一种用于为文档匹配评议专家的系统以及方法

• Format: Patent
• Language: Chinese
• Published: 08.03.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

本发明实施例提供了一种用于为文档匹配评议专家的系统以及方法，该系统包括：专家特征提取模块，其利用神经网络用于根据专家描述文本和专家学术专长信息获取专家特征表示；文档特征提取模块，其利用神经网络根据待评议文档的文档描述、学科分类信息和关键词信息获取文档特征表示；专家匹配模块，其利用神经网络根据专家特征表示和文档特征表示计算专长匹配度，并基于专长匹配度生成候选专家列表；本发明在专家和待评议文档方面均从不同的类别提取相关的信息，以更精准地提取到两者的语义特征，降低语义鸿沟，提高专家推荐的精度。 The embodiment of the invention provides a system and method for matching appraisal experts for documents, and the system comprises an expert feature extraction module which employs a neural network for obtaining expert feature representation according to an expert description text and expert academic specialist information; a document feature extraction module which is used for acquiring document feature representation according to the document description, the subject classification information and the keyword information of the to-be-reviewed document by utilizing a neural network; an expert matching module which is used for calculating an expert matching degree according to the expert feature representation and the document feature representation by utilizing a n