原文地址:http://www.bugingcode.com/blog/ChatterBot_Dialogue_process.html
部署机器人的各种属性,根据前面的章节里聊天机器人的各种属性,对聊天机器人进行相应的配置,创建一个符合自己的机器人。
bot = ChatBot(
'Default Response Example Bot',
storage_adapter='chatterbot.storage.SQLStorageAdapter',
logic_adapters=[
{
'import_path': 'chatterbot.logic.BestMatch'
},
{
'import_path': 'chatterbot.logic.LowConfidenceAdapter',
'threshold': 0.65,
'default_response': 'I am sorry, but I do not understand.'
}
],
trainer='chatterbot.trainers.ListTrainer'
)
logic_adapters:用来设置所选择的算法,这里选择的是chatterbot.logic.BestMatch,也就是最匹配方式,从训练的对话中找到最相识的语句,根据对话,提供回答。
trainer:选择的是chatterbot.trainers.ListTrainer
在trainer中,决定选择哪种构造方式来创建上下文的关系。
def train(self, conversation):
"""
Train the chat bot based on the provided list of
statements that represents a single conversation.
"""
previous_statement_text = None
for conversation_count, text in enumerate(conversation):
print_progress_bar("List Trainer", conversation_count + 1, len(conversation))
statement = self.get_or_create(text)
if previous_statement_text:
statement.add_response(
Response(previous_statement_text)
)
previous_statement_text = statement.text
self.storage.update(statement)
在ListTrainer中,用上下句来构建一个statement ,statement相当于存储了一个上下对话的关系,在查找的时候,先找到最合适的上文,下文就是答案了。这就是一个训练的过程,训练的这一过程,主要是在构建statement,并把statement放到storage中。
storage_adapter有几种可选的方案chatterbot.storage.SQLStorageAdapter,MongoDatabaseAdapter,存储之前训练的statement,把statement存储在数据库中,默认的数据库选择的是本地的sqlite3。
把语料准备好,就聊天机器人进行训练,语料的来源比较重要,像之前的小黄鸭语料的来源,主要是来源于众包,用户会交小黄鸭怎么去回答问题,语料是重要的一种选择,一个语料的质量决定了聊天机器人的可玩性。
训练的过程,就是一个建立statement并存储的过程,代码在ListTrainer中都有详细的体现。
bot.train([
'How can I help you?',
'I want to create a chat bot',
'Have you read the documentation?',
'No, I have not',
'This should help get you started: http://chatterbot.rtfd.org/en/latest/quickstart.html'
])
聊天机器人主要的过程是产生答案的过程,而答案的选择最关键的就是算法的实现,之前有介绍过,可玩性比较高的聊天机器人必须拥有不同的算法,对不同的聊天内容给出不一样的答案,根据输入选择最合适的算法,产生最好的答案。在机器人对话中,最常见的问题是一些生活的问题,比如,天气,时间,笑话等,根据问题,选择最匹配的算法,给出精彩的答案。
response = bot.get_response(‘How do I make an omelette?’)
get_response的过程
采用的是ChatBot的方法,一开始先得到输入,并对数据进行过滤,在根据输入数据选择算法,得出答案。
def get_response(self, input_item, session_id=None):
"""
Return the bot's response based on the input.
:param input_item: An input value.
:returns: A response to the input.
:rtype: Statement
"""
if not session_id:
session_id = str(self.default_session.uuid)
input_statement = self.input.process_input_statement(input_item)
# Preprocess the input statement
for preprocessor in self.preprocessors:
input_statement = preprocessor(self, input_statement)
statement, response = self.generate_response(input_statement, session_id)
# Learn that the user's input was a valid response to the chat bot's previous output
previous_statement = self.conversation_sessions.get(
session_id
).conversation.get_last_response_statement()
self.learn_response(statement, previous_statement)
self.conversation_sessions.update(session_id, (statement, response, ))
# Process the response output with the output adapter
return self.output.process_response(response, session_id)
算法是如何进行选择的呢?
在multi_adapter.py 算法选择中,遍历了所有我们已经选择的算法,算法通过 can_process 进行选择,对输入生成的statement 进行匹配,并通过confidence来进行评分,而应该还可以进行扩展,通过不同的得分,来选择算法,最佳匹配。
def process(self, statement):
"""
Returns the output of a selection of logic adapters
for a given input statement.
:param statement: The input statement to be processed.
"""
results = []
result = None
max_confidence = -1
for adapter in self.get_adapters():
if adapter.can_process(statement):
output = adapter.process(statement)
if type(output) == tuple:
warnings.warn(
'{} returned two values when just a Statement object was expected. '
'You should update your logic adapter to return just the Statement object. '
'Make sure that statement.confidence is being set.'.format(adapter.class_name),
DeprecationWarning
)
output = output[1]
results.append((output.confidence, output, ))
self.logger.info(
'{} selected "{}" as a response with a confidence of {}'.format(
adapter.class_name, output.text, output.confidence
)
)
if output.confidence > max_confidence:
result = output
max_confidence = output.confidence
else:
self.logger.info(
'Not processing the statement using {}'.format(adapter.class_name)
)
# If multiple adapters agree on the same statement,
# then that statement is more likely to be the correct response
if len(results) >= 3:
statements = [s[1] for s in results]
count = Counter(statements)
most_common = count.most_common()
if most_common[0][1] > 1:
result = most_common[0][0]
max_confidence = self.get_greatest_confidence(result, results)
result.confidence = max_confidence
return result
ChatterBot的架构和流程基本清楚以后,就是对ChatterBot的扩展,一个好的ChatterBot聊天机器人,还有很多需要完成的地方,比如多轮对话,
我:天气如何?
机器人:你在位置在那里?
我:厦门
机器人:多云转晴,32摄氏度
转载请标明来之:http://www.go2coding.com/
更多教程:go2coding