Multi-label active learning algorithm for shale gas reservoir prediction

doi:10.11772/j.issn.1001-9081.2021041023

Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (2): 646-654.DOI: 10.11772/j.issn.1001-9081.2021041023

• Frontier and comprehensive applications • Previous Articles Next Articles

Multi-label active learning algorithm for shale gas reservoir prediction

Min WANG¹(), Tingting FENG¹, Fan MIN², Hongming TANG³, Jianping YAN³, Jijia LIAO³

^1.School of Electrical Engineering and Information，Southwest Petroleum University，Chengdu Sichuan 610500，China
^2.School of Computer Science，Southwest Petroleum University，Chengdu Sichuan 610500，China
^3.School of Geoscience and Technology，Southwest Petroleum University，Chengdu Sichuan 610500，China

Received:2021-06-15 Revised:2021-07-05 Accepted:2021-07-09 Online:2022-02-11 Published:2022-02-10
Contact: Min WANG
About author:WANG Min， born in 1980， M. S.， professor. Her research interests include data mining， active learning.
FENG Tingting， born in 1994， M， S. candidate. Her research interests include active learning.
MIN Fan， born in 1973， Ph. D.， professor. His research interests include granular computing， recommender system， active learning.
TANG Hongming， born in 1966， Ph. D.， professor. His research interests include development geology， evaluation of unconventional oil and gas reservoirs.
YAN Jianping， born in 1980， Ph. D.， professor. His research interests include logging geology， rock physics， evaluation of unconventional reservoir logging.
LIAO Jijia， born in 1983， Ph. D. His research interests include sedimentology， reservoir protection.
Supported by:
National Natural Science Foundation of China(62006200);CNPC-Southwest Petroleum University Innovation Consortium Science and Technology Cooperation Project(2020CX020000)

页岩气储层预测的多标签主动学习算法

汪敏¹(), 冯婷婷¹, 闵帆², 唐洪明³, 闫建平³, 廖纪佳³

^1.西南石油大学电气信息学院, 成都 610500
^2.西南石油大学计算机科学学院, 成都 610500
^3.西南石油大学地球科学与技术学院, 成都 610500

通讯作者: 汪敏
作者简介:汪敏（1980—），女，湖南邵阳人，教授，硕士，CCF会员，主要研究方向：数据挖掘、主动学习；
冯婷婷（1994—），女，山东济宁人，硕士研究生，主要研究方向：主动学习；
闵帆（1973—），男，重庆人，教授，博士，CCF会员，主要研究方向：粒计算、推荐系统、主动学习；
唐洪明（1966—），男，四川武胜人，教授，博士，主要研究方向：开发地质学、非常规油气储层评价；
闫建平（1980—），男，内蒙古凉城人，教授，博士，主要研究方向：测井地质学、岩石物理、非常规储层测井评价；
廖纪佳（1983—），男，四川绵竹人，博士，主要研究方向：沉积学、储层保护。
基金资助:
国家自然科学基金资助项目(62006200);中国石油-西南石油大学创新联合体科技合作项目(2020CX020000)

Abstract

Abstract:

Concerning the problems of the difficulties in obtaining， the limitation of labels， and the high cost of labeling of shale gas reservoir data， a Multi-standard Active query Multi-label Learning （MAML） algorithm was proposed. First of all， with the consideration of the informativeness and representativeness of the samples， the preliminary processing was performed on the samples. Secondly， the sample richness constraints including attribute differences and label richness were added， on this basis， the valuable samples were selected and the labels of these samples were queried. Finally， a multi-label learning algorithm was used to predict the labels of the remaining samples. Through experiments on eleven Yahoo datasets， the MAML algorithm was compared with popular multi-label learning algorithms and active learning algorithms， and the superiority of the MAML algorithm was proved. Then， the experiments were extended to four real shale gas well logging datasets. In these experiments， compared with the multi-label learning algorithms： Multi-Label Multi-Label K-Nearest Neighbor （ML-KNN）， BackPropagation for Multi-Label Learning （BP-MLL）， multi-label learning with GLObal and loCAL label correlation （GLOCAL） and active learning by QUerying Informative and Representative Examples （QUIRE）， the MAML algorithm improved the average prediction accuracy of comprehensive quality of shale gas reservoirs by 45 percentage points， 68 percentage points， 68 percentage points， and 51 percentage points， respectively. The practicability and superiority of the MAML algorithm in the prediction of shale gas reservoir sweet spots are fully proved by these experimental results.

