|
|
|
| Research on Claim Feature-Driven Patent Pre-application Evaluation and Grant Probability Prediction |
| Li Wang1, Jia Zhixuan2, Zhang Yiren2, Cheng Fan2, Ran Congjing2 |
1.College of National Governance, Inner Mongolia Normal University, Hohhot 010022
2.School of Information Management, Wuhan University, Wuhan 430072 |
|
|
|
|
Abstract A claim feature-driven model rooted in the “Three-Step Method” of patent examination was developed for patent pre-application evaluation and grant probability prediction, to address the critical imbalances between patent application volume and conversion rates in China, as well as the lack of quantitative mechanisms for pre-application assessment. The Levenshtein algorithm was first utilized in synergy with market transfer data to optimize sample selection by constructing positive and negative datasets that incorporate the dimension of “practical utility.” Subsequently, focusing on the core semantics of independent claims, claim dependency was introduced to quantify the scope of the technical features. This was integrated with a multilayer perceptron attention mechanism to achieve the dynamic weighted fusion of legal and semantic features, thereby realizing a consolidated representation of the “inventiveness” dimension. In constructing a cross-source heterogeneous prior art contrast pool and employing the K-means clustering algorithm, this study establishes adaptive dynamic evaluation thresholds to form a binary classification for the “novelty” dimension, ultimately achieving a pre-application assessment. Further embedding an autoencoder framework based on positive and negative sample comparisons allows the quantification of the evaluation results. Through the reconstruction error, the model characterizes the distribution consistency of the patents under evaluation within feature space, thereby refining the prediction of grant probabilities. Empirical results from the new-energy vehicle sector demonstrate that in the feature extraction stage, an F1-score of 0.919 was achieved by incorporating legal structural features into the model, significantly outperforming general semantic models. In the pre-application evaluation stage, the model identified a “recommended for application” rate of 25.28%. The model optimizes and supplements the existing grant standards by rigorously filtering low-market-value “dormant patents.” In the probability prediction stage, the average grant probabilities for the recommended and non-recommended groups were 72.50% and 47.50%, respectively, indicating significant discriminative power and statistical robustness. This research not only addresses the deficiencies of existing evaluation models regarding logical closed loops and legal feature utilization but also provides a scientific methodological path and technical support for universities and research institutes to improve patent application quality and promote efficient industry-university-research transformation.
|
|
Received: 28 July 2025
|
|
|
|
1 国家知识产权局. 2024年知识产权统计年报[EB/OL]. (2024-12-31) [2025-08-17]. https://www.cnipa.gov.cn/tjxx/jianbao/year2024/indexy.html.
2 冉从敬, 李旺. 高校专利价值评估模型构建[J]. 情报杂志, 2022, 41(7): 65-70.
3 国家知识产权局. 2024年中国专利调查报告[EB/OL]. (2025-01-22) [2025-08-17]. https://www.cnipa.gov.cn/module/download/downfile.jsp?classid=0&showname=2024%E5%B9%B4%E4%B8%AD%E5%9B%BD%E4%B8%93%E5%88%A9%E8%B0%83%E6%9F%A5%E6%8A%A5%E5%91%8A.pdf&filename=aaf2cdea693842ff8dd65d78f7d0f8b3.pdf.
4 谭文英: 专利评估靠前一步 成果转化“落地生根”[EB/OL]. (2024-03-13) [2025-05-11]. https://www.cnipa.gov.cn/art/2024/3/13/art_3344_190953.html.
5 向姝璇, 操玉杰, 毛进. 基于权利要求层级特征的专利相似度计算方法研究[J]. 数据分析与知识发现, 2024, 8(2): 33-43.
6 Indukuri K V, Ambekar A A, Sureka A. Similarity analysis of patent claims using natural language processing techniques[C]// Proceedings of the International Conference on Computational Intelligence and Multimedia Applications. Piscataway: IEEE, 2007: 169-175.
7 Yang S Y, Soo V W. Extract conceptual graphs from plain texts in patent claims[J]. Engineering Applications of Artificial Intelligence, 2012, 25(4): 874-887.
