ABSTRACT
In modern times, different software tools are used in facilities maintenance to record maintenance problems as tickets. When these tickets are resolved, technicians also document the steps they took to fix the issue as resolution notes. The increasing use of these systems helps us gather a lot of information about past tickets and their solutions. Many times, similar tickets are created that can be solved by following similar steps used before. This abundance of data makes it easier to transfer knowledge by recommending resolution steps to solve a new issue based on the solutions applied to similar tickets in the past. The prompt and accurate resolution can help to minimize downtime and maximize productivity. Traditional methods of resolution recommendation for facilities maintenance tickets rely on manual analysis of historical data and predefined rules. These methods are time-consuming and often yield suboptimal results. In this paper, we propose a novel approach for resolution steps recommendation using deep learning techniques. We first generate embeddings of tickets using a fine-tuned sentence transformer model and employ FAISS (Facebook AI Similarity Search) [9] to speed up the process of finding the most similar tickets. Our proposed resolution generator architecture first combines these similar tickets and then passes them to a summarization layer which clubs these resolutions into one, by removing redundancies and only considering actionable sentences. This summarized resolution is then passed to a text generation network which then converts these sentences into a series of steps that technicians can take to solve the current problem. Our approach was evaluated on a real-world facilities maintenance dataset, and the results show that our proposed method outperforms existing approaches.
- Shipra Agrawal, Supratim Deb, K. V. M. Naidu, and Rajeev Rastogi. 2007. Efficient Detection of Distributed Constraint Violations. In 2007 IEEE 23rd International Conference on Data Engineering. 1320–1324. https://doi.org/10.1109/ICDE.2007.369002Google ScholarCross Ref
- David M. Blei, Andrew Y. Ng, and Michael I. Jordan. 2003. Latent Dirichlet Allocation. J. Mach. Learn. Res. 3, null (mar 2003), 993–1022.Google Scholar
- Chenhan Cao, Xiaoyu Fang, Bingqing Luo, and Bin Xia. 2023. SSR-TA: Sequence to Sequence based expert recurrent recommendation for ticket automation. ArXiv abs/2301.12612 (2023).Google Scholar
- Jaime Carbonell and Jade Stewart. 1999. The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries. SIGIR Forum (ACM Special Interest Group on Information Retrieval) (06 1999). https://doi.org/10.1145/290941.291025Google ScholarDigital Library
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. http://arxiv.org/abs/1810.04805 cite arxiv:1810.04805Comment: 13 pages.Google Scholar
- Cristian Estan, Stefan Savage, and George Varghese. 2003. Automatically Inferring Patterns of Resource Consumption in Network Traffic. In Proceedings of the 2003 Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (Karlsruhe, Germany) (SIGCOMM ’03). Association for Computing Machinery, New York, NY, USA, 137–148. https://doi.org/10.1145/863955.863972Google ScholarDigital Library
- Monika Gupta, Allahbaksh Asadullah, Srinivas Padmanabhuni, and Alexander Serebrenik. 2018. Reducing User Input Requests to Improve IT Support Ticket Resolution Process. Empirical Softw. Engg. 23, 3 (jun 2018), 1664–1703. https://doi.org/10.1007/s10664-017-9532-2Google ScholarDigital Library
- Ray Han and Aixin Sun. 2020. DeepRouting: A Deep Neural Network Approach for Ticket Routing in Expert Network. 386–393. https://doi.org/10.1109/SCC49832.2020.00057Google ScholarCross Ref
- J. Johnson, M. Douze, and H. Jegou. 2021. Billion-Scale Similarity Search with GPUs. IEEE Transactions on Big Data 7, 03 (jul 2021), 535–547. https://doi.org/10.1109/TBDATA.2019.2921572Google ScholarCross Ref
- Mahnaz Koupaee and William Yang Wang. 2018. WikiHow: A Large Scale Text Summarization Dataset. ArXiv abs/1810.09305 (2018).Google Scholar
- Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 7871–7880. https://doi.org/10.18653/v1/2020.acl-main.703Google ScholarCross Ref
- Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74–81. https://aclanthology.org/W04-1013Google Scholar
- Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. http://arxiv.org/abs/1907.11692 cite arxiv:1907.11692.Google Scholar
- Steven McCanne and Van Jacobson. 1993. The BSD Packet Filter: A New Architecture for User-Level Packet Capture. In Proceedings of the USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993 Conference Proceedings (San Diego, California) (USENIX’93). USENIX Association, USA, 2.Google ScholarDigital Library
