A Synergistic Multi-Agent Framework for Resilient and Traceable Operational Scheduling from Unstructured Knowledge

In general, the long-term maintenance planning of residential buildings is performed based on uniform repair times. However, in fact, various factors, such as the quality and user patterns, affect the performance of residential building components in the Operation and Maintenance (O&M) phase. Hence, various residential building components are repaired at uncertain times, acting as a risk for the residential building maintenance plan. Therefore, an efficient maintenance plan should be established considering maintenance uncertainty. In this regard, this study aims to analyze the uncertainty of repair times for various finishing works in residential buildings based on a probabilistic methodology and outline the implications for the establishment of efficient maintenance strategies in these buildings. Hence, 47,344 repair data for 63 buildings in 12 public residential building complexes completed between 1991 and 2001 in the Republic of Korea were used for analysis. Before the analysis, a repair time matrix was constructed by classifying the finishing works in 25 types and setting service life times to 6–26 years. The repair time distribution for each finishing work was then derived. Results confirmed that basic repair time setting can be performed and various information for reasonable maintenance decision making regarding each finishing work can be provided through a probabilistic approach. The probabilistic approach can be used as a critical decision-making method because there is uncertainty associated with the repair time of each finishing work owing to the performance degradations of various finishing works due to complex causes. Although this study focused on repair time owing to data collection limitations, maintenance strategies with strategic flexibility can be established by developing probabilistic methods that simultaneously consider frequency and cost by securing additional high-quality cost data.

The purpose of this study is to propose an integrated strategy to determine jointly efficient business and maintenance plans. The studied system is subject to random failures with a dynamic failure law. It must perform a set of missions (among M possible missions) over a finite planning horizon. Each mission may have different characteristics that depend on operational and environmental conditions. The determination of a business plan consists in choosing and scheduling the missions to be performed. To maximize the net profit (profits generated by the achievement of missions minus maintenance costs), two meta-heuristics based on genetic algorithms are developed. The first genetic algorithm is used to determine the business plan and the second one generates an efficient maintenance plan. Two maintenance policies are studied: a minimalist policy which involves only corrective maintenance actions and another policy, called sequential, which involves several imperfect preventive maintenance activities performed at predetermined times. Two cases are studied for the latter strategy. The first one considers the maintenance effectiveness factor as being the same for all preventive maintenance actions and we search for the best factor. In the second case, we consider maintenance actions with different efficiency factors and we look for the optimal value of each factor. Finally, a numerical example illustrates the proposed approach and the difference between the maintenance policies.

Whereas research on recombination indicates that the structure of the firm’s knowledge base has an impact on the usefulness of its innovation, it emphasizes that the usefulness of innovation increases when firms’ search spans organizational boundaries. Current literature is limited however in providing insight in how a firm should organize its boundary-spanning search for recombination, given the specific characteristics of its knowledge base. Delineating a continuum of knowledge structures from highly decomposable to non-decomposable, we contribute to extant literature by demonstrating that the knowledge base and in particular its structure also impacts the organizational governance choice for collaborative recombination. In particular we demonstrate on a sample of 108 Biotech firms engaged in 968 contractual agreements and 152 joint ventures with 928 partners that firms with a decomposable knowledge base are more likely to engage in equity joint ventures for collaboration. Furthermore, we demonstrate that when the partner has a decomposable knowledge base, a joint venture is also more likely to be the chosen mode of collaboration. Results imply that the structure of the knowledge base is not only important for the innovation potential of the firm, but also impacts the governance choices firms make for collaborative recombination.

Existing end-to-end task-oriented dialog systems struggle to dynamically model long dialog context for interactions and effectively incorporate knowledge base (KB) information into dialog generation. To conquer these limitations, we propose a Dual Dynamic Memory Network (DDMN) for multi-turn dialog generation, which maintains two core components: dialog memory manager and KB memory manager. The dialog memory manager dynamically expands the dialog memory turn by turn and keeps track of dialog history with an updating mechanism, which encourages the model to filter irrelevant dialog history and memorize important newly coming information. The KB memory manager shares the structural KB triples throughout the whole conversation, and dynamically extracts KB information with a memory pointer at each turn. Experimental results on three benchmark datasets demonstrate that DDMN significantly outperforms the strong baselines in terms of both automatic evaluation and human evaluation. Our code is available at https://github.com/siat-nlp/DDMN.

This article examines the importance of the knowledge base in the development of an intelligent algorithmic and software complex of underground water intake facilities. When developing the computerized knowledge base of underground water intake facilities, the management knowledge base, the classification of knowledge bases, the use of conventional knowledge bases for creating expert systems and storing information about the facility will be studied. A knowledge base structure will be developed when creating an intelligent algorithmic and software complex of underground water intake facilities. When organizing the process of forming underground water intake facilities, the development of a knowledge base for the watertight properties of single-layer moisture layers will be studied. During the formation of underground water intake facilities, knowledge is calculated to solve the issues of determining the watertightness of single-layer earthworks.

