A method, device and program product for identifying a wargame target intention

Abstract

The application discloses a kind of wargame target intention recognition method, device and program product, the present application is based on wargame battlefield situation data, to automatically determine the moving area of the enemy operator to be observed, and extract its movement intention feature relative to each hexagon in the moving area Then, based on the movement intention feature, the intention probability of the enemy operator to be observed moving to each hexagon is calculated, finally, according to each intention probability, the movement intention recognition result of the enemy operator to be observed can be generated;In this way, the present application realizes the quantitative characterization of the enemy operator movement intention, can output the probabilistic prediction result of fine granularity, not only solves the limitation that artificial research and judgment is difficult to consider multi-dimensional complex factors in mass data comprehensively, but also effectively overcomes the uncertainty and poor real-time problem caused by completely relying on the subjective research and judgment of commander's experience in traditional method, improves the objectivity, accuracy and real-time of intention recognition.

Description

Technical Field

[0001] This invention belongs to the field of wargaming situation estimation technology, specifically relating to a wargaming target intent recognition method, device, and program product. Background Technology

[0002] Modern wargaming, as a means of war simulation, aims to improve commanders' tactical decision-making by simulating real battlefield scenarios through a strategy simulation platform. The wargaming battlefield situation depicts the current state and combat tactics of both sides on the battlefield. It serves as the premise and basis for commanders to grasp overall battlefield information and implement operational command decisions. Given the difficulty for our side to perceive the overall battlefield situation "without blind spots," predicting the enemy's location using known local data on the battlefield will help us discern the enemy's intentions and grasp the key to victory. Therefore, how to process known data to accurately predict the enemy's position in the face of massive and complex battlefield data is a crucial issue in combat.

[0003] In practical applications of wargames, due to the lack of comprehensive automated analysis tools, most situations still rely heavily on the commander's human experience. Commanders subjectively infer the enemy's movement direction and target location by observing the battlefield situation. This approach has several significant drawbacks: First, it is highly subjective; different commanders may arrive at drastically different judgments based on the same situation, leading to poor decision-making stability. Second, it has low prediction accuracy; human information processing capabilities are limited, making it difficult to comprehensively consider complex multi-dimensional factors such as terrain and enemy-friendly distances within massive amounts of data. Third, it lacks real-time response; in fast-paced combat, the speed of manual analysis often lags behind changes in the battlefield situation. Therefore, based on the aforementioned shortcomings, there is an urgent need to provide a wargame target intent recognition method to overcome the deficiencies of traditional manual experience-based analysis, such as high subjectivity, low accuracy, and poor real-time performance, in order to improve the depth of battlefield situation perception and decision support capabilities. Summary of the Invention

[0004] The purpose of this invention is to provide a method, device, and program product for identifying wargame target intentions, in order to solve the problems of strong subjective factors, low accuracy, and poor real-time performance in the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: Firstly, a method for identifying the intent of a wargame target is provided, including: Acquire wargame battlefield situation data, and based on the wargame battlefield situation data, determine the enemy operator to be observed; Based on the wargame battlefield situation data, the movement area of ​​the enemy operator to be observed on the wargame map is determined; Using the wargame battlefield situation data, the movement intention features of the enemy operator to be observed relative to each hexagonal cell in the movement area are extracted; Based on the movement intention characteristics of the enemy operator to be observed relative to each hexagonal grid in the movement area, the probability of the enemy operator's intention to move to each hexagonal grid is calculated. Using the probability of the enemy operator's intention to move to each hexagonal grid, the movement intention recognition result of the enemy operator is generated, and the movement intention recognition result is visualized.

