Knowledge Model Research Articles

The Tpack model as a hybrid training oportunity in masters and postgraduates degrees

In the 2020-2021 academic year, during the pandemic, the teaching team of the Master Social and Educational Interventions of the University of Barcelona applied the Technological Pedagogical Content Knowledge (TPACK) model, which integrates technology in the teaching-learning processes (Mishra & Koehler, 2006). A participatory evaluative research (Redice Redice20-2861), with the participation of faculty and students involved, was carried out to identify the elements that facilitate and hinder virtual teaching, to know the impact of its application and to formulate recommendations applicable to online university higher education. A mixed quantitative and qualitative methodology was used, employing different instruments such as questionnaires, focus groups, interviews and observations during the 2020-2021 academic year, analyzed with NVivo 11, Atlas.ti 8.0 and Excel. The results obtained show that the application of digital environment activities within face-to-face training improve, among others, the connection with the professional world and offer dynamization strategies in the classroom that contribute to the creation of learning communities as an effective strategy.

A unified industrial large knowledge model framework in Industry 4.0 and smart manufacturing

The recent emergence of large language models (LLMs) demonstrates the potential for artificial general intelligence, revealing new opportunities in Industry 4.0 and smart manufacturing. However, a notable gap exists in applying these LLMs in industry, primarily due to their training on general knowledge rather than domain-specific knowledge. Such specialized domain knowledge is vital for effectively addressing the complex needs of industrial applications. To bridge this gap, this paper proposes a unified industrial large knowledge model (ILKM) framework, emphasizing its potential to revolutionize future industries. In addition, ILKMs and LLMs are compared from eight perspectives. Finally, the “6S Principle” is proposed as the guideline for ILKM development, and several potential opportunities are highlighted for ILKM deployment in Industry 4.0 and smart manufacturing.

Sustainable IoT Security in Entrepreneurship: Leveraging Univariate Feature Selection and Deep CNN Model for Innovation and Knowledge

Due to the rapid increase in Internet of Things (IoT) devices in entrepreneurial environments, innovative cybersecurity advancements are needed to defend against escalating cyber threats. The present paper proposes an approach involving univariate feature selection leading to Sustainable IoT security. This method aims at increasing the efficiency and accuracy of the deep Convolutional Neural Network (CNN) model concerning botnet attack detection and mitigation. The approach to obtaining Sustainable IoT Security goes beyond the focus on technical aspects by proving that increased cybersecurity in IoT environments also fosters entrepreneurship in terms of stimulation, knowledge increase, and innovation. This approach is a major step towards providing entrepreneurs with the necessary tools to protect them in this digital era, which will enable and support the defense against cyber threats. A secure, innovative, and knowledgeable entrepreneurial environment is the result of Sustainable IoT security.

MoCab: A framework for the deployment of machine learning models across health information systems

Background and Objective:Machine learning models are vital for enhancing healthcare services. However, integrating them into health information systems (HISs) introduces challenges beyond clinical decision making, such as interoperability and diverse electronic health records (EHR) formats. We proposed Model Cabinet Architecture (MoCab), a framework designed to leverage fast healthcare interoperability resources (FHIR) as the standard for data storage and retrieval when deploying machine learning models across various HISs, addressing the challenges highlighted by platforms such as EPOCH®, ePRISM®, KETOS, and others. Methods:The MoCab architecture is designed to streamline predictive modeling in healthcare through a structured framework incorporating several specialized parts. The Data Service Center manages patient data retrieval from FHIR servers. These data are then processed by the Knowledge Model Center, where they are formatted and fed into predictive models. The Model Retraining Center is crucial in continuously updating these models to maintain accuracy in dynamic clinical environments. The framework further incorporates Clinical Decision Support (CDS) Hooks for issuing clinical alerts. It uses Substitutable Medical Apps Reusable Technologies (SMART) on FHIR to develop applications for displaying alerts, prediction results, and patient records. Results:The MoCab framework was demonstrated using three types of predictive models: a scoring model (qCSI), a machine learning model (NSTI), and a deep learning model (SPC), applied to synthetic data that mimic a major EHR system. The implementations showed how MoCab integrates predictive models with health data for clinical decision support, utilizing CDS Hooks and SMART on FHIR for seamless HIS integration. The demonstration confirmed the practical utility of MoCab in supporting clinical decision making, validated by its application in various healthcare settings. Conclusions:We demonstrate MoCab’s potential in promoting the interoperability of machine learning models and enhancing its utility across various EHRs. Despite facing challenges like FHIR adoption, MoCab addresses key challenges in adapting machine learning models within healthcare settings, paving the way for further enhancements and broader adoption.

