Business Workflow Research Articles

Utilizing Deep Learning for Field-Level Information Extraction from German Real Estate Tax Notices

ABSTRACT Document processing and related tasks such as information extraction represent a large portion of business workloads and therefore offer high potential for efficiency improvements and process automation. Although semistructured documents such as invoices and receipts have been extensively studied, tax notices represent a largely unexplored area due to their information richness and layout complexity. This article presents a study investigating the potential of deep learning-based information extraction for German real estate tax notices. We propose a hybrid approach based on the LayoutLM transformer model that uses textual, positional, and visual information as well as a rule-based information extraction. We show how such a system can be developed and integrated into the business workflow of organizations on the example of a German tax consulting firm. We also discuss the implications and key challenges that organizations face when planning to adopt such technologies. Data Availability: Custom data and code are not publicly available. Relevant public source code is cited in the text. JEL Classifications: M15; M40; M41.

Research on a cloud model intelligent computing platform for water resource management

ABSTRACT As the demand for water management information systems continues to increase, addressing issues such as poor generalizability, low reusability, and difficulties in updating and maintaining water resource planning cloud model service platforms becomes crucial. To achieve goals like business-oriented functionality, high availability, and reliability, this study proposes constructing a cloud model service platform for basin water resource planning based on cloud computing technology and business workflows. This study couples water cycle models with multi-objective optimization models for water resource allocation, using digital topological water networks to achieve dynamic regional water resource allocation. The cloud service platform adopts a business-oriented modeling method based on B/S development architecture. This paper takes the Weihe River Basin as an example to simulate and analyze the evolution of the water cycle pattern and optimize the annual water resources allocation plan. Results show that: (1) the water cycle model of the cloud model service platform can better describe the runoff change process in the verification period; (2) through the cloud platform service model, the water shortage rate of the Weihe River Basin in 2025 is 7.95%. The research findings provide technical references for intelligent water management and refined allocation of water resources in the Weihe River Basin.

Fairness for machine learning software in education: A systematic mapping study

The integration of machine learning (ML) systems into various sectors, notably education, has great potential to transform business workflows and decision-making processes. However, this technological advancement brings forth critical ethical concerns, particularly concerning the fairness of decisions affecting diverse groups of people. Our objective was to systematically map out the landscape of ML fairness research in higher education by exploring seven key research questions. These questions span a range of topics from the types of ML algorithms used in education to the methods of fairness assessment and the results achieved in terms of equity. We included 63 primary studies published between 2002 and 2023. The most common setting for AI Fairness research are: traditional machine learning algorithms (Logistic Regression, Random Forest, Decision Tree), sensitive variables (gender, race, ethnicity), and various definitions of fairness (Group fairness, Demographic parity, Equalized odds). We also identify several future research directions, including fairness assurance for multiple sensitive variables, combining different fairness concepts and metrics, open-source benchmarking tools, and fairness testing for modern ML/AI models.

Role of document management system for business processes optimization

The automation of work processes and seamless integration with various business services highlight the essential role of digital document management systems (DMS) in enhancing organizational flexibility, productivity, and adaptability. DMS serve as centralized repositories that streamline, automate, and interconnect business processes, thereby facilitating effective document management. The integration of DMS with Enterprise Resource Planning (ERP) systems provides a comprehensive solution for optimizing business workflows, addressing the needs for both operational efficiency and strategic management. The research paper delineates a business model for the life cycle management of electronic documents and records, focusing on the integration of processes such as document creation, management, approval, and secure distribution. This integrated approach enhances organizational structure, optimizes processes, and bolsters security, leading to significant cost reductions and increased work efficiency. The model emphasizes the importance of streamlined and automated document workflows in reducing manual errors and operational bottlenecks. Key features of DMS include advanced mechanisms for digitizing physical documents, ensuring that all data is captured accurately and efficiently. Centralized storage with version control allows for easy retrieval and management of documents, ensuring that the latest versions are always accessible. Additionally, advanced search and accessibility features enable quick and efficient document retrieval, which is crucial for maintaining high productivity levels. The study underscores the pivotal role of DMS in modern enterprises, advocating their implementation as a strategic move to drive operational excellence and competitive advantage. By integrating DMS with ERP systems, businesses can achieve a cohesive and efficient operational environment that supports both day-to-day activities and long-term strategic goals. This comprehensive approach to document management not only optimizes efficiency and reduces errors but also enhances the overall agility and responsiveness of the organization in a rapidly changing economic environment.

