Development and analysis of a knowledge graph-based platform for cultural heritage protection and inheritance

Abstract

Cultural heritage is a valuable wealth of human civilization, which needs to be effectively protected and inherited. Knowledge graph is a technology capable of representing and reasoning about complex knowledge, which can provide powerful support for the digitization, intelligence and revitalization of cultural heritage. This paper discusses the methods and effects of the development and analysis of the cultural heritage protection and inheritance platform based on knowledge graph, which mainly includes the following aspects: (1) Introducing the concepts, characteristics, and application fields of knowledge graph, and analyzing the roles and values of knowledge graph in the protection and inheritance of cultural heritage; (2) designing the architecture and functions of a cultural heritage protection and inheritance platform based on knowledge graph, which include four modules of knowledge graph construction, query, application, and update, introduced the technical principle and realization method of each module, respectively, and demonstrated the interface and operation flow of the platform; (3) evaluated the effect and performance of the platform, and carried out experimental design and result analysis from four aspects of the construction, query, application, and update of the knowledge graph, which proved the feasibility and validity of the platform; and (4) discussed the platform’s innovation points and advantages of the platform, analyzed the theoretical and practical significance of the platform, pointed out the shortcomings and room for improvement of the platform, and looked forward to the development prospects and application scenarios of the platform. The method and effect of the development and analysis of the platform for the protection and inheritance of cultural heritage based on knowledge graph proposed in this paper provide a new idea and way for the digital protection and inheritance of cultural heritage, as well as a new paradigm and case for the research and application of knowledge graph, which has certain academic value and social significance.

Keywords

knowledge graph cultural heritage preservation and transmission platform development and analysis

Introduction

Cultural heritage refers to the tangible and intangible cultural achievements created by human societies in the course of historical development, which reflect the cultural diversity and creativity of humankind and are an important part of human civilization. Cultural heritage includes two categories, tangible cultural heritage and intangible cultural heritage. Tangible cultural heritage refers to buildings, ruins, cultural relics, landscapes, and so on, which have historical, artistic and scientific values, while intangible cultural heritage refers to languages, scripts, music, dances, dramas, handicrafts, folklore, and so on, which have historical, cultural, and social values. Cultural heritage is the valuable wealth of the Chinese nation and the common heritage of human civilization, and is of great significance in strengthening national self-confidence, promoting cultural exchanges, and advancing social development.

In China’s 5000-year history, countless cultural heritages have been handed down. However, cultural heritage is facing threats and challenges from various aspects, such as natural disasters, human destruction, environmental pollution, tourism development, lack of information, and faulty inheritance, leading to its destruction, loss, decline, and extinction.^1,2 Therefore, how to effectively protect and pass on cultural heritage is an urgent problem to be solved. With the development of information technology, digitalization, intelligence and visualization provide new ideas and methods for the protection and inheritance of cultural heritage. Digitization refers to the conversion of data and information of cultural heritage into digital format to achieve long-term preservation, wide dissemination and convenient access to cultural heritage. Intellectualization refers to the use of artificial intelligence, big data, cloud computing, and other technologies to analyze, mine, and reason about the data and information of cultural heritage, so as to realize the knowledge discovery, value mining, and intelligent service of cultural heritage. Visualization refers to the use of virtual reality, augmented reality, three-dimensional reconstruction, and other technologies to graphically, dynamically, and interactively present the data and information of cultural heritage, so as to realize the real reproduction, immersive experience, and emotional resonance of cultural heritage.^3,4 The various impact factor percentages are shown in Figure 1.

Figure 1.

Percentage of various influencing factors.

Knowledge graphs stand as a pioneering technology in the realm of knowledge representation and administration. They ingeniously depict entities, their attributes, and interconnections through a graphical schema, while encoding knowledge within logical frameworks, harnessing inference mechanisms for knowledge derivation and validation, and employing query languages to facilitate knowledge retrieval and practical implementation. Endowed with the attributes of structure, semantic richness, and inherent intelligence, these graphs excel in harmoniously integrating, organizing, and leveraging vast, diverse datasets and knowledge repositories. This capability renders them instrumental in tackling intricate challenges across myriad disciplines. In the domain of cultural heritage, knowledge graph technology harbors immense potential, promising a unified, holistic blueprint, and operational platform for the digital transformation, intellectual enrichment, and visual manifestation of our historical treasures. By seamlessly weaving together disparate threads of information, it paves the way for advanced understanding, preservation, and dissemination of humanity’s cultural legacy, thereby safeguarding our collective memory for posterity.

