Dynamic knowledge graph construction method and system based on big data intelligence

Abstract

The invention discloses a dynamic knowledge graph construction method and system based on big data intelligence, and the method comprises the steps: training a classifier according to satellite data of which categories are marked, so that the classifier can learn the difference between various categories, and the categories comprise vegetation, water, buildings and / or geological activities; obtaining and preprocessing new satellite data, generating preprocessed new satellite data, setting an anomaly judgment model of the satellite data, and calculating a composite anomaly value of the preprocessed satellite data in each category; if the composite abnormal value is greater than a preset abnormal threshold value, marking the satellite data in the corresponding category as an abnormal state; latest satellite data is obtained in real time, classification and abnormal state marking are carried out, and therefore construction of the dynamic knowledge graph is completed.

Description

Technical Field

[0001] The present invention belongs to the technical field of building a knowledge base of satellite data, and more specifically, relates to a method and system for building a dynamic knowledge graph based on big data intelligence. Background Art

[0002] Knowledge Graph is a model that organizes information into a graph structure, where nodes represent entities or concepts and edges represent the relationships between them. It can effectively represent complex data relationships and semantics and is widely used in search engines, recommendation systems, natural language processing and other fields.

[0003] The key elements of a knowledge graph include: Nodes: Represent entities or concepts, such as people, places, events, companies, etc.

[0004] Edges: Represents the relationship between nodes, such as "employee-employment-company", "book-author-writer", etc.

[0005] Attributes: Additional information about a node or edge, such as a person’s name, age, company founding date, etc.

[0006] Types: Classify nodes and edges to better organize and query information.

[0007] However, there is currently no technical solution that can detect abnormal conditions in the knowledge graph of satellite data. Summary of the invention

[0008] In order to solve the above technical problems, the present invention proposes a method for constructing a dynamic knowledge graph based on big data intelligence, wherein the big data intelligence is satellite data, including: Based on satellite data with labeled categories, a classifier is trained to learn the differences between various categories, wherein the categories include vegetation, water bodies, buildings and / or geological activities; Acquire new satellite data and preprocess them to generate new preprocessed satellite data, set up an abnormality judgment model for satellite data, and calculate the composite abnormal value of the preprocessed satellite data in each category; If the composite abnormal value is greater than a preset abnormal threshold, the satellite data in the corresponding category is marked as abnormal; Acquire the latest satellite data in real time, classify it and mark abnormal status, so as to complete the construction of dynamic knowledge graph.

[0009] Furthermore, the satellite data anomaly judgment model includes: , in, The preprocessed satellite data The composite outlier value of is the number of categories of satellite data, is the weight of the composite outlier, For the The adjustment factor for the first outlier of the satellite data in each category, For the The first outlier of the satellite data of each category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The second outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The third outlier in the satellite data for each category.

[0010] Furthermore, calculate the The first outlier of the satellite data of each category include: , in, is the first adjustment factor for the first outlier, is the second adjustment factor for the first outlier, is the third adjustment factor for the first outlier, is the fourth adjustment factor for the first outlier, is the fifth adjustment factor for the first outlier.

[0011] Furthermore, calculate the The second outlier of the satellite data of the category include: , in, is the first adjustment factor for the second outlier, is the second adjustment factor for the second outlier, is the third adjustment factor for the second outlier, is the fourth adjustment factor for the second outlier, is the fifth adjustment factor for the second outlier, is the sixth adjustment factor for the second outlier.

[0012] Furthermore, calculate the The third outlier of the satellite data include: , in, is the first adjustment factor for the third outlier, is the second adjustment factor for the third outlier, is the third adjustment factor for the third outlier, is the fourth adjustment factor for the third outlier, is the fifth adjustment factor for the third outlier, is the sixth adjustment factor for the third outlier.

[0013] Furthermore, the abnormal state includes: When the category is vegetation, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the vegetation is destroyed; When the category is water body, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the water body is polluted; When the category is building, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the building is damaged; When the category is geological activity, if the composite anomaly value is greater than a preset anomaly threshold, the anomaly state is crustal movement.