Revitalising legacy video ingest workflow: A case study on cultivating a digital mindset and gaining key stakeholder buy-in to transition to a cloud-based media asset manager

Starz, a premium cable channel and subscription video on demand network founded in 1994, took on a project to migrate its ingest workflow to a cloud-based media asset manager. It was a complex undertaking, involving multiple departments, software developers, product managers and vendors. This paper describes the project history, its genesis, its execution and its results. This paper also examines the business justification for this kind of a project and the issues inherent in replacing a long-standing business workflow.

Implementation of Application and Product System (SAP) in Metal Coating Process Manufacturing Company

In the development of the Industrial Revolution 4.0 era, the use of an Enterprise Resource Planning System is a long-term investment for a company to improve efficiency, performance, and decision-making tools for the company. In general, it uses a centralized database for various business processes to reduce manual labor and simplify existing business workflows. ERP systems usually contain Dashboards where users can view real-time data collected from across the business to measure productivity and profitability. This means that any data or information received will be updated immediately as soon as the user inputs the data into the time system even though the data has been closed, the company can know and control the condition of the company every day and can control a production process so that decision making can be done quickly, carefully, and precisely because it is based on valid internal data and is always up to date. there is still a difference in data between the transaction process, The purpose of the research is to process information in real-time and accurately, The research stage begins with a literature study, hardware prototypes, and making programs, The results of the research are an increase in transaction accuracy of 43% after SAP implementation is optimally implemented.

Preface

The International Conference on Software Engineering and Machine Learning (CONF-SEML) is an annual conference focusing on research areas including software engineering, artificial intelligence, and other information technology areas. It aims to establish a broad and interdisciplinary platform for experts, researchers, and students worldwide to present, exchange, and discuss the latest advance and development in engineering and machine learning.This volume contains the papers of the 2023 International Conference on Software Engineering and Machine Learning (CONF-SEML 2023). Each of these papers has gained a comprehensive review by the editorial team and professional reviewers. Each paper has been examined and evaluated for its theme, structure, method, content, language, and format.CONF-SEML 2023 organized four workshops in cooperation with famous universities worldwide. Dr. Marco Manca chaired the workshop “BioDynaMo: Building the Future Today” in Bologna, Italy. Dr. Christopher Windmill and Dr. Patrick Merritt chaired the workshop “Software development practices for digitally augmented traditional business workflows” at the University of Derby. Dr. Marwan Omar chaired the workshop “Recovering Data in a Digital Forensics Examination” at the Illinois Institute of Technology. Prof. Anil Fernando chaired the workshop “Explainable AI for Stock Market Prediction” at the University of Strathclyde.Besides these workshops, CONF-SEML 2023 also held an online session. Eminent professors from top universities were invited to deliver keynote speeches in this online session, including Prof. Roman Bauer from the University of Surrey, Prof. Michael Harre from the University of Sydney, Prof. Richa Gupta from Jamia Hamdard University, etc. They have given keynote speeches on related topics of utilization of machine learning, digital healthcare intervention, computational model, etc.On behalf of the committee, we would like to give sincere gratitude to all authors and speakers who have made their contributions to CONF-SEML 2023, editors and reviewers who have guaranteed the quality of papers with their expertise, and the committee members who have devoted themselves to the success of the conference.

