CN114036844A - Trajectory data analysis method applied to earth war military chess deduction - Google Patents
Trajectory data analysis method applied to earth war military chess deduction Download PDFInfo
- Publication number
- CN114036844A CN114036844A CN202111333178.4A CN202111333178A CN114036844A CN 114036844 A CN114036844 A CN 114036844A CN 202111333178 A CN202111333178 A CN 202111333178A CN 114036844 A CN114036844 A CN 114036844A
- Authority
- CN
- China
- Prior art keywords
- unit
- combat
- track
- units
- grouping
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a trajectory data analysis method applied to the calculation of land battle weapons and chess, and belongs to the technical field of weapon and chess calculation. The method comprises the following steps: acquiring track information of a combat unit, wherein the combat unit comprises infantries, chariot, tanks and artillery; clustering the track of each operation unit through a clustering algorithm to obtain track clustering information of each operation unit; determining a hot spot area of each combat unit according to the track clustering information of each combat unit; grouping the combat units to obtain a plurality of grouping units; weighting and superposing the hot spot areas of all the combat units in the grouping unit to obtain the hot spot areas of the grouping unit; and analyzing the hot spot area of the grouping unit to obtain the fighting intention. The invention carries out classification and grouping processing on the operation units, thereby carrying out more refined and granular intuitive analysis on the operation indication.
Description
Technical Field
The invention relates to a trajectory data analysis method applied to the calculation of land battle weapons and chess, and belongs to the technical field of weapon and chess calculation.
Background
The system mainly comprises a map, a deduction operator and a deduction rule, and the deduction party carries out a series of decisions and countermeasures through the analysis and understanding of historical knowledge, environment and war experiences to form the simulation analysis of the battle and the war. The war chess deduction can be used for improving the operation deployment, the operation experience and the understanding of the operation of related personnel, and can play a positive role in researching military theory, simulating operation, operation evaluation and the like.
In the prior art, the track analysis process of the war game deduction is as follows:
1) simplifying the actual combat track;
2) segmenting the simplified combat trajectory;
3) clustering the segmented tracks by adopting a density-based clustering method;
4) extracting the statistical characteristics of each class cluster, and detecting the subsequent relation of each class cluster;
5) forming a subsequent relation chain according to all the subsequent relations;
6) and drawing a visual combat situation map according to the successor relationship chain.
It can be seen from the above prior art that, most of the analyses of the ground warfare military chess deduction trajectory data under the current research are not fine enough, and the data analysis rules of single or grouped combat units are difficult to reflect. Therefore, a trajectory data analysis method for war game deduction for finely dividing combat units is required.
Disclosure of Invention
The application aims to provide a track data analysis method applied to military chess deduction of land battles, and provides an effective technical scheme for the track data analysis method of military chess deduction of finely divided combat units.
In order to achieve the purpose, the application provides a technical scheme of a trajectory data analysis method applied to the pursuit of military chess of land battle, which comprises the following steps:
1) acquiring track information of a combat unit, wherein the combat unit comprises infantries, chariot, tanks and artillery;
2) clustering the track of each operation unit through a clustering algorithm to obtain track clustering information of each operation unit;
3) determining a hot spot area of each combat unit according to the track clustering information of each combat unit;
4) grouping the combat units to obtain a plurality of grouping units;
5) weighting and superposing the hot spot areas of all the combat units in the grouping unit to obtain the hot spot areas of the grouping unit; the weight in the weighted superposition process is determined according to the influence of the combat unit on the battlefield and the attack capacity;
6) and analyzing the hot spot area of the grouping unit to obtain the fighting intention.
The technical scheme of the track data analysis method applied to the deduction of the land war chess has the beneficial effects that: the invention classifies the combat entities based on the diversification of the combat entities, clusters the tracks of different combat entities through a clustering algorithm, further marshals the combat units, obtains the hot spot areas and the spatial distribution rules of the marshalling units according to the hot spot areas of the combat units in the marshalling units, and finally obtains the intuitive combat intention based on the marshalling units. The invention carries out classification and grouping processing on the fighting units, thereby carrying out more refined and granular intuitive analysis on the fighting intention.
Furthermore, before the clustering processing is carried out on the track of each operation unit, the method also comprises the step of simplifying the track information of the operation units, and the simplified track of the operation units is clustered.
Further, the track information of the combat unit is simplified by the following method: and replacing the track points falling on the same hexagonal lattice with the center points of the hexagonal lattice for simplification.
Further, the clustering algorithm is a DBSCAN algorithm.
Further, when the grouping unit comprises an infantry, a chariot and a tank, the weights of the infantry, the chariot and the tank fighting unit are respectively 0.1, 0.4 and 0.5.
Furthermore, the epsilon neighborhood of the infantry in the DBSCAN algorithm is 1 hexagonal lattice unit, and the threshold MinPoints is 5.
Drawings
FIG. 1 is a flow chart of a trajectory data analysis method of the present invention applied to the deduction of military chess for land battle;
FIG. 2 is a data classification diagram of the derived trajectory information of the present invention;
FIG. 3 is a schematic diagram showing the spatial distribution of single combat units to marshalling units according to the present invention;
FIG. 4 is a schematic diagram of the present invention for obtaining the fighting intention of the fighter according to the fighting unit and the grouping unit.
Detailed Description
The embodiment of the trajectory data analysis method applied to the deduction of the land warfare chess comprises the following steps:
the invention has the main conception that the track data of the operation units comprise the motion information of the operation units and the associated behavior mode among the operation units in the process of deducing the land war chess. The battle unit/entity track data in the land battle chess deduction is a position sequence with time information, has space-time attribute, and the time and space attribute is always required to be considered for the track data analysis. The land battle chess deduction data analysis method considering the multi-type operation units and the marshalling operation units is provided based on the track information of the multi-type operation units, so that the hot spot regions, the distribution rules and the intuitive operation intentions of the multi-type operation units and the marshalling operation units are analyzed more finely and more granularly.
Specifically, the trajectory data analysis method applied to the deduction of the land war military chess is shown in fig. 1, and comprises the following steps:
1) and acquiring the land battle military chess track information data to be analyzed, and classifying the land battle military chess track information data according to the operation units.
In this step, as shown in fig. 1, the combat unit includes infantry, chariot, tank, artillery, and other combat units, and thus the land combat troop chess trajectory information data includes infantry trajectory information, chariot trajectory information, tank trajectory information, artillery trajectory information, and other combat unit trajectory information.
2) And preprocessing the track information of each fighting unit to obtain simplified track information of the fighting units.
Let the track information of the ith combat unit be RiWhich is represented as follows
Wherein the content of the first and second substances,
time information of a jth track point in an ith combat unit track is obtained;
the horizontal and vertical coordinates of the hexagonal grid of the jth track point in the ith combat unit track are shown; i is the total number of combat units; and m is the total number of the tracing points.
For the track RiPreprocessing is performed, the main purpose of which is to simplify the trajectory RiAnd the calculation amount is reduced. The method is mainly characterized in that the trajectory points of the land battle chess, of which the original trajectory points fall on the same hexagonal lattice, are replaced by hexagonal center points for simplification in continuous time.
The simplified track information of the ith combat unit is R after track preprocessingi', which is represented as follows:
wherein the content of the first and second substances,
time information of a jth track point in the ith combat unit track is simplified;
for the ith track point in the ith simplified combat unit track, the jth track point is the horizontal and vertical coordinates of the central point of the hexagonal lattice, n is the total number of the track points after simplification, and the track points are simplified from m to n.
3) And clustering the track information of the simplified operation units through a clustering algorithm to obtain a track clustering result, wherein i is equal to 1, namely the track of the 1 st operation unit is clustered.