This paper proposes a knowledge graph-based cultural heritage protection and inheritance platform, which uses knowledge graph technology to organize, represent, and reason about data and knowledge of cultural heritage.^5,6 The main contributions and innovations of this paper are as follows: (1) A knowledge graph covering tangible and intangible cultural heritage is constructed, and the concepts, attributes, and relationships of cultural heritage are formally defined and described using ontologies and rules, which realizes the structured and semantic representation of cultural heritage. (2) A query and reasoning system for cultural heritage based on knowledge graph is designed, which utilizes a graph database and reasoning engine for efficient storage and management of the knowledge graph, provides a query language based on SPARQL and a rule language based on SWRL, and realizes intelligent retrieval and reasoning of cultural heritage. (3) Virtual reality, augmented reality, 3D reconstruction, and other technologies are used to present the knowledge graph graphically, dynamically, and interactively, realizing the real reproduction, immersion experience, and emotional resonance of cultural heritage. The main framework of the model is shown in Figure 2.^7,8

Figure 2.

Main framework of the model.

The innovation of this paper is that the paper introduces knowledge graph technology into the field of cultural heritage, and by analyzing the concept and characteristics of knowledge graph and its role and value in cultural heritage protection and inheritance, it puts forward an innovative application model that demonstrates the potential of knowledge graph in promoting the digitization, intellectualization, and revitalization of cultural heritage. A platform for cultural heritage protection and inheritance based on knowledge graph is designed, which contains four core modules: knowledge graph construction, query, application, and update. By elaborating the technical principles and realization methods of each module and showing the platform interface and operation flow, the thesis not only proposes a set of systematic solutions but also verifies the possibility of their realization. Through the experimental design and result analysis, the effect and performance of the platform are evaluated from the four aspects of knowledge graph construction, query, application, and updating, which empirically proves the feasibility and effectiveness of the platform, and provides a reference for quantitative evaluation of similar research.

Literature review

At present, the heat and research literature about cultural heritage protection are gradually rising, and the specific data are shown in Figure 3. Guidi et al.⁹ introduced General Secretary Xi Jinping’s important instructions on the protection and inheritance of cultural heritage, as well as the progress and effectiveness of China’s cultural heritage digitization, intelligence, and visualization in recent years, demonstrating the charm and value of Chinese civilization.

Figure 3.

Heat of cultural heritage preservation and amount of research literature.

