Please wait a minute...
Data Analysis and Knowledge Discovery  2021, Vol. 5 Issue (10): 124-136    DOI: 10.11925/infotech.2096-3467.2021.0137
Current Issue | Archive | Adv Search |
Integrating Expert Reviews for Government Information Projects with Knowledge Fusion
Hua Bin(),Wu Nuo,He Xin
School of Science and Technology, Tianjin University of Finance and Economics, Tianjin 300222, China
Download: PDF (1340 KB)   HTML ( 0
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This paper proposes a new method to integrate the short texts of multi-expert reviews for the same government information project, aiming to generate comprehensive opinion with knowledge fusion at the cognitive level. [Methods] First, we extracted knowledge from the reviews through content mining. Then, we analyzed semantics of these reviews with target knowledge concept tree and customized method. Third, we finished knowledge fusion at the micro and macro levels based on the text structure model and domain ontology. [Results] Compared with the original texts, the amount of information provided by our method was increased by 0.19, while the average ratio of knowledge elements reached 115.38%. [Limitations] The proposed method could be affected by the language of expert reviews and the integrity of domain knowledge. [Conclusions] Our new method could effectively integrate short texts from various fields.

Key wordsGovernment Information System      Project Management      Opinion Mining      Knowledge Fusion      Text Integration     
Received: 08 February 2021      Published: 23 November 2021
ZTFLH:  TP391  
Fund:Special Fund Project of Tianjin E-government Informatization(津党网信函(2018)146号)
Corresponding Authors: Hua Bin,ORCID:0000-0002-2411-3638     E-mail: bigsoon@sina.com

Cite this article:

Hua Bin, Wu Nuo, He Xin. Integrating Expert Reviews for Government Information Projects with Knowledge Fusion. Data Analysis and Knowledge Discovery, 2021, 5(10): 124-136.

URL:

http://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2021.0137     OR     http://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2021/V5/I10/124

Example of Expert Approval Opinions on Government Informatization Projects
Reference Model of E-Government Information System
通用关系名 语义关系描述
LINK_BELONG_TO(属于审批环节) 项目与审批环节之间的关系
ELEMENT_OF(包含项目要素) 项目与项目要素之间的父子类关系
OPINION_BELONG_TO(属于项目) 审批意见与项目之间的关系
ADM_LAW(属于审批环节) 政策法规与审批环节之间的关系
CONTENT_BELONG_TO(属于审批环节) 项目要素与审批环节之间的关系
ADJUSTMENT_BELONG_TO(属于项目要素) 审批意见与项目要素之间的关系
FUNC_DUTY(属于子职能) 项目要素与政务子职能之间的关系
SUB_OF(包含政务子职能) 政务职能与子职能之间的父子类关系
Semantic Relationship Description Between Concepts
Expert Opinion Acquisition Based on Hierarchical Semantic Recognition
Expert Opinion Integration Strategy Based on Knowledge Fusion
Example of Knowledge Fusion Based on SAO Alignment
Example of Project Domain Knowledge Concept Tree (Partial)
Knowledge Ontology of Government Information Project Approval
通用关系名 语义关系描述
BUD_OF(包含项目预算) 项目要素与项目预算之间的父子类关系
