Method, apparatus, and device for generating an execution plan for a satellite imaging mission

Abstract

Embodiments of the present disclosure provide a method, device, electronic equipment, storage medium and program product for generating an execution plan for a satellite imaging task. The method comprises: obtaining task information associated with a target satellite imaging task; mapping a target task set using a pre-defined meta-action library matching an imaging mode and imaging constraint parameters matching the imaging mode to generate an initial candidate action set; processing the initial candidate action set using a state expansion algorithm to generate an effective plan set; calculating a priority weight of each effective plan in the effective plan set using a weight parameter based on a multi-objective optimization function; and sorting each effective plan in the effective plan set according to the priority weight to obtain an execution plan sequence. The method of the embodiments of the present disclosure can automatically generate an effective plan sequence, thereby improving the decision-making efficiency of decision-makers to a certain extent.

Description

Technical Field

[0001] This disclosure relates to the field of satellite imaging mission planning technology, and specifically to a method, apparatus, electronic device, computer-readable storage medium, and computer program product for generating execution plans for satellite imaging missions. Background Technology

[0002] Satellite imaging mission planning is crucial in highly dynamic and complex scenarios such as rescue and disaster monitoring. However, current mainstream traditional mission planning systems (such as Joint Operations Planning and Execution System (JOPES), Joint Mission Planning System (JMPS), or General Mission Planning Platform / Action Planning Collaboration System (APS)) suffer from deep-seated design problems in their system architecture, typically treating closely related aspects such as mission plan generation, resource scheduling, and conflict resolution in a fragmented manner. This architecture lacks modular collaboration mechanisms and adaptive real-time feedback, failing to construct an efficient, robust, and closed-loop dynamic decision-making framework. Consequently, during the execution of satellite imaging missions, the entire planning process is slow to respond, the generated solutions are rigid, and it is difficult to effectively support the smooth execution of satellite imaging missions in complex, dynamic, and time-sensitive scenarios. Summary of the Invention

[0003] To address the aforementioned technical problems, the present disclosure provides a solution. Embodiments of the present disclosure provide a method, apparatus, electronic device, computer-readable storage medium, and computer program product for generating execution plans for satellite imaging missions.

[0004] According to a first aspect of the present disclosure, a method for generating an execution plan for a satellite imaging mission is provided, wherein the method includes: Obtain mission information associated with the target satellite imaging mission; wherein, the mission information includes a set of target missions, imaging modes, imaging constraint parameters matching the imaging modes, and weight parameters; Using a predefined meta-action library that matches the imaging pattern and imaging constraint parameters that match the imaging pattern, the target task set is mapped to generate an initial candidate action set; wherein, the initial candidate action set includes multiple meta-actions, and each meta-action is associated with parameters including name, time window, required resources, preceding actions, and completion target; The initial candidate action set is processed by a state expansion algorithm to generate a set of effective plans; wherein, the state expansion algorithm is an algorithm that combines depth-first search and resource constraints. Based on the multi-objective optimization function, the priority weight of each effective plan in the effective plan set is calculated using the weight parameters. Based on the priority weight, each valid plan in the set of valid plans is sorted to obtain an execution plan sequence; wherein, the associated parameters of each execution plan include action order, total time, priority index, and resource usage.

[0005] According to a second aspect of the present disclosure, an apparatus for generating an execution plan for a satellite imaging mission is provided, wherein the apparatus includes: The data acquisition unit is configured to acquire task information associated with the target satellite imaging task; wherein the task information includes a target task set, an imaging mode, imaging constraint parameters matching the imaging mode, and weight parameters. The meta-action mapping unit is configured to: map the target task set using a predefined meta-action library that matches the imaging mode and imaging constraint parameters that match the imaging mode to generate an initial candidate action set; wherein the initial candidate action set includes multiple meta-actions, and each meta-action is associated with parameters including name, time window, required resources, preceding actions, and completion target; The effective plan generation unit is configured to: process the initial candidate action set through a state expansion algorithm to generate an effective plan set; wherein the state expansion algorithm is an algorithm that combines depth-first search and resource constraints; The priority weight calculation unit is configured to: calculate the priority weight of each effective plan in the effective plan set based on the weight parameters using the multi-objective optimization function; The sequence sorting generation unit is configured to sort each valid plan in the set of valid plans according to the priority weight to obtain an execution plan sequence; wherein, the associated parameters of each execution plan include action order, total time consumption, priority index, and resource usage.

[0006] According to a third aspect of the present disclosure, an electronic device is provided, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method of the present disclosure for generating an execution plan for a satellite imaging mission.

[0007] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, the storage medium storing a computer program for executing the method of the present disclosure for generating an execution plan for a satellite imaging mission.

[0008] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when executed by a processor, the computer program implements the method for generating an execution plan for a satellite imaging mission as described in the present disclosure.

