WO2022095121A1 - 一种基于语义本体的广彩瓷知识库的构建方法 - Google Patents

一种基于语义本体的广彩瓷知识库的构建方法 Download PDF

Info

Publication number
WO2022095121A1
WO2022095121A1 PCT/CN2020/129506 CN2020129506W WO2022095121A1 WO 2022095121 A1 WO2022095121 A1 WO 2022095121A1 CN 2020129506 W CN2020129506 W CN 2020129506W WO 2022095121 A1 WO2022095121 A1 WO 2022095121A1
Authority
WO
WIPO (PCT)
Prior art keywords
knowledge
porcelain
guangcai
ontology
semantic
Prior art date
Application number
PCT/CN2020/129506
Other languages
English (en)
French (fr)
Inventor
代幸洋
孙晓红
纪毅
钟声扬
马明
Original Assignee
广东工业大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 广东工业大学 filed Critical 广东工业大学
Publication of WO2022095121A1 publication Critical patent/WO2022095121A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology

Definitions

  • the present application relates to the technical field of knowledge bases, and in particular, to a method for constructing a knowledge base of Guangcai porcelain based on semantic ontology.
  • Semantic ontology is a formal specification of the display of shared conceptual models, and its goal is to transform a disorganized information source into an orderly and easy-to-use knowledge source.
  • Semantic ontology is the core concept of the Semantic Web, and the core of "semantics" is knowledge sharing.
  • ontology has received extensive attention in the field of information science.
  • the purpose of ontology being introduced into information science is to describe and organize information at the semantic and knowledge level, so as to provide a semantic basis for the common understanding of knowledge by computers.
  • Semantic ontology is an emerging research direction in academia, and the related research in the field of information at home and abroad is relatively mature. Using the research method of semantic ontology can comprehensively construct the semantic description system of elements in a certain field and the research on elements. The reproducibility is conducive to the systematic construction of cultures in different fields.
  • the present application provides a method for constructing a knowledge base of Guangcai porcelain based on semantic ontology, which is used to solve the problem of inheritance of traditional handicrafts of Guangcai porcelain.
  • the present application provides a method for constructing a knowledge base of Guangcai porcelain based on semantic ontology, the method comprising:
  • the elements of Guangcai porcelain are semantically analyzed, and the modeling primitive of semantic ontology is constructed;
  • a semantic retrieval model is constructed based on Guangcai porcelain knowledge model for personalized learning.
  • the semantic analysis is performed on the Guangcai porcelain elements, and the Guangcai porcelain elements include: the form, color, element, and theme of the Guangcai porcelain work.
  • the modeling primitives include: classes, relationships, functions, axioms, instances, and the terms and concepts involved in the field of broad-colored porcelain;
  • the relationship includes an object relationship attribute and a value relationship attribute
  • the function is used to describe the relationship between concepts and data types
  • the instance is a representation of an object.
  • the concept includes a first-level concept and a second-level concept
  • a concept represents a set of objects
  • a relationship pair represents a set of object tuples
  • the concept adopts a frame structure, including the name of the concept, and other concepts A collection of relationships between, and a semantic description of concepts.
  • the library corresponding to the tacit knowledge includes a knowledge base, and the knowledge base includes semantic ontology knowledge information and corresponding pattern information; the library corresponding to the explicit knowledge includes a case sample library, and the case sample library includes a wide range of Image, text, audio, video of polychrome porcelain.
  • the general concepts included in the general knowledge ontology include: the history, craftsmanship, color, and fringing of the porcelain of Guangcai Porcelain.
  • the domain knowledge ontology refers to the knowledge describing a specific application domain and discipline.
  • the ontology of dynamic knowledge is guided by the actual needs of users, the construction process utilizes existing knowledge and network data resources, and is automatically completed by machines, and the dynamic knowledge ontology mainly focuses on objects and objects in specific tasks, events or activities. relationship between.
  • the retrieval process of the semantic retrieval model includes the following steps:
  • the personalized learning process through the semantic retrieval model includes:
  • the present application provides a method for constructing a knowledge base of Guangcai porcelain based on semantic ontology.
  • the management principle is to obtain the explicit knowledge and tacit knowledge of Guangcai porcelain knowledge; divide the library corresponding to the explicit knowledge and the tacit knowledge into general knowledge ontology, dynamic knowledge ontology and domain knowledge ontology; Dynamic knowledge ontology and domain knowledge ontology are integrated into Guangcai Porcelain knowledge model; based on Guangcai Porcelain knowledge model, a semantic retrieval model is constructed for personalized learning.
