Simulation test method based on satellite in-orbit data and related device

Abstract

The invention provides a simulation test method based on satellite in-orbit data and a related device, and the method comprises the steps: building a knowledge graph through a satellite communication protocol and in-orbit service information, building a data recovery model according to the knowledge graph, obtaining a corresponding single-machine data package through the data recovery model, and transmitting the single-machine data package to a server; the method comprises the following steps: firstly, receiving a plurality of stand-alone data packets, then classifying and sorting the plurality of stand-alone data packets according to a satellite on-orbit task, establishing a corresponding simulation data source set, finally, selecting a target test set from the simulation data set according to a target simulation scene, and performing simulation test on a satellite by adopting the target test set, thereby reducing the complexity and specialty of the satellite simulation test, and improving the test efficiency. And a large number of satellite in-orbit scenes can be accurately covered, so that automatic testing during satellite development can be realized.

Description

Technical Field

[0001] The present invention mainly relates to the field of satellite testing technology, and in particular to a simulation testing method, device, electronic equipment and storage medium based on satellite on-orbit data. Background Art

[0002] At present, satellite simulation tests usually use ground-based auxiliary software to simulate actual scenarios. However, scene matching requires the participation of technical personnel, which is not only inefficient but also requires the accumulation of professional knowledge of technical personnel, and has a high professional threshold. Summary of the invention

[0003] The purpose of the present invention is to provide a simulation test method and related devices based on satellite on-orbit data, which are used to reduce the complexity and professionalism of satellite simulation testing, accurately cover a large number of satellite on-orbit scenarios, and thus help to achieve automated testing during satellite development.

[0004] In a first aspect, the present application provides a simulation testing method based on satellite on-orbit data, the method comprising: constructing a knowledge graph according to satellite communication protocols and on-orbit business information, and establishing a data recovery model according to the knowledge graph; obtaining satellite on-orbit data, inputting the satellite on-orbit data into the data recovery model, obtaining corresponding model output data, assembling the model output data according to the position relationship of a single-machine interaction package, and obtaining a corresponding single-machine data packet; classifying and arranging multiple single-machine data packets according to satellite on-orbit missions, and establishing a corresponding simulation data source collection; selecting a target test set from the simulation data collection according to a target simulation scenario, and using the target test set to perform simulation testing on the satellite.

[0005] In some embodiments, a knowledge graph is constructed based on satellite communication protocols and on-orbit business information, including: collecting valid data from satellite communication protocols and on-orbit business information; performing entity extraction on the valid data to obtain a corresponding plurality of entities, and performing relationship extraction on the prepared data based on the plurality of entities to obtain a corresponding plurality of entity association relationships, wherein the entity association relationships include parallel relationships between entities and hierarchical and subordinate relationships between entities; for each entity, forming a triple with the corresponding entity association relationship, and constructing a knowledge graph based on the plurality of triples.

[0006] In some embodiments, the valid data includes any one or a combination of the following: the data packet structure, length, and sending frequency of the stand-alone interaction; the data type and data format of the data packet received on the ground; and the conversion relationship between the stand-alone data and the data received on the ground.

[0007] In some embodiments, for each entity, after forming a triple with its corresponding entity association relationship, it also includes: using a similarity algorithm to perform entity disambiguation and coreference resolution on multiple triples to obtain multiple target triples, so as to construct a knowledge graph based on the multiple target triples.

[0008] In some embodiments, before inputting the satellite on-orbit data into the data recovery model, it also includes: determining the position of the error frame in the satellite on-orbit data, and removing the error frame from the satellite on-orbit data; using the ML algorithm to obtain the supplementary frame corresponding to the error frame, and filling the supplementary frame to the position corresponding to the error frame.

[0009] In some embodiments, after assembling the model output data according to the position relationship of the stand-alone interaction package to obtain the corresponding stand-alone data packet, it also includes: determining the valid fields in the stand-alone data packet based on the supplementary frame; performing weighted average calculation on the valid fields to obtain the credibility of the stand-alone data packet.

