CN112732939B - Spatiotemporal knowledge graph construction method, device, medium and equipment based on GraphDB - Google Patents
Spatiotemporal knowledge graph construction method, device, medium and equipment based on GraphDB Download PDFInfo
- Publication number
- CN112732939B CN112732939B CN202110055126.9A CN202110055126A CN112732939B CN 112732939 B CN112732939 B CN 112732939B CN 202110055126 A CN202110055126 A CN 202110055126A CN 112732939 B CN112732939 B CN 112732939B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- data
- swrl
- individual
- space
- 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.)
- Active
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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- 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)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Remote Sensing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present document relates to methods, apparatus, media and devices for spatiotemporal knowledge graph construction based on GraphDB. The method comprises the following steps: building a framework of a geographic entity by fusing the OGC standard; extracting data related to the geographic entity in the spatio-temporal data to generate an individual knowledge set of the target object; and storing the individual knowledge set into a GraphDB database to form a time-space knowledge map. The method realizes the organization and fusion of the accurate ground object information contained in the multi-temporal and large-scale remote sensing image, comprehensively and delicately describes the temporal-spatial information, and introduces an inference rule to solve the problem of the deficiency of OWL in inference capability, so that the knowledge graph has stronger inference capability.
Description
Technical Field
The present disclosure relates to graph databases, and more particularly, to a method, an apparatus, a medium, and a device for constructing a spatiotemporal knowledge graph based on GraphDB.
Background
In the traditional technology, the feature information in the remote sensing image is expressed through a graph database, so that the feature information can be greatly enriched, but the graph database cannot be used for well reasoning, the time and space information cannot be accurately expressed, the multi-source information cannot be coordinated, and the information perception has a serious island phenomenon.
Disclosure of Invention
In order to overcome the problems in the related art, the invention provides a method, a device, a medium and equipment for constructing a spatiotemporal knowledge graph based on GraphDB.
According to one aspect of the present disclosure, there is provided a method for constructing a graph db-based spatio-temporal knowledge graph, including:
building an architecture of a geographic entity by fusing OGC standards, wherein the geographic entity comprises a plurality of target objects;
extracting data related to geographic entities in the spatio-temporal data to generate an individual knowledge set of the target object, wherein the individual knowledge set comprises more than one individual knowledge, and the individual knowledge is represented by using RDF triple combined with OWL (ontology of Web language) extension language;
storing the individual knowledge sets into a GraphDB database to form a time-space knowledge map;
receiving a query instruction, traversing the spatiotemporal knowledge graph, and determining corresponding spatiotemporal knowledge; when no space-time knowledge corresponding to the query instruction exists, performing OWL ontology reasoning according to the framework; or calling related SWRL rules and an individual knowledge set to carry out reasoning, and determining the new individual knowledge generated by reasoning as corresponding space-time knowledge.
The architecture for constructing the geographic entity comprises:
constructing a class of the geographic entity based on the target object, and adding a constraint relation of the class;
constructing attributes of a class, wherein the attributes of the class comprise data attributes and object attributes, and adding constraints of the object attributes;
the data attributes are used for representing the relationship between the object and the data and comprise label attributes, spatial positions and element attributes; the object attribute is used for representing the relation between the object and the object, including time series, space relation and point-plane record.
Extracting data related to geographic entities from the spatio-temporal data to generate an individual knowledge set of the target object;
and extracting corresponding data from the space-time data according to the attribute of the class of the target object to generate a plurality of pieces of individual knowledge, wherein the individual knowledge forms an individual knowledge set of the target object.
The spatiotemporal data includes: one or more of plain text data, remote sensing images, video or image data, terrain data sets, web page data, map data, POI data, sensor data, terrain distribution data, and artificial tagging factors.
The method for constructing the spatio-temporal knowledge graph based on the GraphDB further comprises the following steps: and establishing an SWRL rule base, wherein the SWRL rule base comprises a plurality of SWRL rules, and the SWRL rules are calculated according to expert knowledge.
The method for constructing the spatio-temporal knowledge graph based on the GraphDB further comprises the following steps: and supplementing the new individual knowledge into the spatiotemporal knowledge map.
According to one aspect herein, there is provided a graph db-based spatiotemporal knowledge graph construction apparatus, comprising:
the body construction module is used for fusing OGC standards to construct a framework of a geographic entity, and the geographic entity comprises a plurality of target objects;
the data extraction module is used for extracting data related to geographic entities in the spatiotemporal data to generate an individual knowledge set of the target object, wherein the individual knowledge set comprises more than one individual knowledge, and the individual knowledge is expressed by using RDF triple combined with OWL (ontology of Web language) extension language;
the storage module is used for storing the individual knowledge sets into a GraphDB database to form a time-space knowledge map;
the query module is used for receiving a query instruction, traversing the spatiotemporal knowledge graph and determining corresponding spatiotemporal knowledge;
the reasoning module is used for carrying out OWL ontology reasoning according to the framework if no spatiotemporal knowledge corresponding to the query instruction exists; or calling related SWRL rules and an individual knowledge set to carry out inference, and determining new individual knowledge generated by inference as corresponding space-time knowledge.
