第一次构建一个对话机器人流程解析（二）

1. 问答机器人的组成-基于知识图谱的搜索

在教育场景下，若学生有关于学习内容的提问，或业务层面的提问，则要求问答机器人的回答必须精准，来满足业务的要求
因此需要通过知识图谱来快速检索，所提内容的相关信息，并针对这些相关信息进行处理，得到精准的回答
本次内容中直接应用了知识图谱基本功能，关系寻找及关系提取
后续学习中会提供更多的应用

2. 伪代码实现

from py2neo import Graph #导入neo4j
from pyhanlp import * #导入nlp的工具包
from random import choice

#知识图谱的初步应用
class GraphSearch():
    def __init__(self):
        self.graph = Graph("http://localhost:7474", username="graph.db", password="lesson1")
        self.iswho_sql = "profile match p=(n)<-[r]-(b) where n.name='%s' return n.name,r.name,b.name"
        self.isrelation_sql = "profile match p=(n)<-[r]-(b) where n.name=~'%s' and b.name=~'%s' return n.name,r.name,b.name" 

 def search_answer(self,question):
        #使用HanLP进行词性判断
        sentence = HanLP.parseDependency(question)
        #后续可以替换成自己训练的模块首先针对句意进行分析，其次针对目标实体进行提取；但主要也是针对业务场景进行分析和处理
        seg = {}
        res_combine = ''
        for word in sentence.iterator(): 
        ##只处理nr名词：人，v动词，n名词，针对进行提问进行词性分析
            if word.POSTAG[0] == 'n' or word.POSTAG in ['v','r']:
                if word.POSTAG not in seg:
                    seg[word.POSTAG] = [word.LEMMA]
                else:
                    seg[word.POSTAG].append(word.LEMMA)
        #简单基于词性和内容判断是否为目标句式'A是谁'以此使用知识图谱进行回答
        if 'v' in seg and '是' in seg['v']:
            if 'r' in seg and 'nr' in seg and '谁' in seg['r']:
                for person in seg['nr']:
                    res = self.graph.run(self.iswho_sql%(person)).data()
                    res_combine = []
                    for i in res[:10]:
                        res_combine.append('%s是:%s%s'%(i['n.name'],i['b.name'],i['r.name']))
                return choice(res_combine)
        #基于词性和内容判断是否为目标句式'A和B的关系'以此使用知识图谱进行回答
        if 'n' in seg and '关系' in seg['n']:
            if len(seg['nr']) == 2:
                res1 = self.graph.run(self.isrelation_sql%(seg['nr'][1],seg['nr'][0])).data()
                if res1 != []:
                    res_combine = seg['nr'][0]+'的'+res2[0]['r.name']+'是'+seg['nr'][1]
                    return res_combine
                res2 = self.graph.run(self.isrelation_sql%(seg['nr'][0],seg['nr'][1])).data()
                if res2 != []:
                    res_combine = seg['nr'][1]+'的'+res2[0]['r.name']+'是'+seg['nr'][0]
                    return res_combine
        if res_combine == '':
            return None

后续在完成业务场景下的实体提取和意图识别，学习及模型训练后，丰富该功能的问答

3. 问答机器人的组成-基于网络的回答

在对话机器人构建的初期，常常面临数据不足，导致机器人无法进行准确回答，因此在前期会适当调用第三方对话的接口，来进行回答
以此防止突然冷场或机器人对话失灵
后续使用生成式的对话机器人，来解决此类问题

python 复制代码

import requests
class InterNet():
    def __init__(self):
        pass
    def search_answer(self,question):
        url = 'https://api.ownthink.com/bot?appid=xiaosi&userid=user&spoken='
        try:
            text = requests.post(url+question).json()
            if 'message' in text and text['message'] == 'success':
                return text['data']['info']['text']
            else:
                return None
        except:
            return None

4. 服务的构建-什么是flask

5. 服务的构建-我的第一个flask

python 复制代码

'''
我的第一个flask_service.py
'''
from flask_cors import cross_origin
from flask import Flask,request,redirect,url_for
import requests,json

#初始化一个flask
app = Flask(__name__)

@app.route('/test', methods=['GET', 'POST'])
@cross_origin()
def myfirst_service():
    if request.method ==  "POST":
        data = request.get_data().decode()
        data = json.loads(data)
        return json.dumps(data['question'],ensure_ascii=False)

if __name__ == "__main__":
    app.run(host='0.0.0.0',port=8080,threaded=True)
'''
我的第一个send.py
'''
import requests
import json
url = 'http://127.0.0.1:8080/test'
question = '你好啊，我的第一个flask'
data = {
    'question':question
    }
print(requests.post(url,data=json.dumps(data)).json())
#service
from flask_cors import cross_origin
from flask import Flask,request,redirect,url_for
import requests,json
from mychatbot import template,CorpusSearch,GraphSearch,InterNet

#global 
app = Flask(__name__)
#init the chatbot
template_model = template()
CorpusSearch_model = CorpusSearch()
GraphSearch_model = GraphSearch()
InterNet_model = InterNet()

@app.route('/test', methods=['GET', 'POST'])
@cross_origin()
def myfirst_service():
    if request.method ==  "POST":
        #sta_post = time.time()
        data = request.get_data().decode()
        data = json.loads(data)
        return json.dumps('1',ensure_ascii=False)

@app.route('/template', methods=['GET', 'POST'])
@cross_origin()
def test_template():
    if request.method ==  "POST":
        #sta_post = time.time()
        data = request.get_data().decode()
        data = json.loads(data)
        question = data['question']
        answer = template_model.search_answer(question)
        return json.dumps(answer,ensure_ascii=False)
@app.route('/CorpusSearch', methods=['GET', 'POST'])
@cross_origin()
def test_CorpusSearch():
    if request.method ==  "POST":
        #sta_post = time.time()
        data = request.get_data().decode()
        data = json.loads(data)
        question = data['question']
        answer = CorpusSearch_model.search_answer(question)
        return json.dumps(answer,ensure_ascii=False)

@app.route('/GraphSearch', methods=['GET', 'POST'])
@cross_origin()
def test_GraphSearch():
    if request.method ==  "POST":
        #sta_post = time.time()
        data = request.get_data().decode()
        data = json.loads(data)
        question = data['question']
        answer = GraphSearch_model.search_answer(question)
        return json.dumps(answer,ensure_ascii=False)

@app.route('/InterNet', methods=['GET', 'POST'])
@cross_origin()
def test_InterNet():
    if request.method ==  "POST":
        #sta_post = time.time()
        data = request.get_data().decode()
        data = json.loads(data)
        question = data['question']
        if '是谁' in question or '关系' in question:
            return json.dumps(None,ensure_ascii=False) 
        try:
            answer = InterNet_model.search_answer(question)
        except:
            answer = None
        # except:
            # answer = '对不起啊，小智无法解决这个问题'
        return json.dumps(answer,ensure_ascii=False)
if __name__ == "__main__":
    app.run(host='0.0.0.0',port=8080,threaded=True)