Construction Of Knowledge Base Research Articles

Jointly Extracting Multiple Triplets with Multilayer Translation Constraints

Triplets extraction is an essential and pivotal step in automatic knowledge base construction, which captures structural information from unstructured text corpus. Conventional extraction models use a pipeline of named entity recognition and relation classification to extract entities and relations, respectively, which ignore the connection between the two tasks. Recently, several neural network-based models were proposed to tackle the problem, and achieved state-of-the-art performance. However, most of them are unable to extract multiple triplets from a single sentence, which are yet commonly seen in real-life scenarios. To close the gap, we propose in this paper a joint neural extraction model for multitriplets, namely, TME, which is capable of adaptively discovering multiple triplets simultaneously in a sentence via ranking with translation mechanism. In experiment, TME exhibits superior performance and achieves an improvement of 37.6% on F1 score over state-of-the-art competitors.

Comprehensive structured knowledge base system construction with natural language presentation

Constructing an ontology-based machine-readable knowledge base system from different sources with minimum human intervention, also known as ontology-based machine-readable knowledge base construction (OMRKBC), has been a long-term outstanding problem. One of the issues is how to build a large-scale OMRKBC process with appropriate structural information. To address this issue, we propose Natural Language Independent Knowledge Representation (NLIKR), a method which regards each word as a concept which should be defined by its relations with other concepts. Using NLIKR, we propose a framework for the OMRKBC process to automatically develop a comprehensive ontology-based machine-readable knowledge base system (OMRKBS) using well-built structural information. Firstly, as part of this framework, we propose formulas to discover concepts and their relations in the OMRKBS. Secondly, the challenges in obtaining rich structured information are resolved through the development of algorithms and rules. Finally, rich structured information is built in the OMRKBS. OMRKBC allows the efficient search of words and supports word queries with a specific attribute. We conduct experiments and analyze the results of relational information extraction, with the results showing that OMRKBS had an accuracy of 84% which was higher than the other knowledge base systems, namely ConceptNet, DBpedia and WordNet.

Tea Plant Information Archive: a comprehensive genomics and bioinformatics platform for tea plant.

SummaryTea is the world's widely consumed nonalcohol beverage with essential economic and health benefits. Confronted with the increasing large‐scale omics‐data set particularly the genome sequence released in tea plant, the construction of a comprehensive knowledgebase is urgently needed to facilitate the utilization of these data sets towards molecular breeding. We hereby present the first integrative and specially designed web‐accessible database, Tea Plant Information Archive (TPIA; http://tpia.teaplant.org). The current release of TPIA employs the comprehensively annotated tea plant genome as framework and incorporates with abundant well‐organized transcriptomes, gene expressions (across species, tissues and stresses), orthologs and characteristic metabolites determining tea quality. It also hosts massive transcription factors, polymorphic simple sequence repeats, single nucleotide polymorphisms, correlations, manually curated functional genes and globally collected germplasm information. A variety of versatile analytic tools (e.g. JBrowse, blast, enrichment analysis, etc.) are established helping users to perform further comparative, evolutionary and functional analysis. We show a case application of TPIA that provides novel and interesting insights into the phytochemical content variation of section Thea of genus Camellia under a well‐resolved phylogenetic framework. The constructed knowledgebase of tea plant will serve as a central gateway for global tea community to better understand the tea plant biology that largely benefits the whole tea industry.

The study on construction and application of knowledge base based on TRIZ and bionics

The TRIZ and bionics are two main methods to guide invention and innovation, which have universal guiding significance to product concept innovation. However, the function of TRIZ is more specific and not conducive to expansion. In this paper, TRIZ function is extended by reclassifying and defining TRIZ function. Then the extended functions and biological functions are combined to build a knowledge base combining TRIZ and bionics. Engineers can use this knowledge base to accurately match imitation sources. It also helps designers improve design efficiency. Finally, the feasibility of the biological instance library is verified by the rib design of the flap-like flaps.

Development of information technology for the automated construction and expansion of the temporal knowledge base in the tasks of supporting management decisions

The object of research is the process of knowledge base (KB) constructing, which involves the development of a formal presentation of knowledge, knowledge extraction, verification of their consistency and inclusion in the KB. The implementation of such a process is a necessary condition to use KB in systems supporting management decisions at the tactical and strategic levels of organizational management. However, there is currently a discrepancy between the practical need for implementation, knowledge-based support for managerial decisions under uncertainty, taking into account the temporal aspect of managing action and also the possibilities of existing techniques and technologies of interactive and automated construction of the KB. The analysis of the research object testifies to the possibility of automated construction of the KB to support managerial decisions using temporal dependencies. The latter can be obtained based on the analysis of the sequence of states corresponds to the behavior of an organizational system as an object of management. Temporal dependencies between states represent the knowledge of control actions that have been implemented in managing decisions. The logical-probabilistic model of temporal knowledge representation is improved by taking into account the hierarchical description of the management solution context, which makes it possible to simplify the construction of this solution. The proposed model provides the ability to support a rational choice from a variety of admissible management decisions by the probability of transition to the target state of the control object. The method of automated construction and support of the temporal KB based on the account of the attributive description of the control object state and the context of the management solution is improved. The method involves the rapid formation and verification of the logical-probabilistic representation of temporal knowledge to support management decisions. The information technology of automated construction and replenishment of temporal KBs is developed. Technology combines the capability of generating representation patterns and semantic verification of knowledge. The verification is performed by a specialist in the subject area. The automatic construction of weighted temporal rules based on the detection of dependencies in known state sequences of the control object. This makes it possible to quickly identify the new temporal dependencies for the subject area and bring them to the KB after semantic verification by an expert.

Public security risk prevention and control support key technology research

Risk prevention and control is a process of taking measures to evade and resolve event risks based on risk source identification and risk assessment. Based on the relationship between risk prevention and control and emergency response, this research relies on modern information technology to propose a key technical system for marine environmental security risk prevention and control support including risk prevention and control knowledge base construction and risk prevention and control scheme generation technology. Through technical research, it provides technical support for the safe and efficient response of the marine environment.

Research on Learning OWL Ontology from Relational Database

Ontology learning is the pivotal technology to construct knowledge base efficiently, and the data of existing knowledge systems are mostly organized in relational mode. In order to reuse and share knowledge in existing knowledge systems, it is necessary to construct ontology for existing knowledge systems. After comparing and analyzing the formal definitions of relational data schema and ontology, this paper proposes a method of extracting knowledge ontology from relational data model. This method builds OWL ontology knowledge base architecture based on metadata of relational data schema, maps different data elements into components of OWL ontology, and implements with prototype tool based on Java platform. As a case study, this method is applied to transform the database of online examination system into OWL ontology model. The method proposed in this paper can be applied to the practice of transferring the widely existing relational-based knowledge base system to the knowledge base system based on OWL ontology framework.

Research on OWL Ontology Learning Method Based on Relational Schema

Ontology learning is the key technology to construct knowledge base effectively. Most of data in information systems are organized in relational mode. Therefore, the purpose of this paper is to solve how to effectively learn ontology from relational data mode. It is found that the definition of OWL DL ontology based on description logic is similar to the formal definition of relational data schema. A semi-automatic learning method of OWL ontology based on relational schema is proposed in this paper. The method includes a set of mapping rules by which learning OWL ontology from relational schema. The mapping rule set consists of attribute axiom mapping, class axiom mapping and heuristic mapping. Finally, a prototype tool based on Java platform is used to build a knowledge base of traditional Chinese medicine, and the validity of the method is verified.

Reinforcement Learning for Distantly Supervised Relation Extraction

Relation extraction is a task of identifying semantic relations between entity pairs from plain text, which can benefit a lot of AI applications such as knowledge base construction and answer questioning. The distant supervision strategy is introduced to automatically create large-scale training data, which inevitably suffers from noisy label problem. Recent works handle the sentence-level denoising by reinforcement learning, which regards the labels from distant supervision as the ground-truth. However, few works focus on the label-level denoising that corrects noisy labels directly. In this paper, we propose a reinforcement learning-based label denoising method for distantly supervised relation extraction. The model consists of two modules: extraction network (ENet) and policy network (PNet). The core of our label denoising is designing a policy in the PNet to obtain latent labels, where we can select the actions of using the distantly supervised labels or the predicted labels from the ENet. More concretely, the task can be modeled as an iterative process. First, the ENet predicts the relation probability, through which the model generates state representation. Second, the PNet learns the latent labels with taken actions and uses them to update the ENet. Then the optimized ENet gives the rewards to the PNet. The joint learning of two modules can obtain a reliable latent label and effectively improve the classification performance. The experimental results show that reinforcement learning is effective for noisy label correction and the proposed method can outperform the state-of-the-art relation extraction systems.

Evolutionary Method of Constructing Artificial Intelligence Systems

An evolutionary model of constructing artificial intelligence is presented, which is destined for designing and developing intelligent systems. The model allows describing a variety of subject areas with constructing knowledge bases. It has universal means to formally describe tasks and environments for implementing computational processes to solve them. The key basic element of the proposed model is the so-called ALF, i.e., an intelligent agent with the abilities to self-learning, communication, self-organization, and joint actions with similar agents. The development of ALF agents is based on evolutionary principles implemented using genetic algorithms. The proposed approach is implemented in the form of a game model. The developed structure and functionality of ALF agents stipulate the flexibility and efficiency of the model, which is confirmed by experiments.

A versatile approach for constructing a domain knowledge graph for culture

ABSTRACT[Question] The construction of cultural knowledge base in digital library is in progress with the development of information technology. However, traditional cultural knowledge bases are facing the problems of high participation of manual operation and monotonous data source. This paper combines knowledge graph, a frontier technology of artificial intelligence, to explore a new method of building high‐quality, automated cultural knowledge base. [Method] Using the experimental method, we selected the knowledge of the Hundred Schools of Thought in ancient China. Because these knowledges are clearly interrelated, it is suitable to construct the knowledge graph of them. The knowledge graph can provide experience for the construction of other cultural knowledge bases. [Conclusion] At present, this paper has preliminarily completed the experimental design of the knowledge graph of the Hundred Schools of Thought, and provided the flowchart of the construction of cultural domain knowledge graph.

Development of a data-based interactive medical expert system for supporting pregnancy consultations: general architecture and methodology

Innovations in telecommunication and online service solutions facilitate the emergence of remote medical diagnosis and treatment consultations. Using information and communication technologies (ICT’s), timely e-health services to individuals are becoming a viable alternative to traditional healthcare solutions, which reduces pressure on the health system. In our scenario for pregnant women, developing an interactive medical expert system connecting to a wearable device for supporting pregnancy consultations based on fetal movement signals is essential. In this paper, we demonstrate the general architecture of MES-SPC (Medical Expert System for Supporting Pregnancy Consultations), which consist of data collection layer, data management layer and application service layer. The three highlighted parts in our system includes: (1) The development of an IoT-based wearable devices for automatic fetal movement signal acquisition and identification. (2) An interface collecting real-time status of pregnant women through online conversations led by doctors. (3) The construction of a self-updating knowledge base including case-based reasoning, rule-based inference and knowledge graph search to assist doctors for decision making.

Intelligent acquisition model of traffic congestion information in the vehicle networking environment based on multi-sensor fusion

Aiming at the problems of low bandwidth, poor anti-interference ability and low-detection accuracy of traditional multi-path coherent vehicle network model, an intelligent acquisition model of traffic congestion information in vehicle network environment based on multi-features is proposed. The model clusters the traffic congestion information in the vehicle network and uses the multi-sensor fusion identification method to mine the traffic flow. In the vehicle networking environment, the vehicle traffic congestion information is analysed by information fusion theory, cross-fusion, text information, location information, image, audio, video and other information-aware technologies, and the coherent matching filter detector is used to realise the detection of traffic congestion information. And data collection, combined with knowledge base and database construction, is used to achieve intelligent collection and storage of traffic congestion information. The simulation results show that the model has high traffic congestion information acquisition accuracy and good feature matching ability, improves the intelligent acquisition ability, and detects the traffic congestion information in the vehicle network environment, thus guiding traffic scheduling.

A Knowledge-Based Method for Rapid Design Concept Evaluation

Concept generation is one of the most critical steps in product design process. Recently, several computational tools for automatically generating design concepts were developed, which can generate a big number of design concepts. This brings a new challenge to traditional expert-based design concept evaluation methods since experts are not capable of evaluating a large number of design concept in a short time. Therefore, this work develops a knowledge-based method to roughly evaluation design concepts and elect a small number of design concepts for expert-based evaluation. In the proposed method, a knowledge base containing 100 design concepts extracted from existing products is constructed, and four features, including Number of Function (#F), Function Compatibility Index (FCI), Function Component Mapping Index (FCMI) and Component Compatibility Index (CCI) are defined for building evaluation models. Based on the knowledge base and features, several computational evaluation models are developed including novelty evaluation model (NEM), feasibility discrimination model (FDM) and feasibility evaluation model (FEM). Empirical results show the proposed method is capable of evaluating design concepts. This work makes two-fold contributes to the research community, the first is a manually constructed knowledge base is published, while the second is four features are defined and used to define design concept evaluation models.

Support decision-making in information control systems using the temporal knowledge base

The subject matter of the article are the processes of using temporal knowledge to support decision-making on the control of composite objects within the framework of the enterprise functioning paradigm. The goal is to develop an integrated approach to building, as well as the use of temporal knowledge bases for analyzing the current state of the enterprise as an integral object at different levels of the organizational hierarchy and decision support for control. Tasks: to develop a model of the temporal knowledge base for the presentation of context-oriented temporal dependencies on the behavior of the control object; improve the method of detecting anomalous states of the control object based on the analysis of temporal data and knowledge; to present technologies for the automated construction and use of a temporal knowledge base to support decision-making on enterprise management. The methods used are: methods of construction knowledge bases and methods of supporting management in conditions of uncertainty. The following results were obtained. The following results were obtained. A model of a temporal knowledge base has been developed for use in information management systems. The method of detecting anomalous states of the control object in information control systems based on the use of temporal dependencies has been improved. Technologies for building and using a temporal knowledge base to support management decisions under uncertainty are proposed. Conclusions. The scientific novelty of the results obtained is as follows: A model of a temporal knowledge base has been developed, containing patterns and the realization of logical facts reflecting the state of the control object, as well as the rules establishing the links between these states over time. The model makes it possible to increase the efficiency of enterprise management in conditions of uncertainty based on an analysis of its current state and the derivation of permissible sequences of actions for the transition to a target state. The method for detecting anomalous states of a control object in information control systems has been improved by taking into account the connection between actions at the control object and the context for performing these actions. The method allows to take into account the current properties of the components of the complex control object to classify the current state in conditions of uncertainty. The proposed technology for the construction and use of a temporal knowledge base in information management systems that provide for the iterative replenishment of knowledge in the operation of an enterprise and their use in the context of incomplete information about the control object.

Identifying Principles for the Construction of an Ontology-Based Knowledge Base: A Case Study Approach.

BackgroundOntologies are key enabling technologies for the Semantic Web. The Web Ontology Language (OWL) is a semantic markup language for publishing and sharing ontologies.ObjectiveThe supply of customizable, computable, and formally represented molecular genetics information and health information, via electronic health record (EHR) interfaces, can play a critical role in achieving precision medicine. In this study, we used cystic fibrosis as an example to build an Ontology-based Knowledge Base prototype on Cystic Fibrobis (OntoKBCF) to supply such information via an EHR prototype. In addition, we elaborate on the construction and representation principles, approaches, applications, and representation challenges that we faced in the construction of OntoKBCF. The principles and approaches can be referenced and applied in constructing other ontology-based domain knowledge bases.MethodsFirst, we defined the scope of OntoKBCF according to possible clinical information needs about cystic fibrosis on both a molecular level and a clinical phenotype level. We then selected the knowledge sources to be represented in OntoKBCF. We utilized top-to-bottom content analysis and bottom-up construction to build OntoKBCF. Protégé-OWL was used to construct OntoKBCF. The construction principles included (1) to use existing basic terms as much as possible; (2) to use intersection and combination in representations; (3) to represent as many different types of facts as possible; and (4) to provide 2-5 examples for each type. HermiT 1.3.8.413 within Protégé-5.1.0 was used to check the consistency of OntoKBCF.ResultsOntoKBCF was constructed successfully, with the inclusion of 408 classes, 35 properties, and 113 equivalent classes. OntoKBCF includes both atomic concepts (such as amino acid) and complex concepts (such as “adolescent female cystic fibrosis patient”) and their descriptions. We demonstrated that OntoKBCF could make customizable molecular and health information available automatically and usable via an EHR prototype. The main challenges include the provision of a more comprehensive account of different patient groups as well as the representation of uncertain knowledge, ambiguous concepts, and negative statements and more complicated and detailed molecular mechanisms or pathway information about cystic fibrosis.ConclusionsAlthough cystic fibrosis is just one example, based on the current structure of OntoKBCF, it should be relatively straightforward to extend the prototype to cover different topics. Moreover, the principles underpinning its development could be reused for building alternative human monogenetic diseases knowledge bases.

ПРИНЦИПИ АВТОМАТИЗОВАНОЇ ПОБУДОВИ ТА ВИКОРИСТАННЯ ТЕМПОРАЛЬНОЇ БАЗИ ЗНАНЬ ДЛЯ ПІДТРИМКИ ПРИЙНЯТТЯ РІШЕНЬ З УПРАВЛІННЯ ПІДПРИЄМСТВОМ

Предметом вивчення в статті є процеси автоматизованої побудови й використання бази темпоральних знань для підтримки управління підприємством в умовах невизначеності, яка виникає в результаті неповноти інформації про стан підприємства як об’єкту управління. Мета полягає в розробці концепції автоматизованої побудови темпоральної бази знань, що містить контекстно-залежні знання про процеси управління в інформаційній системі та забезпечує можливість підтримки прийняття рішень з тактичного управління, а також можливість підтримки виконання на рівні стратегічного управління. Задачі: розробка принципів автоматизованої побудови темпоральної бази знань; впровадження розроблених принципів у вигляді концепції використання темпоральної бази знань для підтримки управління підприємством. Методами, що використовуються, є: методи побудови темпоральних правил та темпоральної баз знань, а також методи ймовірнісного виводу. Отримані такі результати. Розроблено принципи автоматизованої побудови й використання бази знань для підтримки управління підприємством в умовах невизначеності. На базі розроблених принципів запропоновано концепцію побудови темпоральної бази знань та реалізації логічного виводу для вирішення неструктурованих та частково структурованих задач. Висновки. Наукова новизна отриманих результатів полягає в наступному: Запропоновано принципи автоматизованої побудови та використання темпоральної бази знань для підтримки прийняття рішень в інформаційній системі, що відрізняються врахуванням темпоральних залежностей як для процесу управління, так і для об’єкту управління, а також можливостями інтеграції залежностей на різних рівнях організаційної ієрархії. Розроблені принципи та концепція забезпечують можливість побудови множини ймовірнісних рішень вирішення частково структурованих задач на тактичному рівні та неструктурованих задач на стратегічному рівні в умовах неповноти інформації щодо зовнішніх впливів та стану підприємства.

Encoding implicit relation requirements for relation extraction: A joint inference approach

Relation extraction is the task of identifying predefined relationship between entities, and plays an essential role in information extraction, knowledge base construction, question answering and so on. Most existing relation extractors make predictions for each entity pair locally and individually, while ignoring implicit global clues available across different entity pairs and in the knowledge base, which often leads to conflicts among local predictions from different entity pairs. This paper proposes a joint inference framework that employs such global clues to resolve disagreements among local predictions. We exploit two kinds of clues to generate constraints which can capture the implicit type and cardinality requirements of a relation. Those constraints can be examined in either hard style or soft style, both of which can be effectively explored in an integer linear program formulation. Experimental results on both English and Chinese datasets show that our proposed framework can effectively utilize those two categories of global clues and resolve the disagreements among local predictions, thus improve various relation extractors when such clues are applicable to the datasets. Our experiments also indicate that the clues learnt automatically from existing knowledge bases perform comparably to or better than those refined by human.

Bot Chat : Customer Relation dengan Teknologi Artificial Intelligence

<p><em>The application of Artificial Intelligence (AI) is increasingly massive in the industries. One of the advantages of implementing AI is operational efficiency, because by using AI that is implemented on computer machines, the use of human as an operator in an industry can be minimized. This certainly affects the operational efficiency of an organization. One form of AI implementation in the industries is the Chatbot program. Chatbot is a virtual program that is able to communicate like a human. In many cases, Chatbot take role in the Front-End section of an organization that functions as a customer relations medium. This paper aims to examine various techniques of developing Chatbot for the past 8 years in the academic research environment. In this paper there are 6 scientific articles reviewed focusing on the their techniques and methods of development. The results obtained show that there has been a shift or development of Chatbot's communication features, from the original symbol-based computer keyboard to audio-based speech recognition. Also, there are variations in the construction of knowledge bases, ranging from AIML to semantic based.</em></p>

Approach to Online Defect Monitoring in Fused Deposition Modeling Based on the Variation of the Temperature Field

According to the surface state of the product, a process quality monitoring technology based on a Qualitative Trend Analysis method is proposed. The construction of the product surface defect knowledge base provides a basis for online monitoring of the nozzle status of the fused deposition modeling (FDM) machine. Ten workpieces are designed in all, and each one conducts two prints which are normal and abnormal, respectively. An infrared thermal imager is used to obtain the temperature image of each layer of the workpiece surface; the feature values are extracted, and the difference between the feature values in the two kinds of printing is calculated. The Qualitative Trend Analysis method is used to analyze the difference in order to obtain the corresponding sensitive feature parameters corresponding to the starting points in different phases of the product printing. The change rules of the sensitive feature values are summarized, and the threshold of each starting point is solved. Base on that, the knowledge rules are defined and the defect knowledge base is constructed. Finally, a new experiment is designed to obtain the theoretical starting point of each state of the product surface in the building process. By comparing the theoretical starting point with the actual starting point, the feasibility of the knowledge rules in monitoring the nozzle working state is verified.