[0010] In some embodiments, the simulation data source collection includes multiple simulation data sources, wherein each simulation data source includes a triple consisting of a corresponding single-machine data packet, time information, and credibility.

[0011] In the second aspect, the present application provides a simulation test device based on satellite on-orbit data, including: a graph establishment module, which is used to construct a knowledge graph according to satellite communication protocols and on-orbit business information, and establish a data recovery model according to the knowledge graph; a data processing module, which is used to obtain satellite on-orbit data, input the satellite on-orbit data into the data recovery model, obtain corresponding model output data, and assemble the model output data according to the position relationship of the single-machine interaction package to obtain the corresponding single-machine data packet; a data set establishment module, which is used to classify and organize multiple single-machine data packets according to the satellite on-orbit mission, and establish a corresponding simulation data source collection; a simulation test module, which is used to select a target test set from the simulation data collection according to the target simulation scenario, and use the target test set to perform simulation testing on the satellite.

[0012] In some embodiments, a knowledge graph is constructed based on satellite communication protocols and on-orbit business information, and the graph building module is used to: collect valid data from satellite communication protocols and on-orbit business information; perform entity extraction on the valid data to obtain a corresponding plurality of entities, and perform relationship extraction on the prepared data based on the plurality of entities to obtain a corresponding plurality of entity association relationships, wherein the entity association relationships include parallel relationships between entities and hierarchical and subordinate relationships between entities; for each entity, group it and the corresponding entity association relationship into a triple, and construct a knowledge graph based on the plurality of triples.

[0013] In some embodiments, the valid data includes any one or a combination of the following: the data packet structure, length, and sending frequency of the stand-alone interaction; the data type and data format of the data packet received on the ground; and the conversion relationship between the stand-alone data and the data received on the ground.

[0014] In some embodiments, for each entity, after it and the corresponding entity association relationship are organized into a triple, the graph building module is used to: use a similarity algorithm to perform entity disambiguation and coreference resolution on multiple triples to obtain multiple target triples, so as to construct a knowledge graph based on the multiple target triples.

[0015] In some embodiments, before inputting the satellite on-orbit data into the data restoration model, the graph establishment module is also used to: determine the position of the error frame in the satellite on-orbit data, and remove the error frame from the satellite on-orbit data; use the ML algorithm to obtain the supplementary frame corresponding to the error frame, and fill the supplementary frame to the position corresponding to the error frame.

[0016] In some embodiments, after assembling the model output data according to the position relationship of the stand-alone interaction package to obtain the corresponding stand-alone data packet, the data processing module is also used to: determine the valid fields in the stand-alone data packet based on the supplementary frame; perform weighted average calculation on the valid fields to obtain the credibility of the stand-alone data packet.

[0017] In some embodiments, the simulation data source collection includes multiple simulation data sources, wherein each simulation data source includes a triple consisting of a corresponding single-machine data packet, time information, and credibility.

[0018] In a third aspect, the present application provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is called by the processor, the processor executes any method as described in the first aspect above.

[0019] In a fourth aspect, the present application provides a storage medium, including a computer program, which, when called by a computer, enables the computer to execute any method of the first aspect described above.

[0020] Compared with the prior art, the present invention has the following advantages:

[0021] The present application provides a simulation test method and related devices based on satellite on-orbit data, constructs a knowledge graph through satellite communication protocols and on-orbit business information, and establishes a data recovery model based on the knowledge graph. The corresponding single-machine data packet can be obtained through the data recovery model, and then multiple single-machine data packets are classified and sorted according to the satellite on-orbit mission, and a corresponding simulation data source collection is established. Finally, a target test set is selected from the simulation data collection according to the target simulation scenario, and the satellite is simulated and tested using the target test set, thereby reducing the complexity and professionalism of satellite simulation testing, and being able to accurately cover a large number of satellite on-orbit scenarios, thereby helping to realize automated testing during satellite development. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are included to provide a further understanding of the present application. They are included and constitute a part of the present application. The accompanying drawings illustrate embodiments of the present application and together with the present specification serve to explain the principles of the present application. In the accompanying drawings:

