Auxiliary recommendation system, method, device and medium for earth observation mission process

Abstract

The present invention provides an auxiliary recommendation system, method, device and medium for earth observation mission processes, including a data preparation unit, a process link generation module, a process node parameter generation module, a recommended process output unit and a manual interpretation unit; the process link generation module includes a data preprocessing unit, a process mining unit and a process pruning unit; the process node parameter generation module includes a data preprocessing unit, a knowledge reasoning unit and an entity linking unit. The present invention separates the recommendation of process links from the recommendation of process node parameters, simplifies the process of earth observation mission process recommendation; and can mine process models from historical data of earth observation missions to achieve autonomous updating of process models; it can also obtain a potential list of available parameters in real time, and provide alternative solutions for process node parameter conflicts, failures and other problems.

Description

Technical Field

[0001] This invention relates to the field of Earth observation technology, and in particular to auxiliary recommendation systems, methods, equipment and media for Earth observation mission processes. Background Art

[0002] Earth observation missions are an important way to achieve real-time observation and monitoring of ground resources by coordinating ground systems and satellite resources. They are primarily used in civilian fields such as disaster prevention, geographic mapping, and meteorological observation. With the rapid development of aerospace technology and the increasing variety and quantity of Earth observation needs, the execution process of Earth observation missions is becoming increasingly complex. Furthermore, due to the unique nature of Earth observation missions—namely, the requirement for reliable execution processes—most existing Earth observation missions rely on fixed process templates and require manual guidance according to rules. This approach cannot effectively address the challenges of mission process generation and management arising from mission and technological expansion. Updates to equipment or cumbersome process nodes further burden operators and approvers. Therefore, a technical solution is urgently needed to address these issues. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides an auxiliary recommendation system, method, equipment, and medium for Earth observation mission workflows.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] On the one hand, the present invention provides an auxiliary recommendation system for Earth observation mission flow, including a data preparation unit, a flow link generation module, a flow node parameter generation module, a recommended flow output unit, and a manual interpretation unit;

[0006] The data preparation unit inputs the data preparation into the process link generation module and the process node parameter generation module;

[0007] The process link generation module includes a data preprocessing unit, a process mining unit, and a process pruning unit. The data preprocessing unit performs data preprocessing, sets different data collection granularities according to different task types, forms a dataset, and outputs it to the process mining unit. The process mining unit mines a process model based on the received dataset and outputs it to the process pruning unit. The process pruning unit processes the process model into a usable process link and outputs it to the recommended process output unit.

[0008] The process node parameter generation module includes a data preprocessing unit, a knowledge reasoning unit, and an entity linking unit. The data preprocessing unit encodes triple or quadruple data to form a dataset, which is then input into the knowledge reasoning unit. The knowledge reasoning unit outputs a trained knowledge reasoning model based on the received dataset. The entity linking unit constructs the triple or quadruple to be predicted and predicts the tail entity.

[0009] The recommendation process output unit integrates the recommendation process and outputs it.

[0010] The manual interpretation unit is used to edit process nodes and process node parameters.

[0011] On the other hand, the present invention provides an auxiliary recommendation method for Earth observation mission processes, which is implemented based on the aforementioned auxiliary recommendation system for Earth observation mission processes, and includes the following steps:

[0012] S1. Input data preparation;

[0013] S2. Preprocess the input data to form a dataset that can be received by the process mining unit and a dataset that can be received by the knowledge reasoning unit.

[0014] S3. The process mining unit performs data mining based on the received dataset to obtain the process model;

[0015] S4. The knowledge reasoning unit performs knowledge reasoning based on the received dataset to obtain a trained knowledge reasoning model.

[0016] S5. The process pruning unit prunes the process model by setting a threshold, and obtains the pruned process model.

[0017] S6. Recommend processes based on the pruned process model; and recommend parameters based on the process recommendations combined with the trained knowledge reasoning model.

[0018] S7. Combine the results of the combined process recommendation and the results of the parameter recommendation to generate the recommendation process output.

