寻找类似的项目 [英] Finding similiar items

问题描述

哪种Microsoft认知服务（或Azure机器学习服务？）是最好和最简单的用于解决在文章中找到类似文章的问题。文章是一串文字。并假设我没有关于
文章的用户交互数据。 



Microsoft认知服务中是否有任何可以解决此问题的内容-THE盒？我似乎无法使用Recommendations API，因为我没有交互/用户数据。 

Which Microsoft Cognitive Services (or Azure Machine Learning services?) is best and simplest to use to solve the problem of finding similar articles given an article. An article is a string of text. And assuming I do not have user interaction data on the articles. 

Are there anything in Microsoft Cognitive Services that can solve this problem out-of-the-box? It seems I cannot use the Recommendations API since I don't have interaction/user data. 

亲切的问候，

Anthony Mak

Anthony Mak

推荐答案

正确，建议API旨在提供类似用户消耗的项目或可能由同一用户一起消费的项目。这并不意味着项目本身是相似的。

Correct, the Recommendations API is meant to provide items that are consumed by similar users or items that are likely to be consumed together by the same user. It does not mean that the items themselves are similar.

看起来你想要一种方法来检查文本条目是否相似。您可以使用Text Analytics API从文档中提取关键短语......然后使用这些关键短语来评估这些文档之间的相似之处。 Text Analytics
API至少可用于解决您的方案。

It looks like you want a way to check if the text entries are similar. You could use the Text Analytics API to extract key phrases from your documents... and then use those key-phrases to evaluate similarities between those documents. The Text Analytics API may at a minimum be useful in solving your scenario.

这篇关于寻找类似的项目的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！