CN114036316A - Intelligent laboratory management system based on knowledge graph visualization - Google Patents

Intelligent laboratory management system based on knowledge graph visualization Download PDF

Info

Publication number
CN114036316A
CN114036316A CN202111367739.2A CN202111367739A CN114036316A CN 114036316 A CN114036316 A CN 114036316A CN 202111367739 A CN202111367739 A CN 202111367739A CN 114036316 A CN114036316 A CN 114036316A
Authority
CN
China
Prior art keywords
knowledge
data
experimental
layer
graph
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.)
Withdrawn
Application number
CN202111367739.2A
Other languages
Chinese (zh)
Inventor
赵存婕
贺敦伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zezheng Shanghai Biotechnology Co ltd
Original Assignee
Zezheng Shanghai Biotechnology Co ltd
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 Zezheng Shanghai Biotechnology Co ltd filed Critical Zezheng Shanghai Biotechnology Co ltd
Priority to CN202111367739.2A priority Critical patent/CN114036316A/en
Publication of CN114036316A publication Critical patent/CN114036316A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • 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
    • 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
    • G06F16/34—Browsing; Visualisation therefor
    • 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
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G06F40/295—Named entity recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models

Landscapes

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

Abstract

The invention discloses an intelligent laboratory management system based on knowledge graph visualization, relates to the field of knowledge graphs and laboratory information management systems, and solves the problem that the existing laboratory management system cannot inquire a matched experimental method and high-correlation national standards for experiment visualization and can carry out comprehensive evaluation by combining with experimental data. The intelligent laboratory management system based on knowledge graph visualization comprises an original data layer, a data acquisition layer, a data storage layer and a data processing layer, wherein the original data layer is used for collecting and preprocessing experimental data in the field of drug inspection and detection, a matched experimental method and corresponding national standards; the knowledge extraction layer is used for extracting correlation relations from multi-dimensional data sources related to experiments and constructing and forming a standardized knowledge graph; the knowledge integration layer is used for fusing, reasoning and physically storing the extracted knowledge and managing the knowledge by using the ontology; and the knowledge application layer is used for recommending a matching method meeting the experimental requirements and corresponding national standards and generating comprehensive evaluation according to the experimental data.

Description

Intelligent laboratory management system based on knowledge graph visualization
Technical Field
The invention relates to an intelligent laboratory management system based on knowledge graph visualization.
Background
With the rapid development of the medical field, the research and development of new drugs are increasing, a series of related experiments are required to be performed, so that the reliability of the new drugs is ensured, and with the increase of various experiments, related national standards are increasing, and the existing laboratory management system has the problem that the matching experiment method and the highly-related national standards cannot be visually inquired for the experiments and the comprehensive evaluation can be performed by combining with the experiment data.
The knowledge graph is a mode for storing and organizing knowledge, people can understand the internal topological structure in the knowledge graph through a visual means, and the knowledge graph is applied to a medical laboratory management system, so that experimenters can know the experimental method and the national standard related to experiments through the visual means, and the knowledge graph becomes an epoch proposition that every laboratory cannot be avoided.
Disclosure of Invention
In order to solve the technical problems, the invention is realized by the following technical scheme:
intelligent laboratory management system based on knowledge-graph visualization includes: the system comprises an original data layer, a knowledge extraction layer, a knowledge integration layer and a knowledge application layer.
Furthermore, the original data layer is used for collecting and preprocessing experimental data in the field of drug inspection and detection, matched experimental methods and corresponding national standards; the raw data layer comprises data collection, data preprocessing, data integration and data conversion.
Further, the data collection module comprises experimental detection data, experimental methods, experimental results, experimental evaluations and national standards.
Further, the experimental methods include experimental methods actually used in a laboratory and other available methods different from the actual laboratory use.
Further, the experimental results include experimental results actually obtained by a laboratory and results obtained by previous experiments of the same type.
Further, the evaluation of the experiment comprises the evaluation of the experiment by laboratory experimenters.
Further, the national standard includes the national drug standard, which is the technical requirements of the quality index, the inspection method, the production process and the like established by the nation for ensuring the drug quality.
Further, the data preprocessing module standardizes experimental detection data to obtain data with a format consistent with that of national standard detection index data.
Further, the data integration module comprises a database which is newly built by using database software, an experiment data table is built for each experiment, and relevant information of collected data is imported into the built data table.
Further, each experiment has a unique experiment ID.
Further, the experiment data table includes all preprocessed experiment detection data, experiment methods, experiment results, experiment evaluations and national standard information of the corresponding experiments.
Further, the database software is a damming database.
Further, the data conversion module establishes a data node and network relationship for displaying the experimental data and the corresponding experimental detection data, experimental method, experimental result, experimental evaluation and national standard in the graph database, and imports the graph database.
Further, the graphic database is Neo4j graphic database.
Further, the knowledge extraction layer is used for extracting correlation relations from the experiment-related multidimensional data source and constructing and forming a standardized knowledge graph.
Further, the knowledge extraction layer mainly comprises two aspects: establishing a knowledge graph and inquiring the knowledge graph.
And further, the knowledge graph is constructed, namely data acquired by the original data layer are extracted into a triple form, and the knowledge graph is formed and stored according to the entities and the relation of the entities.
Further, the data triple form is a form of "entity 1-relationship-entity 2" obtained by classifying and matching relationships between named entities with a relationship classifier.
Further, the knowledge graph query is to perform keyword query on the constructed knowledge graph, and return to obtain the required nodes and relations.
Further, the knowledge integration layer is used for fusing, reasoning and physically storing the knowledge extracted from the multidimensional data source of the experimental process, and managing the knowledge through the ontology base; the knowledge integration layer comprises a knowledge fusion model, an ontology reasoning model and a storage model.
Further, the extracted knowledge from the multidimensional data source of the experimental process includes triple information consisting of < entities, relationships, attributes > extracted from the experimental name, experimental equipment, experimental method, national standard, experimental result, and experimental data.
Furthermore, the management of the ontology base can provide attribute constraint and incidence relation for the construction of the knowledge graph, and ensure that a laboratory can modify the corresponding ontology model according to the experimental flow of the laboratory.
Further, the knowledge fusion is to construct specific entity elements by entity matching for the triple information extracted in the knowledge extraction stage.
Further, the entity matching is used for ensuring that a perfect entity attribute incidence relation is established between the entities in the multidimensional data source in the construction of the knowledge graph, so that the consistency of the ontology concept is ensured by the method; and matching the object, namely the experiment, with the entity in the knowledge, so as to ensure that the entities extracted from the multidimensional data source can all point to the same medicine inspection and detection experiment, thereby improving the consistency of the pointing to the body.
Further, the ontology reasoning obtains new entity relationships by using known reasoning.
Furthermore, the storage model can greatly reduce the space complexity of calculation and realize the quick response of the knowledge graph by the attribute graph database when querying the adjacent vertex, the adjacent edge and the attribute of the vertex.
Further, the knowledge application layer is used for recommending a matching method meeting the experiment requirements and corresponding national standards and generating comprehensive evaluation according to the experiment data.
Further, the knowledge application layer comprises an automatic recommendation scheme module, a retrieval module and a decision module.
Further, the retrieval module retrieves a knowledge graph subgraph matched with the knowledge graph, a candidate entity list is formed by calculating entity nodes which are the same as or similar to entities in the knowledge graph in the knowledge base, the entity with the minimum number of candidate entities in the candidate entity list is selected as a starting point, a relation predicate connected with the starting point entity is introduced, the subgraph matched with the entity in the knowledge base is retrieved, then the entity and the relation predicate are introduced to continue retrieval, and the steps are repeated continuously until all the entities and the relation predicate are introduced, so that the knowledge subgraph graph finally matched with the knowledge graph is obtained.
Further, the decision module includes decision making and optimization.
Further, the automatic recommendation scheme module establishes a corresponding relationship between the result corresponding to the result and the recommendation scheme, and automatically executes corresponding scheme recommendation aiming at the automatic cause analysis result by using the corresponding relationship.
Compared with the prior art, the intelligent laboratory management system based on knowledge graph visualization provided by the invention has the following beneficial effects:
1. the intelligent laboratory management system based on knowledge graph visualization has the advantages that data information is targeted and comprehensive, data sources are reliable, and data conversion is convenient and rapid;
2. the knowledge application layer can automatically recommend a matching method meeting the experiment requirement and corresponding national standards, and applies the knowledge map to a medical laboratory management system, so that experimenters can know the experiment method and the national standards related to the experiment by a visual means.
Drawings
FIG. 1 is a system hierarchy framework diagram of the present invention.
FIG. 2 is a schematic diagram of a data processing flow of the raw data layer according to the present invention.
FIG. 3 is a flow chart diagram of the method for constructing a knowledge graph according to the present invention.
FIG. 4 is a flow chart of an embodiment of the knowledge integration layer of the present invention.
FIG. 5 is a flow chart of an embodiment of the knowledge application layer of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention.
The invention provides an intelligent laboratory management system based on knowledge graph visualization, which comprises: the system comprises an original data layer, a knowledge extraction layer, a knowledge integration layer and a knowledge application layer.
Specifically, referring to fig. 1, the intelligent laboratory management system based on knowledge-graph visualization has five levels, including: the system comprises an original data layer, a knowledge extraction layer, a knowledge integration layer and a knowledge application layer.
The original data layer is used for collecting and preprocessing experimental data in the field of drug inspection and detection, a matched experimental method and corresponding national standards; the raw data layer comprises data collection, data preprocessing, data integration and data conversion.
Specifically, referring to fig. 2, the data processing of the original data layer of the present invention includes the following processes.
Step 1: data collection: collecting relevant information of experimental detection data, experimental methods, experimental results, experimental evaluations and national standards, wherein the experimental detection data, the experimental methods, the experimental results and the experimental evaluations are from laboratory experimental records, and the national standards data are from pharmacopoeia of the people's republic of China, drug registration standards and other drug standards issued by the State food and drug administration.
Step 2: data preprocessing: and consulting the national standard data index, and converting the data unit into the data unit consistent with the national standard data index.
And step 3: data integration: a server is prepared in advance, and a dream database is installed on the server. After the installation is finished, a database is newly established, then a database table is established according to collected experiment data, each experiment corresponds to one data table, each experiment has a unique experiment ID, and each experiment data table comprises experiment detection data, experiment methods, experiment results, experiment evaluations and corresponding national standards of the corresponding experiment. After the data table is built, the collected data information is imported into the built data table in an Excel form through a data migration tool carried by the Daemon database.
And 4, step 4: data conversion: the Neo4j graphic database was installed on a server prepared in advance. Then writing a Java program, extracting experimental data from the Dameng database through the program, and storing the extracted data into a Neo4j graphic database through a Cypher statement of the Neo4j graphic database.
And the knowledge extraction layer is used for extracting the correlation from the experiment-related multidimensional data source and constructing and forming a standardized knowledge graph.
Specifically, referring to fig. 3, the knowledge graph construction according to the embodiment of the present invention mainly includes the following steps.
Step 1: extraction rules for laboratory drug related information are defined.
Step 1.1: defining the type and content of the triples: classifying according to the characteristics of the key information, and defining the content of the triple into a form of 'entity 1-relation-entity 2';
step 1.2: and generating the regular expression according to the defined triple.
Step 2: extracting the triples: and extracting key information in the data based on the regular expression generated in the step 1.
And step 3: and drawing the acquired triple data into a map, wherein the entity is drawn into nodes, different layout algorithms are applied according to different scenes, and after the nodes are reasonably arranged, the connection lines with arrows are used for representing the mutual relation among the nodes.
And 4, step 4: when the knowledge graph is drawn, key nodes and key relationships are obtained according to weighting coefficients of relationships among all nodes in different scenes and are displayed through different colors, shapes and sizes.
The knowledge integration layer is used for fusing, matching, reasoning and physically storing the knowledge extracted from the multidimensional data source of the experimental process and managing the knowledge through the ontology base; the knowledge integration layer comprises a knowledge fusion model, an entity matching model, an ontology reasoning model and a storage model.
Specifically, referring to fig. 4, the knowledge integration layer includes the following processes:
after the extraction of the knowledge extraction layer is completed, a series of isolated nodes are formed, phenomena such as overlapping of knowledge and unclear association relation exist among the nodes, and the knowledge fusion step can enable the knowledge from the multidimensional data source to establish clear entity elements through an entity matching step.
The key to entity matching is to define a similarity measure experimentally. According to the characteristics of the drug inspection and detection experiment process, the cohesion index of the experiment is reflected emphatically. Therefore, a cohesive association measurement based on semantic similarity is constructed, so that the association relation among different entities and the consistency of entity orientation are realized, and a complete knowledge graph network is formed.
The cohesion association measurement is associated through an experimental process, the similarity degree is judged through the process sharing and overlapping degree between the entities, and the more processes are shared, the higher the similarity degree is. The flow in the experiment is represented as: experiment name, experimental apparatus, experimental method, national standard, experimental result, experimental data and other attribute information.
The cohesive similarity correlation can be expressed as:
Figure BDA0003361262030000051
wherein D1 and D2 are feature vectors, and D1 is (x)1,x2，...，xn),D2＝(y1,y2，...，yn)，match(xi，yi) Representing a matching calculation function, wiRepresenting weights representing the importance of different data characteristics.
And defining a similarity measurement method of a medicine inspection and detection experiment according to a cohesive correlation measurement method, calculating entity element similarity aiming at entity matching to construct a correlation relationship, extracting a knowledge extraction layer to obtain knowledge consisting of (entities, relationships and attributes) in a multi-dimensional data source, and constructing a clear laboratory knowledge map through knowledge fusion.
Ontology reasoning means that characteristic reasoning needs to be carried out on an ontology, and a new entity relationship is obtained by using the reasoning of the prior knowledge.
Specifically, upper and lower entity vectors are calculated according to upper and lower entity characteristics of an entity; and extracting semantic vector characteristic values through a convolutional neural network.
And (4) obtaining a final vector by the entity vector, the upper entity vector and the lower entity vector corresponding to each experimental process through a convolution pooling layer.
And constructing a network model required by the model through the convolutional neural network model and used for experimental methods and national standard recommendation.
The storage model directly determines the physical storage structure of the knowledge-graph. In a knowledge graph network for drug inspection and detection, an attribute graph database Neo4j is adopted, and the database uses a local indexing technology instead of the traditional global indexing to realize the organization of graph structure data, so that when adjacent entities, relations and attributes of the entities are inquired, the space complexity of calculation can be greatly reduced, and the quick response of the knowledge graph is realized. The Neo4j attribute graph database stores vertices, edges, and their attributes in different files, respectively.
Each entity maintains pointers to the first relationship and the first attribute connected thereto, and each relationship maintains pointers to the starting entity, the terminating entity, the front and back edges of the two end entities, and the first attribute. The attributes are managed by a single linked list and the relationships are managed by two double linked lists, which is beneficial to the operations of inserting and deleting the flows and relationships in the experiment.
And the knowledge application layer is used for recommending a matching method meeting the experimental requirements and corresponding national standards and generating comprehensive evaluation according to the experimental data.
Specifically, fig. 5 is a schematic flow chart of an embodiment of the knowledge application layer according to the present invention. Specifically, the following steps may be included.
Step 1: retrieving the knowledge graph subgraphs matched with the knowledge graph, calculating entity nodes which are the same as or similar to the entities in the knowledge graph in the knowledge base to form a candidate entity list, selecting the entity with the least number of candidate entities in the candidate entity list as a starting point, introducing a relation predicate connected with the starting point entity, retrieving the subgraphs matched with the entity in the knowledge base, introducing the entity and the relation predicate, continuing retrieval, and iterating until all the entities and the relation predicate are completely quoted to obtain the final matched knowledge graph subgraphs.
Step 2: and (5) layout decision and optimization.
Step 2.2: if the basic attribute of the knowledge graph structure is represented as a simple tree or a basic ring tree, adopting an ecological tree-like layout mode and carrying out radial processing on the ecological tree;
step 2.3: if the basic attribute of the knowledge graph structure presents a directed acyclic graph, directly adopting a radiation graph layout;
step 2.4: and if the basic attribute of the knowledge graph structure is presented as a complex graph with self-loop or a complex graph with double edges, adopting a force guide graph layout.
And step 3: and establishing a corresponding relation between the result corresponding to the result and the recommended scheme, and automatically executing corresponding scheme recommendation aiming at the automatic cause analysis result by using the corresponding relation.
In summary, the invention relates to an intelligent laboratory management system based on knowledge graph visualization, which applies a knowledge graph to a medical laboratory management system by using a knowledge graph visualization technology, so that laboratory personnel can understand experiment methods and national standards related to an experiment through a visualization means, and the problem that the existing laboratory management system cannot inquire a matched experiment method and a highly-associated national standard for the experiment visualization and perform comprehensive evaluation by combining with experiment data is solved.

Claims (8)

1. Intelligent laboratory management system based on knowledge-graph visualization, its characterized in that includes: the original data layer is used for collecting and preprocessing experimental data in the field of drug inspection and detection, a matched experimental method and corresponding national standards; the knowledge extraction layer is used for extracting correlation relations from multi-dimensional data sources related to experiments and constructing and forming a standardized knowledge graph; the knowledge integration layer is used for fusing, reasoning and physically storing the extracted knowledge and managing the knowledge by using the ontology; and the knowledge application layer is used for recommending a matching method meeting the experimental requirements and corresponding national standards and generating comprehensive evaluation according to the experimental data.
2. The intelligent laboratory management system based on knowledge-graph visualization of claim 1, wherein said raw data layer, using database software to create a new database, creating an experiment data table for each experiment, and importing the related information of the collected data into the created data table, wherein each experiment has a unique experiment ID.
3. The intelligent laboratory management system based on knowledge-graph visualization of claim 1, wherein the raw data layer establishes a data node and network relationship for displaying the experimental data and the corresponding experimental detection data, experimental method, experimental result, experimental evaluation and national standard in a graph database, and imports the graph database.
4. The intelligent laboratory management system based on knowledge-graph visualization of claim 1, wherein the knowledge extraction layer employs a knowledge-graph construction method, forms triple content in the form of "entity 1-relationship-entity 2" according to the characteristics and classification of the data summary key information, and generates a regular expression describing the triples.
5. The knowledge graph construction method according to claim 4, wherein the regular expression of the triplet mainly comprises the following modes: mode 1: the name of the medicine, the production time and the corresponding production time; mode 2: a drug name, an expiration time, corresponding to the expiration time; mode 3: medicine field vocabulary, definition, corresponding definition content; mode 4: drug field experiments, including, corresponding experiments contain content.
6. The knowledge-graph construction method according to claim 4, wherein in the knowledge-graph formed according to the extracted triplet information, the entities are represented by nodes, and the interrelations between the entities are represented by connecting lines with arrows.
7. The intelligent laboratory management system based on knowledge-graph visualization of claim 1, wherein said knowledge integration layer comprises cohesive similarity correlation for drug testing entity matching, network models for experimental methods and national standard recommendations.
8. The intelligent laboratory management system based on knowledge-graph visualization of claim 1, wherein said knowledge application layer comprises an automatic recommendation module, a retrieval module and a decision module.
CN202111367739.2A 2021-11-18 2021-11-18 Intelligent laboratory management system based on knowledge graph visualization Withdrawn CN114036316A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111367739.2A CN114036316A (en) 2021-11-18 2021-11-18 Intelligent laboratory management system based on knowledge graph visualization

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111367739.2A CN114036316A (en) 2021-11-18 2021-11-18 Intelligent laboratory management system based on knowledge graph visualization

Publications (1)

Publication Number Publication Date
CN114036316A true CN114036316A (en) 2022-02-11

Family

ID=80138085

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111367739.2A Withdrawn CN114036316A (en) 2021-11-18 2021-11-18 Intelligent laboratory management system based on knowledge graph visualization

Country Status (1)

Country Link
CN (1) CN114036316A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118118279A (en) * 2024-04-29 2024-05-31 南京亿顺弘信息技术有限公司 Laboratory information management method and system based on homomorphic encryption and Internet of things technology

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118118279A (en) * 2024-04-29 2024-05-31 南京亿顺弘信息技术有限公司 Laboratory information management method and system based on homomorphic encryption and Internet of things technology

Similar Documents

Publication Publication Date Title
CN109710701B (en) Automatic construction method for big data knowledge graph in public safety field
US6665677B1 (en) System and method for transforming a relational database to a hierarchical database
CN110866123B (en) Method for constructing data map based on data model and system for constructing data map
CN110781236A (en) Method for constructing government affair big data management system
KR101835345B1 (en) Concept graph expansion system based on knowledge base
Hor et al. A semantic graph database for BIM-GIS integrated information model for an intelligent urban mobility web application
CN112463980A (en) Intelligent plan recommendation method based on knowledge graph
CN110134724A (en) A kind of the data intelligence extraction and display system and method for Building Information Model
JP2005530250A (en) Data storage, retrieval, operation, and display tools that realize a multi-level perspective
Lbath et al. Schema inference for property graphs
CN111858649A (en) Heterogeneous data fusion method based on ontology mapping
CN115640406A (en) Multi-source heterogeneous big data analysis processing and knowledge graph construction method
CN114004581A (en) Intention interaction system based on multi-dimensional government affair knowledge base
Sheng et al. CEPV: A tree structure information extraction and visualization tool for big knowledge graph
CN115438199A (en) Knowledge platform system based on smart city scene data middling platform technology
Lemaire et al. Analyzing BIM topics and clusters through ten years of scientific publications
JP6375029B2 (en) A metadata-based online analytical processing system that analyzes the importance of reports
JP5639417B2 (en) Information processing apparatus, information processing method, and program
Langenhan et al. The fingerprint of architecture-sketch-based design methods for researching building layouts through the semantic fingerprinting of floor plans
CN114036316A (en) Intelligent laboratory management system based on knowledge graph visualization
Roith et al. Supporting the building design process with graph-based methods using centrally coordinated federated databases
CN115905554A (en) Chinese academic knowledge graph construction method based on multidisciplinary classification
Jiang et al. PG-explorer: Resource Description Framework data exploration with property graphs
Shi et al. An approach to semi-automatic semantic annotation on Web3D scenes based on an ontology framework
Gallego et al. Rdf visualization using a three-dimensional adjacency matrix

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20220211