WO2020233261A1 - 一种基于自然语言生成技术的知识图谱辅助理解系统 - Google Patents
一种基于自然语言生成技术的知识图谱辅助理解系统 Download PDFInfo
- Publication number
- WO2020233261A1 WO2020233261A1 PCT/CN2020/083591 CN2020083591W WO2020233261A1 WO 2020233261 A1 WO2020233261 A1 WO 2020233261A1 CN 2020083591 W CN2020083591 W CN 2020083591W WO 2020233261 A1 WO2020233261 A1 WO 2020233261A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- knowledge graph
- predicate
- subject
- array
- natural language
- Prior art date
- Legal status (The legal status 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 status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 invention relates to the technical field of knowledge graphs, and in particular to a knowledge graph assisted understanding system based on natural language generation technology.
- the knowledge graph is a semantic knowledge base. It usually uses the subject-predicate-object triple form to represent a knowledge point. Compared with the strict requirements of the ontology for logic and semantics, the knowledge graph emphasizes weak semantics and weak logic, so In academia and industry, knowledge graphs have been well promoted. Large Internet companies led by Google have begun to study knowledge graphs to improve the quality of search. According to a 2014 report, Google's knowledge graph has collected more than 1.6 billion facts, of which 271 million facts are believed to be more than 90% authentic. In a Google search in May 2016, Knowledge Graph answered approximately one-third of the 100 billion searches that month.
- Natural language generation technology is one of the major technologies of natural language processing technology. Different from natural language understanding, natural language generation technology focuses on how computers express given meanings and ideas in natural language text. For knowledge graphs, especially knowledge graphs in specific fields, the accuracy requirements for practical knowledge graphs are very high, such as medical-related knowledge graphs. The quality of the knowledge graphs is seriously related to the accuracy of the entire system.
- the programming language used to construct the knowledge graph is the same as the ontology, mainly RDF (Resource Description Framework), OWL (Web Ontology Language, network ontology language), and the software used is mainly Protégé developed by Stanford University. These languages and software are highly professional, and it is difficult for non-related personnel to understand their specific meaning without long-term learning and training.
- Knowledge graphs in many fields require domain experts to have an in-depth and comprehensive understanding of their representations before they are used, so as to ensure their accuracy in actual use.
- the relevant languages and software of the knowledge graph are highly specialized, and the knowledge points on the same topic are scattered. It is difficult for domain experts to master and understand them in a short time.
- most of the software that assists in understanding the knowledge graph is to display the association of different knowledge nodes by visual means through search.
- the knowledge presented in this way is partial knowledge and does not involve the knowledge graph itself. At the same time, these methods are used to discover the problems in the use of knowledge graphs, and they have not been fully understood and evaluated before they are used.
- the purpose of the present invention is to provide a knowledge graph assisted understanding system based on natural language generation technology based on the current insufficient control of the quality of knowledge graphs and the difficulty for domain experts to understand domain-related knowledge graphs.
- the present invention uses Natural language generation technology generates natural language texts based on the content of the knowledge graph, and appropriately aggregates short sentences on the same topic, and each sentence corresponds to the programming language in the knowledge graph, so as to facilitate the domain experts in a shorter time Quickly, comprehensively and in-depth understanding of the knowledge map internally, and control the quality of the knowledge map.
- a knowledge map auxiliary understanding system based on natural language generation technology, the system including a knowledge map selection module, a knowledge map translation module and a result display module;
- the knowledge graph selection module is used to obtain a target knowledge graph conforming to RDF or OWL grammar specifications
- the knowledge graph translation module first extract the triples of the target knowledge graph, and perform string segmentation on the extracted triples to obtain three dynamic arrays: subject array, predicate array, and object array, which have a one-to-one correspondence between the three Relations, and then through nested loops, use the simplenlg tool to assemble the subject, predicate, and object to form a complete sentence. At the same time, there are one-to-many and one-to-many situations for the subject-predicate-object relationship.
- the result display module retrieves the translated content (ie short sentences and long sentences) of the target knowledge graph from the local database, and converts the translated content and the source files of the target knowledge graph (RDF (Resource Description Framework), OWL (Web Ontology Language)) Perform a joint display, obtain a JSON format file at the same time, draw a tree diagram through a visualization tool (you can use the D3 tool) to visualize the hierarchical structure of classes and subclasses and classes and instances in the knowledge graph.
- RDF Resource Description Framework
- OWL Web Ontology Language
- the open source knowledge graph database can choose the National Center for Biomedical Ontology (NCBO)) to crawl from the RDF or
- NCBO National Center for Biomedical Ontology
- the crawled knowledge graph is translated through the knowledge graph translation module, and the translation result is stored in the local database; when it is used to search the knowledge graph of a certain topic in the system, enter the name and knowledge graph Calculate the similarity of the English names of, and sort by the similarity from largest to smallest, and get the knowledge graph of the candidate target;
- Way 2 Users upload a knowledge graph conforming to RDF or OWL grammar specifications as the target knowledge graph.
- the similarity judgment coefficient adopts the Jaccard similarity coefficient (Jaccard coefficient), which is often used to compare the similarity and difference between a limited sample set.
- Jaccard similarity coefficient Jaccard coefficient
- the steps of extracting the triples of the target knowledge graph in the knowledge graph translation module are as follows: using SPARQL (SPARQL Protocol and RDF Query Language, SPARQL protocol and RDF query language) to extract all the knowledge points (classes) in the target knowledge graph , Instances, object attributes, data attributes, annotations, etc.) corresponding subject, predicate, and object, and encode them into a resource description frame triple (RDF Triple).
- SPARQL SPARQL Protocol and RDF Query Language, SPARQL protocol and RDF query language
- the short sentence generation steps of the target knowledge graph in the knowledge graph translation module are specifically as follows: first, the obtained triples are divided into strings, the subject, predicate, and object names are obtained, and three dynamic arrays are constructed. In the generation of short sentences, because the subject, predicate, and object are in a one-to-one relationship, through nested loops, the corresponding subject, predicate, and object can be directly assembled into short sentences using Simplenlg.
- the steps of generating long sentences of the target knowledge graph in the knowledge graph translation module are specifically as follows: first, the obtained triples are divided into strings, the subject, predicate and object names are obtained, and three dynamic arrays are constructed.
- the predicates corresponding to different subjects are marked with special identifiers; in the object array
- the objects of different predicates corresponding to different subjects are marked with another special identifier to realize the one-to-one correspondence between subject, predicate, and object.
- nested loops are used to judge these special identifiers, and the corresponding The subject, predicate and object are assembled using Simplenlg.
- the same subject and different predicates each constitute a sentence
- all sentences of the same subject constitute a paragraph
- different objects are connected by connecting words (and, or).
- annotation information steps of the supplementary sentence of the target knowledge graph in the knowledge graph translation module are specifically as follows: first, loop the predicate array, and if the predicate is "comment" (annotation indicating the object-subject), then the corresponding subject And the object is extracted to form a new dynamic array-annotation array, in which array elements with odd subscripts store the subject, and array elements with even subscripts store the object. Then perform a nested loop of subject array, predicate array and object array to determine whether the subject and object are in the annotation array. If they exist, add parentheses after the subject or object, and the annotations are inside the parentheses, and then judge the predicate, if the predicate If it is not "comment", then proceed to assembly, otherwise not assembly.
- the steps of inserting the short sentences and long sentences of the target knowledge graph in the knowledge graph translation module into the database are specifically as follows: use the JDBC (Java Database Connectivity) API to connect to the database, and first create a database and a data table storing the translation results, Define the table name, table field, confirm the primary key, etc., and then match the English name of the knowledge graph with the name stored in the database. If the translation result of the knowledge graph already exists in the knowledge base, no insert operation is performed. If not, Then add the generated short sentence array and long sentence array to the data table.
- JDBC Java Database Connectivity
- the specific steps for displaying the translated content and source files in the result display module are as follows: After selecting the target knowledge graph in the web interface, use ajax to retrieve all the translated content corresponding to the knowledge graph from the database and display it on the interface , And read the source files of the target knowledge graph from the local server and display them in the interface.
- the specific steps of the visual display in the result display module are as follows: After selecting the target knowledge graph in the web interface, use ajax to obtain the corresponding JSON format file on the back end, and draw the tree diagram; in the tree diagram, Each node represents a subject or an object, and each node is connected to other associated nodes through wires.
- the beneficial effect of the present invention is that the present invention utilizes natural language generation technology to convert the knowledge graph into natural language text, which is convenient for field experts to understand the source code and software of the knowledge graph before using the knowledge graph, for their field knowledge
- the knowledge graph has an accurate, in-depth and comprehensive understanding.
- each short sentence is associated with the corresponding source code of the knowledge graph itself. If the redundancy and error information in the knowledge graph is found, it can be corrected in time, and the method is highly versatile.
- a visualization method is used to further accelerate the understanding of the knowledge graph by domain experts.
- Figure 1 is a structural block diagram of the knowledge graph assisted understanding system based on natural language generation technology of the present invention
- Figure 2 is a flowchart of the implementation of the knowledge graph assisted understanding system based on natural language generation technology of the present invention
- Figure 4 is a schematic diagram of part of the source code of a certain knowledge graph
- Figure 5 is a schematic diagram of short sentences generated using natural language technology
- Figure 6 is a schematic diagram of a long sentence generated using natural language technology
- Figure 7 is a tree diagram of classes and subclasses.
- a knowledge graph assisted understanding system based on natural language generation technology includes a knowledge graph selection module, a knowledge graph translation module and a result display module;
- the knowledge graph selection module is used to obtain the target knowledge graph conforming to RDF or OWL grammar specifications; there are two ways to obtain the target knowledge graph:
- the open source knowledge graph database can choose the National Center for Biomedical Ontology (NCBO)) to crawl from the RDF or
- NCBO National Center for Biomedical Ontology
- the crawled knowledge graph is translated through the knowledge graph translation module, and the translation result is stored in the local database; when it is used to search the knowledge graph of a certain topic in the system, enter the name and knowledge graph Calculate the similarity of the English names of, and sort by the similarity from largest to smallest, and get the knowledge graph of the candidate target;
- the similarity judgment coefficient can be the Jaccard similarity coefficient (Jaccard coefficient), which is often used to compare the similarity and difference between a limited sample set. The larger the Jaccard coefficient value, the higher the sample similarity.
- each search result is sorted by similarity, showing N results with higher similarity, N is user-defined, and N can be set to 15.
- Way 2 Users upload a knowledge graph conforming to RDF or OWL grammar specifications as the target knowledge graph.
- the standardized sentence is inserted into the local database, and the content of the relationship between class and subclass, class and instance is selected from the three dynamic arrays of subject, predicate, and object, and assembled into a JSON format file.
- the local database can use MySQL database. MySQL is currently a popular open source relational database management system. It can store data in different tables instead of putting all the data in one warehouse, which increases the speed. .
- the steps to extract the triples of the target knowledge graph are as follows: Use SPARQL (SPARQL Protocol and RDF Query Language, SPARQL protocol and RDF query language) to extract all knowledge points (classes, instances, object attributes, data attributes, annotations) in the target knowledge graph Etc.) Corresponding subject, predicate, and object, and encode them into a triple of resource description framework (RDF Triple).
- SPARQL SPARQL Protocol and RDF Query Language
- RDF Triple resource description framework
- the specific steps of generating short sentences in the target knowledge graph are as follows: First, the obtained triples are divided into strings, the subject, predicate, and object names are obtained, and three dynamic arrays are constructed. In the generation of short sentences, because the subject, predicate, and object are in a one-to-one relationship, through nested loops, the corresponding subject, predicate, and object can be directly assembled into short sentences using Simplenlg.
- the steps for generating long sentences of the target knowledge graph are as follows: First, the obtained triples are divided into strings, the subject, predicate, and object names are obtained, and three dynamic arrays are constructed.
- the predicates corresponding to different subjects are marked with special identifiers; in the object array
- the objects of different predicates corresponding to different subjects are marked with another special identifier to realize the one-to-one correspondence between subject, predicate, and object.
- nested loops are used to judge these special identifiers, and the corresponding Subject, predicate and object are assembled using Simplenlg.
- the same subject and different predicates each constitute a sentence, all sentences of the same subject constitute a paragraph, and different objects are connected by connecting words (and, or).
- the annotation information steps of the supplementary sentence of the target knowledge graph are as follows: First, loop the predicate array, if the predicate is "comment" (representing the comment of the object-subject), extract the corresponding subject and object to form a new dynamic array -Annotation array, in which array elements with odd subscripts store the subject, and array elements with even subscripts store the object. Then perform a nested loop of subject array, predicate array and object array to determine whether the subject and object are in the annotation array. If they exist, add parentheses after the subject or object, and the annotations are inside the parentheses, and then judge the predicate, if the predicate If it is not "comment", then proceed to assembly, otherwise not assembly.
- the steps for inserting the short and long sentences of the target knowledge graph into the database are as follows: Use the JDBC (Java Database Connectivity) API to connect Java to the database. First, create the database and data table for storing the translation results, and define the table name, table fields, Confirm the primary key, etc., and then match the English name of the knowledge graph with the name stored in the database. If the translation result of the knowledge graph already exists in the knowledge base, no insert operation will be performed. If not, the short sentence array will be generated And the long sentence array is added to the data table.
- JDBC Java Database Connectivity
- the result display is divided into three parts.
- the file or parameters will be submitted to the back-end through ajax.
- its source code will be displayed on the web page and automatically proceed.
- Language generation the generated results will be inserted into the database, and then the relevant content will be read from the database and displayed on the web page.
- the system selects the content of class and subclass, class and instance relationship from the three dynamic arrays of subject, predicate, and object, and assembles them into a JSON format file, transmits it to the front end, and uses the visualization tool D3 to draw a tree diagram to show its main Hierarchical structure. Take a knowledge graph about chronic kidney disease published by the American Biomedical Ontology Center as an example. The running results are shown in Figure 4-7, and Figure 7 shows part of the tree diagram.
- the system After uploading the target knowledge graph to the website or selecting the knowledge graph in the library on the website, the system will automatically query the relevant content in the knowledge graph, segment the string, and translate the RDF Triple into short sentences and long sentences , And further standardize the sentence structure, and finally show the generated text to the domain experts, where each sentence corresponds to the source code of its knowledge graph.
- the system presents the important classes and subclasses, and the relationships between classes and instances in the knowledge graph in the form of a tree diagram, helping experts quickly understand and master the content and information of the knowledge graph, so as to control the quality in a short time.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Machine Translation (AREA)
- Steering-Linkage Mechanisms And Four-Wheel Steering (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
- Power Steering Mechanism (AREA)
Abstract
Description
Claims (10)
- 一种基于自然语言生成技术的知识图谱辅助理解系统,其特征在于,该系统包括知识图谱选择模块、知识图谱翻译模块和结果展示模块;所述知识图谱选择模块用于获取符合RDF或OWL语法规范的目标知识图谱;所述知识图谱翻译模块:首先提取目标知识图谱的三元组,对提取的三元组进行字符串分割得到三个动态数组:主语数组、谓语数组、宾语数组,三者之间具有一一对应关系,然后通过嵌套循环,利用simplenlg工具对主语、谓语和宾语进行组装,形成一句完整的短句;同时对于主语-谓语-宾语的关系存在一对一对多和一对多对多的情况,在谓语数组和宾语数组中加入特殊字符进行标识,以确定该谓语对应某一主语以及该宾语对应某一主语和某一谓语,然后在嵌套循环中判断这些特殊字符以确定主语、谓语、宾语的对应关系,利用simplenlg工具对对应的主语、谓语和宾语进行组装,形成一个完整的长句;其中注解部分对应的三元组不单独成句,而是作为补充其他句子的注解信息;然后将目标知识图谱翻译成短句和长句,句子得到进一步规范后被存入本地数据库中,并从主语、谓语、宾语三个动态数组中选出类与子类、类与实例关系的内容组装成JSON格式的文件;所述结果展示模块从本地数据库调取目标知识图谱的翻译内容,将翻译内容以及目标知识图谱的源文件进行共同展示,同时获取JSON格式的文件,通过可视化工具绘制树状图,对知识图谱中的类与子类以及类与实例的层级结构进行可视化展示。
- 根据权利要求1所述的一种基于自然语言生成技术的知识图谱辅助理解系统,其特征在于,所述知识图谱选择模块获取目标知识图谱的途径包括两种:途径一:从开源知识图谱数据库中爬取符合RDF或OWL语法规范的知识图谱,对爬取的知识图谱通过知识图谱翻译模块进行翻译,将翻译结果存入本地数据库中;当用于在系统中搜索某一主题的知识图谱时,输入名称与知识图谱的英文名称进行相似度计算,按相似度从大到小进行排序,得到待选目标知识图谱;途径二:用户上传符合RDF或OWL语法规范的知识图谱作为目标知识图谱。
- 根据权利要求1所述的一种基于自然语言生成技术的知识图谱辅助理解系统,其特征在于,所述知识图谱翻译模块中提取目标知识图谱的三元组的步骤具体如下:利用SPARQL提取目标知识图谱中全部知识点(类、实例、对象属性、数据属性、注解等)对应的主语、谓语和宾语,并将其编码成资源描述框架的三元组。
- 根据权利要求1所述的一种基于自然语言生成技术的知识图谱辅助理解系统,其特征在于,所述知识图谱翻译模块中目标知识图谱的短句生成步骤具体如下:首先对获取的三元组进行字符串分割,获得主语、谓语和宾语的名称,构建三个动态数组。在短句生成中,由于主语、谓语和宾语关系是一对一对一的关系,所以通过嵌套循环,将对应的主语、谓语、宾语利用Simplenlg直接组装成短句即可。
- 根据权利要求1所述的一种基于自然语言生成技术的知识图谱辅助理解系统,其特征在于,所述知识图谱翻译模块中目标知识图谱的长句生成的步骤具体如下:首先对获取的三元组进行字符串分割,获得主语、谓语和宾语的名称,构建三个动态数组。在长句生成中,考虑到一个主语可以对应多个谓语,而每个谓语又可以对应多个宾语,因此在谓语数组中,不同主语对应的谓语之间用特殊标识符进行标记;在宾语数组中,不同主语对应的不同谓语的宾语之间采用另一特殊标识符进行标记,实现主语、谓语、宾语的一一对应关系,然后采用嵌套循环,对这些特殊标识符进行判断,将对应的主语、谓语和宾语利用Simplenlg进行组装。其中同一主语不同谓语各自构成一个句子,同一主语的所有句子构成一个段落,不同宾语之间用连接词进行连接。
- 根据权利要求1所述的一种基于自然语言生成技术的知识图谱辅助理解系统,其特征在于,所述知识图谱翻译模块中目标知识图谱的补充句子的注解信息步骤具体如下:首先对谓语数组进行循环,如果谓语为“comment”(表示宾语为主语的注释),则将对应的主语和宾语提取,形成一个新的动态数组-注解数组,其中奇数下标的数组元素存储主语,偶数下标的数组元素存储宾语。然后进行主语数组、谓语数组和宾语数组的嵌套循环,判断主语、宾语是否在注解数组中,如果存在,则在该主语或者宾语后面添加括号,括号内为其注解,然后判断谓语,如果谓语不是“comment”,则进行组装,否则不组装。
- 根据权利要求1所述的一种基于自然语言生成技术的知识图谱辅助理解系统,其特征在于,所述知识图谱翻译模块中目标知识图谱的短句和长句插入数据库的步骤具体如下:利用JDBC API进行数据库的连接,首先创建存放翻译结果的数据库以及数据表,定义表名、表字段、确认主键等,然后将知识图谱的英文名称与数据库中存储的名称进行匹配,如果该知识图谱的翻译结果已经存在于本地数据库中,则不进行插入操作,如果没有,则将生成的 短句数组和长句数组添加到数据表中。
- 根据权利要求1所述的一种基于自然语言生成技术的知识图谱辅助理解系统,其特征在于,所述结果展示模块中翻译内容和源文件展示的具体步骤如下:在网页界面中选定目标知识图谱后,利用ajax从数据库中调取该知识图谱对应的所有翻译内容显示在界面上,并且从本地服务器读取目标知识图谱的源文件,共同显示在界面中。
- 根据权利要求1所述的一种基于自然语言生成技术的知识图谱辅助理解系统,其特征在于,所述结果展示模块中可视化展示的具体步骤如下:在网页界面中选定目标知识图谱后,利用ajax获取后端相应的JSON格式的文件,绘制树状图;在树状图中,每个节点表示主语或者宾语,每个节点通过连线与其他关联的节点进行连接。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2021532885A JP7064262B2 (ja) | 2019-07-12 | 2020-04-07 | 自然言語生成技術に基づく知識グラフ理解支援システム |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910629843.0 | 2019-07-12 | ||
| CN201910629843.0A CN110347798B (zh) | 2019-07-12 | 2019-07-12 | 一种基于自然语言生成技术的知识图谱辅助理解系统 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020233261A1 true WO2020233261A1 (zh) | 2020-11-26 |
Family
ID=68176110
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2020/083591 Ceased WO2020233261A1 (zh) | 2019-07-12 | 2020-04-07 | 一种基于自然语言生成技术的知识图谱辅助理解系统 |
Country Status (3)
| Country | Link |
|---|---|
| JP (1) | JP7064262B2 (zh) |
| CN (1) | CN110347798B (zh) |
| WO (1) | WO2020233261A1 (zh) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112749184A (zh) * | 2021-01-13 | 2021-05-04 | 首都师范大学 | 一种sparql联合查询的数据源选择方法 |
| CN113111458A (zh) * | 2021-04-13 | 2021-07-13 | 合肥工业大学 | 一种基于dxf的钣金件自动识别和定位方法 |
| CN113157891A (zh) * | 2021-05-07 | 2021-07-23 | 泰康保险集团股份有限公司 | 知识图谱路径排序方法、系统、设备及存储介质 |
| CN113282762A (zh) * | 2021-05-27 | 2021-08-20 | 深圳数联天下智能科技有限公司 | 知识图谱构建方法、装置、电子设备和存储介质 |
| CN113377349A (zh) * | 2021-06-21 | 2021-09-10 | 浙江工业大学 | 服务流程间差异检测与自然语言翻译方法 |
| CN113407688A (zh) * | 2021-06-15 | 2021-09-17 | 西安理工大学 | 一种基于知识图谱的勘察规范智能问答系统的建立方法 |
| CN113467755A (zh) * | 2021-07-12 | 2021-10-01 | 卡斯柯信号有限公司 | 需求符合性分析方法、系统、电子设备及存储介质 |
| CN113553443A (zh) * | 2021-07-18 | 2021-10-26 | 北京智慧星光信息技术有限公司 | 记录知识图谱游走路径的关系图谱生成方法和系统 |
| CN113805847A (zh) * | 2021-09-15 | 2021-12-17 | 南通在渡教育咨询有限公司 | 在线无代码化开发系统 |
| CN113890899A (zh) * | 2021-09-13 | 2022-01-04 | 北京交通大学 | 一种基于知识图谱的协议转换方法 |
| CN114153943A (zh) * | 2021-11-22 | 2022-03-08 | 之江实验室 | 一种基于知识图谱构建机器人行为树的系统及方法 |
| CN114201618A (zh) * | 2022-02-17 | 2022-03-18 | 药渡经纬信息科技(北京)有限公司 | 药物研发文献可视化解读方法和系统 |
| CN114331062A (zh) * | 2021-12-16 | 2022-04-12 | 浙江工商大学 | 众包翻译任务切割方法及装置 |
| CN114840563A (zh) * | 2021-02-01 | 2022-08-02 | 腾讯科技(深圳)有限公司 | 一种字段描述信息的生成方法、装置、设备及存储介质 |
| CN114896233A (zh) * | 2022-05-11 | 2022-08-12 | 武汉镝次元数据科技有限公司 | 一种数据产品制作管理与发布系统 |
| CN115293176A (zh) * | 2022-08-02 | 2022-11-04 | 南京莱科智能工程研究院有限公司 | 一种基于知识图谱的领域机器翻译模型评价方法 |
| CN115564934A (zh) * | 2022-09-30 | 2023-01-03 | 中铁第四勘察设计院集团有限公司 | 一种基于WebGIS的工程地质遥感解译系统和方法 |
| CN115577713A (zh) * | 2022-12-07 | 2023-01-06 | 中科雨辰科技有限公司 | 一种基于知识图谱的文本处理方法 |
| CN115757812A (zh) * | 2022-10-27 | 2023-03-07 | 高质标准化研究院(山东)有限公司 | 一种基于人工智能的政策匹配方法 |
| WO2023159650A1 (en) * | 2022-02-28 | 2023-08-31 | Microsoft Technology Licensing, Llc | Mining and visualizing related topics in knowledge base |
| CN117436420A (zh) * | 2023-12-18 | 2024-01-23 | 武汉大数据产业发展有限公司 | 一种基于自然语言处理生成业务流程模型的方法和装置 |
| US12591688B2 (en) | 2023-06-27 | 2026-03-31 | International Business Machines Corporation | Context-aware cryptographic inventory |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110347798B (zh) * | 2019-07-12 | 2021-06-01 | 之江实验室 | 一种基于自然语言生成技术的知识图谱辅助理解系统 |
| CN111370127B (zh) * | 2020-01-14 | 2022-06-10 | 之江实验室 | 一种基于知识图谱的跨科室慢性肾病早期诊断决策支持系统 |
| US20210295036A1 (en) * | 2020-03-18 | 2021-09-23 | International Business Machines Corporation | Systematic language to enable natural language processing on technical diagrams |
| CN112100322B (zh) * | 2020-08-06 | 2022-09-16 | 复旦大学 | 一种基于知识图谱的api元素比较结果自动生成方法 |
| CN112101040B (zh) * | 2020-08-20 | 2024-03-29 | 淮阴工学院 | 一种基于知识图谱的古代诗词语义检索方法 |
| CN112380864B (zh) * | 2020-11-03 | 2021-05-28 | 广西大学 | 一种基于回译的文本三元组标注样本增强方法 |
| US11829726B2 (en) | 2021-01-25 | 2023-11-28 | International Business Machines Corporation | Dual learning bridge between text and knowledge graph |
| CN112966493A (zh) * | 2021-02-07 | 2021-06-15 | 重庆惠统智慧科技有限公司 | 一种知识图谱构建方法及系统 |
| CN113094517A (zh) * | 2021-04-27 | 2021-07-09 | 中国美术学院 | 一种产品知识单元的构建方法和系统 |
| CN113434626B (zh) * | 2021-08-27 | 2021-12-07 | 之江实验室 | 一种多中心医学诊断知识图谱表示学习方法及系统 |
| CN113810480B (zh) * | 2021-09-03 | 2022-09-16 | 海南大学 | 基于dikw内容对象的情感通讯方法 |
| CN115271683B (zh) * | 2022-09-26 | 2023-01-13 | 西南交通大学 | 基于标准知识图谱元结构的bim自动标准审查系统 |
| CN115545006B (zh) * | 2022-10-10 | 2024-02-13 | 清华大学 | 规则脚本生成方法、装置、计算机设备及介质 |
| CN116628229B (zh) * | 2023-07-21 | 2023-11-10 | 支付宝(杭州)信息技术有限公司 | 一种利用知识图谱生成文本语料的方法及装置 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020148A (zh) * | 2012-11-23 | 2013-04-03 | 复旦大学 | 一种将中文短语结构树库转化为依存结构树库的系统和方法 |
| CN108959613A (zh) * | 2018-07-17 | 2018-12-07 | 杭州电子科技大学 | 一种面向rdf知识图谱的语义近似查询方法 |
| CN109033260A (zh) * | 2018-07-06 | 2018-12-18 | 天津大学 | 基于rdf的知识图谱交互式可视化查询方法 |
| WO2019103727A1 (en) * | 2017-11-21 | 2019-05-31 | Google Llc | Improved onboarding of entity data |
| WO2019118256A1 (en) * | 2017-12-15 | 2019-06-20 | Microsoft Technology Licensing, Llc | Generation of text from structured data |
| CN110347798A (zh) * | 2019-07-12 | 2019-10-18 | 之江实验室 | 一种基于自然语言生成技术的知识图谱辅助理解系统 |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017018736A1 (en) * | 2015-07-24 | 2017-02-02 | Samsung Electronics Co., Ltd. | Method for automatically generating dynamic index for content displayed on electronic device |
| US10229195B2 (en) * | 2017-06-22 | 2019-03-12 | International Business Machines Corporation | Relation extraction using co-training with distant supervision |
| CN107766483A (zh) * | 2017-10-13 | 2018-03-06 | 华中科技大学 | 一种基于知识图谱的交互式问答方法及系统 |
| CN107798136B (zh) * | 2017-11-23 | 2020-12-01 | 北京百度网讯科技有限公司 | 基于深度学习的实体关系抽取方法、装置及服务器 |
| CN108829696B (zh) * | 2018-04-18 | 2019-10-25 | 西安理工大学 | 面向地铁设计规范中知识图谱节点自动构建方法 |
| CN109062939A (zh) * | 2018-06-20 | 2018-12-21 | 广东外语外贸大学 | 一种面向汉语国际教育的智能导学方法 |
| CN109146078B (zh) * | 2018-07-19 | 2021-04-30 | 桂林电子科技大学 | 一种基于动态路径的知识图谱表示学习方法 |
| CN109408811B (zh) * | 2018-09-29 | 2021-10-22 | 联想(北京)有限公司 | 一种数据处理方法及服务器 |
-
2019
- 2019-07-12 CN CN201910629843.0A patent/CN110347798B/zh active Active
-
2020
- 2020-04-07 WO PCT/CN2020/083591 patent/WO2020233261A1/zh not_active Ceased
- 2020-04-07 JP JP2021532885A patent/JP7064262B2/ja active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020148A (zh) * | 2012-11-23 | 2013-04-03 | 复旦大学 | 一种将中文短语结构树库转化为依存结构树库的系统和方法 |
| WO2019103727A1 (en) * | 2017-11-21 | 2019-05-31 | Google Llc | Improved onboarding of entity data |
| WO2019118256A1 (en) * | 2017-12-15 | 2019-06-20 | Microsoft Technology Licensing, Llc | Generation of text from structured data |
| CN109033260A (zh) * | 2018-07-06 | 2018-12-18 | 天津大学 | 基于rdf的知识图谱交互式可视化查询方法 |
| CN108959613A (zh) * | 2018-07-17 | 2018-12-07 | 杭州电子科技大学 | 一种面向rdf知识图谱的语义近似查询方法 |
| CN110347798A (zh) * | 2019-07-12 | 2019-10-18 | 之江实验室 | 一种基于自然语言生成技术的知识图谱辅助理解系统 |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112749184A (zh) * | 2021-01-13 | 2021-05-04 | 首都师范大学 | 一种sparql联合查询的数据源选择方法 |
| CN112749184B (zh) * | 2021-01-13 | 2024-02-20 | 广东粤通天下科技有限公司 | 一种sparql联合查询的数据源选择方法 |
| CN114840563B (zh) * | 2021-02-01 | 2024-05-03 | 腾讯科技(深圳)有限公司 | 一种字段描述信息的生成方法、装置、设备及存储介质 |
| CN114840563A (zh) * | 2021-02-01 | 2022-08-02 | 腾讯科技(深圳)有限公司 | 一种字段描述信息的生成方法、装置、设备及存储介质 |
| CN113111458A (zh) * | 2021-04-13 | 2021-07-13 | 合肥工业大学 | 一种基于dxf的钣金件自动识别和定位方法 |
| CN113111458B (zh) * | 2021-04-13 | 2022-10-21 | 合肥工业大学 | 一种基于dxf的钣金件自动识别和定位方法 |
| CN113157891A (zh) * | 2021-05-07 | 2021-07-23 | 泰康保险集团股份有限公司 | 知识图谱路径排序方法、系统、设备及存储介质 |
| CN113157891B (zh) * | 2021-05-07 | 2023-11-17 | 泰康保险集团股份有限公司 | 知识图谱路径排序方法、系统、设备及存储介质 |
| CN113282762A (zh) * | 2021-05-27 | 2021-08-20 | 深圳数联天下智能科技有限公司 | 知识图谱构建方法、装置、电子设备和存储介质 |
| CN113407688A (zh) * | 2021-06-15 | 2021-09-17 | 西安理工大学 | 一种基于知识图谱的勘察规范智能问答系统的建立方法 |
| CN113407688B (zh) * | 2021-06-15 | 2022-09-16 | 西安理工大学 | 一种基于知识图谱的勘察规范智能问答系统的建立方法 |
| CN113377349A (zh) * | 2021-06-21 | 2021-09-10 | 浙江工业大学 | 服务流程间差异检测与自然语言翻译方法 |
| CN113377349B (zh) * | 2021-06-21 | 2022-05-13 | 浙江工业大学 | 服务流程间差异检测与自然语言翻译方法 |
| CN113467755A (zh) * | 2021-07-12 | 2021-10-01 | 卡斯柯信号有限公司 | 需求符合性分析方法、系统、电子设备及存储介质 |
| CN113467755B (zh) * | 2021-07-12 | 2022-07-26 | 卡斯柯信号有限公司 | 需求符合性分析方法、系统、电子设备及存储介质 |
| CN113553443A (zh) * | 2021-07-18 | 2021-10-26 | 北京智慧星光信息技术有限公司 | 记录知识图谱游走路径的关系图谱生成方法和系统 |
| CN113553443B (zh) * | 2021-07-18 | 2023-08-22 | 北京智慧星光信息技术有限公司 | 记录知识图谱游走路径的关系图谱生成方法和系统 |
| CN113890899A (zh) * | 2021-09-13 | 2022-01-04 | 北京交通大学 | 一种基于知识图谱的协议转换方法 |
| CN113805847A (zh) * | 2021-09-15 | 2021-12-17 | 南通在渡教育咨询有限公司 | 在线无代码化开发系统 |
| CN114153943A (zh) * | 2021-11-22 | 2022-03-08 | 之江实验室 | 一种基于知识图谱构建机器人行为树的系统及方法 |
| CN114153943B (zh) * | 2021-11-22 | 2024-05-17 | 之江实验室 | 一种基于知识图谱构建机器人行为树的系统及方法 |
| CN114331062A (zh) * | 2021-12-16 | 2022-04-12 | 浙江工商大学 | 众包翻译任务切割方法及装置 |
| CN114331062B (zh) * | 2021-12-16 | 2024-11-26 | 浙江工商大学 | 众包翻译任务切割方法及装置 |
| CN114201618A (zh) * | 2022-02-17 | 2022-03-18 | 药渡经纬信息科技(北京)有限公司 | 药物研发文献可视化解读方法和系统 |
| WO2023159650A1 (en) * | 2022-02-28 | 2023-08-31 | Microsoft Technology Licensing, Llc | Mining and visualizing related topics in knowledge base |
| CN114896233A (zh) * | 2022-05-11 | 2022-08-12 | 武汉镝次元数据科技有限公司 | 一种数据产品制作管理与发布系统 |
| CN115293176A (zh) * | 2022-08-02 | 2022-11-04 | 南京莱科智能工程研究院有限公司 | 一种基于知识图谱的领域机器翻译模型评价方法 |
| CN115564934A (zh) * | 2022-09-30 | 2023-01-03 | 中铁第四勘察设计院集团有限公司 | 一种基于WebGIS的工程地质遥感解译系统和方法 |
| CN115757812A (zh) * | 2022-10-27 | 2023-03-07 | 高质标准化研究院(山东)有限公司 | 一种基于人工智能的政策匹配方法 |
| CN115577713A (zh) * | 2022-12-07 | 2023-01-06 | 中科雨辰科技有限公司 | 一种基于知识图谱的文本处理方法 |
| US12591688B2 (en) | 2023-06-27 | 2026-03-31 | International Business Machines Corporation | Context-aware cryptographic inventory |
| CN117436420A (zh) * | 2023-12-18 | 2024-01-23 | 武汉大数据产业发展有限公司 | 一种基于自然语言处理生成业务流程模型的方法和装置 |
Also Published As
| Publication number | Publication date |
|---|---|
| JP7064262B2 (ja) | 2022-05-10 |
| JP2022510031A (ja) | 2022-01-25 |
| CN110347798B (zh) | 2021-06-01 |
| CN110347798A (zh) | 2019-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7064262B2 (ja) | 自然言語生成技術に基づく知識グラフ理解支援システム | |
| CN111753099B (zh) | 一种基于知识图谱增强档案实体关联度的方法及系统 | |
| CN114218472B (zh) | 基于知识图谱的智能搜索系统 | |
| US11080295B2 (en) | Collecting, organizing, and searching knowledge about a dataset | |
| Wen et al. | Systematic knowledge modeling and extraction methods for manufacturing process planning based on knowledge graph | |
| CN103544242B (zh) | 面向微博的情感实体搜索系统 | |
| CN115455935A (zh) | 一种文本信息智能处理系统 | |
| CN116991869A (zh) | 一种基于nlp语言模型自动生成数据库查询语句的方法 | |
| CN104991905B (zh) | 一种基于层次索引的数学表达式检索方法 | |
| CN104572970B (zh) | 一种基于本体库内容的sparql查询语句生成系统 | |
| CN116244344A (zh) | 基于用户需求的检索方法、装置以及电子设备 | |
| CN105701253A (zh) | 中文自然语言问句语义化的知识库自动问答方法 | |
| CN106776711A (zh) | 一种基于深度学习的中文医学知识图谱构建方法 | |
| CN107766483A (zh) | 一种基于知识图谱的交互式问答方法及系统 | |
| CN105608232B (zh) | 一种基于图形数据库的bug知识建模方法 | |
| CN111553160B (zh) | 一种获取法律领域问句答案的方法和系统 | |
| CN114840657A (zh) | 一种基于混合模式的api知识图谱自适应构建及智能问答方法 | |
| Lin et al. | OWL Ontology Extraction from Relational Databases via Database Reverse Engineering. | |
| CN110555205A (zh) | 否定语义识别方法及装置、电子设备、存储介质 | |
| CN118779439A (zh) | 基于检索增强的问答方法、装置、设备及存储介质 | |
| Cocco et al. | Machine learning of SPARQL templates for question answering over LinkedSpending | |
| CN116204618B (zh) | 一种智能问答生成方法、装置、电子设备及存储介质 | |
| Prudhomme et al. | Automatic integration of spatial data into the semantic web | |
| Song et al. | Semantic query graph based SPARQL generation from natural language questions | |
| CN110795453A (zh) | 一种基于关系数据库自动构建rdf的方法 |
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: 20810763 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2021532885 Country of ref document: JP Kind code of ref document: A |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 20810763 Country of ref document: EP Kind code of ref document: A1 |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 20810763 Country of ref document: EP Kind code of ref document: A1 |