[0014] The present invention also proposes a dynamic knowledge graph construction system based on big data intelligence, wherein the big data intelligence is satellite data, including: A training classifier module is used to train a classifier based on satellite data with labeled categories so that the classifier can learn the differences between various categories, wherein the categories include: vegetation, water bodies, buildings and / or geological activities; Setting up a model module for acquiring new satellite data and preprocessing it, generating new preprocessed satellite data, setting up an anomaly judgment model for satellite data, and calculating composite anomaly values ​​of preprocessed satellite data in each category; A detection module, configured to mark the satellite data in the corresponding category as abnormal if the composite abnormal value is greater than a preset abnormal threshold; The knowledge graph construction module is used to obtain the latest satellite data in real time, classify it and mark abnormal status, thereby completing the construction of a dynamic knowledge graph.

[0015] Furthermore, the satellite data anomaly judgment model includes: , in, The preprocessed satellite data The composite outlier value of is the number of categories of satellite data, is the weight of the composite outlier, For the The adjustment factor for the first outlier of the satellite data in each category, For the The first outlier of the satellite data of each category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The second outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The third outlier in the satellite data for each category.

[0016] Furthermore, calculate the The first outlier of the satellite data of each category include: , in, is the first adjustment factor for the first outlier, is the second adjustment factor for the first outlier, is the third adjustment factor for the first outlier, is the fourth adjustment factor for the first outlier, is the fifth adjustment factor for the first outlier.

[0017] Furthermore, calculate the The second outlier of the satellite data of the category include: , in, is the first adjustment factor for the second outlier, is the second adjustment factor for the second outlier, is the third adjustment factor for the second outlier, is the fourth adjustment factor for the second outlier, is the fifth adjustment factor for the second outlier, is the sixth adjustment factor for the second outlier.

[0018] In general, the above technical solution conceived by the present invention has the following beneficial effects compared with the prior art: The invention obtains new satellite data and performs preprocessing to generate new satellite data after preprocessing, sets an abnormal judgment model for satellite data, and calculates the composite abnormal value of the preprocessed satellite data in each category; if the composite abnormal value is greater than a preset abnormal threshold, the satellite data in the corresponding category is marked as abnormal; the latest satellite data is obtained in real time, and classified and abnormal state marked, thereby completing the construction of a dynamic knowledge graph. Through the above technical solution, the present invention can automatically identify the categories in satellite data, and give abnormal states according to the satellite data in each category. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of the method of embodiment 1 of the present invention; Figure 2 It is a structural diagram of the system of embodiment 2 of the present invention. DETAILED DESCRIPTION

[0020] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0021] The method provided by the present invention can be implemented in the following terminal environment, and the terminal may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, and the instruction is loaded and executed by the processor to implement the method described in the following embodiment.

[0022] The processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts of the entire terminal, and executes various functions of the terminal and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and calling data stored in the storage medium.

[0023] The storage medium may include a random access memory (RAM) or a read-only memory (ROM). The storage medium may be used to store instructions, programs, codes, code sets or instructions.

[0024] The display screen is used to display the user interface of each application.

[0025] In addition, those skilled in the art can understand that the structure of the above terminal does not constitute a limitation on the terminal, and the terminal may include more or fewer components, or combine certain components, or arrange the components differently. For example, the terminal also includes components such as a radio frequency circuit, an input unit, a sensor, an audio circuit, and a power supply, which will not be described in detail here.