[0006] Based on the aforementioned disclosures, this invention automatically determines the movement area of ​​the enemy operator to be observed based on wargaming battlefield situation data, extracts its movement intention features relative to each hexagonal cell in the movement area, and then calculates the probability of the enemy operator's intention to move to each hexagonal cell based on these movement intention features. Finally, based on each intention probability, the movement intention recognition result of the enemy operator to be observed can be generated. In this way, this invention achieves a quantitative representation of the enemy operator's movement intention and can output fine-grained probabilistic prediction results. It not only solves the limitation of manual judgment in comprehensively considering multi-dimensional and complex factors in massive data, but also effectively overcomes the uncertainty and poor real-time performance caused by the subjective judgment of commanders relying entirely on human experience in traditional methods, thus improving the objectivity, accuracy, and real-time performance of intention recognition. Therefore, this invention facilitates commanders' rapid understanding and grasp of the battlefield situation, significantly improves the depth of perception of the battlefield situation and decision support capabilities, and meets the comprehensive requirements of modern wargaming for real-time performance and accuracy. Therefore, it is very suitable for large-scale application and promotion.

[0007] In one possible design, the wargame battlefield situation data includes: historical movement data of enemy operators and real-time dynamic data, wherein the historical movement data includes the coordinates of each historical movement position of the enemy operator, and the real-time dynamic data includes the current position coordinates of the enemy operator. Among them, based on the wargame battlefield situation data, the movement area of ​​the enemy operator to be observed on the wargame map is determined, including: The current position coordinates of the enemy operator to be observed are determined from the real-time dynamic data of the enemy operator; Based on the current position coordinates of the enemy operator to be observed, the most recent movement position coordinates of the enemy operator to be observed are determined from the historical movement data of the enemy operator. The most recent movement position coordinates are the historical movement position coordinates of the enemy operator to be observed that are in the previous time step of the time step corresponding to the current position coordinate. The movement direction of the enemy operator to be observed is determined based on its current position coordinates and its most recently moved position coordinates. Obtain the maximum maneuver speed and prediction time window of the enemy operator to be observed; The maximum maneuver distance of the enemy operator to be observed is calculated based on the maximum maneuver speed and the prediction time window. On the wargame map, a fan-shaped region is constructed with the current position coordinates of the enemy operator to be observed as the center, the movement direction as the center line, and the radius as the maximum maneuver distance, so as to use the fan-shaped region as the movement area.

[0008] In one possible design, the wargame battlefield situation data is used to extract the movement intention features of the enemy operator to be observed relative to each hexagonal cell in the movement area, including: Based on the wargame map, all capture points on the wargame map are determined; For any hexagonal grid in the moving area, based on the wargame battlefield situation data, the observation range of the enemy operator to be observed for all capture points is calculated after the enemy operator to be observed moves to any hexagonal grid. Based on the wargame battlefield situation data, the observation degree of our operator on the enemy operator to be observed after the enemy operator to be observed moves to any of the hexagonal squares is calculated; Based on the wargame battlefield situation data, the movement cost of the enemy operator to be observed moving to any of the hexagonal squares is calculated; Using the observation range, the observation degree, and the movement cost, the movement intention feature of the enemy operator to be observed relative to any hexagonal grid is constructed.

[0009] In one possible design, the wargame battlefield situation data includes: terrain elevation data and terrain data on the wargame map; Specifically, based on wargame battlefield situation data, the observation range of the enemy operator to be observed over all capture points is calculated after the enemy operator moves to any of the hexagonal squares, including: Based on the terrain elevation data, the elevation data of each control point and the elevation data of any hexagonal grid are determined; For any point of control, establish an observation line between any hexagonal grid and any point of control; Determine whether the elevation data of any hexagonal grid is greater than the elevation data of any control point; If so, then correct the elevation data of any hexagonal grid to obtain the corrected elevation data; From the wargame map, determine the hexagonal grid that the observation line passes through, and use it as the target grid; Based on the corrected elevation data and the elevation data of any control point, the line-of-sight height of each target grid along the observation line is calculated. Based on the terrain elevation data and the terrain data, the effective elevation data of each target cell is determined; Determine whether the line-of-sight height of each target cell is greater than the effective elevation data of each target cell; If so, it is determined that after the enemy operator to be observed moves to any of the hexagonal grids, any capture point is exposed within the observation field of the enemy operator to be observed. The observation feature value is incremented by 1, and after all capture points have been polled, the final observation feature value is obtained. The final observation feature value is used as the observation range, wherein the initial value of the observation feature value is 0.

