国内外专利挖掘研究进展与前瞻  

AGlobal Literature Review in Recent Advancement of Patent Mining

作　　者：陈亮[1] 陈利利 许海云 魏超 苏娜 尚玮姣[4] Chen Liang;Chen Lili;Xu Haiyun;Wei Chao;Su Na;Shang Weijiao(Institute of Scientific and Technical Information of China,Beijing 100038;Management School,Shandong University of Technology,Zibo 255000;Institute of Science and Development,Chinese Academy of Sciences,Beijing 100190;Research Institute of Forestry Policy and Information,Chinese Academy of Forestry,Beijing 100091)

机构地区：[1]中国科学技术信息研究所,北京100038 [2]山东理工大学管理学院,淄博255000 [3]中国科学院科技战略咨询研究院,北京100190 [4]中国林业科学研究院林业科技信息研究所,北京100091

出　　处：《图书情报工作》2024年第2期110-133,共24页Library and Information Service

基　　金：中央级公益性科研院所基本科研业务项目“中信所统一数据底座建设与运营管理”(项目编号:ZD2023-04);国家自然科学基金面上项目“基于弱信号时效网络演化分析的变革性科技创新主题早期识别方法研究”(项目编号:72274113)研究成果之一。

摘　　要：[目的/意义]专利挖掘是获取技术情报的重要途径,在近年来智能技术快速发展的驱动下,专利挖掘不仅在方法自动化、智能化和挖掘深度、精确度上取得了长足进步,而且展露出数据与算法紧密融合的发展新范式,亟需通过综述形成对其研究现状和未来发展趋势的全面认识。[方法/过程]将文献调研活动的主要环节连成闭环“检索→筛选→梳理→查漏→拓展和再次检索”并持续更新、反复迭代,调研范围包括国内外专利挖掘的相关论文、专利、数据集、算法竞赛评测活动、专利信息服务平台乃至代码托管网站和模型托管网站,并在叙述内容中穿插专家访谈、竞赛选手交流会以及笔者学术成果评审意见中获得的相关信息,最终完成对专利挖掘的系统综述。[结果/结论]专利基础资源的种类和数量较之前增长较快,专利挖掘方法的训练和性能评测逐步具有数据基准和统一测度标准;专利挖掘前沿方法紧跟智能技术发展步伐以实现技术升级和性能提升,而统计学习、人工规则、软件工具等传统方法也在学习成本、实践成本和方法效果的平衡中得到优化和发展;专利挖掘的研究范围实现了从数据处理、规范化到专利基础服务和技术情报分析的全面覆盖,并开启了专利智慧法律的探索。[Purpose/Significance]Patent mining is a significant means to achieve technical intelligence from patent documents.Driven by recent advancement of AI technologies,not only have patent mining methods achieved competitive performance in terms of automation,intelligence,mining depth and accuracy,but also they have revealed a new paradigm of integrating datasets and algorithms together,which indicates a comprehensive survey of related research achievements and future development trends is urgent.[Method/Process]This paper linked the main steps of literature review into a closed loop“searching→screening→sorting→checking→expanding and re-searching”and kept updating and iterating.Review scope covered the related papers,patents,datasets,algorithm competition,patent information service platforms,and even code hosting and model hosting Websites.In a meanwhile,relevant information from expert interviews,competition player seminar and academic achievement reviews was also included in the narrative content.[Result/Conclusion]It finds that the types and quantity of patent resources are growing more rapidly than before,which paved the way for training and evaluating algorithms and models in an uniform standard.Forefront patent mining methods are closely following the pace of intelligent technology development to achieve technological upgrades and performance enhancements,while traditional methods such as statistical learning,manual rules,and software tools have been optimized and developed in the balance of learning costs,practical costs and method performances.The research scope of patent mining has achieved full coverage from data processing,normalization to basic patent service supporting and technological intelligence analysis,and the exploration of legal judgement prediction for patent lawsuit have been launched.

关 键 词：专利挖掘 基础资源建设 深度学习 信息抽取 专利检索 

分 类 号：G25[文化科学—图书馆学]