Please wait a minute...
Data Analysis and Knowledge Discovery  2022, Vol. 6 Issue (11): 126-138    DOI: 10.11925/infotech.2096-3467.2022.0078
Current Issue | Archive | Adv Search |
Comprehensive Quality Profiling for Micro-, Small-, and Medium-sized Enterprises Based on Deep Learning
Cao Lina1,Zhang Jian1,2,3,Chen Jindong1,2(),Fan Hui4
1School of Economics and Management, Beijing Information Science and Technology University, Beijing 100192, China
2Beijing International Science and Technology Cooperation Base of Intelligent Decision and Big Data Application, Beijing 100192, China
3Laboratory of Big Data Decision Making for Green Development, Beijing 100192, China
4Sino-tone Beijing Consulting Co. Ltd., Beijing 100012, China
Download: PDF (1255 KB)   HTML ( 21
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This paper develops the comprehensive quality profiling technology for the micro-, small-, and medium-sized enterprises (MSMEs) based on deep learning, aiming to more accurately depict the quality of MSMEs. [Methods] We proposed a comprehensive quality profiling system with five dimensions: quality innovation ability, process quality control, product quality level, operational quality and risks, as well as financial quality. Then, we designed a diversified profiling method based on the quality check reports and online user comments. Finally, we proposed the comprehensive quality profiling technology for MSMEs with the help of deep learning. [Results] The F value of our pre-trained BERT model was 4.66%, 1.99%, and 4.25% higher than those of the benchmark models. The review classification model based on the pre-trained Word2Vec was 6.03% higher than the traditional TF-IDF model. [Limitations] More dimensions related to enterprise quality need to be added and optimized. [Conclusions] Deep learning technology expands the dimensions and improves the accuracy of enterprise quality profiling. The proposed method also provides technical support for service innovation.

Key wordsMSMEs      Comprehensive Quality      Enterprise Profiling      Deep Learning     
Received: 26 January 2022      Published: 13 January 2023
ZTFLH:  TP391  
  F274  
Fund:National Key R&D Program of China(2019YFB1405300);National Natural Science Foundation of China(72174018);Beijing Social Science Fund(20GLA002)
Corresponding Authors: Chen Jindong     E-mail: j.chen@amss.ac.cn

Cite this article:

Cao Lina,Zhang Jian,Chen Jindong,Fan Hui. Comprehensive Quality Profiling for Micro-, Small-, and Medium-sized Enterprises Based on Deep Learning. Data Analysis and Knowledge Discovery, 2022, 6(11): 126-138.

URL:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2022.0078     OR     https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2022/V6/I11/126

The Process of the Comprehensive Quality of Micro-, Small-, and Medium-sized Enterprises
Product Quality Spot Checks Portrait Process Based on Named Entity Recognition
数据集 句子数量 标注实体数量分布
被抽检企业名称实体数量 被抽检产品名称实体数量 产品不合格项目实体数量
验证集 4 100 1 001 1 725 1 645
测试集 4 314 1 086 1 907 1 962
训练集 33 406 7 905 13 248 12 828
合计 41 820 9 992 16 880 16 435
The Number of Sentences and Labeled Entities in Each Dataset During the Training of the Model
模型 实体名称 准确率/% 召回率/% F值/%
BERT-BiLSTM-CRF 企业名称 92.47 94.01 93.23
不合格项目 93.34 88.79 91.01
产品名称 93.82 93.16 93.49
BiLSTM-CRF 企业名称 87.83 89.32 88.57
不合格项目 89.61 88.43 89.02
产品名称 89.36 89.12 89.24
Entity Recognition Results of Two Models
Product Quality Comments Portrait Process Based on Sentiment Classification Method
模型 准确率/% 召回率/% F值/%
Word2Vec-SVM 88.54 93.92 91.15
TF-IDF-SVM 83.95 86.33 85.12
Classification Model Results
一级指标 二级指标 三级指标 标签设定方法 标签输出
1. 基本信息 工商信息 注册资本 规则标签 资本实力:强(1 081)、一般(10 811)、弱(23 477)
注册年限 行业经验:丰富(4 534)、一般(15 651)、较少(15 184)
2. 质量创新能力 创新投入 创新经费投入强度 聚类分析 创新投入水平较高(37)、中等(599)、较低(34 733)
研发人力资源占比
创新产出 专利数量* 主成分分析、
聚类分析
创新产出水平较高(56)、中等(734)、较低(34 579)
人均专利占有量
发明专利占比
3.过程质量控制 质量目标 质量目标是否明确制定 事实标签 质量目标明确/不明确
采购过程控制 原材料合格率 主成分分析、
聚类分析
过程质量控制严格、过程质量控制仍有改进空间、过程质量控制松散乱
可追溯情况
生产过程控制 半成品检测合格率
半成品检验频次
关键生产工序的可控性
检验过程控制 例行检验和确认检验的规范化
不合格品的控制 不合格品管理的规范性 事实标签 不合格品管控规范/不规范
4.产品质量 商标信息 商标数量* 聚类分析 企业知名度较高(105)、一般(693)、较低(34 571)
驰名商标数量
产品或质量认证 产品许可/认证 事实标签 拥有产品质量认证或质量体系认证
产品标识认证
质量体系认证
技术认证
产品质量抽检 产品监管抽检情况* 命名实体识别模型、规则标签 无抽检纪录(35 329)、被抽检且均合格(35)、被抽检有不合格(5)
产品入库检验合格率 规则标签 符合标准/不符合标准
客户满意度 产品质量评论* 文本分类、情感判断、规则标签 产品口碑较好
产品口碑一般
产品口碑较差
顾客退货率 事实标签 实际退货率
产品售后情况 缺陷产品召回机制 事实标签 机制完善且处置合理
机制待完善
机制不合理
质量争议处置
5.企业经营质量与风险 处罚信息 行政处罚情况* 关键词提取、
规则标签
企业经营风险等级:无风险(35 084)、低风险(263)、中风险(13)、高风险(9)
税收违法情况*
环保处罚情况*
司法风险 抵质押信息* 规则标签 抵质押风险等级:无风险(35 232)、低风险(19)、中风险(62)、高风险(56)
清算信息* 清算风险:无风险(35 074)、被清算(295)
司法协助信息* 司法风险:无风险(35 185)、低风险(101)、中风险(69)、高风险(13)
劳动仲裁* 劳动仲裁风险:无风险、低风险、中风险、高风险
失信信息* 失信风险:无风险、低风险、中风险、高风险
6. 财务质量 偿债能力 流动比率 熵权法 各财务指标得分
资产负债率
营运能力 总资产周转率
盈利能力 总资产报酬率
发展能力 营业收入增长率
Image Label Setting Method, Output Label Name and Corresponding Enterprise Distribution Statistics under Each Index
Quality Portrait for ZL Food Company
[1] Feigenbaum A V. Total Quality Control[M]. The 4th Edition. New York: McGraw-Hill, 1991.
[2] Hackman J R, Wageman R. Practical Issues[J]. Administrative Science Quarterly, 1995, 40: 309-342.
doi: 10.2307/2393640
[3] Juran J M, Godfrey A B. Quality Handbook[M]. New York: Republished McGraw-Hill, 1999.
[4] 张军扩, 侯永志, 刘培林, 等. 高质量发展的目标要求和战略路径[J]. 管理世界, 2019, 35(7): 1-7.
[4] (Zhang Junkuo, Hou Yongzhi, Liu Peilin, et al. The Goals and Strategy Path of High-Quality Development[J]. Management World, 2019, 35(7): 1-7.)
[5] 张培丽. 中小企业高质量发展的困境与出路探析[J]. 中国特色社会主义研究, 2019, 10(5): 25-31.
[5] (Zhang Peili. The Dilemma of Small and Medium-Sized Enterprises under the Background of High-Quality Development and Its Solutions[J]. Studies on Socialism with Chinese Characteristics, 2019, 10(5): 25-31.)
[6] 周平军. 推进中小企业服务体系建设的战略思考与路径选择[J]. 宏观经济管理, 2017(7): 66-72.
[6] (Zhou Pingjun. Strategic Thinking and Route Selection of Promoting Service System Construction of Small and Medium-sized Enterprises[J]. Macroeconomic Management, 2017(7): 66-72.)
[7] 胡乐炜, 赵晶, 江毅. 基于互联网平台的服务型企业知识共享能力形成及作用过程研究——权变理论视角[J]. 管理评论, 2018, 30(10): 95-105.
[7] (Hu Yuewei, Zhao Jing, Jiang Yi. Research on the Formation and Effects of Knowledge Sharing Capability of Service Firms Based on Internet Platforms: A Perspective of Contingency Theory[J]. Management Review, 2018, 30(10): 95-105.)
[8] 简兆权, 刘晓彦, 李雷. 基于海尔的服务型制造企业“平台+小微企业”型组织结构案例研究[J]. 管理学报, 2017, 14(11): 1594-1602.
[8] (Jian Zhaoquan, Liu Xiaoyan, Li Lei. “Platform+Small and Micro Enterprises” Organization Structure for Service-Oriented Manufacturing Enterprises——A Case Study of Haier[J]. Chinese Journal of Management, 2017, 14(11): 1594-1602.)
[9] Xia L L, Zhang X L. Enterprises Public Service Platform of China[C]// Proceedings of the 12th Wuhan International Conference on E-Business. 2013: 664-671.
[10] 裘华东, 涂莹, 丁麒. 基于标签库系统的电力企业客户画像构建与信用评估及电费风险防控应用[J]. 电信科学, 2017, 33(S1): 206-213.
[10] (Qiu Huadong, Tu Ying, Ding Qi. Construction of Power Customer Portrait and Its Credit Evaluation and Electricity Fee Risk Control Based on Tag Library System[J]. Telecommunications Science, 2017, 33(S1): 206-213.)
[11] 楼裕胜. 公共信用信息环境下的企业信用评价研究[J]. 统计与信息论坛, 2021, 36(2): 110-118.
[11] (Lou Yusheng. Research on Evaluation System of Enterprise Credit Based on Public Credit Information Environment[J]. Journal of Statistics and Information, 2021, 36(2): 110-118.)
[12] 刘玉敏. 大数据时代质量诊断方法的变革[J]. 中国质量, 2016(8): 88-91.
[12] (Liu Yumin. The Transformation of Quality Diagnosis Methods in the Era of Big Data[J]. China Quality, 2016(8): 88-91.)
[13] Melović B, Vukčević M, Dabić M. The Midas Touch of Branding: Banks’ Brand Value, Intellectual Capital and the Optimization of the Interbrand Methodology[J]. Journal of Intellectual Capital, 2021, 22(7): 92-120.
doi: 10.1108/JIC-08-2020-0272
[14] 袁之淇, 易树平, 王钰涵, 等. 基于用户行为分析的企业ERP操作可视化及应用[J]. 工业工程与管理, 2022, 27(3): 127-138.
[14] (Yuan Zhiqi, Yi Shuping, Wang Yuhan, et al. Visualization of ERP Operation Based on User Behavior Analysis and Its Application[J]. Industrial Engineering and Management, 2022, 27(3): 127-138.)
[15] Perrini F. Building a European Portrait of Corporate Social Responsibility Reporting[J]. European Management Journal, 2005, 23(6): 611-627.
doi: 10.1016/j.emj.2005.10.008
[16] Foster L, Grim C, Zolas N. A Portrait of US Firms that Invest in R&D[J]. Economics of Innovation and New Technology, 2020, 29(1): 89-111.
doi: 10.1080/10438599.2019.1595366
[17] Zulfanetti Z, Octavia A, Erida E. Profile and Development Model of Micro, Small and Medium Enterprises (MSMEs) in Jambi Province (Through Superior Commodities Approach)[C]// Proceedings of the 1st International Conference on Economics Education, Economics, Business and Management, Accounting and Entrepreneurship. 2018: 251-262.
[18] 蔡盈芳, 李子林, 虞香群. 基于企业用户画像的政务档案信息整合利用模型设计[J]. 档案学研究, 2021(2): 125-131.
[18] (Cai Yingfang, Li Zilin, Yu Xiangqun. The Model Design of Government Affairs Archives Integration and Utilization Based on Enterprise User Portrait[J]. Archives Science Study, 2021(2): 125-131.)
[19] 蔡承佑, 李莹, 毛浩地, 等. 基于画像技术的僵尸企业分类识别系统的设计[J]. 信息与电脑(理论版), 2020, 32(10): 109-110.
[19] (Cai Chengyou, Li Ying, Mao Haodi, et al. Design of Zombie Enterprise Classification and Recognition System Based on Profiling Technology[J]. China Computer & Communication, 2020, 32(10): 109-110.)
[20] 樊炜, 刘延华, 杨光昊, 等. 基于大数据分析技术的供应商全息画像模型分析与应用[J]. 电气时代, 2019(11): 75-78.
[20] (Fan Wei, Liu Yanhua, Yang Guanghao, et al. Analysis and Application of Supplier Hologram Model Based on Big Data Analysis Technology[J]. Electric Age, 2019(11): 75-78.)
[21] 窦旭蒙, 梁毅, 苏航. 面向农业企业画像系统的大数据存储模型研究[J]. 软件导刊, 2019, 18(8): 36-41.
[21] (Dou Xumeng, Liang Yi, Su Hang. Research on Big Data Storage Model for Portrait System of Agricultural Enterprises[J]. Software Guide, 2019, 18(8): 36-41.)
[22] 刘春江, 李娜, 许海云, 等. 基于高质量专利的企业画像构建研究[J]. 情报工程, 2021, 7(3): 54-67.
[22] (Liu Chunjiang, Li Na, Xu Haiyun, et al. Research on the Construction of Enterprise Profile Based on High-Quality Patent[J]. Technology Intelligence Engineering, 2021, 7(3): 54-67.)
[23] Zhong C L, Lv H, Ji C, et al. Research on Technology and Application of Tag Portrait Based on Electric Power Big Data[C]// Proceedings of the 6th International Conference on Computer Science and Network Technology. 2017: 222-225.
[24] 吕辉, 许道强, 仲春林, 等. 基于电力大数据的标签画像技术与应用研究[J]. 电力信息与通信技术, 2017, 15(2): 43-48.
[24] (Lv Hui, Xu Daoqiang, Zhong Chunlin, et al. Study on Tag Portrait Technology Based on Electric Power Big Data and Its Application[J]. Electric Power Information and Communication Technology, 2017, 15(2): 43-48.)
[25] Ruan T, Xue L J, Wang H F, et al. Building and Exploring an Enterprise Knowledge Graph for Investment Analysis[C]// Proceedings of the 15th International Semantic Web Conference. 2016: 418-436.
[26] 吴行惠, 王光昕, 虞海江, 等. 质监大数据企业画像的研究及应用[J]. 数字通信世界, 2018(2): 204-208.
[26] (Wu Xinghui, Wang Guangxin, Yu Haijiang, et al. Research and Application of Quality Supervision Big Data Enterprise Portrait[J]. Digital Communication World, 2018(2): 204-208.)
[27] Lin H C K, Wang T H, Lin G C, et al. Applying Sentiment Analysis to Automatically Classify Consumer Comments Concerning Marketing 4Cs Aspects[J]. Applied Soft Computing, 2020, 97: 106755.
doi: 10.1016/j.asoc.2020.106755
[28] 谷莹, 李贺, 李叶叶, 等. 基于在线评论的企业竞争情报需求挖掘研究[J]. 现代情报, 2021, 41(1): 24-31.
doi: 10.3969/j.issn.1008-0821.2021.01.003
[28] (Gu Ying, Li He, Li Yeye, et al. Research on Demand Mining of Enterprise Competitive Intelligence Based on Online Reviews[J]. Journal of Modern Information, 2021, 41(1): 24-31.)
doi: 10.3969/j.issn.1008-0821.2021.01.003
[29] Xiong A, Liu D R, Tian H K, et al. News Keyword Extraction Algorithm Based on Semantic Clustering and Word Graph Model[J]. Tsinghua Science and Technology, 2021, 26(6): 886-893.
doi: 10.26599/TST.2020.9010051
[30] 黄晓斌, 张明鑫. 融合多源数据的企业竞争对手画像构建[J]. 现代情报, 2020, 40(11): 13-21, 33.
doi: 10.3969/j.issn.1008-0821.2020.11.002
[30] (Huang Xiaobin, Zhang Mingxin. Construction of Enterprise Competitor Portrait Based on Multi-source Data[J]. Journal of Modern Information, 2020, 40(11): 13-21, 33.)
doi: 10.3969/j.issn.1008-0821.2020.11.002
[31] Severyn A, Moschitti A. Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks[C]// Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2015: 373-382.
[32] Johnson R, Zhang T.Effective Use of Word Order for Text Categorization with Convolutional Neural Networks[OL]. arXiv Preprint, arXiv:1412.1058.
[33] 冷宁. 利用模糊综合评估法构建中小企业质量综合评价模型[J]. 经济问题探索, 2007(6): 101-105.
[33] (Leng Ning. Construction of the Quality Comprehensive Evaluation Model of Small and Medium-Sized Enterprises Based on Fuzzy Comprehensive Evaluation Method[J]. Inquiry into Economic Issues, 2007(6): 101-105.)
[34] 王瑶, 黄贤环. 企业高质量发展的指标体系构建与实现路径[J]. 统计与决策, 2021, 37(12): 182-184.
[34] (Wang Yao, Huang Xianhuan. The Index System Construction and Realization Path of Enterprise High Quality Development[J]. Statistics & Decision, 2021, 37(12): 182-184.)
[35] 刘根, 洪舸, 冷柏寒, 等. 基于知识图谱的汽车运维专家系统集成建模[J]. 工业工程与管理, 2022, 27(5):19-27.
[35] (Liu Gen, Hong Ke, Leng Bohan, et al. Integrated Modelling of Automobile Maintenance Expert System Based on Knowledge Graph[J]. Industrial Engineering and Management, 2022, 27(5):19-27.)
[1] Cheng Quan, She Dexin. Drug Recommendation Based on Graph Neural Network with Patient Signs and Medication Data[J]. 数据分析与知识发现, 2022, 6(9): 113-124.
[2] Wang Lu, Le Xiaoqiu. Research Progress on Citation Analysis of Scientific Papers[J]. 数据分析与知识发现, 2022, 6(4): 1-15.
[3] Zheng Xiao, Li Shuqing, Zhang Zhiwang. Measuring User Item Quality with Rating Analysis for Deep Recommendation Model[J]. 数据分析与知识发现, 2022, 6(4): 39-48.
[4] Yu Chuanming, Lin Hongjun, Zhang Zhengang. Joint Extraction Model for Entities and Events with Multi-task Deep Learning[J]. 数据分析与知识发现, 2022, 6(2/3): 117-128.
[5] Zhang Yunqiu, Li Bocheng, Chen Yan. Automatic Classification with Unbalanced Data for Electronic Medical Records[J]. 数据分析与知识发现, 2022, 6(2/3): 233-241.
[6] Zhang Fangcong, Qin Qiuli, Jiang Yong, Zhuang Runtao. Named Entity Recognition for Chinese EMR with RoBERTa-WWM-BiLSTM-CRF[J]. 数据分析与知识发现, 2022, 6(2/3): 251-262.
[7] Hu Yamin, Wu Xiaoyan, Chen Fang. Review of Technology Term Recognition Studies Based on Machine Learning[J]. 数据分析与知识发现, 2022, 6(2/3): 7-17.
[8] Li Zhi, Sun Rui, Yao Yuxuan, Li Xiaohuan. Recommending Point-of-Interests with Real-Time Event Detection[J]. 数据分析与知识发现, 2022, 6(10): 114-127.
[9] Huang Xuejian, Liu Yuyang, Ma Tinghuai. Classification Model for Scholarly Articles Based on Improved Graph Neural Network[J]. 数据分析与知识发现, 2022, 6(10): 93-102.
[10] Zhou Zeyu,Wang Hao,Zhao Zibo,Li Yueyan,Zhang Xiaoqin. Construction and Application of GCN Model for Text Classification with Associated Information[J]. 数据分析与知识发现, 2021, 5(9): 31-41.
[11] Xu Yuemei, Wang Zihou, Wu Zixin. Predicting Stock Trends with CNN-BiLSTM Based Multi-Feature Integration Model[J]. 数据分析与知识发现, 2021, 5(7): 126-138.
[12] Zhao Danning,Mu Dongmei,Bai Sen. Automatically Extracting Structural Elements of Sci-Tech Literature Abstracts Based on Deep Learning[J]. 数据分析与知识发现, 2021, 5(7): 70-80.
[13] Huang Mingxuan,Jiang Caoqing,Lu Shoudong. Expanding Queries Based on Word Embedding and Expansion Terms[J]. 数据分析与知识发现, 2021, 5(6): 115-125.
[14] Zhong Jiawa,Liu Wei,Wang Sili,Yang Heng. Review of Methods and Applications of Text Sentiment Analysis[J]. 数据分析与知识发现, 2021, 5(6): 1-13.
[15] Zhang Guobiao,Li Jie. Detecting Social Media Fake News with Semantic Consistency Between Multi-model Contents[J]. 数据分析与知识发现, 2021, 5(5): 21-29.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938   E-mail:jishu@mail.las.ac.cn