双源数据驱动下基于“问题-建议”的产品创新机会识别

doi:10.13998/j.cnki.issn1002-1248.25-0663

Abstract

Abstract:

[Purpose/Significance] As the user base grows, the number of online comments is increasing rapidly. The massive volume of comments has broadened the innovative thinking of enterprises and provided more diverse innovative options, but it has also brought about the problem of information overload. Therefore, in the face of the massive amount of online user comments, how to use efficient and precise methods to mine information with practical value, effectively integrate valuable information and identify product innovation opportunities, and transform it into high-quality resources for enterprise product innovation has become a hot topic of great concern in both academic and industrial circles. Against this backdrop, studying how to identify product innovation opportunities based on online reviews is of great theoretical significance and practical value. Unlike previous studies, this paper uses the BERT model to accurately filter out negative user comments and identify key demand points. This article also combines the characteristics of ordinary users and leading users, integrates dual-source data of user comments from e-commerce platforms and online communities, and associates the demand issues of ordinary users with the suggestions of leading users, which can more accurately identify product innovation opportunities. [Method/Process] First, we collected and pre-processed ordinary user comment data and leading user comment data. Second, the BERT model and LDA topic model were used to categorize the sentiment and cluster the comment data to mine the problems of ordinary users and suggestions of leading users. Finally, based on semantic similarity analysis, problem-suggestion topic mapping was realized to identify product innovation opportunities with high innovation value. [Results/Conclusions] This paper constructed a problem-suggestion product innovation opportunity identification method driven by dual-source data, and selected the action camera as a case to elaborate in detail on the specific practice of the proposed method in the field of product innovation. Through case analysis, the feasibility of the proposed method of product innovation was verified, providing an operational reference basis for enterprises on how to efficiently recommend product innovation work. However, this paper still has certain limitations and needs to be improved with more abundant data in subsequent studies. First, the data collected in this article mainly come from e-commerce platforms and online community platforms. Although this data contain a large amount of user information, there are still deficiencies. In the future, we will introduce more data sources, such as news media and technology websites to obtain more comprehensive and diverse data. Second, this paper has only conducted case application research in the field of intelligent digital products. In the future, we need to further explore more fields, such as smart wearables and whole-house intelligence, to enhance the universality of the product innovation opportunity identification framework constructed in this paper.

Key words: dual-source data, natural language processing, Bert model, lDA topic model, product innovation opportunity identification

CLC Number:

F273.2

GUO Yanli, GAO Rui, ZOU Meifeng, LIU Zidan. Identification of Product Innovation Opportunity Based on Problem and Suggestions Using Dual-Source Data[J].Journal of library and information science in agriculture, 2026, (): 1-14.

Figures/Tables 22

Table 1

Fig.1

Table 2

Multi-dimensional technological innovation map"