  • This application constructs a multi-dimensional semantic ontology knowledge model and semantic retrieval model of Guangcai porcelain from the perspective of knowledge application by combining the semantics of Guangcai porcelain elements with the modeling primitives of the ontology, which enhances the practicability and efficiency of the Guangcai porcelain knowledge base.
  • Ease of use can promote people's dissemination and learning of traditional culture, and further provide a new way for people to participate in the learning and inheritance of traditional culture.
  • 1 is a flowchart of an embodiment of a method for constructing a semantic ontology-based Guangcai porcelain knowledge base of the application;
  • FIG. 2 is a flowchart of another embodiment of a method for constructing a semantic ontology-based Guangcai porcelain knowledge base of the present application
  • FIG. 3 is a flowchart of another embodiment of a method for constructing a semantic ontology-based Guangcai porcelain knowledge base of the present application.
  • FIG. 1 is a flowchart of an embodiment of a method for constructing a semantic ontology-based Guangcai porcelain knowledge base of the application, including the following steps:
  • Step S100 performing semantic analysis on the Guangcai porcelain elements according to the Guangcai porcelain pattern, and constructing a modeling primitive of the semantic ontology;
  • the semantic analysis of the elements of Guangcai porcelain can be a semantic analysis of the form, color, element and theme of the works of Guangcai porcelain, to explore and extract the semantic connotation and emotional elements of Guangcai porcelain, and then to obtain the specific semantics. Associative, divergent, and reorganized semantics.
  • the expression ontology constructs 5 modeling primitives which are specifically: class, relationship, function, axiom, instance, and the terms and concepts involved in the field of broad-colored porcelain, such as classification process, production method, etc.
  • Guangcai porcelain can be divided into first-level concepts such as plates, saucers, basins, bowls, cups, pots, cups, bottles, paintings, etc., and the classifications under the first-level concepts are classified as second-level concepts; concepts
  • the representation is a collection of objects, and the relationship pair represents a collection of object tuples.
  • the concept adopts a frame structure, including the name of the concept, the collection of relationships with other concepts, and the description of the concept with semantics.
  • relationship includes an object relationship attribute and a value relationship attribute, wherein the object relationship attribute is used to describe the relationship between classes;
  • axioms are limited descriptions of classes and attributes in the ontology of Guangcai porcelain; instances are representations of objects.
  • Step S200 acquiring explicit knowledge and tacit knowledge of Guangcai porcelain knowledge according to the knowledge management principle
  • explicit knowledge refers to knowledge that can be clearly expressed in language, words, body, diagrams, etc., that is, knowledge that can be understood by others through expression; tacit knowledge is through the outer level, which needs to be further understood. Knowledge of its inner level of connotation. Ontology also reflects different levels when describing knowledge in the real world.
  • the library corresponding to tacit knowledge includes knowledge base, which includes semantic ontology knowledge information and corresponding pattern information; the library corresponding to explicit knowledge includes case sample library, which includes images and texts of Guangcai Porcelain , audio, video.
  • the concept of general knowledge and the concept of domain knowledge are mainly manifested as a relatively stable hierarchical structure.
  • the concept of domain knowledge inherits the properties of general concepts and increases the domain properties of the concept itself.
  • Dynamic knowledge mainly describes the facts that occur dynamically in reality, and its knowledge may directly come from the general knowledge and domain knowledge of the upper layer. According to the characteristics of the application scenario, new knowledge connotations are dynamically added, which is mainly manifested as a dynamic network structure.
  • Step S300 dividing the libraries corresponding to explicit knowledge and tacit knowledge into general knowledge ontology, dynamic knowledge ontology, and domain knowledge ontology;
  • the general concepts included in the general knowledge ontology include: the history, craftsmanship, color and fringe of Guangcai porcelain.
  • Guangcai Porcelain can also consider selecting common vocabulary in the field of porcelain to enrich the available vocabulary, so as to build a knowledge system of a certain number of common concepts.
  • Domain knowledge ontology refers to the knowledge that describes specific application domains and disciplines. Domain knowledge ontology has strong subject dependence, such as industry, art and other fields. To construct domain knowledge, it is necessary to clarify the commonly recognized concepts in the domain, and to use a formal model to represent these concepts and the relationship between concepts, so as to achieve a common understanding of the domain knowledge. For example, if ceramics belong to the industrial field, in the production process of Guangcai porcelain with ceramics as raw materials, you can find more suitable concept vocabulary in industrial terms.
  • Dynamic knowledge ontology is guided by the actual needs of users.
  • the construction process utilizes existing knowledge and network data resources, and relies on machines to automatically complete.
  • Dynamic knowledge ontology mainly focuses on specific tasks, events or activities. Objects and the relationship between objects.
  • some dynamic knowledge can be selected according to the user's learning dynamics and input labels, as well as information about Guangcai Porcelain, to further help the construction of Guangcai Porcelain ontology model.
  • Dynamic knowledge has strong extensibility, can be continuously tracked, actively respond to new developments, and realize dynamic expansion and maintenance of knowledge.
  • Step S400 fuse the general knowledge ontology, dynamic knowledge ontology, and domain knowledge ontology into a Guangcai porcelain knowledge model
  • Step S500 constructing a semantic retrieval model based on the Guangcai porcelain knowledge model for personalized learning.
  • Semantic search fully mines the semantic information contained in web document information, and at the same time converts the user's retrieval requirements into corresponding semantic representations, identifies and infers them based on domain ontology, understands user queries from the semantic level, and makes ontologies-based reasoning. The result is returned to the user. Semantic retrieval and recommendation based on ontology can help users to continuously adjust their retrieval vocabulary and change retrieval strategies to obtain the most relevant knowledge.
  • Step S510 obtaining a user request, and extracting a semantic tag according to the user request
  • Step S520 carrying out information reasoning according to the semantic tag, and carrying out an expanded query in the Guangcai porcelain knowledge model
  • Step S530 filter the retrieval results and push them to the user.
  • the retrieval results can be personalized for learning and use, and the personalized learning process is carried out through the semantic retrieval model, referring to FIG. 3, including:
  • Step S531 generating an image description according to the semantic retrieval result
  • Step S532 extracting and reusing the configuration of Guangcai porcelain according to the image description.
  • the present application provides a method for constructing a knowledge base of Guangcai porcelain based on semantic ontology.
  • the management principle acquires the explicit knowledge and tacit knowledge of Guangcai porcelain knowledge; divides the library corresponding to explicit knowledge and tacit knowledge into general knowledge ontology, dynamic knowledge ontology and domain knowledge ontology; divides general knowledge ontology, dynamic knowledge ontology, Domain knowledge ontology is integrated into Guangcai Porcelain knowledge model; based on Guangcai Porcelain knowledge model, a semantic retrieval model is constructed for personalized learning.
  • This application constructs a multi-dimensional semantic ontology knowledge model and semantic retrieval model of Guangcai porcelain from the perspective of knowledge application by combining the semantic analysis of Guangcai porcelain elements with the modeling primitives of the ontology, which enhances the practicability of the Guangcai porcelain knowledge base. It can promote people's dissemination and learning of traditional culture, and further provide a new way for people to participate in the learning and inheritance of traditional culture.
  • At least one (item) refers to one or more, and "a plurality” refers to two or more.
  • “And/or” is used to describe the relationship between related objects, indicating that there can be three kinds of relationships, for example, “A and/or B” can mean: only A, only B, and both A and B exist , where A and B can be singular or plural.
  • the character “/” generally indicates that the associated objects are an “or” relationship.
  • At least one item(s) below” or similar expressions thereof refer to any combination of these items, including any combination of single item(s) or plural items(s).
  • At least one (a) of a, b or c can mean: a, b, c, "a and b", “a and c", “b and c", or "a and b and c" ", where a, b, c can be single or multiple.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种基于语义本体的广彩瓷知识库的构建方法，包括：根据广彩瓷图案对广彩瓷元素进行语义分析，并构建语义本体的建模元语（S100）；根据知识的管理原则获取广彩瓷知识的显性知识和隐性知识（S200）；将所述显性知识和所述隐性知识对应的文库划分为通用知识本体、动态知识本体、领域知识本体（S300）；将通用知识本体、动态知识本体、领域知识本体融合成广彩瓷知识模型（S400）；基于广彩瓷知识模型构建语义检索模型用于个性化学习（S500）。通过对广彩瓷元素语义分析结合本体的建模元语，从知识应用的角度构建了多维语义本体的广彩瓷知识模型和语义检索模型，增强了广彩瓷知识库的实用性和易用性。

Description

一种基于语义本体的广彩瓷知识库的构建方法 技术领域
本申请涉及知识库技术领域，尤其涉及一种基于语义本体的广彩瓷知识库的构建方法。
背景技术
语义本体是共享概念模型的显示的形式化规范说明,其目标是将杂乱无章的信息源转变为有序易用的知识源。语义本体即是语义网的核心概念，其中“语义”的核心就是知识共享。本体作为知识组织的一种有效形式受到信息科学领域的广泛关注，本体思想被引入信息科学的目的是希望在语义和知识层次上描述和组织信息，为计算机对知识的共同理解提供语义基础。语义本体作为学术界新兴的研究方向，在国内外信息领域的相关研究已较为成熟，采用语义本体的研究方法，可以较为全面地构筑某一领域的要素语义记述体系和要素的研究，具有较好的可复制性，有利于不同领域文化的体系化构筑。
当前已有学者通过语义本体的方法，对徽州民居风貌要素记述体系构筑的基础上，进一步对语义体系进行衍生和拓展。运用HOZO软件对已构筑的语义体系的构筑编码进行导出，并对体系中的不同风貌要素进行模型的制作，通过编程赋予编码图形化信息，将以构筑的体系编码和模型进行叠加，可以建立徽州民居风貌要素的模型数据库，
目前大多数基于语义本体理论构筑数据库模型的设计都是以如何构建数据库模型为主，在构建过程中缺少对数据库模型进一步应用的考虑，使得构建的知识库模型具有应用的局限性。
发明内容
本申请提供了一种基于语义本体的广彩瓷知识库的构建方法，用于解决广彩瓷传统手工艺传承的问题。
有鉴于此，本申请提供了一种基于语义本体的广彩瓷知识库的构建方法，所述方法包括：
根据广彩瓷图案对广彩瓷元素进行语义分析，并构建语义本体的建模元语；
根据知识的管理原则获取广彩瓷知识的显性知识和隐性知识；
将所述显性知识和所述隐性知识对应的文库划分为通用知识本体、动态知识本体、领域知识本体；
将通用知识本体、动态知识本体、领域知识本体融合成广彩瓷知识模型；
基于广彩瓷知识模型构建语义检索模型用于个性化学习。
优选的，所述对广彩瓷元素进行语义分析，所述的广彩瓷元素包括有：广彩瓷作品形态、色彩、元素、主题。
优选的，所述的建模元语包括：类、关系、函数、公理、实例，所述类广彩瓷领域所涉及的术语和概念；
所述关系包括对象关系属性和值关系属性；
所述函数用于描述概念与数据类型间的关系；
所述实例为对象的表示。
优选的，所述所述概念包括一级概念和二级概念，概念表示的则是对象的集合，关系对表示对象元组的集合，所述概念采用框架结构，包括概念的名称，与其他概念之间关系的集合，以及用语义对概念的描述。
优选的，所述隐性知识对应的文库包括知识库，所述知识库包括语义本体知识信息以及相应的图案信息；所述显性知识对应的文库包括案例样本库，所述案例样本库包括广彩瓷的图像、文本、音频、视频。
优选的，所述通用知识本体包括的通用概念有：广彩瓷的瓷器的历史、工艺、色彩、边饰。
优选的，所述领域知识本体指描述特定应用领域和学科的知识。
优选的，动态知识的本体以用户的实际需求为牵引，构建过程利用现有知识和网络数据资源，依靠机器自动完成，所述动态知识本体主要关注特定任务、事件或活动中的对象及对象之间的关系。
优选的，所述语义检索模型的检索流程包括以下步骤：
获取用户请求，根据用户请求提取语义标签；
根据语义标签进行信息推理在广彩瓷知识模型进行扩展查询；
筛选检索结果并将其推送至用户。
优选的，通过语义检索模型进行个性化学习流程包括：
根据语义检索结果生成图像描述；
根据图像描述进行广彩瓷的构型提取语重用。
本申请提供了一种基于语义本体的广彩瓷知识库的构建方法，该方法包括：根据广彩瓷图案对广彩瓷元素进行语义分析，并构建语义本体的建模元语；根据知识的管理原则获取广彩瓷知识的显性知识和隐性知识；将所述显性知识和所述隐性知识对应的文库划分为通用知识本体、动态知识本体、领域知识本体；将通用知识本体、动态知识本体、领域知识本体融合成广彩瓷知识模型；基于广彩瓷知识模型构建语义检索模型用于个性化学习。
本申请通过对广彩瓷元素语义结合本体的建模元语，从知识应用的角度的构建了多维语义本体的广彩瓷知识模型和语义检索模型，增强了广彩瓷知识库的实用性和易用性，能够促进人们对传统文化的传播与学习，进一步为人们参与传统文化的学习传承提供新的途径。
附图说明
图1为本申请一种基于语义本体的广彩瓷知识库的构建方法的一个实施例的流程图；
图2为本申请一种基于语义本体的广彩瓷知识库的构建方法的另一个实施例的流程图；
图3为本申请一种基于语义本体的广彩瓷知识库的构建方法的另一个实施例的流程图。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
请参考图1，其为本申请一种基于语义本体的广彩瓷知识库的构建方法的一个实施例的流程图，包括以下步骤：
步骤S100，根据广彩瓷图案对广彩瓷元素进行语义分析，并构建语义本体的建模元语；
需要说明的是，对广彩瓷元素进行语义分析，可以是对广彩瓷作品形态、色彩、元素、主题进行语义分析，探究提取广彩瓷的语义内涵和情感要素，获取了具体语义后再对语义进行联想、发散和重组。
在本申请中表达本体构建了5个建模元语，具体为：类、关系、函数、公理、实例，类广彩瓷领域所涉及的术语和概念，例如，分类工艺、制作方法等，对于概念在具体的实施例中可以将广彩瓷分为盘、碟、盆、碗、盅、壶、杯、瓶、画等一级概念，将一级概念下的分类归为二级概念；概念表示的则是对象的集合，关系对表示对象元组的集合，概念采用框架结构，包括概念的名称，与其他概念之间关系的集合，以及用语义对概念的描述。
需要说明的是，关系包括对象关系属性和值关系属性，其中对象关系属性用来描述类间的关系；
函数用于描述概念与数据类型间的关系；公理(axioms)是广彩瓷本体中类和属性的限制描述；实例为对象的表示。
步骤S200，根据知识的管理原则获取广彩瓷知识的显性知识和隐性知识；
需要说明的是，显性知识是指能够用语言、文字、肢体、图表等方式表达清楚的知识，即能通过表达而让别人明白的知识；隐性知识则是透过外层次，需要进一步了解其内层次内涵的知识。本体在描述现实世界的知识时也体现出不同的层次性。在本申请中，隐性知识对应的文库包括知识库，知识库包括语义本体知识信息以及相应的图案信息；显性知识对应的文库包括案例样本库，案例样本库包括广彩瓷的图像、文本、音频、视频。
需要说明的是，在本申请中，利用通用知识和领域知识对现有相对稳定的知识资源进行形式化描述，动态知识针对用户对知识进行的交互学习，以及现实中动态发生的事实，例如对广彩瓷的实体对象，进行形式化描述；其次，针对知识涵盖文化应用领域的现状，对所应用领域的知识进行知识体系构建，形式化描述领域术语及关联关系，实现知识的跨领域共享；最后，针 对知识的多语言特性，在不同语言的知识之间建立联系，实现跨语言知识的映射关联，构建完成的多维语义本体描述的概念从抽象到具体，根据适用范围的不同，逐渐细化。通用知识的概念和领域知识的概念主要表现为相对稳定的层次状结构，领域知识的概念在继承通用概念属性的同时，增加概念自身的领域属性。动态知识主要描述现实中动态发生的事实，其知识可能直接来自于上层的通用知识和领域知识，根据应用场景的特点，动态增加新的知识内涵，它主要表现为动态的网状结构。
步骤S300，将显性知识和隐性知识对应的文库划分为通用知识本体、动态知识本体、领域知识本体；
需要说明的是，通用知识本体包括的通用概念有：广彩瓷的瓷器的历史、工艺、色彩、边饰。广彩瓷也可以考虑在瓷器领域内选取通用词汇，丰富可用词汇量，从而构建一定数量的通用概念的知识体系。
领域知识本体指描述特定应用领域和学科的知识。领域知识本体具有较强的学科依赖性，如工业、美术等领域。构建领域知识需要明确领域内共同认可的概念，并用形式化的模型对这些概念以及概念间的关系进行表示，实现对该领域知识的共同理解。如陶瓷属于工业领域范畴，以陶瓷为原材料的广彩瓷在制作工艺上，就可以在工业术语内查找比较合适的概念词汇。
动态知识本体以用户的实际需求为牵引，构建过程利用现有知识和网络数据资源，依靠机器自动完成，动态知识本体主要关注特定任务、事件或活动中的对象及对象之间的关系。例如在广彩瓷的个性化学习过程中，可以根据用户的学习动态和输入标签，以及关于广彩瓷的信息资讯选取一些动态知识，进一步帮助广彩瓷本体模型的构建。动态知识具有很强的可扩展性，可以持续跟踪，积极响应新动态，实现对知识的动态扩充与维护。
步骤S400，将通用知识本体、动态知识本体、领域知识本体融合成广彩瓷知识模型；
步骤S500，基于广彩瓷知识模型构建语义检索模型用于个性化学习。
需要说明的是，在构建了广彩瓷知识模型后需要提供一个实用、易用的检索方式，本申请基于广彩瓷知识模型构建语义检索模型，语义检索的搜索引擎其工作不再拘泥于用户所输入请求语句的字面本身，捕捉到用户所输入 语句后面的真正意图，并以此来进行搜索，从而更准确地向用户返回最符合其需求的搜索结果。语义搜索对网页文档信息所蕴含的语义信息进行充分挖掘，同时把用户的检索要求转换成相应的语义表示，基于领域本体对其进行辨别和推理，从语义层面理解用户查询,并将基于本体推理的结果返回给用户。基于本体的语义检索和推荐能够帮助用户不断调整自己的检索词汇，改变检索策略，以获得最为相关的知识，同时有效弥补了关键词检索的不足，显著提高了查询结果的精准性。
语义检索模型的检索流程，可以参考图2，包括：
步骤S510，获取用户请求，根据用户请求提取语义标签；
步骤S520，根据语义标签进行信息推理在广彩瓷知识模型进行扩展查询；
步骤S530，筛选检索结果并将其推送至用户。
在一种具体的实施方式中，用户在进行语义检索获取了检索结果后，可以对检索结果进行个性化的学习及用于，通过语义检索模型进行个性化学习流程，参考图3，包括：
步骤S531，根据语义检索结果生成图像描述；
步骤S532，根据图像描述进行广彩瓷的构型提取及重用。
本申请提供了一种基于语义本体的广彩瓷知识库的构建方法，该方法包括：根据广彩瓷图案对广彩瓷元素进行语义分析，并构建语义本体的建模元语；根据知识的管理原则获取广彩瓷知识的显性知识和隐性知识；将显性知识和隐性知识对应的文库划分为通用知识本体、动态知识本体、领域知识本体；将通用知识本体、动态知识本体、领域知识本体融合成广彩瓷知识模型；基于广彩瓷知识模型构建语义检索模型用于个性化学习。
本申请通过对广彩瓷元素语义分析结合本体的建模元语，从知识应用的角度的构建了多维语义本体的广彩瓷知识模型和语义检索模型，增强了广彩瓷知识库的实用性和易用性，能够促进人们对传统文化的传播与学习，进一步为人们参与传统文化的学习传承提供新的途径。
本申请的说明书及上述附图中的术语“第一”、“第二”、“第三”、“第四”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例例 如能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
应当理解，在本申请中，“至少一个(项)”是指一个或者多个，“多个”是指两个或两个以上。“和/或”，用于描述关联对象的关联关系，表示可以存在三种关系，例如，“A和/或B”可以表示：只存在A，只存在B以及同时存在A和B三种情况，其中A，B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系。“以下至少一项(个)”或其类似表达，是指这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如，a，b或c中的至少一项(个)，可以表示：a，b，c，“a和b”，“a和c”，“b和c”，或“a和b和c”，其中a，b，c可以是单个，也可以是多个。
以上所述，以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (10)

  1. 一种基于语义本体的广彩瓷知识库的构建方法，其特征在于，包括：
    根据广彩瓷图案对广彩瓷元素进行语义分析，并构建语义本体的建模元语；
    根据知识的管理原则获取广彩瓷知识的显性知识和隐性知识；
    将所述显性知识和所述隐性知识对应的文库划分为通用知识本体、动态知识本体、领域知识本体；
    将通用知识本体、动态知识本体、领域知识本体融合成广彩瓷知识模型；
    基于广彩瓷知识模型构建语义检索模型用于个性化学习。
  2. 根据权利要求1所述的广彩瓷知识库的构建方法，其特征在于，所述对广彩瓷元素进行语义分析，所述的广彩瓷元素包括有：广彩瓷作品形态、色彩、元素、主题。
  3. 根据权利要求1所述的广彩瓷知识库的构建方法，其特征在于，所述的建模元语包括：类、关系、函数、公理、实例，所述类广彩瓷领域所涉及的术语和概念；
    所述关系包括对象关系属性和值关系属性；
    所述函数用于描述概念与数据类型间的关系；
    所述实例为对象的表示。
  4. 根据权利要求3所述的广彩瓷知识库的构建方法，其特征在于，所述所述概念包括一级概念和二级概念，概念表示的则是对象的集合，关系对表示对象元组的集合，所述概念采用框架结构，包括概念的名称，与其他概念之间关系的集合，以及用语义对概念的描述。
  5. 根据权利要求1所述的广彩瓷知识库的构建方法，其特征在于，所述隐性知识对应的文库包括知识库，所述知识库包括语义本体知识信息以及相应的图案信息；所述显性知识对应的文库包括案例样本库，所述案例样本库包括广彩瓷的图像、文本、音频、视频。
  6. 根据权利要求1所述的广彩瓷知识库的构建方法，其特征在于，所述通用知识本体包括的通用概念有：广彩瓷的瓷器的历史、工艺、色彩、边饰。
  7. 根据权利要求1所述的广彩瓷知识库的构建方法，其特征在于，所述领域知识本体指描述特定应用领域和学科的知识。
  8. 根据权利要求1所述的广彩瓷知识库的构建方法，其特征在于，动态知识的本体以用户的实际需求为牵引，构建过程利用现有知识和网络数据资源，依靠机器自动完成，所述动态知识本体主要关注特定任务、事件或活动中的对象及对象之间的关系。
  9. 根据权利要求1所述的广彩瓷知识库的构建方法，其特征在于，所述语义检索模型的检索流程包括以下步骤：
    获取用户请求，根据用户请求提取语义标签；
    根据语义标签进行信息推理在广彩瓷知识模型进行扩展查询；
    筛选检索结果并将其推送至用户。
  10. 根据权利要求1所述的广彩瓷知识库的构建方法，其特征在于，通过语义检索模型进行个性化学习流程包括：
    根据语义检索结果生成图像描述；
    根据图像描述进行广彩瓷的构型提取语重用。
PCT/CN2020/129506 2020-11-05 2020-11-17 一种基于语义本体的广彩瓷知识库的构建方法 WO2022095121A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011222891.7 2020-11-05
CN202011222891.7A CN112307772B (zh) 2020-11-05 2020-11-05 一种基于语义本体的广彩瓷知识库的构建方法

Publications (1)

Publication Number Publication Date
WO2022095121A1 true WO2022095121A1 (zh) 2022-05-12

Family

ID=74325286

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/129506 WO2022095121A1 (zh) 2020-11-05 2020-11-17 一种基于语义本体的广彩瓷知识库的构建方法

Country Status (2)

Country Link
CN (1) CN112307772B (zh)
WO (1) WO2022095121A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116186294A (zh) * 2023-04-28 2023-05-30 浙江大学 一种基于超图的智能工厂元宇宙知识表示方法及其应用
CN116910250A (zh) * 2023-06-28 2023-10-20 北京百度网讯科技有限公司 知识处理方法、装置、电子设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101458732A (zh) * 2008-12-25 2009-06-17 浙江师范大学 面向饰品创新设计的知识应用方法
US20150088888A1 (en) * 2013-09-26 2015-03-26 International Business Machines Corporation Concept Driven Automatic Section Identification
CN106570566A (zh) * 2016-10-28 2017-04-19 安徽农业大学 一种基于本体的茶树虫害知识表示和共享方法
CN109344425A (zh) * 2018-08-13 2019-02-15 湖南师范大学 一种基于长沙窑文物元素再造创意设计集成平台
CN111291132A (zh) * 2020-01-14 2020-06-16 常州大学 面向智慧旅游的文物领域本体构建及分析方法

