PDF(1260 KB)
PDF(1260 KB)
PDF(1260 KB)
语义与演化视角下新兴技术识别——以“工业机器人”领域专利为例
Identification of emerging technologies from a semantic and evolutionary perspective: A case study of industrial robot patents
识别新兴技术发展动态对于国家、企业把握未来机遇和保持竞争优势具有重要意义。为此,本研究从新兴技术特性和专利文本出发,构建基于语义与演化视角的新兴技术识别模型。针对新兴技术评价指标,加入发展潜力以评估技术发展趋势,形成包含新颖性、持久性、社区性、增长性、发展潜力五个维度的指标体系。引入BERTopic模型与熵权法综合筛选新兴主题,弥补了传统主题识别模型在语义深度挖掘方面的不足。此外,研究将专利数据依据时间因素划分为基础期、发展期、表现期三个窗口,最终从主题与关键词两个层面确定新兴主题。以2013—2022年“工业机器人”领域专利数据进行实证分析,结果表明:语义与演化视角的新兴技术识别模型可实现对新兴技术的准确识别,获得的8个新兴技术主题与国家政策高度一致,验证了方法的准确性与科学性。本文的研究不仅为新兴技术探测理论研究提供了新视角,还为企业和政府在科技前沿领域的战略决策提供了参考依据。
Identifying the trends of emerging technology is crucial for nations and enterprises to seize future opportunities and maintain competitive advantages. This study constructed an emerging technology identification model based on the semantic and evolutionary perspectives, focusing on the characteristics of emerging technologies and patent texts. The model incorporates development potential into the evaluation indicators to assess technology development trends, forming an indicator system that includes novelty, persistence, community, growth, and development potential. By integrating the BERTopic model and entropy weight method to comprehensively screen emerging themes, the model addresses the limitations of traditional topic identification models in deep semantic mining. Furthermore, the study divided the patent data into three phases: foundation, development, and performance, and identifies emerging themes from both topic and keyword levels. An empirical analysis using the patent data from the industrial robot field from 2013 to 2022 demonstrated that the model can accurately identify emerging technologies. The eight identified themes revealed a high consistency between the identified themes and national policy documents, validating the accuracy and scientific nature of the method. This research will not only offer a new perspective for theoretical studies on emerging technologies but also provide strategic decision-making references for enterprises and governments in cutting-edge technological fields.
演化视角 / 新兴技术 / 工业机器人 / BERTopic
evolutionary perspective / emerging technology / industrial robot / BERTopic
| [1] |
刘小玲, 谭宗颖. 新兴技术主题识别方法研究进展[J]. 图书情报工作, 2020, 64 (11): 145-152.
[目的/意义] 新兴技术主题识别不仅有助于及时跟踪技术发展动态，更能尽早捕捉技术领域未来的发展契机和可能的变化趋势。梳理新兴技术主题识别的定量研究方法，并对其优缺点进行比较，可以为新兴技术主题识别方法的改进和完善提供参考。[方法/过程] 首先对"新兴技术""新兴技术主题识别"等概念的内涵进行辨析；然后调研和系统梳理国内外新兴技术主题识别的定性和定量研究方法，重点关注以文献计量和数据挖掘为主的定量研究方法，并将其划分为三类：主题词或文献统计方法、引文网络聚类方法和文本挖掘分析方法；最后综合分析各类研究方法在技术主题抽取、新兴技术主题识别指标体系构建、方法有效性验证等方面的异同和存在的缺陷，以及对方法改进的初步思考。[结果/结论] 三类方法在新兴技术主题识别的主要步骤上各有特点和优劣，均有进一步完善的空间，未来可以探索利用深度学习等技术进行技术主题的准确抽取，并构建更加全面、系统的新兴技术主题识别指标体系，以及基于机器学习进行更加严格的方法有效性验证。
<strong>[Purpose/significance]</strong> Identification of emerging technology topics not only can contribute to track the development of technologies, but also can capture the future development opportunities and trends of technologies. Reviewing the quantitative methods of emerging technology topics identification and making a comparison of them can provide reference for an improvement of the methods. <strong>[Method/process]</strong> Firstly, concepts such as "emerging technology" and "emerging technology topics identification" were analyzed; then qualitative and quantitative research methods of emerging technology topics identification at home and abroad were investigated, focusing on bibliometrics and data mining. Quantitative methods were divided into 3 categories:keywords or documents statistical method, citation network clustering and text mining. Similarities, differences and shortcomings of above methods in the extraction of technology topics, construction of emerging technology topic identification indictors, methods verification were analyzed. Improvement methods are provided preliminarily. <strong>[Result/conclusion]</strong> The three types of methods have their own characteristics, advantages and disadvantages in the three steps of emerging technology topics identification, and there is room for further improvement. In the future, we can explore the use of techniques such as deep learning to identify technology topics accurately, and build a group of more comprehensive and systematic emerging technology topic identification indicators, as well as more rigorous method validation based on machine learning.
