在当今科技发展日新月异的背景下，及时发现和把握有价值的技术机会对于实现突破性技术创新具有至关重要的意义。开展技术机会识别研究，可以帮助研究人员敏锐地捕捉未来科技发展趋势，为行业内关键问题提供创新性解决方案，进而推动科技创新与产业升级的良性循环，为社会经济可持续发展提供源源不断的动力。

本文结合语义分析和复杂网络分析构建了一套技术机会识别方法体系。首先以语义网络的形式表示技术知识要素，将SAO结构的SA和AO作为语义网络中的节点。同时，通过识别知识元素之间的共现关系，建立节点之间的连边，形成一个完整的SAO语义网络，用于识别候选技术机会。然后，综合考虑技术机会创新水平、市场前景及技术合作程度和复杂程度等特征因素，根据历史技术机会实证探究影响技术机会价值的特征因素，通过建立回归模型分析各个指标对技术机会的影响，并以显著指标为基础，建立科学的技术机会目标函数。随后，通过运用启发式遗传算法在SAO语义网络上进行技术机会搜索，以得到最优的技术机会集合。最后，通过语义相似度匹配算法识别能体现该技术机会的一组专利，从而为领域技术机会的转化落地指明方向。在实证分析部分，本文选取人工智能领域的专利数据进行了实证研究，并采用定性与定量相结合的评估方法对识别出的技术机会进行验证。

本文的方法与传统技术机会识别方法相比，具有以下优势：（1）本文采用基于SAO结构构建语义网络，能够更准确地表征技术机会中的深层次信息，从而增强语义网络构建的精度。此外，通过将技术机会表征为语义子网络，使得机会的表征形式更为详细和具体，同时易于解读和理解；（2）本文引入启发式遗传算法在SAO语义网络构成的技术空间中搜索技术机会，遗传算法作为一种具有预测性质的优化方法，能够有效地结合技术形成机理、历史机会表征方式，以及面向未来的探索策略，实现对未来技术机会的有效挖掘。通过遗传算法对预测语义网络进行优化搜索，可以在庞大的技术发展空间中筛选出有望引领未来发展的关键技术方向。

In the context of today's rapid technological development, timely discovery and grasp of valuable technological opportunities is of crucial significance for achieving breakthrough technological innovations. Carrying out technology opportunity identification research can help researchers keenly capture future technological development trends, provide innovative solutions to key issues in the industry, and then promote a virtuous cycle of technological innovation and industrial upgrading, providing a steady stream of sustainable social and economic development power.
This paper combines semantic analysis and complex network analysis to construct a set of technology opportunity identification method system. Firstly, technical knowledge elements are expressed in the form of semantic network, and SA and AO of SAO structure are taken as nodes in the semantic network. At the same time, by identifying the co-occurrence relationship between knowledge elements and establishing the connection between nodes, a complete SAO semantic network is formed to identify candidate technology opportunities. Then, comprehensively consider the characteristic factors such as technological opportunity innovation level, market prospect, technical cooperation degree and complexity, explore the characteristic factors that affect the value of technological opportunity based on historical technological opportunity empirical evidence, analyze the impact of each index on technological opportunity by establishing a regression model, and Based on significant indicators, establish a scientific technology opportunity evaluation function and objective function. Then, by using the heuristic genetic algorithm to search for technical opportunities on the SAO semantic network to obtain the optimal set of technical opportunities. Finally, a group of patents that can reflect the technical opportunities are identified through the semantic similarity matching algorithm, thereby pointing out the direction for the transformation of technical opportunities in the field.In the part of empirical analysis, this paper selects patent data in the field of artificial intelligence for empirical research, and a combination of qualitative and quantitative assessment methods to verify the identified technical opportunities.

Compared with the traditional technology opportunity identification method, the method in this paper has the following advantages: (1) This paper constructs a semantic network based on the SAO structure, which can more accurately represent the deep information in the technology opportunity, thereby enhancing the precision of semantic network construction. In addition, by representing technical opportunities as semantic sub-networks, the representation of opportunities is more detailed and specific, and easy to interpret and understand; (2) This paper introduces a heuristic genetic algorithm to search for technical opportunities in the technical space composed of SAO semantic networks , as an optimization method with predictive properties, genetic algorithm can effectively combine technology formation mechanism, historical opportunity representation mode, and future-oriented exploration strategy to realize effective mining of future technological opportunities. Optimizing the search of the predictive semantic network through the genetic algorithm can screen out the key technical directions that are expected to lead the future development in the huge technological development space.