Zero trust architecture: Redefining network security paradigms in the digital age

The prevailing paradigms of network security have demonstrated their inadequacy in safeguarding critical data against the intricate web of advanced cyber threats prevailing in today's ever-shifting digital terrain. The domain of network security has been subjected to a seismic reorientation catalyzed by the advent of the zero-trust paradigm. This novel approach underscores a multifaceted, adaptable, and proactive methodology, thereby punctuating the obsolescence of conventional perimeter-centric strategies. Central to the ethos of the zero-trust doctrine resides a fundamental skepticism concerning the bedrock of trust assumptions that underpin network dynamics. Diverging from entrenched models, the zero-trust architectural edifice operates on the premise that perils are omnidirectional, originating both externally and internally. This nullification of any inherent trust attributed to constituents within stipulated boundaries compels enterprises, regardless of user spatial disposition or network adjacency, to painstakingly ascertain the legitimacy of every user, device, and application endeavoring to access invaluable resources. At the core of the zero-trust architecture lies its distinctive feature of significantly reducing the vulnerable area for potential attacks. This contraction is manifest through the meticulous imposition of stringent access controls and the meticulous segmentation of microcosmic components, thereby effectively constricting the lateral trajectory of threats across the network expanse. Consequently, even in the contingency of a breach, the reverberations upon pivotal assets are attenuated, their potential detriment confined and segregated. Concurrently, the zero-trust ethos assimilates a perpetual vigilance and instantaneous threat discernment as intrinsic tenets. This capacitates organizations to expeditiously counteract aberrations and potential security breaches. To fortify the bulwark of data integrity, the paradigm amalgamates multifarious facets encompassing multifactor authentication, encryption, and the tenet of least privilege. This confluence tangibly augments the intricacy of thwarting unauthorized actors seeking ingress or egress to prized sensitive data. Of paramount import is the alignment of this strategy with the capricious contours of contemporary business workflows, encompassing the ubiquity of mobile devices, the ubiquity of remote work modalities, and the prevalence of cloud-based services, all within an impregnable security aegis. However, the implementation of the zero-trust framework is not devoid of associated difficulties. Organizations must adroitly maneuver through labyrinthine installation protocols, the specter of potential compatibility conflicts, and the imperative of engendering a seismic cultural shift within security practices. Furthermore, the perpetual guardianship and custodianship of such an architecture mandate the marshaling of bespoke resources and expertise.

Интеллектуалды виртуалды кеңесшіні әзірлеуге арналған дауысты тану әдістері

In this article, methods of voice recognition were studied for the development of an intelligent virtual consultant, which plays an important role as an auxiliary tool when working with business process information systems, or rather with an ERP system. This study is intended to describe an intelligent virtual consultant in assessing the usefulness and effectiveness of using real functions in a business process modeling software system for enterprise resource planning (ERP). An intelligent virtual consultant is integrated with a Web-ERP prototype. In this study, natural language processing (NLP) was based using Levenberg Marquardt (LM) and Broyden-Fletcher Goldwarb-Shanno (BFGS) methods with the Mel kepstral frequency coefficients algorithm. A comparative analysis of these methods was also carried out to determine the effectiveness of the methods used. The big advantage of this virtual consultant is the voice input of long text data fields when working in Web-ERP. This system is relevant, as it significantly expands the search for business workflows. The system allows you to convert speech into text by receiving information system (IS) instructions, which, in turn, are transmitted to an ontological database, where a query based on terms is executed to obtain a set of commands available for execution. The introduction of an intelligent virtual consultant not only expands the application’s capabilities for users through the system, but also allows users to interpret data using speech synthesis. This prototype will be used for further research on the integration of intelligent virtual consultant and data analysis.