创新维度	创新法则1	创新法则2	…	创新法则9
创新维度1	↓
……	→ $N = V i ※ F i$
创新维度9

Table 2

Table 3

Table 4

Fig.2

Fig.3

Fig.4

Table 5

Table 6

Fig.5

Fig.6

Fig.7

Table 7

Fig.8

Fig.9

Fig.10

Table 8

Table 9

Table 10

Fig.11

Table 11

References 39

[1]	李秀霞, 邵作运. 基于离群主题词跨学科组合的学术创新机会发现研究[J]. 情报理论与实践, 2023, 46(12): 122-130.
	Li Xiuxia, Shao Zuoyun. Research on the discovery of academic innovation opportunity based on the interdisciplinary combination of outlier topic words[J]. Information Studies: Theory & Application, 2023, 46(12): 122-130.
[2]	Lee H, Choi K, Yoo D, et al. Recommending valuable ideas in an open innovation community: A text mining approach to information overload problem[J]. Industrial Management & Data Systems, 2018, 118(4): 683-699.
[3]	Olsson O. Technological opportunity and growth[J]. Journal of Economic Growth, 2005, 10(1): 31-53.
[4]	dos Santos e Silva D F, Bomtempo J V, Alves F C. Innovation opportunities in the Brazilian sugar-energy sector[J]. Journal of Cleaner Production, 2019, 218: 871-879.
[5]	Sheu D D, Lee H K. A proposed process for systematic innovation[J]. International Journal of Production Research, 2011, 49(3): 847-868.
[6]	Jeong B, Yoon J, Lee J M. Social media mining for product planning: A product opportunity mining approach based on topic modeling and sentiment analysis[J]. International Journal of Information Management, 2019, 48: 280-290.
[7]	王克勤, 刘朝明. 基于在线评论的重要度绩效竞争对手分析的产品设计改进方法[J]. 计算机集成制造系统, 2022, 28(5): 1496-1506.
	Wang Keqin, Liu Zhaoming. Product design improvement based on importance performance competitor analysis of online reviews[J]. Computer Integrated Manufacturing Systems, 2022, 28(5): 1496-1506.
[8]	张硕, 李荣荣, 乔亚丽. 技术组合进化视角下的产品创新机会识别研究[J]. 情报理论与实践, 2024, 47(12): 133-142.
	Zhang Shuo, Li Rongrong, Qiao Yali. Research on identifying product innovation opportunities from the perspective of technology portfolio evolution[J]. Information Studies: Theory & Application, 2024, 47(12): 133-142.
[9]	Lee C, Jeon D, Ahn J M, et al. Navigating a product landscape for technology opportunity analysis: A word2vec approach using an integrated patent-product database[J]. Technovation, 2020, 96/97: 102140.
[10]	刘鹏, 闫煜析, 冯立杰, 等. 用户需求导向下基于三级技术功效矩阵的产品创新机会识别[J]. 情报理论与实践, 2023, 46(8): 138-146.
	Liu Peng, Yan Yuxi, Feng Lijie, et al. Product innovation opportunity identification based on three-level technology-effect matrix under user demand orientation[J]. Information Studies: Theory & Application, 2023, 46(8): 138-146.
[11]	吴红, 张彪, 高道斌, 等. 产品改进需求引导的技术机会发现研究[J]. 情报理论与实践, 2023, 46(2): 156-164, 209.
	Wu Hong, Zhang Biao, Gao Daobin, et al. Research on technology opportunity discovery guided by product improvement requirement[J]. Information Studies: Theory & Application, 2023, 46(2): 156-164, 209.
[12]	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): 213-225.
	Xie Yaoyao, Deng Sanhong, Wang Hao, et al. Matching user needs and patent technology based on SAO semantic mining[J]. Data Analysis and Knowledge Discovery, 2024, 8(8): 213-225.
[13]	王金凤, 王正起, 张珂, 等. 多源数据驱动下基于涌现分析的产品创新机会识别[J]. 情报杂志, 2025, 44(3): 160-169.
	Wang Jinfeng, Wang Zhengqi, Zhang Ke, et al. Identification of product innovation opportunities based on emergence analysis driven by multi-source data[J]. Journal of Intelligence, 2025, 44(3): 160-169.