CONS_OF(包含建设内容) 项目要素与建设内容之间的父子类关系
PRO_OF(包含技术方案) 项目要素与技术方案之间的父子类关系
TAR_OF(包含考核指标) 项目要素与考核指标之间的父子类关系
HARD_OF(包含硬件系统) 建设内容与硬件系统之间的父子类关系
SOFT_OF(包含软件系统) 建设内容与软件系统之间的父子类关系
ENV_OF(包含环境系统) 建设内容与环境系统之间的父子类关系
COM_OF(包含通信系统) 建设内容与通信系统之间的父子类关系
MODUAL_OF(包含功能) 软件系统与功能之间的父子类关系
Description of Semantic Relationship Between Project Elements and Their Subclass Concepts
SAO结构化知识 结构化知识语义特征 例子
SA(主谓) 通常是专家对审批对象表明看法或态度。看法或态度即为谓语(A),多以形容词为基础结构 1.方案可行
2.需求过多
3.建设目标不具体
AO(谓宾) 通常是专家对审批对象表明建议性调整动作。建议性调整动作即为谓语(A),多以动词为基础 1.缺少软硬件部署方案
2.补充预算清单
3.说明系统的可行性
SAO
(主谓宾)
通常是专家对审批对象表明调整性建议或指出问题。谓语(A)通常用以表达项目概念知识之间的关系 1.项目的方案需要补充内容
2.项目的需求需要细化
3.预算方案缺少依据
Semantic Analysis of SAO Structured Knowledge on Expert Approval Opinions
原因 示例(知识抽取结果以S/A/O表示) 自定义规则
①标定的依存关系过于复杂以及错误 原句:
该项目方案包括将多个运维服务方案合成一个项目。
知识抽取结果:
该项目方案/包括/合成项目
定义1:将原句进行分词、词性筛选,抽取名词、动名词以定位概念候选词;抽取动词、形容词以定位修饰性候选词,表示内在语义关系
②存在两个核心依存关系,但原句为含有主语从句或宾语从句的复合语句(以含主从的复合句为例) 原句:
合同复印件作为附件放到申报书。
知识抽取结果:
合同复印件/作为/附件
/放到/申报书
定义2:将主语从句(或宾语从句)的SAO结构化知识作为复合句的主语(或宾语),补全复合句SAO结构化知识
③标定依存关系错误,将名词性的修饰语标定为并列宾语,而非谓语的定中关系。没有准确识别内在的语义包含关系 原句:
减少信息化建设的重复投资。
知识抽取结果:
①/减少/信息化建设
②/减少/重复投资
定义3:将两者的宾语合并为一个宾语,形成新一个SAO结构化知识,将其内在语义包含关系在知识中体现
Semantic Analysis of non-SAO Structured Knowledge on Expert Approval Opinions
意见句语义识别结果 项目综合意见语义识别结果
P/% R/% F1/% U/%
94.18 86.01 89.91 81.42
Results of Semantic Recognition on Evaluation Feature Word Segmentation
结果 RNN LSTM BiRNN BiLSTM
精度/% 85.37 86.79 89.15 90.09
损失/% 26.82 33.51 32.69 29.86
Results of Emotional Analysis
父概念 情感隶属度
1~0.8 0.8~0.6 0.6~0.3 0.3~0
建设方案 合理 较合理 不太合理 不合理
需求分析 清晰 较清晰 不太清晰 不清晰
建设目标 合理 较合理 不太合理 不合理
建设内容 具体 较具体 不太具体 不具体
经费预算 合理 比较合理 不太合理 不合理
考核指标 具体 较具体 不太具体 不具体
技术方案 合理 较合理 不太合理 不合理
实施安排 合理 较合理 不太合理 不合理
Attribute Reference Words
属性 情感隶属度
1~0.8 0.8~0.6 0.6~0.3 0.3~0
政务子职能 符合 较符合 不太符合 不符合
Government Sub Function Attribute Reference Words
专家 审批意见
专家1 ①缺少量化的考核指标
②建设方案不够完整,需求分析不清楚。缺少软硬件部署方案和运行方案;此外,对现有的基础条件和系统要进行更详细的分析
③投资预算不合理,购买很多服务器缺少依据,此外,UPS设备没有给出参考价格
专家2 ①项目建设方案不合理,软件和硬件运行平台方案设计没有分析
②项目建设内容与已有信息化基础之间的关系没有说明
③项目需求分析不清晰,网络设备超出学校实际需求
④项目建设目标不具体
⑤项目验收考核指标不具体
专家3 现有方案不够完整
专家4 ①需求需要细化
②预留标准接口需要详细描述
专家5 项目申报书对于数据库设计没有叙述,需要补充内容,说明设计与硬件和软件系统的配套合理性。项目申报书中提到的云计算与整体设计架构不符
Approval Opinions of Experts in the Group
政务信息化项目审批意见
XXXXXX日,XX委局项目管理部门组织专家对“XX单位”申报的政务信息化项目“ XX市数据安全监督管理平台(编号 XXXX”进行了 可行性研究环节的论证.专家组审阅了项目材料,听取了项目汇报,经过质询与讨论,形成审批意见如下:
1、建设方案不太合理:缺少软硬件部署方案、运行方案;
2、需求分析不清晰:需求需要细化;
3、建设目标不合理;
4、建设内容不太具体:项目建设内容与已有信息化基础之间的关系没有说明;
其中,第一,在【基础设施】方面,
购买很多服务器缺少依据;
UPS设备没有给出参考价格;网络设备超出学校实际需求;
软件和硬件运行平台方案设计没有分析;说明设计与硬件和软件系统的配套合理性;
项目申报书中提到的云计算与整体设计架构不符;
第二,在【软件开发】方面,
现有的基础条件和系统要进行更详细的分析;
项目申报书数据库设计没有叙述, 不符合[建立大数据报备制度]该政务职能的要求;
由于不符合[数据安全保障体系]该政务职能的要求,因此预留标准接口需要详细描述;
5、经费预算不合理;
6、考核指标不太具体:缺少量化考核指标。
根据综合审批结果,该项目暂缓通过此环节的审批。
Results of Expert Group Approval Opinions Integration
单专家审批意见组合 整合后专家组意见 整合后的专家组意见——去除项目知识扩充语句(政务职能、政策法规等)
6.04 6.23 5.92
1 Results of Text Test Based on Effective Information
[1] 国务院办公厅. 国家政务信息化项目建设管理办法[EB/OL]. [2020-08-20].http://www.gov.cn/zhengce/content/2020-01/21/content_5471256.htm.
[1] (General Office of the State Council. Construction Management Measures of National Government Informatization Projects[EB/OL]. [2020-08-20]. http://www.gov.cn/zhengce/content/2020-01/21/content_5471256.htm.)
[2] 国家标准委员会, 发展改革委, 中央网信办. 政务信息系统定义和范围[EB/OL].[2020-08-20]. https://wenku.baidu.com/view/2088fe392a160b4e767f5acfa1c7aa00b42a9d1d.html?fixfr=FI3ZbuFXkNsHOwhOKiTb8g%253D%253D&fr=income1-wk_go_search-search.
[2] (National Standards Commission, National Development and Reform Commission, Office of the Central Cyberspace Affairs Commission. Definition and Scope of Government Information System[EB/OL]. [2020-08-20].https://wenku.baidu.com/view/2088fe392a160b4e767f5acfa1c7aa00b42a9d1d.html?fixfr=FI3ZbuFXkNsHOwhOKiTb8g%253D%253D&fr=income1-wk_go_search-search.)
[3] ZW/T 1001-2019, 电子政务系统建设质量要求和测评规范[S]. 北京: 国家信息中心, 国家电子政务系统质量监督检验中心, 2019.
[3] (ZW/T 1001-2019, Quality Requirements and Evaluation Specification for E-Government System Construction[S]. Beijing:The State Information Center, National E-Government Quality Supervision and Inspection Center, 2019.)
[4] ZW/T 1002-2019, 电子政务系统运行质量要求和测评规范[S]. 北京:国家信息中心, 国家电子政务系统质量监督检验中心, 2019.
[4] (ZW/T 1002-2019, Quality Requirements and Evaluation Specification for E-Government System Operation[S]. Beijing: The State Information Center, National E-Government Quality Supervision and Inspection Center, 2019.)
[5] ZW/T 1003-2019, 政务信息系统整合共享评估规范[S]. 北京: 国家信息中心, 国家电子政务系统质量监督检验中心, 2019.
[5] (ZW/T 1003-2019, Evaluation Specification of E-Government System Integration and Sharing[S]. Beijing:The State Information Center, National E-Government Quality Supervision and Inspection Center, 2019.)
[6] ZW/T 1004-2019, 电子政务数据中心技术要求和测评规范[S]. 北京: 国家信息中心, 国家电子政务系统质量监督检验中心, 2019.
[6] (ZW/T 1004-2019, Technical Requirements and Evaluation Specification for E-Government Data Center[S]. Beijing:The State Information Center, National E-Government Quality Supervision and Inspection Center, 2019)
[7] 杨震, 赖英旭, 段立娟, 等. 基于上下文重构的短文本情感极性判别研究[J]. 自动化学报, 2012, 38(1): 55-67.
[7] (Yang Zhen, Lai Yingxu, Duan Lijuan, et al. Short Text Sentiment Classification Based on Context Reconstruction[J]. Acta Automatica Sinica, 2012, 38(1): 55-67.)
[8] 朱琳, 刘雨欣, 顾文清. 基于共词分析的中国电子政务政策变迁研究[J]. 电子政务, 2020(11): 59-73.