Li et al.¹⁰ introduced 30 cases of digital innovation practice in culture and tourism selected by the Ministry of Culture and Tourism, including cultural heritage scenic spots such as the Xi’an City Wall and the Longmen Grottoes, Li et al.,¹¹ a knowledge service platform for cultural heritage based on knowledge graph is realized, which takes cultural heritage knowledge graph as the core, provides SPARQL-based query language and SWRL-based rule language, realizes the retrieval and reasoning of cultural heritage knowledge, and at the same time makes use of virtual reality, augmented reality, three-dimensional reconstruction, and other technologies to make a graphical, dynamic, and interactive presentation, where real reproduction, immersion experience, and emotional resonance of cultural heritage were realized. The article introduces a knowledge management method of intangible cultural heritage based on Linked Data, including the collection, conversion, storage, and distribution of intangible cultural heritage data, as well as the query and reasoning of intangible cultural heritage knowledge, which realizes the digitization and intelligence of intangible cultural heritage. An innovative achievement of Beijing Normal University is introduced, which is the application of information technology, the establishment of a new cultural heritage protection method, the solution of the key technology of digital protection and inheritance of cultural relics, the realization of accurate modeling and virtual restoration of cultural relics, and the formation of a series of technical standards for the digital protection of cultural resources. It discussed the importance and difficulties of digital protection and inheritance of intangible cultural heritage, put forward the concept and mechanism of digital living inheritance of intangible cultural heritage, and focused on the digital protection of the inheritors, including the digital construction of the information of the inheritors and the digital construction of the knowledge of the inheritors. A research on digital protection and inheritance of cultural heritage based on knowledge mapping is proposed, which utilizes knowledge mapping technology to organize, represent, and reason about the data and knowledge of cultural heritage, realizing the digitization, intelligence, and visualization of cultural heritage, and providing effective support for the protection, inheritance, research, and utilization of cultural heritage. Ren et al.¹² researched the knowledge fusion and application method of ICH knowledge based on knowledge graph, including the acquisition, integration, extension, and utilization of ICH knowledge, realized the cross-domain, cross-lingual, and cross-media fusion of ICH knowledge, as well as the application of ICH knowledge such as visualization, recommendation, and education. Guan et al.¹³ researched the method of visualization and display of cultural heritage knowledge based on knowledge graph, including graphical representation, dynamic demonstration, and interactive exploration of cultural heritage knowledge, and made use of virtual reality, augmented reality, three-dimensional reconstruction, and other technologies to carry out multi-dimensional, multi-level, and multi-form visualization and display of cultural heritage knowledge, which improves the dissemination effect and user experience of cultural heritage knowledge.¹⁴ A knowledge service platform for intangible cultural heritage based on knowledge graph is designed and realized, which is based on knowledge graph of intangible cultural heritage and provides functions of querying, reasoning, visualization, recommendation, and education of knowledge of intangible cultural heritage, and provides a new way of thinking and methodology for the protection, inheritance, research, and utilization of intangible cultural heritage.

Platform design and development

The aim of this paper is to design and develop a cultural heritage protection and inheritance platform based on knowledge graph, which is capable of organizing, representing, querying, reasoning, visualizing, and displaying tangible and intangible cultural heritage data and knowledge to realize the digitization, intelligence, and revitalization of cultural heritage. The main contents of the system design include the following aspects¹⁵:

A triad can be represented as (s, p, and o) where s is the subject, p is the predicate, and o is the object. The subject and object are entities and the predicate is a property or relation. For example, (Beijing, Located, China) is a triple that represents Beijing as an entity, China as an entity, and Located as a relation. An ontology can be represented as O = (C, P, R, A, and H), where C is a set of concepts, P is a set of properties, R is a set of relations, A is a set of axioms, and H is a set of hierarchies. The rule can be expressed as IF antecedent THEN consequent, where antecedent is the premise and consequent is the conclusion.^16,17 Both premise and conclusion are expressions consisting of triples or logical connectives. Rules can be used to derive and verify implicit information and consistency in a knowledge graph. For example, IF (x, is, tangible cultural heritage) AND (x, type, building) THEN (x, needs, protection) is a rule that states that if an entity is tangible cultural heritage and is a building type, then it needs protection. Specific examples are shown in Table 1.^18,19

Table 1.

Examples of ternary groups.

Subject (in grammar)	(grammatical) predicate	Object (grammar)
Mogao Caves in Dunhuang, Gansu	Be	Tangible cultural heritage
Mogao Caves in Dunhuang, Gansu	Typology	Cave temple
Mogao Caves in Dunhuang, Gansu	Be situated at	Gansu Province
Mogao Caves in Dunhuang, Gansu	Built in	Wei of the Northern Dynasties (386–534)
Mogao Caves in Dunhuang, Gansu	There are	Frescos
Mogao Caves in Dunhuang, Gansu	There are	Painted clay figure
Dunhuang frescoes in Gansu	Be	Intangible cultural heritage
Dunhuang frescoes in Gansu	Typology	Sculpture
Dunhuang frescoes in Gansu	Subject matter	Buddhist
Dunhuang frescoes in Gansu	Hairstyle	Dunhuang style in Gansu

In this paper, we adopt a native approach for storage, that is, storing the triples in the knowledge graph directly in the graph database without relational or document-based conversion. In this paper, we use OpenLink Virtuoso3 as the storage and management database for RDF data, which is a hybrid database that supports multiple data models and query languages to efficiently handle large-scale knowledge graph data. In this paper, we also utilize Virtuoso’s built in inference engine to load and execute rules in the knowledge graph, which realizes dynamic updating and expansion of the knowledge graph. The specific format is shown in Table 2.^20,21

Table 2.

Ontologies and rules.

The thing in itself	Rules and regulations
Tangible cultural heritage is a subcategory of cultural heritage	IF (x, yes, tangible cultural heritage) AND (x, type, building) THEN (x, need, protection)
Intangible cultural heritage is a subcategory of cultural heritage	IF (x, yes, intangible cultural heritage) AND (x, type, painting) THEN (x, need, heritage)
Cultural heritage has typological attributes	IF (x, yes, cultural heritage) AND (x, type, y) THEN (y, yes, type of cultural heritage)
Cultural heritage has properties located	IF (x, yes, cultural heritage) AND (x, located, y) THEN (y, yes, geographic location)
Cultural heritage is built on attributes	IF (x, yes, cultural heritage) AND (x, built in, y) THEN (y, yes, historical dynasty)

In terms of knowledge graph querying and reasoning, knowledge graph querying and reasoning refers to retrieving and deducing relevant data and knowledge from the knowledge graph according to the user’s needs and returning them to the user. In this paper, a query and reasoning system for cultural heritage based on knowledge graph is designed,^22,23 which utilizes a graph database and reasoning engine for efficient storage and management of the knowledge graph, provides a query language based on SPARQL4 and a rule language based on SWRL, and realizes intelligent retrieval and reasoning of cultural heritage. The other is natural language query, that is, the user inputs a natural language question, and the system utilizes the natural language processing technology to convert the question into a SPARQL query statement, and then query the knowledge graph to find out the answer and return it to the user. This paper supports two kinds of query methods: one is keyword query, that is, the user inputs one or more keywords, and the system matches entities or attributes in the knowledge graph according to the keywords, and returns the related triples or subgraphs. This paper also supports two kinds of reasoning: one is ontology reasoning, which uses the semantic information of categories, attributes and relationships defined in the ontology to derive the implied triples in the knowledge graph, such as subclasses, parents, and synonyms; and the other is rule-based reasoning, which utilizes the logical relationships of premises and conclusions defined in the rules to derive the implied triples in the knowledge graph, such as causality, conditionality, and similarity.^24,25 This paper develops a knowledge graph-based cultural heritage visualization and presentation system, which uses virtual reality,²⁶ augmented reality, 3D reconstruction, and other technologies to graphically, dynamically, and interactively present the knowledge graph, realizing the real reproduction, immersive experience, and emotional resonance of cultural heritage. This paper supports two types of visualization: one is graphical visualization, that is, entities and relationships in the knowledge graph are displayed on the screen in the form of nodes and edges, and users can browse and explore the knowledge graph through operations such as zooming, dragging, and clicking.^27,28 The system also provides different layout algorithms and theme styles, so that the user can adjust the visualization effect according to his/her own preferences and needs; the second is immersive visualization, that is, using the VR/AR technology to display the cultural heritage in the knowledge map in the form of three-dimensional models in the virtual or real environment, so that users can enter into the scene of the cultural heritage through helmets, handles, glasses, and other devices to observe and interact with the cultural heritage in close proximity and feel the history and culture of the cultural heritage. The specific reasoning model of which is shown in Table 3.^29,30

Table 3.

Specific patterns of reasoning.

Type of query or inference	Importation	Exports
Keyword Search	Dunhuang (city in Gansu)	(Dunhuang Mogao Caves, Yes, Tangible Cultural Heritage)
		(Dunhuang Mogao Caves, Types, Cave Temples)
		(Dunhuang Mogao Caves, located in, Gansu Province)
		(Mogao Caves, Dunhuang, built in, Northern Wei Dynasty)
		(Dunhuang Mogao Caves, Yes, Mural)
		(Mogao Caves, Dunhuang, Yes, colored sculptures)
		(Dunhuang Frescoes, Yes, Intangible Cultural Heritage)
		(Dunhuang Frescoes, Types, Paintings)
		(Dunhuang Frescoes, Subjects, Buddhism)
		(Dunhuang Frescoes, Style, Dunhuang Style)
Natural language query	When were the Mogao Caves built in Dunhuang?	The Mogao Caves in Dunhuang were built during the Northern Wei Dynasty.
Ontological reasoning	(Dunhuang Mogao Caves, Yes, tangible cultural heritage)	(Dunhuang Mogao Caves, Yes, Cultural Heritage)
Regular inference	(Dunhuang Mogao Caves, Yes, tangible cultural heritage)	(Dunhuang Mogao Caves, Needs, Protection)

Platform assessment

Experimental design

The purpose of this paper is to deeply explore and practice the construction method of the cultural heritage protection and inheritance platform based on knowledge graph technology and its effect analysis. In order to comprehensively verify the feasibility and effectiveness of the platform in practical applications, we have carefully designed and implemented experiments in four key areas: first, in Experiment 1, we focus on the assessment of the effect of knowledge graph construction. The industry-recognized accuracy rate, recall rate, and F1 value are used as metrics to quantitatively assess the quality and coverage of the platform’s automatically constructed cultural heritage knowledge graph. We compare the knowledge map automatically generated by the platform with the standard knowledge map manually annotated by experts, and visualize the effectiveness and precision of the platform in the process of constructing the knowledge map by calculating the specific values of each index. Secondly, experiment 2 centers on the evaluation of knowledge graph query effect.^25,26 Core indicators such as response time, correct rate, and user satisfaction are selected to comprehensively evaluate the performance of the knowledge graph query service provided by the platform and its user experience. A series of query tasks of varying complexity and diverse types are designed to test the response speed of the platform to query requests, the accuracy of retrieval results, and the real feedback of users, so as to reflect the practicality and friendliness of the platform’s query function. Furthermore, experiment 3 conducted an exhaustive examination of the effect of the actual application scenarios of knowledge graph. Operational data such as click rate, conversion rate, and retention rate are used to judge the attractiveness and intrinsic value of various cultural heritage applications (e.g., personalized recommendation system, intelligent guide service, and online Q&A module) Developed based on the knowledge graph. Statistics on the number of clicks, registration conversions, and the persistent participation of active users in the process of user interaction are used to confirm the effectiveness of the platform’s application innovation and its social impact. Finally, Experiment 4 focuses on the study of the updating and maintenance effect of the knowledge graph. The three dimensions of update time, update frequency and update quality are chosen to examine the platform’s ability to dynamically maintain and real-time update the knowledge graph and its reliability. The platform regularly collects and integrates the latest cultural heritage-related data information and measures the data update speed, cycle regularity, and accuracy of new content, so as to verify the platform’s efficient update capability and robust stability in meeting the challenge of continuous updating of the knowledge graph.^31,32

Experimental results

We used a dataset of cultural heritage knowledge graph collected from the web, which includes cultural heritage data and information from different domains, types, and geographies, such as intangible cultural heritage, images of cultural artifacts, and documents of simple and silk. We ran the platform on a PC configured with Intel Core i7-8700 CPU, 16 GB RAM, 1 TB hard disk, and Windows 10 operating system. We obtained the following experimental results as shown in Table 4.

Table 4.

Experimental results.

Test	Norm	In the end
Experiment 1	Accuracy	0.92
	Recall rate	0.88
	F1 value	0.90
Experiment 2	Response time	0.35 s
	Correct rate	0.95
	Customer satisfaction	4.5/5
Experiment 3	Click through rate (CTR) (Internet)	0.12
	Conversion rate	0.08
	Retention rate	0.65
Experiment 4	Update time	1 h
	Update Frequency	1/d
	Updating quality	0.93

As can be seen from Table 4, the development and analysis of the cultural heritage protection and inheritance platform based on knowledge graph proposed in this paper is more satisfactory.^33,34 It can effectively construct, query, apply, and update the knowledge graph of cultural heritage, which provides a strong support for the digital protection and inheritance of cultural heritage. In the following, we will analyze and discuss the results of each experiment in detail.³⁵

Conclusion

This paper discusses the methods and effects of the development and analysis of the cultural heritage protection and inheritance platform based on knowledge graph, introduces the concepts, characteristics and application fields of knowledge graph, analyzes the role and value of knowledge graph in cultural heritage protection and inheritance, and points out that knowledge graph can provide effective technical support and solutions for the digitization, intellectualization, and revitalization of cultural heritage. This article designs the architecture and functions of a platform for cultural heritage protection and inheritance based on knowledge mapping, including four modules: construction, query, application, and update of knowledge mapping, introduces the technical principles and realization methods of each module respectively, and demonstrates the platform’s interface and operation flow. The article evaluates the effect and performance of the platform, adopting the indicators of accuracy, recall, F1 value, response time, correctness, user satisfaction, click rate, conversion rate, retention rate, update time, update frequency, and update quality, and carries out the experimental design and result analysis from the four aspects of knowledge graph construction, querying, application, and updating, which proves the feasibility and effectiveness of the platform.

The method and effect of the development and analysis of the cultural heritage protection and inheritance platform based on knowledge graph proposed in this paper provide a new idea and way for the digital protection and inheritance of cultural heritage, as well as a new paradigm and case for the research and application of knowledge graph, which has certain academic value and social significance. The research in this paper still has some shortcomings and limitations, such as the scale, quality, diversity, and dynamics of the knowledge graph still need to be improved; the function, performance, stability, and security of the platform still need to be optimized; and the application, promotion, and evaluation of the platform still need to be deepened. Future research can be expanded and improved in the following aspects: expanding the data source and domain scope of the knowledge graph, increasing the type, quantity and dimension of cultural heritage, and improving the coverage and richness of the knowledge graph. Introducing more knowledge representation and reasoning methods, such as ontology, rules, and logic, to improve the expressive and reasoning ability of knowledge graph.

Statements and declarations

Footnotes

Conflicting interests

The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Funding

The author(s) received no financial support for the research, authorship, and/or publication of this article.

References

Kamel

Gil-Solla

Guerrero-Vásquez

, et al. A crowdsourcing recommendation model for image annotations in cultural heritage platforms. Appl Sci-Basel 2023; 13(19): 10623.

Cui

Shang

. KAGN: knowledge-powered attention and graph convolutional networks for social media rumor detection. J Big Data 2023; 10(1): 45.

Dang

Tang

Pang

, et al. Constructing an educational knowledge graph with concepts linked to Wikipedia. J Comput Sci Technol 2021; 36(5): 1200–1211.

Berven

Christensen

Moldeklev

, et al. A knowledge-graph platform for newsrooms. Comput Ind 2020; 123: 103321.

Sun

Luo

, et al. Scratch-DKG: a framework for constructing scratch domain knowledge graph. IEEE T Emerg Top Com 2022; 10(1): 170–185.

Sun

Tang

, et al. Construction of a knowledge graph for breast cancer diagnosis based on Chinese electronic medical records: development and usability study. BMC Med Inform Decis 2023; 23(1): 210.

Pakiman

Garcke

Schumacher

. Knowledge discovery assistants for crash simulations with graph algorithms and energy absorption features. Appl Intell 2023; 53(16): 19217–19236.

Zhang

Rizvi

, et al. ALOHA: developing an interactive graph-based visualization for dietary supplement knowledge graph through user-centered design. BMC Med Inform Decis 2019; 19: 150.

Guidi

Michienzi

Ricci

. Steem blockchain: mining the inner structure of the graph. IEEE Access 2020; 8: 210251–210266.

10.

Zhang

. Knowledge graph entity similarity calculation under active learning. Complexity 2021; 2021: 3522609.

11.

Zhu

, et al. DCRL-KG: distributed multi-modal knowledge graph retrieval platform based on collaborative representation learning. Intell Autom Soft Co 2023; 36(3): 3295–3307.

12.

Ren

Xiao

Zhou

, et al. CSKG4APT: a cybersecurity knowledge graph for advanced persistent threat organization attribution. IEEE T Knowl Data En 2023; 35(6): 5695–5709.

13.