[1]LIU Z, YIN Y, LIU W, et al. Visualizing the intellectual structure and evolution of innovation systems research: a bibliometric analysis[J]. Scientometrics, 2015, 103(1): 135-158.
[2]刘玉林, 菅利荣. 基于动态专利有向网络的核心技术集群演化分析[J]. 情报杂志, 2021, 40(4): 101-108.
[3]ZHANG Y, WU M, MIAO W, et al. Bi-layer network analytics: a methodology for characterizing emerging general-purpose technologies[J]. Journal of Informetrics, 2021, 15(4): 101202.
[4]YOON B, PARK Y. Development of new technology forecasting algorithm: hybrid approach for morphology analysis and conjoint analysis of patent information[J]. IEEE transactions on engineering management, 2007, 54(3): 588-599.
[5]WANG X, ZHENG X, ZHANG Q, et al. Crowdsourcing in ITS: the state of the work and the networking[J]. IEEE transactions on intelligent transportation systems, 2016, 17(6): 1596-1605.
[6]YE C, LIU D, CHEN N, et al. Mapping the topic evolution using citation-topic model and social network analysis[C]//2015 12th international conference on fuzzy systems and knowledge discovery (FSKD). IEEE, 2015: 2648-2653.
[7]宋凯, 冉从敬. 基于主题挖掘与专利评估的技术机会识别研究——以智慧农业为例[J/OL]. 图书情报工作: 1-11
[8]WANG X, MA P, HUANG Y, et al. Combining SAO semantic analysis and morphology analysis to identify technology opportunities[J]. Scientometrics, 2017, 111(1): 3-24.
[9]王金凤, 吴敏, 岳俊举, 等. 创新过程的技术机会识别路径研究——基于专利挖掘和形态分析[J]. 情报理论与实践, 2017, 40(08): 82-86.
[10]LEE Y, KIM S Y, SONG I, et al. Technology opportunity identification customized to the technological capability of SMEs through two-stage patent analysis[J]. Scientometrics, 2014, 100: 227-244.
[11]SON C, SUH Y, JEON J, et al. Development of a GTM-based patent map for identifying patent vacuums[J]. Expert Systems with Applications, 2012, 39(3): 2489-2500.
[12]YOON B, MAGEE C L. Exploring technology opportunities by visualizing patent information based on generative topographic mapping and link prediction[J]. Technological Forecasting and Social Change, 2018, 132: 105-117.
[13]WANG J, CHEN Y J. A novelty detection patent mining approach for analyzing technologicalopportunities[J]. Advanced Engineering Informatics, 2019, 42: 100941.
[14]许学国, 桂美增. 基于GTM逆向映射的技术创新机会识别——以新能源汽车为例[J]. 情报理论与实践, 2021, 44(06): 146-153+198.
[15]CHANDOLA V, BANERJEE A, KUMAR V. Anomaly detection: A survey[J]. ACM computing surveys (CSUR), 2009, 41(3): 1-58.
[16]LI X, WU Y, CHENG H, et al. Identifying technology opportunity using SAO semantic mining and outlier detection method: A case of triboelectric nanogenerator technology[J]. Technological Forecasting and Social Change, 2023, 189: 122353.
[17]黄鲁成, 李晓宇, 李晋. 基于专利的ABOD-RFM技术机会识别方法研究[J]. 情报理论与实践, 2020, 43(09): 144-149.
[18]CHOI S, YOON J, KIM K, et al. SAO network analysis of patents for technology trends identification: a case study of polymer electrolyte membrane technology in proton exchange membrane fuel cells[J]. Scientometrics, 2011, 88(3): 863-883.
[19]YANG C, HUANG C, SU J. An improved SAO network-based method for technology trend analysis: A case study of graphene[J]. Journal of informetrics, 2018, 12(1): 271-286.
[20]HAN X, ZHU D, WANG X, et al. Technology opportunity analysis: Combining SAO networks and link prediction[J]. IEEE Transactions on Engineering Management, 2019, 68(5): 1288-1298.
[21]MA J, ABRAMS N F, PORTER A L, et al. Identifying translational indicators and technology opportunities for nanomedical research using tech mining: the case of gold nanostructures[J]. Technological Forecasting & Social Change, 2019,146,767-775.
[22]翟东升, 刘鹤, 张杰, 等. 一种基于链路预测的技术机会挖掘方法[J]. 情报学报, 2016, 35(10): 1090-1100.