[0019] Furthermore, the data preparation includes historical data from Earth observation missions, time-series knowledge graph data, and observation requirements.

[0020] Further, in S2, the dataset that the process mining unit can receive is formed according to the following steps:

[0021] S211. Set the data acquisition granularity corresponding to the task execution frequency;

[0022] S212. Extract historical data corresponding to the mission type from historical data of Earth observation missions based on the data acquisition granularity.

[0023] S213. The extracted historical data is processed into triples and used as a dataset that can be received by the process mining unit.

[0024] Further, in S2, the dataset that the knowledge reasoning unit can receive is formed according to the following steps:

[0025] S221. Set the data acquisition granularity corresponding to the task execution frequency;

[0026] S222. Extract triples or quadruples from the time-series knowledge graph data based on the granularity of data collection.

[0027] S223. Process triplet or quadruple data into numerical values, which can be used as a dataset that the knowledge reasoning unit can receive.

[0028] Furthermore, in S6, the recommended process includes the following steps:

[0029] S611. Traverse each sub-process of the pruned process model from the starting point to the ending point, and each time select the sub-process connected by the edge with the largest direct following relationship and the largest dependency metric as the output.

[0030] S612. Combine all selected sub-processes to form a complete process as an alternative process.

[0031] S613. Based on the judgment requirements, select the previous... k The alternative processes are used as the result of the process recommendation. k is the default value.

[0032] Furthermore, in S6, the parameter recommendation includes the following steps:

[0033] S621. Traverse the previous sections in the recommended order. k One alternative process;

[0034] S622, Traverse the subprocesses in the order they are executed. i Sub-process nodes of the alternative process;

[0035] S622. Construct the triplet to be predicted for each subprocess. Head entity, , tail entity>, where, Indicates the The first alternative process The triplet to be predicted consists of each sub-process node. and It is an integer, counting from 0; Indicates the The first alternative process Each sub-process node;

[0036] S623, Get each The list of head and tail entities to be connected;

[0037] S624. Based on the tail entity prediction scores, select the top entities from the list. s The result is recommended as a parameter.

[0038] Furthermore, each of the above The list of connected head and tail entities is obtained by following these steps:

[0039] Triples to be predicted The data is input into the knowledge reasoning unit to obtain the prediction result. s Each tail entity is represented by a tail entity, forming a tail entity list. The tail entities in this list become the head entities for the next sub-process, enabling tail entity prediction for that sub-process. This process continues until all triples to be predicted are identified. Complete the forecast;

[0040] Output each The list of head and tail entities to be connected.

[0041] On the other hand, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of an auxiliary recommendation method for the Earth observation mission process.

[0042] On the other hand, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of an auxiliary recommendation method for Earth observation mission flow.

[0043] Compared with the prior art, the technical effects that this invention can produce are:

[0044] The present invention provides an auxiliary recommendation system, method, device, and medium for Earth observation mission workflows, which separates the recommendation of workflow links from the recommendation of workflow node parameters, simplifying the process of recommending Earth observation mission workflows. The workflow link is mined through a workflow mining unit; the workflow node parameters are mined through a knowledge reasoning unit. Combining these two methods enables auxiliary recommendation of Earth observation mission workflows, better assisting professionals in making workflow recommendation decisions and significantly saving manpower costs.

[0045] Compared with existing technologies, this invention mines process models from historical data of Earth observation missions. While reducing the workload of professionals, it can better handle the complex mapping relationships and changes in functional modules brought about by process model updates, and realize the autonomous updating of process models.