Inv3D: a high-resolution 3D invoice dataset for template-guided single-image document unwarping

Numerous business workflows involve printed forms, such as invoices or receipts, which are often manually digitalized to persistently search or store the data. As hardware scanners are costly and inflexible, smartphones are increasingly used for digitalization. Here, processing algorithms need to deal with prevailing environmental factors, such as shadows or crumples. Current state-of-the-art approaches learn supervised image dewarping models based on pairs of raw images and rectification meshes. The available results show promising predictive accuracies for dewarping, but generated errors still lead to sub-optimal information retrieval. In this paper, we explore the potential of improving dewarping models using additional, structured information in the form of invoice templates. We provide two core contributions: (1) a novel dataset, referred to as Inv3D, comprising synthetic and real-world high-resolution invoice images with structural templates, rectification meshes, and a multiplicity of per-pixel supervision signals and (2) a novel image dewarping algorithm, which extends the state-of-the-art approach GeoTr to leverage structural templates using attention. Our extensive evaluation includes an implementation of DewarpNet and shows that exploiting structured templates can improve the performance for image dewarping. We report superior performance for the proposed algorithm on our new benchmark for all metrics, including an improved local distortion of 26.1 %. We made our new dataset and all code publicly available at https://felixhertlein.github.io/inv3d.

Lessons learned about policymaking: Moving an emergency department-initiated screening protocol to systemwide input in the development and implementation process.

Lessons learned about policymaking: Moving an emergency department-initiated screening protocol to systemwide input in the development and implementation process.

Investigation of Microservice-Based Workflow Management Solutions for Industrial Automation

In an era ruled by data and information, engineers need new tools to cope with the increased complexity of industrial operations. New architectural models for industry enable open communication environments, where workflows can play a major role in providing flexible and dynamic interactions between systems. Workflows help engineers maintain precise control over their factory equipment and Information Technology (IT) services, from the initial design stages to plant operations. The current application of workflows departs from the classic business workflows that focus on office automation systems in favor of a manufacturing-oriented approach that involves direct interaction with cyber-physical systems (CPSs) on the shop floor. This paper identifies relevant industry-related challenges that hinder the adoption of workflow technology, which are classified within the context of a cohesive workflow lifecycle. The classification compares the various workflow management solutions and systems used to monitor and execute workflows. These solutions have been developed alongside the Eclipse Arrowhead framework, which provides a common infrastructure for designing systems according to the microservice architectural principles. This paper investigates and compares various solutions for workflow management and execution in light of the associated industrial requirements. Further, it compares various microservice-based approaches and their implementation. The objective is to support industrial stakeholders in their decision-making with regard to choosing among workflow management solutions.

MONWS: Multi-Objective Normalization Workflow Scheduling for Cloud Computing

Cloud computing is a prominent approach for complex scientific and business workflow applications in the pay-as-you-go model. Workflow scheduling poses a challenge in cloud computing due to its widespread applications in physics, astronomy, bioinformatics, and healthcare, etc. Resource allocation for workflow scheduling is problematic due to the computationally intensive nature of the workflow, the interdependence of tasks, and the heterogeneity of cloud resources. During resource allocation, the time and cost of execution are significant issues in the cloud-computing environment, which can potentially degrade the service quality that is provided to end users. This study proposes a method focusing on makespan, average utilization, and cost. The authors propose a task’s dynamic priority for workflow scheduling using MONWS, which uses the min-max algorithm to minimize the finish time and maximize resource utilization by calculating the dynamic threshold value for scheduling tasks on virtual machines. When the experimental results were compared to existing algorithms, MONWS achieved a 35% improvement in makespan, an 8% increase in maximum average cloud utilization, and a 4% decrease in cost.

Implementing a digital public health project - lessons learned?

Abstract The demand for the digitalisation of public health has been ongoing for more than a decade. The COVID-19 pandemic was the tipping point that accelerated the ideation, implementation, and scale-up of such public health projects. Despite the well-needed push, the same challenges that face every similar implementation will nonetheless be the same if not accentuated. The scope of the presentation is to highlight the difficulties and facilitators that such implementations and evaluations bring forward. We will also see what we can learn as public health professionals to ensure that present and future information systems are well-planned. We have to ensure that they do not succumb to the pressure of well-intended stakeholders who are yearning for such solutions to help their business workflows. This presentation will be enhanced with the lessons learned from implementing, monitoring, and following up on Malta's national contact tracing app and Customer Relationship Management systems based on Microsoft Dynamics 365 technologies that tackled the Test, Track and Trace workflows that were integral to the COVID response in Malta.