Large knowledge bases that are intended for applications such as CAD, corporate repositories or process control will have to be shared by multiple users. For these systems to scale up, to give acceptable performance and to exhibit consistent behavior, it is mandatory to synchronize user transactions using a concurrency control algorithm. In this paper, we examine a novel concurrency control policy called Dynamic Directed Graph (or DDG) policy that effectively exploits the rich semantic structure of a knowledge base.

Structured knowledge bases (KBs) are a foundation of many intelligent applications, yet are notoriously incomplete. Language models (LMs) have recently been proposed for unsupervised knowledge base completion (KBC), yet, despite encouraging initial results, questions regarding their suitability remain open. Existing evaluations often fall short because they only evaluate on popular subjects, or sample already existing facts from KBs. In this work, we introduce a novel, more challenging benchmark dataset, and a methodology tailored for a realistic assessment of the KBC potential of LMs. For automated assessment, we curate a dataset called WD-Known, which provides an unbiased random sample of Wikidata, containing over 3.9 million facts. In a second step, we perform a human evaluation on predictions that are not yet in the KB, as only this provides real insights into the added value over existing KBs. Our key finding is that biases in dataset conception of previous benchmarks lead to a systematic overestimate of LM performance for KBC. However, our results also reveal strong areas of LMs. We could, for example, perform a significant completion of Wikidata on the relations nativeLanguage, by a factor of $$\sim $$ 21 (from 260k to 5.8M) at $$82\%$$ precision, and citizenOf by a factor of $$\sim $$ 0.3 (from 4.2M to 5.3M) at 90% precision. Moreover, we find that LMs possess surprisingly strong generalization capabilities: even on relations where most facts were not directly observed in LM training, prediction quality can be high. We open-source the benchmark dataset and code. ( https://github.com/bveseli/LMsForKBC ).

Knowledge-based visual question answering (VQA) involves answering questions that require external knowledge not present in the image. Existing methods first retrieve knowledge from external resources, then reason over the selected knowledge, the input image, and question for answer prediction. However, this two-step approach could lead to mismatches that potentially limit the VQA performance. For example, the retrieved knowledge might be noisy and irrelevant to the question, and the re-embedded knowledge features during reasoning might deviate from their original meanings in the knowledge base (KB). To address this challenge, we propose PICa, a simple yet effective method that Prompts GPT3 via the use of Image Captions, for knowledge-based VQA. Inspired by GPT-3’s power in knowledge retrieval and question answering, instead of using structured KBs as in previous work, we treat GPT-3 as an implicit and unstructured KB that can jointly acquire and process relevant knowledge. Specifically, we first convert the image into captions (or tags) that GPT-3 can understand, then adapt GPT-3 to solve the VQA task in a few-shot manner by just providing a few in-context VQA examples. We further boost performance by carefully investigating: (i) what text formats best describe the image content, and (ii) how in-context examples can be better selected and used. PICa unlocks the first use of GPT-3 for multimodal tasks. By using only 16 examples, PICa surpasses the supervised state of the art by an absolute +8.6 points on the OK-VQA dataset. We also benchmark PICa on VQAv2, where PICa also shows a decent few-shot performance.

Information contained in mathematical digital writings creates new challenges for knowledge management systems because automated knowledge extraction from natural language texts is a technical challenge. However, mathematical texts possess a distinctive structure. KEA benefits from this structure, and extracts linguistic relations from texts, creates ontologies, and combines them to a knowledge base. This knowledge base is the core of an enhanced retrieval system. Responses of this system are user-adaptive text-based and visualized. Possible applications are mathematical encyclopaedias, context sensitive library search, intelligent book indexes and e-learning software.

Knowledge bases, massive collections of facts (RDF triples) on diverse topics, support vital modern applications. However, existing knowledge bases contain very little data compared to the wealth of information on the Web. This is because the industry standard in knowledge base creation and augmentation suffers from a serious bottleneck: they rely on domain experts to identify appropriate web sources to extract data from. Efforts to fully automate knowledge extraction have failed to improve this standard: these automated systems are able to retrieve much more data and from a broader range of sources, but they suffer from very low precision and recall. As a result, these large-scale extractions remain unexploited. In this paper, we present MIDAS, a system that harnesses the results of automated knowledge extraction pipelines to repair the bottleneck in industrial knowledge creation and augmentation processes. MIDAS automates the suggestion of good-quality web sources and describes what to extract with respect to augmenting an existing knowledge base. We make three major contributions. First, we introduce a novel concept, web source slices, to describe the contents of a web source. Second, we define a profit function to quantify the value of a web source slice with respect to augmenting an existing knowledge base. Third, we develop effective and highly-scalable algorithms to derive high-profit web source slices. We demonstrate that MIDAS produces high-profit results and outperforms the baselines significantly on both real-world and synthetic datasets.

Nowadays, a large portion of clinical data only exists in free text. The wide adoption of Electronic Health Records (EHRs) has enabled the increases in accessing to clinical documents, which provide challenges and opportunities for clinical Natural Language Processing (NLP) researchers. Given free-text clinical notes as input, an ideal system for clinical text understanding should have the ability to support clinical decisions. At corpus level, the system should recommend similar notes based on disease or patient types, and provide medication recommendation, or any other type of recommendations, based on patients' symptoms and other similar medical cases. At document level, it should return a list of important clinical concepts. Moreover, the system should be able to make diagnostic inferences over clinical concepts and output diagnosis. Unfortunately, current work has not systematically studied this system. This study focuses on developing and applying methods/techniques in different aspects of the system for clinical text understanding, at both corpus and document level. We deal with two major research questions: First, we explore the question of How to model the underlying relationships from clinical notes at corpus level? Documents clustering methods can group clinical notes into meaningful clusters, which can assist physicians and patients to understand medical conditions and diseases from clinical notes. We use Nonnegative Matrix Factorization (NMF) and Multi-view NMF to cluster clinical notes based on extracted medical concepts. The clustering results display latent patterns existed among clinical notes. Our method provides a feasible way to visualize a corpus of clinical documents. Based on extracted concepts, we further build a symptom-medication (Symp-Med) graph to model the Symp-Med relations in clinical notes corpus. We develop two Symp-Med matching algorithms to predict and recommend medications for patients based on their symptoms. Second, we want to solve the question of How to integrate structured knowledge with unstructured text to improve results for Clinical NLP tasks? On the one hand, the unstructured clinical text contains lots of information about medical conditions. On the other hand, structured Knowledge Bases (KBs) are frequently used for supporting clinical NLP tasks. We propose graph-regularized word embedding models to integrate knowledge from both KBs and free text. We evaluate our models on standard datasets and biomedical NLP tasks, and results showed encouraging improvements on both datasets. We further apply the graph-regularized word embedding models and present a novel approach to automatically infer the most probable diagnosis from a given clinical narrative.

Being able to undertake more efficient maintenance and renewal planning of road networks has seen a number of pavement management systems (PMS) being developed between the 80s to mid-90s. During the initial years, there was a significant focus on substantiating the need and demonstrating the benefits of using these tools to assist in the investment planning for roads. Today, with substantial experience, and legislative support such as MAP-21 and PASS-55, the use of PMS in the asset management cycle of roads is a given. The challenge these days is to effectively use these tools and ensure robust outcomes are achieved from the overall PMS process. The success of any PMS is determined by a number of factors including having skilled resources, institutional support, and legislative and funding drivers demanding evidence-based forecasted investment needs. Asset managers also realize the importance of having technical robustness in the process to ensure likely outcomes. This paper documents the evolutionary development pathway of the New Zealand PMS that has now been in use across the entire country for more than 18 years. It shows how by always challenging the status quo it has resulted in consistently increasing the overall robustness of the system. In particular, it shows how different validation techniques have been used to improve the practicality and appropriateness of long-term forecasting capabilities.

BackgroundMining logic rules from structured knowledge bases is the basis of knowledge engineering. Due to the NP‐hardness of the rule mining problem, logic rules cannot be efficiently induced from knowledge bases, especially large‐scale ones.IdeaIn this article, we propose a compact and efficient index structure for the maintenance of the intermediate data during top‐down rule mining, such that the memory consumption can be reduced and mining efficiency can be improved.Developing PointsThe index is based on a mapping from constant symbols to integers and the sorting of the mapped integers. Index update has been dissembled into four basic operations. Moreover, the index itself acts as the cache during top‐down mining.ValueMost contributions in existing works employ algorithmic and architectural optimizations to improve efficiency. Data‐oriented optimizations have also been explored to some extent, but the data efficiency is relatively low, and the memory consumption is thus becoming a new challenge for state‐of‐the‐art systems. We tackle this challenge in this article, and our technique has been proven more efficient than state‐of‐the‐art systems. We evaluate our method on six datasets which contain up to 160 K records and are frequently used as benchmarks in tasks related to knowledge engineering. The experimental results show that the proposed technique speeds up the rule mining procedure by on average and reduces memory consumption by up to 70%. The space overhead of the data structure is about twice that of the indexed records, which is more than 80% lower than that of the state‐of‐the‐art technique.

Knowledge-based systems (KBS) are not necessarily based on a well-defined ontologies. In particular it is possible to build very successful KBS for classification problems, but where the classes or conclusions are entered by experts as free-text sentences with little constraint on textual consistency and little systematic organisation of the conclusions. This paper investigates how relations between such ‘classes’ may be discovered from existing knowledge bases. We have based our approach on KBS built with Ripple Down Rules (RDR). RDR is a knowledge acquisition and knowledge maintenance method which allows KBS to be built very rapidly and simply by correcting errors, but does not require a strong ontology. Our experimental results are based on a large real-world medical RDR KBS. The motivation for our work is to allow an ontology in a KBS to ‘emerge’ during development, rather than requiring the ontology to be established prior to the development of the KBS. It follows earlier work on using Formal Concept Analysis (FCA) to discover ontologies in RDR KBS.KeywordsKnowledge AcquisitionConcept LatticeClass RelationFormal ContextFormal Concept AnalysisThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Logical Approaches to Structured Knowledge Bases