[0026] Example 1 like Figure 1 As shown, an embodiment of the present invention provides a method for constructing a dynamic knowledge graph based on big data intelligence, wherein the big data intelligence is satellite data, including: Step 101, training a classifier based on satellite data with labeled categories so that it can learn the differences between various categories, wherein the categories include: vegetation, water bodies, buildings and / or geological activities; Step 102, acquiring new satellite data and preprocessing it to generate preprocessed new satellite data, setting an abnormality judgment model for satellite data, and calculating a composite abnormal value of the preprocessed satellite data in each category; Step 103, if the composite abnormal value is greater than a preset abnormal threshold, the satellite data in the corresponding category is marked as abnormal; Specifically, the satellite data anomaly judgment model includes: , in, The preprocessed satellite data The composite outlier value of is the number of categories of satellite data, is the weight of the composite outlier, For the The adjustment factor for the first outlier of the satellite data in each category, For the The first outlier of the satellite data of each category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The second outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The third outlier of satellite data in deep learning and neural networks, The (Rectified Linear Unit) function is an activation function, which mainly increases the nonlinearity of the network and helps solve the gradient disappearance problem.

[0027] Specifically, calculate The first outlier of the satellite data of each category include: , in, is the first adjustment factor for the first outlier, is the second adjustment factor for the first outlier, is the third adjustment factor for the first outlier, is the fourth adjustment factor for the first outlier, is the fifth adjustment factor for the first outlier.

[0028] Specifically, calculate The second outlier of the satellite data of the category include: , in, is the first adjustment factor for the second outlier, is the second adjustment factor for the second outlier, is the third adjustment factor for the second outlier, is the fourth adjustment factor for the second outlier, is the fifth adjustment factor for the second outlier, is the sixth adjustment factor for the second outlier.

[0029] Specifically, calculate The third outlier of the satellite data include: , in, is the first adjustment factor for the third outlier, is the second adjustment factor for the third outlier, is the third adjustment factor for the third outlier, is the fourth adjustment factor for the third outlier, is the fifth adjustment factor for the third outlier, is the sixth adjustment factor for the third outlier.

[0030] In this embodiment, all adjustment factors and weights are fitted by the gradient descent method.

[0031] Step 104, obtain the latest satellite data in real time, and classify and mark abnormal status, so as to complete the construction of the dynamic knowledge graph.

[0032] Specifically, the abnormal state includes: When the category is vegetation, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the vegetation is destroyed; When the category is water body, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the water body is polluted; When the category is building, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the building is damaged; When the category is geological activity, if the composite anomaly value is greater than a preset anomaly threshold, the anomaly state is crustal movement.

[0033] Example 2 like Figure 2 As shown, an embodiment of the present invention further provides a dynamic knowledge graph construction system based on big data intelligence, wherein the big data intelligence is satellite data, including: A training classifier module is used to train a classifier based on satellite data with labeled categories so that the classifier can learn the differences between various categories, wherein the categories include: vegetation, water bodies, buildings and / or geological activities; Setting up a model module for acquiring new satellite data and preprocessing it, generating new preprocessed satellite data, setting up an anomaly judgment model for satellite data, and calculating composite anomaly values ​​of preprocessed satellite data in each category; A detection module, configured to mark the satellite data in the corresponding category as abnormal if the composite abnormal value is greater than a preset abnormal threshold; Specifically, the satellite data anomaly judgment model includes: , in, The preprocessed satellite data The composite outlier value of is the number of categories of satellite data, is the weight of the composite outlier, For the The adjustment factor for the first outlier of the satellite data in each category, For the The first outlier of the satellite data of each category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The second outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The third outlier in the satellite data for each category.

[0034] Specifically, calculate The first outlier of the satellite data of each category include: , in, is the first adjustment factor for the first outlier, is the second adjustment factor for the first outlier, is the third adjustment factor for the first outlier, is the fourth adjustment factor for the first outlier, is the fifth adjustment factor for the first outlier.

[0035] Specifically, calculate The second outlier of the satellite data of the category include: , in, is the first adjustment factor for the second outlier, is the second adjustment factor for the second outlier, is the third adjustment factor for the second outlier, is the fourth adjustment factor for the second outlier, is the fifth adjustment factor for the second outlier, is the sixth adjustment factor for the second outlier.

