AIEngin

MEMBERS
Teacher

陈振宇
ZhenYu Chen

Professor

Teacher

房春荣
Chunrong Fang

Research Assistant

Teacher

冯洋
Yang Feng

Research Assistant

Student

郭安
An Guo

Ph.D. student

Student

尹伊宁
Yining Yin

Ph.D. student

Student

章许帆
Xufan Zhang

Ph.D. student

Student

钟怡
Yi Zhong

Ph.D. student

Student

杨乙霖
Yilin Yang

Ph.D. student

Student

常家鑫
Jiaxin Chang

M.Sc. Student

Student

袁博
Bo Yuan

M.Sc. Student

Student

张松涛
Songtao Zhang

M.Sc. Student

Student

刘子夕
Zixi Liu

M.Sc. Student

Student

顾雪晴
Xueqing Gu

M.Sc. Student

Student

王睿智
Ruizhi Wang

M.Sc. Student

Student

倪烨
Lever Ni

M.Sc. Student

Student

侯韵晗
Yunhan Hou

M.Sc. Student

Student

夏志龙
Zhilong Xia

M.Sc. Student

Student

曹可凡
Kefan Cao

M.Sc. Student

Student

邓靖琦
Jingqi Deng

M.Sc. Student

Student

高新宇
Xinyu Gao

M.Sc. Student

Student

顾逸飞
Yifei Gu

M.Sc. Student

Student

郭子琛
Zichen Guo

M.Sc. Student

Student

李珍鸿
Zhenhong Li

M.Sc. Student

Student

李卓阳
Zhuoyang Li

M.Sc. Student

Student

刘佳玮
Jiawei Liu

M.Sc. Student

Student

吕军
Jun Lyn

M.Sc. Student

Student

王黛薇
Daiwei Wang

M.Sc. Student

Student

徐彬桐
Bintong Xu

M.Sc. Student

Student

许子桓
Zihuan Xu

M.Sc. Student

Student

张晓波
Xiaobo Zhang

M.Sc. Student

Student

张朱佩田
Zhupeitian Zhang

M.Sc. Student

Student

张子杰
Zijie Zhang

M.Sc. Student

Student

李恩铭
Enming Li

M.Sc. Student

PRODUCTS
Quality Inspection Platform for Civil Judgement Documents

Quality Inspection Platform for Civil Judgement Documents

QRcode Based on the knowledge of data quality and information quality assessment, this product divides the data into structured and unstructured according to the format. Based on the actual needs of the scene, the design of assessment indicators is completed from subjective and objective dimensions. For structured information, mainly including tag data which can be extracted by keywords. In this paper, data quality is measured by the commonly used measurement method, combined with the measurement dimension mentioned in the objective information theory. It covers seven categories: delicacy, delay, authenticity, integrity, consistency, readability and accuracy. 15 detailed evaluation indexes are designed according to the requirements of civil judgment documents. For the unstructured information of text type in data, we pay more attention to the quality of semantic and pragmatic information contained in it. With the help of supervised machine learning and deep learning technology, we take the large number of data accumulated in the system as positive training samples with high information quality to simulate the artificial information quality evaluation process.

Judicial Text Data Automatic Generation System

Judicial Text Data Automatic Generation System

QRcode We design an automated system for generating judicial text data and implements it, including training and testing data generation module. The training data generation module is used to provide data augmentation services for the judicial deep learning model, increasing the high-quality judicial text training data and improving the prediction accuracy of the model. We design two generation methods based on rule and Variational Auto-encoder. Combining with the characteristics of judicial text, we propose an augmentation method for judicial text in rule-based generation. The generation method based on Variational Auto-encoder applies the Variational Auto-encoder in the field of text generation, learning the low-dimensional features of judicial text, adding noise and reconstructing new text with similar distribution. We conducted extensive experiments to prove that the two training data generation methods provided by the system are effective, and can increase the accuracy of the crime prediction TextCNN model from 81.91 % to 83.31 %.

Model Evaluation System Driven by Judicial Data Quality

Model Evaluation System Driven by Judicial Data Quality

QRcode After a comprehensive analysis of the background, current situation and system requirements, we design and implement a model evaluation system driven by judicial data quality, which is mainly divided into data interaction, document analysis, quality detection and model evaluation modules. Through this system, users can select or upload machine learning models, select the built-in documents or upload the data set of judgment documents, carry out judicial intelligence classification tasks such as law articles prediction, and calculate the model evaluation index. Among them, KNN, SVM and Naive Bayes are the basic machine learning models built in the system, and the model evaluation indexes used in the system are Accuracy, F1 score, KS value and PSI. For the built-in or uploaded judgment documents, the system will automatically perform field parsing, label classification and feature extraction, and generate quality inspection reports. The quality attributes include interpretability, relevancy, accuracy and consistency.