[0046] The process node parameter generation module used in this invention differs from the traditional method of relying on manual system relationship mapping. This invention can obtain a list of potentially available parameters in real time, providing alternative solutions for problems such as process node parameter conflicts and failures, thereby better assisting professionals in generating Earth observation mission processes. Attached Figure Description

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0048] Figure 1 This is a schematic diagram of the auxiliary recommendation system structure for an Earth observation mission flow provided in one embodiment;

[0049] Figure 2 A flowchart of an auxiliary recommendation method for Earth observation missions provided in one embodiment;

[0050] Figure 3 A schematic diagram of a process model provided for one embodiment;

[0051] Figure 4 A schematic diagram of the pruned process model provided in one embodiment;

[0052] Figure 5 This is a schematic diagram of the recommendation process results provided in one embodiment, wherein... Figure 5 (a) is a schematic diagram of the recommendation process (1). Figure 5 (b) is a schematic diagram of the recommendation process (2). Figure 5 (c) is a schematic diagram of the recommendation process (3). Detailed Implementation

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0054] Reference Figure 1 One embodiment provides an auxiliary recommendation system for Earth observation mission flow, including a data preparation unit, a flow link generation module, a flow node parameter generation module, a recommended flow output unit, and a manual interpretation unit.

[0055] The data preparation unit inputs the data preparation into the process link generation module and the process node parameter generation module;

[0056] The process link generation module includes a data preprocessing unit, a process mining unit, and a process pruning unit. The data preprocessing unit performs data preprocessing, sets different data collection granularities according to different task types, forms a dataset, and outputs it to the process mining unit. The process mining unit mines a process model based on the received dataset and outputs it to the process pruning unit. The process pruning unit processes the process model into a usable process link and outputs it to the recommended process output unit.

[0057] The process node parameter generation module includes a data preprocessing unit, a knowledge reasoning unit, and an entity linking unit. The data preprocessing unit encodes triple or quadruple data to form a dataset, which is then input into the knowledge reasoning unit. The knowledge reasoning unit outputs a trained knowledge reasoning model based on the received dataset. The entity linking unit constructs the triple or quadruple to be predicted and predicts the tail entity.

[0058] The recommendation process output unit integrates the recommendation process and outputs it.

[0059] The manual interpretation unit is used to edit process nodes and process node parameters.

[0060] Through the manual interpretation unit, users can customize and edit process nodes and process node parameters.

[0061] Reference Figure 2 One embodiment provides an auxiliary recommendation method for Earth observation mission workflow. This method is based on the aforementioned auxiliary recommendation system for Earth observation mission workflow and includes the following steps:

[0062] S1. Input data preparation;

[0063] S2. Preprocess the input data to form a dataset that can be received by the process mining unit and a dataset that can be received by the knowledge reasoning unit.

[0064] S3. The process mining unit performs data mining based on the received dataset to obtain the process model;

[0065] S4. The knowledge reasoning unit performs knowledge reasoning based on the received dataset to obtain a trained knowledge reasoning model.

[0066] S5. The process pruning unit prunes the process model by setting a threshold, and obtains the pruned process model.

[0067] S6. Recommend processes based on the pruned process model; and recommend parameters based on the process recommendations combined with the trained knowledge reasoning model.

[0068] S7. Combine the results of the combined process recommendation and the results of the parameter recommendation to generate the recommendation process output.

[0069] The data preparation includes historical data from Earth observation missions, time-series knowledge graph data, and observation requirements. Specifically, the format of historical data from Earth observation missions is <task type, event ID, head entity, tail entity, activity, timestamp <start time, end time>>; the time-series knowledge graph data is derived from the historical data of Earth observation missions, and the last three or four elements of the above tuples need to be extracted to construct a triple <head entity, tail entity, activity> or a quadruple <head entity, tail entity, activity, timestamp <start time, end time>>; the field list of observation requirements is <task type, requester, observation target, request start and end time>.

[0070] In S2, the dataset that the process mining unit can receive is formed according to the following steps:

[0071] S211. Set the data collection granularity corresponding to the task execution frequency; the data collection granularity corresponds to the execution frequency of different tasks, mainly divided into daily, monthly and grade levels; the daily level indicates that the execution frequency of a certain type of task is on a daily basis, such as meteorological observation tasks, and the other two granularities follow the same principle. Different granularities determine the distribution and size of the dataset, and at the same time can prevent some outdated data from entering the dataset.

[0072] S212. Extract historical data corresponding to the mission type from historical data of Earth observation missions according to the data acquisition granularity; the amount of data to be extracted can be manually set to a specific value, or it can be extracted according to the granularity level.