The time-space knowledge map construction device based on the GraphDB further comprises: and the space-time knowledge complementing module is used for complementing the new individual knowledge into the space-time knowledge map.
According to one aspect herein, there is provided a computer readable storage medium having stored thereon a computer program which, when executed, performs the steps of a method of constructing a spatiotemporal knowledge map.
According to one aspect herein, there is provided a computer apparatus comprising a processor, a memory and a computer program stored on the memory, the processor, when executing the computer program, implementing the steps of the method of constructing a spatiotemporal knowledge map.
The method for constructing the spatiotemporal knowledge graph based on the GraphDB organizes and fuses precise ground object information contained in a multi-temporal and large-range remote sensing image, comprehensively and delicately describes the spatiotemporal information, introduces inference rules to solve the deficiency of OWL in inference capacity, enables the knowledge graph to have stronger inference capacity, simultaneously designs a spatiotemporal knowledge high-performance query engine facing a large-scale spatiotemporal semantic network, and improves the search performance through indexing. The multi-source information is integrated and utilized, the cooperative work is realized, the problem of serious island phenomenon of an information perception channel is solved, and the advanced storage management of semantic association is realized.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the disclosure, and are incorporated in and constitute a part of this specification. In the drawings:
FIG. 1 is a flow diagram illustrating a method for construction of a GraphDB-based spatiotemporal knowledge graph, according to an exemplary embodiment.
FIG. 2 is a diagram illustrating a geographic entity architecture in accordance with an exemplary embodiment.
FIG. 3 is a block diagram illustrating a GraphDB-based spatiotemporal knowledge graph building apparatus according to an exemplary embodiment.
FIG. 4 is a block diagram illustrating a GraphDB-based spatiotemporal knowledge graph building apparatus according to an exemplary embodiment.
FIG. 5 is a block diagram illustrating a computer device for GraphDB-based spatio-temporal knowledge-graph building, according to an example embodiment
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings of the embodiments of the present invention, and it is obvious that the described embodiments are some but not all of the embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments herein without making any creative effort, shall fall within the scope of protection. It should be noted that the embodiments and features of the embodiments may be arbitrarily combined with each other without conflict.
In the traditional technology, people can only determine the geographic spatial distribution and the environmental condition of a target entity through a remote sensing image, but cannot acquire more detailed information. By establishing a graph database, people can supplement various geographic attribute information of a target entity in detail, but the information cannot be queried in a spatio-temporal sense, and knowledge information except the graph database cannot be inferred. For example, with a graph database, we cannot make a query as to which roads have water sources that have never historically been dried within 500 meters and can pass through a fire engine.
Provided herein is a method for constructing a graph db-based spatiotemporal knowledge graph, fig. 1 is a flowchart illustrating a method for constructing a graph db-based spatiotemporal knowledge graph according to an exemplary embodiment, and referring to fig. 1, the method for constructing a graph db-based spatiotemporal knowledge graph includes:
and S11, building a framework of a geographic entity by fusing the OGC standard, wherein the geographic entity comprises a plurality of target objects.
And S12, extracting data related to the geographic entity in the spatio-temporal data, and generating an individual knowledge set of the target object, wherein the individual knowledge set comprises more than one individual knowledge, and the individual knowledge is expressed by combining RDF triples with an OWL extension language.
And S13, storing the individual knowledge set into a GraphDB database to form a space-time knowledge map.
S14, receiving a query instruction, traversing a spatiotemporal knowledge graph, and determining corresponding spatiotemporal knowledge; when no spatiotemporal knowledge corresponding to the query instruction exists, performing OWL ontology reasoning according to the framework; or calling related SWRL rules and an individual knowledge set to carry out inference, and determining new individual knowledge generated by inference as corresponding space-time knowledge.
In step S11, in order to complete the construction of the spatio-temporal knowledge graph, an OGC (Open Geospatial Consortium) standard is introduced herein, so that the spatial data operation and architecture establishment conform to international standards and specifications. And fusing the OGC standard to construct a framework of a geographic entity, and performing data operation on the basis of the framework.
In one embodiment, the architecture for building ontologies includes: constructing a class of the geographic entity based on the target object, and adding a constraint relation of the class;
and constructing attributes of the class, wherein the attributes of the class comprise data attributes and object attributes, and adding constraints of the object attributes.
According to the target object concerned by the project, a class of the geographic entity is first constructed based on the target object. For example, in the forest fire prevention field, the vegetation and the road condition are most concerned, and at the moment, geographic entities can be classified, such as vegetation, buildings, roads and the like, and subclasses are also clarified, for example, the subclasses of buildings are houses, temple and the like, and the subclasses of vegetation can be woods and grassland. After the class construction is completed, the class needs to be constrained, for example, who is a subclass of who, whether there is no intersection with other classes, and the like.
