Terrain analysis method and device of knowledge graph based on SAR satellite, and storage medium

Abstract

The invention discloses a terrain analysis method and device based on a knowledge graph of an SAR satellite and a storage medium, and the method comprises the steps: determining a target region, and constructing a knowledge graph corresponding to the target region based on an obtained first SAR image corresponding to the target region; constructing a first-level display interface for displaying the first SAR image and a plurality of entity types in the knowledge graph, and sending the first-level display interface to terminal equipment in communication connection; in response to a first generation instruction sent by the terminal equipment, constructing and sending a second-level display interface used for displaying a second SAR image corresponding to the target entity type, the target entity type, a target entity relationship corresponding to the target entity type and a local knowledge graph corresponding to the target entity type and the target entity relationship; and in response to a second generation instruction sent by the terminal equipment, constructing and sending a third-level display interface used for displaying the knowledge graph and the entity list.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a terrain analysis method, device and storage medium based on a knowledge graph of SAR satellites. Background Art

[0002] SAR images are high-resolution radar images acquired through active microwave remote sensing technology. Unlike optical sensors, SAR satellites do not rely on sunlight. Instead, they create images by emitting electromagnetic waves and receiving backscattered signals from the target area.

[0003] Because SAR images are produced by emitting electromagnetic waves rather than optical imaging, SAR satellites can operate around the clock and are not restricted by lighting conditions. Furthermore, the microwave signals emitted by SAR satellites can penetrate clouds, haze, and smoke, making them suitable for use in most areas. However, SAR images also have many shortcomings. For example, because SAR uses slant-range imaging, geometric distortions such as perspective contraction, overlap, and shadows can occur in SAR images, making them difficult to interpret. Therefore, the pixel-level features of SAR images cannot be directly used by operators, requiring professionals familiar with radar scattering mechanisms and the electromagnetic characteristics of ground objects. In other words, operators cannot directly analyze SAR images visually; they must undergo professional processing before they can be used, making it extremely inconvenient for operators to analyze and use SAR images.

[0004] For example, when using SAR satellites to collect SAR images to perform terrain analysis on a target area, it is impossible to visually determine the type of terrain objects in the target area using only SAR images, nor is it possible to directly determine the correlation between various terrain object types in the target area, resulting in the operator being unable to quickly and accurately perform terrain analysis on the target area.

[0005] Currently, no effective solution has been proposed to the technical problem in the above-mentioned prior art that operators are unable to directly visualize and analyze SAR images, making it impossible to determine the type of terrain objects in the target area through SAR images, nor to directly determine the correlation between various terrain object types in the target area, thereby preventing operators from quickly and accurately performing terrain analysis on the target area. Summary of the Invention

[0006] The embodiments of the present disclosure provide a terrain analysis method, device, and storage medium based on a knowledge graph of a SAR satellite, to at least solve the technical problem in the prior art that operators are unable to directly visualize and analyze SAR images, resulting in an inability to determine the type of terrain objects in the target area through SAR images, and an inability to directly determine the association between various terrain object types in the target area, thereby preventing operators from quickly and accurately performing terrain analysis on the target area.

[0007] According to one aspect of an embodiment of the present disclosure, a terrain analysis method based on a knowledge graph of a SAR satellite is provided, comprising: determining a target area, and constructing a knowledge graph corresponding to the target area based on an acquired first SAR image corresponding to the target area, wherein nodes in the knowledge graph represent entity types and edges represent entity relationships; constructing a first-level display interface for displaying the first SAR image and multiple entity types in the knowledge graph, and sending the first-level display interface to a communication-connected terminal device; in response to a first generation instruction sent by the terminal device, constructing and sending a second-level display interface for displaying a second SAR image corresponding to the target entity type, the target entity type, the target entity relationship corresponding to the target entity type, and a local knowledge graph corresponding to the target entity type and the target entity relationship, wherein the target entity type is used to indicate any one of multiple entity types; and in response to a second generation instruction sent by the terminal device, constructing and sending a third-level display interface for displaying the knowledge graph and an entity list, wherein the entity list includes multiple entity types and entity relationships between the entity types.

[0008] According to another aspect of an embodiment of the present disclosure, a storage medium is further provided, the storage medium including a stored program, wherein when the program is run, a processor executes any one of the above methods.

[0009] According to another aspect of an embodiment of the present disclosure, a terrain analysis device based on a knowledge graph of a SAR satellite is provided, comprising: a knowledge graph construction module for determining a target area and constructing a knowledge graph corresponding to the target area based on an acquired first SAR image corresponding to the target area, wherein nodes in the knowledge graph represent entity types and edges represent entity relationships; a first-level display interface construction module for constructing a first-level display interface for displaying the first SAR image and multiple entity types in the knowledge graph, and sending the first-level display interface to a communication-connected terminal device; a second-level display interface module for constructing and sending a second-level display interface for displaying a second SAR image corresponding to the target entity type, the target entity type, a target entity relationship corresponding to the target entity type, and a local knowledge graph corresponding to the target entity type and the target entity relationship, in response to a first generation instruction sent by the terminal device, wherein the target entity type is used to indicate any one of multiple entity types; and a third-level display interface construction module for constructing and sending a third-level display interface for displaying the knowledge graph and an entity list in response to a second generation instruction sent by the terminal device, wherein the entity list includes multiple entity types and entity relationships between the entity types.

[0010] According to another aspect of the embodiments of the present disclosure, a SAR satellite-based knowledge graph terrain analysis device is also provided, including: a processor; and a memory connected with the processor, configured to provide the processor with instructions to process the following processing steps: determining a target area, and constructing a knowledge graph corresponding to the target area based on a first SAR image corresponding to the target area, wherein a node in the knowledge graph represents an entity type, and an edge represents an entity relationship; constructing a first-level display interface for displaying the first SAR image and a plurality of entity types in the knowledge graph, and sending the first-level display interface to a terminal device connected in communication; in response to a first generation instruction sent by the terminal device, constructing and sending a second-level display interface for displaying a second SAR image corresponding to a target entity type, the target entity type, a target entity relationship corresponding to the target entity type, and a local knowledge graph corresponding to the target entity type and the target entity relationship, wherein the target entity type is used to indicate any one of the plurality of entity types; and in response to a second generation instruction sent by the terminal device, constructing and sending a third-level display interface for displaying the knowledge graph and an entity list, wherein the entity list includes the plurality of entity types and the entity relationships between the entity types.