8 Lee C, Song B M, Park Y. How to assess patent infringement risks: a semantic patent claim analysis using dependency relationships[J]. Technology Analysis & Strategic Management, 2013, 25(1): 23-38.
9 乔永忠. 技术创新测度: 专利权利要求技术方案创造性[J]. 科学学研究, 2024, 42(7): 1547-1555.
10 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.
11 付姣, 梁丽芝. 融合权利要求语义特征的专利价值早期预测研究[J]. 情报杂志, 2024, 43(2): 183-191.
12 俞琰, 尚明杰, 赵乃瑄. 权利要求特征驱动的专利关键词抽取方法[J]. 情报学报, 2021, 40(6): 610-620.
13 李健智, 王红玲, 王中卿. 基于图卷积网络的专利摘要自动生成研究[J]. 计算机科学, 2022, 49(S1): 172-177.
14 教育部 国家知识产权局 科技部关于提升高等学校专利质量促进转化运用的若干意见[EB/OL]. (2020-02-03) [2024-05-12]. https://www.gov.cn/zhengce/zhengceku/2020-02/21/content_5481750.htm.
15 李鹏, 李坤白, 沈满, 等. 高校专利申请前评估工作体系建设进展——以西安电子科技大学为例[J]. 中国高新科技, 2023(12): 98-100.
16 关于强化高价值专利运营 促进科技成果转化的若干措施[EB/OL]. (2023-06-13) [2025-05-13]. https://www.cideg.tsinghua.edu.cn/info/kjzcck/4760.
17 江苏大学知识产权研究中心, 江苏大学知识产权学院. 江苏大学知识产权工作手册[R/OL]. (2022-04-26) [2025-07-25]. https://zscq.ujs.edu.cn/gongzuoshouce.pdf.
18 华南师范大学专利申请办事指引[R/OL]. (2024-05-23) [2025-07-25]. https://statics.scnu.edu.cn/pics/kjc/2024/0523/1716435349975860.pdf.
19 西安科技大学科技处. 关于在全校范围内开展专利申请前评估工作的通知[EB/OL]. (2024-01-07) [2025-07-25]. https://kjc.xust.edu.cn/info/1035/7207.htm.
20 北京大学. 关于印发《北京大学专利工作管理办法》的通知[EB/OL]. (2022-06-29) [2025-05-13]. https://kjkfb.pku.edu.cn/beijingdaxuezhuanligongzuoguanlibanfaxiaofa-2022-134hao.pdf.
21 西北农林科技大学科学技术发展研究院. 关于开展专利申请前评估工作的通知[EB/OL]. (2025-03-26) [2025-07-27]. https://kyy.nwsuaf.edu.cn/tzgg/cgyzscqc/4d3b1e47a11e42e7814e4971d0a69ed1_mobile.htm.
22 湖南大学图书馆. 服务内容[EB/OL]. (2022-04-21) [2025-05-13]. https://lib.hnu.edu.cn/engine2/general/more?t=21212D6839A525B500595B9E746D1E33732751E3098987B743B22B5108DC16B8FA392BA021B0BF0E912CA5C7B79DB9DA.
23 彭玲玲, 张弦, 张驰. 高校开展专利申请前评估的必要性与可行性研究[J]. 中国发明与专利, 2021, 18(11): 65-70.
24 田海燕. 高校专利申请前评估: 中美差异及启示[J]. 创新科技, 2021, 21(3): 49-56.
25 陈婷, 张立昆. 我国高校专利申请前评估纵深发展的制约因素及对策研究[J]. 图书馆学刊, 2025, 47(6): 91-96.
26 王岩, 王会丽. 高校专利申请前评估的理念与实践问题探讨[J]. 中国高校科技, 2022(10): 75-83.
27 陈从连. 我国高校专利申请前评估制度研究[D]. 广州: 华南理工大学, 2022.
28 赵国璧, 朱欣昱, 周景华. 高校专利申请前评估工作的可实操性研究及典型案例评析[J]. 中国高校科技, 2023(3): 93-96.
29 张玲玲, 林青, 余梦霞, 等. 高质量保护与转化导向下高校专利申请前评估框架体系探索[J]. 科技管理研究, 2024, 44(7): 106-114.
