CN109933669A - A kind of matching process of situation of battlefield data label - Google Patents
A kind of matching process of situation of battlefield data label Download PDFInfo
- Publication number
- CN109933669A CN109933669A CN201910208673.9A CN201910208673A CN109933669A CN 109933669 A CN109933669 A CN 109933669A CN 201910208673 A CN201910208673 A CN 201910208673A CN 109933669 A CN109933669 A CN 109933669A
- Authority
- CN
- China
- Prior art keywords
- situation
- label
- level
- battlefield
- labels
- 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 26
- 230000008569 process Effects 0.000 title claims abstract description 20
- 230000003068 static effect Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000010304 firing Methods 0.000 claims description 6
- 238000011835 investigation Methods 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 231100000225 lethality Toxicity 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 230000003542 behavioural effect Effects 0.000 claims 1
- 239000012141 concentrate Substances 0.000 claims 1
- 102000051759 human factor J Human genes 0.000 claims 1
- 108700008420 human factor J Proteins 0.000 claims 1
- 238000010276 construction Methods 0.000 abstract description 2
- 238000010801 machine learning Methods 0.000 abstract description 2
- 239000000523 sample Substances 0.000 description 13
- 238000010586 diagram Methods 0.000 description 3
- 239000012468 concentrated sample Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
Classifications
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of matching process of situation of battlefield data label, step includes: to construct situation of battlefield ontology knowledge base according to situation of battlefield element；Establish situation of battlefield data label frame；Tree algorithm, which is promoted, using gradient carries out numeralization situation tag match.The matching process of the situation of battlefield data label utilizes ontological construction commander knowledge base, and it fights field data label and carries out numeralization definition, tree algorithm is promoted in conjunction with gradient in machine learning to match situation data label, improves the efficiency of decision-making of battleficld command personnel.
Description
Technical field
The present invention relates to a kind of tag match method, especially a kind of matching process of situation of battlefield data label.
Background technique
Battlefield data label is the important means for assisting commander efficiently to understand situation of battlefield, is also commander's inquiry, benefit
Simple and convenient approach is provided with management battlefield data sample.Battlefield data label not only contains the essence of battlefield element
Feature and inherent attribute, more Macro or mass analysis the general cognitive result of situation of battlefield.
It is different from common labeling method, the military terms that battlefield data label often uses specification rigorous,
User is also usually the battlefield decision-maker of profession, this just makes battlefield data label with more professional and accuracy.Its
Secondary, battlefield data label is related to all kinds of battlefield elements of battle space, and scale is more huge compared to other field label, but certainly
Plan personnel but need to realize the extraction to information and analysis and utilization in a very short period of time, this undoubtedly increases the difficulty of tag match
Degree.
Summary of the invention
Goal of the invention: providing a kind of matching process of situation of battlefield data label, using ontological construction commander's knowledge base,
And fight field data label and carry out numeralization definition, tree algorithm is promoted in conjunction with gradient in machine learning, and situation data label is carried out
Matching improves the efficiency of decision-making of battleficld command personnel.
Technical solution: the matching process of situation of battlefield data label of the present invention includes the following steps:
Step 1, situation of battlefield ontology knowledge base is constructed according to situation of battlefield element；
Step 2, situation of battlefield data label frame is established；
Step 3, tree algorithm is promoted using gradient carry out numeralization situation tag match.
Further, in step 1, situation of battlefield element includes static situation element and dynamic posture element；Static situation
Element includes equipment element, environmental element, staff element, element of resource and element of time；Dynamic posture element then includes row
For element, relational factors and target component；The situation of battlefield ontology knowledge base of building includes situation Factors ' Concept collection, and situation is real
Example collection and situation rule base；Situation Factors ' Concept integrates as the set of concept term in situation knowledge；Situation example set is situation
The set of example；Situation rule base is the rule base of inferenctial knowledge.
Further, in step 2, the situation of battlefield data label frame of foundation is a level-one label and three second level marks
Label constitute tree-like frame structure；Level-one label is that situation result recognizes label；Three second level labels be respectively task category label,
Resource Properties label and ability numeric value label.
Further, task category label includes three task type, task object and task environment three-level labels；Appoint
Service type label includes four rush job, investigation tasks, motor-driven task and war task level Four labels；Task object includes
Main points take control, investigation three level Four labels of enemy's situation and rapid strike by force；Task environment includes mountain operations, jungle operation, cities and towns
Four level Four labels of operation and island operation.