[0011] The present application provides a SAR satellite-based knowledge graph terrain analysis method. First, the processor determines a target area, and constructs a knowledge graph corresponding to the target area based on a first SAR image corresponding to the target area. Then, the processor constructs a first-level display interface for displaying the first SAR image and a plurality of entity types in the knowledge graph. Further, the processor, in response to a first generation instruction sent by a terminal device, constructs and sends a second-level display interface for displaying a second SAR image corresponding to a target entity type, the target entity type, a target entity relationship corresponding to the target entity type, and a local knowledge graph corresponding to the target entity type and the target entity relationship. Finally, the processor, in response to a second generation instruction sent by the terminal device, constructs and sends a third-level display interface for displaying the knowledge graph and an entity list.

[0012] With reference to the above, it can be seen that, unlike the prior art, this application does not directly use the first SAR image corresponding to the target area to perform terrain analysis on the target area. Instead, after constructing a knowledge graph corresponding to the target area based on the first SAR image, it further constructs a first-level display interface that specifically displays the first SAR image of the target area and multiple entity types, a second-level display interface that specifically displays the target entity types and corresponding entity relationships, and a third-level display interface that specifically displays the knowledge graph corresponding to the target area. Thus, the operator can intuitively view the terrain features corresponding to the target area through the images displayed on the first-level display interface, the second-level display interface, and the third-level display interface, and can directly use the first-level display interface, the second-level display interface, and the third-level display interface to perform terrain analysis on the target area.

[0013] Therefore, the operator can directly and visually analyze the first SAR image corresponding to the target area through the third-level display interface, and specifically analyze various entity types in the target area and the second SAR image corresponding to the corresponding entity type through the second-level display interface, thereby significantly improving the comprehensibility, computability and applicability of SAR images, making it easier for operators to use SAR images to perform terrain analysis on the target area.

[0014] This solves the technical problem in the prior art that operators are unable to directly analyze SAR images visually, making it impossible to determine the type of terrain in the target area through SAR images, and also unable to directly determine the correlation between various terrain types in the target area, thereby preventing operators from quickly and accurately performing terrain analysis on the target area. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of this application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation of the present disclosure. In the drawings:

[0016] Figure 1 1 is a schematic diagram of a communication connection system between a SAR satellite and a terminal device according to Example 1 of the present application;

[0017] Figure 2A is a schematic diagram of the hardware architecture of the SAR satellite according to Example 1 of the present application;

[0018] Figure 2B is a schematic diagram of the hardware architecture of a terminal device according to an embodiment of the present application;

[0019] Figure 3 This is a flowchart of the terrain analysis method based on the SAR satellite knowledge graph according to Example 1 of the present application;

[0020] Figure 4 This is a schematic diagram of collecting SAR images of a target area using a SAR satellite according to Example 1 of the present application;

[0021] Figure 5 is a schematic diagram of the first-level display interface according to Example 1 of the present application;

[0022] Figure 6 is a schematic diagram of the second-level display interface according to Example 1 of the present application;

[0023] Figure 7 is a schematic diagram of the third-level display interface according to Example 1 of the present application;

[0024] Figure 8 Schematic diagram of a device for collecting SAR images of a target area based on a SAR satellite according to Example 2 of the present application;

[0025] Figure 9 This is a schematic diagram of a device for collecting SAR images of a target area based on a SAR satellite according to Example 3 of the present application. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present disclosure.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Example 1

[0029] According to this embodiment, an embodiment of a terrain analysis method based on a knowledge graph of a SAR satellite is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] Figure 1 A schematic diagram of a communication connection system between a SAR satellite and a terminal device according to the present embodiment is shown. The system includes: a terminal device 10, a terminal device 10, and a SAR satellite 30. The terminal device 10 sends an instruction to generate a knowledge graph corresponding to a target area to the SAR satellite 30 via the terminal device 10. The processor of the SAR satellite 30 is used to receive and respond to the instruction to construct a knowledge graph corresponding to the target area, and collect SAR images corresponding to the target area. The processor (referring to the processor of the above-mentioned SAR satellite 30, the same below) is also used to construct a first-level display interface, construct a second-level display interface in response to a first generation instruction, and construct a third-level display interface in response to a second generation instruction. The processor is also used to send the first-level display interface, the second-level display interface, and the third-level display interface to the terminal device 10.

[0031] Figure 2A It further shows Figure 1 Schematic diagram of the hardware architecture of the SAR satellite 30. Figure 2A As shown, the SAR satellite 30 includes an integrated electronic system, which includes: a processor, a memory, a bus management module and a communication interface. The memory is connected to the processor, so that the processor can access the memory, read the program instructions stored in the memory, read data from the memory or write data to the memory. The bus management module is connected to the processor and is also connected to a bus such as a CAN bus. The processor can communicate with the onboard peripherals connected to the bus through the bus managed by the bus management module. In addition, the processor is also connected to devices such as cameras, star sensors, measurement and control transponders, and data transmission equipment via the communication interface. It can be understood by those skilled in the art that Figure 2A The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 2A More or fewer components than shown, or with Figure 2A Different configurations shown.

[0032] Figure 2B It further shows Figure 1 Schematic diagram of the hardware architecture of the terminal device 10. Figure 2BAs shown, the terminal device 10 may include one or more processors (the processor may include but is not limited to a microprocessor MCU or a programmable logic device FPGA, etc.), a memory for storing data, a transmission device for communication functions, and an input / output interface. The memory, the transmission device, and the input / output interface are connected to the processor via a bus. In addition, it may also include: a display, a keyboard, and a cursor control device connected to the input / output interface. It will be understood by those skilled in the art that Figure 2B The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 2B More or fewer components than shown, or with Figure 2B Different configurations shown.

[0033] It should be noted that Figure 2A and Figure 2B The one or more processors and / or other data processing circuits shown in the figure may generally be referred to herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be fully or partially integrated into any of the other components of the computing device. As involved in the embodiments of the present disclosure, the data processing circuitry acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0034] Figure 2A and Figure 2B The memory shown in the figure can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the terrain analysis method based on the knowledge graph of SAR satellites in the embodiment of the present disclosure. The processor executes the software programs and modules stored in the memory to perform various functional applications and data processing, that is, to implement the terrain analysis method based on the knowledge graph of SAR satellites in the above-mentioned application. The memory may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0035] It should be noted that, in some optional embodiments, the above Figure 2A and Figure 2B The devices shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. Figure 2A and Figure 2B This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the apparatus described above.