[0023] Figure 1 This is a flow chart of a simulation test method based on satellite on-orbit data provided by the present application;

[0024] Figure 2 It is a schematic diagram of a simulation test device based on satellite in-orbit data provided by the present application;

[0025] Figure 3 It is a schematic diagram of an electronic device provided by the present application. DETAILED DESCRIPTION

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0027] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0028] In addition, it should be noted that the use of words such as "first" and "second" to define components is only for the convenience of distinguishing the corresponding components. If not otherwise stated, the above words have no special meaning and cannot be understood as limiting the scope of protection of this application. In addition, although the terms used in this application are selected from well-known and commonly used terms, some terms mentioned in the specification of this application may be selected by the applicant at his or her discretion, and their detailed meanings are explained in the relevant parts of the description of this article. In addition, it is required to understand this application not only by the actual terms used, but also by the meaning implied by each term.

[0029] Figure 1 This is a flow chart of a simulation test method based on satellite in-orbit data provided by the present application.

[0030] refer to Figure 1 The method can be performed on an electronic device, and specifically includes:

[0031] S101, construct a knowledge graph based on satellite communication protocols and on-orbit business information, and establish a data recovery model based on the knowledge graph.

[0032] S102, obtaining satellite on-orbit data, inputting the satellite on-orbit data into a data recovery model to obtain corresponding model output data, assembling the model output data according to the position relationship of the stand-alone interactive package, and obtaining corresponding stand-alone data package.

[0033] S103, classifying and arranging multiple stand-alone data packets according to the satellite's on-orbit missions, and establishing a corresponding simulation data source collection.

[0034] S104, selecting a target test set from the simulation data collection according to the target simulation scenario, and using the target test set to perform simulation testing on the satellite.

[0035] In some embodiments, a knowledge graph is constructed based on satellite communication protocols and on-orbit business information, including: collecting valid data from satellite communication protocols and on-orbit business information; performing entity extraction on the valid data to obtain a corresponding plurality of entities, and performing relationship extraction on the prepared data based on the plurality of entities to obtain a corresponding plurality of entity association relationships.

[0036] Among them, entity association relationships include parallel relationships between entities and hierarchical relationships between entities; for each entity, it and the corresponding entity association relationship are grouped into triples, and a knowledge graph is constructed based on multiple triples.

[0037] Specifically, valid data can be used to describe the relationship between the data sent by a single machine on the satellite and the data received by ground telemetry and their correspondence. An entity refers to something that is distinguishable and exists independently in the valid data. For example, an entity can refer to a single machine such as a satellite service subsystem, or it can refer to a data packet sent by a single machine, a telemetry parameter name, etc. In the specific implementation, the entity should include but is not limited to the following. Entity extraction can be performed manually and with the assistance of algorithms. For example, it can be extracted directly through business experience, or it can use crawler scripts or manually constructed grammar, semantic rules, or BERT pre-trained models to extract the required entities from the valid data. In the specific implementation, there is no restriction on this.

[0038] In some embodiments, valid data includes any one or a combination of the following: data packet structure, length, and transmission frequency of stand-alone interaction; data type and data format of ground-received data packets; and the conversion relationship between stand-alone data and data received on the ground. In a specific implementation, valid data can also be extracted from structured data and unstructured data. Structured data can be, for example, a table in a protocol file, a structure defined in a code, etc. Unstructured data can be, for example, text information such as a satellite communication protocol. Unstructured data can be processed by rules and NLP to convert text information that is difficult to identify into structured data.

[0039] In some embodiments, for each entity, after forming a triple with its corresponding entity association relationship, it also includes: using a similarity algorithm to perform entity disambiguation and coreference resolution on multiple triples to obtain multiple target triples, so as to construct a knowledge graph based on the multiple target triples.

[0040] For example, if different descriptive information can be extracted from multiple sources for a certain entity, a similarity algorithm can be used to perform entity disambiguation and coreference resolution on multiple triples. After confirming the fused entity, the entity association relationship corresponding to the entity is formed into a target triple. Entity disambiguation mainly solves the ambiguity problem of entities with the same name, and coreference resolution solves the problem that multiple descriptive information corresponds to the same entity. The similarity algorithm can be, for example, a cosine similarity algorithm, which first determines the keywords and their weights of the document or entity, and then represents each document or entity as a vector, each dimension of which corresponds to the weight of a keyword, and then calculates the cosine similarity based on the dot product of the two vectors and their respective moduli. Based on the calculated cosine similarity, it can be determined whether different descriptive information corresponds to the same entity.

[0041] In addition, since the documents and codes in the data source of constructing the knowledge graph are completed by multiple people, knowledge fusion can also be used in this process to logically attribute and filter out redundant / error data. For example, the same nouns used in different contents in different files can be fused, or the multiple expressions that may exist for some nouns can be fused. In specific implementations, knowledge fusion can also be performed manually and / or algorithmically assisted, and there is no limitation on this.

[0042] In some embodiments, before inputting the satellite on-orbit data into the data recovery model, it also includes: determining the position of the error frame in the satellite on-orbit data, and removing the error frame from the satellite on-orbit data; using the ML algorithm to obtain the supplementary frame corresponding to the error frame, and filling the supplementary frame into the position corresponding to the error frame. Among them, the satellite on-orbit data may refer to the downlink data sent by the satellite to the ground measurement and control. When the ground measurement and control receives the satellite on-orbit data, if there is an error frame, it records the state and replaces it with a supplementary frame to avoid the subsequent generation of problems such as poor quality of single-machine data packets and discontinuous data.

[0043] In some embodiments, after assembling the model output data according to the position relationship of the stand-alone interaction package to obtain the corresponding stand-alone data packet, it also includes: determining the valid fields in the stand-alone data packet based on the supplementary frame; performing weighted average calculation on the valid fields to obtain the credibility of the stand-alone data packet.

[0044] The calculation formula of credibility is as follows:

[0045]

[0046] Among them, x i is the i-th value in the value set; w i is with x i The associated weight; n is the total number of values ​​in the value set. The initial weight is set to 1. If there is an error frame, the weight is halved to 0.5. In specific implementation, the weight adjustment method can be changed according to actual conditions.

[0047] Further, after the satellite on-orbit data is input into the data recovery model, a complete stand-alone data packet is obtained by combining the frame format, frame header, frame tail, checksum and other information defined in the stand-alone protocol. In some embodiments, the stand-alone data packet, time information and credibility form a triplet and are put into a corresponding simulation data source. Subsequently, multiple simulation data sources are classified and sorted according to key data parameters or ground mission planning, such as classifying and sorting multiple simulation data sources according to the working mode of the satellite attitude, so as to more conveniently select the target test set applicable to the target simulation scenario from the simulation data collection, thereby improving the efficiency of simulation testing of the satellite.

[0048] Figure 22 is a schematic diagram of a simulation test device based on satellite on-orbit data provided by the present application, including a graph establishment module 201, a data processing module 202, a data set establishment module 203 and a simulation test module 204, wherein:

[0049] The graph establishment module 201 is used to construct a knowledge graph based on satellite communication protocols and on-orbit business information, and to establish a data recovery model based on the knowledge graph.

[0050] The data processing module 202 is used to obtain satellite on-orbit data, input the satellite on-orbit data into the data recovery model to obtain corresponding model output data, and assemble the model output data according to the position relationship of the single-machine interactive package to obtain the corresponding single-machine data package.

[0051] The data set establishment module 203 is used to classify and organize multiple stand-alone data packets according to the satellite on-orbit missions and establish a corresponding simulation data source collection.

[0052] The simulation test module 204 is used to select a target test set from the simulation data collection according to a target simulation scenario, and use the target test set to perform simulation testing on the satellite.

[0053] In some embodiments, a knowledge graph is constructed based on satellite communication protocols and on-orbit business information, and the graph establishment module 201 is used to: collect valid data from satellite communication protocols and on-orbit business information; perform entity extraction on the valid data to obtain a corresponding plurality of entities, and perform relationship extraction on the prepared data based on the plurality of entities to obtain a corresponding plurality of entity association relationships, wherein the entity association relationships include parallel relationships between entities and hierarchical and subordinate relationships between entities; for each entity, group it and the corresponding entity association relationship into a triple, and construct a knowledge graph based on the plurality of triples.

[0054] In some embodiments, the valid data includes any one or a combination of the following: the data packet structure, length, and sending frequency of the stand-alone interaction; the data type and data format of the data packet received on the ground; and the conversion relationship between the stand-alone data and the data received on the ground.

[0055] In some embodiments, for each entity, after forming a triple with its corresponding entity association relationship, the graph establishment module 201 is used to: use a similarity algorithm to perform entity disambiguation and coreference resolution on multiple triples to obtain multiple target triples, so as to construct a knowledge graph based on the multiple target triples.

[0056] In some embodiments, before inputting the satellite on-orbit data into the data restoration model, the map establishment module 201 is also used to: determine the position of the error frame in the satellite on-orbit data, and remove the error frame from the satellite on-orbit data; use the ML algorithm to obtain the supplementary frame corresponding to the error frame, and fill the supplementary frame to the position corresponding to the error frame.

[0057] In some embodiments, after assembling the model output data according to the position relationship of the stand-alone interaction package to obtain the corresponding stand-alone data packet, the data processing module 202 is also used to: determine the valid fields in the stand-alone data packet according to the supplementary frame; perform weighted average calculation on the valid fields to obtain the credibility of the stand-alone data packet.

[0058] In some embodiments, the simulation data source collection includes multiple simulation data sources, wherein each simulation data source includes a triple consisting of a corresponding single-machine data packet, time information, and credibility.

[0059] Further, if Figure 3 An exemplary embodiment of the present application also provides an electronic device, including a memory 301 and a processor 302, wherein the memory 301 stores a computer program, and when the computer program is called by the processor 302, the processor 302 executes the steps of the simulation test method based on satellite in-orbit data as described above.

[0060] It should be understood that the processor mentioned in the embodiments of the present application may be a CPU, or other general-purpose processors, DSPs, ASICs, FPGAs or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0061] It should also be understood that the memory mentioned in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory, dynamic random access memory, synchronous dynamic random access memory, double data rate synchronous dynamic random access memory, enhanced synchronous dynamic random access memory, synchronously connected dynamic random access memory, and direct memory bus random access memory.

[0062] The present application also provides a storage medium storing a computer program, which, when called by a processor of a computer, enables the computer to execute the steps of any of the methods mentioned above.

[0063] A computer-readable medium may include a propagated data signal containing computer program code, such as in baseband or as part of a carrier wave. The propagated signal may have a variety of manifestations, including electromagnetic, optical, etc., or a suitable combination. A computer-readable medium may be any computer-readable medium other than a computer-readable storage medium, which may be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit a program for use. The program code on the computer-readable medium may be propagated via any suitable medium, including radio, cable, fiber optic cable, radio frequency signal, or similar medium, or any combination of the above mediums.

[0064] The basic concepts have been described above. Obviously, for those skilled in the art, the above invention disclosure is only used as an example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.

[0065] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0066] Some aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". The processor may be one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or combinations thereof. In addition, various aspects of the present application may be expressed as computer products located in one or more computer-readable media, which include computer-readable program codes. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, tapes ...), optical disks (e.g., compact disks CDs, digital versatile disks DVDs ...), smart cards, and flash memory devices (e.g., cards, sticks, key drives ...).

[0067] A computer-readable medium may include a propagated data signal containing computer program code, such as in baseband or as part of a carrier wave. The propagated signal may have a variety of manifestations, including electromagnetic, optical, etc., or a suitable combination. A computer-readable medium may be any computer-readable medium other than a computer-readable storage medium, which may be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit a program for use. The program code on the computer-readable medium may be propagated via any suitable medium, including radio, cable, fiber optic cable, radio frequency signal, or similar medium, or any combination of the above mediums.

