CARE-RATE: An AI-based dynamic online information filtering system

滑铁卢的基于对话和人工智能的搜索引擎软件(也称为CARE-Rate)是一个基于云的新软件 软件是通过以用户为中心的设计方法开发的(即目标主要用户的参与)。 它使用自然语言处理和深度学习，因此最终用户将具有问答类型 与系统对话，以捕获他/她遇到的问题以及相关的上下文 信息。软件系统使用该信息来执行搜索、过滤和对相关结果进行排名 补充用户特定上下文的在线资源。它可以在与以下内容相关的网站上学习“元数据” 用户需求(例如，如果用户需要有关财务规划的信息，则需要一组适当的文档 按照这一特定标准进行策划)。用户将能够对结果的“有用性”进行评级，从而启用该系统 随着时间的推移自主学习，改进未来的搜索和结果。当前具有竞争力的搜索引擎 依赖个性化搜索或长期搜索历史，并生成大量(主要)不相关的 信息，特别是在手头的系统无法收集用户的历史搜索历史或 用户的意图因词汇量不足而变得模糊。 滑铁卢技术的优势包括：(1)通过主动调整搜索结果来获得更好的搜索结果 用户需求(2)软件在与用户需求相关的网站上学习“元数据”(3)半监督 学习(即用户对搜索结果的评级)使系统能够执行逐渐更好的搜索。 这项创新在大多数行业都有应用，包括广告、电子商务、教育等。 这些行业的企业面临着拥有大量数据而又缺乏全面数据的挑战 自动搜索系统，并且无法基于用户的查询或关键字提取高度相关的内容 投入。其他用例的示例包括数据库挖掘，特别是内部专有数据搜索 有复杂技术术语或元数据的地方(例如律师事务所、医疗和制药行业)。

Waterloo's Dialog & AI Based Search Engine Software (also called CARE-RATE) is a novel cloud-based software is developed through user-centred design approaches (i.e. involvement from targeted primary users). It employs natural language processing and deep learning such that an end user will have a Q & A type dialogue with the system to capture a problem he/she is encountering as well as relevant contextual information. The software system uses this information to perform a search, filter, and rank results of relevant online resources that complement the user's specific context. It can learn "meta-data" on websites relevant to user needs (e.g. if a user needs information on financial planning, an appropriate set of documents will be curated with that particular criterion). Users will be able to rate the "usefulness" of results, enabling the system to autonomously learn over time, improving future searches and results. Current competitive search engines rely on personalized search or long-term search histories and generate large amounts of (mainly) irrelevant information, particularly in cases where the system at hand is unable to gather users' historical search history or the user' intent is obscured by an inadequate vocabulary. Advantage of Waterloo's technology include: (1) better search results by pro-actively adapting search results to the needs of the user (2) software learns "meta-data" on websites relevant to user needs (3) semi-supervised learning (i.e. user rating of search results) enables system to perform progressively better searches. This innovation has applications in most industries including advertising, e-commerce, education, etc. Enterprises in these industries face the challenge of having large sets of data while lacking comprehensive automated search systems and are unable to extract highly relevant content based on users' queries or keyword inputs. Examples of other use cases include database mining, internal proprietary data searches particularly where there are complex technical terms or meta-data (e.g. law firms, medical and pharmaceutical industries).