def NER(words):
entity_name, entity_type, entity_loaction = [], [], []
entities_name, entities_type, entities_location = [], [], []
result = evaluate_line(words)
for i in range(len(result['entities'])):
entity_name = result['entities'][i]['word']
entity_start_loction = result['entities'][i]['start']
entity_end_loction = result['entities'][i]['end']
entity_type = result['entities'][i]['type']
entities_name.append(entity_name)
entities_type.append(entity_type)
entities_location.append({entity_start_loction, entity_end_loction})
a = ''
t = 0
if result['entities'][i]['type'] == 'VER':
a = result['entities'][i]['word']
t, eachline = VER(a)
if t == 1:
result['entities'][i]['simlity'] = ['Find']
if t == 2:
result['entities'][i]['simlity'] = [eachline]
if t == 0:
result['entities'][i]['simlity'] = ['Lost']
# print('VER entity:')
# print(ver)
else:
simility = []
a = result['entities'][i]['word']
# print('Normal entity:')
# print(ner)
t = lookfordict(a)
if t == 1:
result['entities'][i]['simlity'] = ['Find']
if t == 2:
#print('Looking up Pinyin....'+a)
word = a
pyy, t = test(word)
if t == 3:
#print('Lost')
result['entities'][i]['simlity'] = ['Lost']
elif t == 4:
simility.append(pyy)
result['entities'][i]['simlity'] = [simility]
return entities_name, entities_type, entities_location
filePathNames = fileTools.eachFile("./resourcesTest/")
#print(filePathNames)
maxAllstep = len(filePathNames)
process_bar1 = processBar.ShowProcess(maxAllstep)
trainData = open("trainData", 'w')
for path in filePathNames:
process_bar1.show_process()
fileNames = fileTools.eachFile(path + "/")
#maxstep = len(fileNames)
#process_bar = processBar.ShowProcess(maxstep)
for item in fileNames:
#process_bar.show_process()
content = fileTools.readFile(item)
#print(content)
segmemtSentence = main.evaluate_line(content)
print(segmemtSentence)
exit()
number = 0
for num in segmemtSentence:
tag = num.split("/")
if tag[1] in ["nr", "nrf", "nrj"]:
number += 1
if number:
for word in segmemtSentence:
ll = word.split("/")
#print(ll[0][0])
if ll[1] not in ["nr", "nrf", "nrj"]:
for i in ll[0]:
a = "".join([i, " ", "O", "\n"])
def first_ask():
final_dii = {'-HEIGHT': [], '-WEIGHT': [], '-EAT': [], '-BAD': [], '-EMO': []}
global idd
global special
global all_dict
global dii
if request.method=='GET':
return render_template('first_ask.html')
if request.method=='POST':
id1 = request.form.get("idtext")
if id1!='':
idd=id1
input_text=request.form.get("input_text")
if input_text=='':
return render_template('first_ask.html',res_text = '最近如何？')
if input_text!='' and dii =={'-HEIGHT': [], '-WEIGHT': [], '-EAT': [], '-BAD': [], '-EMO': []}: ##有输入的话
mytext, label_list = evaluate_line(if_ask=True, another_input=input_text, save=FLAGS.ckpt_path)
print(label_list,mytext)
dii = dictionary(label_list=label_list, mytext=mytext)
all_dict.append(dii)
keras.backend.clear_session()
if [] not in dii.values(): #一次输完的话
final_dii=dii
print('finalllllllllllll',final_dii)
suo(dii=final_dii,input_id=idd)
return render_template('first_ask.html', res_text='Thankyou')
if [] in dii.values():
for i, ele in enumerate(dii):
if dii[ele] == []:
used.append(ele)