In this step, the clustering algorithm adopts the DBSCAN algorithm, and the clustering process is as follows:
a. establishing a knowledge base, wherein the knowledge base comprises different combat units and parameters corresponding to the combat units, and the parameters comprise self-adaptive selection of epsilon neighborhoods and threshold MinPoints; the epsilon neighborhood is the area within the radius epsilon of a given object and is called the neighborhood of the object; the threshold MinPoints is the minimum neighborhood point number for a given point to become a core object within the ε neighborhood. The epsilon neighborhood is calculated according to a chess hexagonal grid map, for example: the epsilon neighborhood of the infantry combat unit is 1 hexagonal grid unit, the threshold MinPoints is set to be 5, the significance is that within a hexagonal grid distance, more than 5 infantries consider the infantry cluster.
b. Simplified combat unit trajectory information RiSelecting a track point arbitrarily, and finding all track points which are less than or equal to epsilon neighborhood from the track point (distance information is calculated by a hexagonal lattice of a chess map); further obtaining the total number of all track points, and if the total number is smaller than a threshold MinPoints, taking the track points as noise points; and if the total number is greater than or equal to the threshold MinPoints, taking the track point as a core sample point, and distributing a new label cluster.
c. And if the track point is the core sample point, finding out other core sample points in the epsilon neighborhood of the core sample point according to the same method of the step b, and expanding the cluster class.
d. And (4) selecting other track points, and repeating the step (b) and the step (c) to finish the clustering treatment of the 1 st fighting unit.
4) Determining a hot spot area of the 1 st fighting unit according to the track clustering result: in the clustering result, the region with higher density region is the hot spot region. The area with higher density is the area with larger cluster in the clustering result, and a plurality of hot spot areas can be obtained from the clustering analysis result of one combat unit, which reflects that the number of sample points covered by the area is more and can be classified as the same cluster.
And obtaining the spatial distribution rule of the 1 st fighting unit according to the hotspot region of the 1 st fighting unit and an environment map.
The clustering result can reflect the hot spot area of the operation unit, and then the hot spot area is mapped to a specific environment map, so that the spatial position distribution characteristic of the operation unit in the map can be obtained, and the spatial position distribution characteristic is the distribution rule of the operation unit.
5) And (5) repeating the steps 3) to 4) to obtain the hot spot areas and the spatial distribution rules of the 2 nd combat unit until I is larger than or equal to I, and obtaining the hot spot areas and the spatial distribution rules of all combat units.
6) And grouping the combat units to obtain a plurality of grouped units.
The grouping unit is obtained by combining the combat units, for example: as shown in fig. 2, the infantry + chariot + tank is a grouping unit, and of course, the specific grouping rules of the grouping unit can be determined by the combined effect of the combat units of different combinations, and can also be set as required, or the grouping unit is determined according to the object to be researched and analyzed, and the grouping unit is similar to the armed force organization, for example, a synthetic camp includes tanks, infantries, artillery and infantry, so that the tank, infantry, artillery and infantry combat unit need to be jointly considered by the research synthetic camp grouping unit. Of course, if only one kind of fighting unit is in the military force organization, only one kind of fighting unit can be in the marshalling unit.
7) And determining the hot spot area of the grouping unit according to the hot spot area of each combat unit in the grouping unit, further determining the spatial distribution rule of the grouping unit, and making t equal to 1, namely determining the hot spot area and the spatial distribution rule of the 1 st grouping unit.
The hot spot area and the spatial distribution rule of the grouping unit are determined as follows:
firstly, determining a combat unit of a marshalling unit;
secondly, weighting and overlapping the hot spot areas of the combat units to obtain the hot spot areas of the marshalling units;
and finally, mapping the hot spot area of the grouping unit to a specific environment map to obtain the spatial distribution rule of the grouping unit.
The weights of different combat units are different, and the weights are determined according to the influence of the combat units on the battlefield and the attack capacity, such as: as shown in fig. 3, the grouping unit includes an infantry, a chariot and a tank, and hot spot regions of the infantry, the chariot and the tank are obtained through a clustering algorithm, and then the hot spot regions of the infantry, the chariot and the tank are weighted and superimposed to obtain the hot spot region of the grouping unit. Because the infantry has far less influence on the battlefield than the chariot and the tank, the infantry, the chariot and the tank are respectively 0.1, 0.4 and 0.5 in weight.
8) And (5) repeating the step 7) when T is equal to 2, determining the hot spot regions and the spatial distribution rules of the 2 nd grouping unit until T is greater than or equal to T, and determining the hot spot regions and the spatial distribution rules of all the grouping units.
9) And analyzing the fighting intention by combining the hot spot areas and the spatial distribution rule of the grouping unit, and giving an intuitive fighting intention.
The hot spot area is an important analysis place for realizing military force deployment, material supply, personnel convergence, combat analysis and the like. The spatial distribution rule is an important analysis means for realizing and researching force deployment, combat assessment and the like.
In the step, the fighting intention of the fighter can be visually shown by utilizing the dovetail arrow according to the rules in the previously established knowledge base and the hot spot areas and the spatial distribution rules of the grouping units. The fighting intention is the direction of attack or retreat trend, and the weight can be set by the user according to different hitting purposes for shooting. For example, according to the distribution rule of the grouping unit 1 (including infantry and chariot) and the distribution rule of the grouping unit 2 (including tank and cruise missile) of the red party, the final red party combat distribution rule is obtained through a weighting fusion mode (the grouping unit 1 is set to be 0.3, and the grouping unit 2 is set to be 0.7), and the combat intention is plotted on the graph by observing the final distribution rule and combining with the actual track direction and utilizing a dovetail arrow, namely the obtained combat intention is obtained.
As shown in fig. 4, the force influence deployments of the red and blue parties are respectively formed according to the distribution rules generated by the single combat unit and the grouping unit, and the combat intentions of each party are obtained by combining the military chess map environment and by means of fusion and observation of various data information.
In the foregoing embodiment, the clustering algorithm uses the DBSCAN algorithm, and as other implementation manners, other clustering algorithms such as the cancel algorithm may also be used, which is not limited in the present invention.
The method can analyze the military chess deduction data information of the army at multiple angles in a diversified manner, and can better and more comprehensively analyze the military chess deduction data information compared with the traditional mode, thereby providing a new solution for researching military force deployment, operation evaluation and operation efficiency. The method can also be used in other fields of diversified traffic data analysis and the like, and provides a reliable basis for further improving various data analysis.
Claims (6)
1. A trajectory data analysis method applied to the deduction of land battle military chess is characterized by comprising the following steps:
1) acquiring track information of a combat unit, wherein the combat unit comprises infantries, chariot, tanks and artillery;
2) clustering the track of each operation unit through a clustering algorithm to obtain track clustering information of each operation unit;
3) determining a hot spot area of each combat unit according to the track clustering information of each combat unit;
4) grouping the combat units to obtain a plurality of grouping units;
5) weighting and superposing the hot spot areas of all the combat units in the grouping unit to obtain the hot spot areas of the grouping unit; the weight in the weighted superposition process is determined according to the influence of the combat unit on the battlefield and the attack capacity;
6) and analyzing the hot spot area of the grouping unit to obtain the fighting intention.
2. The trajectory data analysis method applied to the thrust of land war weapons and chess according to claim 1, further comprising the step of simplifying trajectory information of the operational units before the step of clustering the trajectories of each operational unit, wherein the simplified trajectories of the operational units are clustered.
3. The trajectory data analysis method applied to the thrust of land war weapons and chess according to claim 2, wherein the way of simplifying the trajectory information of the battle units is as follows: and replacing the track points falling on the same hexagonal lattice with the center points of the hexagonal lattice for simplification.
4. The trajectory data analysis method applied to the thrust of land war chess according to claim 1, characterized in that said clustering algorithm is a DBSCAN algorithm.
5. The trajectory data analysis method applied to the pursuit of military chess for land battle according to claim 1, characterized in that when the grouping unit comprises an infantry, a chariot and a tank, the weights of the infantry, the chariot and the tank battle unit are respectively 0.1, 0.4 and 0.5.
6. The trajectory data analysis method applied to the thrust of land war chess according to claim 4, wherein the epsilon neighborhood of the infantry in DBSCAN algorithm is 1 hexagonal cell, and the threshold MinPoints is 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111333178.4A CN114036844A (en) | 2021-11-11 | 2021-11-11 | Trajectory data analysis method applied to earth war military chess deduction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111333178.4A CN114036844A (en) | 2021-11-11 | 2021-11-11 | Trajectory data analysis method applied to earth war military chess deduction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114036844A true CN114036844A (en) | 2022-02-11 |
Family
ID=80137251
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111333178.4A Pending CN114036844A (en) | 2021-11-11 | 2021-11-11 | Trajectory data analysis method applied to earth war military chess deduction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114036844A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115062203A (en) * | 2022-08-18 | 2022-09-16 | 中国人民解放军陆军指挥学院 | Trajectory clustering algorithm of war and chess deduction system based on space-time and battle marshalling |
-
2021
- 2021-11-11 CN CN202111333178.4A patent/CN114036844A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115062203A (en) * | 2022-08-18 | 2022-09-16 | 中国人民解放军陆军指挥学院 | Trajectory clustering algorithm of war and chess deduction system based on space-time and battle marshalling |
| CN115062203B (en) * | 2022-08-18 | 2022-11-18 | 中国人民解放军陆军指挥学院 | Trajectory clustering method of war game deduction system based on space-time and combat marshalling |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Przemieniecki | Mathematical methods in defense analyses | |
| CN108647414A (en) | Operation plan adaptability analysis method based on emulation experiment and storage medium | |
| CN111783020B (en) | Battlefield entity target grouping method and system with multidimensional features | |
| Gazibey et al. | Interaction among the Criteria Affecting Main Battle Tank Selection: An Analysis with DEMATEL Method. | |
| CN108764453A (en) | The modeling method and action prediction system of game are synchronized towards multiple agent | |
| CN114036844A (en) | Trajectory data analysis method applied to earth war military chess deduction | |
| CN109541960A (en) | A kind of system and method for the confrontation of aircraft digital battlefield | |
| Chmielewski et al. | Methods and analytical tools for assessing tactical situation in military operations using potential approach and sensor data fusion | |
| CN111797966B (en) | Multi-machine collaborative global target distribution method based on improved flock algorithm | |
| CN108734334A (en) | A kind of missile-gun combined Algorithm of Firepower Allocation preferential based on D numbers and menace | |
| CN108804741A (en) | D-S evidence theory shell combination Algorithm of Firepower Allocation under efficiency maximal condition | |
| Ye et al. | Cognitive cooperative-jamming decision method based on bee colony algorithm | |
| Zhong et al. | Design of air defense deployment optimization model based on adaptive nested PSO algorithm | |
| CN114819038A (en) | Target clustering method for improving image cluster algorithm based on Gaussian mapping and mixed operator | |
| Von Clausewitz | The fog of war | |
| Jia et al. | Heterogeneous Interception Equipment Deployment Method Based on Heuristic Optimization Algorithm | |
| CN110930054A (en) | Data-driven battle system key parameter rapid optimization method | |
| Zhou et al. | An improved discrete shuffled frog leaping algorithm for cooperative multi-target assignment of bvr air combat | |
| CN108805150B (en) | Airspace trafficability analysis method based on grid topographic features | |
| CN117436223A (en) | Construction method of intelligent cluster system combat effectiveness evaluation index system | |
| CN114971423B (en) | Multi-UCAV collaborative task allocation method, device, electronic equipment and medium | |
| Wheeler | It pays to be popular: A study of civilian assistance and guerilla warfare | |
| Qin et al. | Confrontation Simulation Platform Based on Spatio-temporal Agents | |
| Hu et al. | A Neural Network-Based Intelligent Decision-Making in the Air-Offensive Campaign with Simulation | |
| Chen et al. | Index system construction and weight distribution method based on improved credibility |
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 |