CN116485162B - Satellite observation task planning method, system and device based on graph calculation - Google Patents

Satellite observation task planning method, system and device based on graph calculation Download PDF

Info

Publication number
CN116485162B
CN116485162B CN202310740403.9A CN202310740403A CN116485162B CN 116485162 B CN116485162 B CN 116485162B CN 202310740403 A CN202310740403 A CN 202310740403A CN 116485162 B CN116485162 B CN 116485162B
Authority
CN
China
Prior art keywords
task
satellite
target
entity
graph
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310740403.9A
Other languages
Chinese (zh)
Other versions
CN116485162A (en
Inventor
李新明
厉海燕
王志淋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Edge Intelligence Of Cas Co ltd
Original Assignee
Edge Intelligence Of Cas Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Edge Intelligence Of Cas Co ltd filed Critical Edge Intelligence Of Cas Co ltd
Priority to CN202310740403.9A priority Critical patent/CN116485162B/en
Publication of CN116485162A publication Critical patent/CN116485162A/en
Application granted granted Critical
Publication of CN116485162B publication Critical patent/CN116485162B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06316—Sequencing of tasks or work
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G06N5/022—Knowledge engineering; Knowledge acquisition
    • G06N5/025—Extracting rules from data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Strategic Management (AREA)
  • Educational Administration (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • General Engineering & Computer Science (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Abstract

The invention provides a satellite observation task planning method, a system and a device based on graph calculation, which relate to the technical field of satellite observation task planning, and mainly comprise the following steps: defining a satellite observation task planning model based on graph calculation, wherein the satellite observation task planning model comprises a basic knowledge graph and a task situation graph; based on task demands, carrying out sub-graph extraction on related information in the basic knowledge graph, and taking the sub-graph extraction as a task situation graph frame; calculating key data of a task situation map, constructing the task situation map, and calculating through task planning weights to obtain a task planning result; updating the task situation map based on the updated position of the dynamic target; and carrying out task planning weight calculation in an iteration mode, and updating a task planning result. The method and the system effectively improve satellite utilization rate and satellite observation task planning efficiency, intuitively show periodic relations among satellites, orbits and targets, and can also realize continuous observation task planning of dynamic targets.

