Tag Archives: DDA

Identification of technology frontiers of artificial intelligence-assisted pathology based on patent citation network (FULL-TEXT)

Patents related to artificial intelligence-assisted pathology were searched and collected from the Derwent Innovation Index (DII), which were imported into Derwent Data Analyzer (DDA, Clarivate Derwent, New York, NY, USA) for authority control, and imported into the freely available computer program Ucinet 6 for drawing the patent citation network. The patent citation network according to the citation relationship could describe the technology development context in the field of artificial intelligence-assisted pathology. The patent citations were extracted from the collected patent data, selected highly cited patents to form a co-occurrence matrix, and built a patent citation network based on the co-occurrence matrix in each period. Text clustering is an unsupervised learning method, an important method in text mining, where similar documents are grouped into clusters. The similarity between documents are determined by calculating the distance between them, and the two documents with the closest distance are combined. The method of text clustering was used to identify the technology frontiers based on the patent citation network, which was according to co-word analysis of the title and abstract of the patents in this field.

For FULL-TEXT https://doi.org/10.1371/journal.pone.0273355

Author(s): Ting Zhang,Juan Chen,Yan Lu,Xiaoyi Yang,Zhaolian Ouyang
Organization(s):Institute of Medical Information & Library, Chinese Academy of Medical Sciences and Peking Union Medical College
Source: PloSone
Year: 2022

Intelligent Patent Text Summarization Analysis Method

Patent mining and patent analysis of patented technologies will help protect the interests of intellectual property rights and provide enterprises with correct scientific research directions. In order to study the profitable patents of pharmaceutical companies, this paper proposes an Abstractive RL-LSTM neural network method based on patent texts. The reinforcement learning method is introduced into LSTM. The purpose is to rely on Q-learning to learn the relationship between the main layers. The two parallel layers share the weight of attention from the Q value, and realize the hierarchical control between the LSTM structure of the patent document and the LSTM structure of the sentence. The experimental results show that compared with other methods, the method proposed in this paper can further improve the ROUGE index and alleviate the dependence of the decoder on the input.

The team uses Derwent Data Analyzer to provide information about patent trends. Globally, until August 2020, there are a total of 192 patents on gene therapy.


Author(s): Yong Ji
Organization(s): Renmin University of China
Source: 7th International Conference on Systems and Informatics (ICSAI)
Year: 2021