30 方曦, 李清瑞. 高校专利申请前价值评估体系构建及实证研究[J]. 科技管理研究, 2024, 44(8): 48-56.
31 张昭昭, 王军雷, 王亮亮, 等. 汽车企业专利申请前评估模型研究[J]. 汽车文摘, 2022(8): 56-62.
32 姜娟. 基于ISM-AHP的高校专利申请前评估模型研究[J]. 中国高校科技, 2025(1): 47-54.
33 李清瑞. 高校专利申请前价值评估研究[D]. 上海: 上海应用技术大学, 2024.
34 邓娜, 王雨佳, 杨洋, 等. 基于Sentence-BERT与孤立森林算法的专利新颖性评估[J]. 情报杂志, 2025, 44(2): 174-182.
35 周哲文. 基于果蝇嗅觉神经网络与技术聚类的专利新颖度评估方法研究[D]. 武汉: 武汉大学, 2022.
36 中华人民共和国专利法[EB/OL]. (2020-11-19) [2025-06-15]. http://www.npc.gov.cn/npc/c2/c30834/202011/t20201119_308800.html.
37 潘世坤, 刘卓乾. 解读《专利审查指南》(2023)对创造性“三步法”的重要补充[J]. 法制博览, 2024(16): 1-4.
38 王雅平. 论产品专利权利要求中的功能性特征[D]. 济南: 山东大学, 2021.
39 Wu X K, Yang J J. High-speed railway and patent trade in China[J]. Economic Modelling, 2023, 123: 106276.
40 De Marco A, Scellato G, Ughetto E, et al. Global markets for technology: evidence from patent transactions[J]. Research Policy, 2017, 46(9): 1644-1654.
41 王欣, 郭英. 高校专利申请前评估优化研究[J]. 图书情报工作, 2025, 69(8): 131-138.
42 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.
43 Wittfoth S. Measuring technological patent scope by semantic analysis of patent claims - An indicator for valuating patents[J]. World Patent Information, 2019, 58: 101906.
44 张洋, 王乙竹, 李丹阳. 从价值评估到创新赋能: 专利评价的方法、场景与挑战[J]. 情报理论与实践, 2026, 49(4): 29-38, 57.
45 白全民, 王东旭, 贾永飞, 等. 基于专利分类号和文本相似度的双元创新识别及测度方法研究[J]. 科技管理研究, 2025, 45(1): 10-17.
46 Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
47 Vincent P, Larochelle H, Bengio Y, et al. Extracting and composing robust features with denoising autoencoders[C]// Proceedings of the 25th International Conference on Machine Learning. New York: ACM Press, 2008: 1096-1103.
48 冉从敬, 李旺. 校企合作视角下高校高价值专利推荐模型构建——以“新能源汽车”为例[J]. 图书情报工作, 2023, 67(11): 115-126.
49 冉从敬, 丁群哲, 李旺, 等. 基于权重平衡算法的专利可交易性预测研究[J]. 情报学报, 2025, 44(5): 549-561.
50 Riesen K, Bunke H. Graph classification based on vector space embedding[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2009, 23(6): 1053-1081.
51 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.
52 Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection[C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2999-3007.
53 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.
54 Reimers N, Gurevych I. Sentence-BERT: sentence embeddings using Siamese BERT-networks[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2019: 3980-3990.
55 Beltagy I, Lo K, Cohan A. SciBERT: a pretrained language model for scientific text[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2019: 3615-3620.
56 Bekamiri H, Hain D S, Jurowetzki R. PatentSBERTa: a deep NLP based hybrid model for patent distance and classification using augmented SBERT[J]. Technological Forecasting and Social Change, 2024, 206: 123536.
57 Gao T Y, Yao X C, Chen D Q. SimCSE: simple contrastive learning of sentence embeddings[C]// Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2021: 6894-6910.
58 Beltagy I, Peters M E, Cohan A. Longformer: the long-document transformer[PP/OL]. V2. arXiv (2020-12-02). https://doi.org/10.48550/arXiv.2004.05150. |
|
|
|
