利用知识图谱构建医疗问答

1、准备数据集

数据集下载地址：https://github.com/wangle1218/QASystemOnMedicalKG/blob/master/data/medical.json

2、导入相关包

from py2neo import Graph,Node,Relationship
# 在cmd中，输入neo4j.bat console并回车
import pandas as pd

3、连接Neo4j

neo_graph = Graph(host="127.0.0.1",# http_port='7474',user='neo4j',password='xxxx')
neo_graph

4、构建知识图谱

from py2neo import Graph
import os
from tqdm import tqdm
import json
import datetimeclass CreateKG():def __init__(self, kg_host, kg_port, kg_user, kg_password, data_path):self.graph = Graph(host=kg_host,# http_port=kg_port,user=kg_user,password=kg_password)if not data_path or data_path == '':raise Exception("数据集地址为空")if not os.path.exists(data_path):raise Exception("数据集不存在")self.data_path = data_path# 创建节点及关系的语句
# CREATE (n:Person { name: 'Andres', title: 'Developer' }) return n;
# CREATE (n:Person { name: 'Vic', title: 'Developer' }) return n;
# match(n:Person{name:"Vic"}),(m:Person{name:"Andres"}) create (n)-[r:Friend]->(m) return r;
# match(n:Person{name:"Vic"}),(m:Person{name:"Andres"}) create (n)<-[r:Friend]-(m) return r;def saveEntity(self, label, data):print("\n写入实体：", label)for item in tqdm(data, ncols=80):try:property = []for key, value in item.items():value = value.replace("'", "")property.append(key + ":" + "'" + value + "'")if len(property) == 0:continuecql = "MERGE(n:" + label + "{" + ",".join(property) + "})"self.graph.run(cql)except Exception as e:passdef saveRelation(self, s_label, e_label, label, data):print("\n写入关系：", label)for item in tqdm(data, ncols=80):try:s_name = item["s_name"]e_name = item["e_name"]cql = "MATCH(p:" + s_label + "),(q:" + e_label + ") WHERE p.name='" + s_name + "' AND q.name='" + e_name + "' MERGE (p)-[r:" + label + "]->(q)"self.graph.run(cql)except Exception as e:passdef getValue(self, key, data):if key in data:return data[key]return ""def init(self):# 实体# 疾病diseases = []# 科室departments = []# 疾病症状symptoms = []# 治疗方式cureWays = []# 检查项目checks = []# 药物drugs = []# 易感染人群crowds = []# 食物foods = []# 关系# 疾病科室diseaseDepartmentRelations = []# 疾病症状diseaseSymptomRelations = []# 疾病治疗diseaseCureWayRelations = []# 疾病检查diseaseCheckRelations = []# 疾病用药diseaseDrugRelations = []# 疾病易感染人群diseaseCrowdRelations = []# 疾病宜吃食物diseaseSuitableFoodRelations = []# 疾病忌吃食物diseaseTabooFoodRelations = []# 疾病并发症diseaseDiseaseRelations = []print("====数据抽取======")with open(self.data_path, 'r', encoding='utf8') as f:for line in tqdm(f.readlines(), ncols=80):data = json.loads(line)# 疾病实体disease = {"name": data["name"],"desc": self.getValue("desc", data),"prevent": self.getValue("prevent", data),"cause": self.getValue("cause", data),"get_prob": self.getValue("get_prob", data),"get_way": self.getValue("get_way", data),"cure_lasttime": self.getValue("cure_lasttime", data),"cured_prob": self.getValue("cured_prob", data),"cost_money": self.getValue("cost_money", data),}diseases.append(disease)# 科室if "cure_department" in data:for department in data["cure_department"]:# 疾病科室关系diseaseDepartmentRelations.append({"s_name": data["name"],"e_name": department})# 科室实体property = {"name": department}if property not in departments:departments.append(property)# 症状if "symptom" in data:for symptom in data["symptom"]:# 