[8] (Zhu Lin, Liu Yuxin, Gu Wenqing. Co-Word Analysis on Policy Change of E-Government in China[J]. E-Government, 2020(11): 59-73.)
[9] 盛苏平, 刘春燕, 赵新力. 《电子政务主题词表》编制及应用系统开发[J]. 中国信息导报, 2006(3): 37-39.
[9] (Sheng Suping, Liu Chunyan, Zhao Xinli. Compilation and Application System Development of E-Government Thesaurus[J]. China Information Review, 2006(3): 37-39.)
[10] 张卫, 王昊, 邓三鸿, 等. 电子政务领域中文术语层次关系识别研究[J]. 情报学报, 2021, 40(1): 62-76.
[10] (Zhang Wei, Wang Hao, Deng Sanhong, et al. Research on Hierarchy Identification of Chinese Terms in the Field of E-government[J]. Journal of the China Society for Scientific and Technical Information, 2021, 40(1): 62-76.)
[11] 王汀, 冀付军. 基于主题词表与百科知识相融合的领域本体自动构建研究[J]. 情报学报, 2017, 36(7): 723-733.
[11] (Wang Ting, Ji Fujun. Automatic Modeling of Large-Scale Domain Ontology Based on Thesauruses and Online Encyclopedias[J]. Journal of the China Society for Scientific and Technical Information, 2017, 36(7): 723-733.)
[12] 李芳, 许德山. 中文电子政务服务整合领域本体构建研究[J]. 现代情报, 2016, 36(1): 79-83.
[12] (Li Fang, Xu Deshan. Construction of Chinese Domain Ontology on E-government Services Integration[J]. Journal of Modern Information, 2016, 36(1): 79-83.)
[13] 刘晓娟, 李广建, 化柏林. 知识融合:概念辨析与界说[J]. 图书情报工作, 2016, 60(13): 13-19, 32.
[13] (Liu Xiaojuan, Li Guangjian, Hua Bolin. Knowledge Fusion: From the Conceptual Understanding to the System Construction[J]. Library and Information Service, 2016, 60(13): 13-19, 32.)
[14] 邱均平, 余厚强. 知识科学视角下国际知识融合研究进展与趋势[J]. 图书情报工作, 2015, 59(8): 126-132, 148.
[14] (Qiu Junping, Yu Houqiang. Research Progress and Trends of International Knowledge Fusion at the Perspective of Knowledge Science[J]. Library and Information Service, 2015, 59(8): 126-132, 148.)
[15] 王仲远, 程健鹏, 王海勋, 等. 短文本理解研究[J]. 计算机研究与发展, 2016, 53(2): 262-269.
[15] (Wang Zhongyuan, Cheng Jianpeng, Wang Haixun, et al. Short Text Understanding: A Survey[J]. Journal of Computer Research and Development, 2016, 53(2): 262-269.)
[16] 王忠群, 皇苏斌, 修宇, 等. 基于领域专家和商品特征概念树的在线商品评论深刻性度量[J]. 现代图书情报技术, 2015(9): 17-25.
[16] (Wang Zhongqun, Huang Subin, Xiu Yu, et al. Research on Metrics-Model for Online Product Review Depth Based on Domain Expert and Feature Concept Tree of Products[J]. New Technology of Library and Information Service, 2015(9): 17-25.)
[17] 张晓龙, 姚天顺. 基于文本句法的文本生成模型[J]. 中文信息学报, 1995, 9(1): 8-15.
[17] (Zhang Xiaolong, Yao Tianshun. A Model of Text Generation Based on Text-Syntactics[J]. Journal of Chinese Information Processing, 1995, 9(1): 8-15.)
[18] 孙玉娣, 张玉强. 基于本体的综合评价自动生成系统研究[J]. 情报杂志, 2007, 26(2): 31-33.
[18] (Sun Yudi, Zhang Yuqiang. Research of Synjournal Evaluation Automatic Generation System Based on Ontology[J]. Journal of Intelligence, 2007, 26(2): 31-33.)
[19] 祝振媛. 基于信息分类的网络书评内容挖掘与整合研究[J]. 图书情报工作, 2016, 60(1): 114-124.
