A comprehensive pharmaceutical recommendation system was designed based on
the patients and drugs features extracted from this http URL and this http URL.
First, data from these databases were combined, and a dataset of patients and
drug information was built. Secondly, the patients and drugs were clustered,
and then the recommendation was performed using different ratings provided by
patients, and importantly by the knowledge obtained from patients and drug
specifications, and considering drug interactions. To the best of our
knowledge, we are the first group to consider patients conditions and history
in the proposed approach for selecting a specific medicine appropriate for that
particular user. Our approach applies artificial intelligence (AI) models for
the implementation. Sentiment analysis using natural language processing
approaches is employed in pre-processing along with neural network-based
methods and recommender system algorithms for modeling the system. In our work,
patients conditions and drugs features are used for making two models based on
matrix factorization. Then we used drug interaction to filter drugs with severe
or mild interactions with other drugs. We developed a deep learning model for
recommending drugs by using data from 2304 patients as a training set, and then
we used data from 660 patients as our validation set. After that, we used
knowledge from critical information about drugs and combined the outcome of the
model into a knowledge-based system with the rules obtained from constraints on
taking medicine.

设计了一个基于患者和药物特征的全面药物推荐系统，将数据从多个数据库中整合为一个患者和药物信息的数据集，其中使用了人工智能模型、自然语言处理方法和推荐系统算法进行数据建模，通过药物相互作用、患者条件和药物特征生成了基于矩阵分解的模型，构建了基于规则的知识库系统。

RECOMMED: 一款全面的药物推荐系统

RECOMMED: A Comprehensive Pharmaceutical Recommendation System

The MultiCoNER shared task aims at detecting semantically ambiguous and
complex named entities in short and low-context settings for multiple
languages. The lack of contexts makes the recognition of ambiguous named
entities challenging. To alleviate this issue, our team DAMO-NLP proposes a
knowledge-based system, where we build a multilingual knowledge base based on
Wikipedia to provide related context information to the named entity
recognition (NER) model. Given an input sentence, our system effectively
retrieves related contexts from the knowledge base. The original input
sentences are then augmented with such context information, allowing
significantly better contextualized token representations to be captured. Our
system wins 10 out of 13 tracks in the MultiCoNER shared task.

本文介绍了 DAMO-NLP 提出的基于维基百科的多语言知识库，用于提供上下文信息以帮助在短文本和低上下文环境中的多义和复杂命名实体识别。通过将知识库中的相关上下文与输入句子进行匹配，我们的系统能够有效地检索相关上下文信息并将其用于输入句子的增强，从而更好地捕捉上下文信息表示。我们的系统在 MultiCoNER 共享任务中获得了 13 个中 10 个的胜利。