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105808734B (zh) * 2016-03-10 2020-07-28 同济大学 一种基于语义网的钢铁制造过程知识间隐性关系获取方法
US20180039890A1 (en) * 2016-08-03 2018-02-08 Electronics And Telecommunications Research Institute Adaptive knowledge base construction method and system
EP3447663A1 (en) * 2017-08-23 2019-02-27 Tata Consultancy Services Limited System and method for event profiling
CN108763445B (zh) * 2018-05-25 2019-09-17 厦门智融合科技有限公司 专利知识库的构建方法、装置、计算机设备和存储介质
CN110717014B (zh) * 2019-09-12 2020-09-04 北京四海心通科技有限公司 一种本体知识库动态构建方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101458732A (zh) * 2008-12-25 2009-06-17 浙江师范大学 面向饰品创新设计的知识应用方法
US20150088888A1 (en) * 2013-09-26 2015-03-26 International Business Machines Corporation Concept Driven Automatic Section Identification
CN106570566A (zh) * 2016-10-28 2017-04-19 安徽农业大学 一种基于本体的茶树虫害知识表示和共享方法
CN109344425A (zh) * 2018-08-13 2019-02-15 湖南师范大学 一种基于长沙窑文物元素再造创意设计集成平台
CN111291132A (zh) * 2020-01-14 2020-06-16 常州大学 面向智慧旅游的文物领域本体构建及分析方法

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116186294A (zh) * 2023-04-28 2023-05-30 浙江大学 一种基于超图的智能工厂元宇宙知识表示方法及其应用
CN116186294B (zh) * 2023-04-28 2023-08-18 浙江大学 一种基于超图的智能工厂元宇宙知识表示方法及其应用
CN116910250A (zh) * 2023-06-28 2023-10-20 北京百度网讯科技有限公司 知识处理方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN112307772B (zh) 2022-03-25
CN112307772A (zh) 2021-02-02

Similar Documents

Publication Publication Date Title
CN107609052B (zh) 一种基于语义三角的领域知识图谱的生成方法及装置
KR20070112730A (ko) 지능형 정보 검색 처리 시스템 및 방법
WO2022095121A1 (zh) 一种基于语义本体的广彩瓷知识库的构建方法
Alma’aitah et al. Opportunities and challenges in enhancing access to metadata of cultural heritage collections: a survey
Konys Ontology-based approaches to big data analytics
CN105989097A (zh) 一种基于本体的知识库查询方法及系统
Newbury LOUD: Linked Open Usable Data and linked. art
CN102915304A (zh) 文档检索设备和方法
Goyal et al. A Review on Different Content Based Image Retrieval Techniques Using High Level Semantic Feature
CN116595139A (zh) 一种基于多模态知识图谱的智能问答方法
Vasilyeva et al. Leveraging flexible data management with graph databases
CN115982322A (zh) 一种水利行业设计领域知识图谱的检索方法及检索系统
Xie et al. Tree-structure based ontology integration
CN115082010A (zh) 一种电力领域元数据智能管理方法、存储介质及系统
Yamada et al. Interactive service for visualizing data association using a self-organizing structure of schemas
Daoud et al. Building a new semantic social network using semantic web-based techniques
Li et al. A framework of ontology-based knowledge management system
Ruangrajitpakorn et al. Automatic ontology development from semi-structured data in web-portal: Towards ontology of thai rice knowledge
Sancheti et al. Harvesting Knowledge from Cultural Heritage Artifacts in Museums of India
Hakeem A framework for combining software patterns with semantic web for unstructured data analysis
Lima et al. Building Geospatial Ontologies From Geographic Database Schemas In Peer Data Management Systems.
Qu et al. User oriented semi-automatic method of constructing domain ontology
Leshcheva et al. Towards a method of ontology population from heterogeneous sources of structured data
Paulus et al. Recommending Semantic Concepts for Improving the Process of Semantic Modeling
Fan Research on image semantic communication and retrieval based on massive resource library of internet

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20960578

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20960578

Country of ref document: EP

Kind code of ref document: A1