[0036] Under the above operating environment, according to the first aspect of this embodiment, a terrain analysis method based on the knowledge graph of SAR satellite is provided. Figure 2A The processor implementation of the SAR satellite 30 shown in FIG. Figure 3 A schematic diagram showing the process of the method is shown in FIG. Figure 3 As shown, the method includes:

[0037] S302: Determine a target area, and construct a knowledge graph corresponding to the target area based on the acquired first SAR image corresponding to the target area, where nodes in the knowledge graph represent entity types and edges represent entity relationships;

[0038] S304: Constructing a first-level display interface for displaying the first SAR image and multiple entity types in the knowledge graph, and sending the first-level display interface to a communication-connected terminal device;

[0039] S306: In response to the first generation instruction sent by the terminal device, construct and send a second-level display interface for displaying a second SAR image corresponding to the target entity type, the target entity type, the target entity relationship corresponding to the target entity type, and the local knowledge graph corresponding to the target entity type and the target entity relationship, wherein the target entity type is used to indicate any one of the multiple entity types; and

[0040] S308: In response to the second generation instruction sent by the terminal device, construct and send a third-level display interface for displaying the knowledge graph and the entity list, wherein the entity list includes multiple entity types and entity relationships between the entity types.

[0041] Specifically, an operator first uses a terminal device 10 and, via a ground system 20, sends a command to a SAR satellite 30 to construct a knowledge graph corresponding to a target area. The processor of the SAR satellite 30 receives and responds to the command, acquiring a first SAR image corresponding to the target area. The target area can be, for example, an urban area, a mountainous area, or a plain area. It should be noted that the above examples of target area types are merely examples and are not intended to be limiting.

[0042] The flight direction of the SAR satellite 30 is used as the azimuth. Each row in the first SAR image represents the distance (i.e., synthetic aperture length) between the transmission of electromagnetic waves and the reception of return electromagnetic waves by the SAR satellite 30 when flying in that direction. Each column represents the slant range between the target area and the SAR satellite 30 when imaging the target area. Therefore, the abscissa of the first SAR image represents the time-series-related synthetic aperture length, and the ordinate represents the slant range.

[0043] Furthermore, the synthetic aperture length is time-dependent. The specific calculation formula is: L = v × t. Here, L represents the synthetic aperture length, v represents the propagation speed of electromagnetic waves in air, and t represents the time from the emission of the electromagnetic wave to the reception of the return electromagnetic wave.

[0044] Afterwards, when the processor acquires a first SAR image corresponding to the target area, a knowledge graph corresponding to the target area is constructed (S302). The nodes in the knowledge graph represent entity types, and the edges represent entity relationships. Specifically, first, the processor uses the first SAR image to determine multiple time series vectors corresponding to each synthetic aperture length. Then, the processor determines a time series vector sequence corresponding to the multiple time series vectors, inputs the time series vector sequence into a joint extraction model, and determines multiple entity types corresponding to the target area and the entity relationships between the entity types. Finally, the processor constructs a knowledge graph corresponding to the target area based on the multiple entity types and the entity relationships between the entity types. The above content will be described in detail later, so it will not be repeated here.

[0045] When the target area is an urban area, entity types 1 to r corresponding to the urban area may include, for example, high-rise buildings, bungalows, etc. Entity relationships corresponding to the urban area may include, for example, continuous high-rise buildings, scattered high-rise buildings, continuous bungalows, scattered bungalows, etc.

[0046] When the target area is a mountainous area, entity types 1-r corresponding to the mountainous area may include, for example, mountains, hills, etc. Entity relationships corresponding to the mountainous area may include, for example, continuous mountains, scattered mountains, continuous hills, scattered hills, etc.

[0047] When the target area is a plain area, the entity types 1-r corresponding to the plain area may include, for example, calm water surface, choppy water surface, and rough ground surface. Rough ground includes rocks, vegetation, etc. The entity relationships corresponding to the plain area may include, for example, continuous calm water surface, sudden calm water surface (i.e., from calm water surface to choppy water surface), sudden change from calm water surface to rough ground, and sudden change from choppy water surface to rough ground.

[0048] For example, Figure 4 This is a schematic diagram of using a SAR satellite to collect SAR images of a target area according to an embodiment of the present application. Figure 5 Schematic diagram of the first level display interface according to the embodiment of the present application. Figure 4 As shown in FIG, the target area is a plain area, and the plain area includes a water area and a ground area. Thus, the SAR satellite 30 can be used to obtain the corresponding Figure 5 The first SAR image is shown. Figure 5The first SAR image with synthetic aperture length as the horizontal coordinate and slant range as the vertical coordinate includes synthetic aperture lengths l1~l n , slant distance r1~r n And each combination of synthetic aperture length and slant distance determines a unique signal strength. For example, (l1, r1) and signal strength i 1,1 Correspondingly, (l1, r2) and signal strength i 1,2 Correspondingly, (l1, r3) and signal strength i 1,3 Corresponding,...,(l1,r n ) and signal strength i 1,n Corresponding. (l2,r1) and signal strength i 2,1 Correspondingly, (l2, r2) and signal strength i 2,2 Correspondingly, (l2, r3) and signal strength i 2,3 Corresponding,...,(l2,r n ) and signal strength i 2,n Corresponding. And so on. (l m ,r1) and signal strength i m,1 Correspondingly, (l m ,r2) and signal strength i m,2 Correspondingly, (l m ,r3) and signal strength i m,3 Corresponding, ..., (l m ,r n ) and signal strength i m,n correspond.

[0049] In the above Figure 5 In the first SAR image shown, the column corresponding to the synthetic aperture length l1 indicates the start of the water area, and the column corresponding to the synthetic aperture length l5 indicates the start of the ground area. 1,1 ~i 1,n In the case of a low value, the column corresponding to the synthetic aperture length l1 is dark in color, indicating that the entity type corresponding to the water area is a calm water surface. As the SAR satellite 30 continues to move, the SAR satellite 30 begins to move toward the ground area, and the signal strength i in the column corresponding to the synthetic aperture length l5 is low. 5,1 ~i 5,n In the case of a higher value, the column corresponding to the synthetic aperture length l5 appears bright white as a whole, indicating that the entity type corresponding to the ground area is a rough surface.

