以任务为导向的对话式人工智能在Airbnb客户支持中的应用

How Airbnb is powering automated support to enhance the host and guest experience

艾尔邦如何利用自动化支持来提高房东和客人的体验

Gavin Li, Mia Zhao

李佳文赵美雅

mother and daughter sitting on a chair, scrolling through their phone

Customer Support (CS) can make or break a guest’s travel experience. To support Airbnb’s community of guests and Hosts, we have been investing heavily in developing intelligent CS solutions leveraging state-of-the-art natural language processing (NLP), machine learning (ML), and artificial intelligence (AI) technologies.

客户支持(CS)可以成就或破坏客人的旅行体验。为了支持Airbnb的客人和房东社区,我们一直在大力投资,利用最先进的自然语言处理(NLP)、机器学习(ML)和人工智能(AI)技术,开发智能CS解决方案。

In this blog post, we’ll introduce the automated support system at Airbnb, which employs the latest task-oriented conversational AI technology, through the lens of a recently launched feature called Mutual Cancellation. We will describe in detail how we framed the business problem as an AI problem, how we collected and labeled training data, how we designed and built the ML models, and how the models were deployed in the online system. Throughout each step, we’ll discuss some technical challenges we faced during this project and the solutions we innovated to address these challenges.

在这篇博文中,我们将介绍Airbnb的自动支持系统,该系统采用了最新的面向任务的对话式人工智能技术,通过最近推出的名为相互取消的功能来介绍。我们将详细描述我们如何将业务问题框定为人工智能问题,如何收集和标记训练数据,如何设计和建立ML模型,以及如何在在线系统中部署这些模型。在每个步骤中,我们将讨论我们在这个项目中面临的一些技术挑战以及我们为解决这些挑战而创新的解决方案。

A Case Study: Mutual Cancellation

一个案例研究。相互取消

Prior to the development of the mutual cancellation model, guests needed to involve CS agents, even if they had already reached an agreement with the host for canceling a reservation. This meant that issues took longer to get resolved and precious CS agent hours were wasted. To solve this issue, we developed AI models that help guests and Hosts self-resolve cancellation and refund issues without involving a CS agent. This empowers hosts and guests to decide what is best for them, while allowing us to focus CS agent hours where they are needed most.

在开发相互取消模式之前,客人需要涉及CS代理,即使他们已经与房东达成了取消预订的协议。这意味着问题需要更长的时间才能得到解决,宝贵的CS代理时间被浪费了。为了解决这个问题,我们开发了人工智能模型,帮助客人和房东自我解决取消和退...

开通本站会员,查看完整译文。

首页 - Wiki
Copyright © 2011-2024 iteam. Current version is 2.125.3. UTC+08:00, 2024-05-20 20:55
浙ICP备14020137号-1 $访客地图$