[0073] S213. The extracted historical data is processed into the form of triples, which are used as the dataset that the process mining unit can receive; the form of the triple is <event ID, activity, timestamp <start time>>.

[0074] In S2, the dataset that the knowledge reasoning unit can receive is formed according to the following steps:

[0075] S221. Set the data acquisition granularity corresponding to the task execution frequency;

[0076] S222. Extract triples or quadruples from the time-series knowledge graph data based on the granularity of data collection.

[0077] S223. Process triplet or quadruple data into numerical values, which can be used as a dataset that the knowledge reasoning unit can receive.

[0078] Compared to the process mining unit, which can only receive datasets containing triple information for a certain type of task, the time-series knowledge graph data includes triple or quadruple data covering all types of tasks.

[0079] In S3, heuristic operators are used for data mining, which mainly includes three steps: constructing direct follow relationships, constructing dependency metrics, and forming a causal matrix. After mining, a process model of a task is obtained, which is usually a causal matrix.

[0080] In S4, knowledge reasoning operators and temporal knowledge reasoning operators are used for knowledge reasoning, with the main purpose of realizing entity link prediction; after knowledge reasoning, a trained knowledge reasoning model is obtained.

[0081] In S5, the process pruning unit prunes the process model by setting thresholds to obtain the pruned process model. In one embodiment, process model pruning is achieved by setting two thresholds: the first threshold is the minimum number of direct follow-ups, and the second threshold is the minimum dependency metric. When both thresholds are met, the edge between the two activities is preserved; otherwise, pruning is performed, and the pruned process model is obtained after pruning.

[0082] In S6, the recommended process includes the following steps:

[0083] S611. Traverse each sub-process of the pruned process model from the starting point to the ending point, and each time select the sub-process connected by the edge with the largest direct following relationship and the largest dependency metric as the output.

[0084] S612. Combine all selected sub-processes to form a complete process as an alternative process.

[0085] S613. Based on the judgment requirements, select the previous... k The alternative processes are used as the result of the process recommendation. k is the default value.

[0086] In S6, the recommended parameters include the following steps:

[0087] S621. Traverse the previous sections in the recommended order. k One alternative process;

[0088] S622, Traverse the subprocesses in the order they are executed. i Sub-process nodes of the alternative process;

[0089] S622. Construct the triplet to be predicted for each subprocess. Head entity, , tail entity>, where, Indicates the The first alternative process The triplet to be predicted consists of each sub-process node. and It is an integer, counting from 0; Indicates the The first alternative process Each sub-process node; when hour, The header entity is the requester in the observation requirements field. <The person who made the request, ,?>;When At that time, the triplet to be predicted The head entity is The tail entities in the predicted tail entity list.

[0090] S623, Get each The list of head and tail entities to be connected;

[0091] S624. Based on the tail entity prediction scores, select the top entities from the list. s The result is recommended as a parameter.

[0092] In the knowledge reasoning operator of the knowledge reasoning unit, there is a scoring function (each knowledge reasoning operator has a scoring function), and tail entity prediction can obtain the score of each entity.

[0093] Each The list of connected head and tail entities is obtained by following these steps:

[0094] Triples to be predicted The data is input into the knowledge reasoning unit to obtain the prediction result. s Each tail entity is represented by a tail entity, forming a tail entity list. The tail entities in this list serve as the head entities for the next sub-process, enabling tail entity prediction for that sub-process, up to the triplet to be predicted. Content prediction;

[0095] Output each The list of head and tail entities to be connected.

[0096] When a failure occurs at a certain process node, it can be retrieved from each Available nodes can be selected in real time from the list of connected head and tail entities. When a subprocess or subprocess node parameter no longer meets the requirements, professionals can add, delete, or modify it. The changed process will be re-entered as historical data into the dataset of the next recommended process, achieving real-time data updates.

[0097] In one embodiment, the observation requirement is <meteorological observation, Meteorological Bureau, Hunan, <2024122>2000000, 2024122<2020000>>.