[0050] In addition, the signal intensity i of the column corresponding to the synthetic aperture length l4 displayed in the first SAR image is 4,1 ~i 4,nare all low, and the signal intensity i of the column corresponding to the synthetic aperture length l5 5,1 ~i 5,n If both are high (i.e., the column corresponding to synthetic aperture length l4 appears dark black, and the column corresponding to synthetic aperture length l5 appears bright white), this indicates that the first SAR image shows an abrupt change from calm water to a rough surface. In other words, the entity relationship between the calm water and the rough surface is abrupt.

[0051] If the signal strength i of the column corresponding to the synthetic aperture length l4 is 4,1 ~i 4,n The signal intensity i of the column corresponding to the synthetic aperture length l3 is 3,1 ~i 3,n The signal strength i of the column corresponding to the synthetic aperture length l4 is lower. 4,1 ~i 4,n The signal intensity i of the column corresponding to the synthetic aperture length l5 is 5,1 ~i 5,n If the color depth is low (i.e., the column corresponding to synthetic aperture length l3 is dark black, the column corresponding to synthetic aperture length l4 is grayish white, and the column corresponding to synthetic aperture length l5 is bright white), it indicates that the first SAR image is transitioning slowly from calm water to rough ground. In other words, the physical relationship between the calm water and rough ground is changing slowly.

[0052] Therefore, based on the first SAR image, the entity type and entity relationship corresponding to the target area can be determined.

[0053] The processor then constructs a first-level display interface for displaying the first SAR image and multiple entity types in the knowledge graph, and sends the first-level display interface to a communication-connected terminal device (S304). Figure 5 As shown, the first-level display interface includes a first SAR image with synthetic aperture length as the horizontal coordinate and slant range as the vertical coordinate, as well as multiple entity types 1 to g included in the first SAR image. This allows operators to intuitively analyze the entity types and entity relationships included in the first SAR image, and further, use the first SAR image to quickly perform terrain analysis on the target area.

[0054] When an operator views the first-level display interface through a terminal device and clicks on any entity type in the first-level display interface, the processor, in response to a first generation instruction sent by the terminal device, constructs a second-level display interface. Furthermore, when the processor constructs the second-level display interface, the processor further transmits the second-level display interface to the terminal device. Thus, the operator can view the second-level display interface through the terminal device (S306). The second-level display interface is configured to display a second SAR image corresponding to the target entity type, the target entity type, the target entity relationship corresponding to the target entity type, and the local knowledge graph corresponding to the target entity type and the target entity relationship.

[0055] Figure 6 Schematic diagram of the second level display interface according to the embodiment of the present application. Figure 6 As shown, for example, if the operator clicks entity type 1 on the terminal device, entity type 1 becomes the target entity type. Furthermore, the screen displayed on the terminal device jumps from the first-level display interface to the second-level display interface. In the second-level display interface, compared to the first SAR image that displays the global features of the target area, a second SAR image corresponding to the target entity type is specifically displayed.

[0056] The second-level display interface also includes target entity relationships corresponding to the target entity type. For example, if the target entity type is entity type 1, the second-level display interface may also display entity types 2 and 4 that have association relationships with entity type 1, as well as entity relationship 1 between entity types 1 and 2, and entity relationship 2 between entity types 1 and 4.

[0057] In addition, the second-level display interface also specifically displays the local knowledge graph corresponding to the target entity type, making it easier for operators to conduct targeted terrain analysis of the target area based on the local knowledge graph. For example, if the target entity type is entity type 1, the second-level display interface only displays the local knowledge graph corresponding to entity type 1.

[0058] Furthermore, the operator sends a second generation instruction to the processor through the terminal device, and the processor responds to the second generation instruction sent by the terminal device to construct a third-level display interface (S308) for displaying the knowledge graph and entity list corresponding to the target area. Figure 7 Schematic diagram of the third level display interface according to the embodiment of the present application. Figure 7As shown, in the case that the operator clicks the local knowledge graph on the second-level display interface through the terminal device, the screen displayed by the terminal device jumps from the second-level display interface to the third-level display interface. In the third-level display interface, the knowledge graph corresponding to the target region and the entity list corresponding to the knowledge graph are mainly displayed. The knowledge graph corresponding to the target region and the entity list can reflect the association relationship between the multiple entity types in the target region.

[0059] As described in the background, the pixel-level features of the SAR image cannot be directly used by the operator, and the professional personnel need to be familiar with the radar scattering mechanism and the electromagnetic characteristics of the ground objects. That is, the operator cannot directly visualize the analysis of the SAR image, and needs to be processed before the SAR image can be used. It is extremely inconvenient for the operator to analyze and use the SAR image. For example, when using SAR satellite to collect SAR images to analyze the terrain of the target region, the existing SAR image cannot be used to visualize the determination of the ground object type of the target region, nor can it directly determine the association relationship between various ground object types in the target region, so that the operator cannot quickly and accurately analyze the terrain of the target region.

[0060] Therefore, the present application provides a terrain analysis method based on SAR satellite knowledge graph. And as described above, unlike the prior art, the present application does not directly use the first SAR image corresponding to the target region to analyze the terrain of the target region, but constructs the first SAR image and the first-level display interface of the multiple entity types for the target region, the second-level display interface of the target entity type and the corresponding entity relationship, and the third-level display interface of the knowledge graph corresponding to the target region based on the first SAR image corresponding to the target region. The first SAR image corresponding to the target region can be directly visualized by the operator through the third-level display interface, and the various entity types in the target region and the second SAR image corresponding to the corresponding entity type can be analyzed by the operator through the second-level display interface. Thus, the understanding, calculation and applicability of the SAR image are significantly improved, and the operator can use the SAR image to analyze the terrain of the target region.

[0061] Thus, the operator can directly visualize the analysis of the first SAR image corresponding to the target region through the third-level display interface, and the analysis of the various entity types in the target region and the second SAR image corresponding to the corresponding entity type through the second-level display interface. Thus, the understanding, calculation and applicability of the SAR image are significantly improved, and the operator can use the SAR image to analyze the terrain of the target region.

[0062] This solves the technical problem in the prior art that operators are unable to directly analyze SAR images visually, making it impossible to determine the type of terrain in the target area through SAR images, and also unable to directly determine the correlation between various terrain types in the target area, thereby preventing operators from quickly and accurately performing terrain analysis on the target area.

[0063] Optionally, the operation of constructing and sending a second-level display interface for displaying a second SAR image corresponding to the target entity type, the target entity type, the target entity relationship corresponding to the target entity type, and the local knowledge graph corresponding to the target entity type and the target entity relationship includes: displaying the second SAR image corresponding to the target entity type in a first area of ​​the second-level display interface, wherein the abscissa of the second SAR image represents a synthetic aperture length related to the timing, and the ordinate represents a slant distance; displaying the target entity type, entity types having an associated relationship with the target entity type, and the corresponding entity relationships in a second area of ​​the second-level display interface; and displaying the local knowledge graph corresponding to the target entity type in a third area of ​​the second-level display interface.