[0010] In one possible design, based on the corrected elevation data and the elevation data of any control point, the line-of-sight height of each target grid traversed by the observation line is calculated, including: For any target grid, calculate the first elevation difference between the corrected elevation data and the elevation data of any control point, and sum the first elevation difference and the elevation data of any control point to obtain the elevation parameter; Calculate the first horizontal distance between any control point and any target grid, and the second horizontal distance between any control point and any hexagonal grid; The ratio between the first horizontal distance and the second horizontal distance is calculated, and the product of the ratio and the elevation parameter is used as the line-of-sight height of any target grid.

[0011] In one possible design, the wargame battlefield situation data includes: terrain elevation data and terrain data on the wargame map, wherein, based on the wargame battlefield situation data, the movement cost of the observed enemy operator moving to any of the hexagonal squares is calculated, including: Obtain the shortest path for the observed enemy operator to move to any of the hexagonal grids; On the wargame map, all hexagonal grids located on the shortest path are identified, and a set of path points is formed using all the identified hexagonal grids. For the i-th path point and the (i+1)-th path point in the path point set, the terrain type and elevation data of the i-th path point, as well as the terrain type and elevation data of the (i+1)-th path point, are determined based on the terrain elevation data and terrain data. Based on the terrain type of the i-th path point and the terrain type of the (i+1)-th path point, determine the terrain influence factor between the i-th path point and the (i+1)-th path point for the enemy operator to be observed. Calculate the second elevation difference between the elevation data of the i-th path point and the elevation data of the (i+1)-th path point, and based on the second elevation difference, determine the elevation influence factor between the movement of the observed enemy operator from the i-th path point to the (i+1)-th path point. Obtain the basic movement cost, and use the terrain influence factor, elevation influence factor and basic movement cost to calculate the local movement cost of the observed enemy operator from the i-th path point to the (i+1)-th path point; Increment i by 1, and reacquire the terrain type and elevation data of the i-th path point, as well as the terrain type and elevation data of the (i+1)-th path point, until i equals n-1, to obtain multiple local movement costs, where the initial value of i is 1, and n is the total number of path points; Summing multiple local movement costs yields the movement cost of the observed enemy operator moving to any of the hexagonal grids.

[0012] In one possible design, the movement intention feature of the enemy operator to be observed relative to any hexagonal grid in the movement area includes: the observation range of the enemy operator to all capture points on the wargame map and the observation degree of our operator to the enemy operator after the enemy operator to be observed moves to the hexagonal grid, as well as the movement cost of the enemy operator to move to the hexagonal grid. Specifically, based on the movement intention characteristics of the observed enemy operator relative to each hexagonal grid in the movement region, the probability of the observed enemy operator's intention to move to each hexagonal grid is calculated, including: For any hexagonal grid, based on the observation range, observation degree and movement cost corresponding to any hexagonal grid, the movement intention evaluation value of the enemy operator to be observed relative to any hexagonal grid is calculated, and after all hexagonal grids have been polled, the movement intention evaluation value of the enemy operator to be observed relative to each hexagonal grid is obtained. Based on the wargame battlefield situation data, the movement intention control factor of the enemy operator to be observed is calculated; Based on the movement intention control factor and each movement intention evaluation value, the probability of the observed enemy operator moving to each hexagonal grid is calculated.

[0013] In one possible design, based on the movement intention control factor and each movement intention evaluation value, the probability of the observed enemy operator moving to each hexagonal grid is calculated, including: The probability of the observed enemy operator moving to each hexagonal grid is calculated using the following formula; ; In the formula, This represents the probability that the observed enemy operator intends to move to the k-th hexagonal grid. This represents the evaluation value of the observed enemy operator's intention to move relative to the k-th hexagonal grid. The movement intention control factor is represented by K, where K represents the total number of hexagonal grids in the movement area.