- Shashi Narayan, Shay B. Cohen, and Mirella Lapata. 2018. Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, 1797–1807. https://doi.org/10.18653/v1/D18-1206Google ScholarCross Ref
- David Palacios, César Morillas, Manuel Garcés, and Pablo Tapia. 2019. Big data-empowered system for automatic trouble ticket generation in IoT networks. In 2019 IEEE 2nd 5G World Forum (5GWF). 63–68. https://doi.org/10.1109/5GWF.2019.8911636Google ScholarCross Ref
- Rahul Potharaju, Navendu Jain, and Cristina Nita-Rotaru. 2013. Juggling the Jigsaw: Towards Automated Problem Inference from Network Trouble Tickets. In Proceedings of the 10th USENIX Conference on Networked Systems Design and Implementation (Lombard, IL) (nsdi’13). USENIX Association, USA, 127–142.Google ScholarDigital Library
- Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. J. Mach. Learn. Res. 21, 1, Article 140 (jan 2020), 67 pages.Google Scholar
- Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100,000+ Questions for Machine Comprehension of Text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Austin, Texas, 2383–2392. https://doi.org/10.18653/v1/D16-1264Google ScholarCross Ref
- Marcus J. Ranum, Kent Landfield, Michael T. Stolarchuk, Mark Sienkiewicz, Andrew Lambeth, and Eric Wall. 1997. Implementing a Generalized Tool for Network Monitoring. In Proceedings of the 11th Conference on Systems Administration(LISA ’97). USENIX Association, USA, 1–8.Google ScholarDigital Library
- Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. ArXiv abs/1910.01108 (2019).Google Scholar
- Qihong Shao, yi Chen, Shu Tao, Xifeng Yan, and Nikos Anerousis. 2008. EasyTicket: A ticket routing recommendation engine for enterprise problem resolution. PVLDB 1 (08 2008), 1436–1439.Google Scholar
- Dingding Wang, Tao Li, Shenghuo Zhu, and Yihong Gong. 2011. iHelp: An Intelligent Online Helpdesk System. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 41, 1 (2011), 173–182. https://doi.org/10.1109/TSMCB.2010.2049352Google ScholarDigital Library
- Martin Weisser. 2016. SPAADIA (Speech Act Annotated Dialogues) Corpus. (Nov. 2016). http://martinweisser.org/corpora_site/dialogue_corpora.htmlGoogle Scholar
- Jian Xu, Hang Zhang, Wubai Zhou, Rouying He, and Tao Li. 2018. Signature Based Trouble Ticket Classification. Future Gener. Comput. Syst. 78, P1 (jan 2018), 41–58. https://doi.org/10.1016/j.future.2017.07.054Google ScholarDigital Library
- Kuai Xu, Zhi-Li Zhang, and Supratik Bhattacharyya. 2005. Profiling Internet Backbone Traffic: Behavior Models and Applications. SIGCOMM Comput. Commun. Rev. 35, 4 (aug 2005), 169–180. https://doi.org/10.1145/1090191.1080112Google ScholarDigital Library
- Chunqiu Zeng, Wubai Zhou, Tao Li, Larisa Shwartz, and Genady Ya Grabarnik. 2017. Knowledge Guided Hierarchical Multi-Label Classification Over Ticket Data. IEEE Trans. on Netw. and Serv. Manag. 14, 2 (jun 2017), 246–260. https://doi.org/10.1109/TNSM.2017.2668363Google ScholarDigital Library
- Wubai Zhou, Liang Tang, Chunqiu Zeng, Tao Li, Larisa Shwartz, and Genady Ya. Grabarnik. 2016. Resolution Recommendation for Event Tickets in Service Management. IEEE Transactions on Network and Service Management 13, 4 (2016), 954–967. https://doi.org/10.1109/TNSM.2016.2587807Google ScholarDigital Library
- Wubai Zhou, Wei Xue, Ramesh Baral, Qing Wang, Chunqiu Zeng, Tao Li, Jian Xu, Zheng Liu, Larisa Shwartz, and Genady Ya. Grabarnik. 2017. STAR: A System for Ticket Analysis and Resolution. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Halifax, NS, Canada) (KDD ’17). Association for Computing Machinery, New York, NY, USA, 2181–2190. https://doi.org/10.1145/3097983.3098190Google ScholarDigital Library
Index Terms
- SToRM: Smart ticket resolution steps recommendation in facilities management
Recommendations
Generative models for ticket resolution in expert networks
KDD '10: Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data miningTicket resolution is a critical, yet challenging, aspect of the delivery of IT services. A large service provider needs to handle, on a daily basis, thousands of tickets that report various types of problems. Many of those tickets bounce among multiple ...
Expert recommendation for trouble ticket routing
AbstractA trouble ticket is an important information carrier in system maintenance, which records problem symptoms, the resolving process, and resolutions. A critical challenge for the ticket management system is how to quickly assign a proper ...
STAR: A System for Ticket Analysis and Resolution
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningIn large scale and complex IT service environments, a problematic incident is logged as a ticket and contains the ticket summary (system status and problem description). The system administrators log the step-wise resolution description when such ...
Comments