[0009] As described above, the apparatus for generating execution plans for satellite imaging missions provided in this disclosure employs real-time conflict detection technology within a depth-first search framework to automatically intercept invalid branches such as time-series overlaps, logical contradictions, and resource contention. It can output effective plans in milliseconds without manual intervention in the event of sudden parameter changes. An independent replication mechanism based on a resource occupancy table strictly ensures the time-sharing exclusivity of resources. When critical resources are occupied, they are automatically delayed to the next available window. Simultaneously, mandatory verification of pre-dependencies ensures the reliability of the mission instruction chain closed loop. An innovative comprehensive optimization model integrating time efficiency, resource utilization balance, and target coverage is constructed, supporting dynamic weight configuration and outputting sorting schemes according to multi-dimensional priorities. This provides precise quantitative decision support for high-time-efficiency tasks, reducing overall response latency by two orders of magnitude and significantly improving collaborative stability. Attached Figure Description

[0010] The above and other objects, features, and advantages of this disclosure will become more apparent from the more detailed description of the embodiments thereof in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the embodiments of this disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0011] Figure 1 This is a flowchart illustrating a method for generating an execution plan for a satellite imaging mission, provided in an exemplary embodiment of this disclosure. Figure 2 This is a public announcement Figure 1 An exemplary flowchart of a method for generating an execution plan for a satellite imaging mission is provided in this embodiment; Figure 3 This is a public announcement Figure 1 Another exemplary flowchart of the method for generating an execution plan for a satellite imaging mission provided in the embodiments; Figure 4 This is a public announcement Figure 1 This embodiment provides yet another exemplary flowchart of a method for generating an execution plan for a satellite imaging mission; Figure 5 This is a public announcement Figure 1 A further exemplary flowchart of the method for generating an execution plan for a satellite imaging mission provided in the embodiments; Figure 6 This is a schematic diagram of an exemplary user terminal interface in Embodiment 5 (Scenario Embodiment) of this disclosure; Figure 7 This is another exemplary user terminal interface diagram in Embodiment 5 (Scenario Embodiment) of this disclosure; Figure 8This is a schematic diagram of an exemplary user terminal interface "target input" in Embodiment 5 (Scenario Embodiment) of this disclosure; Figure 9 This is a schematic diagram of an exemplary user terminal interface "Advanced Configuration" in Embodiment 5 (Scenario Embodiment) of this disclosure; Figure 10 This is a schematic diagram of the "Effective Base Plan" output of an exemplary user terminal interface in Embodiment 5 (Scenario Embodiment) of this disclosure; Figure 11 This is a schematic diagram of the structure of an apparatus for generating an execution plan for a satellite imaging mission, provided in an exemplary embodiment of this disclosure; Figure 12 This is a schematic diagram of the structure of an application embodiment of the electronic device disclosed herein. Detailed Implementation

[0012] The present disclosure will be further described below with reference to the embodiments shown in the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present disclosure, and not all embodiments of the present disclosure. It should be understood that the present disclosure is not limited to the exemplary embodiments described herein.

[0013] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0014] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of this disclosure are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0015] It should also be understood that in the embodiments disclosed herein, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more.

[0016] It should also be understood that any component, data or structure mentioned in the embodiments of this disclosure can generally be understood as one or more unless expressly defined or given to the contrary in the context.

[0017] Furthermore, the term "and / or" in this disclosure is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this disclosure generally indicates that the preceding and following related objects have an "or" relationship.

[0018] It should also be understood that the description of the various embodiments in this disclosure emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0019] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0020] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0021] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0022] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0023] Example 1 Figure 1 This is a schematic flowchart of a method for generating an execution plan for a satellite imaging mission, provided by an exemplary embodiment of this disclosure. The method can be executed on a server, wherein the server may include, but is not limited to, a server or a cloud computing platform.

[0024] Specifically, refer to Figure 1 The method for generating an execution plan for a satellite imaging mission includes: S110. Obtain mission information associated with the target satellite imaging mission.

[0025] The task information includes a set of target tasks, an imaging mode, imaging constraint parameters matching the imaging mode, and weight parameters.

[0026] S120. Using a predefined meta-action library that matches the imaging pattern and imaging constraint parameters that match the imaging pattern, the target task set is mapped to generate an initial candidate action set.

[0027] The initial candidate action set includes multiple meta-actions, and each meta-action is associated with parameters including name, time window, required resources, preceding actions, and completion target.

[0028] S130. The initial candidate action set is processed by the state expansion algorithm to generate a set of effective plans; wherein the state expansion algorithm is an algorithm that combines depth-first search and resource constraints.

[0029] This algorithm, which integrates depth-first search and resource constraints, can automatically handle issues such as time conflicts, logical conflicts, and resource contention. It intercepts invalid branches in real time through conflict detection and outputs and sorts valid plans within milliseconds, requiring no manual intervention. Specific implementation details are described below.

[0030] S140. Based on the multi-objective optimization function, the priority weight of each effective plan in the effective plan set is calculated using the weight parameters.

[0031] The multi-objective optimization function comprehensively considers the three dimensions of "time, resources, and objectives" to conduct a comprehensive quantitative evaluation of candidate plans. Specific implementation details are described below.

[0032] S150. Sort each valid plan in the set of valid plans according to the priority weight to obtain the execution plan sequence.

[0033] Each of the execution plan's associated parameters includes action order, total time consumption, priority index, and resource usage.

[0034] Optionally, the user may upload the "task information" to the server that is the executing entity in step S110 using a terminal or other form of data interface that communicates with the executing entity. Alternatively, the "task information" may also be stored in a corresponding data server; then the server that is the executing entity in step S110 may obtain the "seismic dataset and migration velocity field" by communicating with the data server.

[0035] Optionally, the target mission set associated objects include at least one mission-executing satellite, at least one target imaging area, and at least one ground data receiving station. The mission-executing satellite is used to photograph the target imaging area and then transmit the photographic results back to the ground data receiving station.

[0036] Optionally, the imaging mode includes single imaging and multiple imaging.

[0037] Single imaging means the satellite only needs to take one picture of the target area. Multiple imaging means the satellite needs to take multiple pictures of the target area.

[0038] Optionally, the weighting parameters include a time weighting parameter, a resource weighting parameter, and a target weighting parameter. Specifically, when matching the single-shot imaging mode, the time weighting parameter is higher than both the resource weighting parameter and the target weighting parameter; when matching the multiple-shot imaging mode, the target weighting parameter is higher than both the time weighting parameter and the resource weighting parameter.

[0039] The predefined meta-action library can be set up in advance according to the needs of the satellite imaging field, and then configured in the form of an application programming interface (API) that can be provided to the outside world; the execution subject (server) that performs the steps of Embodiment 1 of this disclosure can call the services of the predefined meta-action library through the API.

[0040] For each meta-action associated parameter in the initial candidate action set, if it is expressed as a field, it can be (id, time_window, required_resources, pre_meta_actions, goals).

[0041] Specifically, `id` represents a unique identifier, i.e., a name (e.g., `MA_1Send1`, representing a sending action), which can be stored and managed using dictionary key-value pairs (`model["meta_actions"][action_id]`) for fast retrieval. `time_window` represents a time window (e.g., `[(0,0.05),(0.05,0.1)]`), which can be used to dynamically detect conflicts. Specifically, for the occupied interval `bookings[r]` of each resource `r`, an interval intersection check is performed (`end≤s_iorstart≥e_i`). If there is no overlap, the time window is retained; otherwise, it is discarded. For example, an instruction annotation action needs to occupy a communication channel for a certain period of time. If multiple actions occupy the channel simultaneously, resources will be insufficient, so it is necessary to record the occupied interval of each resource separately. `required_resources` represents a list of resource requirements (i.e., required resources) (e.g., `["R1"]`), which can be generated into an independent resource booking table `new_bookings` through deep copying. During updates, new intervals are added and sorted to ensure resource state isolation. `pre_meta_actions` represents the pre-meta dependency logic (i.e., pre-actions). During method execution, if it is a nested list (e.g., [["MA_A","MA_B"], ["MA_C"]]), then each group must satisfy at least one action (any(pinexecutedforpingroup)); if it is a regular list (e.g., ["MA_A","MA_B"]), then any action must have been executed (any(pinexecuted)). If verification fails, it is pruned and skipped. The purpose of this field is to ensure the logical completeness of the execution plan. For example, the data return action can only be performed after imaging data is available, meaning that the imaging action is a pre-dependency of the return action. `goals` represents the set of goals (i.e., the completed goals) (e.g., ["S1"]). During the implementation phase of this method, the completed goals can be dynamically updated through the set operation `completed|set(goals)`, driving the state transition. Further details will be provided in subsequent implementations.

[0042] As described above, the method for generating execution plans for satellite imaging missions provided by the embodiments of this disclosure can automatically handle problems such as time conflicts, logical conflicts, and resource competition. It can intercept invalid branches in real time through conflict detection, and output and sort valid plans within milliseconds without manual intervention; thereby improving the decision-making efficiency of decision-makers to a certain extent.

[0043] Example 2 Based on the above embodiments, as an optional implementation, for the single-shot imaging mode, the imaging constraint parameters include performing the imaging action only once for each target imaging region, denoted as single-shot imaging constraint. For the multiple-shot imaging mode, the imaging constraint parameters include a lower limit on the number of times the imaging action is performed for each target imaging region and a lower limit on the total number of times the imaging action is performed, denoted as multiple-shot imaging constraint.

[0044] Based on the above optional implementation methods, refer to Figure 2 Step S120, "mapping the target task set using a predefined meta-action library matching the imaging mode and imaging constraint parameters matching the imaging mode to generate an initial candidate action set," may include: S1210. In response to the imaging mode being a single-shot imaging mode, the single-shot imaging meta-action library is invoked, and the target task set is mapped based on the single-shot imaging constraints to generate an initial candidate action set.

[0045] S1220. In response to the imaging mode being a multiple imaging mode, the multiple imaging meta-action library is invoked, and the target task set is mapped based on the multiple imaging constraints to generate an initial candidate action set.

[0046] The initial candidate action set may include, for example, instruction uploading, imaging, and data transmission.

[0047] For multiple imaging modes, the initial candidate action set includes the corresponding copied imaging meta-actions based on the lower limit of the number of times the imaging action is executed for each target imaging region.

[0048] It should be noted that the sorting strategy differs depending on the predefined meta-action library invoked. For example, when invoking a single-imaging meta-action library (e.g., in a simulated fishing boat search and rescue scenario), the meta-actions in the execution plan are sorted by time priority. Conversely, when invoking a multiple-imaging meta-action library (e.g., in a simulated disaster monitoring scenario), the meta-actions in the execution plan are sorted by target priority (i.e., receiving satellite images). Specific sorting implementation details are described in the examples below and will not be elaborated upon here.

[0049] Example 3 Based on the above embodiments, optionally, refer to Figure 3 Step S130, "processing the initial candidate action set using the state expansion algorithm to generate a set of effective plans," may include: S1310. Using an algorithm that combines depth-first search (DFS) and resource constraints (RCPSP), perform a state-space search on the initial candidate action set with constraints of resource conflict detection, time window filtering, and pre-dependency verification to generate a set of effective plans.

[0050] As an optional example, step S1310 may include the following steps: S13110. Establish a nine-tuple state model and push the initial state onto the state stack. The associated parameters of the nine-tuple state model include the current action sequence, resource occupancy record table, set of executed meta-actions, global timestamp, set of completed targets, resource usage count, state identifier, state path, and set of consumed feedback actions.

[0051] It should be noted that if the nine-tuple state is represented in field form, it can be represented as follows: State=(seq, bookings, executed, current_time, completed, res_usage, state_id, state_path, used_sends).

[0052] Wherein, seq represents the current action sequence; bookings represents the resource usage record table; executed represents the set of executed meta-actions; current_time represents the global timestamp (initially 0); completed represents the set of completed targets; res_usage represents the resource usage count, used to count the number of times each resource is called; state_id represents the state identifier (e.g., Sta0), used to identify the position of the state in the reachability graph; state_path represents the state path (e.g., ["Sta0", "Sta1"]), used to record the transition path from the initial state to the current state; used_sends represents the set of consumed feedback actions, that is, the set of used transmission actions, used to track the transmission actions that have been used by subsequent actions to ensure logical completeness.

[0053] S13120. In response to the current state satisfying the state termination condition, the action sequence corresponding to the current state is stored in the set of valid plans.

[0054] The state termination conditions include the completion of the target set including the target task set, and the fact that all meta-actions in the executed meta-action set have been used by the return actions in the consumption return action set.

[0055] In a specific example, step S13120 can be implemented as follows: Check whether the completed target set contains all the target tasks input by the user; check whether all executed sending actions have been consumed by subsequent return actions; when the imaging mode is multiple imaging (assuming multiple imaging of target area C), check whether the number of imaging executions N of target imaging area C satisfies the multiple imaging constraint; that is, the number of imaging executions N is not less than the minimum number of imaging executions required for the target imaging area C in the task information.

[0056] If all the above conditions are met after verification, the current state is stored in the feasible plan set. Otherwise, proceed to step S13130.

[0057] S13130. In response to the current state not meeting the state termination condition, the set of executed meta-actions corresponding to the current state is used to filter out unexecuted meta-actions that meet the pre-dependency verification in the initial candidate action set, and a candidate action set is generated.

[0058] The aforementioned prerequisite dependency verification means that the prerequisite action on which the current meta-action depends has been completed.

[0059] In a specific example, step S13130 ​​can be implemented as follows: First, exclude all meta-actions that have been added to the set of executed meta-actions from the initial candidate action set. Then, for the remaining meta-actions, check their prerequisite dependencies. Specifically, if the prerequisite dependency is a regular list (e.g., ["MA_A","MA_B"]), then any meta-action in that list must have been executed. If the prerequisite dependency is a nested list (e.g., [["MA_A","MA_B"],["MA_C"]]), then at least one meta-action in each group of the nested list must have been executed. Finally, add the meta-actions that pass the prerequisite dependency verification to the candidate action set.

[0060] S13140. Using the time window associated with each meta-action in the candidate action set and the required resources in the resource occupancy record table in the current state, the effective meta-actions and corresponding time windows that do not conflict with resources are determined.

[0061] In a specific example, step S13140 can be implemented as follows: For example, firstly, for each resource required by a candidate meta-action, it can be checked whether the time window of the meta-action overlaps with all time periods in the resource occupation record table where the resource has been occupied; if there is an overlap, it is determined to be a resource conflict; otherwise, it is determined that the resource is not conflicted. Then, in the set of meta-actions without resource conflicts, based on the time windows of each valid meta-action, meta-actions with resource conflicts whose start time is no earlier than the current global timestamp are selected and recorded as the first set of meta-actions; then, the meta-action corresponding to the time window with the earliest end time is selected from the first set of meta-actions as a valid meta-action, and its corresponding time window is obtained synchronously.

[0062] Optionally, the above interval overlap conflict detection can be expressed using the logical formula: conflict = any (not(end<=sor start>=e) for (s,e) in bookings[R]). Here, s represents the start time of the time period during which the resource has been occupied; e represents the end time of the time period during which the resource has been occupied; start represents the start time of the time window corresponding to the current meta-action; end represents the end time of the time window corresponding to the current meta-action; and bookings(R) represents the set of time periods for which the resource has been booked.

[0063] Based on the above method, valid meta-actions that do not conflict with resources and their corresponding time windows can be determined.

[0064] S13150. Perform a state update for each of the valid meta-actions and store the updated state into the state stack.

[0065] In a specific example, step S13150 can be implemented as follows: The status update can create an independent branch based on the current status data, and update the current action sequence, resource usage record table, executed meta-action set, global timestamp, completed target set, resource usage count, status identifier, status path, and consumed feedback action set in the independent branch.

[0066] Specifically, a deep copy can be used to replicate all data of the current state to ensure branch state isolation; the time period occupied by the new action can be added to the corresponding resource occupation record table and sorted by start time; the global timestamp can be updated to the larger value of the current global time and the end time of the new action; the goal completed by the new action can be added to the set of completed goals; and a unique new state identifier can be generated.

[0067] S13160, iteratively execute steps S13120 to S13150 until there are no states to be processed in the state stack, and obtain the set of effective plans based on the states that have been processed in the state stack.

[0068] The action sequence, total time consumption, and resource usage associated with each effective plan are determined sequentially based on the current action sequence, the global timestamp, and the resource usage count, respectively. It is understood that through steps S13110~S13160, the action sequence associated with the effective plan can be determined based on the current action sequence, the total time consumption can be determined based on the global timestamp, and the resource usage can be determined based on the resource usage count; that is, through iterative steps, effective plans can be gradually determined, and the corresponding parameters can be adaptively determined.

[0069] Alternatively, after iteratively executing steps S13110 to S13160, a tree-like text can be recursively generated using the state path `state_path`. For example, `k` moves from state `Sta0` (i.e., the initial state) to state `S1` (`MA_1Send1 [0-0.05]`), then from state `Sta1` (`MA_1Send1 [0-0.05]`) to state `Sta2` (`MA_1Send2 [0-0.05]`), and so on, until all state paths are fully represented.

[0070] Example 4 Based on the above embodiments, referring to Figure 4 Step S140, "Calculating the priority weight of each effective plan in the effective plan set using the weight parameters based on the multi-objective optimization function," may include: S1410. For each effective plan, calculate the corresponding time efficiency index using the duration of the effective plan.

[0071] The duration is the time difference between the start time of the first meta-action and the end time of the last meta-action in the effective plan.

[0072] In a specific example, the calculation of the time efficiency index corresponding to the effective plan can be achieved using the following formula:

[0073] Wherein, TimeEfficiency represents the time efficiency index corresponding to each effective plan; Duration represents the duration corresponding to each effective plan; This represents the smoothing factor, with a value of 0.01.

[0074] S1420. For each effective plan, use the resource usage count and balance adjustment factor of the effective plan to calculate the resource utilization rate index corresponding to the effective plan.

[0075] The balance adjustment factor is determined based on the variance of the resource usage count corresponding to the effective plan.

[0076] In an optional example, the "calculation of the resource utilization rate index corresponding to each effective plan" can be achieved using the following formula:

[0077]

[0078]

[0079] Among them, ResourceUtilization represents the resource utilization rate indicator corresponding to each effective plan; This represents the resource usage count for each valid plan; This represents the smoothing factor, with a value of 0.01. Indicates the balance adjustment factor; This indicates the actual number of times the k-th resource has been used. This indicates resource disparity and is used to measure the balance of resource allocation.

[0080] S1430. For each effective plan, use the set of completed objectives of the effective plan to calculate the target weight index corresponding to the effective plan.

[0081] The calculation of the target weight index aims to evaluate the overall value of an effective plan by the number of targets completed. For each effective plan (e.g., Ai={MA1,MA2,...,MAn}, where each action MAi is associated with a set of targets Gi={gi1,gi2,...,gin}), the meta-action sequence is traversed, and the targets of each action are merged into a total target list.

[0082] Furthermore, the overall list objective can be represented as:

[0083] in, This indicates an expansion operation for the list, preserving duplicates.

[0084] Based on this, the total number of targets is:

[0085] Therefore, the target weight indicator corresponding to each effective plan can be expressed as: .

[0086] S1440. For each valid plan, substitute the time weight parameter, resource weight parameter, target weight parameter, time efficiency index, resource utilization rate index, and target weight index into the multi-objective optimization function to calculate the corresponding priority weight, which is used as the priority index.

[0087] The multi-objective optimization function is a weighted fusion function of the time efficiency index, resource utilization index, and target weight index.

[0088] In a specific example, the calculation of the priority index can be achieved using the following formula:

[0089] in, This represents the priority weight corresponding to each valid plan; This represents the time weighting parameter, used to balance the proportion of time efficiency in the overall priority. This represents the resource weight parameter, used to balance the proportion of resource utilization in the overall priority; This represents the target weight parameter, used to balance the proportion of the target weight in the overall priority.

[0090] Optionally, the time weighting parameter can be adjusted to match different imaging modes. Resource weight parameters Target weight parameters The values ​​also differ. For example, in the case of single-shot imaging mode, the time weighting parameter... The value can be 0.55, which is the resource weight parameter. The value can be 0.4, which is the target weight parameter. The value can be 0.05. In the case of multiple imaging mode, the time weighting parameter... The value can be 0.05, which is the resource weight parameter. The value can be 0.4, which is the target weight parameter. The value can be 0.55.

[0091] Based on the above embodiments, referring to Figure 5 Step S150, "sorting each valid plan in the set of valid plans according to the priority weight," may include: S1510. In response to the imaging mode being single imaging, sort each effective plan in the effective plan set according to the priority weight from smallest to largest to obtain a first initial sequence. S1520. In response to the existence of valid plans with the same priority weight in the first primary sequence, the valid plans with the same priority weight are reordered according to the direction of duration from shortest to longest. S1530. In response to the imaging mode being multiple imaging, each effective plan in the effective plan set is sorted according to the priority weight from smallest to largest to obtain a second initial sequence. S1540. In response to the existence of valid plans with the same priority weight in the second primary sequence, the valid plans with the same priority weight are reordered according to the direction of the target weight index from small to large.

[0092] It should be noted that steps S1510 to S1540 here correspond to the specific implementation of the method described in Embodiment 2, which states that "different predefined meta-action libraries are called, and the corresponding sorting strategies are also different. For example, when calling a single imaging meta-action library (for example, in the case of a simulated fishing boat search and rescue scenario), the meta-actions in the execution plan are sorted with time priority. As another example, when calling a multiple imaging meta-action library (for the case of a simulated disaster monitoring scenario), the meta-actions in the execution plan are sorted with target priority (i.e., receiving satellite images)."

[0093] Optionally, the method for generating an execution plan for a satellite imaging mission provided in this disclosure may further include historical storage and comprehensive sorting steps. The historical storage refers to storing valid plans associated with any target mission; the comprehensive sorting may involve sorting all relevant valid plans in the entire historical storage according to indicators such as priority.

[0094] Based on historical data storage, the method for generating execution plans for satellite imaging missions provided in this disclosure further includes retrospectively retrieving valid plans from the historical data storage. The server, in cooperation with the user terminal, can send the retrieved valid plans to the user for review.

[0095] Example 5 This embodiment is an exemplary application scenario. The scenario involves using the "method for generating an execution plan for a satellite imaging mission" provided in the above embodiments of this disclosure to execute a "certain satellite imaging mission".

[0096] In this embodiment, the "method for generating an execution plan for a satellite imaging mission" provided in the above embodiments of this disclosure can be expressed programmatically and integrated into software to run on a server. The server is connected to a user terminal to facilitate front-end and back-end interaction.

[0097] During the task execution phase, a user interface (e.g., such as...) is used on the user terminal. Figure 6 , Figure 7 In the graphical interface shown, you can input your target imaging task according to the input prompts, and simultaneously input the configuration parameters that match the target imaging task.

[0098] For example, if the user's target imaging task is to perform multiple imaging operations on target regions C and D, then the user can refer to... Figure 8The input prompt shown is "Multiple imaging mode can input target combinations S1, S2, C, D, RCC, RCD (using 1 satellite and 2 satellites to image regions C and D)". In the "Target Input" interface window, enter "S1, S2, C, D, RCC, RCD"; where S1 is satellite, S2 is satellite, C is region, D is region, RCC is ground data receiving station, and RCD is ground data receiving station.

[0099] Simultaneously, refer to Figure 9 In the "Advanced Configuration" interface, you can input the following: minimum C imaging (i.e., the lower limit of the number of imaging actions to be executed) is 4, minimum D imaging (i.e., the lower limit of the number of imaging actions to be executed) is 4, minimum total imaging (i.e., the lower limit of the number of total imaging actions to be executed) is 8, time weight (i.e., the time weight parameter) is 0.05, resource weight (i.e., the resource weight parameter) is 0.40, and imaging number weight (i.e., the target weight parameter) is 0.55.

[0100] After completing the above steps, the user can click the "Generate Plan" button in the graphical interface. Then, the server responds to the "Generate Plan" instruction and starts running the "Method for Generating an Execution Plan for a Satellite Imaging Mission" as described in this embodiment of the disclosure based on the input data, thereby generating a valid plan sequence.

[0101] The output format of the "effective plan sequence" can be referred to as follows: Figure 10 In this embodiment, a total of 56 valid plans can be generated. Figure 10 The first four are shown as examples.

[0102] Reference Figure 10 Each effective plan consists of four parts: action sequence, total time, priority, and resource usage. Taking Plan 1 as an example, the action sequence includes four meta-actions: MA_2Send1, MA_21ImageA, MA_21ImageB, and MA_1Receive1. Each meta-action is marked with a time window; for example, the time window corresponding to MA_2Send1 is (0-0.05). Total time is the duration of the effective plan, which is the time difference between the start time of the first meta-action and the end time of the last meta-action in the effective plan. The priority, i.e., the "priority weight" mentioned in the previous embodiment, is calculated according to the method of the previous embodiment. Resource usage refers to the resources required for the execution of the effective plan, such as communication bandwidth, frequency band, etc. Optionally, the resources mentioned in this example can be divided into five categories: R1 to R5.

[0103] As described above, the method for generating execution plans for satellite imaging missions provided in this disclosure employs real-time conflict detection technology within a depth-first search framework. This automatically intercepts invalid branches such as time-series overlaps, logical contradictions, and resource contention, enabling the output of effective plans in milliseconds without manual intervention during sudden parameter changes. An independent replication mechanism based on a resource occupancy table strictly guarantees the time-sharing exclusivity of resources. When critical resources are occupied, they are automatically delayed to the next available window. Simultaneously, mandatory verification of pre-dependencies ensures the reliability of the mission instruction chain closed loop. An innovative comprehensive optimization model integrating time efficiency, resource utilization balance, and target coverage is constructed, supporting dynamic weight configuration and outputting sorting schemes according to multi-dimensional priorities. This provides precise quantitative decision support for high-time-efficiency tasks, reducing overall response latency by two orders of magnitude and significantly improving collaborative stability.

[0104] Example 6 It should be understood that the methods described in the foregoing embodiments for generating execution plans for satellite imaging missions can also be similarly extended to the apparatuses described below for generating execution plans for satellite imaging missions. For simplicity, they are not described in detail.

[0105] Figure 11 This is a schematic diagram of an apparatus for generating an execution plan for a satellite imaging mission, provided in an exemplary embodiment of this disclosure. (Refer to...) Figure 11 The device includes: The data acquisition unit 110 is configured to acquire task information associated with the target satellite imaging task; wherein the task information includes a target task set, an imaging mode, imaging constraint parameters matching the imaging mode, and weight parameters. The meta-action mapping unit 120 is configured to: map the target task set using a predefined meta-action library that matches the imaging mode and imaging constraint parameters that match the imaging mode to generate an initial candidate action set; wherein the initial candidate action set includes multiple meta-actions, and each meta-action is associated with parameters including name, time window, required resources, preceding actions, and completion target; The effective plan generation unit 130 is configured to: process the initial candidate action set through a state expansion algorithm to generate an effective plan set; wherein the state expansion algorithm is an algorithm that combines depth-first search and resource constraints; The priority weight calculation unit 140 is configured to: calculate the priority weight of each effective plan in the effective plan set based on the weight parameters using the multi-objective optimization function; The sequence sorting generation unit 150 is configured to: sort each valid plan in the set of valid plans according to the priority weight to obtain an execution plan sequence; wherein, each execution plan is associated with parameters including action order, total time consumption, priority index, and resource usage.

[0106] As described above, the apparatus for generating execution plans for satellite imaging missions provided in this disclosure employs real-time conflict detection technology within a depth-first search framework to automatically intercept invalid branches such as time-series overlaps, logical contradictions, and resource contention. It can output effective plans in milliseconds without manual intervention when sudden parameter changes occur. An independent replication mechanism based on a resource occupancy table strictly ensures time-sharing exclusivity of resources. When critical resources are occupied, they are automatically delayed to the next available window. Simultaneously, mandatory verification of pre-dependencies ensures the reliability of the mission instruction chain closed loop. An innovative comprehensive optimization model integrating time efficiency, resource utilization balance, and target coverage is constructed, supporting dynamic weight configuration and outputting sorting schemes according to multi-dimensional priorities. This provides precise quantitative decision support for high-time-efficiency tasks, reducing overall response latency by two orders of magnitude and significantly improving collaborative stability.

[0107] Example 7 In addition, this disclosure also provides an electronic device, including: a memory for storing a computer program; and a processor for executing the computer program stored in the memory, wherein when the computer program is executed, it implements the method for generating an execution plan for a satellite imaging mission as described in any of the above embodiments of this disclosure.

[0108] Figure 12 This is a schematic diagram of the structure of an application embodiment of the electronic device disclosed herein. Below, reference is made to… Figure 12 This describes an electronic device according to embodiments of the present disclosure. The electronic device may be either or both of a first device and a second device, or a standalone device independent of them, which may communicate with the first device and the second device to receive acquired input signals from them.

[0109] like Figure 12As shown, the electronic device includes one or more processors and memory. The processor may be a central processing unit (CPU) or other processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. The memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may execute the program instructions to implement the methods for generating execution plans for satellite imaging missions and / or other desired functions described in the various embodiments of this disclosure above.

[0110] In one example, the electronic device may further include input and output devices, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown). Furthermore, the input device may include, for example, a keyboard, a mouse, etc. The output device can output various information to the outside, including determined distance information, direction information, etc. The output device may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0111] Of course, for the sake of simplicity, Figure 12 Only some of the components of the electronic device relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.

[0112] In addition to the methods and apparatus described above, embodiments of this disclosure may also be computer program products comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods for generating execution plans for satellite imaging missions according to various embodiments of this disclosure as described in the foregoing portions of this specification.

[0113] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0114] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions that, when executed by a processor, cause the processor to perform the steps in the method for generating an execution plan for a satellite imaging mission according to various embodiments of this disclosure as described in the foregoing portion of this specification.

[0115] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0116] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as ROM, RAM, magnetic disk, or optical disk.

[0117] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0118] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0119] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0120] The methods and apparatus of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.

[0121] It should also be noted that in the apparatus, devices, and methods of this disclosure, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions to this disclosure.

[0122] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0123] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A method for generating an execution plan for a satellite imaging mission, characterized in that, The method includes: Obtain mission information associated with the target satellite imaging mission; wherein, the mission information includes a set of target missions, imaging modes, imaging constraint parameters matching the imaging modes, and weight parameters; Using a predefined meta-action library that matches the imaging pattern and imaging constraint parameters that match the imaging pattern, the target task set is mapped to generate an initial candidate action set. The initial candidate action set is processed by the state expansion algorithm to generate a set of effective plans; Based on the multi-objective optimization function, the priority weight of each effective plan in the effective plan set is calculated using the weight parameters. Based on the priority weights, each valid plan in the set of valid plans is sorted to obtain an execution plan sequence.

2. The method according to claim 1, characterized in that, The target mission set associated objects include at least one mission-executing satellite, at least one target imaging area, and at least one ground data receiving station; The imaging modes include single imaging and multiple imaging; The weighting parameters include a time weighting parameter, a resource weighting parameter, and a target weighting parameter; wherein, when matching the single imaging mode, the time weighting parameter is higher than the resource weighting parameter and the target weighting parameter; when matching the multiple imaging mode, the target weighting parameter is higher than the time weighting parameter and the resource weighting parameter. The initial candidate action set includes multiple meta-actions, and each meta-action is associated with parameters including name, time window, required resources, preceding actions, and completion target; Each execution plan is associated with parameters including action order, total time, priority metric, and resource usage.

3. The method according to claim 2, characterized in that, Matching the single-imaging mode, the imaging constraint parameters include that the imaging action for each target imaging region is executed only once, denoted as single-imaging constraint; The imaging constraint parameters for matching the multiple imaging mode include a lower limit on the number of imaging actions to be performed for each target imaging region and a lower limit on the total number of imaging actions to be performed, denoted as multiple imaging constraint. The step of mapping the target task set using a predefined meta-action library matching the imaging pattern and imaging constraint parameters matching the imaging pattern to generate an initial candidate action set includes: In response to the imaging mode being a single-shot imaging mode, the single-shot imaging meta-action library is invoked, and the target task set is mapped based on the single-shot imaging constraints to generate an initial candidate action set. In response to the imaging mode being a multiple imaging mode, the multiple imaging meta-action library is invoked, and the target task set is mapped based on the multiple imaging constraints to generate an initial candidate action set.

4. The method according to claim 2, characterized in that, The state expansion algorithm is an algorithm that combines depth-first search and resource constraints; The process of processing the initial candidate action set using the state expansion algorithm to generate a set of effective plans includes: An algorithm that integrates depth-first search and resource constraints is used to perform a state-space search on the initial candidate action set, with constraints including resource conflict detection, time window filtering, and pre-dependency verification, to generate a set of effective plans.

5. The method according to claim 4, characterized in that, An algorithm combining depth-first search and resource constraints is used to perform a state-space search on the initial candidate action set, constrained by resource conflict detection, time window filtering, and pre-dependency verification, including: Establish a nine-tuple state model and push the initial state onto the state stack; The nine-tuple state model associated parameters include the current action sequence, resource occupancy record table, set of executed meta-actions, global timestamp, set of completed targets, resource usage count, state identifier, state path, and set of consumed feedback actions. In response to the current state meeting the state termination condition, the action sequence corresponding to the current state is stored in the valid plan set; wherein, the state termination condition includes the completed target set containing the target task set, and the meta-actions in the executed meta-action set have all been used by the feedback actions in the consumption feedback action set; In response to the current state not meeting the state termination condition, the set of executed meta-actions corresponding to the current state is used to filter out unexecuted meta-actions that meet the prerequisite dependency verification from the initial candidate action set, thereby generating a candidate action set; wherein, the prerequisite dependency verification means that the prerequisite action on which the current meta-action depends has been completed. By matching the time window associated with each meta-action in the candidate action set with the required resources in the resource occupancy record table in the current state, valid meta-actions with no resource conflicts and their corresponding time windows are determined. Perform a state update for each of the valid meta-actions and store the updated state into the state stack; The process iteratively executes the steps from storing the action sequence corresponding to the current state into the effective plan set to storing the updated state into the state stack, until there are no states to be processed in the state stack. Based on the states that have been processed in the state stack, the effective plan set is obtained. The action sequence, total time consumption, and resource usage associated with each effective plan are determined sequentially based on the current action sequence, global timestamp, and resource usage count, respectively.

6. The method according to claim 5, characterized in that, The calculation of the priority weight of each effective plan in the effective plan set based on the multi-objective optimization function and using the weight parameters includes: For each effective plan, the time efficiency index corresponding to the effective plan is calculated using the duration of the effective plan; wherein, the duration is the time difference between the start time of the first meta-action and the end time of the last meta-action in the effective plan; For each effective plan, the resource utilization rate index corresponding to the effective plan is calculated using the resource usage count and the balance adjustment factor of the effective plan; wherein, the balance adjustment factor is determined based on the variance of the resource usage count corresponding to the effective plan. For each effective plan, the target weight index corresponding to the effective plan is calculated using the set of completed targets of that effective plan; For each valid plan, the time weight parameter, resource weight parameter, target weight parameter, time efficiency index, resource utilization rate index, and target weight index are substituted into the multi-objective optimization function to calculate the corresponding priority weight, which is used as the priority index. The multi-objective optimization function is a weighted fusion function of the time efficiency index, resource utilization index, and target weight index.

7. The method according to claim 6, characterized in that, The step of sorting each valid plan in the set of valid plans according to the priority weight includes: In response to the imaging mode being single imaging, each effective plan in the effective plan set is sorted according to the priority weight from smallest to largest to obtain a first initial sequence. In response to the existence of valid plans with the same priority weight in the first primary sequence, the valid plans with the same priority weight are reordered according to the direction of duration from shortest to longest. In response to the imaging mode being multiple imaging, each effective plan in the effective plan set is sorted according to the priority weight from smallest to largest to obtain a second initial sequence. In response to the existence of valid plans with the same priority weight in the second primary sequence, the valid plans with the same priority weight are reordered according to the direction of the target weight index from smallest to largest.

8. An apparatus for generating an execution plan for a satellite imaging mission, characterized in that, The device includes: The data acquisition unit is configured to acquire task information associated with the target satellite imaging task; wherein the task information includes a target task set, an imaging mode, imaging constraint parameters matching the imaging mode, and weight parameters. The meta-action mapping unit is configured to: map the target task set using a predefined meta-action library that matches the imaging mode and imaging constraint parameters that match the imaging mode, to generate an initial candidate action set; The effective plan generation unit is configured to process the initial candidate action set using a state expansion algorithm to generate an effective plan set. The priority weight calculation unit is configured to: calculate the priority weight of each effective plan in the effective plan set based on the weight parameters using the multi-objective optimization function; The sequence sorting generation unit is configured to sort each valid plan in the set of valid plans according to the priority weight to obtain an execution plan sequence.

9. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method for generating an execution plan for a satellite imaging mission as described in claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for executing the method for generating an execution plan for a satellite imaging mission as described in claims 1 to 7.

Images