[14]	Kausar S, Xu H H, Ahmad W, et al. A sentiment polarity categorization technique for online product reviews[J]. IEEE Access, 2020, 8: 3594-3605.
[15]	Zhang W, Kong S X, Zhu Y C, et al. Sentiment classification and computing for online reviews by a hybrid SVM and LSA based approach[J]. Cluster Computing, 2019, 22(5): 12619-12632.
[16]	Su Y, Shen Y. A deep learning-based sentiment classification model for real online consumption[J]. Frontiers in Psychology, 2022, 13: 886982.
[17]	Awajan A. Keyword extraction from Arabic documents using term equivalence classes[J]. ACM Transactions on Asian and Low-Resource Language Information Processing, 2015, 14(2): 1-18.
[18]	孟园, 王洪伟. 中文评论产品特征与观点抽取方法研究[J]. 现代图书情报技术, 2016(2): 16-24.
	Meng Yuan, Wang Hongwei. Extracting product feature and user opinion from Chinese reviews[J]. New Technology of Library and Information Service, 2016(2): 16-24.
[19]	黄冬玲, 刘源, 袁小帅, 等. 基于自然语言处理技术的中国氢能政策数据挖掘研究[J]. 中国科学院院刊, 2024, 39(6): 1032-1046.
	Huang Dongling, Liu Yuan, Yuan Xiaoshuai, et al. Study on data mining of hydrogen energy policy in China based on natural language processing technology[J]. Bulletin of Chinese Academy of Sciences, 2024, 39(6): 1032-1046.
[20]	胡吉明, 郑翔, 程齐凯, 等. 基于BiLSTM-CRF的政府微博舆论观点抽取与焦点呈现[J]. 情报理论与实践, 2021, 44(1): 174-179, 137.
	Hu Jiming, Zheng Xiang, Cheng Qikai, et al. Public opinion extraction and focus presentation in government microblog based on BiLSTM-CRF[J]. Information Studies (Theory & Application), 2021, 44(1): 174-179, 137.
[21]	马翔, 肖狄虎. 大数据时代面向终端用户的信息可视化分类[J]. 设计, 2015, 28(5): 57-59.
	Ma Xiang, Xiao Dihu. End user oriented classification of information visualization in the big data era[J]. Design, 2015, 28(5): 57-59.
[22]	罗婷予, 谢康. 用户画像促进企业与用户互动创新的机制及构建方法[J]. 财经问题研究, 2023(3): 106-116.
	Luo Tingyu, Xie Kang. User profile in enterprise-user interaction innovation: Mechanism and construction method[J]. Research on Financial and Economic Issues, 2023(3): 106-116.
[23]	徐一钊, 闫宏斌, 马铁驹. 竞争性环境下在线评论驱动的新产品开发: 基于QFD的视角[J]. 系统工程, 2022, 40(5): 54-69.
	Xu Yizhao, Yan Hongbin, Ma Tieju. Online review-driven new product development under competitive environments: A QFD perspective[J]. Systems Engineering, 2022, 40(5): 54-69.
[24]	Zhang L, Chu X N, Xue D Y. Identification of the to-be-improved product features based on online reviews for product redesign[J]. International Journal of Production Research, 2019, 57(8): 2464-2479.
[25]	武红玉, 邹波. 中小企业如何实现突破式创新: 领先用户与再创能力的作用机理[J]. 经济与管理, 2024, 38(5): 69-76.
	Wu Hongyu, Zou Bo. How small and medium-sized enterprises achieve radical innovation: Mechanism research of leading users and generative capability[J]. Economy and Management, 2024, 38(5): 69-76.
[26]	沈占波, 王蒙, 刘建泽. 开放式创新社区不同用户群体知识共享角色与协同作用研究——基于小米社区的扎根探索[J]. 现代情报, 2024, 44(5): 32-44.
	Shen Zhanbo, Wang Ming, Liu Jianze. Research on knowledge sharing roles and synergies of different user groups in open innovation community - Grounded Theory Exploration Based on Xiaomi Community[J]. Journal of modern information, 2024, 44(5): 32-44.
[27]	谢赣红, 陆思豪. 开放式创新社区领先用户识别方法研究[J]. 中阿科技论坛(中英文), 2023(8): 22-27.
	Xie Ganhong, Lu Sihao. Research on identification methods of lead users in open innovation community[J]. China-Arab States Science and Technology Forum, 2023(8): 22-27.
[28]	王莉, 李沁芳, 马云龙. 基于改进网络志方法的开放式创新社区中领先用户识别研究[J]. 科研管理, 2019, 40(10): 259-267.
	Wang Li, Li Qinfang, Ma Yunlong. Identifying lead users in open innovation community based on extended netnography[J]. Science Research Management, 2019, 40(10): 259-267.
[29]	Tuarob S, Tucker C S. Automated discovery of lead users and latent product features by mining large scale social media networks[J]. Journal of Mechanical Design, 2015, 137(7): 071402.
[30]	何伟林, 谢红玲, 奉国和. 潜在狄利克雷分布模型研究综述[J]. 信息资源管理学报, 2018, 8(1): 55-64.
	He Weilin, Xie Hongling, Feng Guohe. Review on latent dirichlet allocation model[J]. Journal of Information Resources Management, 2018, 8(1): 55-64.
[31]	冉从敬, 程凡, 李旺. 战略性新兴产业政策与技术主题演化路径识别分析——以新能源汽车产业为例[J]. 情报科学, 2025, 43(1): 147-160.
	Ran Congjing, Cheng Fan, Li Wang. Theme evolution path identification and analysis of strategic emerging industry policies and technology: The case of the new energy vehicle industry[J]. Information Science, 2025, 43(1): 147-160.
[32]	张涛, 马海群. 中国人工智能政策主题热点及演进分析[J]. 现代情报, 2021, 41(11): 150-160.
	Zhang Tao, Ma Haiqun. Hot topics and evolution analysis of China's artificial intelligence policy[J]. Journal of Modern Information, 2021, 41(11): 150-160.
[33]	聂方超, 周锋, 周洋, 等. 基于文本挖掘和社会网络分析的煤矿事故原因分析[J]. 中国安全生产科学技术, 2025, 21(S1): 58-64.
	Nie Fangchao, Zhou Feng, Zhou Yang, et al. Cause analysis of coal mine accidents based on text mining and social network analysis[J]. Journal of Safety Science and Technology, 2025, 21(S1): 58-64.
[34]	党昭洋, 孙晓永, 郭润泽, 等. 融合多视角投影与时空拓扑的多无人机多目标跟踪方法[J/OL]. 仪器仪表学报, 1-14[2025-11-02]. .
	DANG Saoyang, SUN Xiaoyong, GUO Runze, et al. Multi-object tracking for multi-drone systems integrating multi-view projection and spatiotemporal topology[J/OL]. Chinese Journal of Scientific Instrument, 1-14[2025-11-02]. .
[35]	岳俊举, 冯立杰, 冯奕程, 等. 基于多维技术创新地图与关联规则挖掘的技术机会识别方法研究[J]. 情报学报, 2017, 36(8): 798-808.
	Yue Junju, Feng Lijie, Feng Yicheng, et al. Study of technology opportunity discovery methods based on a multidimensional map of technology innovation and association rules mining[J]. Journal of the China Society for Scientific and Technical Information, 2017, 36(8): 798-808.
[36]	冯立杰. 元易创新方法——技术创新的九维九法[M]. 重庆: 重庆大学出版社, 2020: 302.
	Feng Lijie. Yuan Yi innovation method - Nine dimensions and nine methods of technological innovation[M]. Chongqing: Chongqing University Press, 2020: 302.
[37]	冯立杰, 吴敏, 王金凤, 等. 面向低端市场颠覆式创新的技术机会识别路径研究[J]. 软科学, 2019, 33(4): 91-98.
	Feng Lijie, Wu Min, Wang Jinfeng, et al. Research on the path of technology opportunity identification under the low-end market disruptive innovation[J]. Soft Science, 2019, 33(4): 91-98.
[38]	王金凤, 仵轩, 冯立杰, 等. 用户偏好-制造商偏好双重视阈下的产品创新机会识别路径研究[J]. 计算机集成制造系统, 2024, 30(4): 1433-1445.
	Wang Jinfeng, Wu Xuan, Feng Lijie, et al. Product innovation opportunity identification path under dual perspective of user preference and manufacturer preference[J]. Computer Integrated Manufacturing Systems, 2024, 30(4): 1433-1445.
[39]	周艳杰, 李耀辉, 王宇, 等. 情感分析与数据驱动下面向产品迭代设计的用户画像及建模研究[J]. 工业工程, 2024, 27(2): 74-86.
	Zhou Yanjie, Li Yaohui, Wang Yu, et al. User profiles and modeling for iterative product designing with sentiment analysis and data-driven approaches[J]. Industrial Engineering Journal, 2024, 27(2): 74-86.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