Fig. 2 is a diagram illustrating a graph db based geographic entity architecture according to an example embodiment. The present document first builds a class of geographic entities according to the OGC standard, based on the content provided by the OGC standard. In fig. 2, classes are represented by square boxes and attributes are represented by oval boxes. The shaded square frame portions are those provided by the OGC standard, and the unshaded square frame portions are those for the geographical entities in the forest fire protection field, which are made on the OGC standard by the present example. Referring to fig. 2, for example, geographic entities are divided into ground entities and aerial entities, and the sub-classes of ground entities are vegetation classes, building classes, road classes, and the like. Likewise, vegetation may also divide the coniferous and broadleaf Lin Liangge subclasses. It can be seen from the figure that there may be parent-child relationships between different classes, such as conifer forest is the subclass of vegetation, vegetation is the subclass of ground entities, and so on. Class constraint relationships are also added, for example, building classes and road classes have disjoint relationships, i.e., a feature cannot be both a road and a building. After the classes are established, different attributes of different classes of target objects need to be established according to the characteristics of the target objects, for example, the attributes of labels set for vegetation are combustible. For vegetation, the area and position of vegetation are of primary concern, and for roads, the width, slope, etc. of roads are of concern. In order to enrich the information of the target object, in the geographic entity architecture constructed by fusing the OGC standard, a time attribute may be set on the element class, for example, two attributes of prediction time and recording time are set in this embodiment, so that the geographic entity has information in a time sense. The geographic entity framework constructed by fusing the OGC standard can well represent the spatiotemporal information of the geographic entity.
In this embodiment, the attributes of the class include data attributes and object attributes, where the data attributes are used to represent the relationship between the object and the data, and include time tags, spatial positions, and element attributes (such as area, length, slope, etc.); the object attribute is used to represent the relationship between the object and the object, including time series (e.g. past, present), spatial relationship (e.g. object and object are adjacent), point-plane record, etc.
The class construction and attribute construction exemplified herein is to explain how to construct the architecture of the geographic entity, and in practical applications, the class and attribute construction needs to be decided according to the field and use to be faced, and is not limited herein.
In step S12, data related to the geographic entity in the spatio-temporal data is extracted, and the relevant data is acquired for different surface features according to the geographic entity architecture constructed in step S11, so that spatio-temporal knowledge of different surface features meeting the OGC standard can be established. For reasoning on subsequent spatiotemporal knowledge, the RDF triples are used herein in combination with the OWL extension language to represent individual knowledge of a target object, with more than one individual knowledge constituting an individual knowledge set. For example, obtaining area and coordinate data for target vegetation a may establish: the area of the vegetation A is 5 ten thousand square kilometers, and the vegetation A is located in a certain area.
In one embodiment, the corresponding data is extracted from the spatio-temporal data according to the attributes of the class of the target object to form the individual knowledge. For example, the target object is a road, the number a00001, and corresponding data is extracted according to the attribute (width, slope direction) of the road class, so that an individual knowledge set of the road can be obtained: the width of a00001 road is 5 meters; the slope of road a00001 is 45 degrees. Contains 2 individual knowledge items. Can be expressed as:
<http://CAS/AIR/20210111/ontology/road/a00001>
<http://CAS/AIR/20210111/ontology/hasWidth>5
the road a00001 is 5m wide.
<http://CAS/AIR/20210111/ontology/road/a00001>
<http://CAS/AIR/20210111/ontology/hasSlope>
45
Represents: the slope of the road a00001 is 45 degrees.
In one embodiment, the spatiotemporal data comprises: one or more of plain text data, remote sensing images, video or image data, terrain data sets, web page data, map data, POI data, sensor data, terrain distribution data, and artificial tagging factors. Spatio-temporal data may be acquired among the various data described above. The method comprises the following steps of obtaining plain text data, remote sensing images, videos or image data, wherein the plain text data, the remote sensing images, the videos or the image data are unstructured data; the Terrain data set, the webpage data, the map data, the POI data and the sensor data are semi-structured data; and the ground feature distribution data and the artificial marking factors are structured data.
Knowledge extraction oriented to plain text data needs to acquire relevant spatial information and historical event information from a free text, and in the process of extracting entities, space-time entity identification and relation extraction are needed to express semantic relations between two or more entities; the knowledge extraction facing the remote sensing image is to extract the spatial information of a target ground object from the remote sensing image, and add some extra attribute information (for example, mountain roads are extracted from the remote sensing image, width data are added through calculation), and the spatial information can be stored into a knowledge map after being expressed by regular geojson; the video/image mainly refers to monitoring purposes, image recognition operation is carried out when the image is taken, whether a concerned event occurs or not is detected, if yes, corresponding event semantics are correspondingly generated, and then extraction is finished aiming at a template for generating the event (for example, an event occurs at a certain time and a certain place). For semi-structured data, only a knowledge extractor is needed to be designed, the content under a specific label is extracted and mapped to the ontology of the target object. The structured data is generally the structurality of the existing data storage and exists in a relational database, and at the moment, some existing standards and tools can be used for supporting the conversion of the data in the database into an OWL ontology, so that the ontology mapping is directly completed without additionally designing an extractor.
In step S13, the individual knowledge sets are stored in the GraphDB database to form a spatiotemporal knowledge map. And storing the data obtained from the spatiotemporal data and the individual knowledge into a GraphDB database in a form of RDF triple combined with an OWL extension language representation to form a preliminary spatiotemporal knowledge map. A great deal of space-time knowledge and interrelation are stored in the space-time knowledge map.
In step S14, receiving a query instruction, traversing the spatiotemporal knowledge graph, and determining corresponding spatiotemporal knowledge; and when no spatiotemporal knowledge corresponding to the query instruction exists, performing OWL ontology inference according to the framework, or invoking a relevant SWRL rule and an individual knowledge set to perform inference, and determining new individual knowledge generated by inference as corresponding spatiotemporal knowledge.
When a query instruction is received, the query instruction can be traversed in a spatiotemporal knowledge graph to find relevant spatiotemporal knowledge, for example, the instruction is as follows: the width of road a00001 is queried. When traversing to the space-time knowledge map
<http://CAS/AIR/20210111/ontology/road/a00001>
And when the http:// CAS/AIR/20210111/ontology/hasWidth >5, determining the corresponding space-time knowledge as follows: the width of road a00001 is 5 meters.
If the received query instruction is: is coniferous forest flammable? Still taking fig. 2 as an example, the spatio-temporal knowledge map is traversed to find out spatio-temporal knowledge related to the conifer forest, and there is no information about whether the conifer forest is combustible or not, but because of using the owl language, the abundant semantic expression ability can express more information in the geographic entity, according to the constructed geographic entity architecture, it can be derived that the vegetation is combustible, and further reasoning is carried out, and according to the conifer forest as the vegetation, two new individual knowledge that the conifer forest is combustible and the broadleaf forest is combustible can be deduced.
However, OWL still has a deficiency in reasoning ability, and some knowledge cannot be obtained by ontology reasoning, for example, the query instruction is: how many degrees are the uphill direction of road a 00001? Traversing the time-space knowledge graph, the following can be found:
<http://CAS/AIR/20210111/ontology/road/a00001>
<http://CAS/AIR/20210111/ontology/hasSlope>
45
the individual knowledge is: the slope of road a00001 is 45 degrees. At this time, SWRL (semantic webrule language) rules can be introduced to further refine the inference mechanism of the knowledgebase. For example, inference rules can be designed: "when the slope is <180 °, the upward slope = the slope +180 °", the SWRL rule is added to the SWRL rule base, and by calling individual knowledge "the slope is 45 ° and the SWRL rule" when the slope is <180 °, the upward slope = the slope +180 ° ", space-time knowledge inference can be performed to obtain: the uphill direction of the road a00001 is 225 degrees. Then, the new individual knowledge "225 degrees uphill direction of road a 00001" is determined as the spatiotemporal knowledge corresponding to the query instruction.
In one embodiment, the method for constructing the graph db-based spatio-temporal knowledge graph further comprises: and establishing an SWRL rule base, wherein the SWRL rule base comprises a plurality of SWRL rules, and the SWRL rules are determined according to expert knowledge. And adding the designed inference rule into the SWRL rule base, and calling an SWRL rule base engine API to search a related SWRL rule when inquiring the space-time knowledge. Some SWRL rules can be designed in advance and added into the SWRL rule base, calling is facilitated during query, and the SWRL rules can be designed according to query contents during query, and then the designed SWRL rules are added into the SWRL rule base. Notably, the SWRL rule is not freely designed and needs to be determined based on expert knowledge. Therefore, the new individual knowledge is not generated by space, and is strictly calculated according to expert knowledge on the basis of the original individual knowledge.
In an embodiment, the method for constructing the graph db-based spatio-temporal knowledge graph further includes: and supplementing new individual knowledge into the space-time knowledge map. In the process of reasoning, new individual knowledge is generated, the new individual knowledge is supplemented into the space-time knowledge map, the original individual knowledge is supplemented, the space-time knowledge map is continuously improved, and when relevant contents are inquired later, the corresponding individual knowledge can be quickly provided. For example, how many degrees are the uphill direction for the query instruction "road No. a 00001? "after SWRL reasoning, the following new individual knowledge is obtained:
<http://CAS/AIR/20210111/ontology/road/a00001>
<http://CAS/AIR/20210111/ontology/hasUpSlope>225
represents: the uphill direction of the road a00001 is 225 degrees.