Guan

Cheng

Bai

, et al. What is event knowledge graph: a survey. IEEE T Knowl Data En 2023; 35(7): 7569–7589.

14.

Liu

YSY

, et al. Resource recommendation based on industrial knowledge graph in low-resource conditions. Int J Comput Int Sys 2022; 15(1): 42.

15.

Shen

Pan

, et al. A novel DL-based algorithm integrating medical knowledge graph and doctor modeling for Q& pair matching in OHP. Inform Process Manag 2023; 60(3): 103322.

16.

Mawkhiew

Sahoo

Kharshiing

. Gene-to-trait knowledge graphs show association of plant photoreceptors with physiological and developmental processes that can confer agronomic benefits. Genet Resour Crop Ev 2021; 68(7): 2727–2735.

17.

Opdahl

Al-Moslmi

Dang-Nguyen

, et al. Semantic knowledge graphs for the news: a review. ACM Comput Surv 2023; 55(7): 140–238.

18.

Pavel

Saarimäki

Möbus

, et al. The potential of a data centred approach & knowledge graph data representation in chemical safety and drug design. Comput Struct Biotec 2022; 20: 4837–4849.

19.

Fei

Wang

, et al. HAPE: a programmable big knowledge graph platform. Inf Sci (N Y) 2020; 509: 87–103.

20.

Silva

Vieira

Campos

, et al. Development and validation of a descriptive cognitive model for predicting usability issues in a low-code development platform. Hum Factors 2021; 63(6): 1012–1032.

21.

Chen

Yang

Chang

, et al. Development of a semi-structured, multifaceted, computer-aided questionnaire for outbreak investigation: e-Outbreak Platform. Biomed J 2020; 43(4): 318–324.

22.

Lyu

Chen

. Achieving Knowledge-as-a-Service in iiot-driven smart manufacturing: a crowdsourcing-based continuous enrichment method for Industrial Knowledge Graph. Adv Eng Inform 2022; 51: 101494.

23.

Sakurai

Togo

Ogawa

, et al. Controllable music playlist generation based on knowledge graph and reinforcement learning. Sensors-Basel 2022; 22(10): 3722.

24.

Liu

Pan

Zhang

, et al. Cross-platform product matching based on entity alignment of knowledge graph with raea model. World Wide Web 2023; 26(4): 2215–2235.

25.

Choi

Jang

, et al. Masked entity model for knowledge graph completion with pre-trained language model. IEEE Access 2021; 9: 132025–132032.

26.

Bonner

Barrett

, et al. A review of biomedical datasets relating to drug discovery: a knowledge graph perspective. Brief Bioinform 2022; 23(6): bbac404.

27.

Feng

Shen

, et al. E-TSN: an interactive visual exploration platform for target-disease knowledge mapping from literature. Brief Bioinform 2022; 23(6): bbac465.

28.

Liu

Ding

, et al. Urbankg: an urban knowledge graph system. ACM T Intel Syst Tec 2023; 14(4): 1–25.

29.

Liu

YSY

, et al. A metrics-based meta-learning model with meta-pretraining for industrial knowledge graph construction. Comput Ind 2022; 143: 103753.

30.

Chi

Qin

Song

, et al. Knowledge graph in smart education: a case study of entrepreneurship scientific publication management. Sustainability-Basel 2018; 10(4): 995.

31.

Zhao

, et al. Fault localization based on knowledge graph in software-defined optical networks. J Lightwave Technol 2021; 39(13): 4236–4246.

32.

Cha

Choi

Lee

, et al. Knowledge retrieval model based on a graph database for semantic search in equipment purchase order specifications for steel plants. Sustainability-Basel 2023; 15(7): 6319.

33.

Shang

Ding

, et al. Construction and application of the user behavior knowledge graph in software platforms. J Web Eng 2021; 20(2): 387–411.

34.

Slifka

Knaisl

Pergl

. Evolvable transformation of knowledge graphs into human-oriented formats. J Intell Inf Syst 2023; 62: 295–316.

35.

Song

Schilder

Hertz

, et al. Building and querying an enterprise knowledge graph. IEEE T Serv Comput 2019; 12(3): 356–369.