Ensuring the reliability and availability of cloud services necessitates efficient root cause analysis (RCA) for cloud incidents. Traditional RCA methods, which rely on manual investigations of data sources such as logs and traces, are often laborious, error-prone, and challenging for on-call engineers. In this paper, we introduce RCACopilot, an innovative on-call system empowered by the large language model for automating RCA of cloud incidents. RCACopilot matches incoming incidents to corresponding incident handlers based on their alert types, aggregates the critical runtime diagnostic information, predicts the incident's root cause category, and provides an explanatory narrative. We evaluate RCACopilot using a real-world dataset consisting of a year's worth of incidents from Microsoft. Our evaluation demonstrates that RCACopilot achieves RCA accuracy up to 0.766. Furthermore, the diagnostic information collection component of RCACopilot has been successfully in use at Microsoft for over four years.

In microservice systems, the identification of root causes of anomalies is imperative for service reliability and business impact. This process is typically divided into two phases: (i)constructing a service dependency graph that outlines the sequence and structure of system components that are invoked, and (ii) localizing the root cause components using the graph, traces, logs, and Key Performance Indicators (KPIs) such as latency. However, both phases are not straightforward due to the highly dynamic and complex nature of the system, particularly in large-scale commercial architectures like Microsoft Exchange.

Root Cause Analysis (RCA) is becoming increasingly crucial for ensuring the reliability of microservice systems. However, performing RCA on modern microservice systems can be challenging due to their large scale, as they usually comprise hundreds of components, leading significant human effort. This paper proposes TraceDiag, an end-to-end RCA framework that addresses the challenges for large-scale microservice systems. It leverages reinforcement learning to learn a pruning policy for the service dependency graph to automatically eliminates redundant components, thereby significantly improving the RCA efficiency. The learned pruning policy is interpretable and fully adaptive to new RCA instances. With the pruned graph, a causal-based method can be executed with high accuracy and efficiency. The proposed TraceDiag framework is evaluated on real data traces collected from the Microsoft Exchange system, and demonstrates superior performance compared to state-of-the-art RCA approaches. Notably, TraceDiag has been integrated as a critical component in the Microsoft M365 Exchange, resulting in a significant improvement in the system's reliability and a considerable reduction in the human effort required for RCA.

In the diversified market competition environment promoted by emerging information technology, diversified business functions run collaboratively based on the shared data, that is, it has become the norm for enterprise data to be shared by various business functions. Therefore, there is a need for the partition of enterprise information system structure based on business functions and data usage connections to improve the collaboration efficiency of various business functions based on shared data. This research proposes a system structure partition algorithm based on link feature (SPLF). The SPLF algorithm takes non-interference sequence as the theoretical basis, and introduces link feature and link shared degree of sets as a measure of similarity between entities or sets. The SPLF algorithm includes two stages: entity link feature calculation and pre-clustering stage, and two-dimensional entity set clustering stage. Experiment shows that the clustering results produced by the SPLF algorithm have high cohesion and accuracy, and can effectively aggregate discrete original data from two dimensions in parallel, and realize sub-system partition according to the clustering results. The SPLF algorithm adopts the idea of joint clustering, and takes the sharing of links as the basis for similarity measurement, and extends the traditional clustering method from one-dimensional to two-dimensional. Based on the SPLF algorithm, this research proposes an enterprise information system structure partition framework, which structurally solves the problem of enterprise business function and data organization under the background of big data, and provides an effective solution for data sharing and cooperation for various business functions of the enterprise, so as to improve business processing efficiency and competitiveness.

Taking the lowest cost as the objective, considering the influence of the weight gain of iron oxide oxidation process, the burning loss of raw materials and the amount of desulfurization on the chemical composition and cost of pellet products, this paper constructs an optimization model of pellet proportioning, and gives the particle swarm optimization algorithm based on penalty function. This model can not only meet the chemical composition requirements of finished ore, but also reduce the cost effectively, and greatly reduce the time cost of calculation. Compared with the existing research results, it has higher calculation efficiency on the basis of ensuring the accuracy of calculation results.

The air pollutants concentration is affected by various recent factors such as the weather, environmental conditions and the season. For this reason, this study used grey interval GM(1,1) prediction model whose research object is small data to predict the air quality grade and major pollutants. The experimental results show that the model for air quality grade of prediction accuracy is 75%, and the primary pollutant can be well found by the prediction results of the major pollutants. In addition, it is found that the prediction values of pollutant concentration are impacted by the degree of data fluctuation, which also indirectly affects the accuracy in predicting air quality grade and the primary pollutant.

This paper examines the evaluation of ability in human endurance sports. First, it presents the formula used to calculate the Endurance Index. Second, the k-means clustering algorithm is used to analyze different cross-country running competitions to provide accurate measurement of the contestants. The finish times of randomly selected contestants were predicted, and the average accuracy of the predictions was more than 94%. This study provides a way for contestants, organizers, and the sports industry to predict the duration of running events.

Abstract The widespread scale effect always generates significant changes in the properties or characteristics of management objects with different observation scales. Thus, this paper studies the scale transformation mechanism problem of management objects. The observation scale hierarchy (management scale) with clear management objectives could automatically be recognized through changing the observation scales, in order to improve the practical management efficiency. Firstly, an intelligent computing framework based on the scale transformation is established, which reduces the over-dependency of human involvement in traditional scale transformation methods. Then, the scale characteristic reasoning inference is put forward to improve the knowledge acquisition mechanism of scale transformation. Finally, a knowledge acquisition algorithm based on the variable-scale clustering (KAVSC) is proposed. Experiments selected the multiple products inventory data of a manufacturing enterprise from 1 January 2015 to 31 December 2017. The experiment results illustrate that the proposed algorithm KAVSC is able to accurately recognize different management scale levels and scale characteristics of each product, which could effectively support managers making differentiated inventory management plans.

Clustering validation has long been recognized as one of the vital issues essential to the success of clustering applications. In general, clustering validation can be categorized into two classes, external clustering validation and internal clustering validation. In this paper, we focus on internal clustering validation and present a study of 11 widely used internal clustering validation measures for crisp clustering. The results of this study indicate that these existing measures have certain limitations in different application scenarios. As an alternative choice, we propose a new internal clustering validation measure, named clustering validation index based on nearest neighbors (CVNN), which is based on the notion of nearest neighbors. This measure can dynamically select multiple objects as representatives for different clusters in different situations. Experimental results show that CVNN outperforms the existing measures on both synthetic data and real-world data in different application scenarios.

It is a general problem in the data mining field to detect the overlapping community structure in a complex network. A novel approach is presented in this paper to identify communities based on core vertices and shared neighbors, which can find both separate and overlapping community structures in networks. Experimental results on synthetic and real-world networks show that the new algorithm is effective and efficient in identification of communities and it can find overlapping and bridge vertices.

Clustering validation has long been recognized as one of the vital issues essential to the success of clustering applications. In general, clustering validation can be categorized into two classes, external clustering validation and internal clustering validation. In this paper, we focus on internal clustering validation and present a detailed study of 11 widely used internal clustering validation measures for crisp clustering. From five conventional aspects of clustering, we investigate their validation properties. Experiment results show that S_Dbw is the only internal validation measure which performs well in all five aspects, while other measures have certain limitations in different application scenarios.

To solve the prediction of customer churn, the paper proposed a new algorithm. Based on rough set theory, the algorithm used the consistency of condition attributes and decision attributes in information table, and the conception of super-cube and scan vector to discretize the continuous attributes, reduce the redundant attributes. And furthermore, it took BP neural network as the calculating tool to predict customer churn. The experimental results showed the refined data by rough set was more concise and more convenient to be applied in BP neural network, whose prediction result was more accurate. So, the algorithm via BP neural network based on rough set theory is efficient and effective