文本挖掘技术分类		参考文献	研究内容
情感分析技术	基于词典	[14]	基于SentiWordNet情感词典，考虑5类情感类别和3种极性特征，构建情感极性分类模型
	基于机器学习	[15]	将LSA与SVM算法相结合对在线评论进行多粒度情感分析
	基于深度学习	[16]	构建CA-LSTM深度学习模型，识别消费者在线评论中的情感倾向
主题挖掘技术	基于频率	[17]	利用空间向量模型抓取文本中最频繁的词语实现关键词抽取
	基于语义	[18]	利用特征词和观点词的关联关系和语义关系，抽取并识别产品特征观点
	基于机器学习	[19]	应用LDA主题模型对氢能政策文件进行主题词挖掘，获取氢能政策文件的核心主题
	基于深度学习	[20]	构建POF-BiLSTM-CRF深度学习模型，对微博评论进行观点的抽取和焦点呈现

数据	数据来源	数量/条	预处理后数量/条	收集时间范围
普通用户评论数据	京东	9 706	6 113	2024.09—2025.02
普通用户评论数据	淘宝	9 945	6 538	2024.09—2025.02
领先用户评论数据	大疆社区	3 546	2 402	2024.09—2025.02
领先用户评论数据	影石社区	2 472	1 601	2024.09—2025.02

原句	清洗后评论内容	分词后评论内容	停用词停用后评论内容
外觀漂亮，待機時間短，發熱非常嚴重	外观漂亮，待机时间短，发热非常严重	外观/漂亮/，/待机/时间/短/，/发热/非常/严重	外观/漂亮/待机/时间/短/发热
比较一般，实用意义并不大。主要原因在于电池。你设想的很多应用场景电量其实无法维持	比较一般，实用意义并不大。主要原因在于电池。你设想的很多应用场景电量其实无法维持	比较/一般/，/实用/意义/并不大/。/主要/原因/在于/电池/。/你/设想/的/很多/应用/场景/电量/其实/无法/维持	实用/意义/并不大/原因/电池/设想/场景/电量

情感倾向编号	情感类别	例子
0	积极	值得称赞的国货精品，小摄像头可以离开机身，能续航30分钟，非常值得运动玩家拥有，能够与佳明设备数据匹配，挂绳磁吸非常稳固
1	中立	马马虎虎，就是不太会调参数
2	消极	画质令人失望，发热严重，不是死机就是存储卡错误，真是服了

主题编号	主题命名	关键词	问题描述
PTopic1	稳定性	效果、性能、防水、防抖、稳定	相机稳定性差，画面抖动严重
PTopic2	性价比	质量、性价比、价格、做工、贵	产品价格偏高
PTopic3	拍摄画质	画质、色彩、清晰、夜景、拍摄	噪点过多、画面模糊、色彩失真
PTopic4	使用场景	记录、旅游、运动、日常、学习	遇到极端天气、高速运动中的画面模糊等问题
PTopic5	操作难易便携性	小巧、操作、简单、便携、轻便	高级设置埋藏过深，新手需频繁查阅说明书
PTopic6	电池续航	充电、续航、发热、连接、够用	电池续航差，长时间拍摄设备发烫严重
PTopic7	外观	外观、轻便、颜值、质感、脆	裸机使用易因摩擦产生划痕，影响美观；低温状态下外壳开裂
PTopic8	物流配送	京东、物流、快递、速度、送货	包装设计不合理，导致相机在包装内晃动
PTopic9	功能	功能、模式、软件、智能、兼容	语音控制在嘈杂环境下失效；跟拍模式在复杂场景中误判
PTopic10	售后服务	客服、不耐烦、解答、专业、服务态度	产品售后服务令用户不满

Identification of Product Innovation Opportunity Based on Problem and Suggestions Using Dual-Source Data

RichHTML

PDF (PC)

Abstract

Cite this article

share this article

Figures/Tables 22

References 39

Related Articles 3

Metrics

Comments

Recommended 0

主题编号	主题名称	关键词	建议解释
STopic1	外观	屏幕、机身、云台、固件、操作	材质优化、人体工学改进及配件生态完善
STopic2	设备更新	更新、固件、后期、选项、增加	固件更新透明化，强化云服务隐私保护
STopic3	拍摄效果	拍照、延时、切换、速度、效果	针对场景优化设置与配件搭配
STopic4	连接设备	电脑、蓝牙、连接、设备、稳定	提升软件兼容性
STopic5	文件导出	导出、时间、文件、分钟、慢	生成代理文件及设置自动云上传
STopic6	拍摄画质	镜头、画面、效果、拍摄、画质	综合硬件性能、软件算法及使用技巧
STopic7	电池续航	充电、续航、关机、开机、速度	关闭无关功能、降低屏幕亮度等习惯延长续航
STopic8	功能	语音、功能、控制、记录、模式	语音控制支持离线命令

普通用户问题主题编号	领先用户建议主题编号	相似度值
PTopic3	STopic3	0.855
PTopic9	STopic8	0.832
PTopic6	STopic7	0.814
PTopic7	STopic1	0.628

创新维度	具体表征	创新要素
结构维	运动相机镜头、传感器、机身等与结构相关的属性	电池、摄像头、手柄、充电接口、显示屏、主板、屏幕、外壳
功能维	运动相机镜头、机身等与功能相关的属性	图像显示、像素分辨率、使用寿命、电池寿命、防水性能、散热性能
材料维	运动相机手柄、外壳等与材料相关的属性	硬件处理器、数字信号处理器、控制芯片、显示组件、存储介质、光学传感器、光模块
动力体系维	运动相机动力源等与动力体系相关的属性	能量自给、太阳能、机械能、转化、充电

序号	创新机会描述	创新维度	创新法则	具象创新方案
1	改善夜景画质，增加多种画幅选择	结构维+功能维	组成与集合+替代	模仿蜻蜓复眼结构，在传感器表面集成微透镜阵列，每个像素点配备独立光电二极管，将进光量提升400%，ISO 409600下噪点控制达日光水平。配备“液态镜头+棱镜组”，通过电磁驱动在35mm全画幅与9:16竖屏模式间切换
2	增强运动相机拍摄性能及稳定性，提升防水、防抖性能	结构维+功能维+材料维	组成与集合+替代	在镜头模组中集成“三轴陀螺仪+加速度计”，通过微型无刷电机驱动浮动镜头组，模仿鸟类头部稳定机制，实现±5级防震补偿。外壳表面采用微结构纹理涂层，模仿鲨鱼皮肤流体动力学，同时集成疏水性纳米材料，实现“防水+自动水珠脱落”功能
3	提升运动相机续航能力，改善充电及长时间拍摄相机发热问题	结构维+材料维+动力体系维	动态化+自服务	在相机手柄集成微型压电材料与柔性太阳能薄膜，运动震动或阳光照射时可自动充电。在机身设计仿生鲨鱼鳃结构，利用运动气流被动散热

[1]	HUO Mengjia, LIU Juan, Huang Jie. Construction and Application of the Attention Analysis Model of Brand Management Policies of Agricultural Products with Geographical Indications [J]. Journal of library and information science in agriculture, 2023, 35(7): 94-104.
[2]	AN Bo. Literature Classification Methods based on Structural Information Enhancement [J]. Journal of library and information science in agriculture, 2023, 35(3): 15-24.
[3]	SHI Yunlai, CUI Yunpeng, DU Zhigang. A Classification Method of Agricultural News Text Based on BERT and Deep Active Learning [J]. Journal of library and information science in agriculture, 2022, 34(8): 19-29.