Further, Resource Properties label includes natural environment resources, weaponry resource and information resources three three
Grade label；Natural environment resources include three weather temperature, height above sea level and the visual field visibility level Four labels；Weaponry money
Source includes four communication capacity, weapon lethality, firing area and sensitivity level Four labels；Information resources include troops' letter
Three breath, decision information and information level Four labels.
Further, ability numeric value label includes three weapon performance, fight capability and logistics support ability three-level labels；
Weapon performance includes three attack, firing area and phylactic power defensive power level Four labels；Fight capability includes troops' quantity, action
Four power, implementation capacity and military theory level level Four labels；Logistics support ability includes resource provisioning amount, supply personnel's number
And three level Four labels of information network radiancy.
Further, it is quantitatively calculated to some level Four label progress tag capabilities numerical value in ability numeric value label
When, the set of data samples compositions all for the level Four label in the data sample of battlefieldTake collection
Maximum value in conjunctionAnd minimum valueCalculate maximum value and minimum value
Difference Δ dm=(dm)max-(dm)min, define the index score of the level Four label are as follows:
If measuring the level Four label shares n indexs, the tag capabilities numerical computational formulas of the level Four label are as follows:
In formula, f1,f2,...,fnThe respectively weight of indices.
Further, in step 3, being promoted when tree algorithm carries out numeralization situation tag match using gradient includes two
With step:
Step 3.1, training set is generated by the training of GBDT algorithm to situation of battlefield data sample, and reserves one group of battlefield number
Examine final matching result whether reasonable as verifying collection according to sample；
Step 3.2, the matching result that polynary GBDT sorting algorithm generates task category label is first passed through, then is returned by GBDT
The matching result of reduction method generation Resource Properties label and ability numeric value label.
Further, the data label concentrated to the matching result and verifying that obtain in step 3.2 carries out similarity examination,
If the battlefield data label collection that GBDT algorithm generates is LR, wherein sharingSubtab；Verify the battlefield concentrated
Sample data is the result is that LT, including identical quantitySubtab；Then define similarity factor are as follows:
In formula, ratio is by LRWith LTIntersection and LRWith LTWhat union was divided by, as set LRAnd LTIt is similar when being sky
Coefficient J (LR,LT) it is defined as 1, final similarity examination standard is that similarity factor is bigger, illustrates that similarity is higher, matched data
Label result is also more accurate.
Compared with prior art, the present invention the beneficial effect is that: (1) concept of " situation element ontology " is introduced, to abstract
Situation of battlefield element classify, the relation on attributes between situation Factors ' Concept and concept is described, the final situation ontology that constructs is known
Know library；(2) four class situation of battlefield labels are classified and are defined with numeralization, establish perfect situation of battlefield label frame
Frame；(3) promoting tree algorithm with gradient according to the intension of different situation labels realizes the classification to unknown battlefield data sample
With matching process, reasonable tag match method is proposed.
Detailed description of the invention
Fig. 1 is the flow diagram of situation data label matching process of the invention；
Fig. 2 is the structural schematic diagram of situation ontology knowledge base of the invention；
Fig. 3 is the schematic diagram of situation data label frame of the invention.
Specific embodiment
Technical solution of the present invention is described in detail with reference to the accompanying drawing, but protection scope of the present invention is not limited to
The embodiment.
As shown in Figure 1, the matching process of situation of battlefield data label of the present invention, includes the following steps:
Step 1, situation of battlefield ontology knowledge base is constructed according to situation of battlefield element；
Step 2, situation of battlefield data label frame is established；
Step 3, tree algorithm is promoted using gradient carry out numeralization situation tag match.
Further, in step 1, situation of battlefield element includes static situation element and dynamic posture element；Static situation
Element includes equipment element, environmental element, staff element, element of resource and element of time；Dynamic posture element then includes row
For element, relational factors and target component；As shown in Fig. 2, the situation of battlefield ontology knowledge base of building includes that situation element is general
Read collection, situation example set and situation rule base；Situation Factors ' Concept integrates as the set of concept term in situation knowledge；Situation is real
Example integrates as the set of situation example；Situation rule base is the rule base of inferenctial knowledge.Static situation element will in military field
Specific classification, such as: river, military base, aircraft and airport etc.；Dynamic posture element will be specific in military field
Classification, such as: Operation Target can regard dynamic posture element as, set the maneuvering target under the scene of airport as reconnaissance plane, fighter plane
And bomber etc..
Further, in step 2, the situation of battlefield data label frame of foundation is a level-one label and three second level marks
Label constitute tree-like frame structure, as shown in Figure 3；Level-one label is that situation result recognizes label；Three second level labels are respectively to appoint
Business class label, Resource Properties label and ability numeric value label.
Further, task category label includes three task type, task object and task environment three-level labels；Appoint
Service type label includes four rush job, investigation tasks, motor-driven task and war task level Four labels；Task object includes
Main points take control, investigation three level Four labels of enemy's situation and rapid strike by force；Task environment includes mountain operations, jungle operation, cities and towns
Four level Four labels of operation and island operation.
Further, Resource Properties label includes natural environment resources, weaponry resource and information resources three three
Grade label；Natural environment resources include three weather temperature, height above sea level and the visual field visibility level Four labels；Weaponry money
Source includes four communication capacity, weapon lethality, firing area and sensitivity level Four labels；Information resources include troops' letter
Three breath, decision information and information level Four labels.
Further, ability numeric value label includes three weapon performance, fight capability and logistics support ability three-level labels；
Weapon performance includes three attack, firing area and phylactic power defensive power level Four labels；Fight capability includes troops' quantity, action
Four power, implementation capacity and military theory level level Four labels；Logistics support ability includes resource provisioning amount, supply personnel's number
And three level Four labels of information network radiancy.
Further, it is quantitatively calculated to some level Four label progress tag capabilities numerical value in ability numeric value label
When, the set of data samples compositions all for the level Four label in the data sample of battlefieldTake collection
Maximum value in conjunctionAnd minimum valueCalculate maximum value and minimum value
Difference Δ dm=(dm)max-(dm)min, define the index score of the level Four label are as follows:
If measuring the level Four label shares n indexs, the tag capabilities numerical computational formulas of the level Four label are as follows:
In formula, f1,f2,...,fnThe respectively weight of indices.
Further, in step 3, being promoted when tree algorithm carries out numeralization situation tag match using gradient includes two
With step:
Step 3.1, training set is generated by the training of GBDT algorithm to situation of battlefield data sample, and reserves one group of battlefield number
Examine final matching result whether reasonable as verifying collection according to sample；
Step 3.2, the matching result that polynary GBDT sorting algorithm generates task category label is first passed through, then is returned by GBDT
The matching result of reduction method generation Resource Properties label and ability numeric value label.
For task category label, task type or task object are either described, what is taken is all qualitative
Description, defines to artificialization the type of all task category labels.Therefore, the result of tag match also must be task gesture mark
Sign certain class label determined in frame.In other words, the matching of task gesture label substantially belongs to a multivariate classification problem,
Therefore polynary GBDT sorting algorithm is used, the specific steps are as follows:
1) log-likelihood loss function is defined are as follows:
2) if output sample class is k, yk=1, kth class Probability pk(x) expression formula are as follows:
3) comprehensive upper two formula, i-th of sample for calculating t wheel correspond to the negative gradient error of classification l are as follows:
4) for the decision tree of generation, each best negative gradient match value of leaf node are as follows:
5) it for convenience of optimization above formula, is generally replaced with approximation, the match value after approximation are as follows:
For Resource Properties label, the actual value of battlefield data can be portrayed directly as label numerical value, it
An often continuous real number value；For ability numeric value label, it is on the basis of Resource Properties label numerical value according to public affairs
What formula was derived by, it is again with the continuous real number value information within the scope of 0-1.To Resource Properties label and ability numeric value label
For, matched result should be that the new data sample label value of prediction is specially how many, therefore resource and ability gesture label
The step of matching substantially belongs to regression problem, GBDT regression algorithm is as follows:
1) the training set sample for assuming input is T={ (x1,y1),(x2,y2),...(xm,ym), maximum number of iterations is
T, loss function are denoted as L, export strong learner f (x)；
2) weak learner is initialized are as follows:
To iteration wheel number t=1,2 ... m has:
A) to sample i=1,2 ... m calculates negative gradient are as follows:
B) (x is utilizedi,rti) (i=1,2 ..m), it is fitted and obtains the t CART regression tree, corresponding leaf node region
For Rij, j=1,2 ..J, wherein J is leaf node number；
C) best-fit values are calculated to area foliage j=1,2 ..J are as follows:
D) strong learner is updated are as follows:
3) final strong learner f (x) expression formula is obtained are as follows:
Further, the data label concentrated to the matching result and verifying that obtain in step 3.2 carries out similarity examination,
If the battlefield data label collection that GBDT algorithm generates is LR, wherein sharingSubtab；Verify the battlefield concentrated
Sample data is the result is that LT, including identical quantitySubtab；Then define similarity factor are as follows:
In formula, ratio is by LRWith LTIntersection and LRWith LTWhat union was divided by, as set LRAnd LTIt is similar when being sky
Coefficient J (LR,LT) it is defined as 1, final similarity examination standard is that similarity factor is bigger, illustrates that similarity is higher, matched data
Label result is also more accurate.
The matching process of battlefield data label proposed by the present invention helps battleficld command personnel in face of the situation of battlefield of variation
When rapidly extracting battle field information, reduce the incorrect decision rate of commanding, improve the battlefield efficiency of decision-making.
As described above, must not be explained although the present invention has been indicated and described referring to specific preferred embodiment
For the limitation to invention itself.It without prejudice to the spirit and scope of the invention as defined in the appended claims, can be right
Various changes can be made in the form and details for it.
Claims (9)
1. a kind of matching process of situation of battlefield data label, which comprises the steps of:
Step 1, situation of battlefield ontology knowledge base is constructed according to situation of battlefield element；
Step 2, situation of battlefield data label frame is established；
Step 3, tree algorithm is promoted using gradient carry out numeralization situation tag match.
2. the matching process of situation of battlefield data label according to claim 1, which is characterized in that in step 1, battlefield state
Important and influential persons element includes static situation element and dynamic posture element；Static situation element includes equipment element, environmental element, Ren Yuanyao
Element, element of resource and element of time；Dynamic posture element then includes behavioral primitive, relational factors and target component；Building
Situation of battlefield ontology knowledge base include situation Factors ' Concept collection, situation example set and situation rule base；Situation Factors ' Concept
Integrate as the set of concept term in situation knowledge；Situation example set is the set of situation example；Situation rule base is inferenctial knowledge
Rule base.
3. the matching process of situation of battlefield data label according to claim 1, which is characterized in that in step 2, foundation
Situation of battlefield data label frame is that a level-one label and three second level labels constitute tree-like frame structure；Level-one label is state
Gesture result recognizes label；Three second level labels are respectively task category label, Resource Properties label and ability numeric value label.
4. according to the matching process for the situation of battlefield data label that claim 3 is stated, which is characterized in that task category label includes
Three task type, task object and task environment three-level labels；Task type label include rush job, investigation tasks,
Four level Four labels of motor-driven task and war task；Task object includes that main points take control, investigation enemy's situation and rapid strike three by force
A level Four label；Task environment includes four mountain operations, jungle operation, cities and towns operation and island operation level Four labels.
5. according to the matching process for the situation of battlefield data label that claim 3 is stated, which is characterized in that Resource Properties label includes
Three natural environment resources, weaponry resource and information resources three-level labels；Natural environment resources include weather temperature, sea
Three level Four labels of degree of lifting and visual field visibility；Weaponry resource includes communication capacity, weapon lethality, firing area
And four level Four labels of sensitivity；Information resources include three troops' information, decision information and information level Four labels.
6. according to the matching process for the situation of battlefield data label that claim 3 is stated, which is characterized in that ability numeric value label includes
Three weapon performance, fight capability and logistics support ability three-level labels；Weapon performance includes attack, firing area and prevents
Imperial three level Four labels of power；Fight capability includes four troops' quantity, action edge, implementation capacity and military theory level level Four marks
Label；Logistics support ability includes resource provisioning amount, supply three level Four labels of personnel's number and information network radiancy.
7. according to the matching process for the situation of battlefield data label that claim 6 is stated, which is characterized in that ability numeric value label
In some level Four label carry out tag capabilities numerical value when quantitatively calculating, it is all for the level Four label in the data sample of battlefield
The set that data sample is constitutedTake the maximum value in setAnd most
Small valueCalculate the difference Δ d of maximum value and minimum valuem=(dm)max-(dm)min, define the level Four mark
The index score of label are as follows:
If measuring the level Four label shares n indexs, the tag capabilities numerical computational formulas of the level Four label are as follows:
In formula, f1,f2,...,fnThe respectively weight of indices.
8. the matching process for the situation of battlefield data label stated according to claim 1, which is characterized in that in step 3, utilize gradient
Promoted tree algorithm carry out numeralization situation tag match when include two matching steps:
Step 3.1, training set is generated by the training of GBDT algorithm to situation of battlefield data sample, and reserves one group of battlefield data sample
Whether this conduct verifying collection examines final matching result reasonable；
Step 3.2, the matching result that polynary GBDT sorting algorithm generates task category label is first passed through, then is returned and is calculated by GBDT
The matching result of method generation Resource Properties label and ability numeric value label.
9. according to the matching process for the situation of battlefield data label that claim 8 is stated, which is characterized in that obtained in step 3.2
Matching result and verifying concentrate data label carry out similarity examination, if GBDT algorithm generate battlefield data label collection be
LR, wherein sharingSubtab；The battlefield sample data concentrated is verified the result is that LT, including identical number
AmountSubtab；Then define similarity factor are as follows:
In formula, ratio is by LRWith LTIntersection and LRWith LTWhat union was divided by, as set LRAnd LTWhen being sky, similarity factor
J(LR,LT) it is defined as 1, final similarity examination standard is that similarity factor is bigger, illustrates that similarity is higher, matched data label
As a result also more accurate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910208673.9A CN109933669B (en) | 2019-03-19 | 2019-03-19 | Matching method of battlefield situation data labels |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910208673.9A CN109933669B (en) | 2019-03-19 | 2019-03-19 | Matching method of battlefield situation data labels |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109933669A true CN109933669A (en) | 2019-06-25 |
| CN109933669B CN109933669B (en) | 2023-04-21 |
Family
ID=66987714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910208673.9A Active CN109933669B (en) | 2019-03-19 | 2019-03-19 | Matching method of battlefield situation data labels |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109933669B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110619052A (en) * | 2019-08-29 | 2019-12-27 | 中国电子科技集团公司第二十八研究所 | Knowledge graph-based battlefield situation sensing method |
| CN110742595A (en) * | 2019-11-12 | 2020-02-04 | 中润普达(十堰)大数据中心有限公司 | Abnormal blood pressure monitoring system based on cognitive cloud system |
| CN111597202A (en) * | 2020-04-27 | 2020-08-28 | 中国电子科技集团公司第二十九研究所 | Battlefield situation information on-demand extraction method and device based on fractal theory |
| CN112685615A (en) * | 2021-01-05 | 2021-04-20 | 河北冀联人力资源服务集团有限公司 | Intelligent database data processing method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110271822A1 (en) * | 2010-05-04 | 2011-11-10 | Makor Issues And Rights Ltd. | Automatic Real Time Command and Control System |
| CN103488886A (en) * | 2013-09-13 | 2014-01-01 | 清华大学 | State threat assessment method based on fuzzy dynamic Bayesian network |
| CN107748803A (en) * | 2017-11-20 | 2018-03-02 | 中国运载火箭技术研究院 | A kind of roomage state characteristic event database design method |
| CN108647414A (en) * | 2018-04-27 | 2018-10-12 | 北京华如科技股份有限公司 | Operation plan adaptability analysis method based on emulation experiment and storage medium |
| CN109035003A (en) * | 2018-07-04 | 2018-12-18 | 北京玖富普惠信息技术有限公司 | Anti- fraud model modelling approach and anti-fraud monitoring method based on machine learning |
-
2019
- 2019-03-19 CN CN201910208673.9A patent/CN109933669B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110271822A1 (en) * | 2010-05-04 | 2011-11-10 | Makor Issues And Rights Ltd. | Automatic Real Time Command and Control System |
| CN103488886A (en) * | 2013-09-13 | 2014-01-01 | 清华大学 | State threat assessment method based on fuzzy dynamic Bayesian network |
| CN107748803A (en) * | 2017-11-20 | 2018-03-02 | 中国运载火箭技术研究院 | A kind of roomage state characteristic event database design method |
| CN108647414A (en) * | 2018-04-27 | 2018-10-12 | 北京华如科技股份有限公司 | Operation plan adaptability analysis method based on emulation experiment and storage medium |
| CN109035003A (en) * | 2018-07-04 | 2018-12-18 | 北京玖富普惠信息技术有限公司 | Anti- fraud model modelling approach and anti-fraud monitoring method based on machine learning |
Non-Patent Citations (2)
| Title |
|---|
| 司成等: "基于本体的网络安全态势要素知识库模型研究", 《计算机科学》 * |
| 李军等: "指挥与控制系统体系结构能力指标模型构建方法研究", 《第五届中国指挥控制大会论文集》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110619052A (en) * | 2019-08-29 | 2019-12-27 | 中国电子科技集团公司第二十八研究所 | Knowledge graph-based battlefield situation sensing method |
| CN110619052B (en) * | 2019-08-29 | 2021-12-28 | 中国电子科技集团公司第二十八研究所 | Knowledge graph-based battlefield situation sensing method |
| CN110742595A (en) * | 2019-11-12 | 2020-02-04 | 中润普达(十堰)大数据中心有限公司 | Abnormal blood pressure monitoring system based on cognitive cloud system |
| CN111597202A (en) * | 2020-04-27 | 2020-08-28 | 中国电子科技集团公司第二十九研究所 | Battlefield situation information on-demand extraction method and device based on fractal theory |
| CN111597202B (en) * | 2020-04-27 | 2022-08-16 | 中国电子科技集团公司第二十九研究所 | Battlefield situation information on-demand extraction method based on fractal theory |
| CN112685615A (en) * | 2021-01-05 | 2021-04-20 | 河北冀联人力资源服务集团有限公司 | Intelligent database data processing method and system |
| CN112685615B (en) * | 2021-01-05 | 2023-11-03 | 河北冀联人力资源服务集团有限公司 | Intelligent database data processing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109933669B (en) | 2023-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109933669A (en) | A kind of matching process of situation of battlefield data label | |
| CN110223168B (en) | Label propagation anti-fraud detection method and system based on enterprise relationship map | |
| CN109034044B (en) | Pedestrian re-identification method based on fusion convolutional neural network | |
| CN113722509B (en) | Knowledge graph data fusion method based on entity attribute similarity | |
| Hu et al. | Identification of migratory insects from their physical features using a decision-tree support vector machine and its application to radar entomology | |
| CN110188209A (en) | Cross-module state Hash model building method, searching method and device based on level label | |
| CN112417176B (en) | Method, equipment and medium for mining implicit association relation between enterprises based on graph characteristics | |
| CN113254507B (en) | Intelligent construction and inventory method for data asset directory | |
| CN114897085A (en) | Clustering method based on closed subgraph link prediction and computer equipment | |
| CN112149556B (en) | Face attribute identification method based on deep mutual learning and knowledge transfer | |
| Tan et al. | The research of air combat intention identification method based on bilstm+ attention | |
| Chen | Multiple criteria choice modeling using the grounds of T‐spherical fuzzy REGIME analysis | |
| Feng et al. | Research on Threat Assessment evaluation model based on improved CNN algorithm | |
| CN107392243A (en) | A kind of image classification method of the semantic space supervised learning based on kernel LDA | |
| CN115358477B (en) | Fight design random generation system and application thereof | |
| CN116070696A (en) | Cross-domain data deep migration method, device, equipment and storage medium | |
| CN105701510A (en) | Zero lens image classification method based on shared model space learning | |
| CN111652102B (en) | Power transmission channel target identification method and system | |
| CN114970684A (en) | Community detection method for extracting network core structure by combining VAE | |
| Liu | Research on Naive Bayes Integration Method based on Kmeans++ digital teaching clustering | |
| CN110968795B (en) | Data association matching system of company image lifting system | |
| CN113283604A (en) | Multi-element situation self-adaptive reasoning method and application | |
| CN117592385B (en) | System design optimization method based on influence factors, server and storage medium | |
| CN116578613B (en) | Data mining system for big data analysis | |
| Mei et al. | A pests image classification method based on improved wolf pack algorithm to optimize Bayesian network structure learning |
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 |