodes(disease_infos)
self.create_node('Drug', Drugs)
print(len(Drugs))
self.create_node('Food', Foods)
print(len(Foods))
self.create_node('Check', Checks)
print(len(Checks))
self.create_node('Department', Departments)
print(len(Departments))
self.create_node('Producer', Producers)
print(len(Producers))
self.create_node('Symptom', Symptoms)
return
'''创建实体关系边'''
def create_graphrels(self):
Drugs, Foods, Checks, Departments, Producers, Symptoms, Diseases, disease_infos, rels_check, rels_recommandeat, rels_noteat, rels_doeat, rels_department, rels_commonddrug, rels_drug_producer, rels_recommanddrug,rels_symptom, rels_acompany, rels_category = self.read_nodes()
self.create_relationship('Disease', 'Food', rels_recommandeat, 'recommand_eat', '推荐食谱')
self.create_relationship('Disease', 'Food', rels_noteat, 'no_eat', '忌吃')
self.create_relationship('Disease', 'Food', rels_doeat, 'do_eat', '宜吃')
self.create_relationship('Department', 'Department', rels_department, 'belongs_to', '属于')
self.create_relationship('Disease', 'Drug', rels_commonddrug, 'common_drug', '常用药品')
self.create_relationship('Producer', 'Drug', rels_drug_producer, 'drugs_of', '生产药品')
self.create_relationship('Disease', 'Drug', rels_recommanddrug, 'recommand_drug', '好评药品')
self.create_relationship('Disease', 'Check', rels_check, 'need_check', '诊断检查')
self.create_relationship('Disease', 'Symptom', rels_symptom, 'has_symptom', '症状')
self.create_relationship('Disease', 'Disease', rels_acompany, 'acompany_with', '并发症')
self.create_relationship('Disease', 'Department', rels_category, 'belongs_to', '所属科室')
'''创建实体关联边'''
def create_relationship(self, start_node, end_node, edges, rel_type, rel_name):
count = 0
# 去重处理
set_edges = []
for edge in edges:
set_edges.append('###'.join(edge))
all = len(set(set_edges))
for edge in set(set_edges):
edge = edge.split('###')
p = edge[0]
q = edge[1]
query = "match(p:%s),(q:%s) where p.name='%s'and q.name='%s' create (p)-[rel:%s{name:'%s'}]->(q)" % (
start_node, end_node, p, q, rel_type, rel_name)
try:
self.g.run(query)
count += 1
print(rel_type, count, all)
except Exception as e:
print(e)
return
'''导出数据'''
def export_data(self):
Drugs, Foods, Checks, Departments, Producers, Symptoms, Diseases, disease_infos, rels_check, rels_recommandeat, rels_noteat, rels_doeat, rels_department, rels_commonddrug, rels_drug_producer, rels_recommanddrug, rels_symptom, rels_acompany, rels_category = self.read_nodes()
f_drug = open('drug.txt', 'w+')
f_food = open('food.txt', 'w+')
f_check = open('check.txt', 'w+')
f_department = open('department.txt', 'w+')
f_producer = open('producer.txt', 'w+')
f_symptom = open('symptoms.txt', 'w+')
f_disease = open('disease.txt', 'w+')
f_drug.write('\n'.join(list(Drugs)))
f_food.write('\n'.join(list(Foods)))
f_check.write('\n'.join(list(Checks)))
f_department.write('\n'.join(list(Departments)))
f_producer.write('\n'.join(list(Producers)))
f_symptom.write('\n'.join(list(Symptoms)))
f_disease.write('\n'.join(list(Diseases)))
f_drug.close()
f_food.close()
f_check.close()
f_department.close()
f_producer.close()
f_symptom.close()
f_disease.close()
return
if __name__ == '__main__':
handler = MedicalGraph()
#handler.export_data()
handler.create_graphnodes()
handler.create_graphrels()三、问答机器人对话
python
from question_classifier import *
from question_parser import *
from answer_search import *
'''问答类'''
class ChatBotGraph:
def __init__(self):
self.classifier = QuestionClassifier()
self.parser = QuestionPaser()
self.searcher = AnswerSearcher()
def chat_main(self, sent):
answer = '没能理解您的问题，我数据量有限。。。能不能问的标准点'
res_classify = self.classifier.classify(sent)
if not res_classify:
return answer
res_sql = self.parser.parser_main(res_classify)
final_answers = self.searcher.search_main(res_sql)
if not final_answers:
return answer
else:
return '\n'.join(final_answers)
if __name__ == '__main__':
handler = ChatBotGraph()
while 1:
question = input('咨询:')
answer = handler.chat_main(question)
print('客服机器人:', answer)