return render_template('first_ask.html', res_text='那今天的%s状况怎么样呢?\n' % (look_up[i]))
if input_text!='' and dii!={'-HEIGHT': [], '-WEIGHT': [], '-EAT': [], '-BAD': [], '-EMO': []}: #第二次询问
print('2_ask') #我的身高90公分
cou = 0
for i in dii:
if dii[i] != []:
cou = cou + 1
for i,ele in enumerate(dii):
print(i,ele,dii[ele],used)
if dii[ele] ==[] and ele not in used:
used.append(ele)
mytext2, label_list2 = evaluate_line(if_ask=True, another_input=input_text,save=FLAGS.ckpt_path)
all_dict.append(dictionary(label_list=label_list2, mytext=mytext2))
# print(i,ele)
print('看看吧',all_dict)
return render_template('first_ask.html', res_text='那今天的%s状况怎么样呢?\n' % (look_up[i]))
elif len(used)==5-cou: ##最后一条
mytext2, label_list2 = evaluate_line(if_ask=True, another_input=input_text, save=FLAGS.ckpt_path)
all_dict.append(dictionary(label_list=label_list2, mytext=mytext2))
print('看看final吧', all_dict)
for diction in all_dict:
for i in diction:
final_dii[i] = final_dii[i] + diction[i]
print('finalllllllllllll',final_dii)
suo(dii=final_dii, input_id=idd)
return render_template('first_ask.html', res_text='Thankyou')
else:
continue
def hello():
query=input('您好，有什么可以帮助您：\n')
now_text=np.array(list(query))
print(now_text)
print(type(now_text))
v_now=t.texts_to_sequences(now_text)
print(v_now)
count2=[]
for i in v_now:
count2 = count2 + i
print(count2)
pad_now= pad_sequences([count2],maxlen=maxlen,padding='post')
print(pad_now)
modeling=train_class()
result_list=list(modeling.predict(pad_now))
# print(m.predict(X_dev))m.predict(pad_now)
#
# classis=np.argmax(m.predict(X_dev), axis=1)
for i in result_list:
if i <=0.5:
class_result=input('您需要的服务是修理本公司的产品吗(回答 yes or no )？\n')
if class_result=='yes':
print('抱歉，修理产品系统维护中，敬请期待！')
else:
hello()
else:
body_query=input('您需要的服务是检查身体吗(回答 yes or no )？\n')
if body_query=='yes':
keras.backend.clear_session()
height,weight=evaluate_line(if_ask=False)
print(height,weight)
while height==''or weight=='':
body_query2=input('对不起我还不够智能，请重新告知完整的身高和体重\n')
keras.backend.clear_session()
height, weight = evaluate_line(if_ask=True, another_input=body_query2)
reask =input('确认您的身高是'+height+'您的体重是'+weight+'(回答 yes or no)?\n')
if reask=='yes':
import pymongo
client = pymongo.MongoClient(host='localhost', port=27017)
db = client.test
collection = db.students
student = {
'id': '20191023',
'Height': height,
'weight': weight,
}
result = collection.insert(student)
print('已录入数据库，稍后为您服务')
else:
hello()
else:
hello()
collection = db.students
FLAGS = tf.app.flags.FLAGS
look_up = [
'身高',
'体重',
'吃的',
'抽烟喝酒',
'情绪',
]
all_dict = []
from mainto_diction import cut_max, get_char_list, dictionary
input_id = input('请输入ID\n')
# keras.backend.clear_session()
mytext, label_list = evaluate_line(save=FLAGS.ckpt_path)
dii = dictionary(label_list=label_list, mytext=mytext)
keras.backend.clear_session()
if [] in dii.values(): ##缺什么问什么
for i, key in enumerate(dii):
if dii[key] == []:
re_ask = input('那今天的%s状况怎么样呢?\n' % (look_up[i]))
keras.backend.clear_session()
mytext2, label_list2 = evaluate_line(if_ask=True,
another_input=re_ask,
save=FLAGS.ckpt_path)
all_dict.append(dictionary(label_list=label_list2, mytext=mytext2))
for diction in all_dict: