CN114117073A - Method and device for identifying group intention, computer equipment and readable medium - Google Patents
Method and device for identifying group intention, computer equipment and readable medium Download PDFInfo
- Publication number
- CN114117073A CN114117073A CN202111431123.7A CN202111431123A CN114117073A CN 114117073 A CN114117073 A CN 114117073A CN 202111431123 A CN202111431123 A CN 202111431123A CN 114117073 A CN114117073 A CN 114117073A
- Authority
- CN
- China
- Prior art keywords
- intention
- cluster
- entity
- formation
- type
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 89
- 238000012549 training Methods 0.000 claims description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000003491 array Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 abstract description 7
- 238000005755 formation reaction Methods 0.000 description 64
- 230000008569 process Effects 0.000 description 13
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 235000003283 Pachira macrocarpa Nutrition 0.000 description 1
- 241000270295 Serpentes Species 0.000 description 1
- 241001083492 Trapa Species 0.000 description 1
- 235000014364 Trapa natans Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 235000009165 saligot Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Animal Behavior & Ethology (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method, a device, computer equipment and a readable medium for identifying a cluster intention, wherein the method comprises the following steps: acquiring the position and the model information of an airplane in a cluster formation to be analyzed currently, and identifying the cluster array type of the cluster formation according to the position information; obtaining a first fleet intent associated with a fleet array type and a second fleet intent associated with each aircraft model from a fleet knowledge map; intersecting the first cluster intention with the second cluster intention to obtain an initial intention identification result; if the initial intention identification result contains more than one cluster intention, calculating the real intention of the current cluster formation to be analyzed by adopting a Savenoqi decision criterion; screening and outputting a target entity associated with the real intention from the cluster knowledge graph; the method and the device perform cluster intention identification based on the knowledge graph, take various factors into consideration to obtain the most possible cluster intention, improve the accuracy of intention identification and provide reference for command and control decisions under intelligent conditions.
Description
Technical Field
The present application relates to the field of command and control system technologies, and in particular, to a method and an apparatus for identifying a group intention, a computer device, and a readable medium.
Background
With the rapid development of the intelligent sensing technology, the detection and identification precision and accuracy of the aerial target are greatly improved. The efficient and correct analysis of the aerial target intention can provide effective support for correct decision making, and is one of key factors for obtaining decision making advantages. As the number of targets in the air increases rapidly and exhibits highly dynamic changes, challenges are also presented to the correct identification of the intent of the target. Because aerial targets are typically organized in groups, performing tasks together, aerial clusters typically have a more consistent intent.
In the aspect of group intention identification, most of the existing research focuses on identifying a formation through certain characteristics of the formation linear formation, such as field characteristics and tactical group characteristics, and the characteristics serve as important bases for identifying target intentions; the intention analysis on how to carry out the target based on the identified cluster formation is less researched, and the intention analysis effect is not improved by combining a knowledge means.
Disclosure of Invention
Aiming at least one defect or improvement requirement in the prior art, the invention provides a cluster intention identification method, a device, computer equipment and a readable medium, on the basis of analyzing cluster characteristics and the intentions, a correlation model between the cluster characteristics and the intentions is constructed to establish a cluster knowledge graph capable of being expanded iteratively, and the cluster intention is comprehensively identified by combining a method of a Savengqi decision criterion in a decision theory so as to provide reference for command control under an intelligent condition.
To achieve the above object, according to a first aspect of the present invention, there is provided a cluster intention identifying method including the steps of:
acquiring the position and the model information of an airplane in a cluster formation to be analyzed currently, and identifying the cluster array type of the cluster formation according to the position information;
acquiring a first cluster intention associated with the cluster matrix type and a second cluster intention respectively associated with each aircraft model from a pre-established cluster knowledge graph;
intersecting the first cluster intention with the second cluster intention to obtain an initial intention identification result;
if the initial intention identification result contains a cluster intention, taking the cluster intention as a real intention of a current cluster formation to be analyzed;
if the initial intention identification result contains more than one machine group intention, screening out the real intention of the current machine group formation to be analyzed from the multiple machine group intentions by adopting a Savenoqi decision criterion;
and searching and outputting a target entity associated with the real intention from the cluster knowledge graph.
Preferably, in the above cluster intention identifying method, if there is no cluster intention in the initial intention identification result, the first cluster intention is merged with the second cluster intention to obtain an updated initial intention identification result.
Preferably, in the above method for identifying a fleet intent, the creating of the fleet knowledge graph includes:
respectively establishing an intention entity and a common entity, and defining the attribute of each entity; the intention entity is a cluster intention type entity; the common entities comprise an airplane type entity, a cluster formation array entity, an airplane model type entity, a departure place entity, a target type entity and a target entity;
and establishing incidence relations among the common entities and between the intention entity and the common entities.
Preferably, in the above method for identifying a cluster intention, the screening out a real intention of a cluster formation currently to be analyzed from a plurality of cluster intentions by using a savanqi decision criterion includes:
based on a Savenoqi decision criterion, constructing an intention discrimination income table of each cluster intention relative to a real intention in an initial intention recognition result;
establishing an intention judgment opportunity loss table based on the intention judgment income table to obtain an opportunity loss value of each cluster intention relative to a real intention in an initial intention identification result;
and searching the minimum maximum opportunity loss in the intention judgment opportunity loss table, wherein the cluster intention corresponding to the minimum maximum opportunity loss is a real intention of cluster formation.
Preferably, in the cluster intention identifying method, when n cluster intents exist in the initial intention identification result, the size of the intention discrimination profit table is n × n, and the element b in the ith row and the jth column of the tableijA profit value representing the cluster intent of the jth column relative to the real intent of the ith row; wherein n is a natural number greater than or equal to 2; i is more than or equal to 1 and less than or equal to n, and j is more than or equal to 1 and less than or equal to n.
Preferably, in the above method for identifying a fleet intent, the searching for and outputting a target entity associated with the real intent from the fleet knowledge graph includes:
searching a target type set associated with the real intention from the cluster knowledge graph;
if any target type does not exist in the target type set, indicating that the current cluster formation to be analyzed does not aim at a specific target type;
otherwise, inquiring a target entity set associated with each target type in the target type sets from the cluster knowledge graph, counting all target entities falling into the moving radius of the cluster formation in the target entity set, and outputting the target entities serving as target entities possibly aimed at by the current cluster formation to be analyzed.
Preferably, in the above method for identifying a cluster intent, the identifying a cluster array type of the cluster formation includes:
training the convolutional neural network by adopting a cluster formation array type training set to obtain a trained cluster formation array type structural feature model; the cluster formation array type training set comprises a plurality of training samples with different cluster formation arrays;
and identifying the cluster array type of the cluster formation to be analyzed currently according to the trained cluster formation array structure characteristic model.
According to a second aspect of the present invention, there is also provided a crowd intention identifying apparatus comprising:
the array type identification module is used for acquiring the position and the type information of the airplane in the current cluster formation to be analyzed and identifying the cluster array type of the cluster formation according to the position information;
the intention identification module is used for acquiring a first airplane group intention associated with the airplane group type and a second airplane group intention respectively associated with each airplane model from a pre-established airplane group knowledge graph; intersecting the first cluster intention with the second cluster intention to obtain an initial intention identification result;
if the initial intention identification result contains a cluster intention, taking the cluster intention as a real intention of a current cluster formation to be analyzed;
if the initial intention identification result contains more than one machine group intention, screening out the real intention of the current machine group formation to be analyzed from the multiple machine group intentions by adopting a Savenoqi decision criterion;
and the result output module is used for searching the target entity associated with the real intention from the cluster knowledge graph and outputting the target entity.
According to a second aspect of the present invention, there is also provided a computer device comprising at least one processing unit, and at least one storage unit, wherein said storage unit stores a computer program which, when executed by said processing unit, causes said processing unit to perform the steps of any of the above described fleet intent recognition methods.
According to a second aspect of the present invention, there is also provided a computer readable medium, storing a computer program executable by a computer device, for causing the computer device to perform the steps of any of the above described fleet intent identification methods, when the computer program is run on the computer device.
In general, compared with the prior art, the above technical solution contemplated by the present invention can achieve the following beneficial effects:
the cluster intention identification method, the cluster intention identification device, the computer equipment and the readable medium construct a cluster knowledge graph capable of reflecting the association relationship among cluster type, aircraft attribute, departure place, target and cluster intention, better solve the association description among cluster group, aircraft individual and intention, and have iterative expansibility; all possible cluster intentions are obtained from the cluster knowledge map based on the identified cluster type of the cluster formation and all the airplane types contained in the cluster formation, and then the real intentions are screened out by utilizing a cluster intention comprehensive judgment method.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart of a cluster intent identification method according to this embodiment;
FIG. 2 is a schematic flow chart illustrating a cluster intent comprehensive identification process according to the present embodiment;
fig. 3 is a logic block diagram of the cluster intention identifying apparatus provided in this embodiment;
fig. 4 is a logic block diagram of the computer device provided in the present embodiment.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
The terms "first," "second," "third," and the like in the description and claims of this application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Because the airplanes are usually organized into clusters in a formation form and cooperatively complete a unified task goal, a more consistent group intention can be embodied. The knowledge graph has the capability of representing and analyzing complex relationships among entities, can well describe attributes of the entities and incidence relationships among the entities, and is widely applied to the fields of information recommendation, intelligent search, deep question answering and the like. The invention provides a knowledge-based cluster intention identification method by taking a cluster as an object, mainly considering the intention embodied by the formation array type structural characteristics embodied by the cluster and the intention embodied by the functional attributes of an airplane, establishing the association between the characteristics and the intention through a knowledge map, and then comprehensively identifying the cluster intention. The specific technical scheme is as follows: training the structural features of the common array type of the cluster by using a convolutional neural network algorithm to obtain an array type structural feature model for identifying the array type of cluster formation; performing associated modeling on information such as a cluster matrix type, attributes and intentions to construct a cluster knowledge graph; inquiring a cluster knowledge map through the identified cluster type and aircraft model information to obtain a cluster possible intention set; finally, the cluster intention is identified through a comprehensive discrimination method.
Fig. 1 is a flowchart of a cluster intent identification method provided in this embodiment, and referring to fig. 1, the method mainly includes the following steps:
s1, acquiring the position and model information of the airplane in the current airplane group formation to be analyzed, and identifying the airplane group type of the airplane group formation according to the position information of each airplane;
in the embodiment, the intelligent identification of the cluster array type is realized by adopting a convolutional neural network based on deep learning; specifically, the method comprises the following steps:
training the convolutional neural network by adopting a cluster formation array type training set to obtain a trained cluster formation array type structural feature model; the cluster formation array type training set comprises a plurality of training samples with different cluster formation arrays; the different fleet formation formations include but are not limited to arrow, water chestnut, snake, wedge, longitudinal, ladder, horizontal and other common formations, and the training samples include images of various fleet formation formations and movement directions thereof generated by the aircraft position information.
And identifying the cluster array type of the cluster formation to be analyzed currently according to the trained cluster formation array structure characteristic model.
The training process of the fleet formation array type structural feature model refers to the conventional training process of the convolutional neural network, which is not described in detail in this embodiment.
The cluster array type identification in this embodiment may be performed by using features based on the domain features of the cluster array, the task state attributes, and the like in the conventional literature, and is not limited to the convolutional neural network.
S2, acquiring a first cluster intention associated with the cluster matrix type and a second cluster intention respectively associated with each aircraft model from a pre-established cluster knowledge map;
in this embodiment, the intention analysis is performed based on a fleet knowledge graph which is created in advance and can be expanded iteratively, where the creation of the fleet knowledge graph includes:
respectively establishing an intention entity and a common entity, and defining the attribute of each entity; the intention entity is a cluster intention type entity; the common entities comprise an airplane type entity, a cluster formation array entity, an airplane model type entity, a departure place entity, a target type entity and a target entity; and establishing incidence relations among the common entities and between the intention entity and the common entities.
Specifically, the detailed process of establishing the fleet knowledge association model is as follows:
step 1.1, establishing an airplane type entity for representing various airplane types such as fighter planes, transport planes, early warning planes, reconnaissance planes and the like, wherein the attribute of each airplane type is defined as a quantity alpha representing the importance degree of the airplane type, and the value range is [0,1 ].
Step 1.2, establishing a cluster type entity, corresponding to the airplane type, for expressing different types of clusters formed by different airplane types, such as fighter clusters, transport cluster scout clusters and the like. Meanwhile, the situation that different types of airplanes are mixed and formed is shown by adding one type of mixed forming group.
Step 1.3, establishing a cluster formation array entity for representing common cluster formation arrays such as a horizontal team and a wedge team, wherein the attribute of the cluster formation array entity is linked with a cluster formation array structure characteristic model trained by a Convolutional Neural Network (CNN) method.
Step 1.4, establishing an airplane model type entity for representing the specific model of the airplane, such as 'F-35A', 'F-22' and the like. For different types of airplanes, the attributes of the airplanes are related to various indexes in the development process of the airplanes, including the maximum voyage, the moving radius, the maximum flying height, the use and the like; the purpose attributes of each model aircraft represent the tasks that it is capable of performing, in relation to its intentions.
Step 1.5, establishing a cluster intention type entity for expressing different intentions such as fighting, bombing, monitoring, early warning, air refueling and the like. Because of the different threat levels caused by different intentions, the attribute of the cluster intent type entity is defined as a quantity beta reflecting the threat level of the intentions, and the value range is [0,1 ].
Step 1.6, establishing a departure place entity for representing each airport, a water surface movable airport, a land mobile platform and the like where the cluster departs, wherein the attribute of the departure place entity is cluster departure place position information stored or updated in a knowledge graph in real time.
Step 1.7, establishing target type entities including ground targets, air targets, water surface targets and the like.
Step 1.8, establishing a target entity for the target entities of our part such as water surface targets, air targets, airports, ports and the like of various activities, wherein the attributes of the target entities comprise: and the target position information comprises static target position longitude and latitude information stored in a knowledge map or dynamic target current position information acquired and updated in real time.
Step 1.9, establishing an association relationship between various entities, wherein the association relationship mainly comprises two types: the method comprises the following steps that firstly, common entity relations comprise the belonged, formed, presented and possessed relations between a cluster type entity and an airplane type entity, between the airplane type entity and an airplane model, between a cluster formation array type entity and the cluster type entity, between a target type entity and a target entity and between each entity and the attribute of the entity; the second is the incidence relation of the common entity to the intention entity, including the support relation between the fleet type entity and the intention entity, the support relation between each aircraft type entity and the intention entity, and the relation of the intention entity to the target type entity, such as the fighting intention to the aerial target, the ground attack intention to the ground target, etc.
Then, carrying out cluster intention comprehensive identification based on the knowledge graph association query result, specifically:
s21, intersecting the first cluster intention with the second cluster intention to obtain an initial intention identification result;
particularly, if any cluster intention does not exist in the initial intention identification result, the first cluster intention and the second cluster intention are combined to obtain an updated initial intention identification result;
s22, if the initial intention identification result contains a cluster intention, the cluster intention is used as the real intention of the current cluster formation to be analyzed;
s23, if the initial intention identification result contains more than one cluster intention, screening out the real intention of the current cluster formation to be analyzed from the multiple cluster intentions by adopting a Savencjue decision criterion;
in this embodiment, the method for screening out the real intention of the current fleet formation to be analyzed from the multiple fleet intentions by using the savanqi decision criterion specifically includes:
based on a Savenoqi decision criterion, constructing an intention discrimination income table of each cluster intention relative to a real intention in an initial intention recognition result;
when n machine group intents exist in the initial intention identification result, the size of the intention distinguishing income table is n multiplied by n, and the element b of the ith row and the jth column in the tableijA profit value representing the cluster intent of the jth column relative to the real intent of the ith row; wherein n is a natural number greater than or equal to 2; i is more than or equal to 1 and less than or equal to n, and j is more than or equal to 1 and less than or equal to n.
Establishing an intention judgment opportunity loss table based on the intention judgment income table to obtain an opportunity loss value of each cluster intention relative to a real intention in an initial intention identification result;
and searching the minimum maximum opportunity loss in the intention judgment opportunity loss table, wherein the cluster intention corresponding to the minimum maximum opportunity loss is a real intention of cluster formation.
S4, searching and outputting a target entity associated with the real intention from the cluster knowledge graph; the method specifically comprises the following steps:
searching a target type set associated with the real intention from the cluster knowledge graph;
if any target type does not exist in the target type set, indicating that the current cluster formation to be analyzed does not aim at the specific target type;
otherwise, inquiring a target entity set associated with each target type in the target type set from the cluster knowledge graph, counting all target entities falling within the movable radius of the cluster formation in the target entity set, and outputting the target entities serving as target entities possibly targeted by the current cluster formation to be analyzed.
Fig. 2 is a schematic flow chart of a cluster-purpose integrated identification process according to this embodiment, where the input and output of the cluster-purpose integrated identification process are respectively:
inputting: based on the correlation query result of the knowledge graph, acquiring an intention set I associated with the current cluster typeMatrix formIntentions I associated with the various types of aircraft contained in the fleetModel typeThe fleet includes a total number k of aircraft types and a number N of aircraft types of type tt(e.g., number of bombers for aircraft type 2), origin information for the fleet.
And (3) outputting: and judging a result I of cluster intention and a target entity to which the cluster is possibly directed.
As shown in fig. 2, the specific steps of comprehensive identification are as follows:
step 2.1, the cluster intention related to the formation entity of the cluster formation obtained by query is intersected with the cluster intention related to each airplane model entity in the cluster, and an initial intention identification result I is obtainedInitial＝IMatrix form∩IModel 1∩IModel 2…∩IModel M。
Step 2.2 judge the initial intention recognition result, IInitialThere may be three cases: case 1, if IInitialIf there is one cluster intention, the integrated identification result is I ═ IInitialWhen the comprehensive intention judging process is finished, turning to the step 2.7; case 2, if IInitialIf a plurality of cluster intents exist, each cluster intention can be the final cluster intention, and the step 2.4 is carried out for further judgment; case 3, if
I.e., there is no intersection of cluster intents, then all of the initial cluster intents may be cluster intents, and step 2.3 is performed for further processing.
Step 2.3, merging the cluster intention corresponding to the cluster formation type entity with the cluster intention corresponding to each airplane type entity in the cluster, namely IInitial＝IMatrix form∪IModel 1∪IModel 2…∪IModel M。
And 2.4, constructing an intention discrimination income table of each cluster intention relative to the real intention in the initial intention recognition result based on the Savenki decision criterion.
If IInitialIf there are n intents, the profit table size is n × n, the element b in the ith row and jth column of the tableijA profit value representing the intention estimation result of the j-th column relative to the true intention of the i-th row; wherein n is a natural number greater than or equal to 2; i is more than or equal to 1 and less than or equal to n, and j is more than or equal to 1 and less than or equal to n.
When i is j, the profit value is the product of the threat degree of the real intention of the ith row and the sum of the products of the importance of each type of airplane and the number of the type of airplane, namely
When i is not equal to j, the profit value is the profit value of j row and j column minus the profit value of i row and i column, namely bij＝bjj-bii。
And 2.5, establishing an intention discrimination opportunity loss table based on the intention discrimination income table, namely subtracting the element values of each row from the maximum value of each row in the intention discrimination income table to obtain the opportunity loss value of each cluster intention relative to the real intention in the initial intention recognition result.
And 2.6, searching the minimum maximum opportunity loss for judgment, counting the maximum value of each row of opportunity losses in the intention judgment opportunity loss table, and then searching the minimum value of the maximum opportunity losses in each row of the maximum opportunity losses, namely the minimum maximum opportunity loss of the intention estimation result relative to the real intention, wherein the intention estimation result corresponding to the row is the final intention identification result of the cluster, namely the real intention.
Step 2.7, inquiring the knowledge graph of the cluster, and searching a target type set corresponding to the real intention as OType (B). If it is
Indicating that the cluster is not aimed at the specific target type, outputting a final intention identification result, and turning to step 2.9; otherwise, associating the target entity set O corresponding to the query target typeEntity。
Step 2.8 statistics of target entity set OEntityAnd calculating all the target entities O in the active radius of the current cluster as the target information which is possibly aimed at by the current cluster intention identification result according to the position information of the cluster departure place, the intersection of the active radii of all the models in the cluster (the active radii are derived from the attributes of the airplane) and the position information of the target entities.
And 2.9, finishing the comprehensive identification process.
It should be noted that although in the above-described embodiments, the operations of the methods of the embodiments of the present specification are described in a particular order, this does not require or imply that these operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Rather, the steps depicted in the flowcharts may change the order of execution. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.
The embodiment also provides a group intention identifying device, as shown in fig. 3, which comprises a matrix identifying module, an intention identifying module and a result outputting module, wherein,
the array type identification module is used for acquiring the position and the type information of the airplane in the current airplane group formation to be analyzed and identifying the airplane group array type of the airplane group formation according to the position information of each airplane;
the intention identification module is used for acquiring a first airplane group intention associated with the airplane group type and a second airplane group intention respectively associated with each airplane model from a pre-established airplane group knowledge graph; intersecting the first cluster intention with the second cluster intention to obtain an initial intention identification result;
if the initial intention identification result contains a cluster intention, taking the cluster intention as a real intention of a current cluster formation to be analyzed;
if the initial intention identification result contains more than one machine group intention, screening out the real intention of the current machine group formation to be analyzed from the multiple machine group intentions by adopting a Savenoqi decision criterion;
and the result output module is used for searching and outputting the target entity associated with the real intention from the cluster knowledge graph.
For the specific definition of the cluster intent recognition device, reference may be made to the above definition of the cluster intent recognition method, which is not described herein again. The various modules in the cluster intent recognition apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
The present embodiment further provides a computer device, as shown in fig. 4, which includes at least one processor and at least one memory, where the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above cluster intent identification method, which is not described herein again; in this embodiment, the types of the processor and the memory are not particularly limited, for example: the processor may be a microprocessor, digital information processor, on-chip programmable logic system, or the like; the memory may be volatile memory, non-volatile memory, a combination thereof, or the like.
The computer device may also communicate with one or more external devices (e.g., keyboard, pointing terminal, display, etc.), with one or more terminals that enable a user to interact with the computer device, and/or with any terminals (e.g., network card, modem, etc.) that enable the computer device to communicate with one or more other computing terminals. Such communication may be through an input/output (I/O) interface. Also, the computer device may communicate with one or more networks (e.g., a Local Area Network (LAN), Wide Area Network (WAN), and/or a public Network, such as the internet) via the Network adapter.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for identifying a cluster intention, comprising:
acquiring the position and the model information of an airplane in a cluster formation to be analyzed currently, and identifying the cluster formation type of the cluster formation according to the position information;
acquiring a first cluster intention associated with the cluster matrix type and a second cluster intention respectively associated with each aircraft model from a pre-established cluster knowledge graph;
intersecting the first cluster intention with the second cluster intention to obtain an initial intention identification result;
if the initial intention identification result contains a cluster intention, taking the cluster intention as a real intention of a current cluster formation to be analyzed;
if the initial intention identification result contains more than one cluster intention, calculating the real intention of the current cluster formation to be analyzed by adopting a Savenoqi decision criterion;
and searching and outputting a target entity associated with the real intention from the cluster knowledge graph.
2. The cluster intent identification method according to claim 1,
and if any cluster intention does not exist in the initial intention identification result, merging the first cluster intention and the second cluster intention to obtain an updated initial intention identification result.
3. The fleet intent identification method as set forth in claim 1, wherein the creating of the fleet knowledge graph comprises:
respectively establishing an intention entity and a common entity, and defining the attribute of each entity; the intention entity is a cluster intention type entity; the common entities comprise an airplane type entity, a cluster formation array entity, an airplane model type entity, a departure place entity, a target type entity and a target entity;
and establishing incidence relations among the common entities and between the intention entity and the common entities.
4. A fleet intent recognition method according to any one of claims 1 to 3, wherein said calculating a true intent of a fleet formation currently under analysis using a savart decision criterion comprises:
based on a Savenoqi decision criterion, constructing an intention discrimination income table of each cluster intention relative to a real intention in an initial intention recognition result;
establishing an intention judgment opportunity loss table based on the intention judgment income table, and calculating an opportunity loss value of each cluster intention relative to a real intention in an initial intention identification result;
and searching the minimum maximum opportunity loss in the intention judgment opportunity loss table, wherein the cluster intention corresponding to the minimum maximum opportunity loss is a real intention of cluster formation.
5. The cluster intent recognition method as claimed in claim 4, wherein if n cluster intents exist in the initial intent recognition result, the intent discrimination profit table has a size of n x n, and the element b of the ith row and the jth column in the table isijA profit value representing the cluster intent of the jth column relative to the real intent of the ith row; wherein n is a natural number greater than or equal to 2; i is more than or equal to 1 and less than or equal to n, and j is more than or equal to 1 and less than or equal to n.
6. A fleet intent identification method according to any one of claims 1 to 3, wherein said finding and outputting a target entity associated with said real intent from a fleet knowledge graph comprises:
searching a target type set associated with the real intention from the cluster knowledge graph;
if any target type does not exist in the target type set, indicating that the current cluster formation to be analyzed does not aim at a specific target type;
otherwise, inquiring a target entity set associated with each target type in the target type sets from the cluster knowledge graph, counting all target entities falling into the moving radius of the cluster formation in the target entity set, and outputting the target entities serving as target entities possibly aimed at by the current cluster formation to be analyzed.
7. A fleet intent identification method according to any one of claims 1 to 3, wherein said identifying a fleet array type of fleet formation comprises:
training the convolutional neural network by adopting a cluster formation array type training set to obtain a trained cluster formation array type structural feature model; the cluster formation array type training set comprises a plurality of training samples with different cluster formation arrays;
and identifying the cluster array type of the cluster formation to be analyzed currently according to the trained cluster formation array structure characteristic model.
8. A crowd intention recognition apparatus, comprising:
the array type identification module is used for acquiring the position and the type information of the airplane in the current cluster formation to be analyzed and identifying the cluster array type of the cluster formation according to the position information;
the intention identification module is used for acquiring a first airplane group intention associated with the airplane group type and a second airplane group intention respectively associated with each airplane model from a pre-established airplane group knowledge graph; intersecting the first cluster intention with the second cluster intention to obtain an initial intention identification result;
if the initial intention identification result contains a cluster intention, taking the cluster intention as a real intention of a current cluster formation to be analyzed;
if the initial intention identification result contains more than one cluster intention, calculating the real intention of the current cluster formation to be analyzed by adopting a Savenoqi decision criterion;
and the result output module is used for searching the target entity associated with the real intention from the cluster knowledge graph and outputting the target entity.
9. A computer arrangement comprising at least one processing unit and at least one memory unit, wherein the memory unit stores a computer program that, when executed by the processing unit, causes the processing unit to carry out the steps of the fleet intent recognition method as defined in any one of claims 1 to 7.
10. A computer-readable medium, characterized in that it stores a computer program executable by a computer device, which, when run on the computer device, causes the computer device to perform the steps of the fleet intent identification method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111431123.7A CN114117073B (en) | 2021-11-29 | 2021-11-29 | Cluster intention recognition method and device, computer equipment and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111431123.7A CN114117073B (en) | 2021-11-29 | 2021-11-29 | Cluster intention recognition method and device, computer equipment and readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114117073A true CN114117073A (en) | 2022-03-01 |
| CN114117073B CN114117073B (en) | 2024-04-23 |
Family
ID=80371153
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111431123.7A Active CN114117073B (en) | 2021-11-29 | 2021-11-29 | Cluster intention recognition method and device, computer equipment and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114117073B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115061501A (en) * | 2022-07-28 | 2022-09-16 | 中国人民解放军空军预警学院 | Method and system for identifying coded data of air formation |
| CN115238832A (en) * | 2022-09-22 | 2022-10-25 | 中国人民解放军空军预警学院 | CNN-LSTM-based air formation target intention identification method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200184278A1 (en) * | 2014-03-18 | 2020-06-11 | Z Advanced Computing, Inc. | System and Method for Extremely Efficient Image and Pattern Recognition and Artificial Intelligence Platform |
| CN111930793A (en) * | 2020-06-26 | 2020-11-13 | 西安电子科技大学 | Target behavior mining and retrieval analysis method, system, computer equipment and application |
-
2021
- 2021-11-29 CN CN202111431123.7A patent/CN114117073B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200184278A1 (en) * | 2014-03-18 | 2020-06-11 | Z Advanced Computing, Inc. | System and Method for Extremely Efficient Image and Pattern Recognition and Artificial Intelligence Platform |
| CN111930793A (en) * | 2020-06-26 | 2020-11-13 | 西安电子科技大学 | Target behavior mining and retrieval analysis method, system, computer equipment and application |
Non-Patent Citations (1)
| Title |
|---|
| 蒋超，赵娜，闻子侠: "军用无人机飞控技术发展简述", 中国军转民, pages 40 - 42 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115061501A (en) * | 2022-07-28 | 2022-09-16 | 中国人民解放军空军预警学院 | Method and system for identifying coded data of air formation |
| CN115061501B (en) * | 2022-07-28 | 2022-11-22 | 中国人民解放军空军预警学院 | Method and system for identifying coded data of air formation |
| CN115238832A (en) * | 2022-09-22 | 2022-10-25 | 中国人民解放军空军预警学院 | CNN-LSTM-based air formation target intention identification method and system |
| CN115238832B (en) * | 2022-09-22 | 2022-12-02 | 中国人民解放军空军预警学院 | CNN-LSTM-based air formation target intention identification method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114117073B (en) | 2024-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Simulating land use change by integrating ANN-CA model and landscape pattern indices | |
| US20190385338A1 (en) | Synthesizing training data for broad area geospatial object detection | |
| US20190236479A1 (en) | Method and apparatus for providing efficient testing of systems by using artificial intelligence tools | |
| US20160379388A1 (en) | System and method for combining geographical and economic data extracted from satellite imagery for use in predictive modeling | |
| CN114117073A (en) | Method and device for identifying group intention, computer equipment and readable medium | |
| CN112417176B (en) | Method, equipment and medium for mining implicit association relation between enterprises based on graph characteristics | |
| CN109886719B (en) | Data mining processing method and device based on grid and computer equipment | |
| Bai et al. | A forecasting method of forest pests based on the rough set and PSO-BP neural network | |
| CN103839183A (en) | Intelligent credit extension method and intelligent credit extension device | |
| Yemshanov et al. | A new multicriteria risk mapping approach based on a multiattribute frontier concept | |
| CN105046323B (en) | Regularization-based RBF network multi-label classification method | |
| CN111259167B (en) | User request risk identification method and device | |
| CN114707685A (en) | Event prediction method and device based on big data modeling analysis | |
| Sujatha et al. | A new efficient SIF-based FCIL (SIF–FCIL) mining algorithm in predicting the crime locations | |
| Das et al. | A geo-statistical approach for crime hot spot prediction | |
| Alhaj Ali et al. | Distributed data mining systems: techniques, approaches and algorithms | |
| Chandrayan et al. | Atmospheric weather fluctuation prediction using machine learning | |
| Kavitha | Assessing teacher’s performance evaluation and prediction model using cloud computing over multi-dimensional dataset | |
| Dilts et al. | The landscape similarity toolbox: new tools for optimizing the location of control sites in experimental studies | |
| Zhang et al. | Two-stage traffic clustering based on HNSW | |
| Yıldırım | Unsupervised classification of multispectral Landsat images with multidimensional particle swarm optimization | |
| Chen et al. | Spatio-Temporal Dynamic Multi-graph Attention Network for Ride-Hailing Demand Prediction | |
| CN111339446A (en) | Interest point mining method and device, electronic equipment and storage medium | |
| Liu et al. | Semisupervised community preserving network embedding with pairwise constraints | |
| Kamsing et al. | Deep neural learning adaptive sequential Monte Carlo for automatic image and speech recognition |
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 |