[23]PARK I, YOON B. Technological opportunity discovery for technological convergence based on the prediction of technology knowledge flow in a citation network[J]. Journal of Informetrics, 2018, 12(4): 1199-1222.
[24]任海英, 赵育慧, 于立婷. 基于知识网络的科学研究机会发现的机理和应用[J]. 情报理论与实践, 2018, 41(11): 89-95.
[25]任海英, 于立婷, 黄鲁成. 基于链接预测的科学研究机会发现方法研究[J]. 情报杂志, 2016, 35(10): 53-58.
[26]LEE C, KANG B, SHIN J. Novelty-focused patent mapping for technology opportunity analysis[J]. Technological Forecasting and Social Change, 2015, 90: 355-365.
[27]伊惠芳, 刘细文, 龙艺璇. 技术创新全视角下技术机会发现研究进展[J]. 图书情报工作, 2021, 65(07): 132-142.
[28]GEUM Y, JEON J, SEOL H. Identifying technological opportunities using the novelty detection technique: A case of laser technology in semiconductor manufacturing[J]. Technology Analysis & Strategic Management, 2013, 25(1): 1-22.
[29]任智军, 乔晓东, 徐硕, 等. 基于数据挖掘的技术机会发现模型研究[J]. 情报杂志, 2015, 34(06): 174-177+190.
[30]REN H, ZHAO Y. Technology opportunity discovery based on constructing, evaluating, and searching knowledge networks[J]. Technovation, 2021, 101: 102196.
[31]KLEVORICK A K, LEVIN R C, NELSON R R, et al. On the sources and significance of interindustry differences in technological opportunities[J]. Research policy, 1995, 24(2): 185-205.
[32]PORTER A L, DETAMPEL M J. Technology opportunities analysis[J]. Technological Forecasting and Social Change, 1995, 49(3): 237-255.
[33]OLSSON O. Technological opportunity and growth[J]. Journal of Economic Growth, 2005: 35-57.
[34]张妍. 市场创新活动中的技术机会[J]. 科技管理研究, 2011, 31(03): 31-34.
[35]YOON J, PARK H, SEO W, et al. Technology opportunity discovery (TOD) from existing technologies and products: A function-based TOD framework[J]. Technological Forecasting and Social Change, 2015, 100: 153-167.
[36]SONG K, KIM K S, LEE S. Discovering new technology opportunities based on patents: Text-mining and F-term analysis[J]. Technovation, 2017, 60: 1-14.
[37]YOON J, KIM K. Detecting signals of new technological opportunities using semantic patent analysis and outlier detection[J]. Scientometrics, 2012, 90(2): 445-461.
[38]LEE S, YOON B, PARK Y. An approach to discovering new technology opportunities: Keyword-based patent map approach[J]. Technovation, 2009, 29(6-7): 481-497.
[39]YUN S, SONG K, KIM C, et al. From stones to jewellery: Investigating technology opportunities from expired patents[J]. Technovation, 2021, 103: 102235.
[40]LEE M H, KIM S, KIM H, et al. Technology opportunity discovery using deep learning-based text mining and a knowledge graph[J]. Technological Forecasting and Social Change, 2022, 180: 121718.
[41]PARK M, GEUM Y. Two-stage technology opportunity discovery for firm-level decision making: GCN-based link-prediction approach[J]. Technological Forecasting and Social Change, 2022, 183: 121934.
[42]CARNABUCI G, OPERTI E. Where do firms' recombinant capabilities come from? Intraorganizational networks, knowledge, and firms' ability to innovate through technological recombination[J]. Strategic management journal, 2013, 34(13): 1591-1613.
[43]FLEMING L. Recombinant uncertainty in technological search[J]. Management science, 2001, 47(1): 117-132.
[44]ARTHUR W B. The structure of invention[J]. Research policy, 2007, 36(2): 274-287.
[45]张振刚, 罗泰晔. 基于RFM模型和随机行动者导向模型的技术机会识别[J]. 情报学报, 2021, 40(01): 53-61.
[46]ENGELBART D C. Augmenting human intellect: A conceptual framework[J]. Menlo Park, CA, 1962, 21.
[47]KHALIFA M, LIU V. Semantic network discussion representation: applicability and some potential benefits[J]. IEEE transactions on professional communication, 2006, 49(1): 69-81.
[48]杨雯丹, 曹国忠. 基于依存句法和语义网络的用户需求识别方法[J]. 机械设计, 2022, 39(10): 154-160.
[49]YOON J, KIM K. Identifying rapidly evolving technological trends for R&D planning using SAO-based semantic patent networks[J]. Scientometrics, 2011, 88(1): 213-228.