[0098] Input data preparation, the historical data of earth observation is shown in Table 1;

[0099] Table 1 Example table of historical data of earth observation

[0100]

[0101] Among them, entities are represented by and activities are represented by The timestamp is only replaced by numbers to simplify the display of specific year, month and day. The triples or quadruples of the temporal knowledge graph take the last three or four columns of Table 1.

[0102] The current task type is meteorological observation, and the data collection granularity is set to daily. The data that meets the following conditions is taken from Table 1: (1) The task type is meteorological observation; (2) The data of the n months before the demand time 0:00 on December 22, 2024, n is the preset value. Subsequently, the event ID column, activity column and timestamp column of this data are taken to form the dataset that can be received by the process mining unit of the current meteorological observation task, as shown in Table 2. The k months of data that meet the conditions when the event ID in Table 2 is 1009.

[0103] Table 2 Dataset that can be received by the process mining unit of meteorological observation task

[0104]

[0105] The data that meets the following conditions is taken from Table 1 to form the dataset that can be received by the knowledge reasoning unit: (1) The data of the n months before the demand event 0:00 on December 22, 2024; (2) Take the head entity column, tail entity column, activity column, timestamp <start time, end time> column; when the knowledge reasoning operator does not require temporal information, the timestamp column can be omitted.

[0106] Refer to Figure 3 for the process model obtained by data mining. Example 780(0.99) represents that the direct following count between two activities and is 780 and the dependence metric value is 0.99.

[0107] After adopting the knowledge reasoning operator, a trained knowledge reasoning model can be obtained, and entity link prediction can be realized by using this model.

[0108] The minimum number of direct follow-throughs is set to 50, and the minimum dependency metric is set to 0.9. The above process model is then pruned, resulting in the following pruned process model: Figure 4 As shown, the process model is simplified, and the process model pruning process has a noise reduction effect.

[0109] Take respectively ;

[0110] The process of selecting the top 3 candidate processes for meteorological observation tasks is as follows: For each subprocess, select the activities connected by the edges with higher direct follow counts and higher dependency metrics and add them to the candidate processes. The recommended result is: (1) < ,< >, , , >;(2)< ,< >, , , >;(3)< , , , >. Among them, < >This is a parallel subprocess.

[0111] The recommended process for obtaining the first three parameters for a meteorological observation task is as follows: The first sub-process node, whose triplet to be predicted is: Weather Bureau ,?>, will Inputting this into a trained knowledge reasoning model yields a list of the top three predicted entities. < >; respectively, the tail entity list The entity is used as the head entity of the next subprocess, and the output triplet to be predicted is... < >、< >、< >; < >、< >、< >; < >、< >、< These predicted triples will also output different lists of tail entities; repeating this process will allow you to traverse all sub-process nodes. Note that... and The tail entity set obtained by the three triplets to be predicted will be the same as the tail entity set obtained by the three triplets to be predicted. Reconstructing the predicted triplet leads to There will be many pairs of recommended parameters. At this point, only the top 3 pairs with the highest prediction scores for the tail entity are retained.

[0112] By combining the results of the above process recommendations and the results of parameter recommendations, a recommendation process output is generated, such as... Figure 5 As shown; will Figure 4 The activity relationships in the process become edges in the recommendation process, and the entity pairs in the parameter recommendation become process nodes in the recommendation process. Each entity has a corresponding entity recommendation list above / below it. When a process node fails, an available alternative node can be quickly selected from the list.

[0113] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, memory, a network interface, a display screen, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements an auxiliary recommendation method for Earth observation mission procedures. The display screen may be a liquid crystal display (LCD) or an e-ink display. The input device may be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0114] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps in the above method embodiments.

