Temporal event searches based on event maps and relationships

To satisfy a user’s need to find and understand the whole picture of an event effectively and efficiently, in this paper we formalize the problem of temporal event searches and propose a framework of event relationship analysis for search events based on user queries. We define three kinds of event relationships: temporal, content dependence, and event reference, that can be used to identify to what extent a component event is dependent on another in the evolution of a target event (i.e., the query event). The search results are organized as a temporal event map (TEM) that serves as the whole picture about an event’s evolution or development by showing the dependence relationships among events. Based on the event relationships in the TEM, we further propose a method to measure the degrees of importance of events, so as to discover the important component events for a query, as well as the several algebraic operators involved in the TEM, that allow users to view the target event. Experiments conducted on a real data set show that our method outperforms the baseline method Event Evolution Graph (EEG), and it can help discover certain new relationships missed by previous methods and even by human annotators.     

Enabling user-driven rule management in event data analysis

Event data analysis is becoming increasingly of interest to academic researchers looking for patterns in the data. Unlike domain experts working in large companies who have access to IT staff and expensive software infrastructures, researchers find it harder to efficiently manage their event data analysis by themselves. Particularly, user-driven rule management is a challenge especially when analysis rules increase in size and complexity over time. In this paper, we propose an event data analysis platform called EP-RDR intended for non-IT experts that facilitates the evolution of event processing rules according to changing requirements. This platform integrates a rule learning framework called Ripple-Down Rules (RDR) operating in conjunction with an event pattern detection component invoked as a service (EPDaaS). We have built a prototype to demonstrate this solution on real-life scenario involving financial data analysis.     

A decentralized approach for mining event correlations in distributed system monitoring

Nowadays, there is an increasing demand to monitor, analyze, and control large scale distributed systems. Events detected during monitoring are temporally correlated, which is helpful to resource allocation, job scheduling, and failure prediction. To discover the correlations among detected events, many existing approaches concentrate detected events into an event database and perform data mining on it. We argue that these approaches are not scalable to large scale distributed systems as monitored events grow so fast that event correlation discovering can hardly be done with the power of a single computer. In this paper, we present a decentralized approach to efficiently detect events, filter irrelative events, and discover their temporal correlations. We propose a MapReduce-based algorithm, MapReduce-Apriori, to data mining event association rules, which utilizes the computational resource of multiple dedicated nodes of the system. Experimental results show that our decentralized event correlation mining algorithm achieves nearly ideal speedup compared to centralized mining approaches.     

Assessing event correlation in non-process-aware information systems

Many present-day companies carry out a huge amount of daily operations through the use of their information systems without ever having done their own enterprise modeling. Business process mining is a well-proven solution which is used to discover the underlying business process models that are supported by existing information systems. Business process discovery techniques employ event logs as input, which are recorded by process-aware information systems. However, a wide variety of traditional information systems do not have any in-built mechanisms with which to collect events (representing the execution of business activities). Various mechanisms with which to collect events from non-process-aware information systems have been proposed in order to enable the application of process mining techniques to traditional information systems. Unfortunately, since business processes supported by traditional information systems are implicitly defined, correlating events into the appropriate process instance is not trivial. This challenge is known as the event correlation problem. This paper presents an adaptation of an existing event correlation algorithm and incorporates it into a technique in order to collect event logs from the execution of traditional information systems. The technique first instruments the source code to collect events together with some candidate correlation attributes. Based on several well-known design patterns, the technique provides a set of guidelines to support experts when instrumenting the source code. The event correlation algorithm is subsequently applied to the data set of events to discover the best correlation conditions, which are then used to create event logs. The technique has been semi-automated to facilitate its validation through an industrial case study involving a writer management system and a healthcare evaluation system. The study demonstrates that the technique is able to discover an appropriate correlation set and obtain well-formed event logs, thus enabling business process mining techniques to be applied to traditional information systems.     

面向新领域的事件抽取研究综述

在当前互联网时代,大量新领域下的非结构文本数据中蕴含了海量信息.面向新领域的事件抽取方法研究能快速地构建领域知识库,用于支撑基于知识的下游应用.但现有事件抽取系统的领域限定性强,在新领域中从零构建会极度依赖事件体系和标注数据的质量及规模,需要大量人力和专家知识来定制模板和标注语料.而且数据集中常见在相同的上下文中出现多...     

Modeling and execution of event stream processing in business processes

The Internet of Things and Cyber-physical Systems provide enormous amounts of real-time data in the form of streams of events. Businesses can benefit from the integration of these real-world data; new services can be provided to customers, or existing business processes can be improved. Events are a well-known concept in business processes. However, there is no appropriate abstraction mechanism to encapsulate event stream processing in units that represent business functions in a coherent manner across the process modeling, process execution, and IT infrastructure layer. In this paper we present Event Stream Processing Units (SPUs) as such an abstraction mechanism. SPUs encapsulate application logic for event stream processing and enable a seamless transition between process models, executable process representations, and components at the IT layer. We derive requirements for SPUs and introduce EPC and BPMN extensions to model SPUs at the abstract and at the technical process layer. We introduce a transformation from SPUs in EPCs to SPUs in BPMN and implement our modeling notation extensions in Software AG ARIS. We present a runtime infrastructure that executes SPUs and supports implicit invocation and completion semantics. We illustrate our approach using a logistics process as running example.     

Pattern-based event detection in sensor networks

Many applications of wireless sensor networks monitor the physical world and report events of interest. To facilitate event detection in these applications, in this paper we propose a pattern-based event detection approach and integrate the approach into an in-network sensor query processing framework. Different from existing threshold-based event detection, we abstract events into patterns in sensory data and convert the problem of event detection into a pattern matching problem. We focus on applying single-node temporal patterns, and define the general patterns as well as five types of basic patterns for event specification. Considering the limited storage on sensor nodes, we design an on-node cache manager to maintain the historical data required for pattern matching and develop event-driven processing techniques for queries in our framework. We have conducted experiments using patterns for events that are extracted from real-world datasets. The results demonstrate the effectiveness and efficiency of our approach.     

基于四元数门控图神经网络的脚本事件预测

脚本事件预测需要考虑两类信息来源:事件间的关联与事件内的交互。针对于事件间的关联,采用门控图神经网络对其进行建模。而对于事件内的交互,采用四元数对事件进行表征,接着通过四元数的哈密顿乘积来捕捉事件4个组成部分之间的交互。提出结合四元数和门控图神经网络来学习事件表示,它既考虑了外部事件图的交互作用,又考虑了事件内部的依赖关系。得到事件表示后,利用注意机制学习上下文事件表示和每个候选上下文表示的相对权值。然后通过权重计算上下文事件表示的和,再计算其与候选事件表示的欧氏距离。最后选择距离最小的候选事件作为正确的候选事件。在纽约时报语库上进行了实验,结果表明,通过多项选择叙事完形填空评价,本文的模型优于现有的基线模型     

基于事件共享机制的物联网复杂事件处理方法

针对物联网(IOT)复杂事件查询处理过程中的重复查询、存储和处理的问题,提出了事件共享机制(ESM)。首先,为了实现复杂事件的查询与检测,给出了物联网语义事件定义及事件操作符的语义描述;其次,从公共子查询的定义、公共内部查询结构的设计以及事件资源的共享三个角度对物联网事件共享机制展开研究,通过查询表达式的重写、有向无环图(DAG)的构建,以及在结点上使用改进的Continuous参数上下文对事件流进行处理,实现公共子事件查询、存储和处理的共享;最后,构建了基于事件共享机制的语义形式化查询计划处理模型(SFQPM),该模型可自动对查询表达式和查询谓词进行处理,实现复杂事件检测和处理的自动化。仿真结果表明,与基于二叉树(BTree)的处理方法进行对比,所提出的SFQPM具有较高的处理效率和可靠性,实现了复杂事件检测与中间结果共享机制的有机统一,提高了系统的处理效率。最后通过案例研究验证了所提出算法的有效性和可行性。     

Modeling and control of fuzzy discrete event systems

In order to make it possible to effectively represent deterministic uncertainties and vagueness as well as the human subjective observation and judgement inherent to many real-world problems, especially those in biomedicine, we introduce, in this paper, fuzzy states and fuzzy events and generalize (crisp) discrete event systems (DES) to fuzzy DES. The largely graph-based current framework of the crisp DES is unsuitable for the expansion, and we have thus reformulated it using state vectors and event transition matrices which can be extended to fuzzy vectors and matrices by allowing their elements to take values between 0 and 1. To measure information related to fuzzy DES, we generalize the crisp DES observability. The new observability allows one to determine whether or not the system output observed is sufficient for decision making. Finally, we extend the optimal control of DES to fuzzy DES. The new fuzzy DES theory is consistent with the existing theory, both at the conceptual and the computation levels, in that the former contains the latter as a special case when the memberships must be either 0 or 1. Numerical examples are provided to illustrate the theoretical development.     

On integrating event definition and event detection

We develop, in this paper, a representation of time and events that supports a range of reasoning tasks such as monitoring and detection of event patterns which may facilitate the explanation of root cause(s) of faults. We shall compare two approaches to event definition: the active database approach in which events are defined in terms of the conditions for their detection at an instant, and the knowledge representation approach in which events are defined in terms of the conditions for their occurrence over an interval. We shall show the shortcomings of the former definition and employ a three-valued temporal first order nonmonotonic logic, extended with events, in order to integrate both definitions.     

Discovering process models from event multiset

The aim of process mining is to discover the process model from the event log which is recorded by the information system. Typical steps of process mining algorithm can be described as: (1) generating event traces from event log, (2) analyzing event traces and obtaining ordering relations of tasks, (3) generating process model with ordering relations of tasks. The first two steps could be very time consuming involving millions of events and thousands of event traces. This paper presents a novel algorithm (λ-algorithm) which almost eliminates these two steps in generating event traces from event log and analyzing event traces so as to reduce the performance of process mining algorithm. Firstly, we retrieve the event multiset (input data of algorithm marked as MS) which records the frequency of each event but ignores their orders when extracted from event logs. The event in event multiset contains the information of post-activities. Secondly, we obtain ordering relations from event multiset. The ordering relations contain causal dependency, potential parallelism and non-potential parallelism. Finally, we discover a process models with ordering relations. The complexity of λ-algorithm is only bound up with the event classes (the set of events in event logs) that has significantly improved the performance of existing process mining algorithms and is expected to be more practical in real-world process mining based on event logs, as well as being able to detect SWF-nets, short-loops and most of implicit dependency (generated by non-free choice constructions).     

LaSER: Language-specific event recommendation

While societal events often impact people worldwide, a significant fraction of events has a local focus that primarily affects specific language communities. Examples include national elections, the development of the Coronavirus pandemic in different countries, and local film festivals such as the César Awards in France and the Moscow International Film Festival in Russia. However, existing entity recommendation approaches do not sufficiently address the language context of recommendation. This article introduces the novel task of language-specific event recommendation, which aims to recommend events relevant to the user query in the language-specific context. This task can support essential information retrieval activities, including web navigation and exploratory search, considering the language context of user information needs. We propose LaSER, a novel approach toward language-specific event recommendation. LaSER blends the language-specific latent representations (embeddings) of entities and events and spatio-temporal event features in a learning to rank model. This model is trained on publicly available Wikipedia Clickstream data. The results of our user study demonstrate that LaSER outperforms state-of-the-art recommendation baselines by up to 33 percentage points in MAP@5 concerning the language-specific relevance of recommended events.     

Automated discovery and integration of semantic urban data streams: The ACEIS middleware

With the growing popularity of Internet of Things (IoT) technologies and sensors deployment, more and more cities are leaning towards smart cities solutions that can leverage this rich source of streaming data to gather knowledge that can be used to solve domain-specific problems. A key challenge that needs to be faced in this respect is the ability to automatically discover and integrate heterogeneous sensor data streams on the fly for applications to use them. To provide a domain-independent platform and take full benefits from semantic technologies, in this paper we present an Automated Complex Event Implementation System (ACEIS), which serves as a middleware between sensor data streams and smart city applications. ACEIS not only automatically discovers and composes IoT streams in urban infrastructures for users’ requirements expressed as complex event requests, but also automatically generates stream queries in order to detect the requested complex events, bridging the gap between high-level application users and low-level information sources. We also demonstrate the use of ACEIS in a smart travel planner scenario using real-world sensor devices and datasets.     

Partial order reduction for state/event LTL with application to component-interaction automata

Software systems assembled from a large number of autonomous components become an interesting target for formal verification due to the issue of correct interplay in component interaction. State/event LTL (Chaki et al. (2004, 2005) [1] and [2]) incorporates both states and events to express important properties of component-based software systems.The main contribution of this paper is a partial order reduction technique for verification of state/event LTL properties. The core of the partial order reduction is a novel notion of stuttering equivalence which we call state/event stuttering equivalence. The positive attribute of the equivalence is that it can be resolved with existing methods for partial order reduction. State/event LTL properties are, in general, not preserved under state/event stuttering equivalence. To this end we define a new logic, called weak state/event LTL, which is invariant under the new equivalence.To bring some evidence of the method’s efficiency, we present some of the results obtained by employing the partial order reduction technique within our tool for verification of component-based systems modelled using the formalism of component-interaction automata (Brim et al. (2005) [3]).     

Building text-based temporally linked event network for scientific big data analytics

Events formulate the world of the human being and could be regarded as the semantic units in different granularities for information organization. Extracting events and temporal information from texts plays an important role for information analytics in big data because of the wide use of multilingual texts. This paper surveys existing research work on text-based event temporal resolution and reasoning including identification of events, temporal information resolutions of events in English and Chinese texts, the rule-based temporal relation reasoning between events and relevant temporal representations. For the scientific big data analytics, we point out the shortcomings of existing research work and give the argument about the future research work for advancing identification of events, establishment of temporal relations and reasoning of temporal relations.     

基于ECA规则的网络协同设计动态数据交换技术研究*

动态数据交换是实现网络协同设计的关键技术,但是如果在协同设计中每一步的设计信息都进行实时交换,那必然在动态数据交换中包含了不必要的数据。为了解决这个问题,提出基于ECA规则的动态数据交换技术,并建立了应用该技术的网络协同设计系统框架结构。该技术通过应用主动数据库中的ECA规则监控几何图形的变换矩阵来识别模型实体数据的更新,并只传输满足条件的更新数据给STEP动态数据交换进行数据转换,从而减少数据信息的网络传输量以及在更新数据中降低不必要数据产生的可能性。另外,应用一个基于锁的并发控制机制来解决多用户的交互冲突。最后通过建立跨平台网络协同设计原型系统(CISCD)验证动态数据交换技术的有效性。