All Projects → WenRichard → Customer Chatbot

WenRichard / Customer Chatbot

Licence: mit
中文智能客服机器人demo,包含闲聊和专业问答2个部分,支持自定义组件(Chinese intelligent customer chatbot Demo, including the gossip and the professional Q&A(FAQ) , support for custom components!)

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Customer Chatbot

Tensorflow Ml Nlp
텐서플로우와 머신러닝으로 시작하는 자연어처리(로지스틱회귀부터 트랜스포머 챗봇까지)
Stars: ✭ 176 (-11.11%)
Mutual labels:  chatbot, similarity
Qamodel For Retrievalchatbot
客服机器人,Chinese Retreival chatbot(中文检索式机器人)用到的一些QA模型,基于tf-idf,lsa,cnn,transformer,bert等
Stars: ✭ 326 (+64.65%)
Mutual labels:  chatbot, qa
chatbot
kbqa task-oriented qa seq2seq ir neo4j jena seq2seq tf chatbot chat
Stars: ✭ 32 (-83.84%)
Mutual labels:  qa, chatbot
Chat
基于自然语言理解与机器学习的聊天机器人,支持多用户并发及自定义多轮对话
Stars: ✭ 516 (+160.61%)
Mutual labels:  chatbot, qa
FAQ-Bot-QQ
一个基于Mirai框架的Q群问答机器人
Stars: ✭ 30 (-84.85%)
Mutual labels:  qa, chatbot
Nlp tensorflow project
Use tensorflow to achieve some NLP project, eg: classification chatbot ner attention QAetc.
Stars: ✭ 27 (-86.36%)
Mutual labels:  chatbot, qa
Deep Reinforcement Learning For Dialogue Generation In Tensorflow
Deep-Reinforcement-Learning-for-Dialogue-Generation-in-tensorflow
Stars: ✭ 178 (-10.1%)
Mutual labels:  chatbot
Yve Bot
Smart rule-based bot. For Browser & Node.
Stars: ✭ 181 (-8.59%)
Mutual labels:  chatbot
Tock
Tock - the open source conversational AI toolkit
Stars: ✭ 175 (-11.62%)
Mutual labels:  chatbot
Fbmq
(Deprecated) Facebook Messenger Platform Python Library (Facebook Chatbot Library)
Stars: ✭ 172 (-13.13%)
Mutual labels:  chatbot
Delbot
It understands your voice commands, searches news and knowledge sources, and summarizes and reads out content to you.
Stars: ✭ 191 (-3.54%)
Mutual labels:  chatbot
Chatbot
一个可以自己进行训练的中文聊天机器人, 根据自己的语料训练出自己想要的聊天机器人,可以用于智能客服、在线问答、智能聊天等场景。目前包含seq2seq、seqGAN版本、tf2.0版本、pytorch版本。
Stars: ✭ 2,441 (+1132.83%)
Mutual labels:  chatbot
Environmentoverrides
QA assistant for a SwiftUI app: change the color scheme, accessibility settings, and localization on the fly!
Stars: ✭ 181 (-8.59%)
Mutual labels:  qa
Linebot
🤖 SDK for the LINE Messaging API for Node.js
Stars: ✭ 184 (-7.07%)
Mutual labels:  chatbot
Qiscus Sdk Android
Qiscus provide everything you need to power up your app with chats. And it's now made simple.
Stars: ✭ 175 (-11.62%)
Mutual labels:  chatbot
Red Discordbot
A multi-function Discord bot
Stars: ✭ 2,855 (+1341.92%)
Mutual labels:  chatbot
Flottbot
A chatbot framework written in Go. All configurations are made in YAML files, or inside scripts written in your favorite language.
Stars: ✭ 175 (-11.62%)
Mutual labels:  chatbot
Mutual
A Dataset for Multi-Turn Dialogue Reasoning
Stars: ✭ 181 (-8.59%)
Mutual labels:  chatbot
Hackerbot
Chat with hacker assistant
Stars: ✭ 186 (-6.06%)
Mutual labels:  chatbot
Adversarial Learning For Neural Dialogue Generation In Tensorflow
Adversarial-Learning-for-Neural-Dialogue-Generation-in-Tensorflow
Stars: ✭ 181 (-8.59%)
Mutual labels:  chatbot

Customer-Chatbot

中文智能客服机器人demo,包含闲聊和专业问答2个部分,支持自定义组件

Chinese intelligent customer chatbot Demo, including the gossip and the professional Q&A(FAQ) , support for custom components!

smart-chatbot-zero (First version)

  • 介绍

一、 本项目由两个部分组成,一是基于tf-idf检索的召回模型,二是基于CNN的精排模型,本项目将两者融合,构建 召回+排序 的客服聊天机器人。系统支持闲聊模式FAQ问答模式,采取的数据分别为小黄鸡闲聊数据集和垂直领域的FAQ问答数据集。该版本为第一版本,速度等其他性能还有待提升,这些工作会在后期陆续上传。根据目前的反馈,系统的难点在于构建一个精度高且耗时短的rerank模型,如果要在工业上使用,需要大改;如果是想要熟悉问题系统的一个整套流程,这个项目百分之百能满足需求。

二、 只有recall阶段的系统可查看:
基于tf-idf的问答机器人


xiaotian-chatbot1.0 (Second version)

  • 介绍

该项目是在 First version 的基础上进行改进,加入了一些规则
目前该系统的优点在于:
一、召回+排序 2个模块互不干扰,便于自定义修改以及维护
二、系统采取了排序规则优化,提升了检索速度
三、加入了简单的倒排索引,优化了检索流程

本项目依靠route函数进行问答任务转换,分为 chat模式 和 faq 模式,这样做的目的主要是系统可以根据不同的任务设置不同的情景对话,同时系统将2个语料集分开管理,避免了搜索时间的增加。目前的效果是如果你不输入end终止对话,那么你可以在对话中进行chat模式和faq模式的随意转化,随心所欲!

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].