An Oversampling Technique with Descriptive Statistics

Oversampling is often applied as a means to win a better knowledge model. Several oversampling methods based on synthetic instances have been suggested, and SMOTE is one of the representative oversampling methods that can generate synthetic instances of a minor class. Until now, the oversampled data has been used conventionally to train machine learning models without statistical analysis, so it is not certain that the machine learning models will be fine for unseen cases in the future. However, because such synthetic data is different from the original data, we may wonder how much it resembles the original data so that the oversampled data is worth using to train machine learning models. For this purpose, I conducted this study on a representative dataset called wine data in the UCI machine learning repository, which is one of the datasets that has been experimented with by many researchers in research for knowledge discovery models. I generated synthetic data iteratively using SMOTE, and I compared the synthetic data with the original data of wine to see if it was statistically reliable using a box plot and t-test. Moreover, since training a machine learning model by supplying more high-quality training instances increases the probability of obtaining a machine learning model with higher accuracy, it was also checked whether a better machine learning model of random forests can be obtained by generating much more synthetic data than the original data and using it for training the random forests. The results of the experiment showed that small-scale oversampling produced synthetic data with statistical characteristics that were statistically slightly different from the original data, but when the oversampling rate was relatively high, it was possible to generate data with statistical characteristics similar to the original data, in other words, after generating high-quality training data, and by using it to train the random forests, it was possible to generate random forests with higher accuracy than using the original data alone, from 97.75% to 100%. Therefore, by supplying additional statistically reliable synthetic data as a way of oversampling, it was possible to create a machine-learning model with a higher predictive rate.

Practice Trends in (C)APD Assessment and Management: A Survey of Audiologists in Kerala.

Aims Present study investigates the current trends in (Central) Auditory Processing Disorder [(C)APD] assessment and management practices among Audiologists practicing in Kerala, India. Materials and Methods The questionnaire for the survey was developed based on the Knowledge, Attitude, and Practices(KAP) model and underwent validation by experts in Audiology. Online survey was conducted to collect data from Audiologists practicing in Kerala, with a valid RCI-CRR number. Descriptive statistics were used to analyze the responses. Results The majority of participants held bachelor's degrees and completed training modules on the assessment of (C)APD during their undergraduate studies. However, clinical exposure was very low. Even though 59.2% of participants reported that they were performing screening for (C)APD, the use of standardized screening tools was limited. Only 35% of participants reported that they were performing diagnostic evaluation. However, the rest of the participants used only speech-in-noise tests for (C)APD evaluation. The participants who performed management of (C)APD were even fewer, at only 13.4%. Lack of facilities, inadequate patient load, and lack of practical exposure were major obstacles to (C)APD assessment and management. The majority of participants strongly agreed that Audiologists are the most qualified persons to deal with (C)APD; however, the practice trends obtained from the study suggest that Audiologists have a really poor practice in this area. Conclusion The study highlights the need for standardized assessment tools, improved training opportunities, and increased awareness among Audiologists regarding (C)APD. Multidisciplinary collaboration and further research are essential for enhancing (C)APD assessment and management practices in Kerala.

Imprecise Bayesian optimization

Bayesian optimization (BO) with Gaussian processes (GPs) surrogate models is widely used to optimize analytically unknown and expensive-to-evaluate functions. In this paper, we propose a robust version of BO grounded in the theory of imprecise probabilities: Prior-mean-RObust Bayesian Optimization (PROBO). Our method is motivated by an empirical and theoretical analysis of the GP prior specifications’ effect on BO’s convergence. A thorough simulation study finds the prior’s mean parameters to have the highest influence on BO’s convergence among all prior components. We thus turn to this part of the prior GP in more detail. In particular, we prove regret bounds for BO under misspecification of GP prior’s mean parameters. We show that sublinear regret bounds become linear under GP misspecification but stay sublinear if the misspecification-induced error is bounded by the variance of the GP. In response to these empirical and theoretical findings, we introduce PROBO as a univariate generalization of BO that avoids prior mean parameter misspecification. This is achieved by explicitly accounting for prior GP mean imprecision via a prior near-ignorance model. We deploy our approach on graphene production, a real-world optimization problem in materials science, and observe PROBO to converge faster than classical BO.11Open Science: Implementations of PROBO and reproducible scripts for the experimental analysis as well as all reported data are available at: https://github.com/rodemann/imprecise-bayesian-optimization.22Some parts of an earlier version of this work have been presented at the Ninth International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making (IUKM) and published in the corresponding proceedings [1], see Appendix D for details.

Continuing Education and Curriculum: Complementary Dimensions of Education

Objective: This study aimed to carry out an investigative review, under the State of Knowledge model, which addresses the curriculum in continuing education in order to look for evidence that continuing education improves/reframes/refutes the conception of curriculum. Theoretical Framework: The incessant search for quality education seems to be the keynote of the ongoing training available to teachers with the most varied themes and formats. Continuing professional improvement and critical reflection on pedagogical practice, as well as the need to review the simplistic view of teaching activity, are arguments in favor of training. Method: Data collection was carried out on the Journal Portal of the Coordination for the Improvement of Higher Education Personnel with the descriptors: “continuing education for teachers”, “curriculum”, “National Common Core Curriculum” and “basic education”. The research is of qualitative nature and follows the arguments of Discursive Textual Analysis. Results and Discussion: The results suggest that continuing education improves, reframes and/or reaffirms the conception of curriculum. Research Implications: The study found evidence showing that curriculum and continuing education are intrinsically linked; as such, thinking about either one individually may undermine discussions. Originality/Value: This study contributes to the literature as the reality caused by the Covid-19 pandemic has called into question the training provided by education networks and brought to light aspects of the curriculum that need to be reviewed.

Prioritizing management actions for invasive non-native plants through expert-based knowledge and species distribution models

Given the high number of non-native plants that are being introduced worldwide and the time required to process formal pest risk analyses, a framework for the prioritization of management actions is urgently required. We therefore propose a framework for a replicable and standardized prioritization for management actions (eradication, control and monitoring) of invasive non-native plants, combining expert knowledge, current and future climatic suitability estimated by species distribution models (SDMs), clustering and ordination techniques. Based on expert consultation and using Italy as case study, invasive non-native plant species were selected and three categories of management actions were identified: eradication, control and containment, and monitoring. Finally, two further classes of priorities were proposed for each of the management actions: “high” and “low” priority. Overall, SDMs highlighted a high and very high suitability for Continental and Mediterranean bioregions for most invasive plants. Cluster analysis revealed three distinct clusters with varying levels of suitability for the Italian bioregions. Cluster 1 exhibited a higher suitability across all Italian bioregions, whereas non-native plants grouped in Cluster 2 predominantly featured high suitability in Mediterranean areas. Finally, Cluster 3 showed the lowest suitability values. Two ordination analysis highlighted the variability in bioclimatic suitability for each non-native plant within each cluster, as well as their current distribution pattern. Lastly, a third ordination, integrating bioclimatic suitability and spatial patterns, has allowed the differentiation of management actions for each non-native plant at both national and bioregional scales. Specifically, seven non-native plants were earmarked for eradication action, six for monitoring action, while the remaining species were deemed suitable for control and containment. Our results and the methodology proposed meet the demand for replicable new early warning tools; that is to predict the location of new outbreaks, to establish priorities for eradication, control and containment, and to monitor invasive non-native species.

Investigating stakeholder rationales for participating in collaborative interactions at the policy–science nexus

Contemporary politics has become increasingly reliant on scientific knowledge. In evidence-based policymaking, science is invoked to address complex, ‘wicked’ problems. Yet, policymakers do not necessarily base decisions on the best-available evidence, and models of knowledge used in policymaking have long been criticised as simplistic. Therefore, collaboration with non-scientific actors has emerged as a possible way forward. On both sides of the policy–science nexus, collaborative interactions are extended to include ‘stakeholders’ to improve the impact of knowledge (that is, its usability and applicability). And while stakeholder involvement often follows this overarching justification, the question of stakeholder rationales for participating in these processes has previously received little scholarly attention. To address this gap, this article analyses stakeholder rationales, asking why organisations get involved in collaborative research. The theoretical expectations about divergent organisational rationales, drawing on theories of institutional and organisational logics, are investigated through an exploratory case study of stakeholders engaged in collaborative research projects in Norway. The theoretical and empirical analysis form the basis for a proposed new typology of stakeholder rationales. In this way, the article contributes towards the development of better tools for understanding and assessing the sources and potential pathways of knowledge, shaped by self-interested actors, making its way into policymaking processes, often as ‘neutral’ evidence.

Assessing the Accuracy of AI Models in Orthodontic Knowledge: A Comparative Study Between ChatGPT-4 and Google Bard.

To compare the knowledge accuracy of ChatGPT-4 and Google Bard in response to knowledge-based questions related to orthodontic diagnosis and treatment modalities. Cross-sectional comparative study. Place and Duration of the Study: Department of Orthodontics, Rawal Institute of Health Sciences, Islamabad, Pakistan, from June 23rd to August 30th 2023. A comprehensive content analysis was designed based on a mini implant-assisted rapid palatal expansion (MARPE), clear aligners (CA), and cone beam computed tomography (CBCT), involving 30 questions for each category (total = 90) derived from recent review articles. Questions were prepared and presented to two large language models (LLMs): Google Bard and ChatGPT-4. Two independent raters evaluated the accuracy of the responses using a scoring system ranging from one to five, by comparing the answers to a standard key. Statistical analyses, including the paired sample t-test, were used to assess the performance of the two language models. GPT-4 demonstrated superior performance, outperforming Google Bard significantly in the MARPE, CBCT, and CA categories, and achieved a higher mean score. A p-value was found to be (p = 0.001) for MARPE and CBCT, while it was (p = 0.013) for CA. Overall, GPT-4 achieved a total score of 92.6%, surpassing Google Bard's which was 72%. GPT-4 is more efficient than Google Bard in providing accurate and up-to-date information regarding recent trends in orthodontic treatment modalities. Aligners, Cone beam computed tomography, ChatGPT-4, Google Bard, Mini implant-assisted rapid palatal expansion.

ChecKAP: A Checklist for Reporting a Knowledge, Attitude, and Practice (KAP) Study.

The Knowledge, Attitudes, and Practices (KAP) model is a foundational tool in public health research. KAP surveys play a vital role in this process by gauging a population's current level of knowledge about a specific health issue. Rigorous evaluation is essential for ensuring the validity and reliability of KAP studies. Therefore, in this study, a comprehensive checklist for reporting Knowledge, Attitude, and Practices (KAP) Studies was developed. This study was conducted using a systematic six-step roadmap. A comprehensive review of available relevant quality assessment tools led to the development of specific new items. An expert panel reviewed the initial draft, and after corrections were made, the second draft was finalized and subjected to psychometric analysis by experts. The development of ChecKAP (Checklist for Reporting Items for Knowledge, Attitude, and Practice) represents a significant contribution to KAP studies. The final tool consists of 46 items across 8 fields: title (1 item), abstract (6 items), keywords (1 item), introduction (6 items), method (11 items), findings (7 items), discussion (15 items), and conclusion (1 item). ChecKAP assesses the inherent complexity of KAP research methods and ensures consistent reporting. It fills an important gap in the KAP research literature and serves a dual purpose. First, it acts as a quality assessment tool for reviewers, enabling them to evaluate the methodological rigor and clarity of submitted manuscripts. Second, it serves as a guideline for authors, promoting a more systematic and transparent approach to reporting.

From data acquisition to digital reconstruction: virtual restoration of the Great Wall’s Nine Eyes Watchtower

This article presents the virtual restoration of the Nine Eyes Watchtower, a significant cultural heritage site along the Great Wall. By applying the Seville Charter and digital technology, a detailed virtual restoration workflow is developed. The methodology involves acquiring data from multiple sources, including physical evidence, historical data, and comparative data. Advanced survey technologies, architectural knowledge, historical research, and computer modelling techniques are integrated to accurately capture the architectural and historical significance of the Nine Eyes Watchtower. The virtual restoration process follows a systematic approach, combining evidence interpretation and explicit deduction steps. The main outcome is a comprehensive virtual restoration model that accurately represents the architectural features and historical context of the Nine Eyes Watchtower. The virtual scene includes environmental elements, with potential for immersive exploration. By bridging the gap between interpretation and deduction, this study advances the scientific understanding and presentation of virtual restorations. The project contributes to ongoing research, education, and appreciation of the Great Wall's cultural legacy, ensuring its continued relevance for future generations.

Extraction of Knowledge Models from Textbooks

Isaac Alpizar-Chacon is an assistant professor in the Software Technology for Learning and Teaching group at the Department of Information and Computing Sciences, Utrecht University. In addition to his primary role, he is also an associate professor at the Instituto Tecnológico de Costa Rica. His research interests focus on the impact of GenAI tools in computing education, the integration of these tools into the classroom, the teaching and learning of computational thinking skills, and knowledge extraction. Dr. Alpizar-Chacon holds a MSc degree in Computer Science from Saarland University (Saarbrücken, Germany) and a PhD degree in Information and Computing Sciences from Utrecht University (Utrecht, Netherlands). Homepage: https://isaacalpizar.info/

Automated Building Information Modeling Compliance Check through a Large Language Model Combined with Deep Learning and Ontology

Ensuring compliance with complex industry standards and regulations during the design and implementation phases of construction projects is a significant challenge in the building information modeling (BIM) domain. Traditional manual compliance checking methods are inefficient and error-prone, failing to meet modern engineering demands. Natural language processing (NLP) and deep learning methods have improved efficiency and accuracy in rule interpretation and compliance checking. However, these methods still require extensive manual feature engineering, large, annotated datasets, and significant computational resources. Large language models (LLMs) provide robust language understanding with minimal labeled data due to their pre-training and few-shot learning capabilities. However, their application in the AEC field is still limited by the need for fine-tuning for specific tasks, handling complex texts with nested clauses and conditional statements. This study introduces an innovative automated compliance checking framework that integrates LLM, deep learning models, and ontology knowledge models. The use of LLM is motivated by its few-shot learning capability, which significantly reduces the need for large, annotated datasets required by previous methods. Deep learning is employed to preliminarily classify regulatory texts, which further enhances the accuracy of structured information extraction by the LLM compared to directly feeding raw data into the LLM. This novel combination of deep learning and LLM significantly enhances the efficiency and accuracy of compliance checks by automating the processing of regulatory texts and reducing manual intervention. This approach is crucial for architects, engineers, project managers, and regulators, providing a scalable and adaptable solution for automated compliance in the construction industry with broad application prospects.

Sequential explanatory technological pedagogical and content knowledge of madrasah teachers in Jambi

This study aims to describe the structural model of Sequential Explanatory Technological Pedagogical and Content Knowledge (TPACK) of Madrasah Teachers in Jambi Province.This research involved 132 teachers for surveys and 5 teachers for interviews. Descriptive statistics, t-test, Anova, and SEM-PLS were used in quantitative data analysis, while qualitative data was carried out using descriptive thematics. The findings show that Madrasah teachers' TPACK is at a good category level. There are no differences in teachers' TPACK levels based on gender, certification status, madrasa level, age, teaching experience, and field of study. Technological pedagogical knowledge (TPK) has a stronger influence on technological pedagogical and content knowledge (TPACK) compared to technological content knowledge (TCK) and pedagogical content knowledge (PCK). Teachers need support from schools and communities to increase TPACK knowledge in addition to from self-awareness to developing competence as well as several other information that have been discussed in the discussion of this research. Teachers should increase their TPACK knowledge so that they can confidently implement technology in their learning.

Granular transfer learning

Transfer learning is aimed at supporting the design of machine learning models in the target domain Dt, given that the knowledge (model) has already been constructed in the source domain Ds. The domains Dt and Ds (as well as the corresponding tasks Ts and Tt) are similar, yet not identical. As a result, the model transferred from Ds to Dt in this new environment exhibits its relevance (credibility) only to some limited extent. In this study, we develop an original approach, where we advocate that the knowledge transfer (model transfer) gives rise to a granular model where the level of information granularity associated with the produced results quantifies the relevance (quality or credibility) of the transferred model. In other words, we stress that the quality of knowledge transferred to Dt becomes captured through a granular generalization of the original numeric model. The overall systematic design process is elaborated on by focusing on the development process of granular neural networks carried out on a basis of the numeric neural networks coming from Ds. The key aspect of the design is to elevate the existing numeric neural network to its granular counterpart by admitting that the connections of the developed model come in the form of information granules, in particular intervals and fuzzy sets. The optimization process is guided by adjusting (optimizing) the level of information granularity being regarded as an essential design asset. The optimized performance index builds upon the descriptors of information granules commonly encountered in Granular Computing. In particular, coverage and specificity measures are treated as sound performance indicators of the quality of knowledge transfer (viz. the performance of the granular neural network expressed in the target domain). Several illustrative examples are provided to visualize the performance of the established design environment.

The MTSK model as a tool for designing tasks for teacher education

This paper studies the knowledge developed by a group of sixty-two pre-service primary teachers during a training session on the definition of a polygon and the mathematical practice of defining. We explore the knowledge developed by pre-service teachers when they carry out a series of training tasks oriented around the practice of defining with primary pupils, within the theoretical framework of the Mathematics Teachers’ Specialised Knowledge model, and using videos of an authentic lesson as prompt. Data were collected by means of video recordings of the implementation of the training tasks, in conjunction with the pre-service teachers’ own written observations as they watched the recorded lesson. A content analysis was carried out on the collected data using the Mathematics Teachers’ Specialised Knowledge model. The results highlight the way in which knowledge of the mathematical practice of defining is constructed, along with the mathematical objects involved in this practice, and pedagogical aspects of defining with young pupils. They also illustrate how a sequence of tasks oriented around a model of teachers’ knowledge can contribute to the development of this knowledge in initial training programmes, and more especially provide orientation about the training of pre-service teachers in the mathematical practice of defining.

Determinants of preventive behavior against Covid-19 in secondary school students based on Health Belief Model (HBM): a structural equations modeling (SEM)

Measures such as education, improving knowledge, attitude and taking preventive action to protect against COVID-19 are vital strategies for prevention. The aim of this study was to determine the predictability of Health Belief Model (HBM) constructs in performing preventive behaviors against COVID-19 among secondary school students in Chabahar, Iran. In this cross-sectional-analytical study, 400 secondary school students of Chabahar city were investigated by simple random sampling. The data collection tool was a questionnaire including demographic characteristics, knowledge, behavior, and Health Belief Model constructs’ questions. Exploratory Factor Analysis (EFA) was used to evaluate the validity of HBM constructs, and the structural equation modeling (SEM) method was used to evaluate the direct and indirect effects of the relationship between knowledge, HBM constructs, and preventive behavior against COVID-19 based on the conceptual model. Based on the results of the structural modeling, the direct effect of knowledge on the constructs of the health belief model was positive and significant (β = 0.34, P-value < 0.001), and on the preventive behavior of students was insignificant (β = 0.12, P-value = 0.07) while the indirect effect of knowledge through increasing the constructs of the HBM on student behavior was positive and significant (β = 0.30, P < 0.001). The relationship between the constructs of the HBM constructs and student behavior was also positive and significant (β = 0.89, P-value < 0.001).Due to the fact that knowledge and HBM structures played a role in predicting the adoption of preventive behavior from COVID-19, it is possible to design appropriate interventions to increase knowledge, sensitivity, perceived severity, and self-efficacy, in order to recover from COVID-19 by adopting preventive behaviors.

Reaction Templates: Bridging Synthesis Knowledge and Artificial Intelligence.

ConspectusThe field of chemical research boasts a long history of developing software to automate synthesis planning and reaction prediction. Early software relied heavily on expert systems, requiring significant effort to encode vast amounts of synthesis knowledge into a computer-readable format. However, recent advancements in deep learning have shifted the focus toward AI models, offering improved prediction capabilities. Despite these advancements, current AI models often lack the integration of known synthesis rules and intuitions, creating a gap that hinders interpretability and future development of the models. To bridge them, our research group has been actively working on incorporating reaction templates into deep learning models, achieving promising results across various applications.In this Account, we present our latest works to incorporate the known synthesis knowledge into the deep learning models through the utilization of reaction templates. We begin by highlighting the limitations of early computer programs heavily reliant on hand-coded rules. These programs, while providing a foundation for the field, presented limitations in scalability and adaptability. We then introduce SMARTS (SMILES arbitrary target specification), a popular Python-readable format for representing chemical reactions. This format of reaction encoding facilitates the quick integration of synthesis knowledge into AI models built using the Python language. With the SMARTS-based reaction templates, we introduce our recent efforts of developing an AI model for reaction-based molecule optimization. Subsequently, we discuss the recent efforts to automate the extraction of reaction templates from vast chemical reaction databases. This approach eliminates the previously required manual effort of encoding knowledge, a process that could be time-consuming and prone to error when dealing with large data sets. By customizing the automated extraction algorithm, we have developed powerful AI models for specific tasks such as retrosynthesis (LocalRetro), reaction outcome prediction (LocalTransform), and atom-to-atom mapping (LocalMapper). These models, aligned with the intuition of chemists, demonstrate the effectiveness of incorporating reaction templates into deep learning frameworks.Looking toward the future, we believe that utilizing reaction templates to connect known chemical knowledge and AI models holds immense potential for various applications. Not only can this approach significantly benefit future AI models focused on challenging tasks like reaction mechanism labeling and prediction, but we anticipate it can also extend its reach to the realm of inorganic synthesis. By integrating synthesis knowledge, we can not only achieve improved performance but also enhance the interpretability of AI models, paving the way for further advancements in AI-powered chemical synthesis.