[0064] Specifically, refer to Figure 6 As shown, in response to a first generation instruction sent by an operator via a terminal device, the processor constructs a second SAR image corresponding to the target entity type in the first area of ​​the second-level display interface. The abscissa of the second SAR image represents the synthetic aperture length associated with the time sequence, and the ordinate represents the slant distance.

[0065] The second SAR image is used to specifically display the SAR image corresponding to the target entity type. For example, if the target entity type is entity type 1, the second SAR image is used to display the signal strength corresponding to each synthetic aperture length and slant distance of entity type 1. In practice, the second SAR image is a grayscale image, and the electromagnetic wave backscatter signal strength corresponding to a unique synthetic aperture length and slant distance is equivalent to the pixel value in the second SAR image. That is, the greater the signal strength, the larger the pixel value; the smaller the signal strength, the smaller the pixel value.

[0066] Thus, the operator can further analyze the entity type 1 of the target area based on the pixel values ​​corresponding to each synthetic aperture length and slant distance in the second SAR image.

[0067] The second area of ​​the second-level display interface also displays the target entity type, entity types associated with the target entity type, and corresponding entity relationships. For example, the second area displays entity type 2 and entity type 4, which have an association relationship with entity type 1. Furthermore, entity relationship 1 between entity type 1 and entity type 2, and entity relationship 2 between entity type 1 and entity type 4 are displayed. Furthermore, the third area of ​​the second-level display interface also displays the local knowledge graph corresponding to the target entity type. For example, the third area displays the local knowledge graph corresponding to entity type 1.

[0068] For another example, entity type 1 (i.e., the target entity type) is calm water, entity type 2 is rough ground, and entity type 4 is gentle ground. Furthermore, entity relationship 1 between entity types 1 and 2 is a sudden change from calm water to rough ground, while the entity relationship between entity type 1 and 4 is a gradual transition from calm water to gentle ground.

[0069] Therefore, the operator can determine the terrain characteristics of any entity type in the target area based on the image displayed on the second-level display interface, thereby facilitating the operator to conduct a targeted terrain analysis of the target area.

[0070] Optionally, the operation of constructing a first-level display interface for displaying a first SAR image and multiple entity types in a knowledge graph includes: constructing a first SAR image corresponding to a target area in a fourth area of ​​the first-level display interface, wherein the first SAR image corresponds to multiple entity types; and constructing multiple entity types corresponding to the target area in a fifth area of ​​the first-level display interface.

[0071] Specifically, refer to Figure 7 As shown, the processor constructs a first SAR image corresponding to the target area in the fourth area of ​​the first-level display interface. The abscissa of the first SAR image represents the synthetic aperture length associated with the time sequence, and the ordinate represents the slant distance. Furthermore, the first SAR image can display terrain features corresponding to all entity types within the target area, allowing an operator to perform a global analysis of the target area based on the first SAR image.

[0072] In addition, the fifth area of ​​the first-level display interface also displays multiple entity types corresponding to the target area, so that the operator can quickly and accurately perform terrain analysis on the target area based on the knowledge graph corresponding to the target area displayed in the first-level interface area and the multiple entity types contained in the target area.

[0073] Optionally, the operation of constructing a knowledge graph corresponding to the target area includes: using the first SAR image to determine multiple time series vectors corresponding to each synthetic aperture length, wherein the time series vector is used to indicate the distribution of the signal intensity of the electromagnetic wave backscattering corresponding to different slant distances, and each element in the time series vector is used to represent the signal intensity of the electromagnetic wave backscattering corresponding to different slant distances; determining a time series vector sequence corresponding to the multiple time series vectors, and inputting the time series vector sequence into a joint extraction model, and determining multiple entity types corresponding to the target area and the entity relationships between the entity types; and constructing a knowledge graph corresponding to the target area based on the multiple entity types and the entity relationships between the entity types.

[0074] Specifically, referring to the above-mentioned content, it can be known that the first SAR image includes synthetic aperture lengths l1 to l m , slant distance r1~r n And each combination of synthetic aperture length and slant distance determines a unique signal strength. For example, (l1, r1) and signal strength i 1,1 Correspondingly, (l1, r2) and signal strength i 1,2 Correspondingly, (l1, r3) and signal strength i 1,3 Corresponding,...,(l1,r n ) and signal strength i 1,n Corresponding. (l2,r1) and signal strength i 2,1 Correspondingly, (l2, r2) and signal strength i 2,2 Correspondingly, (l2, r3) and signal strength i 2,3 Corresponding,...,(l2,r n ) and signal strength i 2,n Corresponding. And so on. (l m ,r1) and signal strength i m,1 Correspondingly, (l m ,r2) and signal strength i m,2 Correspondingly, (l m ,r3) and signal strength i m,3 Corresponding, ..., (l m ,r n ) and signal strength i m,n Corresponding. And referring to the above content, it can be seen that the signal strength is positively correlated with the pixel value, that is, the greater the signal strength, the greater the pixel value, and the greater the brightness of the pixel point presented; the smaller the signal strength, the smaller the pixel value, and the smaller the brightness of the pixel point presented.

[0075] Since the synthetic aperture length l1 corresponds to the time t1, the time t1 corresponds to the time series vector I1, and I1 = [i 1,1 ,i 1,2 ,i1,3 ,...,i 1,n ] T The synthetic aperture length l2 corresponds to the time t2, so the time t2 corresponds to the time series vector I2, and I2 = [i 2,1 ,i 2,2 ,i 2,3 ,...,i 2,n ] T And so on. Synthetic aperture length l m and time t m Correspondingly, so time t m With the time series vector I m Corresponding, and I m =[i m,1 ,i m,2 ,i m,3 ,...,i m,n ] T .

[0076] Thus the processor can determine the timing vectors I1~I m The time series vector is used to indicate the distribution of the signal strength of the electromagnetic wave backscatter corresponding to different slant distances, and each element in the time series vector is used to represent the signal strength of the electromagnetic wave backscatter corresponding to different slant distances.

[0077] It is worth noting that, since the SAR satellite 30 moves continuously in azimuth and the unit synthetic aperture length of the SAR satellite 30 moving in azimuth is the same, multiple time series vectors can be generated based on each synthetic aperture length in the SAR image.

[0078] When the processor determines multiple time series vectors, it further determines the time series vector sequence corresponding to the multiple time series vectors, inputs the time series vector sequence into the joint extraction model, and determines multiple entity types corresponding to the target area and the entity relationships between each entity type. Specifically, the joint extraction model includes an entity recognition network and an entity relationship extraction network. The entity recognition network is used to determine the entity type label sequence corresponding to each time series vector from the time series vector sequence, thereby determining multiple entities corresponding to the target area. And the entity recognition network includes a first LSTM unit and a CRF unit. The first LSTM unit can solve the problem of long-distance dependency and capture complete contextual features. Therefore, when the time series vector sequence is input into the first LSTM unit, a first enhanced time series vector sequence can be output.

[0079] The processor then inputs the first enhanced time series vector sequence into the CRF unit and uses the CRF unit to select the optimal label path through global optimization, thereby obtaining an entity type label sequence corresponding to the time series vector sequence. The entity type label sequence includes the probability corresponding to each entity type. For example, the time series vector sequence includes multiple time series vectors I1~I m The entity type label sequence includes multiple entity type label vectors P1~P m , where P1 represents the probability that the time series vector I1 corresponds to each entity type; P2 represents the probability that the time series vector I2 corresponds to each entity type; and so on; P m Represents the time series vector I m The probability corresponding to each entity type.

[0080] For example, the entity type label vector P1 = [p 1,1 ,p 1,2 ,...,[ 1,r ],[ 1,1 represents the probability corresponding to entity type 1 in the time series vector I1, p2 represents the probability corresponding to entity type 2 in the time series vector I2, ..., p r Indicated in the time series vector I m The probability that ∈ R corresponds to entity type r.

[0081] And when each probability in each entity type label vector is greater than the preset probability, the entity type of the corresponding time series vector is determined. For example, the entity type label vector P1 = [p 1,1 ,p 1,2 ,...,p 1,r ] corresponds to the probability p of entity type 2 1,2 Greater than the preset threshold p x , so that entity type 2 is the entity type corresponding to the time series vector I1, that is, the entity type corresponding to the column with a synthetic aperture length of l2.

[0082] Thus, the processor determines the timing vectors I1~I m In the case of corresponding entity types, multiple entity types corresponding to the target area can be determined.

[0083] When the processor uses the entity recognition network to determine multiple entities corresponding to the target area, it further uses the entity relationship extraction network to determine the entity relationship label vector sequence corresponding to the time series vector sequence. Among them, the entity relationship extraction network includes a second LSTM unit, a local attention mechanism, a fully connected layer and a softmax classifier. Among them, the second LSTM unit can solve the long-distance dependency problem and capture complete contextual features. The local attention mechanism layer can automatically identify and weight the local semantic units around the entity pair, rather than all the words in the whole sentence, so that by limiting the scope of attention, it can more efficiently capture the semantic clues around the entity. Therefore, when the processor inputs the entities corresponding to each time series vector and the time series vector sequence into the second LSTM unit and the local attention mechanism layer, it can output a second enhanced time series vector sequence.

[0084] Furthermore, the processor inputs the second enhanced time series vector sequence into the fully connected layer, and the fully connected layer maps the high-level features to the specific entity relationship category space, thereby outputting the entity relationship vector sequence corresponding to the time series vector sequence. Finally, the processor inputs the entity relationship vector sequence corresponding to the time series vector sequence into the softmax classifier, so that the softmax classifier can output the entity relationship label sequence corresponding to the entity relationship vector sequence. Among them, the entity relationship label sequence includes the probability corresponding to each entity relationship. For example, the time series vector sequence includes multiple time series vectors I1~I m The entity relationship label sequence includes multiple entity relationship label vectors Q1~Q m-1 , where Q1 represents the probability of the time series vector I1 corresponding to each entity relationship; Q2 represents the probability of the time series vector I2 corresponding to each entity relationship; and so on; Q m Represents the time series vector I m The probability corresponding to each entity relationship.

[0085] For example, the entity relationship label vector Q1 = [q 1,1 ,q 1,2 ,...,q 1,s ],q 1,1 represents the probability corresponding to entity relation 1, q 1,2 represents the probability corresponding to entity relation 2, ..., q 1,s Represents the probability corresponding to the entity relation s.

[0086] And when each probability in each entity relationship label vector is greater than a preset threshold, the entity relationship with the corresponding time series vector is determined. For example, the entity relationship label vector Q1 = [q 1,1 ,q 1,2 ,...,q 1,s ] corresponds to the probability q of entity relation 21,2 Greater than the preset threshold q x , so that entity relationship 2 is the entity relationship corresponding to the time series vector I1.

[0087] Therefore, when the processor determines the entity relationships corresponding to each time series vector, multiple entity relationships corresponding to the target area can be determined.

[0088] After determining the entity types and entity relationships corresponding to each time series vector, the entity types and entity relationship descriptions are combined into triples. For example, if time series vector I1 corresponds to entity type u1, time series vector I2 corresponds to entity type u2, and there is an entity relationship v1 between entity types 1 and 2, then the triple is R1 = (u1, v1, u2).

[0089] Based on the above operations, the processor can determine the multiple triples R1 to R2 corresponding to each time series vector in the time series vector sequence. o .

[0090] Therefore, the above method can construct a knowledge graph corresponding to the target area, which is convenient for operators to analyze and use the first SAR image corresponding to the target area based on the knowledge graph.

[0091] Therefore, according to the first aspect of this embodiment, the comprehensibility, computability, and applicability of SAR images are significantly improved, making it easier for operators to use SAR images to perform terrain analysis on target areas.

[0092] In addition, reference Figure 1 As shown, according to a second aspect of this embodiment, a storage medium is provided, wherein the storage medium includes a stored program, wherein when the program is run, a processor executes any one of the above methods.

[0093] Therefore, according to this embodiment, the comprehensibility, computability, and applicability of SAR images are significantly improved, making it easier for operators to use SAR images to perform terrain analysis on target areas.

[0094] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0095] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0096] Example 2

[0097] Figure 8 FIG. 8 shows a terrain analysis device 800 based on a knowledge graph of a SAR satellite according to this embodiment, which corresponds to the method according to embodiment 1. Figure 8 As shown, the apparatus 800 includes: a knowledge graph construction module 810, configured to determine a target area and, based on an acquired first SAR image corresponding to the target area, construct a knowledge graph corresponding to the target area, wherein nodes in the knowledge graph represent entity types and edges represent entity relationships; a first-level display interface construction module 820, configured to construct a first-level display interface for displaying the first SAR image and multiple entity types in the knowledge graph, and to send the first-level display interface to a communication-connected terminal device; a second-level display interface module 830, configured to, in response to a first generation instruction sent by the terminal device, construct and send a second-level display interface for displaying a second SAR image corresponding to the target entity type, the target entity type, the target entity relationship corresponding to the target entity type, and a local knowledge graph corresponding to the target entity type and the target entity relationship, wherein the target entity type is used to indicate any one of multiple entity types; and a third-level display interface construction module 840, configured to, in response to a second generation instruction sent by the terminal device, construct and send a third-level display interface for displaying the knowledge graph and an entity list, wherein the entity list includes multiple entity types and entity relationships between the entity types.

[0098] Optionally, the second-level display interface module 830 includes a first area display module, which is used to display a second SAR image corresponding to the target entity type in the first area of ​​the second-level display interface, wherein the horizontal axis of the second SAR image represents the synthetic aperture length related to the timing, and the vertical axis represents the slant distance; a second area display module, which is used to display the target entity type, entity types having an associated relationship with the target entity type, and corresponding entity relationships in the second area of ​​the second-level display interface; and a third area display module, which is used to display a local knowledge graph corresponding to the target entity type in the third area of ​​the second-level display interface.

[0099] Optionally, the first-level display interface module 820 includes: a fourth area display module, used to display a first SAR image corresponding to the target area in the fourth area of ​​the first-level display interface, wherein the first SAR image corresponds to multiple entity types; and a fifth area display module, used to display multiple entity types corresponding to the target area in the fifth area of ​​the first-level display interface.

[0100] Optionally, the knowledge graph construction module 810 includes: a first SAR image acquisition module, used to determine the target area, and use a SAR satellite to collect a first SAR image corresponding to the target area; a time series vector determination module, used to use the first SAR image to determine multiple time series vectors corresponding to each synthetic aperture length, wherein the time series vector is used to indicate the distribution of the signal intensity of the electromagnetic wave backscattering corresponding to different slant distances, and each element in the time series vector is used to represent the signal intensity of the electromagnetic wave backscattering corresponding to different slant distances; an extraction module, used to determine the time series vector sequence corresponding to the multiple time series vectors, and input the time series vector sequence into the joint extraction model, and determine multiple entity types corresponding to the target area and the entity relationships between the entity types; and a knowledge graph construction submodule, used to construct a knowledge graph corresponding to the target area based on the multiple entity types and the entity relationships between the entity types.

[0101] Therefore, according to this embodiment, the comprehensibility, computability, and applicability of SAR images are significantly improved, making it easier for operators to use SAR images to perform terrain analysis on target areas.

[0102] Example 3

[0103] Figure 9 FIG. 9 shows a terrain analysis device 900 based on a knowledge graph of a SAR satellite according to this embodiment, which corresponds to the method according to embodiment 1. Figure 9As shown, the apparatus 700 includes a processor 910 and a memory 920 connected with the processor 910, for providing the processor 910 with instructions to process the following processing steps: determining a target region, and constructing a knowledge graph corresponding to the target region based on the acquired first SAR image corresponding to the target region, wherein the nodes in the knowledge graph represent entity types and the edges represent entity relationships; constructing a first-level display interface for displaying the first SAR image and a plurality of entity types in the knowledge graph, and sending the first-level display interface to a terminal device in communication connection; in response to a first generation instruction sent by the terminal device, constructing and sending a second-level display interface for displaying a second SAR image corresponding to a target entity type, the target entity type, a target entity relationship corresponding to the target entity type, and a local knowledge graph corresponding to the target entity type and the target entity relationship, wherein the target entity type is used to indicate any one of the plurality of entity types; and in response to a second generation instruction sent by the terminal device, constructing and sending a third-level display interface for displaying the knowledge graph and an entity list, wherein the entity list includes a plurality of entity types and entity relationships between each entity type.

[0104] Optionally, the operation of constructing and sending the second-level display interface for displaying the second SAR image corresponding to the target entity type, the target entity type, the target entity relationship corresponding to the target entity type, and the local knowledge graph corresponding to the target entity type and the target entity relationship includes: displaying the second SAR image corresponding to the target entity type in a first area of the second-level display interface, wherein the abscissa of the second SAR image represents the synthetic aperture length related to the time sequence and the ordinate represents the slant range; displaying the target entity type, the entity types having a correlation relationship with the target entity type, and the corresponding entity relationships in a second area of the second-level display interface; and displaying the local knowledge graph corresponding to the target entity type in a third area of the second-level display interface.

[0105] Optionally, the operation of constructing the first-level display interface for displaying the first SAR image and the plurality of entity types in the knowledge graph includes: constructing the first SAR image corresponding to the target region in a fourth area of the first-level display interface, wherein the first SAR image corresponds to the plurality of entity types; and constructing the plurality of entity types corresponding to the target region in a fifth area of the first-level display interface.

[0106] Optionally, the operation of constructing a knowledge graph corresponding to the target area includes: using the first SAR image to determine multiple time series vectors corresponding to each synthetic aperture length, wherein the time series vector is used to indicate the distribution of the signal intensity of the electromagnetic wave backscattering corresponding to different slant distances, and each element in the time series vector is used to represent the signal intensity of the electromagnetic wave backscattering corresponding to different slant distances; determining a time series vector sequence corresponding to the multiple time series vectors, and inputting the time series vector sequence into a joint extraction model, and determining multiple entity types corresponding to the target area and the entity relationships between the entity types; and constructing a knowledge graph corresponding to the target area based on the multiple entity types and the entity relationships between the entity types.

[0107] Therefore, according to this embodiment, the comprehensibility, computability, and applicability of SAR images are significantly improved, making it easier for operators to use SAR images to perform terrain analysis on target areas.

[0108] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0109] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0110] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as 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.

[0111] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0112] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0113] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0114] The above is only the preferred embodiment of the present application, it should be pointed out that, for those skilled in the art, without departing from the principles of the present application, can make a number of improvements and refinements, these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A terrain analysis method based on SAR satellite knowledge graph, characterized in that: include: Determine a target area, and construct a knowledge graph corresponding to the target area based on the acquired first SAR image corresponding to the target area, wherein nodes in the knowledge graph represent entity types and edges represent entity relationships; Constructing a first-level display interface for displaying the first SAR image and a plurality of entity types in the knowledge graph, and sending the first-level display interface to a communication-connected terminal device; In response to a first generation instruction sent by the terminal device, construct and send a second-level display interface for displaying a second SAR image corresponding to the target entity type, the target entity type, a target entity relationship corresponding to the target entity type, and a local knowledge graph corresponding to the target entity type and the target entity relationship, wherein the target entity type is used to indicate any one of the multiple entity types; as well as In response to the second generation instruction sent by the terminal device, a third-level display interface for displaying the knowledge graph and the entity list is constructed and sent, wherein the entity list includes the multiple entity types and the entity relationships between the respective entity types.

2. The method according to claim 1, characterized in that The operation of constructing and sending a second-level display interface for displaying a second SAR image corresponding to the target entity type, the target entity type, a target entity relationship corresponding to the target entity type, and a local knowledge graph corresponding to the target entity type and the target entity relationship includes: constructing a second SAR image corresponding to the target entity type in the first area of ​​the second-level display interface, wherein the abscissa of the second SAR image represents a synthetic aperture length related to the time sequence, and the ordinate represents a slant distance; Displaying the target entity type, entity types associated with the target entity type, and corresponding entity relationships in the second area of ​​the second-level display interface; and The local knowledge graph corresponding to the target entity type is displayed in the third area of ​​the second-level display interface.

3. The method according to claim 2, characterized in that The operation of constructing a first-level display interface for displaying the first SAR image and multiple entity types in the knowledge graph includes: constructing a first SAR image corresponding to the target area in a fourth area of ​​the first-level display interface, wherein the first SAR image corresponds to the multiple entity types; and A plurality of entity types corresponding to the target area are constructed in the fifth area of ​​the first-level display interface.

4. The method according to claim 3, characterized in that The operation of constructing a knowledge graph corresponding to the target area includes: Determining, using the first SAR image, a plurality of time series vectors corresponding to respective synthetic aperture lengths, wherein the time series vectors are used to indicate a distribution of electromagnetic wave backscattering signal intensities corresponding to different slant distances, and each element in the time series vectors is used to represent the electromagnetic wave backscattering signal intensities corresponding to the different slant distances; Determining a time series vector sequence corresponding to the plurality of time series vectors, inputting the time series vector sequence into a joint extraction model, and determining a plurality of entity types corresponding to the target region and entity relationships between the entity types; and Based on the multiple entity types and the entity relationships between the entity types, a knowledge graph corresponding to the target area is constructed.

5. A storage medium, characterized in that The storage medium includes a stored program, wherein when the program is run, the processor executes the method according to any one of claims 1 to 4.

6. A terrain analysis device based on SAR satellite knowledge graph, characterized in that: include: a knowledge graph construction module, configured to determine a target area and construct a knowledge graph corresponding to the target area based on the acquired first SAR image corresponding to the target area, wherein nodes in the knowledge graph represent entity types and edges represent entity relationships; A first-level display interface construction module is used to construct a first-level display interface for displaying the first SAR image and multiple entity types in the knowledge graph, and send the first-level display interface to a terminal device connected to the communication; a second-level display interface construction module, configured to construct and send, in response to a first generation instruction sent by the terminal device, a second-level display interface for displaying a second SAR image corresponding to the target entity type, the target entity type, a target entity relationship corresponding to the target entity type, and a local knowledge graph corresponding to the target entity type and the target entity relationship, wherein the target entity type is used to indicate any one of the multiple entity types; as well as A third-level display interface construction module is used to construct and send a third-level display interface for displaying the knowledge graph and the entity list in response to the second generation instruction sent by the terminal device, wherein the entity list includes the multiple entity types and the entity relationships between the respective entity types.

7. The device according to claim 6, characterized in that The second-level display interface module includes a first area display module, configured to display a second SAR image corresponding to the target entity type in the first area of ​​the second-level display interface, wherein the abscissa of the second SAR image represents a synthetic aperture length related to a time sequence, and the ordinate represents a slant distance; A second area display module, configured to display the target entity type, entity types associated with the target entity type, and corresponding entity relationships in a second area of ​​the second-level display interface; as well as A third area display module is used to display a local knowledge graph corresponding to the target entity type in the third area of ​​the second-level display interface.

8. The device according to claim 7, characterized in that The first-level display interface module includes: a fourth area display module, configured to display a first SAR image corresponding to the target area in a fourth area of ​​the first level display interface, wherein the first SAR image corresponds to the multiple entity types; and The fifth area display module is configured to display a plurality of entity types corresponding to the target area in the fifth area of ​​the first level display interface.

9. The device according to claim 8, characterized in that The knowledge graph construction module includes: a first SAR image acquisition module, configured to determine the target area and acquire a first SAR image corresponding to the target area using a SAR satellite; a time series vector determination module, configured to determine, using the first SAR image, a plurality of time series vectors corresponding to respective synthetic aperture lengths, wherein the time series vectors are used to indicate a distribution of electromagnetic wave backscatter signal intensities corresponding to different slant distances, and each element in the time series vectors is used to represent the electromagnetic wave backscatter signal intensities corresponding to the different slant distances; an extraction module, configured to determine a time series vector sequence corresponding to the plurality of time series vectors, input the time series vector sequence into a joint extraction model, and determine a plurality of entity types corresponding to the target region and entity relationships between the entity types; and The knowledge graph construction submodule is used to construct a knowledge graph corresponding to the target area based on the multiple entity types and the entity relationships between the entity types.

10. A terrain analysis device based on SAR satellite knowledge graph, characterized in that: include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: Determine a target area, and construct a knowledge graph corresponding to the target area based on the acquired first SAR image corresponding to the target area, wherein nodes in the knowledge graph represent entity types and edges represent entity relationships; Constructing a first-level display interface for displaying the first SAR image and a plurality of entity types in the knowledge graph, and sending the first-level display interface to a communication-connected terminal device; In response to a first generation instruction sent by the terminal device, construct and send a second-level display interface for displaying a second SAR image corresponding to the target entity type, the target entity type, a target entity relationship corresponding to the target entity type, and a local knowledge graph corresponding to the target entity type and the target entity relationship, wherein the target entity type is used to indicate any one of the multiple entity types; as well as In response to the second generation instruction sent by the terminal device, a third-level display interface for displaying the knowledge graph and the entity list is constructed and sent, wherein the entity list includes the multiple entity types and the entity relationships between the respective entity types.

Images