|
|
|
| Technology Genealogy Construction and Innovation Path Identification Based on Multi-granularity Semantic Computing |
| Yang Jinqing1, Luo Xingyu1, Xiong Bingqiao2, Cao Gaohui1 |
1.School of Information Management, Central China Normal University, Wuhan 430079
2.Strategic Studies Institute of Hubei Yangtze Laboratory, Wuhan 430010 |
|
|
|
|
Abstract As global technological competition intensifies and investments in research and development continue to increase, governments and investment institutions are increasingly pressured to identify novel paths that can drive technological innovation, mitigate technological uncertainty, avoid redundant efforts, and increase the output efficiency and social value of technological investments. Thus, unraveling the deep genealogical structures embedded within massive volumes of patents, clarifying the kinship among technologies, and tracing their inheritance chains are central to dispel the “technology fog” and detect “technological white spaces,” thereby facilitating the effective translation of patents and fostering industrial innovation. Building on the technological development theory, this study introduces the concept and framework of technological genealogy. First, we computed the patent similarity at the paragraph and phrase granularities. Subsequently, the optimal weighted combination of these granularities was determined by validating it against co-occurrence patterns in the international patent classification hierarchy, thereby quantifying the inheritance relationships among patents. A tree-structured technological genealogy was then constructed using patents as nodes and semantic associations as edges aligned along a temporal axis. Leveraging this genealogy, multiple types of innovation paths were identified, and the flow patterns of technological elements were revealed. Finally, an empirical analysis was conducted on 16899 patents for the B81B-007* technology in the 2.5-dimensional packaging domain. The results demonstrate that the technological genealogies exhibit complex dynamics of derivation and convergence while maintaining strong continuity. The discrete innovation paths focus on short-term advances, are highly diverse, and appear fragmented. The extended innovation paths capture the convergence and recombination of technological elements, demonstrating dynamic transitions from derivation to convergence. In addition, the sustained innovation paths span the entire timeline, forming coherent evolutionary paths, with later stages marked by iterative upgrades toward higher precision.
|
|
Received: 13 May 2025
|
|
|
|
1 邬金鸣, 胡智杰, 姚茹, 等. 面向技术创新过程表征和描述的技术要素关联概念模型[J]. 图书情报工作, 2024, 68(10): 53-65.
2 Hain D S, Jurowetzki R, Buchmann T, et al. A text-embedding-based approach to measuring patent-to-patent technological similarity[J]. Technological Forecasting and Social Change, 2022, 177: 121559.
3 唐晓波, 吴海婷, 吴佳琳. 基于特征知识元的专利语义引用识别方法研究——以量子计算领域为例[J]. 情报理论与实践, 2023, 46(10): 86-95.
4 索传军, 牌艳欣. 科学问题谱系构建研究[J]. 中国图书馆学报, 2025, 51(1): 61-81.
5 李旺, 冉从敬, 王福新, 等. 基于权利要求层级结构的专利相似度计算方法研究[J]. 图书情报工作, 2025, 69(23): 84-98.
6 邓娜, 纪媛琳, 胡云川. 融合多关系异构图和语义特征的核心专利预测方法[J]. 情报杂志, 2026, 45(1): 83-90.
7 谢瑶瑶, 邓三鸿, 王昊, 等. 基于SAO语义挖掘的用户需求-专利技术匹配[J]. 数据分析与知识发现, 2024, 8(8/9): 213-225.
8 任海英, 宋圆圆, 彭锐. 发明中的知识搜索规则与搜索成本——基于知识网络建模与仿真[J]. 情报科学, 2025, 43(4): 148-159.
9 Lee P C, Su H N, Chan T Y. Assessment of ontology-based knowledge network formation by vector-space model[J]. Scientometrics, 2010, 85(3): 689-703.
10 吴柯烨, 孙建军, 谢紫悦. 基于专利文本挖掘的细粒度技术机会分析[J]. 情报学报, 2023, 42(10): 1199-1212.
11 钱翰. 福柯的谱系学究竟何指[J]. 学术研究, 2016(3): 155-159, 178.
12 刘绍怀. 学术链: 客观存在的学术关系形态[J]. 思想战线, 2011, 37(1): 1-3.
13 王宏宇, 王晓光. 基于大规模开放学术图谱的研究前沿分析框架[J]. 情报理论与实践, 2021, 44(1): 102-109.
14 王双, 赵筱媛, 潘云涛, 等. 学术谱系视角下的科技人才成长研究——以图灵奖人工智能领域获奖者为例[J]. 情报学报, 2018, 37(12): 1232-1240.
15 刘宇航, 张云泉. 构建与方法学对称的问题学——以计算机学科为例[J]. 中国科学院院刊, 2024, 39(7): 1264-1275.