疾病科室关系diseaseSymptomRelations.append({"s_name": data["name"],"e_name": symptom})# 症状实体property = {"name": symptom}if property not in symptoms:symptoms.append(property)# 治疗方式if "cure_way" in data:for cure_way in data["cure_way"]:# 疾病科室关系diseaseCureWayRelations.append({"s_name": data["name"],"e_name": cure_way})# 治疗方式实体property = {"name": cure_way}if property not in cureWays:cureWays.append(property)# 检查项目if "check" in data:for check in data["check"]:# 疾病科室关系diseaseCheckRelations.append({"s_name": data["name"],"e_name": check})# 检查项目实体property = {"name": check}if property not in checks:checks.append(property)# 一般用药if "common_drug" in data:for common_drug in data["common_drug"]:# 疾病科室关系diseaseDrugRelations.append({"s_name": data["name"],"e_name": common_drug})# 用药实体property = {"name": common_drug}if property not in drugs:drugs.append(property)# 易感染人群if "easy_get" in data:easy_get = data["easy_get"]# 疾病科室关系diseaseCrowdRelations.append({"s_name": data["name"],"e_name": easy_get})# 易感染人群实体property = {"name": easy_get}if property not in crowds:crowds.append(property)# 宜吃食物if "recommand_eat" in data:for recommand_eat in data["recommand_eat"]:# 疾病科室关系diseaseSuitableFoodRelations.append({"s_name": data["name"],"e_name": recommand_eat})# 食物实体property = {"name": recommand_eat}if property not in foods:foods.append(property)# 忌吃食物if "not_eat" in data:for not_eat in data["not_eat"]:# 疾病科室关系diseaseTabooFoodRelations.append({"s_name": data["name"],"e_name": not_eat})# 食物实体property = {"name": not_eat}if property not in foods:foods.append(property)# 并发症if "acompany" in data:for acompany in data["acompany"]:# 疾病科室关系diseaseDiseaseRelations.append({"s_name": data["name"],"e_name": acompany})# 疾病self.saveEntity("disease", diseases)# 科室self.saveEntity("department", departments)# 疾病症状self.saveEntity("symptom", symptoms)# 治疗方式self.saveEntity("cureWay", cureWays)# 检查项目self.saveEntity("check", checks)# 药物self.saveEntity("drug", drugs)# 易感染人群self.saveEntity("crowd", crowds)# 食物self.saveEntity("food", foods)# 关系# 疾病科室self.saveRelation("disease", "department", "diseaseDepartmentRelations", diseaseDepartmentRelations)# 疾病症状self.saveRelation("disease", "symptom", "diseaseSymptomRelation", diseaseSymptomRelations)# 疾病治疗self.saveRelation("disease", "cureWay", "diseaseCureWayRelation", diseaseCureWayRelations)# 疾病检查self.saveRelation("disease", "check", "diseaseCheckRelation", diseaseCheckRelations)# 疾病用药self.saveRelation("disease", "drug", "diseaseDrugRelation", diseaseDrugRelations)# 疾病易感染人群self.saveRelation("disease", "crowd", "diseaseCrowdRelation", diseaseCrowdRelations)# 疾病宜吃食物self.saveRelation("disease", "food", "diseaseSuitableFoodRelation", diseaseSuitableFoodRelations)# 疾病忌吃食物self.saveRelation("disease", "food", "diseaseTabooFoodRelation", diseaseTabooFoodRelations)# 疾病并发症self.saveRelation("disease", "disease", "diseaseDiseaseRelation", diseaseDiseaseRelations)if __name__ == '__main__':start = datetime.datetime.now()kg_host = "127.0.0.1"kg_port = 7474kg_user = "neo4j"kg_password = "960418.hmx"data_path = "dataset/知识图谱/medical.json"kg = CreateKG(kg_host, kg_port, kg_user, kg_password, data_path)kg.init()end = datetime.datetime.now()print("共耗时：{}".format(end - start))