Key words: multi-label learning, active learning, multi-standard optimization, query, sweet spot prediction

摘要：

针对页岩气储层数据获取困难、标签稀缺、标注成本高昂的问题，提出一种多标准主动查询的多标签学习（MAML）算法。首先，考虑样本的信息性和代表性来对样本进行初步处理；其次，加入包括属性差异性和标签丰富性的样本丰富性约束，在此基础上选择有价值的样本进行标签查询；最后，利用多标签学习算法来预测剩余样本的标签。通过11个Yahoo数据集上的实验，将MAML算法与流行的多标签学习算法和主动学习算法进行比较，验证了MAML算法的优越性。然后将实验扩展到4个真实的页岩气测井数据集。在该实验中，与多标签学习算法：基于K最近邻的多标签（ML-KNN）学习方法、多标签学习的反向传播（BP-MLL）算法、具有全局和局部标签相关性的多标签学习方法（GLOCAL）和通过查询信息性和代表性样本的主动学习（QUIRE）方法相比，MAML算法在页岩气储层综合品质预测精度均值上分别提升了45个百分点、68个百分点、68个百分点和51个百分点。实验结果充分验证了MAML算法在页岩气储层甜点预测领域的实用性和优越性。

关键词: 多标签学习, 主动学习, 多标准优化, 查询, 甜点预测

CLC Number:

TP181

Min WANG, Tingting FENG, Fan MIN, Hongming TANG, Jianping YAN, Jijia LIAO. Multi-label active learning algorithm for shale gas reservoir prediction[J]. Journal of Computer Applications, 2022, 42(2): 646-654.

汪敏, 冯婷婷, 闵帆, 唐洪明, 闫建平, 廖纪佳. 页岩气储层预测的多标签主动学习算法[J]. 《计算机应用》唯一官方网站, 2022, 42(2): 646-654.

Figures/Tables 8

References 29

1	董大忠，王玉满，李新景，等.中国页岩气勘探开发新突破及发展前景思考［J］.天然气工业， 2016， 36（1）： 19-32. 10.3787/j.issn.1000-0976.2016.01.003
	DONG D Z， WANG Y M， LI X J， et al. Breakthrough and prospect of shale gas exploration and development in China［J］. Natural Gas Industry， 2016， 36（1）： 19-32. 10.3787/j.issn.1000-0976.2016.01.003
2	邹才能，董大忠，王玉满，等.中国页岩气特征、挑战及前景（一）［J］.石油勘探与开发， 2015， 42（6）： 689-701. 10.11698/PED.2015.06.01
	ZOU C N， DONG D Z， WANG Y M， et al. Shale gas in China： characteristics， challenges and prospects （Ⅰ）［J］. Petroleum Exploration and Development， 2015， 42（6）： 689-701. 10.11698/PED.2015.06.01
3	梁兴，王高成，徐政语，等.中国南方海相复杂山地页岩气储层甜点综合评价技术——以昭通国家级页岩气示范区为例［J］.天然气工业， 2016， 36（1）： 33-42. 10.3787/j.issn.1000-0976.2016.01.004
	LIANG X， WANG G C， XU Z Y， et al. Comprehensive evaluation technology for shale gas sweet spots in the complex marine mountains， South China： a case study from Zhaotong national shale gas demonstration zone［J］. Natural Gas Industry， 2016， 36（1）： 33-42. 10.3787/j.issn.1000-0976.2016.01.004
4	AL-SALEMI B， AYOB M， KENDALL G， et al. Multi-label Arabic text categorization： a benchmark and baseline comparison of multi-label learning algorithms［J］. Information Processing and Management， 2019， 56（1）： 212-227. 10.1016/j.ipm.2018.09.008
5	IVAN CHANG C I， CHEN R B. Active learning with simultaneous subject and variable selections［J］. Neurocomputing， 2019， 329： 495-505. 10.1016/j.neucom.2018.11.036
6	HUANG S J， LI G X， HUANG W Y， et al. Incremental multi-label learning with active queries［J］. Journal of Computer Science and Technology， 2020， 35（2）： 234-246. 10.1007/s11390-020-9994-3
7	RODRIGUEZ A， LAIO A. Clustering by fast search and find of density peaks［J］. Science， 2014， 344（6191）： 1492-1496. 10.1126/science.1242072
8	ZHANG M L， ZHOU Z H. Multi-label learning by instance differentiation ［C］// Proceedings of the 22nd AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2007： 669-674. 10.1609/aaai.v34i07.6986
9	钟光海，陈丽清，廖茂杰，等.页岩气储层品质测井综合评价［J］.天然气工业， 2020， 40（2）： 54-60.
	ZHONG G H， CHEN L Q， LIAO M J， et al. A comprehensive logging evaluation of shale gas reservoir quality［J］. Natural Gas Industry， 2020， 40（2）： 54-60.
10	UEDA N， SAITO K. Parametric mixture models for multi-labeled text ［C］// Proceedings of the 15th International Conference on Neural Information Processing Systems. Cambridge： MIT Press， 2002： 737-744. 10.1145/775047.775140
11	REYES O， ALTALHI A H， VENTURA S. Statistical comparisons of active learning strategies over multiple datasets［J］. Knowledge-Based Systems， 2018， 145： 274-288. 10.1016/j.knosys.2018.01.033
12	严伟，刘帅，冯明刚，等.四川盆地丁山区块页岩气储层关键参数测井评价方法［J］.岩性油气藏， 2019， 31（3）： 95-104. 10.12108/yxyqc.20190311
	YAN W， LIU S， FENG M G， et al. Well logging evaluation methods of key parameters for shale gas reservoir in Dingshan block， Sichuan Basin［J］. Lithologic Reservoirs， 2019， 31（3）： 95-104. 10.12108/yxyqc.20190311
13	赖富强，罗涵，覃栋优，等.基于层次分析法的页岩气储层可压裂性评价研究［J］.特种油气藏， 2018， 25（3）： 154-159. 10.3969/j.issn.1006-6535.2018.03.031
	LAI F Q， LUO H， QIN D Y， et al. Crushability evaluation of shale gas reservoir based on analytic hierarchy process［J］. Special Oil and Gas Reservoirs， 2018， 25（3）： 154-159. 10.3969/j.issn.1006-6535.2018.03.031
14	石文睿，张超谟，张占松，等.涪陵页岩气田焦石坝页岩气储层含气量测井评价［J］.测井技术， 2015， 39（3）： 101-106.
	SHI W R， ZHANG C M， ZHANG Z S， et al. Log evaluation of gas content from Jiaoshiba shale gas reservoir in Fuling gas field［J］. Well Logging Technology， 2015， 39（3）： 101-106.
15	QUEVEDO J R， LUACES O， BAHAMONDE A. Multilabel classifiers with a probabilistic thresholding strategy［J］. Pattern Recognition， 2012， 45（2）： 876-883. 10.1016/j.patcog.2011.08.007
16	WANG M， FU K， MIN F， et al. Active learning through label error statistical methods［J］. Knowledge-Based Systems， 2020， 189： No.105140. 10.1016/j.knosys.2019.105140
17	WANG M， MIN F， ZHANG Z H， et al. Active learning through density clustering［J］. Expert Systems with Applications， 2017， 85： 305-317. 10.1016/j.eswa.2017.05.046
18	LUO X， DU H Q， ZHOU G M， et al. A novel query strategy-based rank batch-mode active learning method for high-resolution remote sensing image classification［J］. Remote Sensing， 2021， 13（11）： No.2234. 10.3390/rs13112234
19	MIN F， LIU F L， WEN L Y， et al. Tri-partition cost-sensitive active learning through kNN［J］. Soft Computing， 2019， 23（5）： 1557-1572. 10.1007/s00500-017-2879-x
20	YAN Y F， HUANG S J， CHEN S Y， et al. Active learning with query generation for cost-effective text classification ［C］// Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2020： 6583-6590. 10.1609/aaai.v34i04.6133
21	WANG M， YU H T， MIN F， et al. Noise label learning through label confidence statistical inference［J］. Knowledge-Based Systems， 2021， 227： No.107234. 10.1016/j.knosys.2021.107234
22	WU J， GUO A Q， SHENG V S， et al. An active learning approach for multi-label image classification with sample noise［J］. International Journal of Pattern Recognition and Artificial Intelligence， 2018， 32（3）： No.1850005. 10.1142/s0218001418500052
23	LI S N， ZHANG Z H， DUAN J Q. An ensemble multi-label feature selection algorithm based on information entropy［J］. The International Arab Journal of Information Technology， 2014， 11（4）： 379-386.
24	HARCOURT R D. Angular eigenvalues and some classical probability density functions for the helium isoelectronic sequence［J］. Physics Letters A， 1995， 200（2）： 144-148. 10.1016/0375-9601(95)00141-o
25	WANG M， ZHANG Y Y， MIN F. Active learning through multi-standard optimization［J］. IEEE Access， 2019， 7： 56772-56784. 10.1109/access.2019.2914263
26	ZHANG M L， ZHOU Z H. ML-KNN： a lazy learning approach to multi-label learning［J］. Pattern Recognition， 2007， 40（7）： 2038-2048. 10.1016/j.patcog.2006.12.019
27	ZHANG M L， ZHOU Z H. Multilabel neural networks with applications to functional genomics and text categorization［J］. IEEE Transactions on Knowledge and Data Engineering， 2006， 18（10）： 1338-1351. 10.1109/tkde.2006.162
28	ZHU Y， KWOK J T， ZHOU Z H. Multi-label learning with global and local label correlation［J］. IEEE Transactions on Knowledge and Data Engineering， 2018， 30（6）： 1081-1094. 10.1109/tkde.2017.2785795
29	HUANG S J， JIN R， ZHOU Z H. Active learning by querying informative and representative examples［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2014， 36（10）： 1936-1949. 10.1109/tpami.2014.2307881

数据集	样本数	标签数	属性数
Arts	5 000	26	462
Business	5 000	30	438
Computers	5 000	33	681
Education	5 000	33	550
Entertainment	5 000	21	640
Health	5 000	32	612
Recreation	5 000	22	606
Reference	5 000	33	793
Science	5 000	40	743
Social	5 000	39	1 047
Society	5 000	27	636

数据集	样本数	标签数	属性数
Arts	5 000	26	462
Business	5 000	30	438
Computers	5 000	33	681
Education	5 000	33	550
Entertainment	5 000	21	640
Health	5 000	32	612
Recreation	5 000	22	606
Reference	5 000	33	793
Science	5 000	40	743
Social	5 000	39	1 047
Society	5 000	27	636

算法	AveragePrecision	Coverage	OneError	RankingLoss
MAML	1.0909	3.000 0	1.6364	2.727 3
ML-KNN	2.818 2	1.0000	3.136 4	1.0909
BP-MLL	3.545 5	2.000 0	3.227 3	2.181 8
GLOCAL	2.545 5	4.000 0	2.000 0	4.000 0

算法	AveragePrecision	Coverage	OneError	RankingLoss
MAML	1.0909	3.000 0	1.6364	2.727 3
ML-KNN	2.818 2	1.0000	3.136 4	1.0909
BP-MLL	3.545 5	2.000 0	3.227 3	2.181 8
GLOCAL	2.545 5	4.000 0	2.000 0	4.000 0

数据集	算法	评价指标
数据集	算法	AveragePrecision	Coverage	OneError	RankingLoss
Arts	MAML	0.503 0±0.000 0	7.053 2±0.000 0	0.617 1±0.000 0	0.194 5±0.000 0
	ML-KNN^*	0.458 6±0.000 0	6.038 2±0.000 4	0.682 0±0.000 0	0.174 5±0.000 0
	BP-MLL^*	0.431 6±0.000 0	6.243 1±0.008 3	0.751 8±0.000 0	0.181 6±0.000 0
	GLOCAL^*	0.464 6±0.000 0	9.000 9±0.000 5	0.629 6±0.000 0	0.268 6±0.000 0
	QUIRE^**	0.511 1±0.000 0	6.864 8±0.012 9	0.605 8±0.000 1	0.190 3±0.000 0
Business	MAML	0.855 8±0.000 0	3.374 4±0.000 0	0.137 4±0.000 0	0.064 3±0.000 0
	ML-KNN^*	0.854 9±0.000 0	2.732 4±0.000 8	0.136 9±0.000 0	0.051 1±0.000 0
	BP-MLL^*	0.854 1±0.000 0	2.900 8±0.002 9	0.132 4±0.000 0	0.053 1±0.000 0
	GLOCAL^*	0.788 5±0.000 0	4.917 0±0.009 1	0.204 4±0.000 0	0.100 6±0.000 0
	QUIRE^**	0.866 5±0.000 0	3.191 0±0.006 6	0.120 2±0.000 0	0.058 7±0.000 0
Computers	MAML	0.632 5±0.000 0	6.074 5±0.000 0	0.435 0±0.000 0	0.134 0±0.000 0
	ML-KNN^*	0.599 7±0.000 0	4.723 1±0.004 7	0.477 3±0.000 0	0.103 5±0.000 0
	BP-MLL^*	0.596 6±0.000 0	4.906 4±0.002 1	0.477 3±0.000 0	0.101 9±0.000 0
	GLOCAL^*	0.566 9±0.000 0	8.517 7±0.004 1	0.483 3±0.000 0	0.204 8±0.000 0
	QUIRE^**	0.630 9±0.000 1	6.015 8±0.042 8	0.431 3±0.000 1	0.131 8±0.000 0
Education	MAML	0.510 0±0.000 0	6.149 0±0.000 0	0.624 6±0.000 0	0.147 0±0.000 0
	ML-KNN^*	0.504 5±0.000 5	4.694 1±0.000 3	0.637 1±0.001 7	0.114 6±0.000 0
	BP-MLL^*	0.472 9±0.000 0	4.791 2±0.000 0	0.685 8±0.000 0	0.114 9±0.000 0
	GLOCAL^*	0.484 4±0.000 0	9.906 2±0.001 4	0.622 7±0.000 0	0.237 4±0.000 0
	QUIRE^**	0.509 3±0.000 2	6.358 8±0.099 2	0.627 2±0.000 4	0.150 7±0.000 1
Entertainment	MAML	0.573 5±0.000 0	4.103 3±0.000 0	0.560 0±0.000 0	0.153 8±0.000 0
	ML-KNN^*	0.544 7±0.000 0	3.635 9±0.003 1	0.600 9±0.000 1	0.137 1±0.000 0
	BP-MLL^*	0.472 7±0.000 0	4.097 7±0.001 3	0.990 5±0.000 0	0.156 2±0.000 0
	GLOCAL^*	0.569 2±0.000 0	5.664 5±0.000 0	0.524 0±0.000 0	0.217 9±0.000 0
	QUIRE^**	0.549 2±0.000 3	4.586 1±0.082 9	0.578 3±0.000 6	0.176 7±0.000 2
Health	MAML	0.699 5±0.000 0	4.689 7±0.000 0	0.373 8±0.000 0	0.085 7±0.000 0
	ML-KNN^*	0.642 9±0.000 0	3.776 7±0.000 3	0.452 5±0.000 0	0.075 6±0.000 0
	BP-MLL^*	0.609 8±0.000 0	4.207 5±0.003 1	0.493 9±0.000 0	0.085 8±0.000 0
	GLOCAL^*	0.648 4±0.000 0	7.040 1±0.000 2	0.413 8±0.000 0	0.146 5±0.000 0
	QUIRE^**	0.680 7±0.000 1	4.701 1±0.059 7	0.398 4±0.000 2	0.089 4±0.000 0
Recreation	MAML	0.481 3±0.000 0	5.740 8±0.000 0	0.651 0±0.000 0	0.216 7±0.000 0
	ML-KNN^*	0.427 5±0.000 0	5.099 4±0.009 4	0.736 6±0.000 1	0.200 8±0.000 0
	BP-MLL^*	0.367 3±0.000 0	5.415 9±0.000 5	0.825 4±0.000 1	0.219 0±0.000 0
	GLOCAL^*	0.488 4±0.000 0	6.811 6±0.001 0	0.620 0±0.000 0	0.261 6±0.000 0
	QUIRE^**	0.492 1±0.000 2	5.708 4±0.024 3	0.641 1±0.000 3	0.213 0±0.000 0
Reference	MAML	0.621 3±0.000 0	5.159 6±0.001 4	0.467 2±0.000 0	0.134 2±0.000 0
	ML-KNN^*	0.574 4±0.000 0	3.780 3±0.005 7	0.553 3±0.000 0	0.102 0±0.000 0
	BP-MLL^*	0.561 1±0.000 0	4.212 7±0.000 5	0.533 0±0.000 0	0.112 5±0.000 0
	GLOCAL^*	0.589 0±0.000 0	6.885 5±0.013 1	0.491 1±0.000 0	0.182 5±0.000 0
	QUIRE^**	0.568 0±0.000 2	5.776 6±0.512 2	0.525 6±0.000 1	0.160 4±0.000 7
Science	MAML	0.435 7±0.000 0	9.326 5±0.000 0	0.679 8±0.000 0	0.185 6±0.000 0
	ML-KNN^*	0.366 7±0.000 2	7.635 5±0.002 2	0.799 6±0.000 4	0.158 7±0.000 0
	BP-MLL^*	0.393 2±0.000 0	7.955 0±0.001 3	0.763 7±0.000 0	0.159 4±0.000 0
	GLOCAL^*	0.428 1±0.000 0	12.310 4±0.000 6	0.669 1±0.000 0	0.254 8±0.000 0
	QUIRE^**	0.423 4±0.000 6	9.617 3±0.131 1	0.702 5±0.001 2	0.192 4±0.000 1
Social	MAML	0.701 3±0.000 0	4.718 3±0.000 0	0.386 3±0.000 0	0.092 7±0.000 0
	ML-KNN^*	0.668 3±0.000 0	3.947 6±0.003 3	0.430 6±0.000 0	0.080 6±0.000 0
	BP-MLL^*	0.590 0±0.000 0	4.259 6±0.000 3	0.575 2±0.000 0	0.084 3±0.000 0
	GLOCAL^*	0.682 0±0.000 0	6.850 7±0.000 4	0.378 0±0.000 0	0.138 6±0.000 0
	QUIRE^**	0.689 6±0.000 0	4.921 4±0.064 9	0.395 7±0.000 1	0.105 4±0.000 1
Society	MAML	0.548 7±0.000 0	7.931 3±0.000 0	0.484 0±0.000 0	0.204 5±0.000 0
	ML-KNN^*	0.529 8±0.000 1	6.159 6±0.000 6	0.558 1±0.000 4	0.160 9±0.000 0
	BP-MLL^*	0.542 4±0.000 0	6.345 8±0.000 9	0.502 0±0.000 0	0.163 6±0.000 0
	GLOCAL^*	0.512 1±0.000 0	9.348 7±0.000 8	0.533 8±0.000 1	0.253 2±0.000 0
	QUIRE^**	0.545 3±0.000 1	7.731 6±0.023 6	0.492 1±0.000 2	0.198 6±0.000 0

Multi-label active learning algorithm for shale gas reservoir prediction

页岩气储层预测的多标签主动学习算法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 29

Related Articles 15

Recommended Articles

Metrics

算法	AveragePrecision	Coverage	RankingLoss	Accuracy
MAML	1.500 0	4.000 0	2.500 0	1.000 0
ML-KNN	2.000 0	1.000 0	1.250 0	2.000 0
BP-MLL	3.750 0	2.875 0	3.750 0	3.500 0
GLOCAL	2.750 0	2.125 0	2.500 0	3.500 0

数据集	量化指标	样本1	样本2	样本3	样本4	样本5	样本6	样本7	样本8	样本9	样本10
Well_1	信息性	0.616 5	0.615 7	0.616 0	0.615 6	0.615 3	0.615 1	0.614 9	0.614 6	0.614 7	0.614 5
	代表性	10.452 7	10.241 6	10.233 6	10.010 9	10.396 2	9.708 2	9.601 6	9.443 9	9.582 8	9.282 9
	丰富性	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0
Well_2	信息性	0.627 6	0.627 5	0.627 4	0.627 1	0.626 9	0.626 7	0.626 7	0.626 5	0.626 3	0.626 2
	代表性	23.034 1	21.597 6	22.309 6	21.898 6	21.663 8	21.311 3	21.521 0	21.285 5	22.080 6	20.615 3
	丰富性	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0
Well_3	信息性	0.627 3	0.627 6	0.627 9	0.628 4	0.628 3	0.627 9	0.628 1	0.627 9	0.627 9	0.627 7
	代表性	29.288 9	31.409 8	29.119 9	27.062 8	31.215 9	28.639 7	30.950 4	28.760 5	30.801 1	29.030 4
	丰富性	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0
Well_4	信息性	0.630 3	0.630 2	0.629 7	0.630 0	0.629 9	0.629 7	0.629 7	0.629 5	0.629 3	0.629 0
	代表性	37.107 3	39.411 0	37.947 1	38.015 3	37.197 5	37.585 8	37.038 1	38.503 6	36.040 5	38.402 3
	丰富性	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0	0.250 0

序号	信息性	代表性	丰富性
1	0.628 3	4.764 6	0.250 0
2	0.628 3	4.753 2	0.250 0
3	0.628 1	4.747 9	0.250 0
4	0.628 0	4.746 2	0.250 0
5	0.628 0	4.743 5	0.250 0
6	0.628 0	4.738 9	0.250 0
7	0.628 0	4.735 0	0.250 0
8	0.628 0	4.734 0	0.250 0
9	0.628 0	4.730 9	0.250 0
10	0.628 0	4.718 0	0.250 0

[1]	Fan MENG, Qunli YANG, Jing HUO, Xinkuan WANG. EraseMTS： iterative active multivariable time series anomaly detection algorithm based on margin anomaly candidate set [J]. Journal of Computer Applications, 2024, 44(5): 1458-1463.
[2]	Guoxiang CHEN, Ziqiang YU, Haoyu ZHAO. Distributed k-nearest neighbor query algorithm for moving objects in dynamic road network [J]. Journal of Computer Applications, 2024, 44(11): 3403-3410.
[3]	Yunyun GAO, Lasheng ZHAO, Qiang ZHANG. Acoustic word embedding model based on Bi-LSTM and convolutional-Transformer [J]. Journal of Computer Applications, 2024, 44(1): 123-128.
[4]	Jinghong WANG, Zhixia ZHOU, Hui WANG, Haokang LI. Attribute network representation learning with dual auto-encoder [J]. Journal of Computer Applications, 2023, 43(8): 2338-2344.
[5]	Jinhui LAI, Zichen XU, Yicheng TU, Guolong TAN. OmegaDB： concurrent computing framework of relational operators for heterogeneous architecture [J]. Journal of Computer Applications, 2023, 43(7): 2017-2025.
[6]	Fangshu CHEN, Wei ZHANG, Xiaoming HU, Yufei ZHANG, Xiankai MENG, Linxiang SHI. Dynamic aggregate nearest neighbor query algorithm in weighted road network space [J]. Journal of Computer Applications, 2023, 43(7): 2026-2033.
[7]	Libin CEN, Jingdong LI, Chunbo LIN, Xiaoling WANG. Approximate query processing approach based on deep autoregressive model [J]. Journal of Computer Applications, 2023, 43(7): 2034-2039.
[8]	Wenhao HU, Jing LUO, Xinhui TU. Pseudo relevance feedback method for dense retrieval [J]. Journal of Computer Applications, 2023, 43(4): 1036-1042.
[9]	Tao QIU, Jianli DING, Xiufeng XIA, Hongmei XI, Peiliang XIE, Qingyi ZHOU. Efficient complex event matching algorithm based on ordered event lists [J]. Journal of Computer Applications, 2023, 43(2): 423-429.
[10]	Yu HONG, Hongchang CHEN, Jianpeng ZHANG, Ruiyang HUANG. Graph summarization algorithm based on node similarity grouping and graph compression [J]. Journal of Computer Applications, 2023, 43(10): 3047-3053.
[11]	MA Yongqiang, CHEN Xiaomeng, YU Ziqiang. Range query algorithm for large scale moving objects in distributed environment [J]. Journal of Computer Applications, 2023, 43(1): 111-121.
[12]	Nanjiang CHENG, Zhenxia YU, Lin CHEN, Hezhe QIAO. Multi-source and multi-label pedestrian attribute recognition based on domain adaptation [J]. Journal of Computer Applications, 2022, 42(8): 2401-2406.
[13]	Wendi HUA, Yuan GAO, Meng LYU, Ping XIE. Research on Bloom filter： a survey [J]. Journal of Computer Applications, 2022, 42(6): 1729-1747.
[14]	Runze LI, Xuejiao SUN. Data stream preference query based on extraction sequence according to temporal condition [J]. Journal of Computer Applications, 2022, 42(3): 724-730.
[15]	Jun FENG, Bingfa WANG, Jiamin LU. Query performance evaluation of distributed resource description framework data management systems [J]. Journal of Computer Applications, 2022, 42(2): 440-448.