End-to-End Automated UI Testing Workflow for Web Sites with Intensive User–System Interactions

The user interface (UI) is the software component with which the end users interact the most in the mobile and web world today. Therefore, when evaluating end-user satisfaction with a software, besides the functional features, the possibilities provided by the UIs are significant. End-user interfaces offer several capabilities today, necessitating a complex structure. Examples include interfaces developed in technologies such as Google Flutter and React. Therefore, we foresee a need for UI testing business workflows allowing comprehensive testing of UIs to improve customer satisfaction. Within the scope of this research, we propose an end-to-end approached automated UI testing business workflow for testing UI components on websites with intense user actions.

P-197 Successful implementation of an end-to-end artificial intelligence (AI) platform in a busy IVF clinic: A prospective observational study

Abstract Study question How demanding in terms of time and resource allocation is the full integration of an AI platform to the routine operation of an IVF clinic? Summary answer The rapid and effective implementation, and continuous performance, of EMA was qualitatively and quantitatively demonstrated for the first time in a real-world clinical setting. What is known already The role of AI-based embryo predictive analysis tools is often hailed as one of the most important recent developments in the IVF clinic. The high precision of such systems has been reported. For instance, the AI-system implemented here, EMATM(AiVF), employs a convolutional neural network architecture, providing an area-under-the-curve (AUC) of 0.95 with 83% accuracy. However, little was reported to date on the full implementation of these advanced systems in the active IVF lab. This study prospectively evaluated the clinical implementation and process-of-use in an IVF clinic of EMA, the first end-to-end AI-driven platform designed to algorithmically aid in evaluating embryos. Study design, size, duration A prospective observational single center study. The study was performed in two phases. Phase I: EMA was integrated into standard workflow and qualitatively evaluated over the course of one month by five embryologists in a series of twice-daily qualitative checks and questionaries. Phase II: The rate of agreement between EMA and embryologists were benchmarked and compared to evaluate how the model aids embryologists in efficiently assessing embryos. Participants/materials, setting, methods Phase I: Five senior embryologists completed electronic questionaries to qualitatively report on the ease-of-use, functionality, and performance of EMA after using the platform as adjunctive information on 588 embryos; ICSI was performed on all treatment cycles. Phase I was completed within 2 weeks. Phase II: The rate of agreement between five senior embryologists and EMA was calculated for the accuracy in ranking embryo(s) for transfer/freeze (146 treatment cycles). Phase II was undertaken in 4 weeks. Main results and the role of chance EMA was effectively incorporated into a busy IVF laboratory for routine daily use to algorithmically assess all embryos at 105 hours post-fertilization prior to vitrification. All embryos were cultured in a time-lapse incubator and successfully evaluated by both EMA and embryologists in parallel to conventional morphologic embryo evaluation. In Phase I, all five embryologists qualitatively approved of EMA’s integration and clinical utility inside their workflow and reported enhanced efficiency when EMA was used per its intended use. In Phase II we demonstrated a 86% agreement rate between embryologists and EMA. Of all embryos selected for transfer by embryologists 100% were also identified by EMA as having the highest potential for implantation. Of all embryos selected for vitrification by embryologists, 85%were identified by EMA as top-quality (Gardner criteria: A/B grade) embryos. Among embryos that were graded C/D (Gardner criteria) by embryologists, 89% were identified by EMA as “low grade” as well. Pregnancies were shown to be highly associated with EMA's embryo selection. The final stage of our implementation analysis of EMA is currently ongoing; the association between the algorithmic outputs of EMA and clinical implantation rates are being investigated in a prospective double-blinded, observation cohort study and results will be presented. Limitations, reasons for caution This is a single center study, based on relatively homogenous patient population. Nevertheless, given the impressive results reported herein, we conclude that this single case-study is sufficient for demonstrating rapid and successful implementation and process-validation of EMA for routine use by the clinic. Wider implications of the findings AI-based decision support systems like EMA have the potential to increase rapid and objective standardization inside the clinic, thereby improving accurate decision making and saving time and resources without interfering with the busy workflow of an IVF setting. Routine use of EMA in IVF should be prioritized for further evaluation. Trial registration number N/A

Decision Support Model to Determine the Best Employees (Mechanic) using Fuzzy Logic and Profile Matching

In a company, verifying the best employees is practically very essential. Knowing the best employees or understanding each employee's performance can be an advantage for the company to evaluate the whole company's performance and improve the lack. Determining the best employees is also necessary for giving appreciation to employees and is expected to be able to expand the performance and morale of employees. This study aims to build a Decision Support Model (DSM) to determine the best employee using a combination of fuzzy logic and profile matching methods. In developing the model, there are twelve selected parameters considered; i.e., performance problem diagnosis, problem-solving, preventive action, concept, time management, disciplinary, work management, efficiency, education, support skills, and business workflow. Finally, the model has been methodologically constructed. It is operated in determining the best employee (especially for mechanic staff in workshop) thru evaluating all employees' performance.

Sosialisasi Penerapan Sistem Informasi Dokumen Perencanaan Berbasis Web di Bappeda Gianyar

Document management of an institution/organization is very important to do. Documents are not managed properly, resulting in reduced work efficiency. The Regional Development Planning Agency or Bappeda Gianyar is a Regional Apparatus Organization in Gianyar Regency - Bali, which is tasked with coordinating the preparation, control and evaluation of the implementation of regional development plans (RPD). Collection and recording of planning documents in the form of softcopies from Regional Apparatus Organizations sent via Whatsapp to different employees in the Program Sector, to allow the existence of these softcopies to be scattered, and also when there is a hardcopy of planning document borrowing to the Program Preparation Division, the recording of the loan is not recorded so well that it would be difficult to trace. In this community service, a Planning Document Information System was designed which aims to serve as a forum for the management of planning documents managed by Bappeda also Research and Development of Gianyar Regency. In order to provide an understanding in terms of business processes and workflows of the system that has been built, in this community service training/socialization of the use of the planning document system is held. So it is hoped that after the socialization of the use of the planning document system, it can provide convenience and work efficiency for state officials in managing planning documents.

Viv - The Personal Voice Assistant

Abstract: Voice control is a major growing feature that changes the way people are living their lives. Since speech recognition and natural language processing continues to advance at a rapid stage, a virtual assistant's ability and efficiency to comprehend and perform tasks will grow as well. And as voice-recognition technology improves, virtual assistant use will deeply integrate into business workflows. Tomorrow's virtual assistants are going to be built with more advanced cognitive computing technologies, which can allow a virtual assistant to know and perform multistep requests and perform more complex tasks. Virtual assistants are cloud-based programs that need internet-connected devices and/or applications to work. Examples of such services are: Siri on Apple devices, Cortana on Microsoft devices, Google Assistant for Android devices, whereas Bixby for Samsung devices. Keywords: Desktop Assistant, Voice Recognition, Virtual Assistant, Text to Speech, Speech to Text, Language Processing, Python Script.

Pengembangan Sistem Pelacakan Proyek Berbasis Web dengan Rapid Application Development Berdasarkan Studi Kasus PT. XYZ

PT. XYZ is a company that supplies automotive spare parts with a complex business workflow. One project consists of several jobs involving a series of steps and different sections of the department. In this study, we developed a web-based project tracking system using rapid application development based on a set of user requirements. The system was tested using black box testing which indicated success in response to its functionality. The result successfully provided employees the means to select a job according to their order, upload files, write notes, and pass the job to the next section when done. For Inspection and Assembly, the testing showed success for returning jobs to Design when revisions were required. Assembly was also able to declare project completion when every job has been fully executed by its respective sections. Every stage of the project was successfully recorded which provided information on the progress of each project to the management. Furthermore, our testing also found the system to be capable of providing a facility for customer to track the progress and duration of their project anywhere and anytime by entering a project code.