[0068] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this application, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0069] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0070] Although the present application has been described with reference to the current specific embodiments, ordinary technicians in this technical field should recognize that the above embodiments are only used to illustrate the present application, and various equivalent changes or substitutions may be made without departing from the spirit of the present application. Therefore, as long as the changes and modifications to the above embodiments are within the essential spirit of the present application, they will fall within the scope of the claims of the present application.

Claims

1. A simulation test method based on satellite on-orbit data, characterized in that: include: Construct a knowledge graph based on satellite communication protocols and on-orbit business information, and establish a data recovery model based on the knowledge graph; Acquire satellite on-orbit data, input the satellite on-orbit data into the data recovery model to obtain corresponding model output data, assemble the model output data according to the position relationship of the stand-alone interactive package, and obtain corresponding stand-alone data package; Classify and sort the plurality of stand-alone data packets according to the satellite on-orbit missions, and establish a corresponding simulation data source collection; A target test set is selected from the simulation data collection according to a target simulation scenario, and a simulation test is performed on the satellite using the target test set.

2. The method according to claim 1, characterized in that The construction of a knowledge graph based on satellite communication protocols and on-orbit business information includes: Collecting valid data from the satellite communication protocol and the on-orbit service information; Perform entity extraction on the valid data to obtain a corresponding plurality of entities, and perform relationship extraction on the prepared data based on the plurality of entities to obtain a corresponding plurality of entity association relationships, wherein the entity association relationships include parallel relationships between entities and entity hierarchical relationships; For each entity, its association relationship with the corresponding entity is grouped into a triple, and a knowledge graph is constructed based on multiple triples.

3. The method according to claim 2, characterized in that The valid data includes any one or combination of the following: Data packet structure, length, and sending frequency for stand-alone interaction; The data type and data format of the data packets received on the ground; The conversion relationship between stand-alone data and data received on the ground.

4. The method according to claim 2, characterized in that After forming a triplet with respect to each entity and the corresponding entity association relationship, the following further includes: A similarity algorithm is used to perform entity disambiguation and coreference resolution on the multiple triples to obtain multiple target triples, so as to construct a knowledge graph based on the multiple target triples.

5. The method according to claim 1, characterized in that Before inputting the satellite on-orbit data into the data recovery model, the method further comprises: Determine the position of the error frame in the satellite on-orbit data, and remove the error frame from the satellite on-orbit data; An ML algorithm is used to obtain a supplementary frame corresponding to the error frame, and the supplementary frame is filled into a position corresponding to the error frame.

6. The method according to claim 5, characterized in that After assembling the model output data according to the position relationship of the stand-alone interactive package to obtain the corresponding stand-alone data package, the method further includes: Determine the valid fields in the stand-alone data packet according to the supplementary frame; A weighted average calculation is performed on the valid fields to obtain the credibility of the single-machine data packet.

7. The method according to claim 6, characterized in that The simulation data source collection includes multiple simulation data sources, wherein each simulation data source includes a triple consisting of a corresponding single-machine data packet, time information and credibility.

8. A simulation test device based on satellite on-orbit data, characterized in that: include: A graph building module, used to build a knowledge graph based on satellite communication protocols and on-orbit business information, and to build a data recovery model based on the knowledge graph; A data processing module is used to obtain satellite on-orbit data, input the satellite on-orbit data into the data recovery model to obtain corresponding model output data, and assemble the model output data according to the position relationship of the stand-alone interactive package to obtain a corresponding stand-alone data package; A data set establishment module, used to classify and organize the plurality of single-machine data packets according to the satellite on-orbit missions, and establish a corresponding simulation data source collection; The simulation test module is used to select a target test set from the simulation data collection according to a target simulation scenario, and use the target test set to perform simulation testing on the satellite.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is called by the processor, the processor executes the method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The method comprises a computer program, which, when called by a computer, enables the computer to execute the method according to any one of claims 1 to 7.

Images