And supplementing the new individual knowledge into the space-time knowledge map to perfect the space-time knowledge map.
In one embodiment, the query statement is designed in the SPARQL language to query the spatiotemporal knowledge of the target object. The SPARQL language is a query language supported by the GraphDB database, and since the geographic entity is expanded on the OGC standard, a certain expansion of the SPARQL language is required to perform a spatial relationship query.
After a series of construction and completion from step S11 to step S14, a more complete and huge spatiotemporal knowledge map can be obtained, and the spatiotemporal knowledge map can be applied to a plurality of aspects of life. For example, the method can be applied to forest fire fighting, and if people need to know: "which road sections have water sources never dried up historically in 500 meters and can pass through the foam fire fighting truck", SPARQL sentences need to be designed to search: "which road sections have widths larger than the car width of the fire-fighting truck", and then which roads have water sources in the buffer area of 500 meters and exist all the time. Therefore, the target road section can be quickly and accurately found, and necessary information is provided for forest fire prevention.
The method for constructing the spatiotemporal knowledge graph organizes and fuses precise ground object information contained in multi-temporal phase and large-range remote sensing images, comprehensively and delicately delineates the spatiotemporal information, and introduces inference rules to solve the problem of the deficiency of OWL in inference capacity, so that the knowledge graph has stronger inference capacity, and simultaneously designs a spatiotemporal knowledge high-performance query engine facing a large-scale spatiotemporal semantic network, and improves the search performance through indexing. By the method, multi-source information can be integrated and utilized, the cooperative work is realized, the problem of serious information perception channel island phenomenon is solved, and high-level storage management of semantic association is realized.
FIG. 3 is a block diagram illustrating a construction apparatus of a GraphDB-based spatiotemporal knowledge-graph according to an exemplary embodiment. Referring to fig. 3, the apparatus for constructing a graph db-based spatio-temporal knowledge graph includes: the system comprises an ontology construction module 301, a data extraction module 302, a storage module 303, a query module 304 and an inference module 305.
The ontology building module 301 is configured to build an architecture of the geographic entity in fusion with the OGC standard.
The data extraction module 302 is configured to extract data related to a geographic entity from spatio-temporal data, and generate an individual knowledge set of the target object, where the individual knowledge set includes one or more individual knowledge, and the individual knowledge is expressed by using RDF triples in combination with OWL extension language.
The storage module 303 is configured to store the individual knowledge sets in a GraphDB database, forming a spatiotemporal knowledge graph.
The query module 304 is configured for receiving a query instruction, traversing the spatiotemporal knowledge-graph, and determining corresponding spatiotemporal knowledge.
The inference module 305 is configured to perform OWL ontology inference according to the architecture if there is no spatiotemporal knowledge corresponding to the query instruction; or calling related SWRL rules and an individual knowledge set to carry out reasoning, and determining the new individual knowledge generated by reasoning as corresponding space-time knowledge.
FIG. 4 is a block diagram illustrating a graph DB-based spatiotemporal knowledge-graph construction apparatus according to an exemplary embodiment. Referring to fig. 4, the graph db-based spatio-temporal knowledge graph constructing apparatus further includes: a spatiotemporal knowledge completion module 406.
The spatiotemporal knowledge completion module 406 is configured to supplement the spatiotemporal knowledge map with new individual knowledge.
FIG. 5 is a block diagram illustrating a computer device 500 for GraphDB-based spatio-temporal knowledge-graph building, according to an exemplary embodiment. For example, the computer device 500 may be provided as a server. Referring to fig. 5, the computer device 500 includes a processor 501, and the number of the processors may be set to one or more as necessary. The computer device 500 further comprises a memory 502 for storing instructions, such as an application program, executable by the processor 501. The number of the memories can be set to one or more according to needs. Which may store one or more application programs. The processor 501 is configured to execute instructions to execute the above-mentioned geographic knowledge database construction method
As will be appreciated by one skilled in the art, the embodiments herein may be provided as a method, apparatus (device), or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied in the medium. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, including, but not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by the computer, and the like. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as is well known to those skilled in the art.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices) and computer program products according to embodiments herein. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that an article or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such article or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of another identical element in an article or device that comprises the element.
While the preferred embodiments herein have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following appended claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of this disclosure.
It will be apparent to those skilled in the art that various changes and modifications may be made herein without departing from the spirit and scope thereof. Thus, it is intended that such changes and modifications be included herein, provided they come within the scope of the appended claims and their equivalents.
Claims (5)
1. A spatiotemporal knowledge graph construction method based on GraphDB is characterized by comprising the following steps:
building an architecture of a geographic entity by fusing OGC standards, wherein the geographic entity comprises a plurality of target objects;
the architecture for constructing the geographic entity comprises:
constructing a class of the geographic entity based on the target object, and adding a constraint relation of the class;
constructing attributes of a class, wherein the attributes of the class comprise data attributes and object attributes, and adding constraints of the object attributes;
the data attributes are used for representing the relationship between the object and the data and comprise label attributes, spatial positions and element attributes; the object attribute is used for representing the relation between the object and the object, including time sequence, space relation and point-plane record;
extracting data related to geographic entities in the spatio-temporal data to generate an individual knowledge set of the target object, wherein the individual knowledge set comprises more than one individual knowledge, and the individual knowledge is expressed by combining RDF triples with an OWL (ontology Web language) extension language; the method specifically comprises the following steps: knowledge extraction oriented to plain text data needs to acquire relevant spatial information and historical event information from a free text, and in the process of extracting entities, space-time entity identification and relation extraction are needed to express semantic relations between two or more entities; extracting knowledge oriented to the remote sensing image, namely extracting spatial information of a target ground object from the remote sensing image, and adding some extra attribute information, including extracting mountain roads from the remote sensing image, calculating and adding width data, expressing the width data by using a regularized geojson, and storing the data into a knowledge graph; the video/image mainly refers to monitoring purposes, image recognition operation is carried out when the image is taken, whether a concerned event occurs or not is detected, if yes, corresponding event semantics are correspondingly generated, and then extraction is completed aiming at a template for generating the event; for semi-structured data, only a knowledge extractor is needed to be designed, the content under a specific label is extracted and mapped to the body of a target object;
the spatiotemporal data includes: one or more of plain text data, remote sensing images, video or image data, terrain data sets, webpage data, map data, POI data, sensor data, surface feature distribution data and artificial marking factors; the method comprises the following steps of obtaining plain text data, remote sensing images, videos or image data, wherein the plain text data, the remote sensing images, the videos or the image data are unstructured data; the Terrain data set, the webpage data, the map data, the POI data and the sensor data are semi-structured data; the ground feature distribution data and the artificial marking factors are structured data; storing the individual knowledge sets into a GraphDB database to form a time-space knowledge map; receiving a query instruction, traversing the spatiotemporal knowledge graph, and determining corresponding spatiotemporal knowledge; when no space-time knowledge corresponding to the query instruction exists, performing OWL ontology reasoning according to the framework; or calling related SWRL rules and an individual knowledge set to carry out inference, and determining new individual knowledge generated by inference as corresponding space-time knowledge; further comprising: establishing an SWRL rule base, wherein the SWRL rule base comprises a plurality of SWRL rules, and the SWRL rules are determined according to expert knowledge; adding the designed inference rule into an SWRL rule base, and calling an SWRL rule base engine API to search a related SWRL rule when performing time-space knowledge query; designing some SWRL rules in advance, adding the SWRL rules into an SWRL rule base to facilitate calling in query, or designing the SWRL rules according to query contents in query, and adding the designed SWRL rules into the SWRL rule base; the SWRL rules need to be determined according to expert knowledge; the new individual knowledge is obtained by strictly calculating according to expert knowledge on the basis of the original individual knowledge;
further comprising: the new individual knowledge is supplemented into the space-time knowledge map, the new individual knowledge is generated in the reasoning process, the new individual knowledge is supplemented into the space-time knowledge map, the original individual knowledge is supplemented, the space-time knowledge map is continuously improved, and the corresponding individual knowledge can be quickly provided when relevant contents are inquired later.
2. The method of claim 1, wherein extracting data related to geographic entities from the spatiotemporal data to generate an individual knowledge set of the target object comprises;
and extracting corresponding data from the space-time data according to the attribute of the class of the target object to generate a plurality of pieces of individual knowledge, wherein the individual knowledge forms an individual knowledge set of the target object.
3. A spatiotemporal knowledge map construction device based on GraphDB is characterized by comprising the following steps:
the body construction module is used for fusing OGC standards to construct a framework of a geographic entity, and the geographic entity comprises a plurality of target objects; the architecture for constructing the geographic entity comprises:
constructing a class of the geographic entity based on the target object, and adding a constraint relation of the class;
constructing attributes of a class, wherein the attributes of the class comprise data attributes and object attributes, and adding constraints of the object attributes;
the data attributes are used for representing the relationship between the object and the data and comprise label attributes, spatial positions and element attributes; the object attribute is used for representing the relation between the object and the object, and comprises a time sequence, a spatial relation and a point-surface record;
the data extraction module is used for extracting data related to geographic entities in the spatio-temporal data and generating an individual knowledge set of the target object, wherein the individual knowledge set comprises more than one individual knowledge, and the individual knowledge is expressed by combining RDF (remote data format) triples with an OWL (ontology Web language) extension language; knowledge extraction oriented to plain text data needs to acquire relevant spatial information and historical event information from a free text, and in the process of extracting entities, space-time entity identification and relation extraction are needed to express semantic relations between two or more entities; the knowledge extraction facing the remote sensing image is to extract spatial information of a target ground object from the remote sensing image, and attach some additional attribute information, including extracting mountain paths from the remote sensing image, attaching width data through calculation, expressing by using a regularized geojson, and storing into a knowledge map; the video/image mainly refers to monitoring purposes, when the image is taken, image recognition operation is carried out, whether a concerned event occurs or not is detected, if yes, corresponding event semantics are correspondingly generated, and then extraction is completed aiming at a template for generating the event; for semi-structured data, only a knowledge extractor is needed to be designed, the content under a specific label is extracted and mapped to the body of a target object;
the spatiotemporal data includes: one or more of plain text data, remote sensing images, video or image data, terrain data sets, webpage data, map data, POI data, sensor data, surface feature distribution data and artificial marking factors; the method comprises the following steps of obtaining plain text data, remote sensing images, videos or image data, wherein the plain text data, the remote sensing images, the videos or the image data are unstructured data; the Terrain data set, the webpage data, the map data, the POI data and the sensor data are semi-structured data; the ground feature distribution data and the artificial marking factor are structured data;
the storage module is used for storing the individual knowledge sets into a GraphDB database to form a time-space knowledge map;
the query module is used for receiving a query instruction, traversing the spatiotemporal knowledge graph and determining corresponding spatiotemporal knowledge;
the reasoning module is used for carrying out OWL ontology reasoning according to the framework if no spatiotemporal knowledge corresponding to the query instruction exists; or calling related SWRL rules and an individual knowledge set to carry out inference, and determining new individual knowledge generated by inference as corresponding space-time knowledge;
further comprising: establishing an SWRL rule base, wherein the SWRL rule base comprises a plurality of SWRL rules, and the SWRL rules are determined according to expert knowledge; adding the designed inference rule into an SWRL rule base, and calling an SWRL rule base engine API to search a related SWRL rule when inquiring the space-time knowledge; designing some SWRL rules in advance, adding the SWRL rules into an SWRL rule base to facilitate calling in query, or designing the SWRL rules according to query contents in query, and adding the designed SWRL rules into the SWRL rule base; the SWRL rules need to be determined according to expert knowledge; the new individual knowledge is obtained by strictly calculating according to expert knowledge on the basis of the original individual knowledge;
further comprising: the new individual knowledge is supplemented into the space-time knowledge map, the new individual knowledge is generated in the reasoning process, the new individual knowledge is supplemented into the space-time knowledge map, the original individual knowledge is supplemented, the space-time knowledge map is continuously improved, and the corresponding individual knowledge can be quickly provided when relevant contents are inquired later.
4. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed, implements the steps of the method according to any of claims 1-2.
5. A computer arrangement comprising a processor, a memory and a computer program stored on the memory, characterized in that the steps of the method according to any of claims 1-2 are implemented when the computer program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110055126.9A CN112732939B (en) | 2021-01-15 | 2021-01-15 | Spatiotemporal knowledge graph construction method, device, medium and equipment based on GraphDB |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110055126.9A CN112732939B (en) | 2021-01-15 | 2021-01-15 | Spatiotemporal knowledge graph construction method, device, medium and equipment based on GraphDB |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112732939A CN112732939A (en) | 2021-04-30 |
| CN112732939B true CN112732939B (en) | 2022-11-29 |
Family
ID=75593258
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110055126.9A Active CN112732939B (en) | 2021-01-15 | 2021-01-15 | Spatiotemporal knowledge graph construction method, device, medium and equipment based on GraphDB |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112732939B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113505234B (en) * | 2021-06-07 | 2023-11-21 | 中国科学院地理科学与资源研究所 | Construction method of ecological civilized geographic knowledge graph |
| CN113297395B (en) * | 2021-07-08 | 2021-09-24 | 中国人民解放军国防科技大学 | Spatio-temporal multi-modal mixed data processing method, correlation method and indexing method |
| CN113569931B (en) * | 2021-07-16 | 2024-04-05 | 中国铁道科学研究院集团有限公司 | Dynamic data fusion method, device, equipment and medium |
| CN113408663B (en) * | 2021-07-20 | 2022-04-08 | 中国科学院地理科学与资源研究所 | Fusion model construction method, fusion model using device and electronic equipment |
| CN113641831B (en) * | 2021-08-16 | 2022-04-15 | 中国科学院空天信息创新研究院 | Knowledge graph-based forest fire spreading trend prediction method oriented to multi-source discrete data |
| CN113641832B (en) * | 2021-08-16 | 2022-05-10 | 中国科学院空天信息创新研究院 | Knowledge graph-based multi-source discrete data-oriented forest fire rescue path planning method |
| CN113837028B (en) * | 2021-09-03 | 2024-05-14 | 广州大学 | Road flow analysis method and device based on space-time knowledge graph |
| CN115204269B (en) * | 2022-06-15 | 2024-03-12 | 南通市测绘院有限公司 | Urban treatment data fusion method and system based on space-time reference |
| CN116720578B (en) * | 2023-05-12 | 2024-01-23 | 航天恒星科技有限公司 | Storage method of knowledge graph with space-time characteristics |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107491555A (en) * | 2017-09-01 | 2017-12-19 | 北京纽伦智能科技有限公司 | Knowledge mapping construction method and system |
| CN109284394A (en) * | 2018-09-12 | 2019-01-29 | 青岛大学 | A method of Company Knowledge map is constructed from multi-source data integration visual angle |
| CN110362660A (en) * | 2019-07-23 | 2019-10-22 | 重庆邮电大学 | A kind of Quality of electronic products automatic testing method of knowledge based map |
| CN111488467A (en) * | 2020-04-30 | 2020-08-04 | 北京建筑大学 | Construction method and device of geographical knowledge graph, storage medium and computer equipment |
| CN112215441A (en) * | 2020-11-17 | 2021-01-12 | 北京明略软件系统有限公司 | Prediction model training method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6202063B1 (en) * | 1999-05-28 | 2001-03-13 | Lucent Technologies Inc. | Methods and apparatus for generating and using safe constraint queries |
| CN108154555B (en) * | 2017-12-27 | 2021-08-10 | 江西理工大学 | Three-dimensional modeling method for complex geological structure under knowledge rule constraint |
-
2021
- 2021-01-15 CN CN202110055126.9A patent/CN112732939B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107491555A (en) * | 2017-09-01 | 2017-12-19 | 北京纽伦智能科技有限公司 | Knowledge mapping construction method and system |
| CN109284394A (en) * | 2018-09-12 | 2019-01-29 | 青岛大学 | A method of Company Knowledge map is constructed from multi-source data integration visual angle |
| CN110362660A (en) * | 2019-07-23 | 2019-10-22 | 重庆邮电大学 | A kind of Quality of electronic products automatic testing method of knowledge based map |
| CN111488467A (en) * | 2020-04-30 | 2020-08-04 | 北京建筑大学 | Construction method and device of geographical knowledge graph, storage medium and computer equipment |
| CN112215441A (en) * | 2020-11-17 | 2021-01-12 | 北京明略软件系统有限公司 | Prediction model training method and system |
Non-Patent Citations (1)
| Title |
|---|
| 顾及时空特征的地理知识图谱构建方法;张雪英 等;《中国科学:信息科学》;20200708;第50卷(第7期);第1019-1032页，正文第2-5节，图5 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112732939A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112732939B (en) | Spatiotemporal knowledge graph construction method, device, medium and equipment based on GraphDB | |
| Nogueira et al. | FrameSTEP: A framework for annotating semantic trajectories based on episodes | |
| US20190205310A1 (en) | 3d analytics actionable solutions support system and apparatus | |
| Scharl et al. | The geospatial web: how geobrowsers, social software and the Web 2.0 are shaping the network society | |
| US11367346B2 (en) | Digitizing and mapping the public space using collaborative networks of mobile agents and cloud nodes | |
| CN109918478A (en) | The method and apparatus of knowledge based map acquisition geographic products data | |
| Tracewski et al. | Repurposing a deep learning network to filter and classify volunteered photographs for land cover and land use characterization | |
| US20160275196A1 (en) | Semantic search apparatus and method using mobile terminal | |
| Kosowska-Stamirowska et al. | Evolving structure of the maritime trade network: evidence from the Lloyd’s Shipping Index (1890–2000) | |
| CN107679221A (en) | Towards the time-space data acquisition and Services Composition scheme generation method of mitigation task | |
| CN113127506B (en) | Target query statement construction method and device, storage medium and electronic device | |
| CN111310074B (en) | Method and device for optimizing labels of interest points, electronic equipment and computer readable medium | |
| CN112765322A (en) | Remote sensing image search recommendation method based on water conservancy domain knowledge graph | |
| Koubarakis et al. | Big, linked geospatial data and its applications in earth observation | |
| Regueiro et al. | Virtual integration of sensor observation data | |
| Khatoon et al. | Social media-based intelligence for disaster response and management in smart cities | |
| KR20200082179A (en) | Data transformation method for spatial data's semantic annotation | |
| Masmoudi et al. | PREDICAT: a semantic service-oriented platform for data interoperability and linking in earth observation and disaster prediction | |
| Francalanci et al. | Exploratory spatio-temporal queries in evolving information | |
| Verma et al. | A graph based analysis of user mobility for a smart city project | |
| Sudmanns et al. | Big earth data: from data to information | |
| US20180253673A1 (en) | Real-time monitoring of terrestrial logistics networks | |
| Ahmadian et al. | Semantic integration of OpenStreetMap and CityGML with formal concept analysis | |
| CN112925939A (en) | Picture searching method, description information generating method, device and storage medium | |
| CN115878826A (en) | Multi-source remote sensing image metadata traceability information organization method and management system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |