Earth resources and environment tuple representation method, device, equipment and storage medium

Abstract

The present application discloses a method, device, equipment and storage medium for tuple representation of earth resources and environment, wherein the method comprises: determining a concept tuple expressing the semantic relationship of earth resources and environment based on various geographical concepts in earth resources and environment data and the semantic hierarchical relationship between geographical concepts; determining an instance tuple of a physical phenomenon corresponding to each geographical concept based on each geographical concept and earth resources and environment data in a concept tuple framework; determining a rule tuple corresponding to the geographical concept based on the relationship between each geographical concept and domain expert knowledge in the concept tuple; determining an earth resources and environment tuple model based on the concept tuple, all instance tuples and all rule tuples; wherein the earth resources and environment tuple model is used to represent earth resources and environment data and domain expert knowledge; earth resources and environment data are represented by concept tuples and instance tuples, and domain expert knowledge is represented by concept tuples and rule tuples.

Description

Technical Field

[0001] The present application relates to the fields of earth resources and environment technology and artificial intelligence technology, and relates to but is not limited to a method, device, equipment and storage medium for tuple representation of earth resources and environment. Background Art

[0002] In recent years, many attempts have been made around knowledge graphs in the field of earth resources and environment, including "geographic / spatial-temporal knowledge graphs". However, the existing earth resource data sources are diverse and separated from each other, making it difficult to efficiently conduct collaborative analysis and calculations. At the same time, domain expert knowledge, as the result of human cognition of objective things, is usually contained in expert experience, procedures and specifications, and model formulas in a discrete form. It is difficult for the experiential knowledge in a single field to support the actual analysis needs of earth resources and environment. Summary of the invention

[0003] In view of this, the embodiments of the present application at least provide a method, apparatus, device and storage medium for representing the earth's resources and environment in a tuple format.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] On the one hand, an embodiment of the present application provides a method for tuple representation of earth resources and environment, the method comprising: determining a concept tuple expressing the semantic relationship of earth resources and environment based on various geographical concepts in earth resources and environment data and the semantic hierarchical relationship between geographical concepts; determining an instance tuple of a physical phenomenon corresponding to each geographical concept based on each geographical concept in the concept tuple framework and the earth resources and environment data; determining a rule tuple corresponding to the geographical concept based on the relationship between each geographical concept and domain expert knowledge in the concept tuple; determining an earth resources and environment tuple model based on the concept tuple, all instance tuples and all rule tuples; wherein the earth resources and environment tuple model is used to represent earth resources and environment data and domain expert knowledge; the earth resources and environment data is represented by the concept tuple and the instance tuple, and the domain expert knowledge is represented by the concept tuple and the rule tuple.

[0006] On the other hand, an embodiment of the present application provides a tuple representation device for earth resources and environment, the device comprising: a first determination module, used to determine a concept tuple expressing the semantic relationship of earth resources and environment based on various geographical concepts in earth resources and environment data and the semantic hierarchical relationship between geographical concepts; a second determination module, used to determine the instance tuple of the physical phenomenon corresponding to each geographical concept based on each geographical concept in the concept tuple framework and the earth resources and environment data; a third determination module, used to determine the rule tuple corresponding to the geographical concept based on the relationship between each geographical concept and domain expert knowledge in the concept tuple; a fourth determination module, used to determine an earth resources and environment tuple model based on the concept tuple, all instance tuples and all rule tuples; wherein the earth resources and environment tuple model is used to represent earth resources and environment data and domain expert knowledge; the earth resources and environment data are represented by the concept tuple and the instance tuple, and the domain expert knowledge is represented by the concept tuple and the rule tuple.

[0007] On the other hand, an embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program that can be executed on the processor, and when the processor executes the program, some or all of the steps in the above method are implemented.

[0008] On the other hand, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which implements part or all of the steps in the above method when executed by a processor.

[0009] The tuple representation method of the earth resources and environment provided in the embodiment of the present application first determines the concept tuple expressing the semantic relationship of the earth resources and environment based on various geographical concepts in the earth resources and environment data, and determines the instance tuple of the physical phenomenon corresponding to each of the geographical concepts; then, based on the relationship between each of the geographical concepts and the domain expert knowledge, determines the rule tuple corresponding to the geographical concept; finally, based on the concept tuple, all the instance tuples and all the rule tuples, determines the tuple model of the earth resources and environment. This tuple representation method of the earth resources and environment provides a basis for data fusion by establishing a tuple description framework with a unified time and space reference, and at the same time tuples the domain expert knowledge, so that the expert knowledge that was originally separated from each other is digitized and can be reasoned and analyzed, so that data and knowledge interact with each other to achieve perception, understanding and analytical calculation of tasks.

[0010] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0012] Figure 1A A schematic diagram of the implementation process of a method for representing the earth resources and environment in a tuple form provided in an embodiment of the present application;

[0013] Figure 1B A schematic diagram of a concept tuple provided in an embodiment of the present application;

[0014] Figure 1C A schematic diagram of an example tuple of temperature provided in an embodiment of the present application;

[0015] Figure 1D A schematic diagram of an example tuple of a building provided in an embodiment of the present application;

[0016] Figure 1E A schematic diagram of a rule tuple provided in an embodiment of the present application;

[0017] Figure 1F A schematic diagram of a tuple model of earth resources and environment provided in an embodiment of the present application;

[0018] Figure 1G A schematic diagram of an earth resource environment data expression provided in an embodiment of the present application;

[0019] Figure 1H A schematic diagram of a formal expression of domain expert knowledge provided in an embodiment of the present application;

[0020] Fig. 1I A schematic diagram of the linkage expression of a concept tuple, an instance tuple, and a rule tuple provided in an embodiment of the present application;

[0021] Figure 2 A schematic diagram of a high temperature orange warning signal rule tuple and a high temperature orange warning defense rule tuple provided in an embodiment of the present application;

[0022] Figure 3 A schematic diagram of the implementation process of applying a tuple representation of earth resources and environment in the direction of knowledge reasoning provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of the implementation process of a tuple representation of earth resources and environment in the direction of knowledge computing provided in an embodiment of the present application;

[0024] Figure 5A schematic diagram of an implementation flow of a method for determining spatial feature data in an instance tuple provided in an embodiment of the present application;

[0025] Figure 6 A schematic diagram of a tuple model of earth resources and environment provided in an embodiment of the present application;

[0026] Figure 7 A schematic diagram of a remote sensing image data processing process provided in an embodiment of the present application;

[0027] Figure 8 A schematic diagram of a chain reasoning process for data and knowledge fusion reasoning analysis provided in an embodiment of the present application;

[0028] Fig. 9 A schematic diagram of a fire hazard risk calculation implementation process provided in an embodiment of the present application;

[0029] Fig.10 A schematic diagram of the composition structure of a device for representing earth resources and environment in a tuple form provided in an embodiment of the present application;

[0030] Fig.11 A hardware entity diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. The following embodiments are used to illustrate the present application, but are not intended to limit the scope of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0032] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0033] It should be pointed out that the terms "first\second\third" involved in the embodiments of the present application are merely to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0034] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the general understanding of those skilled in the art in the field to which the embodiments of the present application belong. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0035] Before describing the embodiments of the present application, the nouns and terms involved in the embodiments of the present application are described. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.

[0036] Tuple: In the Python programming language, a tuple represents a data structure that is used to group multiple data elements together.

[0037] Conceptual Tuple: It is the core concept in the tuple model, representing various geographical concepts in the real world and the semantic hierarchical relationships between geographical concepts.

[0038] Spatial Tuple: refers to a specific expression of the geophysical phenomenon corresponding to a geographical concept established under the framework of a conceptual tuple. It is a combination of geographical concepts and related characteristic information such as space and time. It describes the spatial characteristics, temporal characteristics, geometric characteristics and thematic characteristics of the geographical concepts defined in the conceptual tuple on the earth's surface.

[0039] Rule Tuple: A tuple type used to describe the relationship and constraints between geographic concepts and domain expert knowledge. It is a knowledge-based tuple based on data such as concept tuples and instance tuples.

[0040] Well-Known Text (WKT): is a standard format for describing spatial data. It uses text to describe the geometric features of geographic and geometric objects. The basic structure includes geometry type and coordinate data, where the geometry type can be points, lines, polygons, etc., and the coordinate data describes the location information of each point.

[0041] Graph Database: A new type of non-relational database based on graph theory. Its data storage structure and data query method are based on graph theory. The basic elements of a graph in graph theory are nodes and edges, which correspond to nodes and relationships in a graph database. In a graph database, the relationship between data and data forms a graph structure through nodes and edges, and all the characteristics of the database are implemented on this structure, such as the ability to create, read, update, and delete (Create, Read, Update, Delete, referred to as: CRUD) graph data objects, as well as the ability to handle transactions and high availability.

[0042] Knowledge Graph: It is called knowledge domain visualization or knowledge domain mapping map in the library and information industry. It is a series of various graphs that show the development process and structural relationship of knowledge. It uses visualization technology to describe knowledge resources and their carriers, and to mine, analyze, construct, draw and display knowledge and their interrelationships.

[0043] Triple: A common representation of knowledge graphs. The basic form of triples mainly includes entity 1, relationship, entity 2 and concepts, attributes, attribute values, etc. Entities are the most basic elements in knowledge graphs, and different entities have different relationships.

[0044] In recent years, many attempts have been made around knowledge graphs in the field of earth resources and environment, including "geographic / spatiotemporal knowledge graphs". However, the existing sources of earth resource data are diverse, such as remote sensing data, IoT sensor data, video surveillance data, historical data of field reserves, and data generated by people when using the Internet. These data are often separated from each other, making it difficult to conduct efficient collaborative analysis and calculation. At the same time, domain expert knowledge, as the result of human cognition of objective things, includes factual and declarative knowledge, rule-based and control-based knowledge, decision-making and method-based knowledge, etc. These domain expert knowledge are contained in expert experience, procedures or model formulas in a discrete form, and a single domain experience knowledge is often difficult to support the actual analysis needs of earth resources and environment. At present, there is no better method to effectively represent earth resources and environment data and the relationship between earth resources and environment data and domain expert knowledge. It is impossible to effectively combine the experience knowledge of the laws of the occurrence and development of spatiotemporal events in the field of earth resources and environment, and organically integrate knowledge and data from different sources, fields, and forms.

[0045] The present application embodiment provides a method for representing the earth resources and environment in a tuple format, such as Figure 1A As shown, the method may include steps S100 to S103:

[0046] Step S100: Based on various geographical concepts in the earth resources and environment data and the semantic hierarchical relationships between the geographical concepts, a concept tuple expressing the earth resources and environment semantic relationship is determined.

[0047] Here, earth resources and environmental data refers to various data and information about the earth's natural resources and environmental conditions, including:

[0048] (1) Meteorological data: temperature, humidity, precipitation, wind direction and wind speed, etc.;

[0049] (2) Topographic data: elevation, topographic and geomorphic information;

[0050] (3) Land cover data: forests, grasslands, cities, water bodies, etc.;

[0051] (4) Geological data: internal structure of the earth, rock types, mineral resources, etc.;

[0052] (5) Hydrological data: data on groundwater and surface water resources, including river flow, water quality, water level, etc.;

[0053] (6) Ecological and environmental data: including vegetation index, biodiversity data, wildlife migration and other information;

[0054] (7) Atmospheric environmental data: data on atmospheric composition, air quality, greenhouse gas emissions, etc. These data are closely related to climate change research, environmental protection and air quality monitoring;

[0055] (8) Soil data: describes information such as soil type, soil quality, and soil moisture. These data are of great significance to agricultural production and sustainable land use.

[0056] Geographical concepts are defined as concepts that describe physical phenomena on Earth in the field of geography. Figure 1BAs shown in the figure, “Earth resources and environment data 01”, “Meteorological data 11”, “Terrain data 12”, “Vegetation data 13”, “Surface data 14” and the next layer “Temperature 110”, “Humidity 111”, “Wind speed 112”, “Slope 121”, “Aspect 122”, “Elevation 123”, “Coniferous forest 131”, “Broad-leaved forest 132”, “Shrub forest 133”, “Building 141”, “Road 142”, “Cultivated land 143”, etc. are all used as geographical concepts. There is a top-down inclusive relationship between these geographical concepts, such as “Earth resources and environment data 01”, “Meteorological data 11”, “Vegetation data 12”, “Surface data 14”, etc. 1” includes “meteorological data 11”, “terrain data 12”, “vegetation data 13” and “land feature data 14”; further, “meteorological data 11” includes “temperature 110”, “humidity 111”, “wind speed 112”, etc.; “terrain data 12” includes “slope 121”, “slope aspect 122”, “elevation 123”, etc.; “vegetation data 13” can be divided into “coniferous forest 131”, “broad-leaved forest 132”, “shrub forest 133”, etc.; “land feature data 14” can be divided into “building 141”, “road 142”, “cultivated land 143”, etc.

[0057] Semantic hierarchical relationships refer to the semantic connections and associations between words. They can be described through multiple dimensions such as word meaning, morphology, syntax, and context. For example, synonymy, antonymy, hyponymy, and inclusion are all specific manifestations of semantic hierarchical relationships.

[0058] Step S101: Based on each geographical concept in the concept tuple framework and the earth resources and environment data, determine the instance tuple of the physical phenomenon corresponding to each geographical concept.

[0059] Here, the concept tuple framework is a framework organized based on various geographical concepts in earth resources and environmental data and the semantic hierarchical relationships between geographical concepts.

[0060] Each geographic concept in the concept tuple framework corresponds to a series of geographic entities with different time, space and other attribute characteristics. Among them, a geographic entity is a specific object or individual associated with a geographic concept and corresponding to various levels of specific geographic objects. Geographic entities can include many types, such as temperature entities, humidity entities, slope entities, etc. In general, geographic concepts are an abstract expression of the objective real world, while geographic entities are the embodiment of countless specific examples of geographic concepts in the real world.

[0061] like Figure 1CAs shown, the temperature entities of the geographical concept "temperature 15" at a specific time and space (location) are listed. Taking "a certain city A, a certain area D 2023-08-15 18:00:00 temperature entity 16" as an example, this temperature entity occurs in a certain city A, a certain area D at 18:00:00 on 2023-08-15, among which "a certain city A, a certain area D" represents spatial feature 161, "2023-08-15 18:00:00" represents temporal feature 163, "38°C" represents thematic feature 162, and "polygon" represents geometric feature 164.

[0062] like Figure 1D As shown, the instance tuple "City A Region B Community C Residential Building-0001 Entity 18" corresponding to the geographical concept "Building 17" is listed, among which "City A Region B116.97634, 40.28183" represents the spatial feature 182, "Built in 1980" represents the time feature 183, and "Polygon formed by the outline of the residential building" represents the geometric feature 184, "High" represents the thematic feature 181 describing the age of the building, and "Brick, sand, stone, cement, wood, tile, concrete, etc." represents the thematic feature 185 describing the material of the building.

[0063] Through the above two examples, the instance tuple materializes the two geographical concepts of "temperature" and "building", and associates the specific instance with attribute information such as spatial features, geometric features, time features, and thematic features. It should be noted that in some embodiments, the attribute information of the instance tuple may be incomplete.

[0064] Step S102: Based on the relationship between each of the geographic concepts in the concept tuple and the domain expert knowledge, determine a rule tuple corresponding to the geographic concept.

[0065] Here, domain expert knowledge covers multiple disciplines, including physical geography, atmospheric science, geology, ecology, hydrology, disaster science, environmental science, remote sensing and geographic information system (GIS). Figure 1E As shown, the rule tuple includes a rule tuple name 19 , a rule tuple trigger condition 191 and a rule tuple response action 192 .

[0066] Step S103: Determine the earth resources environment tuple model based on the concept tuple, all instance tuples and all rule tuples.

[0067] Here, the earth resources and environment tuple model includes concept tuples, instance tuples and rule tuples, and the model is used to represent earth resources and environment data and domain expert knowledge.

[0068] like Figure 1FAs shown, the earth resource tuple model 02 includes a concept tuple 21, an instance tuple 20 and a rule tuple 22, wherein the earth resource environment data is represented by the concept tuple 21 and the instance tuple 20, the domain expert knowledge is represented by the concept tuple 21 and the rule tuple 22, and the earth resource environment data and the domain expert knowledge are integrated and linked through the concept tuple 21.

[0069] A complete earth resources and environment data record includes a concept tuple (describing the concept type of the data) and an instance tuple (indicating the characteristics of the data), such as Figure 1G As shown, the concept of "temperature 30" in the earth resources and environment data 03, combined with the relevant data of temperature in the earth resources and environment data, determines an instance tuple [a certain city A a certain area D 2023-08-15 18:00:00 temperature entity 31], and the instance tuple contains descriptions of attribute information such as space and time; the concept of "building 32" in the earth resources and environment data 03, combined with the relevant data of buildings in the earth resources and environment data, determines an instance tuple [a certain city A a certain area B a certain community C residential building-0001 entity 33], and the instance tuple includes descriptions of attribute information such as space, geometry, and age;

[0070] Combine concept tuples with rule tuples to fully represent domain expert knowledge, such as Figure 1H As shown in the figure, the geographical concept corresponding to the domain expert knowledge is "temperature 40". Based on the knowledge in the domain expert knowledge that "the standard for the high temperature orange warning signal is that the maximum temperature will rise to 37℃-39℃ within 24 hours", the triggering condition and response action of the rule tuple [high temperature orange warning signal 41] are determined; based on the knowledge in the domain expert knowledge that "defense guidelines: 1. Relevant departments and units shall implement heatstroke prevention and cooling protection measures in accordance with their duties; 2. Try to avoid outdoor activities during high temperature periods, and personnel working under high temperature conditions shall shorten continuous working hours; 3. Provide heatstroke prevention and cooling guidance to the elderly, weak, sick, and young people, and take necessary protective measures; 4. Relevant departments and units shall pay attention to preventing fires caused by excessive power consumption and excessive power loads such as wires and transformers", the triggering condition and response action of the rule tuple [high temperature orange warning defense 42] are determined.

[0071] Combining concept tuples, instance tuples, and rule tuples together can fully represent how geographic entities such as "temperature" and "building" obtain action responses under the guidance of domain expert knowledge rules such as "high temperature orange warning signal" and "urban old residential building fire risk warning". Fig. 1IAs shown, a new temperature entity 53 is created, which is associated with the "temperature 50" in the concept tuple, and the "temperature 50" is associated with the rule tuple [high temperature orange warning signal 51]. The response action of the rule tuple [high temperature orange warning signal 51] triggers the execution of the rule tuple [urban old residential building fire risk warning 52]. The response action of the rule tuple [urban old residential building fire risk warning 52] is further associated with the building entity [a certain city A certain area B certain community C residential building -0001 entity 54], and finally the warning information is output.

[0072] The tuple representation method of the earth resources and environment provided in the embodiment of the present application first determines the concept tuple expressing the semantic relationship of the earth resources and environment based on various geographical concepts in the earth resources and environment data, and determines the instance tuple of the physical phenomenon corresponding to each of the geographical concepts; then, based on the relationship between each of the geographical concepts and the domain expert knowledge, determines the rule tuple corresponding to the geographical concept; finally, based on the concept tuple, all the instance tuples and all the rule tuples, determines the tuple model of the earth resources and environment. This tuple representation method of the earth resources and environment provides a basis for data fusion by establishing a tuple description framework with a unified time and space reference, and at the same time tuples the domain expert knowledge, so that the expert knowledge that was originally separated from each other is digitized and can be reasoned and analyzed, so that data and knowledge interact with each other to achieve perception, understanding and analytical calculation of tasks.

[0073] In some embodiments, the above step S102, determining the rule tuple corresponding to the geographic concept based on the relationship between each geographic concept in the concept tuple and the domain expert knowledge, may include steps S200 to S203:

[0074] Step S200: Determine the domain expert knowledge corresponding to each geographic concept in the concept tuple framework.

[0075] Step S201: Based on each of the domain expert knowledge, determine the rule tuple name and rule tuple triggering condition corresponding to the domain expert knowledge.

[0076] Here, the rule tuple name is the identifier or name of the rule tuple, which is used to uniquely identify the rule tuple. Usually, meaningful names such as "Orange Warning Signal for High Temperature" and "Fire Risk Warning for Old Residential Buildings in Cities" are used to describe the role or meaning of the rule for easier management and understanding.

[0077] Rule tuple trigger conditions, trigger conditions can be one or more logical conditions, used to describe under what circumstances the rule should be triggered or activated, and the rule will only be executed when these conditions are met. The retrieval frequency of the trigger condition is related to the data update frequency. When the data is continuously monitored and continuously updated, the trigger condition is timed by minutes or hours. Some additional processing measures such as data filtering and data cleaning are required to reduce the database storage pressure. The specific processing is handled by technical personnel in this field according to the actual situation, and no specific restrictions are made here. In actual application scenarios, for data with a low update frequency, such as terrain, vegetation, etc., the trigger condition can be retrieved every time the data is updated; for data with a high update frequency such as meteorology, the device hardware may be difficult to support the retrieval of the trigger condition every time the data is updated. At this time, the retrieval frequency of the trigger condition can be adjusted according to the actual efficiency of different hardware devices in processing meteorological data-related services.

[0078] Step S202: Based on the rule tuple triggering condition, determine a response action corresponding to the rule tuple triggering condition.

[0079] Here, the response action is the action executed after the rule is triggered. These actions include modifying the system state, generating output, triggering other rules, etc., and can be implemented by functions in programming languages. The response action is the core of the rule tuple, which defines the actual behavior of the rule. The frequency of the response action is related to the trigger update frequency. When the data is continuously monitored and continuously updated, and the trigger condition is timed by minutes or hours, the response will also occur frequently. At this time, some additional processing measures such as data filtering and data cleaning are required to reduce the database storage pressure. The specific processing is handled by those skilled in the art according to the actual situation, and no specific restrictions are made here. In actual application scenarios, for data with a low update frequency, such as terrain, vegetation, etc., the trigger condition can be retrieved and the response action can be executed every time the data is updated; for data with a high update frequency such as meteorology, the hardware device may be difficult to support the retrieval of the trigger condition and the execution of the response action every time the data is updated. At this time, the retrieval of the trigger condition and the execution frequency of the response action can be adjusted according to the actual efficiency of the hardware device in processing meteorological data-related services.

[0080] Step S203: Determine the corresponding rule tuple based on each rule tuple name and the triggering condition and response action of the corresponding rule tuple name.

[0081] like Figure 2As shown, taking the high temperature orange warning signal 51 and the high temperature orange warning defense 52 as examples to describe the rule tuple, the rule tuple can describe various types of knowledge including factual and declarative knowledge (for example: the temperature is 37°C), rule and control knowledge (for example: the maximum temperature within 24 hours rises to 37°C-39°C, which will trigger the high temperature orange warning signal), decision-making and methodological knowledge (for example: defense guide: 1. Relevant departments and units implement heatstroke prevention and cooling protection measures in accordance with their responsibilities...).

[0082] In some embodiments, the earth resources environment tuple representation is applied in the direction of knowledge reasoning, such as Figure 3 As shown, it may include steps S300 to S302:

[0083] Step S300: when the earth resources and environment data is updated, based on the earth resources and environment tuple model, determining a target instance tuple corresponding to the updated earth resources and environment data;

[0084] Step S301: determining a target geographical concept corresponding to the target instance tuple, and determining a signal rule tuple corresponding to the target geographical concept;

[0085] Step S302: Based on the data of the target instance tuple, when it is determined that the triggering condition of the signal rule tuple is satisfied, executing a response action of the signal rule tuple.

[0086] In some embodiments, further application of the earth resources and environment tuple model in the direction of knowledge reasoning may include steps S310 to S313: Step S310: When the response action of the signal rule tuple causes the triggering condition of the warning rule tuple to be met, execute the first response action of the warning rule tuple; Step S311: Based on the first response action, determine the candidate first land object; Step S312: After the first response action is executed, based on the candidate first land object, execute the second response action corresponding to the warning rule tuple to determine the land object to be warned; Step S313: After the second response action is executed, execute the third response action corresponding to the warning rule tuple to obtain the warning information of the land object to be warned.

[0087] In some embodiments, the earth resources environment tuple representation is applied in the direction of knowledge computing, such as Figure 4 As shown, it may include steps S400 to S405:

[0088] Step S400: obtaining a second ground object to be risk assessed at a preset time.

[0089] For example, the fire hazard risk of entity 0001 in residential building C in community B in area A of a city needs to be calculated at 8:00 on September 17, 2023.

[0090] Step S401: Based on the earth resource environment tuple model, determine the instance tuple corresponding to the second ground feature object and the rule tuple corresponding to the risk assessment.

[0091] Here, the instance tuple of the entity "residential building C" in a certain area of ​​a certain city A and a certain community B -0001 is retrieved in the earth resources and environment tuple model to obtain the corresponding instance tuple [entity "residential building C" in a certain area of ​​a certain city A and a certain community B -0001]; the rule tuple for calculating the fire hazard risk is retrieved in the earth resources and environment tuple model to obtain the corresponding rule tuple [fire hazard risk calculation].

[0092] Step S402: Determine spatial feature data corresponding to the second geographical object based on data of the instance tuple corresponding to the second geographical object.

[0093] Here, through the data of the obtained instance tuple [city A certain area B certain community C residential building-0001 entity], it can be determined that the spatial feature data is "city A certain area B 116.97634, 40.28183".

[0094] Step S403: executing a response action of the rule tuple based on the spatial feature data and preset time data corresponding to the second ground object.

[0095] Here, the triggering conditions of the rule tuple [fire hazard risk calculation] are the target area space and the target area time. Here, the target area space corresponds to the spatial feature data, that is, "A certain area B in a certain city A 116.97634, 40.28183", and the target area time corresponds to the preset time data, that is, "8:00 on September 17, 2023". When the triggering conditions of the rule tuple [fire hazard risk calculation] are met, the response action of the rule tuple [fire hazard risk calculation] is executed.

[0096] Step S404: Based on the input parameters of the response action, determine the instance tuple corresponding to the input parameters.

[0097] Here, the response action of the rule tuple [fire hazard risk calculation] is a risk calculation action function, wherein the input parameters of the risk calculation action function are the attributes and weights of the risk factors. Further, the earth resources and environment tuple model is retrieved to determine the instance tuple [urban old residential building fire risk factor] corresponding to the input parameters.

[0098] Step S405: Determine the output of the response action based on the data of the instance tuple corresponding to the input parameter; the output is the risk value of the second ground feature object.

[0099] Here, the instance tuple [fire risk factor of old residential buildings in cities] is used as the data base, and the data of the instance tuple [fire risk factor of old residential buildings in cities] is input into the risk calculation action function. After obtaining the specific data, the risk calculation action function starts the calculation. After the calculation is completed, the risk value of the fire occurring in the residential building C in a certain area B in a certain city -0001 entity at 8:00 on September 17, 2023 is output.

[0100] In some embodiments, the method for determining the spatial feature data is as follows: Figure 5 As shown, it may include steps S500 to S502:

[0101] Step S500: Based on the remote sensing image data of the second land object, determine the pyramid index map structure corresponding to the geographic information data in the remote sensing image of the second land object.

[0102] Here, the pyramid index graph structure is an index structure for efficiently storing and retrieving geographic information data. Geographic information data is organized in the form of a pyramid, which is a hierarchical structure with decreasing resolution. The spatial index of the data is based on spatial coordinates, so that queries for geographic locations can be efficiently mapped to corresponding tile codes.

[0103] Step S501: determining a tile code corresponding to the pyramid index map structure of the second geographical feature object based on the geographical coordinates and the geographical coding function of the second geographical feature object.

[0104] Here, the representation form of the geographic coordinates of the second feature object is the WKT spatial semantics of the GeoSPARQL standard. The GeoSPARQL standard supports the representation and query of geospatial data on the semantic Web, defines a vocabulary for representing geospatial data using RDF (Resource Description Framework), and defines an extension of the SPARQL (SPARQL Protocol and RDF Query Language) query language for processing geospatial data.

[0105] Tile encoding is a method of storing image data in blocks. It divides the image into multiple small blocks, each of which is called a tile, and assigns a unique number to each tile for identification and storage. In implementation, the image data corresponds to the pyramid index map structure of the second feature object described above.

[0106] The geocoding function is a function that calculates the tile coding corresponding to the pyramid index map structure of the feature object based on the geographic coordinates and its reverse process.

[0107] In some embodiments, the specific process of determining the tile code corresponding to the pyramid index map structure of the second geographical feature object through the geographical coding function based on the geographical coordinates of the second geographical feature object is as follows:

[0108] The relationship between the map zoom level z and the number of tiles per row (or column) n is as follows:

[0109] n = 2^z (1);

[0110] The longitude range of the projected map is [-180, 180]. The number of tiles in each row at level z is n. Then the x-axis number corresponding to the longitude of the feature object at level z is:

[0111] tileX=(lon+180) / 360*n (2);

[0112] Among them, lon represents the longitude of the second feature object, the unit is degree, and tile represents the axis.

[0113] The y-axis number corresponding to the latitude of the feature object at level z is:

[0114] tileY=n*((1-((log(tan(lat)+sec(lat)))) / π)) / 2 (3);

[0115] Among them, lat represents the latitude of the second feature object, the unit is radian, log represents logarithm, tan represents tangent, and sec represents secant.

[0116] Step S502: Determine spatial feature data of the second land object based on the tile code and the pyramid index map structure of the second land object.

[0117] In some embodiments, the above step S500 may include steps S510 to S513:

[0118] Step S510: converting the remote sensing image data of the second land object into GeoJSON format data.

[0119] Here, GeoJSON is a format for encoding various geographic data structures, a geographic spatial information data exchange format based on JavaScript Object Notation (JSON). GeoJSON objects can represent geometries, features, or feature collections. GeoJSON supports the following geometry types: points, lines, surfaces, multipoints, multilines, multifaceted surfaces, and geometry collections. Features in GeoJSON contain a geometry object and other properties, and feature collections represent a series of features.

[0120] Step S511: Based on the geographic information data in the GeoJSON format data, determine the geographic information data in the string format.

[0121] Here, the geographic information data in GeoJSON format is further converted into a string format.

[0122] Step S512: Mapping the geographic information data in the string format to a spatial grid based on a gridded geocoding algorithm.

[0123] Here, the geocoding algorithm refers to an algorithm that links the pixel information in the image with the actual geographic coordinates on the surface of the earth. Through the geocoding algorithm, the information in the image can be easily matched with the actual location of the object, thereby facilitating subsequent data analysis, application and visualization. In some embodiments, the geocoding algorithm can be a Google tile algorithm.

[0124] Step S513: Based on the spatial grid, determine the pyramid index map structure corresponding to the geographic information data of the second feature object.

[0125] The above-mentioned method of tuple representation of earth resources and environment is explained below in conjunction with a specific embodiment. This application embodiment starts from the construction of an earth resources and environment tuple model, tuples the earth resources and environment, and then explains the data and knowledge fusion reasoning analysis based on the earth resources and environment tuple model. Then it is explained that in other embodiments, an earth resources and environment knowledge graph can be constructed based on the earth resources and environment tuple model, and then the knowledge graph can be used for the next step of analysis. Finally, the application of the earth resources and environment tuple model is explained with specific examples. However, it is worth noting that this specific embodiment is only for better illustrating the present application and does not constitute an improper limitation on the present application.

[0126] The tuple representation method of earth resources proposed in the embodiment of the present application first establishes a tuple description framework with a unified time and space reference to mine the associations between data and between data and domain expert knowledge, thereby providing a basis for data fusion; then, a formal expression method of tuple domain expert knowledge is used to digitize the expert knowledge that was originally separated from each other and enable reasoning and analysis; further, a query, reasoning and calculation model is established that integrates tuple earth resource environment data and domain expert knowledge, so that data and knowledge interact with each other and realize the perception, understanding and analytical calculation of tasks.

[0127] 1. Construction of the meta-model of earth resources and environment;

[0128] In the embodiments of the present application, Figure 6 As shown, the earth resources and environment tuple model 06 can represent earth resources and environment data 62 and domain expert knowledge 61, wherein the earth resources and environment data 62 include meteorological data 621, topographic data 622, surface cover data 623, hydrological data 624, ecological environment data 625, atmospheric environment data 626, soil data 627 and geological data 628, and the domain expert knowledge 61 includes physical geography 611, atmospheric science 612, geology 613, ecology 614, hydrology 615, disaster science 616, environmental science 617 and remote sensing information and geographic system 618.

[0129] Here, when expressing the earth's resource and environmental data, real ground feature information is indispensable. In addition to numerical ground feature information such as temperature, humidity, slope and aspect that can be obtained through measurement, another important data source is ground feature image information obtained through remote sensing technology. At present, the use of machine learning and deep learning-based methods to extract ground feature information from remote sensing images has become quite mature. These technologies can identify and classify geographic entities such as buildings, roads, and water bodies.

[0130] The vector results extracted from remote sensing images are an important part of the earth's resources and environment data. In order to effectively integrate these data, the extracted vector data must be converted into GeoJSON format. Through this conversion, the ground feature information can be stored in the form of triples, and then the instance tuples of buildings, roads, water bodies, etc. can be formally described. In this way, not only can the features of the ground features be accurately recorded, but also the interoperability and availability of data can be promoted, providing a solid foundation for the understanding and analysis of the earth's resources and environment.

[0131] like Figure 7As shown, step S701: converting data of different formats into GeoJSON format. In some embodiments, data of different formats may be geographic information data, text data, sensor transmission data, etc.; step S702: mapping the geographic information data in GeoJSON format obtained in step S701 to a limited multi-scale (0-N level) spatial grid through a grid geocoding algorithm, and obtaining a multi-scale grid geocoding set of each geographic entity; step S703: the multi-scale grid geocoding set of each geographic entity establishes a pyramid index graph structure of each geographic entity based on a graph database (GraphDB). In some embodiments, the geocoding algorithm may be a Google tile algorithm.

[0132] When searching for specific geographical objects, first, the geographic coordinates of the geographical objects to be searched are expressed using the WKT spatial semantics based on the GeoSPARQL standard; then, based on the geographic coordinates of the geographical objects to be searched, the corresponding tile codes in the pyramid index graph structure of the geographical objects to be searched are determined through the geocoding function; finally, the tile codes are used as the entry to quickly obtain the information of the geographical objects to be searched, including the spatial, temporal and state attribute information of the geographical objects to be searched, and other information of the geographical objects to be searched. In some embodiments, the specific geographical objects may be buildings, roads or vegetation, etc.

[0133] The remote sensing image processing method in the embodiment of the present application replaces the inefficient GeoSPARQL breadth search, utilizes the "deep retrieval" advantage of the graph database, searches for massive triples, and greatly improves the efficiency of geographic information conditional queries in random spatial areas under large data volumes.

[0134] Through the information extraction technology of remote sensing images, a large number of instance tuples describing geographic entities can be obtained. Taking buildings as an example, the buildings directly extracted from remote sensing images can obtain their geographic coordinates, area and other information, however, some attribute information such as construction time, age, structure, material, etc. is still lacking. This information can be obtained through archives, housing management offices and other channels and input into instance tuples.

[0135] Furthermore, the earth resources and environment tuple model includes instance tuples, concept tuples and rule tuples, where instance tuples and concept tuples are used to represent earth resources and environment data, and rule tuples and concept tuples are used to represent domain expert knowledge. Figure 1GAs shown in the figure, the temperature concept corresponds to the temperature entity, forming a quantitative description of the temperature data in the earth resources and environment data; the building concept corresponds to the building entity, forming a quantitative description of the building data in the earth resources and environment data. Similarly, other earth resources and environment data, such as humidity, wind direction, wind speed, slope, and slope direction, can be represented by a combination of concept tuples and instance tuples. Figure 1H As shown, the geographical concepts in the domain expert knowledge are extracted and represented based on the hierarchical relationship of concept tuples. The domain expert knowledge is formalized into rule tuples, and the rule tuples are used to represent the triggering conditions and response actions of the domain expert knowledge.

[0136] 2. Data and knowledge fusion reasoning analysis;

[0137] After the earth resources and environment tuple model is successfully created, data and knowledge fusion reasoning analysis can be performed based on this model. The instance tuple in the earth resources and environment tuple model usually contains multiple attributes and may continue to change in time and space dimensions; at the same time, the instance tuple is also constrained by the abstract concepts in the concept tuple. When the instance tuple changes, the system associates the corresponding abstract concept through the instance tuple to determine whether the trigger condition of the rule tuple containing the abstract concept is met. If the trigger condition is met, the response action of the rule tuple is executed. The response action may also cause the trigger conditions of other rules to be met, thereby generating a new trigger response, forming a chain reasoning process for data and knowledge fusion reasoning analysis. Figure 8 As shown, step S801: [temperature geographic tuple] changes; step S802: upwardly associate the corresponding abstract concept "temperature" through [temperature geographic tuple]; step S803: retrieve the rule tuple containing the concept of "temperature" to obtain the rule tuple [high temperature orange warning signal]; step S804: determine whether the triggering condition of the rule tuple [high temperature orange warning signal] is met; step S805: if the triggering condition is met, execute the response action of the rule tuple [high temperature orange warning signal]; step S806: the execution of the response action will cause the triggering condition of the rule tuple [fire risk warning for residential buildings in old urban areas of cities] to be met, and trigger the [fire risk warning for residential buildings in old urban areas of cities] rule tuple through a chain reaction, and output the fire risk warning defense guide for residential buildings in old urban areas of cities, that is, it is strictly forbidden to build or place residential buildings randomly, keep fire passages unobstructed, and check fire facilities, etc., thereby forming a chain reasoning.

[0138] 3. Construction of tuple model and knowledge graph of earth environment resources;

[0139] In some embodiments, the earth environment resource tuple model can also provide an effective data expression and management method for constructing an earth resource environment knowledge graph.

[0140] Concept tuples are used to define and describe basic concepts and classifications in the field of earth resources and environment. In the knowledge graph, concept tuples constitute the architecture and classification system of the graph, and determine the hierarchical relationship between different entity types and concepts in the graph. These concept tuples help build a unified spatiotemporal basic framework for the knowledge graph, making the organization of data and information more systematic and logical.

[0141] Instance tuples represent specific entities in the field of earth resources and environment. In the knowledge graph, these tuples are equivalent to the nodes of the graph, and each node represents a specific entity or thing. For example, an instance tuple about a specific forest area may contain specific information such as the tree species, soil type, and climate conditions in the area. These instance tuples provide rich entity data for the knowledge graph, enabling it to more accurately reflect the complexity and diversity of the real world.

[0142] Rule tuples contain information representing the relationships and logical rules between earth resources and environmental data. In the knowledge graph, these tuples provide key information about the interactions and dependencies between entities. Rule tuples enable knowledge graphs to perform dynamic reasoning and pattern recognition, providing strong support for understanding complex interactions between entities.

[0143] In short, the concept tuple, instance tuple and rule tuple in the earth resources and environment tuple model together constitute the core elements of the earth resources and environment knowledge graph. It not only provides structured data and conceptual framework for the earth resources and environment knowledge graph, but also gives the knowledge graph dynamic reasoning and analysis capabilities, making the earth resources and environment knowledge graph a composite intelligent system that can effectively support earth resources and environment decision-making analysis.

[0144] 4. Examples of application of tuple representation of earth resources and environment.

[0145] After the earth resources and environment tuple model is successfully constructed, practical applications can be carried out based on this model. The following is a specific explanation from the three application directions of information query, knowledge reasoning and knowledge computing.

[0146] 1) Information Query

[0147] Query the attribute information of a geographic entity [city A region B community C residential building-0001 entity 18], such as Figure 1DAs shown, the remote sensing image patch information of [a certain city A certain area B certain community C residential building -0001 entity 18] can be queried, wherein the remote sensing image patch information includes a spatial feature 182 of "a certain city A certain area B 116.97634, 40.28183" and a geometric feature 184 of "polygon", the construction year is "built in 1980", the age is "high", and the building materials are "brick, sand, stone, cement, wood, tile, concrete, etc.".

[0148] 2) Knowledge reasoning (knowledge warning) means that the process can be completed through logical judgment (yes / no) reasoning without the need for complex calculations between spatiotemporal data.

[0149] like Fig. 1I As shown, a new temperature entity 53 [the temperature in area D in city A reached 38°C at 18:00:00 on August 15, 2023] is created; the temperature entity is associated with the geographical concept of "temperature", and then based on "temperature", it is associated with the rule tuple [high temperature orange warning signal 51]; when the temperature reaches "38°C", the trigger condition of the rule tuple [high temperature orange warning signal 51] is met, and the response action is executed.

[0150] The execution of the response action satisfies the triggering condition of the rule tuple [early warning of fire risk of old residential buildings in cities 52], and the response action of the rule tuple [early warning of fire risk of old residential buildings in cities 52] is executed; the residential building entities belonging to old buildings are retrieved, among which the geographical entity [residential building C in a certain area B in a certain city - 0001 entity 54] belongs to an old building with a high degree of oldness; after the rule tuple [early warning of fire risk of old residential buildings in cities 52] is executed, a warning message is given: "Orange warning weather for high temperature, pay attention to prevent fire", and the geographical entity [residential building C in a certain area B in a certain city - 0001 entity 54] receives the warning message.

[0151] It should be noted that, during implementation, the above-mentioned temperature entity 53 [the temperature in a certain area D in a certain city A reached 38°C at 18:00:00 on August 15, 2023] may correspond to the target instance tuple of step S300 in the aforementioned embodiment, the geographical concept "temperature" may correspond to the target geographical concept of step S301 in the aforementioned embodiment, the rule tuple [high temperature orange warning signal 51] corresponds to the signal rule tuple of step S301 in the aforementioned embodiment, the rule tuple [fire risk warning for old residential buildings in the city 52] corresponds to the warning rule tuple of step S310 in the aforementioned embodiment, and the geographical entity [residential building C in a certain area B in a certain city A-0001 entity 54] corresponds to the ground object to be warned in step S312 in the aforementioned embodiment.

[0152] 3) Knowledge computing

[0153] like Fig. 9As shown, when the fire hazard risk calculation is triggered by the designated target area "a certain city A certain area B certain community C residential building-0001 entity 90", first, the target area spatial information (spatial feature data) is determined based on the instance tuple corresponding to the target area associated with the target area; then, based on the target area time determined when the previous task is triggered and the target area spatial information, the trigger condition of the [fire hazard risk calculation 91] rule tuple is determined to start executing the response action; further, the response action of the [fire hazard risk calculation 91] rule tuple calls the "risk calculation action function 93", and based on the input parameters of the "risk calculation action function 93", the instance tuple [urban old residential building fire risk factor 92] corresponding to the input parameters is called; finally, the instance tuple [urban old residential building fire risk factor 92] is used as the data base, and according to the algorithm logic of the "risk calculation action function 93", the fire risk value of "a certain city A certain area B certain community C residential building-0001 entity 90" is output. In some embodiments, the calculation of the fire hazard risk can be an automatically triggered calculation task or a manually triggered calculation task.

[0154] It should be noted that, during implementation, the above-mentioned instance tuple [city A, region B, community C, residential building - 0001 entity 90] may correspond to the instance tuple corresponding to the second ground feature object of step S401 in the aforementioned embodiment, the rule tuple [fire hazard risk calculation 91] may correspond to the rule tuple corresponding to the risk assessment of step S401 in the aforementioned embodiment, and the instance tuple [urban old residential building fire risk factor 92] may correspond to the instance tuple corresponding to the input parameter of step S404 in the aforementioned embodiment.

[0155] According to the above implementation process, the tuple representation of earth resources in the embodiment of the present application provides a unified data expression and management method for the earth resource environment and its data application, and also expresses expert knowledge in the same form, so that efficient instance tuple retrieval query can be carried out, supporting simple reasoning and reasoning that requires further analysis and calculation, which is the technical foundation for realizing the smart earth and building the earth brain. Based on the embodiment of the present application, the following beneficial effects can be obtained:

[0156] By establishing a description framework with a unified spatiotemporal benchmark, the organic integration of earth resource and environmental data and domain expert knowledge is achieved, providing a technical approach for the perception, understanding, analysis and calculation of tasks in spatiotemporal scenarios.

[0157] It is applicable to various mission scenarios of earth resources and environment, such as risk prediction analysis, development trend analysis and refined computational analysis, and provides an organic technical support system for intelligent judgment based on experience or models such as perception, cognition, monitoring, prediction and evaluation related to the development status of earth resources and environment.

[0158] Based on the foregoing embodiments, the embodiments of the present application provide a device for representing the earth's resources and environment in a grouped manner, which includes the modules included, and the units included in the modules, etc., and can be implemented by a processor in a computer device; of course, it can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA), etc.

[0159] The present application embodiment provides a device for representing the earth resources and environment in a tuple form, such as Fig.10 As shown, the device 1000 includes:

[0160] The first determination module 1001 is used to determine the concept tuple expressing the semantic relationship of earth resources and environment based on various geographical concepts in earth resources and environment data and the semantic hierarchical relationship between geographical concepts;

[0161] A second determination module 1002 is used to determine, based on each geographical concept in the concept tuple framework and the earth resources and environment data, an instance tuple of a physical phenomenon corresponding to each geographical concept;

[0162] The third determination module 1003 is used to determine the rule tuple corresponding to the geographical concept based on the relationship between each of the geographical concepts and the domain expert knowledge in the concept tuple;

[0163] The fourth determination module 1004 is used to determine the earth resources and environment tuple model based on the concept tuple, all instance tuples and all rule tuples; wherein the earth resources and environment tuple model is used to represent earth resources and environment data and domain expert knowledge; the earth resources and environment data are represented by the concept tuple and the instance tuple, and the domain expert knowledge is represented by the concept tuple and the rule tuple.

[0164] In some embodiments, the third determination module includes: a first determination unit, used to determine the domain expert knowledge corresponding to each geographic concept in the concept tuple framework; a second determination unit, used to determine the rule tuple name and rule tuple triggering condition corresponding to the domain expert knowledge based on each of the domain expert knowledge; wherein the rule tuple name is used to uniquely identify the rule tuple; a third determination unit, used to determine the response action corresponding to the rule tuple triggering condition based on the rule tuple triggering condition; and a fourth determination unit, used to determine the corresponding rule tuple based on each of the rule tuple names and the triggering condition and response action of the corresponding rule tuple name.

[0165] In some embodiments, the device also includes: a fifth determination module, which is used to determine the target instance tuple corresponding to the updated earth resources and environment data based on the earth resources and environment tuple model when the earth resources and environment data is updated; a sixth determination module, which is used to determine the target geographical concept corresponding to the target instance tuple, and determine the signal rule tuple corresponding to the target geographical concept; and a first execution module, which is used to execute the response action of the signal rule tuple based on the data of the target instance tuple and when it is determined that the trigger condition of the signal rule tuple is met.

[0166] In some embodiments, the device also includes: a second execution module, which is used to execute the first response action of the warning rule tuple when the response action of the signal rule tuple causes the triggering condition of the warning rule tuple to be met; a seventh determination module, which is used to determine the candidate first ground object based on the first response action; an eighth determination module, which, after the first response action is executed, executes the second response action corresponding to the warning rule tuple based on the candidate first ground object to determine the ground object to be warned; and an obtaining module, which, after the second response action is executed, executes the third response action corresponding to the warning rule tuple to obtain the warning information of the ground object to be warned.

[0167] In some embodiments, the device also includes: an acquisition module for acquiring a second geographical object to be risk assessed at a preset time; a ninth determination module for determining, based on the earth resources and environment tuple model, the instance tuple corresponding to the second geographical object and the rule tuple corresponding to the risk assessment; a tenth determination module for determining, based on the data of the instance tuple corresponding to the second geographical object, the spatial feature data corresponding to the second geographical object; a third execution module for executing a response action of the rule tuple based on the spatial feature data and preset time data corresponding to the second geographical object; an eleventh determination module for determining, based on the input parameters of the response action, the instance tuple corresponding to the input parameters; a twelfth determination module for determining the output of the response action based on the data of the instance tuple corresponding to the input parameters; the output is the risk value of the second geographical object.

[0168] In some embodiments, the device also includes: a thirteenth determination module, used to determine the pyramid index map structure corresponding to the geographic information data in the remote sensing image of the second geographic object based on the remote sensing image data of the second geographic object; a fourteenth determination module, used to determine the tile code corresponding to the pyramid index map structure of the second geographic object based on the geographic coordinates and geographic coding function of the second geographic object; and a fifteenth determination module, used to determine the spatial feature data of the geographic object based on the tile code and the pyramid index map structure of the second geographic object.

[0169] In some embodiments, the thirteenth determination module includes: a conversion unit, used to convert the remote sensing image data of the second geographical object into GeoJSON format data; a fifth determination unit, used to determine the geographical information data in the string format based on the geographical information data in the GeoJSON format data; a mapping unit, used to map the geographical information data in the string format to a spatial grid based on a gridded geocoding algorithm; and a sixth determination unit, used to determine the pyramid index map structure corresponding to the geographical information data of the second geographical object based on the spatial grid.

[0170] The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. In some embodiments, the functions or modules included in the device provided in the embodiment of the present application can be used to execute the method described in the above method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.

[0171] It should be noted that in the embodiment of the present application, if the above method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific hardware, software or firmware, or any combination of hardware, software, and firmware.

[0172] An embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, some or all of the steps in the above method are implemented.

[0173] The embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, some or all of the steps in the above method are implemented. The computer-readable storage medium can be transient or non-transient.

[0174] An embodiment of the present application provides a computer program, including a computer-readable code. When the computer-readable code is run in a computer device, a processor in the computer device executes some or all of the steps for implementing the above method.

[0175] The embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, some or all of the steps in the above method are implemented. The computer program product can be implemented specifically by hardware, software or a combination thereof. In some embodiments, the computer program product is specifically embodied as a computer storage medium, and in other embodiments, the computer program product is specifically embodied as a software product, such as a software development kit (SDK) and the like.

[0176] It should be noted here that the description of the various embodiments above tends to emphasize the differences between the various embodiments, and the same or similar aspects can be referenced to each other. The description of the above device, storage medium, computer program and computer program product embodiments is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the embodiments of the device, storage medium, computer program and computer program product of this application, please refer to the description of the method embodiment of this application for understanding.

[0177] The present application embodiment provides a computer device, such as Fig.11 As shown, the hardware entity of the computer device 1100 includes: a processor 1101, a communication interface 1102 and a memory 1103, wherein: the processor 1101 generally controls the overall operation of the computer device 1100. The communication interface 1102 can enable the computer device to communicate with other terminals or servers through a network. The memory 1103 is configured to store instructions and applications executable by the processor 1101, and can also cache data to be processed or processed by the processor 1101 and each module in the computer device 1100 (for example, image data, audio data, voice communication data and video communication data), which can be implemented by flash memory (FLASH) or random access memory (Random Access Memory, RAM). Data transmission can be carried out between the processor 1101, the communication interface 1102 and the memory 1103 through the bus 1104.

[0178] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the serial number of each step / process mentioned above does not mean the order of execution, and the execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The serial numbers of the embodiments of the present application mentioned above are for description only and do not represent the advantages and disadvantages of the embodiments.

[0179] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0180] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0181] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, the functional units in the embodiments of the present application may be all integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0182] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0183] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0184] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for representing earth resources and environment in tuple form, characterized in that: The method comprises: Based on various geographical concepts in earth resources and environment data and the semantic hierarchical relationships between geographical concepts, the concept tuples expressing the semantic relationships of earth resources and environment are determined; Based on each geographical concept in the framework of the concept tuple and the earth resources and environment data, determining an instance tuple of a physical phenomenon corresponding to each geographical concept; Based on the relationship between each of the geographic concepts in the concept tuple and the domain expert knowledge, determining a rule tuple corresponding to the geographic concept; Determine a tuple model of earth resources and environment based on the concept tuple, all instance tuples and all rule tuples; The earth resource environment tuple model is used to represent earth resource environment data and domain expert knowledge; the earth resource environment data is represented by the concept tuple and the instance tuple, and the domain expert knowledge is represented by the concept tuple and the rule tuple; The method further comprises: In the case where the earth resources and environment data are updated, based on the earth resources and environment tuple model, determining a target instance tuple corresponding to the updated earth resources and environment data; Determining a target geographic concept corresponding to the target instance tuple, and determining a signal rule tuple corresponding to the target geographic concept; Based on the data of the target instance tuple, when it is determined that the triggering condition of the signal rule tuple is satisfied, executing the response action of the signal rule tuple; When the response action of the signal rule tuple causes the triggering condition of the warning rule tuple to be satisfied, executing the first response action of the warning rule tuple; Based on the first response action, determining a candidate first ground feature object; After the first response action is executed, based on the candidate first ground object, the second response action corresponding to the warning rule tuple is executed to determine the ground object to be warned; After the second response action is executed, a third response action corresponding to the warning rule tuple is executed to obtain warning information of the ground feature to be warned.

2. Based on the method described in claim 1, it is characterized in that The determining of the rule tuple corresponding to the geographical concept based on the relationship between each geographical concept and the domain expert knowledge in the concept tuple comprises: Determine the domain expert knowledge corresponding to each geographic concept in the framework of the concept tuple; Based on each of the domain expert knowledge, determine the rule tuple name and rule tuple triggering condition corresponding to the domain expert knowledge; wherein the rule tuple name is used to uniquely identify the rule tuple; Based on the rule tuple triggering condition, determining a response action corresponding to the rule tuple triggering condition; Based on each of the rule tuple names and the triggering conditions and response actions corresponding to the rule tuple names, the corresponding rule tuple is determined.

3. Based on the method described in claim 1 or 2, it is characterized in that The method further comprises: Acquire a second ground feature object to be risk assessed at a preset time; Based on the earth resources and environment tuple model, determining an instance tuple corresponding to the second ground feature object and a rule tuple corresponding to the risk assessment; Determining spatial feature data corresponding to the second geographical object based on data of the instance tuple corresponding to the second geographical object; Execute a response action of the rule tuple based on the spatial feature data and the preset time data corresponding to the second ground object; Based on the input parameters of the response action, determining the instance tuple corresponding to the input parameters; Based on the data of the instance tuple corresponding to the input parameter, the output of the response action is determined; the output is the risk value of the second ground feature object.

4. Based on the method described in claim 3, it is characterized in that The method for determining the spatial feature data of the instance tuple corresponding to the second ground feature object comprises: Based on the remote sensing image data of the second land object, determining a pyramid index map structure corresponding to the geographic information data in the remote sensing image of the second land object; Determine a tile code corresponding to the pyramid index map structure of the second geographical feature object based on the geographical coordinates and the geographical coding function of the second geographical feature object; Based on the tile code and the pyramid index map structure of the second ground object, spatial feature data of the second ground object is determined.

5. Based on the method described in claim 4, it is characterized in that The step of determining the pyramid index map structure corresponding to the geographic information data in the remote sensing image of the second land object based on the remote sensing image data of the second land object comprises: Converting the remote sensing image data of the second land object into GeoJSON format data; Based on the geographic information data in the GeoJSON format data, determine the geographic information data in a string format; Based on a gridded geocoding algorithm, mapping the geographic information data in the string format to a spatial grid; Based on the spatial grid, a pyramid index map structure corresponding to the geographic information data of the second land feature object is determined.

6. A device for representing earth resources and environment in a tuple form, characterized in that: The device comprises: The first determination module is used to determine the concept tuple expressing the semantic relationship of earth resources and environment based on various geographical concepts in earth resources and environment data and the semantic hierarchical relationship between geographical concepts; The second determination module is used to determine the instance tuple of the physical phenomenon corresponding to each geographical concept based on each geographical concept in the concept tuple framework and the earth resources and environmental data; the third determination module is used to determine the rule tuple corresponding to the geographical concept based on the relationship between each geographical concept and the domain expert knowledge in the concept tuple; A fourth determination module, used to determine the earth resources environment tuple model based on the concept tuple, all instance tuples and all rule tuples; The earth resource environment tuple model is used to represent earth resource environment data and domain expert knowledge; the earth resource environment data is represented by the concept tuple and the instance tuple, and the domain expert knowledge is represented by the concept tuple and the rule tuple; The device also includes: A fifth determination module is used to determine, when the earth resources and environment data is updated, a target instance tuple corresponding to the updated earth resources and environment data based on the earth resources and environment tuple model; a sixth determination module, configured to determine a target geographical concept corresponding to the target instance tuple, and to determine a signal rule tuple corresponding to the target geographical concept; A first execution module, configured to execute a response action of the signal rule tuple based on the data of the target instance tuple and when it is determined that a trigger condition of the signal rule tuple is satisfied; A second execution module, configured to execute a first response action of the warning rule tuple when a triggering condition of the warning rule tuple is satisfied due to a response action of the signal rule tuple; A seventh determination module, configured to determine a candidate first ground feature object based on the first response action; An eighth determination module, configured to, after the first response action is executed, execute a second response action corresponding to the warning rule tuple based on the candidate first ground object to determine the ground object to be warned; The obtaining module is used to execute the third response action corresponding to the warning rule tuple after the second response action is executed, so as to obtain the warning information of the ground object to be warned.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the program, the steps in the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images