Resolution Recommendation for Event Tickets in Service Management

Zhou, Wubai; Tang, Liang; Zeng, Chunqiu; Li, Tao; Shwartz, Larisa; Grabarnik, Genady Ya.

doi:10.1109/tnsm.2016.2587807

Cited by 33 publications

(19 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An recommendation generation algorithm for ticket management services was presented in the work of Zhou et al, which generates recommendation based on the similarity between the earlier tickets and current one with the resolution generated earlier. The method uses the KNN algorithm to measure the similarity and to reduce the false ratio.…”

Section: Related Workmentioning

confidence: 99%

Multilevel Petri net‐based ticket assignment and IT management for improved IT organization support

Mukunthan

Selvakumar

2019

Concurrency and Computation

View full text Add to dashboard Cite

Summary The problem of incident management has been well studied and the ticketing has been handled by various approaches. Still, the methods suffer to produce higher growth in IT service management towards the development of IT organizations. To solve this issue, a multilevel Petri net‐based ticket assignment scheme has been proposed. The method maintains different services in different levels. According to the ticket identified, the ticket has been assigned through number of services in different levels. At each level, the status of service and ticket has been collected and maintained. Similarly, the number of ticket and service states has been generated. For each level and for each service, the method computes the popularity based on their previous ticket management support measure and the error rate. Finally, a single set of services has been selected for the assignment of ticket. At the selected composite service, the six sigma has been applied and validated for the quality of output. Based on the error rate identified, the process has been iterated until an optimal service has been identified. The proposed algorithm identifies an efficient set of services to be assigned for the ticket and improves the performance of ticket management. In addition, the proposed algorithm improves performance of organizational support greatly.

show abstract

Section: Related Workmentioning

confidence: 99%

Multilevel Petri net‐based ticket assignment and IT management for improved IT organization support

Mukunthan

Selvakumar

2019

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…．ChangeFinder (9) では，AR (Auto Regression)モデルにより時系列を参照されたい．また，多様なネットワークデータを対象にした研究として，データ間の関係性を分析する NICE (17) や，NICE の拡張版である異常検知技術 SYNERGY (18) などもある．本章の最後に，上記で述べた各技術にネットワークデータを入力する際の前処理に関して述べる．トラヒック量の時系列データといった数値データに関しては，時間粒度の設定が重要になる．テキストログについてはルールベースの手法を適用するのが主流であると考えられる．一方で時系列モデルや関係性モデルでテキストログを利用するには，異常検知に有用な情報を集約しつつ数値ベクトル化する必要がある．筆者らの研究グループでは，これまでに，テキストログの自動分類技術 (19) を提案してきた．この技術を用いて，テキストログを ID 化して各 ID の出現回数を用いて数値化し，AE を用いた異常検知技術 (14) への入力としている．また統合ログ分析技術 (12) (21) や，イベント間のラグ (時間的な依存関係) を分析する方法 (22) 等が提案されている．一方，生成モデルベースの手法として，Shrink (23) では，ネットワーク構成情報などを基に，図 5 の (24) や，ネットワークの性能指標間の因果グラフをデータから推定して，異常の要因となるイベントを特定する CauseInfer (25) (45) ，ルールベースの単語マッチング (46) ，トピックモデルに基づく方法 (47) など様々な機械学習に基づく手法が提案されている．また，復旧作業時間を短縮するための，発生した事象に対応した復旧作業の把握手法としては，トピックモデル (48) や深層学習 (49) によって関連したトラブルチケットを提示する手法や，解決可能な問合せ先の探索手法 (50)…”

unclassified

Application of AI to Network Operation

Kawahara¹,

Watanabe²,

Harada³

et al. 2018

IEICE Commun. Mag.

View full text Add to dashboard Cite

“…One of the most prominent topic modeling algorithm is Latent Dirichlet Allocation (LDA) [40], used for ticket modeling in [16,27,[41][42][43]. It models each ticket as a probability distribution of topics; each topic is a mixture of multiple words.…”

Section: Extract Information From Ticketsmentioning

confidence: 99%

“…The results of using LDA-based approaches are data set and application dependent. For example, [41] used topic number 300 for its experiments and 100 topics are used for query expansion to support advanced search applications by Deng et al [42]. A trained LDA model can be used to extract features from tickets.…”

Section: Extract Information From Ticketsmentioning

confidence: 99%

“…From a ticket, extracting software mentions and correctly linking them to the product and version would benefit ticket routing as well as other ticket processing application. These include automatic ticket analysis and understanding [15,57], advanced ticket search [42] and classification [9], root cause analysis [19], resolution recommendation [37,41,52] , and in-domain knowledge-base construction [2,51]. 60…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mining software support tickets for assistive routing

Han¹

View full text Add to dashboard Cite

for sparing the time for discussions and reviewing my manuscripts. During my years studying in Nanyang Technological University of Singapore, I have the pleasure getting acquainted with many awesome people. Many of them are established researchers working in different fields, I wish them all the success and happiness in life.At SAP, I would like to thank my managers Steve Lee, Dr. Daniel Dahlmeier, and Dr. Chen Wang, for the careers guidance. A special regard to my first mentor Naveen Nandan, who introduced me to the company, and to Dr. Mohammad Akbari for his advice in research. For this special project on support tickets, I am always grateful to Andreas Heckmann, who envisioned an intelligent support application, and Christian Boos, who recommended me for the assignment. Since the beginning of the project, I worked closely with Project Manager Wilhelm Juette to form a productive team, his mentorship and friendship are always appreciated. Moreover, I wish to thank David Molinera, Kazuhiro Inaba and Ka Hian Goh for their hands-on support in the experiments.Most importantly, no word can describe my love and appreciation to my family, who are always there for me. Lastly, to my daughter. Learning is a lifelong journey, always be ready to embrace what is coming next.

show abstract

Resolution Recommendation for Event Tickets in Service Management

Cited by 33 publications

References 40 publications

Multilevel Petri net‐based ticket assignment and IT management for improved IT organization support

Multilevel Petri net‐based ticket assignment and IT management for improved IT organization support

Application of AI to Network Operation

Mining software support tickets for assistive routing

Contact Info

Product

Resources

About