Description

Satellite observation task planning method, system and device based on graph calculation
Technical Field
The invention relates to the technical field of satellite observation task planning, in particular to a satellite observation task planning method, system and device based on graph calculation.
Background
At present, aiming at the satellite earth observation task planning problem, a common solution is to firstly extract constraint conditions by combining the characteristics of the satellite, then establish formal description or mathematical model of the problem, and further solve the model by adopting a related algorithm. Wherein the mathematical model trends use constraint satisfaction models or multi-objective optimization models, and the solution algorithm trends use smart search algorithms or modified smart search algorithms. In a mission planning method, two aspects are generally focused on: firstly, modeling the service field, and secondly, a model-based search algorithm. The existing task planning algorithm comprises dynamic scheduling, greedy iteration, tabu search, linear programming, genetic algorithm, ant colony algorithm, integer programming and the like. These mission planning algorithms typically model the domain with classical mathematical models such as the traditional knapsack problem, TSP, etc., abstract the problem into mathematical problems, and find related solution space search algorithms.
However, the conventional task planning method considers the visual relationship between the observation target and the satellite at different running moments independently, and in this way, the problem that the revisit period of the satellite is taken as a planning time unit and can be reused in the whole satellite life period is ignored; moreover, the traditional task planning method has insufficient intuitiveness, cannot embody the periodic relation among satellites, orbits and targets in the problem, and has poor man-machine interaction effect; in addition, the traditional task planning method takes targets with maximum satellite resource utilization efficiency, maximum observable targets and the like as planning algorithm design basis, and does not consider task requirements of continuous observation of targets.
Disclosure of Invention
The invention aims to provide a satellite observation task planning method, system and device based on graph calculation, which are used for solving at least one of the technical problems in the prior art.
In order to solve the above technical problems, the present invention provides a satellite observation task planning method based on graph calculation, which includes the following steps:
step 1, defining a satellite observation task planning model based on graph calculation, wherein the satellite observation task planning model comprises a basic knowledge graph and a task situation graph; the model comprises nodes and edges, wherein the nodes represent a certain entity, and the edges represent a relation between the certain two entities; the model represents the entity or the label of the relation through different triples, and represents the relation, the attribute description of the entity and the attribute description of the relation through different triples; constructing a basic knowledge graph according to the general knowledge in the satellite observation field;
step 2, carrying out sub-graph extraction on related information in the basic knowledge graph based on task requirements, and taking the sub-graph extraction as a task situation graph frame;
step 3, calculating key data of the task situation map based on the task situation map framework, constructing the task situation map, and obtaining a task planning result through task planning weight calculation; the task situation map comprises a target entity, wherein the attribute description of the target entity comprises a target type, and the target type comprises a dynamic target and a static target;
Step 4, updating a task situation map based on the updated position of the dynamic target;
and 5, iteratively executing the task planning weight calculation in the step 3, and updating the task planning result.
Through the steps, a situation map can be established for a satellite earth observation task based on a data organization mode of map calculation, and a basic knowledge map facing to satellite, satellite orbit and target real-time state is used for calculating the periodic relation between the longitude and latitude of the target and the longitude and latitude of a satellite point under the satellite along with the time.
In a possible embodiment, the step 1 is performed by means of a binary setRepresentation entity->Corresponding tag->；
Through tripletsRepresentation entity->And->Relation between->；
Through tripletsRepresentation entity->Is>A description of attributes, wherein->Representation entity->Is>Personal attribute name,/-, for>A value representing the attribute;
by two tuplesExpress relationship->Corresponding tag->；
Through tripletsExpress relationship->Is>A description of attributes, wherein->Express relationship->Is>Personal attribute name,/-, for>Representing the value corresponding to the attribute.
Thus, the nodes and edges of the satellite observation task planning model can be conveniently defined.
In a possible implementation manner, the basic knowledge graph is a general knowledge graph oriented to the satellite observation task planning field, and is used for providing knowledge for sub-graph generation of a task situation graph, including satellite knowledge, target knowledge and the like; the satellite knowledge comprises a programmable satellite set, load information of satellites, orbit characteristic information and the like; the target knowledge comprises target basic information, target geographic positions, target observation requirements and the like.
In one possible embodiment, the set of planable satellites includes satellite entities; the attribute description of the satellite entity includes satellite name, satellite usage class (e.g., civilian, commercial, etc.), time of transmission, satellite regression period, satellite orbit time consumption, satellite orbit point latitude where the satellite orbit point is highest in northern hemisphere latitude, etc.
In a possible embodiment, the loading information of the satellite includes a loading entity, and the attribute description of the loading entity includes a loading name, a loading type, a resolution, a breadth, a yaw angle, and the like.
In a possible embodiment, the target basic information includes a target entity; the attribute description of the target entity comprises a target name and a target type.
In a possible embodiment, the target geographic location comprises a target location entity, and the attribute description of the target location entity comprises a discovery target time, a target location, and the like.
In a possible embodiment, the satellite entityAnd (2) load entity->The relation between them can be expressed as +.>The label of the relationship may be expressed as；
The load entityLoad type and target entity- >A relation between the load type matching target entities, which can be expressed as +.>The label of the relation can be expressed as +.>The attribute description of the relationship includes a matching type name;
the load entityResolution and target entity->A relation between the resolution matching target entities, which can be expressed as +.>The label of the relation can be expressed as +.>The attribute description of the relationship includes matching resolution;
the target entityWith the target positionPut entity->The relation between them can be expressed as +.>The label of the relationship may be expressed as。
In a possible implementation manner, the task situation map includes satellites, satellite orbits and target real-time states meeting task requirements;
screening satellites meeting task requirements in a programmable satellite set to obtain a satellite set meeting task requirements, wherein each satellite in the set is used as a satellite entityThe tags of the satellite entities may be represented as；
For target information in task demands, a single target is taken as a target entityThe tag of the target entity may be denoted +.>The method comprises the steps of carrying out a first treatment on the surface of the The attribute description of the target entity comprises a target type (dynamic target or static target), a target name, a target longitude, a target latitude, a current state time and the like;
For each satellite in the satellite set meeting the task requirement, dividing the orbit information of the satellite in the task duration according to the moment that the satellite passes through the satellite orbit satellite point and the satellite point latitude with the highest northern hemisphere latitude, wherein each circle of orbit is taken as a satellite orbit entityThe method comprises the steps of carrying out a first treatment on the surface of the The tag of the satellite orbital entity can be expressed asThe method comprises the steps of carrying out a first treatment on the surface of the The attribute description of the satellite orbit entity comprises orbit start time, orbit end time, orbit turns and the like;
for satellite orbital entitiesAnd satellite entity->The relation between, defined as satellite entity +.>Operating on satellite orbital entity->The relationship can be expressed as +.>The label of the relation can be expressed as +.>；
For satellite entitiesIs +.>The relation between, defined as satellite entity +.>Matching target entity->The relationship can be expressed as +.>The label of the relationship may be expressed as；
For target entitiesIs>The relationship between is defined as satellite orbit entityVisible target entity->The relationship can be expressed as +.>The label of the relation can be expressed as +.>。
In a possible implementation manner, the sub-graph extraction in the step 2 includes:
step 21, receiving task demands, identifying target positions and time in the task demands, task constraint and other information, and creating a task;
Step 22, inquiring whether related target information exists in the basic knowledge graph based on the target name: if yes, comparing and updating target position entity information associated with the target; if not, the target is used as a newly added target entity in the basic knowledge graph, and a relation between the load entity and the target entity is established according to task requirements, wherein the relation comprises resolution matching, load type matching and the like;
and step 23, extracting load entity information associated with the target and corresponding satellite entity information according to the relation between the satellite load entity and the target entity in the basic knowledge graph.
Therefore, the related information in the basic knowledge graph can be conveniently extracted according to task requirements and used for subsequent processing.
In a possible implementation manner, the specific method for calculating the key data of the task situation map in the step 3 includes:
step 31, acquiring satellite imaging requirements in task requirements, including target information, imaging requirements required by a target, task starting time, task ending time and the like;
step 32, establishing a target entity according to satellite imaging requirementsThe attribute description of the entity includes a target type, target longitude +.>Target latitude->Task Start time- >Task end time->Etc.;
step 33, matching satellites according to imaging requirements required by the target, and obtaining a satellite list;
step 34, for each satellite in the satellite list, establishing an orbital entity for that satellite；
Step 35, for each satellite in the satellite list, calculating a target entityOrbital entity with corresponding satellite->Relationship between them.
Through the steps, the target entity, the track entity and the relation between the target entity and the track entity are conveniently constructed.
In a possible embodiment, the step 34 includes:
step 341, calculating orbit data of the satellite at the task starting time according to the satellite list, the task starting time and the task ending time;
step 342, obtaining the orbit feature data of the satellite from the basic knowledge graph, including satellite regression periodTime spent by a circle of satellite orbit>Satellite orbit satellite lower point is at the highest satellite lower point latitude of northern hemisphere latitude；
Step 343, calculating the number of turns of the satellite in the task timeDefining one circle of satellite at task starting time as a first circle;
step 344, calculating the number of turns of the satellite in the primary regression period；
Step 345, based on the latitude of the satellite at the satellite point below the task start time orbit Calculating satellite arrival circle->Time of hour->；
Step 346, according to the number of turnsDefine satellite orbital entity name->, wherein ,/>Represents the number of track turns, the value of which is equal to +.>；
Step 347, calculating a track start time of the track, the attribute description of which may be expressed asAttribute value->Defined as->Refers to the initial circle at latitude +.>Time of hour plus track turns +.>Reduced time to track consumption>Is a product of (2);
step 348, defining the physical attribute of the number of track turns of the track, which may be expressed in particular as, wherein />The value is track circle number +.>。
Through the steps, the orbit entity of each satellite in the satellite list can be established。
In a possible embodiment, the step 35 includes:
step 351, based on the latitude of the orbital satellite point at the start time of the taskCalculating the time of arrival of the satellite at the target latitude in the orbit +.>；
Step 352, obtaining the time for the satellite to reach the target latitude under the first orbit based on the above formulaAfter that, the longitude +.>Latitude->；
Step 353, calculateAnd->Longitude difference +.>；
Step 354, calculating the undersea points of the same longitude as the target in all the tracks, and selecting the circle closest to the target as the nearest circle number Thus, the target can be nearest to the undersea point;
step 355, establishing a relationship between the target entity and the satellite orbit entity, wherein the number of turns of the satellite orbit entity isThe relation may be expressed specifically as +.>。
Through the steps, the relationship between the target entity and the satellite orbit entity can be conveniently and accurately calculated.
In a possible implementation manner, the specific method for calculating the task planning weight in the step 3 includes:
step 36, reading the task situation map to obtain the target entityRelationship and methodAll satellite orbital entities associated +.>；
Step 37, obtaining a preset planning direction of the current task, wherein the preset planning direction comprises objective functions such as time optimization, quality optimization and the like, and establishing a task planning evaluation weight factor set according to the preset planning direction； wherein ,/>Is a time weighting factor, the weighting factor is related to satellite imaging time, and the earlier the imaging time is, the larger the weight is; />Is an imaging quality weight factor, the weight factor is related to the satellite imaging side sway angle, and the weight is larger when the side sway angle is smaller;
step 38, extracting target entityVisible time window set, calculating time window weight value set ； wherein ,/>Indicate->Weight values for the respective time windows;
step 39, time window weight value setSequencing according to the weight values, and selecting a time window with the highest weight value as a task planning scheme of the current task; the mission planning scheme includes a certain time window specifying that a certain mission uses a certain satellite.
Through the steps, the task planning scheme can be reasonably determined according to the situation map content and the weight value.
In a possible implementation manner, the method for updating the task situation map in the step 4 includes:
step 41, when the position of the dynamic target is updated, creating a target entityThe attribute description of the target entity comprises the time of target update and the position of target movement;
step 42, targeting the target entityStep 35 is performed iteratively.
Through the steps, the latest position of the dynamic target can be accurately injected into the task situation map in real time, so that the dynamic target can be adjusted and planned periodically in the follow-up process.
The application also provides a satellite observation task planning system based on graph calculation, which comprises a data receiving module, a data processing module and a result generating module:
The data receiving module is used for receiving task demands and the updated positions of the dynamic targets;
the data processing module comprises a flow control unit, a calculation model unit, a basic knowledge graph unit and a task situation graph unit;
the calculation model unit is used for storing a satellite orbit calculation model, a subgraph extraction model, a situation map key data calculation model, a situation map updating model and a task planning model:
the satellite orbit calculation model is used for calculating orbit data of the satellite at the task starting time according to the satellite list, the task starting time and the task ending time;
the subgraph extraction model is used for extracting relevant load entity information and satellite entity information in the basic knowledge graph unit based on task requirements to form a subgraph as a task situation graph frame, and outputting the subgraph to the task situation graph unit;
the situation map key data calculation model is used for establishing a target entity and matching satellites according to satellite imaging requirements in task requirements, wherein the target entity comprises a dynamic target and a static target, the satellite orbit calculation model is called to calculate the orbit entity of each matching satellite, and the relation between the target entity and the orbit entity of the corresponding matching satellite is calculated and output to the task situation map unit;
The situation map updating model is used for creating a target entity based on the updating position of the dynamic target, calling the situation map key data calculating model, iteratively calculating the relation between the target entity and the orbit entity corresponding to the matched satellite, and outputting the relation to the task situation map unit;
the task planning model calls a task situation map, acquires a target entity and all related satellite orbit entities, calculates a time window weight value of each task based on a preset planning direction, and selects a time window with the highest weight value as a task planning scheme of the current task;
the basic knowledge graph unit is used for storing a basic knowledge graph;
the task situation map unit is used for storing the task situation map;
the flow control unit is used for inputting task demands into the subgraph extraction model and the situation map key data calculation model, inputting the update position of a dynamic target into the situation map update model, controlling the task planning model to perform iterative calculation and monitoring the running condition of each unit in the module;
and the result generation module is used for issuing the task planning scheme.
The application also provides a satellite observation task planning device based on graph calculation, which comprises a processor, a memory and a bus, wherein the memory stores instructions and data which can be read by the processor, the processor is used for calling the instructions and the data in the memory to execute any satellite observation task planning method based on graph calculation, and the bus is used for transmitting information among all functional components.
By adopting the technical scheme, the invention has the following beneficial effects:
the invention provides a satellite observation task planning method, a system and a device based on graph calculation, which provides a data organization mode based on graph calculation, establishes a situation knowledge graph facing a real-time state of a satellite, a satellite orbit and a target, comprises key data such as a relation among entities, entity attributes and the like, can calculate a periodic relation between the longitude and latitude of the target and the longitude and latitude of a satellite point along with the change of time, effectively improves the satellite utilization rate and the satellite observation task planning efficiency, intuitively shows the periodic relation among the satellite, the orbit and the target, and can realize the continuous observation task planning of a dynamic target.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are some embodiments of the invention and that other drawings may be obtained from these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a satellite observation task planning method based on graph calculation provided by an embodiment of the invention;
FIG. 2 is a flow chart of sub-graph extraction provided in an embodiment of the present invention;
FIG. 3 is a flow chart of a key data method for calculating a task situation map according to an embodiment of the present invention;
FIG. 4 is a flowchart of step 34 according to an embodiment of the present invention;
FIG. 5 is a flowchart showing a step 35 according to an embodiment of the present invention;
FIG. 6 is a flowchart illustrating a method for task planning weight calculation according to an embodiment of the present invention;
fig. 7 is a diagram of a satellite observation task planning system based on graph calculation according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The invention is further illustrated with reference to specific embodiments.
It should be further noted that the following specific examples or embodiments are a series of optimized arrangements of the present invention for further explaining specific summary, and all the arrangements may be combined or used in association with each other.
Embodiment one:
as shown in fig. 1, the satellite observation task planning method based on graph calculation provided in this embodiment includes the following steps:
step 1, defining a satellite observation task planning model based on graph calculation, wherein the satellite observation task planning model comprises a basic knowledge graph and a task situation graph; the model comprises nodes and edges, wherein the nodes represent a certain entity, and the edges represent a relation between the certain two entities; the model represents the entity or the label of the relation through different triples, and represents the relation, the attribute description of the entity and the attribute description of the relation through different triples; constructing a basic knowledge graph according to the general knowledge in the satellite observation field;
step 2, carrying out sub-graph extraction on related information in the basic knowledge graph based on task requirements, and taking the sub-graph extraction as a task situation graph frame;
Step 3, calculating key data of the task situation map based on the task situation map framework, constructing the task situation map, and obtaining a task planning result through task planning weight calculation; the task situation map comprises a target entity, wherein the attribute description of the target entity comprises a target type, and the target type comprises a dynamic target and a static target;
step 4, updating a task situation map based on the updated position of the dynamic target;
and 5, iteratively executing the task planning weight calculation in the step 3, and updating the task planning result.
Through the steps, a situation map can be established for a satellite earth observation task based on a data organization mode of map calculation, and a basic knowledge map facing to satellite, satellite orbit and target real-time state is used for calculating the periodic relation between the longitude and latitude of the target and the longitude and latitude of a satellite point under the satellite along with the time.
Further, in the step 1, the two groups are passedRepresentation entity->Corresponding tag->；
Through tripletsRepresentation entity->And->Relation between->；
Through tripletsRepresentation entity->Is>A description of attributes, wherein->Representation entity->Is>Personal attribute name,/-, for>A value representing the attribute;
by two tuples Express relationship->Corresponding tag->；
Through tripletsExpress relationship->Is>A description of attributes, wherein->Express relationship->Is>Personal attribute name,/-, for>Representing the value corresponding to the attribute.
Thus, the nodes and edges of the satellite observation task planning model can be conveniently defined.
Further, the basic knowledge graph is a general knowledge graph oriented to the satellite observation task planning field and is used for providing knowledge for sub-graph generation of a task situation graph, wherein the knowledge comprises satellite knowledge, target knowledge and the like; the satellite knowledge comprises a programmable satellite set, load information of satellites, orbit characteristic information and the like; the target knowledge comprises target basic information, target geographic positions, target observation requirements and the like.
Further, the set of planable satellites includes satellite entities; the attribute description of the satellite entity includes satellite name, satellite usage class (e.g., civilian, commercial, etc.), time of transmission, satellite regression period, satellite orbit time consumption, satellite orbit point latitude where the satellite orbit point is highest in northern hemisphere latitude, etc.
Further, the loading information of the satellite comprises a loading entity, and the attribute description of the loading entity comprises a loading name, a loading type, resolution, breadth, a side swing angle and the like.
Further, the target basic information comprises a target entity; the attribute description of the target entity comprises a target name and a target type.
Further, the target geographic location includes a target location entity, and the attribute description of the target location entity includes a discovery target time, a target location, and the like.
Further, the satellite entityAnd (2) load entity->The relation between them can be expressed as +.>The label of the relation can be expressed as +.>；
The load entityLoad type and target entity->A relation between the load type matching target entities, which can be expressed as +.>The label of the relation can be expressed as +.>The attribute description of the relationship includes a matching type name;
the load entityResolution and target entity->A relation between the resolution matching target entities, which can be expressed as +.>The label of the relation can be expressed as +.>The attribute description of the relationship includes matching resolution;
the target entityIs->The relation between them can be expressed as +.>The label of the relationship may be expressed as。
Further, the task situation map comprises satellites, satellite orbits and target real-time states meeting task requirements;
Screening satellites meeting task requirements in a programmable satellite set to obtain a satellite set meeting task requirements, wherein each satellite in the set is used as a satellite entityThe tags of the satellite entities may be represented as；
For target information in task demands, a single target is taken as a target entityThe tag of the target entity may be denoted +.>The method comprises the steps of carrying out a first treatment on the surface of the The attribute description of the target entity comprises a target type (dynamic target or static target), a target name, a target longitude, a target latitude, a current state time and the like;
for each satellite in the satellite set meeting the task requirement, dividing the orbit information of the satellite in the task duration according to the moment that the satellite passes through the satellite orbit satellite point and the satellite point latitude with the highest northern hemisphere latitude, wherein each circle of orbit is taken as a satellite orbit entityThe method comprises the steps of carrying out a first treatment on the surface of the The tag of the satellite orbital entity can be expressed asThe method comprises the steps of carrying out a first treatment on the surface of the The attribute description of the satellite orbit entity comprises orbit start time, orbit end time, orbit turns and the like;
for satellite orbital entitiesAnd satellite entity->The relation between, defined as satellite entity +.>Operating on satellite orbital entity- >The relationship can be expressed as +.>The label of the relation can be expressed as +.>；
For satellite entitiesIs +.>The relation between, defined as satellite entity +.>Matching target entity->The relationship can be expressed as +.>The label of the relationship may be expressed as；
For target entitiesIs>The relationship between is defined as satellite orbit entityVisible target entity->The relationship can be expressed as +.>The label of the relation can be expressed as +.>。
Further, as shown in fig. 2, the sub-graph extraction in step 2 includes:
step 21, receiving task demands, identifying target positions and time in the task demands, task constraint and other information, and creating a task;
step 22, inquiring whether related target information exists in the basic knowledge graph based on the target name: if yes, comparing and updating target position entity information associated with the target; if not, the target is used as a newly added target entity in the basic knowledge graph, and a relation between the load entity and the target entity is established according to task requirements, wherein the relation comprises resolution matching, load type matching and the like;
and step 23, extracting load entity information associated with the target and corresponding satellite entity information according to the relation between the satellite load entity and the target entity in the basic knowledge graph.
Therefore, the related information in the basic knowledge graph can be conveniently extracted according to task requirements and used for subsequent processing.
Further, as shown in fig. 3, the specific method for calculating the key data of the task situation map in the step 3 includes:
step 31, acquiring satellite imaging requirements in task requirements, including target information, imaging requirements required by a target, task starting time, task ending time and the like;
step 32, establishing a target entity according to satellite imaging requirementsThe attribute description of the entity includes a target type, target longitude +.>Target latitude->Task Start time->Task end time->Etc.;
step 33, matching satellites according to imaging requirements required by the target, and obtaining a satellite list;
step 34, for each satellite in the satellite list, establishing an orbital entity for that satellite；
Step 35, for each satellite in the satellite list, calculating a target entityOrbital entity with corresponding satellite->A relationship between;
through the steps, the target entity, the track entity and the relation between the target entity and the track entity are conveniently constructed.
Further, as shown in fig. 4, the step 34 includes:
step 341, calculating orbit data of the satellite at the task starting time according to the satellite list, the task starting time and the task ending time by using a conventional satellite orbit data calculation formula;
Step 342, obtaining the orbit feature data of the satellite from the basic knowledge graph, including satellite regression periodTime spent by a circle of satellite orbit>Satellite orbit satellite lower point is at the highest satellite lower point latitude of northern hemisphere latitude；
Step 343, calculating the number of turns of the satellite in the task timeThe specific formula can beDefining one circle of satellite at task starting time as a first circle;
step 344, calculating the number of turns of the satellite in the primary regression periodThe specific formula can be；
Step 345, based on the latitude of the satellite at the satellite point below the task start time orbitCalculating satellite arrival circle->Time of hour->The specific formula can be +.>；
Step 346, according to the number of turnsDefine satellite orbital entity name->, wherein ,/>Represents the number of track turns, the value of which is equal to +.>；
Step 347, calculating a track start time of the track, the attribute description of which may be expressed asAttribute value->Defined as->Refers to the initial circle at latitude +.>Time of hour plus track turns +.>Reduced time to track consumption>The specific formula can be: />
；
Step 348, defining the physical attribute of the number of track turns of the track, which may be expressed in particular as, wherein />The value is track circle number +. >。
Through the steps, the orbit entity of each satellite in the satellite list can be established。
Further, as shown in fig. 5, the step 35 includes:
step 351, based on the latitude of the orbital satellite point at the start time of the taskCalculating the time of arrival of the satellite at the target latitude in the orbit +.>The specific formula may be:
；
step 352, obtaining the time for the satellite to reach the target latitude under the first orbit based on the above formulaAfter that, the longitude +.>Latitude->；
Step 353, calculateAnd->Longitude difference +.>The specific formula may be:；
step 354, calculating the undersea points of the same longitude as the target in all the tracks, and selecting the circle closest to the target as the nearest circle numberIn this way, the target can be nearest to the undersea point, and the specific formula can be:
;
step 355, establishing a relationship between the target entity and the satellite orbit entity, wherein the number of turns of the satellite orbit entity isThe relation may be expressed specifically as +.>。
Through the steps, the relationship between the target entity and the satellite orbit entity can be conveniently and accurately calculated.
Further, as shown in fig. 6, the specific method for calculating the task planning weight in the step 3 includes:
Step 36, reading the task situation map to obtain the target entityRelationship and methodAll satellite orbital entities associated +.>；
Step 37, obtaining a preset planning direction of the current task, wherein the preset planning direction comprises objective functions with optimal time, optimal quality and the like, the objective functions are all conventional objective functions in the field, and a task planning evaluation weight factor set is established according to the preset planning direction； wherein ,/>Is a time weighting factor, the weighting factor is related to satellite imaging time, and the earlier the imaging time is, the larger the weight is; />Is an imaging quality weight factor, the weight factor is related to the satellite imaging side sway angle, and the weight is larger when the side sway angle is smaller;
step 38, extracting target entityVisible time window set, calculating time window weight value set； wherein ,/>Indicate->The specific formula of the weight value of each time window can be: />
；
wherein ,indicate->A time window; />Indicating that the satellite is at->Load side swing angles of the respective time windows;
step 39, time window weight value setAnd sorting according to the weight values, and selecting a time window with the highest weight value as a task planning scheme of the current task.
Through the steps, the task planning scheme can be reasonably determined according to the situation map content and the weight value.
Further, the method for updating the task situation map in the step 4 includes:
step 41, when the position of the dynamic target is updated, creating a target entityThe attribute description of the target entity comprises the time of target update and the position of target movement;
step 42, targeting the target entityStep 35 is performed iteratively.
Through the steps, the latest position of the dynamic target can be accurately injected into the task situation map in real time, so that the dynamic target can be adjusted and planned periodically in the follow-up process.
Embodiment two:
as shown in fig. 7, the present application provides a satellite observation task planning system based on graph calculation, which includes a data receiving module, a data processing module and a result generating module:
the data receiving module is used for receiving task demands and the updated positions of the dynamic targets;
the data processing module comprises a flow control unit, a calculation model unit, a basic knowledge graph unit and a task situation graph unit;
the calculation model unit is used for storing a satellite orbit calculation model, a subgraph extraction model, a situation map key data calculation model, a situation map updating model and a task planning model:
The satellite orbit calculation model is used for calculating orbit data of the satellite at the task starting time according to the satellite list, the task starting time and the task ending time;
the subgraph extraction model is used for extracting relevant load entity information and satellite entity information in the basic knowledge graph unit based on task requirements to form a subgraph as a task situation graph frame, and outputting the subgraph to the task situation graph unit;
the situation map key data calculation model is used for establishing a target entity and matching satellites according to satellite imaging requirements in task requirements, wherein the target entity comprises a dynamic target and a static target, the satellite orbit calculation model is called to calculate the orbit entity of each matching satellite, and the relation between the target entity and the orbit entity of the corresponding matching satellite is calculated and output to the task situation map unit;
the situation map updating model is used for creating a target entity based on the updating position of the dynamic target, calling the situation map key data calculating model, iteratively calculating the relation between the target entity and the orbit entity corresponding to the matched satellite, and outputting the relation to the task situation map unit;
the task planning model calls a task situation map, acquires a target entity and all related satellite orbit entities, calculates a time window weight value of each task based on a preset planning direction, and selects a time window with the highest weight value as a task planning scheme of the current task;
The basic knowledge graph unit is used for storing a basic knowledge graph;
the task situation map unit is used for storing the task situation map;
the flow control unit is used for inputting task demands into the subgraph extraction model and the situation map key data calculation model, inputting the update position of a dynamic target into the situation map update model, controlling the task planning model to perform iterative calculation and monitoring the running condition of each unit in the module;
and the result generation module is used for issuing the task planning scheme.
Embodiment III:
the application provides a satellite observation task planning device based on graph calculation, which comprises a processor, a memory and a bus, wherein the memory stores instructions and data which can be read by the processor, the processor is used for calling the instructions and the data in the memory so as to execute any satellite observation task planning method based on the graph calculation, and the bus is connected with all functional components to transmit information.
In yet another embodiment, the present solution may be implemented by means of an apparatus, which may include corresponding modules performing each or several steps of the above-described embodiments. A module may be one or more hardware modules specifically configured to perform the respective steps, or be implemented by a processor configured to perform the respective steps, or be stored within a computer-readable medium for implementation by a processor, or be implemented by some combination.
The processor performs the various methods and processes described above. For example, method embodiments in the present solution may be implemented as a software program tangibly embodied on a machine-readable medium, such as a memory. In some embodiments, part or all of the software program may be loaded and/or installed via memory and/or a communication interface. One or more of the steps of the methods described above may be performed when a software program is loaded into memory and executed by a processor. Alternatively, in other embodiments, the processor may be configured to perform one of the methods described above in any other suitable manner (e.g., by means of firmware).
The device may be implemented using a bus architecture. The bus architecture may include any number of interconnecting buses and bridges depending on the specific application of the hardware and the overall design constraints. The bus connects together various circuits including one or more processors, memories, and/or hardware modules. The bus may also connect various other circuits such as peripherals, voltage regulators, power management circuits, external antennas, and the like.
The bus may be an industry standard architecture (ISA, industry Standard Architecture) bus, a peripheral component interconnect (PCI, peripheral Component) bus, or an extended industry standard architecture (EISA, extended Industry Standard Component) bus, etc., and may be classified as an address bus, a data bus, a control bus, etc.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.

Claims (9)

1. The satellite observation task planning method based on graph calculation is characterized by comprising the following steps of:
step 1, defining a satellite observation task planning model based on graph calculation, wherein the satellite observation task planning model comprises a basic knowledge graph and a task situation graph; the model comprises nodes and edges, wherein the nodes represent a certain entity, and the edges represent a relation between the certain two entities; the model represents the entity or the label of the relation through different triples, and represents the relation, the attribute description of the entity and the attribute description of the relation through different triples; constructing a basic knowledge graph according to the general knowledge in the satellite observation field;
Step 2, carrying out sub-graph extraction on related information in the basic knowledge graph based on task requirements, and taking the sub-graph extraction as a task situation graph frame;
step 3, calculating key data of the task situation map based on the task situation map framework, constructing the task situation map, and obtaining a task planning result through task planning weight calculation; the task situation map comprises a target entity, wherein the attribute description of the target entity comprises a target type, and the target type comprises a dynamic target and a static target;
the key data of the calculation task situation map comprises:
step 31, acquiring satellite imaging requirements in task requirements, including target information, imaging requirements required by a target, task starting time and task ending time;
step 32, establishing a target entity according to satellite imaging requirementsThe attribute description of the entity includes a target type, target longitude +.>Target latitude->Task Start time->Task end time->；
Step 33, matching satellites according to imaging requirements required by the target, and obtaining a satellite list;
step 34, for each satellite in the satellite list, establishing an orbital entity for that satellite；
Step 35, for each satellite in the satellite list, calculating a target entity Orbital entity with corresponding satelliteA relationship between;
step 4, updating a task situation map based on the updated position of the dynamic target;
and 5, iteratively executing the task planning weight calculation in the step 3, and updating the task planning result.
2. The method according to claim 1, wherein in step 1,
by two tuplesRepresentation entity->Corresponding tag->；
Through tripletsRepresentation entity->And->Relation between->；
Through tripletsRepresentation entity->Is>A description of attributes, wherein->Representation entity->Is>Personal attribute name,/-, for>A value representing the attribute;
by two tuplesExpress relationship->Corresponding tag->；
Through tripletsExpress relationship->Is>A description of attributes, wherein->Express relationship->Is>Personal attribute name,/-, for>Representing the value corresponding to the attribute.
3. The method according to claim 1, wherein the sub-graph extraction in step 2 comprises:
step 21, receiving task demands, identifying target positions, target time and task constraints in the task demands, and creating a task;
step 22, inquiring whether related target information exists in the basic knowledge graph based on the target name: if yes, comparing and updating target position entity information associated with the target; if not, the target is used as a newly added target entity in the basic knowledge graph, and a relation between the load entity and the target entity is established according to task requirements, wherein the relation comprises resolution matching and load type matching;
And step 23, extracting load entity information associated with the target and corresponding satellite entity information according to the relation between the satellite load entity and the target entity in the basic knowledge graph.
4. The method according to claim 1, wherein the step 34 comprises:
step 341, calculating orbit data of the satellite at the task starting time according to the satellite list, the task starting time and the task ending time;
step 342, obtaining the orbit feature data of the satellite from the basic knowledge graph, including satellite regression periodTime spent by a circle of satellite orbit>Satellite orbit satellite lower point with highest latitude in northern hemisphere>；
Step 343, calculating the number of turns of the satellite in the task timeThe specific formula is->Defining one circle of satellite at task starting time as a first circle;
step 344, calculating the number of turns of the satellite in the primary regression periodThe specific formula is->；
Step 345, based on the latitude of the satellite at the satellite point below the task start time orbitCalculating satellite arrivalThis circleTime of hour->The specific formula is->；
Step 346, according to the number of turnsDefine satellite orbital entity name->, wherein ,/>Represents the number of track turns, the value of which is equal to +. >；
Step 347, calculating the track start time of the track, the attribute description of which is expressed asAttribute value->Defined as->Refers to the initial circle at latitude +.>Time of hour plus track turns +.>Reduced time to track consumption>The specific formula is:
；
step 348, defining the physical attribute of the track turns of the track, specifically expressed as, wherein />The value is track circle number +.>。
5. The method according to claim 1, wherein said step 35 comprises:
step 351, based on the latitude of the orbital satellite point at the start time of the taskCalculating the time of arrival of the satellite at the target latitude in the orbit +.>The specific formula is as follows:
；
step 352, obtaining the time for the satellite to reach the target latitude under the first orbit based on the above formulaAfter that, the longitude +.>Latitude->；
Step 353, calculateAnd->Longitude difference +.>The specific formula is as follows:；
step 354, calculating the undersea points of the same longitude as the target in all the tracks, and selecting the circle closest to the target as the nearest circle numberThe specific formula is as follows:
;
step 355, establishing a relationship between the target entity and the satellite orbit entityThe number of turns of the satellite orbit entity is +. >The relationship is specifically expressed as +.>。
6. The method according to claim 1, wherein the specific method for calculating the task planning weight in step 3 includes:
step 36, reading the task situation map to obtain the target entityRelationship and methodAll satellite orbital entities associated +.>；
Step 37, obtaining a preset planning direction of a current task, and establishing a task planning evaluation weight factor set according to the preset planning direction:
；
wherein ,is a time weight factor; />Is an imaging quality weighting factor;
step 38, extracting target entityVisible time window set, calculating time window weight value set； wherein ,/>Indicate->Weight values for the respective time windows; for->The specific formula of the weight value of each time window is as follows:
；
wherein ,indicate->A time window; />Indicating that the satellite is at->Load side swing angles of the respective time windows;
step 39, time window weight value setAnd sorting according to the weight values, and selecting a time window with the highest weight value as a task planning scheme of the current task.
7. The method according to claim 1, wherein the method for updating the task situation map in step 4 comprises:
Step 41, when the position of the dynamic target is updated, creating a target entityThe attribute description of the target entity comprises the time of target update and the position of target movement;
step 42, targeting the target entityStackingStep 35 is performed instead.
8. The satellite observation task planning system based on graph calculation is characterized by comprising a data receiving module, a data processing module and a result generating module:
the data receiving module is used for receiving task demands and the updated positions of the dynamic targets;
the data processing module comprises a flow control unit, a calculation model unit, a basic knowledge graph unit and a task situation graph unit;
the calculation model unit is used for storing a satellite orbit calculation model, a subgraph extraction model, a situation map key data calculation model, a situation map updating model and a task planning model:
the satellite orbit calculation model is used for calculating orbit data of the satellite at the task starting time according to the satellite list, the task starting time and the task ending time;
the subgraph extraction model is used for extracting relevant load entity information and satellite entity information in the basic knowledge graph unit based on task requirements to form a subgraph as a task situation graph frame, and outputting the subgraph to the task situation graph unit;
The situation map key data calculation model is used for establishing a target entity and matching satellites according to satellite imaging requirements in task requirements, wherein the target entity comprises a dynamic target and a static target, the satellite orbit calculation model is called to calculate the orbit entity of each matching satellite, and the relation between the target entity and the orbit entity of the corresponding matching satellite is calculated and output to the task situation map unit;
the situation map updating model is used for creating a target entity based on the updating position of the dynamic target, calling the situation map key data calculating model, iteratively calculating the relation between the target entity and the orbit entity corresponding to the matched satellite, and outputting the relation to the task situation map unit;
the task planning model calls a task situation map, acquires a target entity and all related satellite orbit entities, calculates a time window weight value of each task based on a preset planning direction, and selects a time window with the highest weight value as a task planning scheme of the current task;
the basic knowledge graph unit is used for storing a basic knowledge graph;
the task situation map unit is used for storing the task situation map;
the flow control unit is used for inputting task demands into the subgraph extraction model and the situation map key data calculation model, inputting the update position of a dynamic target into the situation map update model, controlling the task planning model to perform iterative calculation and monitoring the running condition of each unit in the module;
And the result generation module is used for issuing the task planning scheme.
9. A satellite observation task planning device based on graph calculation, which is characterized by comprising a processor, a memory and a bus, wherein the memory stores instructions and data which can be read by the processor, the processor is used for calling the instructions and the data in the memory to execute the method according to any one of claims 1-7, and the bus is used for transmitting information among all functional components.
CN202310740403.9A 2023-06-21 2023-06-21 Satellite observation task planning method, system and device based on graph calculation Active CN116485162B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310740403.9A CN116485162B (en) 2023-06-21 2023-06-21 Satellite observation task planning method, system and device based on graph calculation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310740403.9A CN116485162B (en) 2023-06-21 2023-06-21 Satellite observation task planning method, system and device based on graph calculation

Publications (2)

Publication Number Publication Date
CN116485162A CN116485162A (en) 2023-07-25
CN116485162B true CN116485162B (en) 2023-09-19

Family

ID=87227230

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310740403.9A Active CN116485162B (en) 2023-06-21 2023-06-21 Satellite observation task planning method, system and device based on graph calculation

Country Status (1)

Country Link
CN (1) CN116485162B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113283666A (en) * 2021-06-10 2021-08-20 中国人民解放军国防科技大学 Heuristic intelligent task reasoning and decision-making method for satellite group
CN114169066A (en) * 2021-09-18 2022-03-11 中国人民解放军63921部队 Space target characteristic measuring and reconnaissance method based on micro-nano constellation approaching reconnaissance
CN114706672A (en) * 2022-06-06 2022-07-05 安徽三禾一信息科技有限公司 Satellite autonomous mission planning system and method based on event-driven dynamic assembly
CN115391545A (en) * 2022-04-26 2022-11-25 航天宏图信息技术股份有限公司 Knowledge graph construction method and device for multi-platform collaborative observation task
CN115422373A (en) * 2022-09-05 2022-12-02 中国人民解放军国防科技大学 Knowledge graph and user intention task decomposition method for satellite task planning

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113283666A (en) * 2021-06-10 2021-08-20 中国人民解放军国防科技大学 Heuristic intelligent task reasoning and decision-making method for satellite group
CN114169066A (en) * 2021-09-18 2022-03-11 中国人民解放军63921部队 Space target characteristic measuring and reconnaissance method based on micro-nano constellation approaching reconnaissance
CN115391545A (en) * 2022-04-26 2022-11-25 航天宏图信息技术股份有限公司 Knowledge graph construction method and device for multi-platform collaborative observation task
CN114706672A (en) * 2022-06-06 2022-07-05 安徽三禾一信息科技有限公司 Satellite autonomous mission planning system and method based on event-driven dynamic assembly
CN115422373A (en) * 2022-09-05 2022-12-02 中国人民解放军国防科技大学 Knowledge graph and user intention task decomposition method for satellite task planning

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
对地观测卫星任务规划问题研究述评;姜维;郝会成;李一军;;系统工程与电子技术(第09期);第1878-1884页 *
遥感卫星特定领域大规模知识图谱构建关键技术;谢榕;罗知微;王雨晨;陈文;;无线电工程(第04期);第1-6页 *

Also Published As

Publication number Publication date
CN116485162A (en) 2023-07-25

Similar Documents

Publication Publication Date Title
US11393341B2 (en) Joint order dispatching and fleet management for online ride-sharing platforms
Wang et al. Decomposition‐based multiinnovation gradient identification algorithms for a special bilinear system based on its input‐output representation
US11507894B2 (en) System and method for ride order dispatching
WO2019232693A1 (en) System and method for ride order dispatching
CN114187412B (en) High-precision map generation method and device, electronic equipment and storage medium
WO2022035441A1 (en) Dynamic dispatching with robustness for large-scale heterogeneous mining fleet via deep reinforcement learning
CN113064449B (en) Unmanned aerial vehicle scheduling method and system
WO2016118122A1 (en) Optimization of truck assignments in a mine using simulation
Yang et al. Onboard coordination and scheduling of multiple autonomous satellites in an uncertain environment
CN116485162B (en) Satellite observation task planning method, system and device based on graph calculation
Gong et al. Real-time Taxi–passenger matching using a differential evolutionary fuzzy controller
Song et al. Generalized Model and Deep Reinforcement Learning-Based Evolutionary Method for Multitype Satellite Observation Scheduling
CN116518979B (en) Unmanned plane path planning method, unmanned plane path planning system, electronic equipment and medium
Cao et al. A grey wolf optimizer–cellular automata integrated model for urban growth simulation and optimization
Contell et al. Long-term sustainability of a distributed RI: the EPOS case
CN116501826A (en) Autonomous generation method, system and device for satellite observation task
Li et al. A sequence and network embedding method for bus arrival time prediction using GPS trajectory data only
CN107844576B (en) A kind of environmentally friendly orbit generation method and system of patrolling
CN115330556A (en) Training method and device for information adjustment model of charging station and product
CN114742644A (en) Method and device for training multi-scene wind control system and predicting business object risk
KR20220084752A (en) Business model of route recommendation services based on artificial intelligence using marine meteorological big data
CN114492905A (en) Customer appeal rate prediction method and device based on multi-model fusion and computer equipment
US20220237639A1 (en) System and method for data prediction using heat maps
CN115829169B (en) Business processing method and device based on mixed integer linear programming
Wan et al. Deep Reinforcement Learning Enabled Multi-UAV Scheduling for Disaster Data Collection With Time-Varying Value

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant