Auxiliary recommendation system, method and equipment for earth observation task process and medium

Abstract

The invention provides an auxiliary recommendation system, method and device for earth observation task processes and a medium. The auxiliary recommendation system comprises a data preparation unit, a process link generation module, a process node parameter generation module, a recommendation process output unit and a manual interpretation unit. The flow link generation module comprises a data preprocessing unit, a flow mining unit and a flow pruning unit; and the flow node parameter generation module comprises a data preprocessing unit, a knowledge reasoning unit and an entity linking unit. According to the method, the recommendation of the process links and the recommendation of the process node parameters are separated, so that the process of recommending the earth observation task process is simplified; the process model can be mined from historical data of earth observation tasks, and autonomous updating of the process model is achieved; in addition, potential available parameter lists can be obtained in real time, and alternative schemes are provided for problems of flow node parameter conflicts, faults and the like.

Description

Technical Field

[0001] The present invention relates to the field of earth observation technology, and in particular to an auxiliary recommendation system, method, device and medium for earth observation task processes. Background Art

[0002] Earth observation mission is an important way to achieve real-time observation and monitoring of ground resources by coordinating ground systems and satellite resources. It is mainly used in civil fields such as disaster prevention, geographic mapping and meteorological observation. With the rapid development of aerospace technology and the increasing types and numbers of various earth observation needs, the execution process of earth observation missions has become increasingly complex. At the same time, due to the particularity of earth observation missions, that is, the execution process of the mission must be reliable, most of the existing earth observation missions are fixed process templates, and require manual execution of the process according to the rules. It cannot effectively deal with the problems of task process generation and control brought about by task expansion and technological expansion. The update of equipment or cumbersome process nodes has brought more burdens to operators and reviewers. Therefore, a technical solution is urgently needed to solve the above problems. Summary of the invention

[0003] In view of the deficiencies in the prior art, the present invention provides an auxiliary recommendation system, method, device and medium for earth observation mission processes.

[0004] To achieve the above object, the technical solution adopted in the present invention is as follows: On the one hand, the present invention provides an auxiliary recommendation system for earth observation task 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 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 a 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 an available process link and outputs it 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.

[0005] On the other hand, the present invention provides an auxiliary recommendation method for earth observation task flow, which is implemented based on the auxiliary recommendation system for earth observation task flow, and includes the following steps: 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 recommend parameters based on the process recommendation combined with the trained knowledge reasoning model; S7. Combine the results of process recommendation and parameter recommendation to generate a recommended process output.

[0006] Furthermore, the data preparation includes historical data of earth observation tasks, time series knowledge graph data, and observation requirements.

[0007] Further, 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.

[0008] Further, in S2, the data set that the knowledge reasoning unit can receive 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.

[0009] Further, in S6, 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.

[0010] Further, in S6, 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.

[0011] Furthermore, each 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 head and tail entities to connect to.

[0012] 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 implements the steps of an auxiliary recommendation method for an earth observation mission process when executing the computer program.

[0013] On the other hand, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for assisting recommendation of an earth observation mission process.

[0014] Compared with the prior art, the technical effects that the present invention can produce are: The auxiliary recommendation system, method, device and medium for earth observation task process provided by the present invention separate the recommendation of process link and the recommendation of process node parameters, thus simplifying the process of earth observation task process recommendation. The mining of process link is realized by process mining unit; the mining of process node parameters is realized by knowledge reasoning unit, and the two are combined to realize auxiliary recommendation of earth observation task process, which can better assist professionals in process recommendation decision-making and greatly save labor costs.

[0015] Compared with the prior art, the present invention mines process models from historical data of earth observation missions, which can reduce the burden on professionals and better handle the more complex mapping relationships and changes in functional modules brought about by process model updates, thereby realizing autonomous updates of process models.

[0016] The process node parameter generation module adopted by the present invention is different from the traditional method of relying on manpower to establish system relationship mapping. The present invention can obtain a potential available parameter list in real time, and provide alternative solutions for process node parameter conflicts, failures and other problems, thereby better assisting professionals in generating earth observation mission processes. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 creative work.

[0018] Figure 1 A schematic diagram of the structure of an auxiliary recommendation system for an earth observation task process provided by an embodiment; Figure 2 A flowchart of an auxiliary recommendation method for an earth observation mission process provided by an embodiment; Figure 3 A schematic diagram of a process model provided by an embodiment; Figure 4A schematic diagram of a pruned process model provided by an embodiment; Figure 5 A schematic diagram of a recommended process result provided by an embodiment, wherein Figure 5 (a) is a schematic diagram of the recommended process (1). Figure 5 (b) is a schematic diagram of the recommended process (2). Figure 5 (c) is a schematic diagram of the recommended process (3). DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Reference Figure 1 , an embodiment provides an auxiliary recommendation system 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 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 a 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 an available process link and outputs it 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.

[0021] Through the manual interpretation unit, users can customize and edit process nodes and process node parameters.

[0022] Reference Figure 2An embodiment provides an auxiliary recommendation method for an earth observation task process. The method is implemented based on the auxiliary recommendation system for an earth observation task process, and includes the following steps: 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 recommend parameters based on the process recommendation combined with the trained knowledge reasoning model; S7. Combine the results of process recommendation and parameter recommendation to generate a recommended process output.

[0023] The data preparation includes historical data of earth observation tasks, time series knowledge graph data, and observation requirements. Specifically, the format of the historical data of earth observation tasks is <task type, event ID, head entity, tail entity, activity, timestamp <start time, end time>>; the time series knowledge graph data comes from the historical data of earth observation tasks, and the last three or four elements of the above tuple 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, start and end time of requirements>.

[0024] In S2, the data set that the process mining unit can receive is formed according to the following steps: S211. Set the data collection granularity corresponding to the task execution frequency. The data collection granularity corresponds to the execution frequency of different tasks, which is mainly divided into day level, month level and year level. The day level indicates that the execution frequency of a certain type of task is on a daily basis, such as a meteorological observation task. The other two granularities are similar. Different granularities determine the distribution and size of the data set, and can prevent some expired data from entering the data set.

[0025] S212. Extracting historical data of a corresponding task type from historical data of earth observation tasks according to data collection granularity; the amount of extracted data may be manually set to a specific value, or may be extracted according to the granularity level.

[0026] S213, processing the extracted historical data into a triplet form as a data set that can be received by the process mining unit; the triplet form is <event ID, activity, timestamp <start time>>.

[0027] 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.

[0028] Compared with the data set that the process mining unit can receive, which only contains triple information of a certain type of task, the triple or quadruple data of the temporal knowledge graph data covers all types of tasks.

[0029] In S3, heuristic operators are used for data mining, which mainly includes three steps: building direct follow-up relationships, building dependency measurement tables, and forming causal matrices. After mining, a process model of a task is obtained, usually a causal matrix.

[0030] In S4, knowledge reasoning operators and temporal knowledge reasoning operators are used for knowledge reasoning, the main purpose of which is to achieve entity link prediction; after knowledge reasoning, a trained knowledge reasoning model is obtained.

[0031] In S5, the process pruning unit prunes the process model by setting a threshold to obtain a pruned process model. In one embodiment, the process model is pruned by setting two thresholds, the first threshold is the minimum number of direct follow-ups, and the second threshold is the minimum dependency measure. When both thresholds are met, the edge between the two activities is retained, otherwise it is pruned. After the pruning is completed, the pruned process model is obtained.

[0032] In S6, 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.

[0033] In S6, 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; when hour, The header entity is the requester in the observation request field. <Requester, ,?>; when When the triplet to be predicted is The head entity is The tail entity in the predicted tail entity list.

[0034] 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.

[0035] There is a scoring function in the knowledge reasoning operator of the knowledge reasoning unit (each knowledge reasoning operator has a scoring function), and the score of each entity can be obtained by performing tail entity prediction.

[0036] 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 the triple to be predicted Content realization prediction; Output each List of head and tail entities to connect to.

[0037] When a process node fails, Select available nodes in real time from the list of connected head entities and tail entities; when the parameters of a sub-process or sub-process node no longer meet the requirements, professionals can perform addition, deletion, modification, and adjustment operations. The changed process will be re-entered as historical data into the dataset of the next recommended process to achieve real-time data update.

[0038] In one embodiment, the observation requirement is <Meteorological Observation, Meteorological Bureau, Hunan, <2024122>2000000, 2024122<2020000>>.

[0039] Input data preparation, the historical data of earth observation is shown in Table 1; Table 1 Example Table of Historical Data of Earth Observation

[0040] Among them, entities are represented by and activities are represented by The time stamp 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.

[0041] The current task type is meteorological observation, and the data collection granularity is set to daily. The data that meets the following conditions is retrieved from Table 1: (1) The task type is meteorological observation; (2) The time stamp is the data of the n months before the required time of 0:00 on December 22, 2024, n is a preset value. Subsequently, the event ID column, activity column, and time stamp 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 first k months of data that meet the conditions when the event ID in Table 2 is 1009.

[0042] Table 2 Dataset That Can Be Received by the Process Mining Unit of the Meteorological Observation Task

[0043] The data that meets the following conditions is retrieved from Table 1 to form the dataset that can be received by the knowledge reasoning unit: (1) The time stamp is the data of the n months before the required event of 0:00 on December 22, 2024; (2) The head entity column, tail entity column, activity column, and time stamp <start time, end time> column are taken; when the knowledge reasoning operator does not require temporal information, the time stamp column can be omitted.

[0044] Refer to Figure 3 for the process model obtained by data mining. Example 780 (0.99) represents the direct following count of 780 and the dependency metric value of 0.99 between two activities and ​

[0045] After using the knowledge reasoning operator, a trained knowledge reasoning model can be obtained, which can be used to realize entity link prediction.

[0046] Set the minimum number of direct follow-ups to 50 and the minimum dependency measure to 0.9, and prune the above process model. The pruned process model is as follows Figure 4 As shown, it can be seen that the process model is simplified and the process model pruning process has a denoising effect.

[0047] Take separately ; The process of selecting the first three candidate processes for the meteorological observation task is as follows: for each sub-process, select the activities connected by the edges with higher direct follow-up times and dependency metrics and add them to the pending candidate processes. The recommended results are: (1) < ,< >, , , >;(2)< ,< >, , , >;(3)< , , , >. Among them < > for parallel subprocesses.

[0048] The recommended process for taking the first three parameters of the meteorological observation task is: is the first sub-process node, and its triples to be predicted are <Weather Bureau, ,?>, will Input into the trained knowledge reasoning model, and you can get the predicted top 3 tail entity list < >; respectively put the tail entity in the list The entity is used as the head entity of the next sub-process and the output triple to be predicted is < >、< >、< > < >、< >、< > < >、< >、< >; These triples to be predicted will also output different tail entity lists, and repeating this process can traverse all sub-process nodes. Note and The tail entity set of the triples to be predicted will be Recompose the triples to be predicted, resulting in There will be many recommended parameter pairs formed. At this time, only the top 3 pairs with the highest tail entity prediction scores are retained.

[0049] Combining the above process recommendation results and parameter recommendation results, we can generate the recommended process output, such as Figure 5 As shown; Figure 4 The activity relationships in the example become edges in the recommendation process, and the entity pairs in the parameter recommendation become process nodes in the recommendation process. There is a corresponding entity recommendation list above / below each entity. When a process node fails, an available replacement node can be quickly selected from the list.

[0050] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an auxiliary recommendation method for an earth observation mission process is implemented. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball, or touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0051] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above method embodiment when executing the computer program.

[0052] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0053] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may 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 many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0054] The technical features of the above embodiments may 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.

[0055] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An auxiliary recommendation system for earth observation task flow, characterized in that: It includes 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.

2. The auxiliary recommendation method for earth observation task flow based on the system as claimed in claim 1 is 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; S7. Combine the results of process recommendation and parameter recommendation to generate a recommended process output.

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

4. The auxiliary recommendation method for earth observation task flow according to claim 2, 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.

5. The auxiliary recommendation method for earth observation task flow according to claim 2, 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.

6. The method for assisting recommendation of earth observation task flow according to claim 2, characterized in that: In S6, 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.

7. The method for assisting recommendation of earth observation task flow according to claim 2, characterized in that: In S6, 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.

8. The method for assisting recommendation of earth observation task flow according to claim 7, characterized in that: 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 head and tail entities to connect to.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 2 to 8 are implemented.

10. 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 2 to 8 are implemented.

Images