16 Hu D Y, Wang C Y, Zheng S, et al. Investigating the genealogy of the literature on digital pathology: a two-dimensional bibliometric approach[J]. Scientometrics, 2022, 127(2): 785-801.
17 Zheng Z J, Ma Y X, Ba Z C, et al. Tree knowledge structure for better insight: capturing biomedical science-technology knowledge linkage with MeSH[J]. Journal of Informetrics, 2024, 18(4): 101568.
18 Morrison D A. Genealogies: pedigrees and phylogenies are reticulating networks not just divergent trees[J]. Evolutionary Biology, 2016, 43(4): 456-473.
19 朱宇婧, 陈芳, 赵萍, 等. 融合美国商业管制清单和专利的技术链关键路径识别研究——以EDA软件领域为例[J]. 图书情报工作, 2023, 67(21): 89-99.
20 郭靖怡, 王学昭, 陈小莉. 基于专利文本中产品关联关系的产业技术链构建与实证研究——以锂离子电池产业为例[J]. 图书情报工作, 2023, 67(5): 108-118.
21 李剑飞, 吴红, 崔哲, 等. 产品/技术纵向延伸视域下的高校专利转移对象识别研究——以气凝胶领域为例[J]. 图书情报工作, 2021, 65(3): 67-74.
22 翟东升, 夏军, 张杰, 等. 基于专利特征抽取的技术树构建方法研究[J]. 情报学报, 2015, 34(7): 717-724.
23 张硕, 汪雪锋, 乔亚丽, 等. 技术预测研究现状、趋势及未来思考: 数据分析视角[J]. 图书情报工作, 2022, 66(10): 4-18.
24 林原, 张乐, 丁堃, 等. 融合专利表示的技术路线图构建研究[J]. 情报杂志, 2021, 40(10): 15-20.
25 戎军涛, 索传军, 周彦廷, 等. 基于创新知识元谱系的学术论文新颖性测度研究[J]. 图书情报工作, 2024, 68(1): 27-38.
26 丁晟春, 秦天允, 王艺霖. 基于知识图谱的专利侵权风险预警研究[J]. 情报学报, 2024, 43(8): 992-1002.
27 曹树金, 曹茹烨. 基于知识图谱支持科研创新的跨学科知识发现研究[J]. 情报理论与实践, 2022, 45(11): 10-20.
28 刘俊婉, 庞博, 徐硕. 基于弱信号的颠覆性技术早期识别研究[J]. 情报学报, 2023, 42(12): 1395-1411.
29 胡泽文, 王梦雅, 韩雅蓉. 基于LDA2Vec-BERT的新兴技术主题多维指标识别与演化分析研究——以颠覆性技术领域: 区块链为例[J]. 现代情报, 2024, 44(9): 42-58.
30 马建红, 王晨曦, 闫林, 等. 基于产品生命周期的专利技术主题演化分析[J]. 情报学报, 2022, 41(7): 684-691.
31 邓娜, 林涵辉, 陈旭, 等. ILRD: 一种融合IPC_LDA和文本语义特征的专利推荐模型[J]. 情报杂志, 2025, 44(3): 170-179, 207.
32 Liu Y M, Chen M. The knowledge structure and development trend in artificial intelligence based on latent feature topic model[J]. IEEE Transactions on Engineering Management, 2024, 71: 12593-12604.
33 苗宏慧, 全情爽, 舒心. 基于BERTopic的科技人才政策文本主题识别与量化分析——以东北三省为例[J]. 现代情报, 2025, 45(4): 110-121.
34 刘颖, 于春梅, 李晓晨, 等. 基于改进BERTopic模型的领域主题表征及演化研究[J]. 图书情报工作, 2025, 69(3): 78-89.
35 王益成, 蒋星宇, 郑彦宁. 基于BERTopic模型的科技报告主题挖掘与演化分析——以生物技术领域为例[J]. 情报科学, 2024, 42(9): 51-60.
36 丁敬达, 汤迎涛, 邱均平. 专利离群程度演变视角的高价值专利评估研究——以新能源汽车领域为例[J]. 情报科学, 2025, 43(11): 100-108.
37 Wang Y X, Hou Y T, Che W X, et al. From static to dynamic word representations: a survey[J]. International Journal of Machine Learning and Cybernetics, 2020, 11(7): 1611-1630.
38 Mikolov T, Chen K, Corrado G, et al. Efficient estimation of word representations in vector space[PP/OL]. V3. arXiv (2013-09-07). https://doi.org/10.48550/arXiv.1301.3781.
39 Pennington J, Socher R, Manning C D. GloVe: global vectors for word representation[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2014: 1532-1543.
40 Bojanowski P, Grave E, Joulin A, et al. Enriching word vectors with subword information[J]. Transactions of the Association for Computational Linguistics, 2017, 5: 135-146.
41 Devlin J, Chang M W, Lee K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: Association for Computational Linguistics, 2019: 4171-4186.
42 周志刚, 窦路遥, 李毅, 等. 基于双边语义和文本序列特征的潜在高价值专利识别研究[J]. 数据分析与知识发现, 2024, 8(12): 52-61.
43 周潇, 高雅倩, 樊嘉逸. 基于BERT词嵌入的专利检索策略研究[J]. 情报学报, 2023, 42(11): 1347-1357.
44 张贞港, 余传明. 基于知识增强的文本语义匹配模型研究[J]. 情报学报, 2024, 43(4): 416-429.
45 陈帅朴, 钱宇星, 钱志强, 等. 多重特征关联和图注意力网络融合的文献分类方法研究——以中文医学文献为例[J]. 情报学报, 2024, 43(4): 470-490.
46 谢小东, 吴洁, 盛永祥, 等. 基于多模态特征融合的相似专利识别方法研究[J]. 图书情报工作, 2024, 68(18): 112-122.
47 赵建飞, 陈挺, 王小梅, 等. 基于大语言模型知识自蒸馏的无标注专利关键信息抽取[J]. 数据分析与知识发现, 2024, 8(8/9): 133-143.
48 邢晓昭, 苑朋彬, 陈亮, 等. 面向技术识别的专利实体抽取——以类脑智能领域为例[J]. 情报杂志, 2024, 43(6): 126-133, 144.
49 郭世杰, 董璐, 孙蒙鸽, 等. 基于智能文本挖掘的技术水平预测研究——以声呐技术为例[J]. 情报理论与实践, 2024, 47(5): 12-17, 38.
50 刘鹏, 王炳森, 张珂, 等. 基于弱信号感知的“卡脖子”关键核心技术甄别与竞争态势分析——以深海潜水器为例[J]. 情报理论与实践, 2025, 48(6): 102-112.
51 张娴, 方曙. 专利引用网络主路径方法研究述评与展望[J]. 图书情报工作, 2016, 60(20): 140-148.
52 Li L, Lin H F, Lyu Y B. Technology cluster coupling and invulnerability of industrial innovation networks: the role of centralized structure and technological turbulence[J]. Scientometrics, 2022, 127(3): 1209-1231.
53 陈悦, 王康, 宋超, 等. 一种用于技术融合与演化路径探测的新方法: 技术群相似度时序分析法[J]. 情报学报, 2021, 40(6): 565-574.
54 Stek P E. Identifying spatial technology clusters from patenting concentrations using heat map kernel density estimation[J]. Scientometrics, 2021, 126(2): 911-930.
55 林巧, 胡智杰, 吴俣, 等. 数智驱动的科研领域创新路径识别方法[J]. 科技管理研究, 2025, 45(18): 250-258.
56 刘春江, 刘自强, 方曙. 基于SAO的技术主题创新演化路径识别及其可视化研究[J]. 情报学报, 2023, 42(2): 164-175.
57 岳丽欣, 刘自强, 刘春江, 等. 融合引用和文本特征的技术创新路径识别研究[J]. 图书情报工作, 2023, 67(3): 49-60.
58 冯立杰, 秦浩, 张珂, 等. 基于离群专利和多维技术创新地图的技术机会识别路径研究[J]. 情报理论与实践, 2023, 46(9): 79-86.
59 冯立杰, 刘可辉, 王金凤, 等. 基于知识网络与多维技术创新地图的技术机会识别路径研究与应用[J]. 数据分析与知识发现, 2023, 7(8): 62-77.
60 冯立杰, 马亚坤, 王金凤, 等. 多维技术创新地图融合TO-RFM模型的技术机会识别与评价路径研究[J]. 情报理论与实践, 2023, 46(2): 145-155, 108.
61 逯万辉. 基于专利引文网络挖掘的技术研发路径识别与颠覆性创新信号探测研究[J]. 情报学报, 2024, 43(9): 1059-1069.
62 颜端武, 白敬毅, 李晨晨, 等. 科技领域技术演进的多路径识别及创新特性分析[J]. 情报理论与实践, 2021, 44(11): 99-107.
63 Grootendorst M. KeyBERT: BibTeX[CP/OL]. (2021-01-25) [2025-04-25]. https://doi.org/10.5281/zenodo.4461265.
64 Khan M Q, Shahid A, Uddin M I, et al. Impact analysis of keyword extraction using contextual word embedding[J]. PeerJ Computer Science, 2022, 8: e967.
65 刘怀兰, 刘盛, 周源, 等. 基于多源文本挖掘的技术演化路径识别[J]. 情报理论与实践, 2022, 45(11): 178-187.
66 Patra B G, Maroufy V, Soltanalizadeh B, et al. A content-based literature recommendation system for datasets to improve data reusability-A case study on Gene Expression Omnibus (GEO) datasets[J]. Journal of Biomedical Informatics, 2020, 104: 103399. 责任编辑 魏瑞斌） |
|
|
|
