import codecs
import sys
import gl
import query
import similarity
import time
import mention_id
import knowledge_base
reload(sys)
sys.setdefaultencoding('utf-8')
if __name__ == '__main__':
# Step1: load knowledge base
print 'begin to load kb'
kb = knowledge_base.KnowledgeBase()
kb.load_knowledge_base()
print 'finish loading kb'
# Step2: load mention2id
print 'begin to load mention2id'
mid = mention_id.MentionID()
mid.load_mention_2_id()
print 'finish loading mention2id'
# training phase
# Step3: load questions
print 'begin to load questions'
query_list = query.QueryList()
query_list.read_query_file(gl.testing_data_split_file_name)
import sys
import cherrypy
sys.path.insert(-1, '../nlp/')
sys.path.insert(-1, '../logic_component/')
import tagger
import knowledge_base
from rulebases import rb_sports
db = knowledge_base.KnowledgeBase(rb_sports.SportsClaim)
class Server(object):
def __init__(self):
self.tgr = tagger.initialize_tagger()
def factcheck(self, txt):
tokens = tagger.tokenize(txt)
tags = tagger.get_tags(self.tgr, tokens)
answers = []
for extractor in [
tagger.extract_player_relation, tagger.extract_age_relation
]:
relation = extractor(tags)
if relation:
print 'found relation', relation
ans = db.trueOrFalse(
rb_sports.SportsClaim(relation[0], tuple(relation[1:])))
print ans
def response_message(self, message):
# 의도 분류
# 0: Fragments
# 1: Statement
# 2: Question
# 3: Command
# 4: Rhetorical question
# 5: Rhetorical command
# 6: Intonation - dependent utterance
intent_index = self.intent_analyzer.predict(self.mecab, message)
print('intent_index : ' + str(intent_index))
# 사용자의 말과 챗봇의 말이 어떤 message_type 인지 기록
# message_type : CN -> Client Normal, BF -> Bot Feature ( 추출을 위한 질문 )
message_type = ''
if intent_index == 2:
message_type = 'CQ'
elif intent_index == 3:
message_type = 'CC'
else:
if self.conversation_list:
last_conversation = self.conversation_list[-1]
if last_conversation['type'] == 'BF':
message_type = 'CA'
self.save_conversation_list(message, message_type, '')
response_message = []
if intent_index not in [2, 3]:
# 로직대로.. 원래 하던대로
# type 을 가져올 때, Bot 이 말한 마지막 message_type 을 가지고 옴
prior_conversation_type = self.get_prior_bot_message_type()
response_message = self.print_gambit_message(
message, intent_index, prior_conversation_type['message_type'],
prior_conversation_type['feature_key'])
elif intent_index == 2:
bot_message_type = ''
know_base = knowledge_base.KnowledgeBase()
response_message = know_base.response_question(self.mecab, message)
# knowledgebase 에서 검색 실패 하는 경우 정규식 매칭 진행
if len(response_message) == 0:
bot_message_type = 'BA'
response_message = self.find_matching_rule(message)
# 정규식 매칭도 진행되지 않는 경우는 얼버무리기 로직
if len(response_message) == 0:
bot_message_type = 'BQ'
response_message = self.response_quibble_message(message)
else:
bot_message_type = 'BA'
self.save_conversation_list(response_message, bot_message_type, '')
elif intent_index == 3:
bot_message_type = ''
comm_processor = command_processor.CommandProcessor()
response_message_dict = comm_processor.process_command(
self.mecab, message)
# response_message 를 dict 으로 받아서 적절한 처리를 하는 방향으로 수정
# recoomand 의 경우 봇과 함께 동작해야 함 ( 다른 항목들처럼 독립적이지 않음 )
if response_message_dict['command'] == 'recommend':
bot_message_type = 'BF'
self.find_feature_candidate(message)
response_message = self.print_gambit_message(
message, intent_index, bot_message_type, '')
else:
bot_message_type = 'BA'
response_message = response_message_dict['message']
if not response_message:
response_message = self.response_quibble_message(message)
self.save_conversation_list(response_message, bot_message_type,
'')
return response_message