Efficient customer incident triage via linking with system incidents

Gu, Jiazhen; Wen, Jiaqi; Wang, Zijian; Zhao, Pu; Luo, Chuan; Kang, Yu; Zhou, Yangfan; Li, Yang; Sun, Jeffrey; Xu, Zhangwei; Qiao, Bo; Li, Liqun; Lin, Qingwei; Zhang, Dongmei

doi:10.1145/3368089.3417061

Cited by 14 publications

(6 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LinkCM. LinkCM [51] is proposed to facilitate the triage of a customer-reported alert by matching it with an alert of cloud systems. LinkCM learns the correlation by purely fusing the titles between the report and alert via a decomposable attention mechanism and transfer learning.…”

Section: Methodsmentioning

confidence: 99%

“…2) RQ2 The Effectiveness of ticket-event correlation: In this RQ, the focus is on evaluating the accuracy of the ticket-event correlation step of iPACK, i.e., the proposed attentive interaction Network (AIN). The performance of AIN is compared with LinkCM [51] and four popular machine learning algorithms: LR (logistic regression), SVM (support vector machine), RF (random forest), and LightGBM (light gradient boosting machine). Additionally, the contribution of the attentive feature interaction component to AIN is studied.…”

Section: Experimental Details 1) Rq1mentioning

confidence: 99%

See 1 more Smart Citation

Incident-aware Duplicate Ticket Aggregation for Cloud Systems

Liu¹,

He²,

Chen³

et al. 2023

Preprint

View full text Add to dashboard Cite

In cloud systems, incidents are potential threats to customer satisfaction and business revenue. When customers are affected by incidents, they often request customer support service (CSS) from the cloud provider by submitting a support ticket. Many tickets could be duplicate as they are reported in a distributed and uncoordinated manner. Thus, aggregating such duplicate tickets is essential for efficient ticket management. Previous studies mainly rely on tickets' textual similarity to detect duplication; however, duplicate tickets in a cloud system could carry semantically different descriptions due to the complex service dependency of the cloud system. To tackle this problem, we propose iPACK, an incident-aware method for aggregating duplicate tickets by fusing the failure information between the customer side (i.e., tickets) and the cloud side (i.e., incidents). We extensively evaluate iPACK on three datasets collected from the production environment of a large-scale cloud platform, Azure. The experimental results show that iPACK can precisely and comprehensively aggregate duplicate tickets, achieving an F1 score of 0.871∼0.935 and outperforming state-of-the-art methods by 12.4%∼31.2%.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Experimental Details 1) Rq1mentioning

confidence: 99%

Incident-aware Duplicate Ticket Aggregation for Cloud Systems

Liu¹,

He²,

Chen³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Murphy et al report that as the software systems are getting bigger, the issue triaging takes increasingly larger amount time (Murphy and Cubranic 2004). Therefore, many approaches have been proposed in the literature to automate the process of issue triaging (Ahsan et al 2009;Alenezi et al 2013;Anvik and Murphy 2011;Podgurski et al 2003;Anvik et al 2006;Baysal et al 2009;Jeong et al 2009;Bhattacharya et al 2012;Lin et al 2009;Helming et al 2010;Park et al 2011;Xia et al 2013;Xie et al 2012;Dedík and Rossi 2016;Jonsson et al 2016;Lee et al 2017;Chen et al 2019;Gu et al 2020;Zhang 2020;Sajedi-Badashian et al 2020;Aung et al 2021;Chmielowski et al 2021).…”

Section: Related Workmentioning

confidence: 99%

Using Screenshot Attachments in Issue Reports for Triaging

Aktaş¹,

Yılmaz

2022

Empir Software Eng

View full text Add to dashboard Cite

In previous work, we deployed IssueTAG, which uses the texts present in the one-line summary and the description fields of the issue reports to automatically assign them to the stakeholders, who are responsible for resolving the reported issues. Since its deployment on January 12, 2018 at Softtech, i.e., the software subsidiary of the largest private bank in Turkey, IssueTAG has made a total of 301, 752 assignments (as of N ovember 2021). One observation we make is that a large fraction of the issue reports submitted to Softtech has screenshot attachments and, in the presence of such attachments, the reports often convey less information in their one-line summary and the description fields, which tends to reduce the assignment accuracy. In this work, we use the screenshot attachments as an additional source of information to further improve the assignment accuracy, which (to the best of our knowledge) has not been studied before in this context. In particular, we develop a number of multi-source (using both the issue reports and the screenshot attachments) and single-source assignment models (using either the issue reports or the screenshot attachments) and empirically evaluate them on real issue reports. In the experiments, compared to the currently deployed singlesource model in the field, the best multi-source model developed in this work, significantly (both in the practical and statistical sense) improved the assignment accuracy for the issue reports with screenshot attachments from 0.843 to 0.858 at acceptable overhead costs -a result strongly supporting our basic hypothesis.

show abstract

“…Some work focuses on incident triage in large-scale online systems [6] [7] [11]. Chen et al [6] perform a comprehensive empirical study of incident triage on 20 real-world, largescale online service systems.…”

Section: A Incident Triagementioning

confidence: 99%

Fast Outage Analysis of Large-Scale Production Clouds with Service Correlation Mining

Wang

et al. 2021

2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE)

Self Cite

View full text Add to dashboard Cite

Cloud-based services are surging into popularity in recent years. However, outages, i.e., severe incidents that always impact multiple services, can dramatically affect user experience and incur severe economic losses. Locating the rootcause service, i.e., the service that contains the root cause of the outage, is a crucial step to mitigate the impact of the outage. In current industrial practice, this is generally performed in a bootstrap manner and largely depends on human efforts: the service that directly causes the outage is identified first, and the suspected root cause is traced back manually from service to service during diagnosis until the actual root cause is found. Unfortunately, production cloud systems typically contain a large number of interdependent services. Such a manual root cause analysis is often time-consuming and labor-intensive. In this work, we propose COT, the first outage triage approach that considers the global view of service correlations. COT mines the correlations among services from outage diagnosis data. After learning from historical outages, COT can infer the root cause of emerging ones accurately. We implement COT and evaluate it on a real-world dataset containing one year of data collected from Microsoft Azure, one of the representative cloud computing platforms in the world. Our experimental results show that COT can reach a triage accuracy of 82.1%~83.5%, which outperforms the state-of-the-art triage approach by 28.0%~29.7%.Index Terms-cloud computing, root cause analysis, outage triage, machine learning I. I n t r o d u c t io nCloud computing has become increasingly popular in recent years. Many companies have migrated their services to various cloud computing platforms, e.g., Microsoft Azure, Amazon AWS, and Google Cloud. These platforms provide a variety of services to millions of users from all over the world every day. Availability is one of the most critical concern to cloud computing platforms, influencing the user experience and the cloud providers' revenue significantly.Although tremendous efforts have been devoted to main taining high service availability [1]-[4], cloud computing plat forms still encounter many incidents, i.e., unplanned interrup tions of the services. These incidents, especially outages (i.e.,

show abstract

Efficient customer incident triage via linking with system incidents

Cited by 14 publications

References 46 publications

Incident-aware Duplicate Ticket Aggregation for Cloud Systems

Incident-aware Duplicate Ticket Aggregation for Cloud Systems

Using Screenshot Attachments in Issue Reports for Triaging

Fast Outage Analysis of Large-Scale Production Clouds with Service Correlation Mining

Contact Info

Product

Resources

About