Bing An
Research Subjects
Research Interests
Bing An has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Honggang Wang
Big Data Center of State Grid of China, Beijing 100052, P. R. China
1 shared publication - Jiasong Chen
School of Informatics, Xiamen University, Xiamen 361005, Fujian, P. R. China
1 shared publication - Ke Dong
Big Data Center, State Grid Corporation of China, China
1 shared publication - Shenglong Liu
Big Data Center of State Grid of China, Beijing 100052, P. R. China
1 shared publication - Shuo Cui
Big Data Center, State Grid Corporation of China, China
1 shared publication - Weining Shi
School of Informatics, Xiamen University, Xiamen 361005, Fujian, P. R. China
1 shared publication
Latest Publications
- 30 September 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of High Speed Electronics and Systems
- Vol. 34 (03)
TUHTC: Two-Stage Unsupervised Hierarchical Text Classification of Power Grid Data Assets
Data classification and grading provide the foundation and guidance for information security management, and the construction of data security system is inseparable from this cornerstone. In recent years, the high-frequency use and complex interactions of power grid data have made the data security management increasingly in need of automated, efficient and credible data classification and grading. The characteristics of power grid data assets, such as sensitivity, complexity and multi-dimensions, exacerbate the challenges of the task. Due to the scattered businesses and complex categories of existing data, experts in a single field have limited knowledge and cannot label all data in all the fields, which also makes data labeling very difficult. To address the aforementioned issues, we present a two-stage unsupervised methodology for hierarchical text classification (TUHTC). Initially, we leverage the semantic information inherent in hierarchical labels for data augmentation of annotated datasets. Subsequently, we enhance the semantic embedding of labels to facilitate the effective classification of data. We conducted experimental verification using database information in authentic business scenarios, thereby validating the efficacy of the proposed methodology.
- 30 September 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of High Speed Electronics and Systems
- Vol. 34 (03)
TUHTC: Two-Stage Unsupervised Hierarchical Text Classification of Power Grid Data Assets
Data classification and grading provide the foundation and guidance for information security management, and the construction of data security system is inseparable from this cornerstone. In recent years, the high-frequency use and complex interactions of power grid data have made the data security management increasingly in need of automated, efficient and credible data classification and grading. The characteristics of power grid data assets, such as sensitivity, complexity and multi-dimensions, exacerbate the challenges of the task. Due to the scattered businesses and complex categories of existing data, experts in a single field have limited knowledge and cannot label all data in all the fields, which also makes data labeling very difficult. To address the aforementioned issues, we present a two-stage unsupervised methodology for hierarchical text classification (TUHTC). Initially, we leverage the semantic information inherent in hierarchical labels for data augmentation of annotated datasets. Subsequently, we enhance the semantic embedding of labels to facilitate the effective classification of data. We conducted experimental verification using database information in authentic business scenarios, thereby validating the efficacy of the proposed methodology.
- Open Access
- 25 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-9
The Topologies Exploration on the Knowledge Graph of Alarm Correlation by a Community-based Link Prediction Model
Alarm correlation refers to identifying the correlation between alarms in the system through technical means, accurately categorizing alarms caused by the same problem, and realizing root cause location. Accurate and efficient alarm association identification technology is of great practical significance to accelerate system troubleshooting and ensure the safety of large systems. This paper innovatively proposes a link prediction model considering community similarity and resource allocation between nodes. Based on the application scenario of alarm association knowledge graph, the key innovative technologies and innovation paths in this field are mined and identified, and the potential technological development trends are predicted in the future. Based on the information of 431 invention patents related to alarm correlation in China from 2006 to 2022 and 535 papers from 1998 to 2023, the alarm correlation knowledge map is constructed, and key technologies are identified by topology analysis method. An improved link prediction method is proposed combining community discovery method and resource allocation index, and the potential innovation path of alarm association field is predicted based on the improved index, so as to comprehensively analyze the application status and development prospect of alarm association technology. It is found that technologies such as multilevel classification and causal knowledge will produce innovative results in the fields of alarm clustering and intrusion detection. The research will provide reference for technology prediction in the field of knowledge graph and scientific research innovation of network security personnel.
- 25 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessThe Topologies Exploration on the Knowledge Graph of Alarm Correlation by a Community-based Link Prediction Model
Alarm correlation refers to identifying the correlation between alarms in the system through technical means, accurately categorizing alarms caused by the same problem, and realizing root cause location. Accurate and efficient alarm association identification technology is of great practical significance to accelerate system troubleshooting and ensure the safety of large systems. This paper innovatively proposes a link prediction model considering community similarity and resource allocation between nodes. Based on the application scenario of alarm association knowledge graph, the key innovative technologies and innovation paths in this field are mined and identified, and the potential technological development trends are predicted in the future. Based on the information of 431 invention patents related to alarm correlation in China from 2006 to 2022 and 535 papers from 1998 to 2023, the alarm correlation knowledge map is constructed, and key technologies are identified by topology analysis method. An improved link prediction method is proposed combining community discovery method and resource allocation index, and the potential innovation path of alarm association field is predicted based on the improved index, so as to comprehensively analyze the application status and development prospect of alarm association technology. It is found that technologies such as multilevel classification and causal knowledge will produce innovative results in the fields of alarm clustering and intrusion detection. The research will provide reference for technology prediction in the field of knowledge graph and scientific research innovation of network security personnel.