[0115] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0116] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0117] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0118] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An auxiliary recommendation method for earth observation task flow, characterized in that: The following steps are involved: S1. Input data preparation; S2. Preprocess the input data to form a data set that can be received by the process mining unit and the knowledge reasoning unit; S3, the process mining unit performs data mining based on the received data set to obtain a process model; S4, the knowledge reasoning unit performs knowledge reasoning according to the received data set to obtain a trained knowledge reasoning model; S5, the process pruning unit prunes the process model by setting a threshold to obtain a pruned process model; S6. Recommend processes based on the pruned process model; And parameter recommendations are made based on process recommendations combined with trained knowledge reasoning models; The process recommendation includes the following steps: S611, traverse each sub-process of the pruned process model from the starting point to the end point, and each time select the sub-process connected by the edge with the largest direct follow-up relationship and dependency measure as output; S612, combining all selected sub-processes to form a complete process as an alternative process; S613, according to the judgment needs, select the previous k As a result of process recommendation, k is the default value; The parameter recommendation includes the following steps: S621, traverse the front in the recommended order k Alternative processes; S622, traverse the sub-processes in the order in which they are executed. i Sub-process nodes of alternative processes; S622: Construct a triple to be predicted for each sub-process <header entity, , tail entity>, where, Indicates The first of the alternative processes The triples to be predicted are composed of sub-process nodes. and is an integer, starting from 0; Indicates The first of the alternative processes Sub-process nodes; S623, get each List of connected head and tail entities; S624. Select the first entity in the list according to the predicted score of the last entity. s The results are recommended as parameters; Each of the The connected head entity and tail entity list are obtained according to the following steps: The triplet to be predicted Input into the knowledge reasoning unit to get the prediction s tail entities to form a tail entity list. The tail entity in the tail entity list is used as the head entity of the next sub-process to realize the tail entity prediction of the next sub-process until all the triples to be predicted are Complete the forecast; Output each List of connected head and tail entities; S7. Combine the results of process recommendation and parameter recommendation to generate a recommended process output.

2. The method for assisting recommendation of earth observation task flow according to claim 1, characterized in that: The data preparation includes historical data of earth observation missions, time series knowledge graph data, and observation requirements.

3. The auxiliary recommendation method for earth observation task flow according to claim 1, characterized in that: In S2, the data set that the process mining unit can receive is formed according to the following steps: S211, setting the data collection granularity corresponding to the task execution frequency; S212, extracting historical data of a corresponding task type from historical data of earth observation tasks according to data collection granularity; S213: Process the extracted historical data into a triple form as a data set that can be received by the process mining unit.

4. The method for assisting recommendation of earth observation task flow according to claim 1, characterized in that: In S2, the data set that can be received by the knowledge reasoning unit is formed according to the following steps: S221, setting the data collection granularity corresponding to the task execution frequency; S222, extracting triples or quadruples of temporal knowledge graph data according to the data collection granularity; S223. Process the triple or quadruple data into numerical values ​​as a data set that can be received by the knowledge reasoning unit.

5. An auxiliary recommendation system for earth observation task flow, characterized in that: The auxiliary recommendation method for implementing the earth observation mission process as claimed in claim 1 comprises a data preparation unit, a process link generation module, a process node parameter generation module, a recommended process output unit and a manual interpretation unit; The data preparation unit inputs the data preparation into the process link generation module and the process node parameter generation module; The process link generation module includes a data preprocessing unit, a process mining unit and a process pruning unit; The data preprocessing unit performs data preprocessing, sets different data collection granularities according to different task types, forms a data set and outputs it to the process mining unit; The process mining unit mines the process model according to the received data set and outputs it to the process pruning unit; The process pruning unit processes the process model into available process links and outputs the links to the recommended process output unit; The process node parameter generation module includes a data preprocessing unit, a knowledge reasoning unit, and an entity linking unit; The data preprocessing unit encodes the triple or quadruple data to form a data set and inputs it into the knowledge reasoning unit; the knowledge reasoning unit outputs a trained knowledge reasoning model according to the received data set; the entity linking unit realizes the construction of the triple or quadruple to be predicted and the prediction of the tail entity; The recommendation process output unit integrates and outputs the recommendation process; The manual interpretation unit is used to edit process nodes and process node parameters.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images