System for Testing Judicial Case Screening System

System for Testing Judicial Case Screening System

QRcode The main work of this product is to set up a series of multi-dimensional case screening test criteria and to build a highly functional testing platform for case screening system. This system conducts the test of case screening system in two aspects: the model level and the system level. The relevant machine learning models for the case screening system are evaluated by basic and extensive metrics based on the specific data set. Multi-dimensional similarity metrics test the system-level interfaces of the case screening system. The testing system eventually works well in the form of a web application. The user can access the system through a browser to manage data set and model files, conduct testing tasks automatically to generate corresponding testing results. This testing system could be highly practical for developers and testers in the legal field.

PROJECTS
  1. National natural science foundation of China (Key Program):Software testing technology for security-critical deep learning system(61832009), 2019-2023
    国家自然科学基金项目(重点项目):面向安全攸关深度学习系统的软件测试技术(61832009), 2019-2023

  2. National natural science foundation of China (General Program):Research on detection and repair technology of software numerical stability(61772260),2018-2021
    国家自然科学基金项目(面上项目):软件数值稳定性的检测与修复技术研究(61772260), 2018-2021

  3. National natural science foundation of China (Major Program): Convergence feedback mechanism and support platform for massive information in software development (61690201), 2017-2021
    国家自然科学基金(重大项目):软件开发中海量信息的融合反馈机制与支撑平台(61690201),2017-2021

  4. National key R&D program of China:Research and development of people's court business and data standards, construction of basic judicial service database and case screening and evaluation model (2016YFC0800805), 2016-2020
    国家重点研发计划课题:人民法院业务和数据标准研究和制定、司法基本服务库和案例筛选评估模型构建(2016YFC0800805)

  5. National program on key basic research project (973 Program): Research on the construction and quality assurance of security critical software systems (2014CB340700), 2014-2018
    国家重点基础研究发展计划(973计划):安全攸关软件系统的构造与质量保障方法研究(2014CB340700),2014-2018

  6. National natural science foundation of China (Projects of international cooperation and exchanges): Stability analysis of numerical programs based on transmutation relation metamorphic relations (61311130424), 2013
    国家自然科学基金项目(国际合作交流项目):基于蜕变关系的数值程序稳定性分析(61311130424), 2013

  7. Supported by projects of international cooperation and exchanges NSFC:Research on software engineering recommendation technology based on developer social network (61211120438), 2012
    国家自然科学基金项目(国际合作交流项目):基于开发者社会化网络的软件工程推荐技术研究(61211120438), 2012

  8. National natural science foundation of China:Stability analysis for numerical programs (61211130035). 2012-2012
    国家自然科学基金:数值计算程序的稳定性分析(61211130035),2012-2012

  9. National natural science foundation of China:Reliability testing for numerical programs (61111130187). 2011-2011
    国家自然科学基金:数值计算程序的可靠性测试(61111130187),2011-2011

  10. National natural science foundation of China:Software testing techniques in scientific computing(61011130171), 2010
    国家自然科学基金:科学计算中的软件测试技术(61011130171),2010

PUBLICATIONS

2020

  1. Yang Feng, Qingkai Shi, Xinyu Gao, Jun Wan, Chunrong Fang and Zhenyu Chen. DeepGini: Prioritizing Massive Tests to Enhance the Robustness of Deep Neuron Networks ISSTA 2020

2019

  1. Weiqin Zou, David Lo, Pavneet Singh Kochhar, Xuan-Bach Dinh Le, Xin Xia, Yang Feng, Zhenyu Chen and Baowen Xu. Smart contract development: challenges and opportunities. IEEE Transactions on Software Engineering
  2. Tianxing He, Shengcheng Yu, Ziyuan Wang, Jieqiong Li and Zhenyu Chen. From data quality to model quality: an exploratory study on Deep Learning. Internetware 2019
  3. Cheng Lei, Benlin Hu, Dong Wang, Shu Zhang and Zhenyu Chen. A preliminary study on data augmentation of Deep Learning for image classification. Internetware 2019
  4. Jiawei Cao, Xingya Wang, Zixin Li, Qiqi Gu and Zhenyu Chen. The evolution of open-source blockchain systems: an empirical study. Internetware 2019
  5. Haoran Wu, Xingya Wang, Jiehui Xu, Weiqin Zou, Lingming Zhang, Zhenyu Chen. Mutation testing for ethereum smart contract. arXiv.1908.03707
  6. Xufan Zhang, Ziyue Yin, Yang Feng, Qingkai Shi, Jia Liu, Zhenyu Chen. NeuralVis: visualizing and interpreting deep learning models. ASE 2019-Demo
  7. Qingkai Shi, Jun Wan, Yang Feng, Chunrong Fang, Zhenyu Chen. DeepGini: prioritizing massive tests to reduce labeling cost. arXiv 1903.00661
  8. Qiqi Gu, Weilin Cai, Shengcheng Yu, Zhenyu Chen. Judicial image quality assessment based on deep learning: an exploratory study. QRS 2019
  9. Weiqin Zou, Weiqiang Zhang, Xin Xia, Reid Holmes, Zhenyu Chen. Branch use in practice--a large-scale empirical study of 2,923 projects on GitHub. QRS 2019
  10. Dong Wang, Ziyuan Wang, Chunrong Fang, Yanshan Chen, Zhenyu Chen. DeepPath: Path-driven testing criteria for Deep Neural Networks. AITest 2019
  11. Weiqin Zou, Jifeng Xuan, Xiaoyuan Xie, Zhenyu Chen, Baowen Xu. How does code style inconsistency affect pull request integration? An exploratory study on 117 GitHub projects. Empirical Software Engineering.
  12. Xie Wang, Huaijin Wang, Zhendong Su, Enyi Tang, Xin Chen, Weijun Shen, Zhenyu Chen, Linzhang Wang, Xianpei Zhang, Xuandong Li. Global optimization of numerical programs via prioritized stochastic algebraic transformations. ICSE 2019

2018

  1. Weijun Shen, Jun Wan, Zhenyu Chen. MuNN: Mutation analysis of neural networks. QRS-C 2018
  2. Tieke He, Hao Lian, Zemin Qin, Zhenyu Chen, Bin Luo. PTM: A topic model for the inferring of the penalty. Journal of Computer Science and Technology
  3. Yang Feng, James A. Jones, Zhenyu Chen, Chunrong Fang. An empirical study on software failure classification with multi-label and problem-transformation techniques. ICST 2018, pp. 320-330

2017

  1. Enyi Tang, Xiangyu Zhang, Norbert Th. Müller, Zhenyu Chen, Xuandong Li. Software numerical Instability detection and diagnosis by combining stochastic and infinite-precision testing[Chinese Brief] IEEE Transactions on Software Engineering. 43(10): 975-994

2016

  1. Tieke He, Hongzhi Yin, Zhenyu Chen, Xiaofang Zhou, Shazia Sadiq, Bin Luo. A spatial-temporal topic model for the semantic annotation of POIs in LBSNs ACM Transactions on Intelligent Systems and Technology

Before the 2015

  1. Yabin Wang, Ruizhi Gao, Zhenyu Chen, Eric Wong, Bin Luo. WAS: a weighted attribute-based strategy for cluster test selection. Journal of Systems and Software
  2. Shuai Wei, Enyi Tang, Tianyu Liu, Norbert Mueller, Zhenyu Chen. Automatic numerical analysis based on infinite-precision arithmetic. SERE 2014, pp. 216-224
  3. Xin Xia, Feng Yang, David Lo, Zhenyu Chen and Xinyu Wang. Towards more accurate multi-label software behavior learning.[Chinese Brief] CSMR/WCRE 2014, pp. 134-143
  4. Jia Liu, Weiqing Wang, Zhenyu Chen, Xingzhong Du, Qi Qi. A novel user-based collaborative filtering method by inferring tag ratings. ACM Applied Computing Review
  5. Yang Feng, Zhenyu Chen. Multi-label software behavior learning. ICSE 2012, pp. 1305-1308
  6. Zhenyu Chen, T.Y. Chen, Baowen Xu. A revisit of fault class hierarchies in general boolean specifications. ACM Transactions on Software Engineering and Methodology, 20(3)
  7. Zhenyu Chen, Baowen Xu, Decheng Ding. The complexity results of variable minimal formulas. Chinese Science Bulletin, 55(18):1957-1960
  8. Changbin Ji, Zhenyu Chen, Baowen Xu, Zhihong Zhao. A novel method of mutation clustering based on domain analysis. SEKE 2009, pp. 422-425
TOP