Fractal dimension optimization-based global command and control platform data processing and decision-making method

Abstract

The invention discloses a fractal dimension optimization-based global command and control platform data processing and decision-making method, which comprises the following steps of S1, data acquisition: collecting data of a battlefield environment through various sensors; s2, fractal dimension calculation: after data acquisition in the step S1 is completed, fractal dimension calculation is carried out, and complexity and information richness evaluation is carried out on the acquired data. According to the invention, the data processing capability and decision support efficiency of the global command and control platform can be effectively improved, the method is suitable for a rapidly changing battlefield environment, and the operation efficiency and decision quality of commanders are improved.

Description

Technical Field

[0001] The present invention belongs to the fields of computer application technology and command and control technology, and relates to a data processing and decision-making method for a global command and control platform based on fractal dimension optimization, which is applied to data processing and decision support systems in global command and control systems. More specifically, it relates to a technology that uses fractal geometry and self-similarity theory to optimize complex data analysis, information fusion and decision-making. Background Art

[0002] In modern warfare, commanders face challenges such as processing large amounts of information and making decisions quickly. Although existing global command and control platforms are capable of processing multi-source information, they are still limited in terms of data fusion efficiency, processing speed, and decision-making accuracy. In particular, in the face of highly complex and dynamically changing battlefield environments, traditional algorithms often have difficulty in quickly and accurately processing and analyzing large-scale heterogeneous data. In addition, existing systems are also insufficient in analyzing and utilizing the self-similarity characteristics of data, and fail to fully utilize the potential pattern recognition and prediction value in the data. Summary of the invention

[0003] (I) Purpose of the invention

[0004] The purpose of the present invention is to provide a data processing and decision-making method for a global command and control platform based on fractal dimension optimization, so as to improve the efficiency of data processing and the accuracy of decision-making.

[0005] (II) Technical solution

[0006] In order to solve the above technical problems, the present invention provides a global command and control platform data processing and decision-making method based on fractal dimension optimization, which comprises the following steps:

[0007] S1: Data Collection

[0008] Collect data about the battlefield environment through a variety of sensors;

[0009] S2: Fractal dimension calculation

[0010] After completing the data collection in step S1, the fractal dimension calculation is performed to evaluate the complexity and information richness of the collected data.

[0011] Furthermore, in step S1, the multiple sensors include satellites, drones, and ground reconnaissance systems.

[0012] Furthermore, in step S1, the data types collected include enemy and friendly positions, movement trajectories, communication activities and environmental changes.

[0013] Furthermore, in step S1, the collected data is firstly screened and verified to eliminate interference and errors; then it is uniformly formatted, and the uniform formatting includes time synchronization, coordinate alignment and data type standardization. The uniformly formatted data is integrated into a unified data set to form a data set.

[0014] Furthermore, in step S2, the fractal dimension calculation includes the following sub-steps:

[0015] S21. Data preparation;

[0016] S22.Box covering;

[0017] S23. Counting boxes;

[0018] S24. Result analysis and storage.

[0019] Furthermore, in step S21, the data preparation process is: cleaning and preprocessing the sensor collected data, and the data preprocessing includes removing noise, normalizing data, and processing missing data.

[0020] Furthermore, in step S22, the process of box covering is: using the box dimension method, covering boxes of various sizes on the multidimensional data set, and the box size depends on the characteristics of the data and the analysis objectives.

[0021] Furthermore, in step S23, the process of counting boxes is: for each box size, the minimum number of boxes that can completely cover all data points is calculated.

[0022] Furthermore, in step S24, the calculation results are analyzed to evaluate the complexity of each data point or region to identify areas that require special attention; the results are stored for the next step of self-similarity analysis and decision support.

[0023] The present invention also provides a global command and control platform data processing and decision-making system based on fractal dimension optimization, which includes:

[0024] Fractal dimension calculation module: Automatically calculate the fractal dimension of battlefield data using the box dimension method to evaluate the complexity and information richness of the data;

[0025] Self-similarity analysis module: Analyzes the self-similarity of data at different time and space scales to identify potential behavior patterns and predict future trends;

[0026] Decision support module: Combines fractal dimension and self-similarity analysis results to generate real-time situation awareness and decision suggestions, supporting decision-making from tactical to strategic levels;

[0027] Multi-level information fusion framework: Through the optimized information fusion framework, data from different sources and different types are integrated to improve the efficiency and quality of data fusion.

[0028] (III) Beneficial effects

[0029] The data processing and decision-making method of the global command and control platform based on fractal dimension optimization provided by the above technical solution can effectively improve the data processing capability and decision support efficiency of the global command and control platform, is suitable for rapidly changing battlefield environments, and improves the operational efficiency and decision-making quality of commanders. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a schematic diagram of the box dimension situation.

[0031] The cube represents the system's operational levels from strategic to tactical, and the nesting and size represent the different levels of command and control, and the decision-making level. When the coordinate state of a level (cube box) changes, the change in the connection reflects the mobilization of information instructions and resources.

[0032] Note: The present invention is temporarily based on the concept of Euclidean space flat data but is not limited to Riemann space surface data.

[0033] Figure 2 The data processing flow chart is shown in Figure 2. DETAILED DESCRIPTION

[0034] In order to make the purpose, content and advantages of the present invention more clear, the specific implementation methods of the present invention are further described in detail below in conjunction with the drawings and examples.

[0035] Reference Figure 2 As shown, the data processing and decision-making method of the global command and control platform based on fractal dimension optimization in this embodiment includes the following steps:

[0036] S1: Data Collection

[0037] In this step, data on the battlefield environment is collected through a variety of sensors (such as satellites, drones, and ground reconnaissance systems). The types of data collected include but are not limited to enemy and friendly positions, movement trajectories, communication activities, and environmental changes. To ensure the quality and relevance of the data, all collected raw data will undergo preliminary screening and verification to eliminate interference and errors. These preliminarily processed data will then be uniformly formatted for subsequent in-depth analysis. Data formatting includes time synchronization, coordinate alignment, and data type standardization to ensure that data from different sources can be effectively integrated. After completing these key preprocessing steps, all data will be integrated into a unified dataset to form a data set. This dataset will provide a solid foundation for subsequent fractal dimension calculation and self-similarity analysis, supporting accurate and efficient decision making.

[0038] S2: Fractal dimension calculation

[0039] After the data collection phase in step S1, the fractal dimension calculation is performed, which is an evaluation of the complexity and information richness of the collected data. This is performed by the following steps:

[0040] 1. Data preparation: After completing data collection, the sensor data is first cleaned and preprocessed to ensure data quality. This step is common to all types of data sources. Data preprocessing includes removing noise, normalizing data, and processing missing data.

[0041] 2. Box coverage: Use the box dimension method to cover boxes of various sizes on a multidimensional dataset (the box size depends on the characteristics of the data and the analysis objectives). For battlefield data, such as enemy and friendly positions, movement trajectories, etc., it is necessary to select an appropriate box size to cover the key spatial and temporal dimensions.

[0042] 3. Counting boxes: For each box size, calculate the minimum number of boxes that can completely cover all data points. This counting process is not only applicable to flat data, but also to higher-dimensional data such as time series or multi-parameter systems.

[0043] Dimension calculation:

[0044]

[0045] Where ε is the size of the box, and N(ε) is the minimum number of boxes required to cover the fractal. By selecting a series of ε, a graph of logN(ε) versus log1 / ε is constructed, and the slope is obtained through statistical techniques such as the least squares method, which is the desired fractal dimension.

[0046] 4. Result analysis and storage:

[0047] The calculation results are analyzed to evaluate the complexity of each data point or area to identify areas that require special attention. The results are stored for the next step of self-similarity analysis and decision support.

[0048] Example description:

[0049] A battlefield environment involving ground forces, drones, and satellite surveillance is proposed. Assume that enemy activity increases and our logistics supply situation is complicated. The global command and control platform needs to analyze data in real time to optimize deployment and response.

[0050] Deduction sample data table

[0051]

[0052] 1. Data collection:

[0053] Satellites collect imagery of enemy movement in the A1 area.

[0054] The drone monitors the B2 area and conducts fire support activities.

[0055] Ground forces report logistics supply situation in C3 area.

[0056] 2. Data preparation:

[0057] The collected images and report data are cleaned to remove environmental noise and irrelevant information.

[0058] Data normalization to unify the format and scale of data from different sources.

[0059] 3.Box Coverage:

[0060] Boxes of different sizes are overlaid on the data in areas A1, B2, and C3, respectively. For example, boxes ranging from 0.5 km × 0.5 km to 10 km × 10 km are used to overlay ground troop movements and satellite imagery data, respectively.

[0061] 4. Counting boxes:

[0062] Calculate the minimum number of boxes of each size required to cover all data points in A1, B2, and C3. For example, area A1 may require a smaller number of boxes due to its high density of enemy activity.

[0063] 5. Dimension calculation:

[0064] The fractal dimension of each region was calculated by performing linear regression analysis on logN(ε) and log1 / ε of each region.

[0065] The fractal dimension of region A1 is 1.7;

[0066] The fractal dimension of region B2 is 1.3;

[0067] The fractal dimension of the C3 region is 2.0.

[0068] 6. Result storage and analysis:

[0069] The fractal dimension results of each region are stored and compared with historical data for analysis, generating specific tactical, operational and strategic recommendations for each region, such as Figure 1 For example:

[0070] Area A1 (enemy deployment, fractal dimension is 1.7):

[0071] The higher the fractal dimension, the more complex the enemy deployment is, which may involve multi-level or multi-element military activities. The decision recommendation is to send more reconnaissance teams to obtain more information and deal with possible complex situations. The strategic level is tactical, which means that this decision mainly affects specific on-site operations.

[0072] Area B2 (friendly action, fractal dimension is 1.3):

[0073] The fractal dimension is relatively low, indicating that the friendly action is relatively simple, possibly a single or predetermined action. The decision recommendation is to adjust the fire support priority to more effectively support the current friendly action. The strategic level is operational, reflecting the direct impact of this decision on combat operations.

[0074] Area C3 (logistics supply, fractal dimension is 2.0):

[0075] The fractal dimension is the highest, indicating that the logistics supply situation is extremely complex and may contain multiple uncertainties and multiple supply chain nodes. The decision recommendation is to optimize the logistics transportation route to improve efficiency and ensure the timeliness and safety of supply. The strategy level is strategic, indicating that this decision has long-term and extensive impacts and is related to the success of the entire operational plan.

[0076] By calculating the fractal dimension of each point on the battlefield in real time, the global command and control platform can quickly identify those areas and events that need priority attention. For example, if the fractal dimension of a certain area increases suddenly, the system can automatically prompt the commander of possible abnormal conditions or complex combat states, and then make corresponding decision suggestions. These decision suggestions will be classified into different strategic levels according to the urgency and tactical importance of the event, ensuring effective response from tactical to strategic levels.

[0077] This multi-level decision support model enables the global command and control platform to maintain a high degree of flexibility and adaptability in complex and changing battlefield environments, effectively improving the efficiency and combat effectiveness of command and control.

[0078] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A data processing and decision-making method for a global command and control platform based on fractal dimension optimization, characterized in that: The following steps are involved: S1: Data Collection Collect data about the battlefield environment through a variety of sensors; S2: Fractal dimension calculation After completing the data collection in step S1, the fractal dimension calculation is performed to evaluate the complexity and information richness of the collected data.

2. The global command and control platform data processing and decision-making method based on fractal dimension optimization according to claim 1 is characterized in that: In step S1, the various sensors include satellites, drones, and ground reconnaissance systems.

3. The data processing and decision-making method for the global command and control platform based on fractal dimension optimization according to claim 2 is characterized in that: In step S1, the data types collected include enemy and friendly positions, movement trajectories, communication activities and environmental changes.

4. The data processing and decision-making method for the global command and control platform based on fractal dimension optimization according to claim 3 is characterized in that: In step S1, the collected data is firstly screened and verified to eliminate interference and errors; then it is uniformly formatted, which includes time synchronization, coordinate alignment and data type standardization. The uniformly formatted data is integrated into a unified data set to form a data set.

5. The data processing and decision-making method for the global command and control platform based on fractal dimension optimization according to claim 4 is characterized in that: In step S2, the fractal dimension calculation includes the following sub-steps: S21. Data preparation; S22.Box covering; S23. Counting boxes; S24. Result analysis and storage.

6. The data processing and decision-making method for the global command and control platform based on fractal dimension optimization according to claim 5 is characterized in that: In step S21, the data preparation process is: cleaning and preprocessing the data collected by the sensor, and the data preprocessing includes removing noise, normalizing the data, and processing missing data.

7. The global command and control platform data processing and decision-making method based on fractal dimension optimization according to claim 6 is characterized in that: In step S22, the process of box covering is: using the box dimension method, covering boxes of various sizes on the multidimensional data set, and the box size depends on the characteristics of the data and the analysis objectives.

8. The global command and control platform data processing and decision-making method based on fractal dimension optimization according to claim 7 is characterized in that: In step S23, the process of counting boxes is: for each box size, the minimum number of boxes that can completely cover all data points is calculated.

9. The global command and control platform data processing and decision-making method based on fractal dimension optimization as claimed in claim 8, characterized in that: In step S24, the calculation results are analyzed to evaluate the complexity of each data point or region to identify areas that require special attention; the results are stored for the next step of self-similarity analysis and decision support.

10. A global command and control platform data processing and decision-making system based on fractal dimension optimization, characterized in that: include: Fractal dimension calculation module: Automatically calculate the fractal dimension of battlefield data using the box dimension method to evaluate the complexity and information richness of the data; Self-similarity analysis module: Analyzes the self-similarity of data at different time and space scales to identify potential behavior patterns and predict future trends; Decision support module: Combines fractal dimension and self-similarity analysis results to generate real-time situation awareness and decision suggestions, supporting decision-making from tactical to strategic levels; Multi-level information fusion framework: Through the optimized information fusion framework, data from different sources and different types are integrated to improve the efficiency and quality of data fusion.

Images