[0036] Specifically, calculate The third outlier of the satellite data include: , in, is the first adjustment factor for the third outlier, is the second adjustment factor for the third outlier, is the third adjustment factor for the third outlier, is the fourth adjustment factor for the third outlier, is the fifth adjustment factor for the third outlier, is the sixth adjustment factor for the third outlier.

[0037] In this embodiment, all adjustment factors and weights are fitted by the gradient descent method.

[0038] The knowledge graph construction module is used to obtain the latest satellite data in real time, classify it and mark abnormal status, thereby completing the construction of a dynamic knowledge graph.

[0039] Specifically, the abnormal state includes: When the category is vegetation, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the vegetation is destroyed; When the category is water body, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the water body is polluted; When the category is building, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the building is damaged; When the category is geological activity, if the composite anomaly value is greater than a preset anomaly threshold, the anomaly state is crustal movement.

[0040] Example 3 An embodiment of the present invention also proposes a storage medium storing multiple instructions, wherein the instructions are used to implement the method for constructing a dynamic knowledge graph based on big data intelligence.

[0041] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0042] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps: Step 101, training a classifier based on satellite data with labeled categories so that the classifier can learn the differences between various categories, wherein the categories include: vegetation, water bodies, buildings and / or geological activities; Step 102, acquiring new satellite data and preprocessing it to generate preprocessed new satellite data, setting an abnormality judgment model for satellite data, and calculating a composite abnormal value of the preprocessed satellite data in each category; Step 103, if the composite abnormal value is greater than a preset abnormal threshold, the satellite data in the corresponding category is marked as abnormal; Specifically, the satellite data anomaly judgment model includes: , in, The preprocessed satellite data The composite outlier value of is the number of categories of satellite data, is the weight of the composite outlier, For the The adjustment factor for the first outlier of the satellite data in each category, For the The first outlier of the satellite data of each category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The second outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The third outlier in the satellite data for each category.

[0043] Specifically, calculate The first outlier of the satellite data of each category include: , in, is the first adjustment factor for the first outlier, is the second adjustment factor for the first outlier, is the third adjustment factor for the first outlier, is the fourth adjustment factor for the first outlier, is the fifth adjustment factor for the first outlier.

[0044] Specifically, calculate The second outlier of the satellite data of the category include: , in, is the first adjustment factor for the second outlier, is the second adjustment factor for the second outlier, is the third adjustment factor for the second outlier, is the fourth adjustment factor for the second outlier, is the fifth adjustment factor for the second outlier, is the sixth adjustment factor for the second outlier.

[0045] Specifically, calculate The third outlier of the satellite data include: , in, is the first adjustment factor for the third outlier, is the second adjustment factor for the third outlier, is the third adjustment factor for the third outlier, is the fourth adjustment factor for the third outlier, is the fifth adjustment factor for the third outlier, is the sixth adjustment factor for the third outlier.

[0046] In this embodiment, all adjustment factors and weights are fitted by the gradient descent method.

[0047] Step 104, obtain the latest satellite data in real time, and classify and mark abnormal status, so as to complete the construction of the dynamic knowledge graph.

[0048] Specifically, the abnormal state includes: When the category is vegetation, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the vegetation is destroyed; When the category is water body, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the water body is polluted; When the category is building, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the building is damaged; When the category is geological activity, if the composite anomaly value is greater than a preset anomaly threshold, the anomaly state is crustal movement.

[0049] Example 4 An embodiment of the present invention also proposes an electronic device, including a processor and a storage medium connected to the processor, wherein the storage medium stores multiple instructions, and the instructions can be loaded and executed by the processor so that the processor can execute the method for constructing a dynamic knowledge graph based on big data intelligence.

[0050] Specifically, the electronic device of this embodiment may be a computer terminal, and the computer terminal may include: one or more processors, and a storage medium.