|
| [2] |
唐恒, 邱悦文. 多源信息视角下的多指标新兴技术主题识别研究:以智能网联汽车领域为例[J]. 情报杂志, 2021, 40 (3): 81-88.
|
| [3] |
孔德婧, 董放, 陈子婧, 等. 离群专利视角下的新兴技术预测:基于BERT模型和深度神经网络[J]. 图书情报工作, 2021, 65 (17):131-141.
[目的/意义] 由于新兴技术本身的超前性，其刚出现的关注度往往不是很高。目前研究更多遵循技术发展路径依赖进行新兴技术的识别，会忽略一些颠覆现有技术轨道的技术研发。通过对与领域内主流技术相似度较低的离群专利进行分析，可以更有效地识别这类技术研发并预测新兴技术。[方法/过程] 提出一种基于深度学习的离群专利识别与新兴技术预测方法。首先使用BERT预训练模型基于专利文本构建相似度网络，识别离群专利，然后基于DNN模型构建离群专利指标与技术影响力之间的关系，实现从海量离群专利中快速、准确地预测新兴技术。最后以数控系统领域为例，从德温特专利数据库获取近10年领域内所有专利，进行实证分析。[结果/结论] 数控系统领域的实证分析结果验证了模型的有效性，同时对国家的技术发展政策制定以及相关领域企业技术布局具有重要的指导意义。
[Purpose/significance] Due to the advanced nature of emerging technologies, they are often marginalized at the initial stage of formation. Most of present researches forecast emerging technologies by analyzing the mainstream technology development path, which would neglect some research that disrupts existing technology routes. By analyzing outlier patents that are less similar to the mainstream technologies in the field, it can identify and forecast the future emerging technologies more effectively.[Method/process] This paper presented an outlier patent identification and emerging technology prediction method based on deep learning. Firstly, the Bert pre-trained model was used to construct the similarity network based on texts of patents and outlier patents identification. The relationship model between outlier patent indicators and technical influence was then built based on DNN model, thus realizing the fast and accurate emerging technology prediction using large-scale outlier patents. Finally, an empirical analysis was conducted in the field of numerical control system with all patents applied in the last ten years obtained from DI database.[Result/conclusion] The result of empirical analysis in the field of numerical control system not only verifies the validity of the model, but also has important guiding significance to the formulation of national technology development policy and the technology layout of enterprises in related fields.
|
| [4] |
乔治·戴, 保罗·休梅克. 沃顿论新兴技术管理[M].石莹,等,译. 北京: 华夏出版社, 2002.
|
| [5] |
赵振元, 银路, 成红. 新兴技术对传统管理的挑战和特殊市场开拓的思路[J]. 中国软科学, 2004 (7): 72-77.
|
| [6] |
王凌燕, 方曙, 季培培. 利用专利文献识别新兴技术主题的技术框架研究[J]. 图书情报工作, 2011, 55 (18): 74-78+23.
解析新兴技术主题的概念，同时结合专利文献的特点，利用专利文献提出识别新兴技术主题的初步技术框架，并以工业生物技术领域的专利文献为数据来源，采用文本聚类技术、共词战略坐标分析、共词网络分析、专利分析等方法对该技术领域的新兴技术主题进行实证分析。
This paper investigates the concept of emerging technology topics. With the characteristics of patent documents, the paper proposes the technology framework of detecting emerging technology topics. Taking industrial biology patent documents as data source, integrating the methods of text cluster, strategic diagram analysis, word cooccurrence network analysis etc, it completes the tasks of emerging technology topics identification.
|
| [7] |
徐建国, 李孟军, 游翰霖. 新兴技术识别研究进展[J]. 情报杂志, 2018, 37 (12): 8-12+7.
|
| [8] |
周萌, 朱相丽. 新兴技术概念辨析及其识别方法研究进展[J]. 情报理论与实践, 2019, 42 (10): 162-169.
［目的/意义］新兴技术识别是国家和企业进行科技创新的主要活动。对新兴技术识别的各类方法进行总结对比，以期为研究人员进行新兴技术的识别与预测提供参考性建议。［方法/过程］通过对新兴技术与前沿技术、颠覆性技术等概念进行辨析，明晰新兴技术的内涵与特征。总结各类新兴技术识别方法的优缺点，并从分析深度和分析结果的表现形式两个维度对各方法进行梳理比较，发现现有识别方法的局限性并提出改进建议。［结果/结论］从概念来看，新兴技术的本质特征在于内容上的根本创新性和对未来发展产生实际影响的不确定性；从识别方法来看，不同方法均有其适用场景。未来研究需要从微观层面深入对新兴技术概念和特征的认知，以便更准确地对新兴技术进行识别；另外还需要不断优化改进现有方法以提高识别过程中的客观性和准确性。
|
| [9] |
曹艺文, 许海云, 武华维, 等. 基于引文曲线拟合的新兴技术主题的突破性预测:以干细胞领域为例[J]. 图书情报工作, 2020, 64 (5): 100-113.
[目的/意义] 通过对新兴技术主题的引文曲线进行拟合分析，提炼和归纳引文曲线的主要类型和特征，以期能为微观层面突破性创新主题预测方法的研究提供参考。[方法/过程] 首先提出利用引文曲线追踪感知新兴技术主题形成突破性创新的假设，并提出跃迁指数的概念和计量方法，从知识跃迁和持续增长两个维度总结识别突破性创新的标准并构建突破性识别的方法模型。其次利用新兴技术主题发文的时序被引数据构建引文曲线并进行拟合分析，实现对不同主题包含的引文曲线的类型分类，提炼引文曲线的主要特征进行突破性预测。[结果/结论] 新兴技术主题引文曲线的特征包括：近期持续增长；近期持续下降；生命周期短；相近年份变化趋势一致。根据突破性创新的识别标准，如果引文曲线跃迁次数多、跃迁幅度大，最高被引峰值出现时间较晚，并且在近期保持高被引且持续稳定或快速增长，则新兴技术主题具有成为突破性创新的潜力。结合领域专家对预测结果的评估以及不同新兴技术主题的研究进展，验证了利用引文曲线可以有效预测新兴技术主题的突破性。
<strong>[Purpose/significance]</strong> Through the fitting analysis of the citation curves of emerging technology topics, this paper refined and summarized the main types and characteristics of the citation curves, in order to provide a useful reference for the study of prediction methods for radical innovation topics at the micro level.<strong>[Method/process]</strong> Firstly, the hypothesis of using citation curves to trace the emerging technology topics to produce radical innovation was proposed and the concept and measurement method of the transition index were proposed. The criteria of predicting radical innovation were summarized and the method model of radical innovation identification was constructed from the two dimensions of knowledge transition and continuous growth. Then used the time slices cited data of each emerging technology topic to construct the citation curves, classify and summarize the types and characteristics of citation curves of different emerging technology topics.<strong>[Result/conclusion]</strong> The citation curves of emerging technology topics includes four types:continuous growth in the near future; continuous decline in the near future; short life cycle; consistent trends in similar years. According to the identification criteria of radical innovation, the citation curves have the potential to become radical innovation if they have many transitions and a large transition range, and the highest citation peak occurs later, and maintains a high citation rate in the near future with a sustained stable or rapid growth. Combined with the assessment of the prediction results by domain experts and the research progress of different emerging technology topics, it is verified that the citation curve fitting analysis can effectively predict the breakthrough of emerging technology topics.
|
| [10] |
杨思洛, 江曼. 新兴技术内涵特征和识别方法研究进展[J]. 情报科学, 2023, 41 (5): 181-190.
|
| [11] |
|
| [12] |
|
| [13] |
李昌, 杨中楷, 董坤. 基于多维属性动态变化特征的新兴技术识别研究[J]. 情报学报, 2022, 41 (5): 463-474.
|
| [14] |
魏国平. 新兴技术管理策略研究[D]. 杭州: 浙江大学, 2006.
|
| [15] |
|
| [16] |
曹兴, 朱晶莹, 杨春白雪. 新兴技术创新网络“液态化”机理及实证分析[J]. 科研管理, 2022, 43 (2): 55-64.
|
| [17] |
|
| [18] |
With the strategic importance of discerning opportunities and threats from technological development to achieve sustainable competitiveness, exploring technological trends becomes critical for a successful technology strategy in logistics. Given the rapid pace of development and varying technological options, logistics also increasingly requires methodological support and appropriate data to reduce the complexity and burden of exploring technology trends. While previous research has largely relied on experts’ insights, the value of patent-based approaches for exploring technological trends has been underestimated in logistics. To address this gap, this study proposes a topic modeling-based approach using logistics-related patents registered at the United States Patents and Trademark Office (USPTO). The core of the suggested approach is latent Dirichlet allocation (LDA), allowing the identification of logistics-related technological topics behind patents. The topics identified by LDA are further investigated regarding both filed-level and firm-level trends. The suggested approach is expected to offer implications of the use of patents for the purpose of exploring the trends of technology development outside the organization in logistics. In addition, we believe that the information on the technological topics and their trends generated by the suggested approach can offer an enhanced understanding of the technological landscape in logistics.
|
| [19] |
奉国和, 武佳佳, 莫幸清. 多测度的突发词探测及验证研究[J]. 图书情报工作, 2020, 64(11):67-76.
[目的/意义] 为有效探测科技文献中潜在的研究热点，研究文献中关键词突发的特征条件，构建突发词识别模型对促进科研人员精确把握研究方向具有重要意义。[方法/过程] 获取各年度内关键词及词频，构建关键词-年度矩阵，将分析时间段划分为标准窗口、观察窗口和表现窗口，在观察窗口内利用多测度突发词探测模型识别具有突发特征的关键词；在表现窗口内利用LDA挖掘主题词汇作为热点词集合。设计突发词覆盖率指标，辅助滑动时间窗口法，计算不同时间窗口内突发词集合和热点词集合的覆盖率，验证模型识别准确性。[结果/结论] 3次滑动时间窗口，计算得到3次突发词覆盖率都在70%以上；与Citespace突发词的对照试验中，本模型3次覆盖率均大于前者，表明设计的突发词探测模型性能良好。
<strong>[Purpose/significance]</strong> In order to effectively detect potential research hotspots in scientific and technological literature, to study the characteristic conditions of keyword emergencies in the literature, and to construct a model of burst word recognition is of great significance to promote scientific researchers to accurately grasp the research direction. <strong>[Method/process]</strong> This paper got keywords and word frequency in each year, constructed keyword-year matrix, divided the analysis period into standard window, observation window and performance window, used multi-measure burst word detection model to identify keywords with burst characteristics in the observation window, and used LDA to mine topic words as hot words set in the performance window. The coverage index of burst words was designed, and the sliding time window method was used to calculate the coverage of burst words and hot words in different time windows to verify the accuracy of model recognition. <strong>[Result/conclusion]</strong> The three sliding time windows calculated that the coverage of the three sudden words is more than 70%. In the control test with Citespace, the coverage of the model three times is greater than the former, indicating that the designed burst word detection model performs well.
|
| [20] |
宋欣娜, 郭颖, 席笑文. 基于专利文献的多指标新兴技术识别研究[J]. 情报杂志, 2020, 39 (6): 76-81+88.
|
| [21] |
奉国和, 孔泳欣. 基于时间加权关键词词频分析的学科热点研究[J]. 情报学报, 2020, 39(1):100-110.
|
| [22] |
This article puts forth a new indicator of emerging technological topics as a tool for addressing challenges inherent in the evaluation of interdisciplinary research. We present this indicator and test its relationship with interdisciplinary and atypical research combinations. We perform this test by using metadata of scientific publications in three domains with different interdisciplinarity challenges: Nano-Enabled Drug Delivery, Synthetic Biology, and Autonomous Vehicles. Our analysis supports the connection between technological emergence and interdisciplinarity and atypicality in knowledge combinations. We further find that the contributions of interdisciplinary and atypical knowledge combinations to addressing emerging technological topics increase or stay constant over time. Implications for policymakers and contributions to the literature on interdisciplinarity and evaluation are provided.
|
| [23] |
|
| [24] |
|
| [25] |
吕鲲, 项旻昊, 邱佳烨. 颠覆性技术的价值评价体系构建及实证研究:基于AHP和熵权法[J]. 中国科技论坛, 2023(2): 30-38.
|
| [26] |
杨超, 朱东华, 汪雪锋, 等. 专利技术主题分析:基于SAO结构的LDA主题模型方法[J]. 图书情报工作, 2017, 61 (3): 86-96.
[目的/意义]改善现有专利技术主题分析方法主题辨识度低、主题词二义性、无法识别技术信息中的"问题"与相应"解决方案"等问题。[方法/过程]本文通过抽取专利文本中的SAO结构，并从SAO结构中识别"问题和解决方案"（P&S）模式，基于"bag of P&S"假设，构建基于"主语-行为-宾语"（subject-action-object，SAO）结构的LDA主题模型，实现对专利文献主题结构的识别和分析。[结果/结论]案例研究表明，该方法能够有效识别主题分布，并在主题辨识度和语义消岐方面较传统LDA模型具有较大优势。
[Purpose/significance] There are three problems we have to fix in performing technical topic analysis:difficult to classify topic; homonyms of words and terms; difficult to identify technical problem and solution. [Method/process] In this paper, we first extract SAO structures from patents, and then we explore and identify the problem & solution patterns embodied in SAO structures. At last, SAO-Based LDA model is built based on the "bag of P&S" assumption and it performs technical topic analysis at concept level. [Result/conclusion] The case study shows that the proposed method can effectively identify topics' distribution, and has great advantages in topic identification and word disambiguation compared with traditional LDA model. |
| [27] |
郝张红, 陈剑. 机器人在三缸曲轴打磨工艺中的应用研究[J]. 机床与液压, 2020, 48(21): 17-20,25.
为了对三缸曲轴进行自动、快速、精确的打磨，设计了一套采用多台机器人协作的打磨单元。对三缸曲轴铸件及其披缝的外形特征进行分析，在此基础上，设计了磨具形式、机器人应用方式和曲轴装夹方式，并进行了详细介绍。在打磨过程控制方面，提出了利用磨削电主轴的电流实时控制机器人的打磨进给速度的方法，提高了系统的安全性。此系统已投入使用，实现了对三缸曲轴安全、可靠、精确、高效的自动打磨。
|
| [28] |
丁杨, 张明路, 焦鑫, 等. 关节电机驱动六足机器人仿生结构设计与柔顺运动控制[J]. 工程设计学报, 2023, 30 (2):154-163.
现有六足机器人在单足结构设计、机体布置形式及柔顺运动控制等方面存在不足,导致其地形适应能力不强,运动柔顺性能不高。为此,开展了典型六足生物——蚂蚁的观测实验,基于蚂蚁生理结构特征和驱动方式分析,提出了适用于六足机器人结构设计的基本原则;基于低惯量单足结构设计,通过优化机器人机体布局,提出了关节电机驱动六足机器人整体仿生结构;基于六足机器人直行和转向运动步态,规划了三角函数曲线与直线相结合的足端轨迹,提出了基于分级控制的六足机器人柔顺运动控制方法。样机实验结果表明,六足机器人结构设计合理,能够实现相对柔顺的直行和转向运动。研究结果可以为机器人仿生结构设计及柔顺运动控制提供重要参考。
The existing hexapod robots have shortcomings in single foot structure design, body layout and compliant motion control, resulting in weak terrain adaptability and low motion compliant performance. Therefore, observation experiment was conducted on a typical hexapod organism-ant.Based on the analysis of the physiological structure characteristic and driving mode of ant, basic principles applicable to the structure design of hexapod robot were proposed; based on the design of a low inertia single foot structure, an overall biomimetic structure of a hexapod robot driven by joint motors was proposed by optimizing the body layout of the robot; based on the gait of the straight and turning movements of the hexapod robot, a foot end trajectory combining trigonometric function curve and straight line was planned, and a compliant motion control method for the hexapod robot based on hierarchical control was proposed. The prototype experimental results showed that the hexapod robot had a reasonable structure design and could achieve relatively compliant straight and turning movements. The research results can provide important references for the design of robot biomimetic structure and compliant motion control.
|
| [29] |
黄云. 砂带磨削技术的研究现状和发展方向简介[J]. 金刚石与磨料磨具工程, 2020, 40 (3): 1-4.
|
| [30] |
杨思明, 单征, 丁煜, 等. 深度强化学习研究综述[J]. 计算机工程, 2021, 47(12): 19-29.
深度强化学习是指利用深度神经网络的特征表示能力对强化学习的状态、动作、价值等函数进行拟合，以提升强化学习模型性能，广泛应用于电子游戏、机械控制、推荐系统、金融投资等领域。回顾深度强化学习方法的主要发展历程，根据当前研究目标对深度强化学习方法进行分类，分析与讨论高维状态动作空间任务上的算法收敛、复杂应用场景下的算法样本效率提高、奖励函数稀疏或无明确定义情况下的算法探索以及多任务场景下的算法泛化性能增强问题，总结与归纳4类深度强化学习方法的研究现状，同时针对深度强化学习技术的未来发展方向进行展望。
Deep Reinforcement Learning(DRL) refers to using feature representation capabilities of deep neural networks to fit Reinforcement Learning(RL) functions, including the state, action, and value, so the performance of RL models can be improved.It has been widely used in video games, mechanical control, recommendation system, financial investment and other fields.This article reviews the development history of DRL methods, and categorizes them based on the existing research goals.Then the article analyzes the algorithm convergence problem in high-dimensional state action space tasks, problem of improving sampling efficiency of the algorithms in the complex application scenarios, the algorithm exploration problem in the complex scenarios where the reward functions are sparse or inexplicitly defined, and the problem of enhancing the generalization ability of the algorithm in the multitasking scenarios.Finally, the article summarizes the current development of the four kinds of DRL methods, and discusses the future development trends of DRL technology.
|
| [31] |
郭娟. 工业机器人示教器体验优化设计系统研究[J]. 造纸装备及材料, 2023, 52 (7): 42-44.
|
| [32] |
高攀, 邹胤, 汤超, 等. 虚实结合的工业机器人实训教学平台和方法[J]. 机电工程技术, 2022, 51 (9):116-121.
|
| [33] |
陆先亮, 徐明华, 江一山, 等. 基于“新工科”的人才培养实验平台建设研究[J]. 实验技术与管理, 2019, 36 (7): 12-14,19.
|
| [34] |
田辉, 贺硕, 林尚静, 等. 工业互联网感知通信控制协同融合技术研究综述[J]. 通信学报, 2021, 42 (10): 211-221.
感知通信控制的协同融合是工业互联网发展的必然趋势，梳理工业互联网感知通信控制协同融合技术的研究现状与挑战对推动工业互联网发展具有重要意义。首先，介绍了工业互联网中感知-通信-控制三要素间的复杂耦合关系。然后，综述了国内外关于工业互联网感知通信控制协同融合技术的研究现状和面临的问题。最后，围绕工业互联网中感知通信控制协同融合问题对未来的研究方向进行了总结和展望。
The cooperative fusion with perception, communication and control is the inevitable trend of industrial Internet.Sorting out the research development and challenges of the cooperative fusion technologies with perception, communication and control in industrial Internet is of great significance to promote the development of industrial Internet.Firstly, the complicated coupling relationship among perception, communication and control in industrial Internet was introduced.Then, the related works and open problems of the cooperative fusion technologies with perception, communication and control were summarized.Finally, the future research directions were summarized and prospected for the problems of the cooperative fusion technologies with perception, communication and control in industrial Internet. |
| [35] |
|
| [36] |
陈永平, 王凯凯. 基于ABB机器人的双追踪传送包装系统设计[J]. 包装工程, 2020, 41(1):116-122.
|
| [37] |
万燕英, 伍祁林. 工业机器人安全防护技术综述[J]. 机电工程技术, 2021, 50 (9):121-123+173.
|
| [38] |
奉国和, 刘任铧, 邓伟伟. 高价值专利影响因素分析及主题挖掘:以纳米药物领域为例[J]. 图书馆论坛, 2024, 44(7):48-60.
|
/
| 〈 |
|
〉 |