[50]周潇, 许银彪, 史益. 基于深度学习与语义挖掘的技术创新组合识别与追踪[J]. 图书情报工作, 2022, 66(10): 33-44.
[51]董建卫, 施国平, 郭立宏. 联合投资网络和引导基金网络对企业创新的影响[J]. 科学学研究, 2019, 37(02): 362-374.
[52]厉娜, 林润辉, 谢在阳. 多重网络嵌入下企业探索式创新影响机制研究[J]. 科学学研究, 2020, 38(01): 169-179.
[53]谭章禄, 陈晓, 宋庆正, 等. 基于文本挖掘的煤矿安全隐患分析[J]. 安全与环境学报, 2017, 17(04): 1262-1266.
[54]FREEMAN L C. Centrality in social networks: Conceptual clarification[J]. Social network: critical concepts in sociology. Londres: Routledge, 2002, 1: 238-263.
[55]BONACICH P. Power and centrality: A family of measures[J]. American journal of sociology, 1987, 92(5): 1170-1182.
[56]WANG X, REN H, CHEN Y, et al. Measuring patent similarity with SAO semantic analysis[J]. Scientometrics, 2019, 121: 1-23.
[57]KIM K, PARK K, LEE S. Investigating technology opportunities: the use of SAOx analysis[J]. Scientometrics, 2019, 118(1): 45-70.
[58]GUJARATI D N. Basic econometrics[M]. Prentice Hall, 2022.
[59]JOHNSON N L, KOTZ S, BALAKRISHNAN N. Continuous univariate distributions, volume 2[M]. John wiley & sons, 1995.
[60]CAMERON A C, TRIVEDI P K. Regression analysis of count data[M]. Cambridge university press, 2013.
[61]赵育慧. 基于知识网络的技术机会发现方法研究[D].北京工业大学,2020.
[62]HOLLAND J H. Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence[M]. MIT press, 1992.
[63]MITCHELL M. An introduction to genetic algorithms[M]. MIT press, 1998.
[64]DEB K. Multi-objective optimisation using evolutionary algorithms: an introduction[M]. Springer London, 2011.
[65]张阳, 王小宁. 基于Word2Vec词嵌入和高维生物基因选择遗传算法的文本特征选择方法[J]. 计算机应用, 2021, 41(11): 3151-3155.
[66]徐明远. 一种基于遗传算法的试题推荐方法[J]. 软件导刊, 2022, 21(05): 55-60.
[67]杜茂康, 李晓光, 刘岽. 融合遗传算法的特定领域情感词库构建[J]. 重庆邮电大学学报(自然科学版), 2022, 34(04): 576-584.
[68]郑荣, 魏明珠, 高志豪, 等. 基于SCAN-CPM的产业新兴技术识别与演化路径分析：以新能源汽车产业为例[J]. 图书情报工作, 2022, 66(11): 100-109.
[69]刘明信, 李丹丹, 李荣, 等. 专利视阈下产业技术创新合作网络演化分析——以肿瘤疫苗为例[J]. 图书情报工作, 2022, 66(09): 117-127.
[70]LI X, XIE Q, DAIM T, et al. Forecasting technology trends using text mining of the gaps between science and technology: The case of perovskite solar cell technology[J]. Technological Forecasting and Social Change, 2019, 146: 432-449.
[71]CHOI J, LEE J, YOON J. Anticipating promising services under technology capability for new product-service system strategies: An integrated use of patents and trademarks[J]. Computers in Industry, 2021, 133: 103542.
[72]LEE C, LEE G. Technology opportunity analysis based on recombinant search: patent landscape analysis for idea generation[J]. Scientometrics, 2019, 121: 603-632.
[73]LANJOUW, SCHANKERMAN M. Patent quality and research productivity: Measuring innovation with multiple indicators[J]. The Economic Journal, 2004, 114(495): 441-465.
[74]BASTIAN M, HEYMANN S, JACOMY M. Gephi: an open source software for exploring and manipulating networks[C]//Proceedings of the international AAAI conference on web and social media. 2009, 3(1): 361-362.
[75]吕一博, 韦明, 林歌歌. 基于专利计量的技术融合研究:判定、现状与趋势——以物联网与人工智能领域为例[J]. 科学学与科学技术管理, 2019, 40(04): 16-31.
[76]HARHOFF D, SCHERER F M, VOPEL K. Citations, family size, opposition and the value of patent rights[J]. Research policy, 2003, 32(8): 1343-1363.