[0051] Among them, the storage medium can be used to store software programs and modules, such as a dynamic knowledge graph construction method based on big data intelligence in an embodiment of the present invention, corresponding program instructions / modules, and the processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium, that is, realizing the above-mentioned method for constructing a dynamic knowledge graph based on big data intelligence. The storage medium may include high-speed random storage media, and may also include non-volatile storage media, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include storage media remotely arranged relative to the processor, and these remote storage media may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0052] The processor may call the information and application program stored in the storage medium through the transmission system to perform the following steps: Step 101, training a classifier based on satellite data with labeled categories so that the classifier can learn the differences between various categories, wherein the categories include: vegetation, water bodies, buildings and / or geological activities; Step 102, acquiring new satellite data and preprocessing it to generate preprocessed new satellite data, setting an abnormality judgment model for satellite data, and calculating a composite abnormal value of the preprocessed satellite data in each category; Step 103, if the composite abnormal value is greater than a preset abnormal threshold, the satellite data in the corresponding category is marked as abnormal; Specifically, the satellite data anomaly judgment model includes: , in, The preprocessed satellite data The composite outlier value of is the number of categories of satellite data, is the weight of the composite outlier, For the The adjustment factor for the first outlier of the satellite data in each category, For the The first outlier of the satellite data of each category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The second outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The third outlier in the satellite data for each category.

[0053] Specifically, calculate The first outlier of the satellite data of each category include: , in, is the first adjustment factor for the first outlier, is the second adjustment factor for the first outlier, is the third adjustment factor for the first outlier, is the fourth adjustment factor for the first outlier, is the fifth adjustment factor for the first outlier.

[0054] Specifically, calculate The second outlier of the satellite data of the category include: , in, is the first adjustment factor for the second outlier, is the second adjustment factor for the second outlier, is the third adjustment factor for the second outlier, is the fourth adjustment factor for the second outlier, is the fifth adjustment factor for the second outlier, is the sixth adjustment factor for the second outlier.

[0055] Specifically, calculate The third outlier of the satellite data include: , in, is the first adjustment factor for the third outlier, is the second adjustment factor for the third outlier, is the third adjustment factor for the third outlier, is the fourth adjustment factor for the third outlier, is the fifth adjustment factor for the third outlier, is the sixth adjustment factor for the third outlier.

[0056] In this embodiment, all adjustment factors and weights are fitted by the gradient descent method.

[0057] Step 104, obtain the latest satellite data in real time, and classify and mark abnormal status, so as to complete the construction of the dynamic knowledge graph.

[0058] Specifically, the abnormal state includes: When the category is vegetation, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the vegetation is destroyed; When the category is water body, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the water body is polluted; When the category is building, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the building is damaged; When the category is geological activity, if the composite anomaly value is greater than a preset anomaly threshold, the anomaly state is crustal movement.

[0059] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0060] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0061] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system 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. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0062] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, 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 solution of this embodiment.

[0063] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0064] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only storage medium (ROM, Read-Only Memory), random access storage medium (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0065] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A method for constructing a dynamic knowledge graph based on big data intelligence, wherein the big data intelligence is satellite data, characterized in that: include: Based on satellite data with labeled categories, a classifier is trained to learn the differences between various categories, wherein the categories include vegetation, water bodies, buildings and / or geological activities; Acquire new satellite data and preprocess them to generate new preprocessed satellite data, set up an abnormality judgment model for satellite data, and calculate the composite abnormal value of the preprocessed satellite data in each category; If the composite abnormal value is greater than a preset abnormal threshold, the satellite data in the corresponding category is marked as abnormal; Acquire the latest satellite data in real time, classify it and mark abnormal status, so as to complete the construction of dynamic knowledge graph.

2. A method for constructing a dynamic knowledge graph based on big data intelligence as claimed in claim 1, characterized in that: The satellite data anomaly judgment model includes: ， in, The preprocessed satellite data The composite outlier value of is the number of categories of satellite data, is the weight of the composite outlier, For the The adjustment factor for the first outlier of the satellite data in each category, For the The first outlier of the satellite data of each category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The second outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The third outlier in the satellite data for each category.

3. A method for constructing a dynamic knowledge graph based on big data intelligence as claimed in claim 2, characterized in that: Calculate the The first outlier of the satellite data of each category include: ， in, is the first adjustment factor for the first outlier, is the second adjustment factor for the first outlier, is the third adjustment factor for the first outlier, is the fourth adjustment factor for the first outlier, is the fifth adjustment factor for the first outlier.

4. A method for constructing a dynamic knowledge graph based on big data intelligence as claimed in claim 2, characterized in that: Calculate the The second outlier of the satellite data of the category include: ， in, is the first adjustment factor for the second outlier, is the second adjustment factor for the second outlier, is the third adjustment factor for the second outlier, is the fourth adjustment factor for the second outlier, is the fifth adjustment factor for the second outlier, is the sixth adjustment factor for the second outlier.

5. A method for constructing a dynamic knowledge graph based on big data intelligence as claimed in claim 2, characterized in that: Calculate the The third outlier of the satellite data include: ， in, is the first adjustment factor for the third outlier, is the second adjustment factor for the third outlier, is the third adjustment factor for the third outlier, is the fourth adjustment factor for the third outlier, is the fifth adjustment factor for the third outlier, is the sixth adjustment factor for the third outlier.

6. A method for constructing a dynamic knowledge graph based on big data intelligence as claimed in claim 1, characterized in that: The abnormal conditions include: When the category is vegetation, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the vegetation is destroyed; When the category is water body, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the water body is polluted; When the category is building, if the composite abnormal value is greater than a preset abnormal threshold, the abnormal state is that the building is damaged; When the category is geological activity, if the composite anomaly value is greater than a preset anomaly threshold, the anomaly state is crustal movement.

7. A dynamic knowledge graph construction system based on big data intelligence, used to implement the dynamic knowledge graph construction method based on big data intelligence according to any one of claims 1 to 6, wherein the big data intelligence is satellite data, characterized in that: include: A training classifier module is used to train a classifier based on satellite data with labeled categories so that the classifier can learn the differences between various categories, wherein the categories include: vegetation, water bodies, buildings and / or geological activities; Setting up a model module for acquiring new satellite data and preprocessing it, generating new preprocessed satellite data, setting up an anomaly judgment model for satellite data, and calculating composite anomaly values ​​of preprocessed satellite data in each category; A detection module, configured to mark the satellite data in the corresponding category as abnormal if the composite abnormal value is greater than a preset abnormal threshold; The knowledge graph construction module is used to obtain the latest satellite data in real time, classify it and mark abnormal status, thereby completing the construction of a dynamic knowledge graph.

8. A dynamic knowledge graph construction system based on big data intelligence as claimed in claim 7, characterized in that: The satellite data anomaly judgment model includes: ， in, The preprocessed satellite data The composite outlier value of is the number of categories of satellite data, is the weight of the composite outlier, For the The adjustment factor for the first outlier of the satellite data in each category, For the The first outlier of the satellite data of each category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The adjustment factor for the second outlier of the satellite data of the category, For the The second outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The adjustment factor for the third outlier of the satellite data of the category, For the The third outlier in the satellite data for each category.

9. A dynamic knowledge graph construction system based on big data intelligence as claimed in claim 8, characterized in that: Calculate the The first outlier of the satellite data of each category include: ， in, is the first adjustment factor for the first outlier, is the second adjustment factor for the first outlier, is the third adjustment factor for the first outlier, is the fourth adjustment factor for the first outlier, is the fifth adjustment factor for the first outlier.

10. A dynamic knowledge graph construction system based on big data intelligence as claimed in claim 8, characterized in that: Calculate the The second outlier of the satellite data of the category include: ， in, is the first adjustment factor for the second outlier, is the second adjustment factor for the second outlier, is the third adjustment factor for the second outlier, is the fourth adjustment factor for the second outlier, is the fifth adjustment factor for the second outlier, is the sixth adjustment factor for the second outlier.

Images