Domain Knowledge Base Research Articles

Research on Machine Learning Program Generation Algorithm Based on AORBCO

Abstract The design and development of machine learning programs require selecting appropriate data and algorithms, and coding and debugging based on specific task requirements and the programming experience of developers. However, the current knowledge structure in the field of machine learning is relatively complex, lacking systematic organization, and developers often face the problem of lack of experience when choosing algorithms and designing programs, resulting in a long development cycle and easy errors in machine learning programs. In response to the above issues, this article proposes and designs a machine learning program generation algorithm based on the AORBCO model. The program generation ability includes two sub abilities: algorithm decision-making ability and code generation ability. AD-EKG has been designed for algorithmic decision-making ability, allowing Ego to select appropriate machine learning algorithms based on datasets in massive data. This algorithm combines the characteristics of the AORBCO model's domain knowledge base, knowledge graph based recommendation algorithm, and collaborative filtering algorithm. By calculating the descriptive and structural information between the dataset and algorithm, the interaction probability between the dataset and algorithm is obtained, allowing Ego to make algorithmic decisions interaction probability based. Results of the experiment have shown that the AD-EKG algorithm can fully utilize structural and descriptive information to improve the accuracy of Ego algorithm decision-making. CodeT5-EKG has been designed for code generation capability, allowing Ego to automatically generate machine learning program code. This algorithm combines the CodeT5 generative model with the domain knowledge base of the AORBCO model, by adding auxiliary information extracted using DPR technology to the code generation task, and performing diversified fusion operations to improve code generation quality. The CodeT5-EKG algorithm combines the creativity and efficiency of generative models and DPR technology, and is an algorithm that can improve the quality of generated code while also having the advantages of generative models. The experiments have proved that the code generated by this algorithm has better quality compared to other generative models with the same number of parameters.

Acupuncture and tuina knowledge graph with prompt learning.

Acupuncture and tuina, acknowledged as ancient and highly efficacious therapeutic modalities within the domain of Traditional Chinese Medicine (TCM), have provided pragmatic treatment pathways for numerous patients. To address the problems of ambiguity in the concept of Traditional Chinese Medicine (TCM) acupuncture and tuina treatment protocols, the lack of accurate quantitative assessment of treatment protocols, and the diversity of TCM systems, we have established a map-filling technique for modern literature to achieve personalized medical recommendations. (1) Extensive acupuncture and tuina data were collected, analyzed, and processed to establish a concise TCM domain knowledge base. (2)A template-free Chinese text NER joint training method (TemplateFC) was proposed, which enhances the EntLM model with BiLSTM and CRF layers. Appropriate rules were set for ERE. (3) A comprehensive knowledge graph comprising 10,346 entities and 40,919 relationships was constructed based on modern literature. A robust TCM KG with a wide range of entities and relationships was created. The template-free joint training approach significantly improved NER accuracy, especially in Chinese text, addressing issues related to entity identification and tokenization differences. The KG provided valuable insights into acupuncture and tuina, facilitating efficient information retrieval and personalized treatment recommendations. The integration of KGs in TCM research is essential for advancing diagnostics and interventions. Challenges in NER and ERE were effectively tackled using hybrid approaches and innovative techniques. The comprehensive TCM KG our built contributes to bridging the gap in TCM knowledge and serves as a valuable resource for specialists and non-specialists alike.

Construction contract risk identification based on knowledge-augmented language models

Contract review is an essential step in construction projects to prevent potential losses. However, the current methods for reviewing construction contracts lack effectiveness and reliability, leading to time-consuming and error-prone processes. Although large language models (LLMs) have shown promise in revolutionizing natural language processing (NLP) tasks, they struggle with domain-specific knowledge and addressing specialized issues. This paper presents a novel approach that leverages LLMs with construction contract knowledge to emulate the process of contract review by human experts. Our tuning-free approach incorporates construction contract domain knowledge to enhance language models for identifying construction contract risks. The use of natural language when building the domain knowledge base facilitates practical implementation. We evaluated our method on real construction contracts and achieved solid performance. Additionally, we investigated how LLMs employ logical thinking during the task and provided insights and recommendations for future research.

TREE-GPT: MODULAR LARGE LANGUAGE MODEL EXPERT SYSTEM FOR FOREST REMOTE SENSING IMAGE UNDERSTANDING AND INTERACTIVE ANALYSIS

Abstract. This paper introduces a novel framework, Tree-GPT, which incorporates Large Language Models (LLMs) into the forestry remote sensing data workflow, thereby enhancing the efficiency of data analysis. Currently, LLMs are unable to extract or comprehend information from images and may generate inaccurate text due to a lack of domain knowledge, limiting their use in forestry data analysis. To address this issue, we propose a modular LLM expert system, Tree-GPT, that integrates image understanding modules, domain knowledge bases, and toolchains. This empowers LLMs with the ability to comprehend images, acquire accurate knowledge, generate code, and perform data analysis in a local environment. Specifically, the image understanding module extracts structured information from forest remote sensing images by utilizing automatic or interactive generation of prompts to guide the Segment Anything Model (SAM) in generating and selecting optimal tree segmentation results. The system then calculates tree structural parameters based on these results and stores them in a database. Upon receiving a specific natural language instruction, the LLM generates code based on a thought chain to accomplish the analysis task. The code is then executed by an LLM agent in a local environment and . For ecological parameter calculations, the system retrieves the corresponding knowledge from the knowledge base and inputs it into the LLM to guide the generation of accurate code. We tested this system on several tasks, including Search, Visualization, and Machine Learning Analysis. The prototype system performed well, demonstrating the potential for dynamic usage of LLMs in forestry research and environmental sciences.

Business model innovation: Integrative review, framework, and agenda for future innovation management research

AbstractThe business model innovation (BMI) concept has become a well‐established phenomenon of current academic research. While Foss and Saebi's (Journal of Management, 2017, 43, 200–227) seminal literature review on BMI revealed 349 articles on BMI published between 1972 and 2015, an additional number of 1727 articles on the topic have been published since 2016. In contrast to this overall interest in the BMI phenomenon, innovation‐focused journals include only a limited number of publications on BMI. Further, besides the valuable insights and fruitful research directions of extant literature reviews, they tend also to overlook the linkages between traditional innovation management and the majority of BMI research. Given this underrepresentation of BMI research in the innovation management literature, we conduct an integrative literature review to bring the disconnected literature closer together and offer directions for future research. Our literature review applies the review strategy of blending and merging the literature across domains. First, we blend the knowledge base of the BMI domain by applying the Product Development and Management Association (PDMA) Body of Knowledge categories. Second, we merge the literature across domains by developing an integrative framework. As recent BMI literature increasingly converged to two lines of research, our framework differentiates between the relatedness of the BMI and BMI openness. Thereby, we offer new avenues for future research that can enrich the dialogue on BMI research in the innovation management community. These results demonstrate how the BMI domain covers aspects that fit, contribute to, and extend classical innovation‐focused research, how both research domains can be merged to enrich each other, and how future research can foster the dialogue across disconnected domains.

AIMS: An Automatic Semantic Machine Learning Microservice Framework to Support Biomedical and Bioengineering Research.

The fusion of machine learning and biomedical research offers novel ways to understand, diagnose, and treat various health conditions. However, the complexities of biomedical data, coupled with the intricate process of developing and deploying machine learning solutions, often pose significant challenges to researchers in these fields. Our pivotal achievement in this research is the introduction of the Automatic Semantic Machine Learning Microservice (AIMS) framework. AIMS addresses these challenges by automating various stages of the machine learning pipeline, with a particular emphasis on the ontology of machine learning services tailored to the biomedical domain. This ontology encompasses everything from task representation, service modeling, and knowledge acquisition to knowledge reasoning and the establishment of a self-supervised learning policy. Our framework has been crafted to prioritize model interpretability, integrate domain knowledge effortlessly, and handle biomedical data with efficiency. Additionally, AIMS boasts a distinctive feature: it leverages self-supervised knowledge learning through reinforcement learning techniques, paired with an ontology-based policy recording schema. This enables it to autonomously generate, fine-tune, and continually adapt to machine learning models, especially when faced with new tasks and data. Our work has two standout contributions demonstrating that machine learning processes in the biomedical domain can be automated, while integrating a rich domain knowledge base and providing a way for machines to have self-learning ability, ensuring they handle new tasks effectively. To showcase AIMS in action, we have highlighted its prowess in three case studies of biomedical tasks. These examples emphasize how our framework can simplify research routines, uplift the caliber of scientific exploration, and set the stage for notable advances.

Keyword Extraction-based Library Intelligence Services: Challenges, Adaptations and Reinvention

Abstract This paper proposes a domain knowledge base construction platform for thematic intelligence services of library intelligence institutions. The platform proposes a keyword extraction algorithm applicable to the literature resources of library intelligence services based on a statistical model and N-Gram model combined with feature word information. The automatic summary algorithm based on statistics combines the information of sentence content and location to comprehensively evaluate the weights of candidate summary sentences and achieve automatic summary extraction. Based on the HDP topic model, a literature recommendation model oriented to the resource retrieval context is proposed, which can convert the literature feature similarity calculation to the topic similarity calculation with implied literature feature semantics from the perspective of semantic analysis and improve the accuracy of recommended literature. The technical feasibility of this system platform is verified through relevant data experiments. Regarding the accuracy of the literature recommendation, the platform of this paper and the traditional method are 86.36% and 75.16%, respectively, and the recall rate is 67.29% and 57.25%, respectively. The platform scored 3.85 on the comprehensive evaluation of library intelligence service, close to the excellent level. Therefore, the platform can realize various functions, from resource collection and organization to resource processing and utilization, with certain practical significance.

The application of knowledge graphs in the Chinese cultural field: the ancient capital culture of Beijing

A methodology is proposed to introduce knowledge graphs into the study of the Chinese cultural field for use in a newly designed, complete application. At present, the combination of culture and information technology has become a trend. Among various technologies, knowledge graphs are a very promising option. The contributions of this paper are as follows: it supplies for the first time a knowledge graph in the cultural field of the ancient capital of Beijing, establishes a domain knowledge base, and develops a platform for visual analysis and interactive question and answer. In this process, a framework for applying knowledge graphs to research in the cultural field is summarized, providing ideas for research in the cultural field.

An Ontology-Based Question Answering System for University Admissions Advising

Question-Answer systems are now very popular and crucial to support human in automatically responding frequent questions in many fields. However, these systems depend on learning methods and training data. Therefore, it is necessary to prepare such a good dataset, but it is not an easy job. An ontology-based domain knowledge base is able to help to reason semantic information and make effective answers given user questions. This study proposes a novel chatbot model involving ontology to generate efficient responses automatically. A case study of admissions advising at the International University–VNU HCMC is taken into account in the proposed chatbot. A domain ontology is designed and built based on the domain knowledge of university admissions using Protégé. The Web user interface of the proposed chatbot system is developed as a prototype using NetBeans. It includes a search engine reasoning the ontology and generating answers to users’ questions. Two experiments are carried out to test how the system reacts to different questions. The first experiment examines questions made from some templates, and the second one examines normal questions taken from frequent questions. Experimental results have shown that the ontology-based chatbot can release meaningful and long answers. The results are analysed to prove the proposed chatbot is usable and promising.

CIViCdb 2022: evolution of an open-access cancer variant interpretation knowledgebase.

CIViC (Clinical Interpretation of Variants in Cancer; civicdb.org) is a crowd-sourced, public domain knowledgebase composed of literature-derived evidence characterizing the clinical utility of cancer variants. As clinical sequencing becomes more prevalent in cancer management, the need for cancer variant interpretation has grown beyond the capability of any single institution. CIViC contains peer-reviewed, published literature curated and expertly-moderated into structured data units (Evidence Items) that can be accessed globally and in real time, reducing barriers to clinical variant knowledge sharing. We have extended CIViC's functionality to support emergent variant interpretation guidelines, increase interoperability with other variant resources, and promote widespread dissemination of structured curated data. To support the full breadth of variant interpretation from basic to translational, including integration of somatic and germline variant knowledge and inference of drug response, we have enabled curation of three new Evidence Types (Predisposing, Oncogenic and Functional). The growing CIViC knowledgebase has over 300 contributors and distributes clinically-relevant cancer variant data currently representing>3200 variants in>470 genes from>3100 publications.

Ballast Water Dynamic Allocation Optimization for Revolving Floating Cranes Based on a Hybrid Algorithm of Fuzzy-Particle Swarm Optimization with Domain Knowledge

Ballast systems and ballast water dynamic allocation between ballast tanks are very important for ensuring the offshore operation efficiency and safety of the revolving floating crane (RFC). Its modeling and solving have multiple difficulties such as modeling complexity, solving complexity and engineering practicability. Early studies showed that domain knowledge is of great significance for the optimization of the design quality and innovation of such complex engineering issues. By analyzing the coupled operation process characteristics among the floating crane, ship hull and ballast system, a ballast water allocation optimization model based on dynamic programming strategy is established. The domain knowledge of ship ballasting is extracted, and a domain knowledge base of expert experience rules for the ballast water allocation is established. A Fuzzy-Particle Swarm Optimization (FPSO) algorithm is given to obtain the optimal allocation scheme, which uses fuzzy logic inference to process domain knowledge and improve the solving quality. Three different cases are given to illustrate the validity of the proposed model and algorithm by comparing it with other algorithms. The analysis results show that the established optimization method can effectively improve the operation efficiency and reduce the calculation time and the number of ballast tanks involved in allocation, which makes the optimal scheme more suitable for engineering applications.

Deep learning based high similarity automatic retrieval algorithm for vocabulary interpretation of workers of Food Sector in china

In order to build a high similarity English vocabulary interpretation domain knowledge base and ensure the automatic retrieval effect of high similarity English vocabulary interpretation, this paper standardizes the automatic retrieval specification of authoritative interpretation of high similarity English vocabulary knowledge, and takes high similarity English vocabulary as the source corpus of the knowledge base. On the basis of the existing work, this paper attempts to propose an automatic retrieval algorithm of high similarity English word interpretation based on deep learning. The goal is to diversify the sources of high similarity English word knowledge and achieve the accuracy of automatic retrieval of word interpretation while ensuring a certain knowledge coverage. A suitable domain knowledge base of machine-readable dictionary is constructed through a new method It can not only provide accurate knowledge information for high similarity English vocabulary, but also provide retrieval verification for user needs analysis and high similarity English vocabulary indexing of snippet. The experimental results show that the algorithm based on deep learning is effective and can fully meet the research requirements.

Auxiliary Teaching System of Higher Mathematics Based on Random Matrix Model

With the development of computer technology, computers have become a part of people’s lives and the Internet has connected the world’s networks as a whole. Computer technology is changing people’s study, life, and work. People’s traditional education mode, thinking, content, method, and talent training program have a significant impact. The development from traditional to computer technology-based teaching methods has brought new developments and leaps in educational technology. This paper analyzes the research background, significance, and research status of the advanced mathematics auxiliary teaching system, introduces the related technologies and development modes used in the development of the system, and especially discusses the access database technology by ADO and the mathematical expression based on MathML language. Secondly, starting from the actual teaching, we analyze the functional requirements and performance requirements of the system in detail and make detailed planning and design for the system architecture, database selection, functional modules, etc. The design and implementation process of this teaching system are summarized. The teaching strategy inference engine is the key to the personalization and intelligence of the ICAI system. According to the learning models provided by different students, the system designs a corresponding teaching sequence for the learners by controlling the meta-knowledge of the domain knowledge base. The teaching strategy inference engine cuts the domain knowledge tree, selects the knowledge points suitable for the student, and sorts the selected knowledge points reasonably to generate an optimal teaching sequence. According to the students’ learning situation, combined with the teaching rules in the teaching rule library, the students’ grades are dynamically adjusted, so as to select new learning content for students and provide teaching suggestions in time. The student model is the premise of the ICAI system to achieve individualization and intelligence. The system makes a comprehensive evaluation and diagnosis of students through fuzzy comprehensive evaluation and fuzzy reasoning. On this basis, a cognitive student model is established, which is the teaching strategy that provided the basis for the formulation.

Combining attention with spectrum to handle missing values on time series data without imputation

In the development of predictive models, the problem of missing data is a critical issue that traditionally requires a two-step analysis. Data scientists analyze the patterns of missing values, select variables, impute missing values on the basis of domain knowledge, and then train a model. Models typically have their input sizes hardcoded, and have limitations in handling data with high missing rates or changes in available variables. We propose an attention-based neural network combined with a novel real number representation, which requires little work on manually selecting variables, and in which missing data can be overlooked, making imputation unnecessary. In this proposed model, data analysis can be one step, omitting the first step of imputing missing values. The study included data on 32,709 intensive care unit (ICU) admissions and 60 healthcare variables from the Medical Information Mart for Intensive Care (MIMIC)-IV. The proposed algorithm yielded an area under the receiver operating characteristic curve (AUC) of 0.842 (95% CIs: 0.828–0.856) when predicting prolonged length of stay in the ICU, outperforming current approaches using imputation methods. The proposed algorithm can be applied to a range of problems in data science, as it addresses the issue of incomplete data with automatic variable selection.

A conversational agent system for dietary supplements use

BackgroundDietary supplements (DS) have been widely used by consumers, but the information around the efficacy and safety of DS is disparate or incomplete, thus creating barriers for consumers to find information effectively. Conversational agent (CA) systems have been applied to healthcare domain, but there is no such system to answer consumers regarding DS use, although widespread use of DS. In this study, we develop the first CA system for DS use.MethodsOur CA system for DS use developed on the MindMeld framework, consists of three components: question understanding, DS knowledge base, and answer generation. We collected and annotated 1509 questions to develop a natural language understanding module (e.g., question type classifier, named entity recognizer) which was then integrated into MindMeld framework. CA then queries the DS knowledge base (i.e., iDISK) and generates answers using rule-based slot filling techniques. We evaluated the algorithms of each component and the CA system as a whole.ResultsCNN is the best question classifier with an F1 score of 0.81, and CRF is the best named entity recognizer with an F1 score of 0.87. The system achieves an overall accuracy of 81% and an average score of 1.82 with succ@3 + score of 76.2% and succ@2 + of 66% approximately.ConclusionThis study develops the first CA system for DS use using the MindMeld framework and iDISK domain knowledge base.

TECHNOLOGY FOR CREATING A DOMAIN KNOWLEDGE BASE OF QUESTION-ANSWERING SYSTEM BASED ON A LARGE-SCALE UNIVERSAL KNOWLEDGE BASE

Usage of question-answering systems has become a popular way to access knowledge bases that contain a large number of facts from different domains. Large-scale universal knowledge bases with open access, such as Wikidata, contain huge collections of facts. Although those bases cover the most significant part of the accumulated humankind knowledge, there are a number of reasons why their direct usage in question-answering systems can be less preferable than the creation of specialized domain knowledge bases based on them. This paper presents a technology for building a domain knowledge base for a dialogue system based on domain boundaries detection from an open large-scale universal knowledge base. It is based on a multi-step process of analyzing a large number of free-form questions on a given subject area that were collected using a crowdsourcing platform. The technology includes the correction of the original knowledge base ontological structure and its filling with additional content. The proposed technology is invariant to the original knowledge base and the modeling subject area. We tested it on the Wikidata knowledge base and six subject areas.

Semantic Association and Decision-Making for the Internet of Things Based on Partial Differential Fuzzy Unsupervised Models

This study presents an in-depth study and analysis of IoT semantic association and decision-making using a partial differential fuzzy unsupervised approach. It focuses on a semantic annotation framework for device metadata and a knowledge base construction method to further improve the interoperability of IoT domain knowledge by building a unified IoT domain knowledge base and designing and implementing a semantic IoT knowledge management and application generation system. The main proposal is an IoT generic domain ontology, which reuses the existing excellent ontologies of IoT as much as possible, extracts the commonly used concepts of the domain and combines them, and provides a unified semantic template for IoT applications. On the other hand, by applying the entity linking technique to the extension of the knowledge base and linking the structured metadata of devices to the corresponding entities of the background knowledge base, the domain knowledge base can be made to share the rich background knowledge. At the same time, the interoperability of heterogeneous IoT metadata between applications is enhanced by unifying data and concepts from different device applications to the same background knowledge base through entity alignment techniques. The semantic representation of events applicable to IoT application scenarios is investigated, and an IoT event ontology for representing abstract events and event relationships in IoT is designed; next, a domain ontology with IoT sensing and control event representation capability is constructed based on the IoT event ontology, in which the typical domain ontology (SSN) that can be used for IoT applications is followed by the ontology reuse principle is improved and extended to support the description of event types and interevent relationships, and the IoT event model is associated with the improved IoT base ontology through an ontology alignment approach. Finally, the IoT sensing and control ontology are validated by semantic modeling of device composition, component relationships, and operational processes based on the IoT sensing and control ontology.

Enhancing unsupervised medical entity linking with multi-instance learning

BackgroundA lot of medical mentions can be extracted from a huge amount of medical texts. In order to make use of these medical mentions, a prerequisite step is to link those medical mentions to a medical domain knowledge base (KB). This linkage of mention to a well-defined, unambiguous KB is a necessary part of the downstream application such as disease diagnosis and prescription of drugs. Such demand becomes more urgent in colloquial and informal situations like online medical consultation, where the medical language is more casual and vaguer. In this article, we propose an unsupervised method to link the Chinese medical symptom mentions to the ICD10 classification in a colloquial background.MethodsWe propose an unsupervised entity linking model using multi-instance learning (MIL). Our approach builds on a basic unsupervised entity linking method (named BEL), which is an embedding similarity-based EL model in this paper, and uses MIL training paradigm to boost the performance of BEL. First, we construct a dataset from an unlabeled large-scale Chinese medical consultation corpus with the help of BEL. Subsequently, we use a variety of encoders to obtain the representations of mention-context and the ICD10 entities. Then the representations are fed into a ranking network to score candidate entities.ResultsWe evaluate the proposed model on the test dataset annotated by professional doctors. The evaluation results show that our method achieves 60.34% accuracy, exceeding the fundamental BEL by 1.72%.ConclusionsWe propose an unsupervised entity linking method to the entity linking in the medical domain, using MIL training manner. We annotate a test set for evaluation. The experimental results show that our model behaves better than the fundamental model BEL, and provides an insight for future research.

Estrazione automatica delle caratteristiche del personaggio d’opera attraverso pattern lessico-sintattici

The paper presents the experimentation of rules based on syntactic patterns for the extraction of interpersonal relationships between characters from the opera repertoire of the 18th century. The study illustrates the application of this unsupervised approach to identify this kind of relationships described within the captions accompanying the lists of characters in the librettos. The results demonstrate the effectiveness of the proposed solution in extracting relations defined through formal ontologies with a precision that allows them to be included in a domain knowledge base without further supervision. The experimentation contributes to the elaboration of a formal model for the description of the features of opera characters required for the reconstruction of their profiles. Given the size of the repertoire under examination and the number of characters, the use of automated analysis offers the researcher a useful tool to support the critical analysis of the sources. The ability to reconstruct the network of relationships and the features of the characters is in turn preparatory to the use of the character as a dimension of analysis to reconstruct the complex tradition of this kind of texts.

Full-Abstract Biomedical Relation Extraction with Keyword-Attentive Domain Knowledge Infusion

Relation extraction (RE) is an essential task in natural language processing. Given a context, RE aims to classify an entity-mention pair into a set of pre-defined relations. In the biomedical field, building an efficient and accurate RE system is critical for the construction of a domain knowledge base to support upper-level applications. Recent advances have witnessed a focus shift from sentence to document-level RE problems, which are more challenging due to the need for inter- and intra-sentence semantic reasoning. This type of distant dependency is difficult to understand and capture for a learning algorithm. To address the challenge, prior efforts either attempted to improve the cross sentence text representation or infuse domain or local knowledge into the model. Both strategies demonstrated efficacy on various datasets. In this paper, a keyword-attentive knowledge infusion strategy is proposed and integrated into BioBERT. A domain keyword collection mechanism is developed to discover the most relation-suggestive word tokens for bio-entities in a given context. By manipulating the attention masks, the model can be guided to focus on the semantic interaction between bio-entities linked by the keywords. We validated the proposed method on the Biocreative V Chemical Disease Relation dataset with an F1 of 75.6%, outperforming the state-of-the-art by 5.6%.