TY - EJOU AU - Qin, Wei AU - Luo, Xiangfeng TI - Association Link Network Based Concept Learning in Patent Corpus T2 - Intelligent Automation \& Soft Computing PY - 2018 VL - 24 IS - 3 SN - 2326-005X AB - Concept learning has attracted considerable attention as a means to tackle problems of representation and learning corpus knowledge. In this paper, we investigate a challenging problem to automatically construct a patent concept learning model. Our model consists of two main processes; which is the acquisition of the initial concept graph and refined process for the initial concept graph. The learning algorithm of a patent concept graph is designed based on the Association Link Network (ALN). A concept is usually described by multiple documents utilizing ALN here in concept learning. We propose a mixture-ALN, which add links between documents and the lexical level, compared with the ALN. Then, a heuristic algorithm is proposed to refine the concept graph, leading to a more concise and simpler knowledge for the concept. The heuristic algorithm consists of four phases; first, for simplifying bag of words for concept in patent corpus, we start to select a core node from the initial concept graph. Second,for learning the association rule for the concept, we searched important association rules around the core node in our rules collection. Third, to ensure coherent semantics of the concept, we selected corresponding documents based on the selected association rules and words. Finally, for enriching semantics of the refined concept, we iteratively selected core nodes based on the corresponding documents and restarted our heuristic algorithm. In the experiments, our model shows effectiveness and improvements in prediction accuracy in the retrieve task of the patent. KW - Association link network KW - Concept learning KW - Heuristic algorithm KW - Patent corpus KW - Retrieve task DO - 10.31209/2018.100000032