GithubHelp home page GithubHelp logo

wenrichard / customer-chatbot Goto Github PK

View Code? Open in Web Editor NEW
305.0 8.0 112.0 4.69 MB

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!)

License: MIT License

Python 100.00%
nlp chatbot customer-chatbot faq similarity-measures similarity qa

customer-chatbot's Introduction

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!

  • 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


  • 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!

Cite
如果你在研究中使用了xiaotian-chatbot1.0,请按如下格式引用:

@software{xiaotian-chatbot1.0,
  author = {ZhengWen Xie},
  title = {xiaotian-chatbot1.0: A Customer-Chatbot System},
  year = {2019},
  url = {https://github.com/WenRichard/Customer-Chatbot},
}

customer-chatbot's People

Contributors

wenrichard avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

customer-chatbot's Issues

关于word_vocab.txt问题

请问这个word_vocab.txt文件作用是什么呢?能否提供下?在精排的时候出现了数据维度不对齐的情况「Assign requires shapes of both tensors to match. lhs shape= [3,200] rhs shape= [1146,200]」

运行项目

整个项目要看到效果图那样,运行顺序是怎么样的呢,具体运行哪个文件,要重新训练数据吗

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.