[19] (Zhu Zhenyuan. Content Mining and Integration Study of Online Book Reviews Based on Information Classification[J]. Library and Information Service, 2016, 60(1): 114-124.)
[20] 张良, 蔡生. 信息量的度量及应用[J]. 沈阳大学学报, 2004, 16(2): 89-91.
[20] (Zhang Liang, Cai Sheng. Measurement and Application of Information Quantity[J]. Journal of Shenyang University, 2004, 16(2): 89-91.)
[21] 文庭孝. 知识单元的演变及其评价研究[J]. 图书情报工作, 2007, 51(10): 72-76.
[21] (Wen Tingxiao. Research on Knowledge Unit Evolution and Evaluation[J]. Library and Information Service, 2007, 51(10): 72-76.)
[22] 钟毅平, 叶茂林. 认知心理学[M]. 合肥: 安徽人民出版社, 2010: 8.
[22] (Zhong Yiping, Ye Maolin. Cognitive Psychology[M]. Hefei: Anhui Renmin Press, 2010: 8.)
[23] 华斌, 吴诺, 李若瑄. 基于知识图谱的电子政务项目评价方法研究与实践[J]. 情报理论与实践, 2021, 44(2): 147-153, 146.
[23] (Hua Bin, Wu Nuo, Li Ruoxuan. Research and Practice of E-Government Project Evaluation Method Based on Knowledge Graph[J]. Information Studies: Theory & Application, 2021, 44(2): 147-153, 146.)
[24] 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.
doi: 10.1007/s11192-011-0420-z
[25] Abdulghafour M, Chandra T, Abidi A. Data Fusion Through Fuzzy Logic Applied to Feature Extraction from Multi-Sensory Images [C]//Proceedings of IEEE International Conference on Robotics and Automation. 1993: 359-366.
[1] Zheng Xinman, Dong Yu. Constructing Degree Lexicon for STI Policy Texts[J]. 数据分析与知识发现, 2021, 5(10): 81-93.
[2] Xu Hongxia,Yu Qianqian,Qian Li. Studying Content Interaction Data with Topic Model and Sentiment Analysis[J]. 数据分析与知识发现, 2020, 4(7): 110-117.
[3] Bocheng Li,Yunqiu Zhang,Kaixi Yang. Extracting Emotion Tags from Comments of Microblog Commodities[J]. 数据分析与知识发现, 2019, 3(9): 115-123.
[4] Yujie Cao,Jin Mao,Rongqing Pan,Zhichao Ba,Gang Li. Analyzing Characteristics of Interdisciplinary Research Evolutions: Case Study of Medical Informatics[J]. 数据分析与知识发现, 2019, 3(5): 107-116.
[5] Li Weiqing,Wang Weijun. Building Product Feature Dictionary with Large-scale Review Data[J]. 数据分析与知识发现, 2018, 2(1): 41-50.
[6] Guo Bo,Li Shouguang,Wang Hao,Zhang Xiaojun,Gong Wei,Yu Zhaojun,Sun Yu. Examining Product Reviews with Sentiment Analysis and Opinion Mining[J]. 数据分析与知识发现, 2017, 1(12): 1-9.
[7] Zhang Li, Xu Xin. Implicit Feature Identification in Product Reviews[J]. 现代图书情报技术, 2015, 31(12): 42-47.
[8] You Guirong, Wu Wei, Qian Yuntao. Feature Extraction Method for Detecting Spam in Electronic Commerce[J]. 现代图书情报技术, 2014, 30(10): 93-100.
[9] Cao Li, Jiang Yi, Gan Chunmei, Zhang Yichi, Chen Guiqiang. Construction of Software Testing Platform on Cloud Computing[J]. 现代图书情报技术, 2012, (11): 34-39.
[10] Li Gang,Chen Jing,Cheng Mingjie,Kou Guangzeng. Study on the City Image Network Monitoring System Based on Opinion-mining[J]. 现代图书情报技术, 2010, 26(2): 56-62.
[11] Yu Chuanming. Mining Product Aspects from User Reviews----An SOM-based Approach[J]. 现代图书情报技术, 2009, 25(5): 61-66.
[12] Ma Jing,Li Qv . The Essential Elements of System Behavior and Design of Its Inspect Mechanism[J]. 现代图书情报技术, 2007, 2(1): 77-80.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938   E-mail:jishu@mail.las.ac.cn