[0014] Secondly, a wargame target intent recognition device is provided, comprising: The operator determination unit is used to acquire wargame battlefield situation data and determine the enemy operator to be observed based on the wargame battlefield situation data. The movement area prediction unit is used to determine the movement area of ​​the enemy operator to be observed on the wargame map based on the wargame battlefield situation data. The intent feature extraction unit is used to extract the movement intent features of the enemy operator to be observed relative to each hexagonal cell in the movement area using the wargame battlefield situation data. An intent recognition unit is used to calculate the probability of the intent of the observed enemy operator to move to each hexagonal grid based on the movement intent characteristics of the enemy operator to be observed relative to each hexagonal grid in the movement area. The intent recognition unit is also used to generate the movement intent recognition result of the observed enemy operator by using the intent probability of the enemy operator moving to each hexagonal grid, and to visualize the movement intent recognition result.

[0015] Thirdly, another wargame target intent recognition device is provided. Taking the device as an electronic device as an example, it includes a memory, a processor, and a transceiver that are connected in sequence. The memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the wargame target intent recognition method as described in the first aspect or any possible design of the first aspect.

[0016] Fourthly, a storage medium is provided, on which instructions are stored, which, when executed on a computer, perform the wargame target intent recognition method as described in the first aspect or any possible design of the first aspect.

[0017] Fifthly, a computer program product containing instructions is provided, which, when executed on a computer, cause the computer to perform the wargame target intent recognition method as described in the first aspect or any possible design of the first aspect.

[0018] Beneficial effects: (1) Based on wargame battlefield situation data, this invention automatically determines the movement area of ​​the enemy operator to be observed and extracts its movement intention features relative to each hexagonal cell in the movement area. Then, based on the movement intention features, the probability of the enemy operator to be observed moving to each hexagonal cell is calculated. Finally, based on each intention probability, the movement intention recognition result of the enemy operator to be observed can be generated. In this way, this invention realizes the quantitative representation of the enemy operator's movement intention and can output fine-grained probabilistic prediction results. It not only solves the limitation of manual judgment in considering multiple complex factors in massive data, but also effectively overcomes the uncertainty and poor real-time performance caused by the subjective judgment of the commander's human experience in the traditional method. It improves the objectivity, accuracy and real-time performance of intention recognition. As a result, this invention makes it easier for the commander to quickly understand and grasp the battlefield situation, significantly improves the perception depth of the battlefield situation and decision support capability, and meets the comprehensive requirements of modern wargame simulation for real-time performance and accuracy. Therefore, it is very suitable for large-scale application and promotion. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the steps of the wargame target intent recognition method provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of the wargame target intent recognition device provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0021] It should be understood that although the terms first, second, etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, without departing from the scope of the exemplary embodiments of the invention.

[0022] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist simultaneously. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0023] Example: See Figure 1 As shown, the wargame target intent recognition method provided in this embodiment can be executed by, but is not limited to, computer devices with certain computing resources, such as servers, edge computers, personal computers (PCs, which are multi-purpose computers of a size, price and performance suitable for personal use; desktop computers, laptops to mini-laptops and tablets and ultrabooks are all personal computers), smartphones or personal digital assistants (PDAs) and other electronic devices. It is understood that the aforementioned execution entities do not constitute a limitation on the embodiments of this application. Accordingly, the operation steps of this method can be, but are not limited to, the steps S1 to S5 below.

[0024] S1. Acquire wargame battlefield situation data and determine the enemy operator to be observed based on the wargame battlefield situation data; in this embodiment, the wargame battlefield situation data at the current time step (i.e., the current moment) is acquired to predict the movement position of the enemy operator to be observed using the wargame battlefield situation data at the current time step; wherein, the wargame battlefield situation data may include, but is not limited to: the historical movement data and real-time dynamic data of the enemy operator, as well as the terrain elevation data and terrain data on the wargame map (of course, it also includes the real-time dynamic data of our operator); optionally, the historical movement data includes the coordinates of each historical movement position of the enemy operator (i.e., the position coordinates of each enemy operator before the current time step), and the real-time dynamic data includes the current position coordinates of the enemy operator; at the same time, the terrain elevation data may include, but is not limited to, the elevation data of each hexagonal grid on the wargame map, and the terrain data includes the terrain type of each hexagonal grid, such as jungle, settlement, etc.

[0025] Thus, after obtaining the wargame battlefield situation data, it is necessary to determine the enemy operator to be observed at the current time step from all enemy operators. The determination process is as follows: S11. For any enemy operator among all enemy operators, based on the real-time dynamic data of that enemy operator, determine whether that enemy operator is within the observation range of our operator. In this embodiment, for example, but not limited to, first obtaining the standard observation distance and current position coordinates of our operator; then, obtaining the current position coordinates of that enemy operator; next, based on the current position coordinates of our operator and the current position coordinates of that enemy operator, calculating the interval distance between our operator and that enemy operator; then, based on the terrain data, determining the terrain type of that enemy operator, and correcting the standard observation distance according to the terrain type to obtain the corrected distance (e.g., if the terrain type is residential or jungle, the standard observation distance is halved to obtain the corrected distance); after obtaining the corrected distance, it can be determined whether the interval distance is less than or equal to the corrected distance; if so, it is necessary to determine whether there is occlusion between the position of our operator and the position of that enemy operator (described in detail in the observation range section below); where, if there is no occlusion, it is determined that that enemy operator is within the observation range of our operator.

[0026] After determining that any enemy operator is within the observation range of our operator, the enemy operator can be marked as the initial observation target. At this time, it is also necessary to determine whether its position has changed. The process is as shown in step S12 below.

[0027] S12. If so, the historical movement data and real-time dynamic data of any enemy operator are used to determine whether the position of any enemy operator has changed within a preset time period. In specific implementation, it is to determine whether the historical movement coordinates and current position coordinates of any enemy operator have changed within the preset time period. If so, it is determined that the position of any enemy operator has changed continuously and can be regarded as an enemy operator to be observed. The process is as shown in step S13 below. Of course, if the position has not changed, it is regarded as a stationary target and can be directly attacked.

[0028] S13. If so, then any of the aforementioned enemy operators is taken as an enemy operator to be observed, and after all enemy operators have been polled, all enemy operators to be observed are obtained.

[0029] After determining the enemy operator to be observed through the aforementioned steps S11 to S13, the position prediction process can be entered, as shown in steps S2 to S5 below.

[0030] S2. Based on the wargame battlefield situation data, determine the movement area of ​​the enemy operator to be observed on the wargame map; in specific implementation, first determine the movement direction of the enemy operator to be observed (here, one enemy operator to be observed is used as an example for explanation), and then, combine its maximum maneuver distance to predict the movement area. The process can be, but is not limited to, the steps S21 to S26 below.

[0031] S21. Determine the current position coordinates of the enemy operator to be observed from the real-time dynamic data of the enemy operator.

[0032] After determining the current position coordinates of the enemy operator to be observed, its movement direction can be determined by combining its most recent movement position coordinates, as shown in steps S22 and S23 below.

[0033] S22. Based on the current position coordinates of the enemy operator to be observed, determine the most recent movement position coordinates of the enemy operator to be observed from the historical movement data of the enemy operator. The most recent movement position coordinates are the historical movement position coordinates of the enemy operator to be observed that are in the previous time step corresponding to the current position coordinate. In this embodiment, it is equivalent to determining the movement position of the enemy operator to be observed in the previous time step, and then determining the movement direction by combining it with the current position. The process is shown in step S23 below.

[0034] S23. Determine the movement direction of the enemy operator to be observed based on its current position coordinates and its most recently moved position coordinates. In this embodiment, assuming the current position coordinates are Xnow and the most recently moved position coordinates are Xprew, subtract the two coordinates (Xnow - Xprew) to obtain the displacement vector. Then, based on the displacement vector and using inverse trigonometric functions, calculate the azimuth angle. Thus, the movement direction of the enemy operator to be observed can be obtained.

[0035] After determining the direction of movement, it is also necessary to calculate the maximum maneuver distance of the enemy operator to be observed, so as to determine its corresponding movement area by combining the maximum maneuver distance; the calculation process of the maximum maneuver distance is shown in steps S24 and S25 below.

[0036] S24. Obtain the maximum maneuver speed and prediction time window of the enemy operator to be observed; in this embodiment, the maximum maneuver speed can be, but is not limited to, the average speed of the enemy operator to be observed during its historical movement; and the prediction time window is a preset value, which can be the guided firing waiting time, the system decision cycle, or the enemy reaction time, etc.; thus, after obtaining the above two parameters, the maximum maneuver distance can be calculated, and the process is shown in step S25 below.

[0037] S25. Calculate the maximum maneuver distance of the enemy operator to be observed based on the maximum maneuver speed and the prediction time window. In practice, the maximum maneuver distance can be obtained by multiplying the maximum maneuver speed by the prediction time window. Then, the movement area of ​​the enemy operator to be observed can be determined by combining the aforementioned movement direction. The process is shown in step S26 below.

[0038] S26. On the wargame map, a fan-shaped region is constructed with the current position coordinates of the enemy operator to be observed as the center, the movement direction as the center line, and the radius as the maximum maneuver distance, so as to use the fan-shaped region as the movement area; in this embodiment, it is equivalent to using the current position coordinates of the enemy operator to be observed as the center, and then using the movement direction as the center line, extending a preset angle (such as 30 degrees to 60 degrees) on both sides of the center line, and taking the maximum maneuver distance as the radius of the fan-shaped region, so as to use the constructed fan-shaped region as the movement area of ​​the enemy operator to be observed.

[0039] After determining the movement area of ​​the enemy operator to be observed through the aforementioned steps S21 to S26, the movement intention can be identified, as shown in the following steps S3 to S5.

[0040] S3. Using the wargame battlefield situation data, extract the movement intention features of the enemy operator to be observed relative to each hexagonal cell in the movement area; in specific applications, this embodiment assumes that the enemy operator to be observed moves to any hexagonal cell. Then, after moving to any hexagonal cell, construct its movement intention features relative to any hexagonal cell from three aspects: the observation range of the enemy operator to be observed on all capture points on the wargame map, the observation degree (i.e., observation extent) of our operator on the enemy operator to be observed, and its corresponding movement cost.

[0041] Optionally, the aforementioned process for extracting mobile intent features may be, but is not limited to, the steps S31 to S35 below.

[0042] S31. Based on the wargaming map, determine all control points on the wargaming map; in specific implementation, the control points are pre-set location points that have been marked on the wargaming map in advance, so they can be directly read from the wargaming map; after determining all control points, the observation range can be calculated, and the process is as shown in step S32 below.

[0043] S32. For any hexagonal grid in the movement area, based on the wargame battlefield situation data, calculate the observation range of the enemy operator to be observed over all capture points after the enemy operator moves to the hexagonal grid. In specific implementation, in order to better observe the enemy's movements and positions, it is usually chosen to move to a position with a wide field of view. Therefore, the larger the observation range of any hexagonal grid over all capture points, the easier it is for the enemy to move to its position. Thus, in this embodiment, the observation range is used as one of the indicator data of the movement intention feature.

[0044] The calculation process for the observation range is shown in steps S32a to S32i below.

[0045] S32a. Based on the terrain elevation data, determine the elevation data of each control point and the elevation data of any hexagonal grid. In this embodiment, after determining the elevation data of each control point and the elevation data (i.e., elevation value) of any hexagonal grid, an observation line can be established between them. The process is shown in step S32b below.

[0046] S32b. For any control point, establish an observation line between the hexagonal grid and the control point; in this embodiment, the connection between the center of the hexagonal grid and the center of the control point is used as the observation line; thus, after obtaining the observation line, elevation correction can be performed, as shown in steps S32c and S32d below.

[0047] S32c. Determine whether the elevation data of any hexagonal grid is greater than the elevation data of any capture point; In this embodiment, when the elevation of the observation point (i.e., the position of the enemy operator to be observed after moving to any hexagonal grid) is greater than the elevation of the target point (i.e., any capture point), an elevation gain will be given to the observation point so that it is easier to see the lower point from the higher position, which is more in line with military common sense; The elevation correction process is as shown in step S32d below.

[0048] S32d. If so, the elevation data of any hexagonal grid is corrected to obtain the corrected elevation data. In this embodiment, a height gain value is preset (which can be set according to actual use). Then, the height gain value is added to the elevation data of any hexagonal grid to obtain the corrected elevation data.

[0049] Thus, after obtaining the corrected elevation data, the hexagonal grids along the observation line can be determined, as shown in step S32e below.

[0050] S32e. From the wargame map, determine the hexagonal grid along which the observation line passes, as the target grid; after determining the hexagonal grid along which the observation line passes, occlusion judgment can be performed, the process of which is shown in the following steps S32f to S32i.

[0051] S32f. Based on the corrected elevation data and the elevation data of any control point, calculate the line-of-sight height of each target grid along the observation line. In specific implementation, for any target grid, for example, but not limited to, first calculate the first elevation difference between the corrected elevation data and the elevation data of any control point; then, sum the first elevation difference with the elevation data of any control point to obtain an elevation parameter; next, calculate the first horizontal distance between any control point and any target grid, and the second horizontal distance between any control point and any hexagonal grid; then, calculate the ratio between the first horizontal distance and the second horizontal distance; finally, the product of the ratio and the elevation parameter can be used as the line-of-sight height of any target grid.

[0052] Based on the aforementioned step S32f, after calculating the line-of-sight height of each target cell, the effective elevation data of each target cell can be determined, as shown in step S32g below.

[0053] S32g. Based on the terrain elevation data and the terrain data, the effective elevation data of each target cell is determined. In this embodiment, the original elevation value of each target cell is first determined according to the terrain elevation data. Then, the terrain type of each target cell is determined according to the terrain data. Next, if the terrain type of any target cell is a specified type, the original elevation value of that target cell is added with an elevation compensation value to obtain the effective elevation data of that target cell. Of course, if the terrain type of any target cell is not a specified type, the original elevation value is directly used as its corresponding effective elevation data. The specified types are jungle and settlement. That is, when the hexagonal cell on the observation line is jungle or settlement, its effective elevation is temporarily increased to a large value, thereby introducing the terrain occlusion factor when the enemy operator to be observed observes the target point from the observation point.

[0054] After determining the effective elevation data, it can be compared with the respective line-of-sight height to determine whether each hexagonal grid on the observation line will block the observation point's observation of the target point. The process is shown in steps S32h and S32i below.

[0055] S32h. Determine whether the line-of-sight height of each target cell is greater than the effective elevation data of each target cell.

[0056] S32i. If so, it is determined that after the enemy operator to be observed moves to any of the hexagonal grids, any capture point is exposed within the observation field of the enemy operator to be observed. The observation feature value is incremented by 1, and after all capture points have been polled, the final observation feature value is obtained. The final observation feature value is used as the observation range, wherein the initial value of the observation feature value is 0.

[0057] In this embodiment, when the line-of-sight height of each target grid is greater than its corresponding effective elevation data, it indicates that any capture point is exposed within the observation field of the enemy operator to be observed in any hexagonal grid. That is, the enemy operator to be observed can observe any capture point in any hexagonal grid (without obstruction). At this time, the observation feature value can be incremented by 1 to indicate that the enemy operator to be observed can observe a capture point in any hexagonal grid. In this way, the remaining capture points are processed in the aforementioned manner to obtain the total number of capture points observed by the enemy operator to be observed in any hexagonal grid, which is the final observation feature value. Based on this, the final observation feature value can be used as the observation range of the enemy operator to be observed over all capture points after moving to any hexagonal grid.

[0058] Of course, if the elevation data of any of the aforementioned hexagonal grids is less than or equal to the elevation data of any of the control points, then the original elevation data of both are used to determine the line-of-sight height of each target grid, and then step S32g is executed directly.

[0059] Therefore, after calculating the observation range of the enemy operator to be observed on all control points after it moves to any of the hexagonal grids through the aforementioned steps S32a to S32i, the observation degree of our operator on the enemy operator to be observed can be calculated, and the process is shown in step S33 below.

[0060] S33. Based on the wargame battlefield situation data, calculate the observation degree of our operator on the enemy operator to be observed after the enemy operator to be observed moves to any of the hexagonal squares. In this embodiment, the observation degree of our operator on the enemy operator to be observed is essentially whether the enemy operator to be observed falls within the observation range of our operator after moving to any of the hexagonal squares. The process is as follows: For any our operator, for example, but not limited to, first obtain the standard observation distance and current position coordinates of any our operator; then, obtain the position coordinates of any hexagonal square; next, based on the current position coordinates of any our operator and the position coordinates of any hexagonal square, calculate the interval distance between any our operator and any hexagonal square; then, based on the terrain data, determine the terrain type of any hexagonal square, and adjust the standard observation distance according to the terrain type. The correction is performed to obtain the correction distance (e.g., if the terrain type is residential or jungle, the standard observation distance is halved to obtain the correction distance). After obtaining the correction distance, it can be determined whether the interval distance is less than or equal to the correction distance. If so, it is necessary to determine whether there is occlusion between the position of any friendly operator and the position of any enemy operator (the process can be referred to in the aforementioned steps S32a to S32i). Otherwise, the observation degree remains unchanged, that is, the interval distance between the two is greater than the correction distance, and it cannot be observed. If there is no occlusion, it is determined that after the enemy operator to be observed moves to any hexagonal grid, it is within the observation range of any friendly operator. At this time, the observation degree is incremented by 1 (the initial value of the observation degree is 0). Based on this, after all friendly operators have been polled in the aforementioned manner, the observation degree of the friendly operator on the enemy operator to be observed can be obtained.

[0061] Based on this, the observation degree essentially represents how many of our operators can observe the enemy operator after it moves to any hexagonal grid. Therefore, the smaller the observation degree, the more concealed the position is, which means that it is an ideal concealed position for the enemy. Thus, using the observation degree as an indicator of the movement intention is a key consideration for the movement of enemy operators.

[0062] After calculating the observation degree of our operator on the enemy operator to be observed, the movement cost can be calculated, as shown in step S34 below.

[0063] S34. Based on the wargame battlefield situation data, calculate the movement cost of the enemy operator to be observed moving to any of the hexagonal squares; in this embodiment, for example, but not limited to, the following steps S34a to S34h can be used to calculate the aforementioned movement cost.

[0064] S34a. Obtain the shortest path for the observed enemy operator to move to any of the hexagonal grids; in this embodiment, traditional path planning algorithms (Dijkstra's algorithm, etc.) can be used, but are not limited to. The algorithm is used to calculate the shortest path for the enemy operator to move to any of the hexagonal grids. After obtaining the shortest path, the local cost of each path point on the shortest path can be calculated by combining the aforementioned wargame battlefield situation data. The process is shown in steps S34b to S34h below.

[0065] S34b. On the wargame map, identify all hexagonal grids that are on the shortest path, and use all the identified hexagonal grids to form a set of path points.

[0066] After determining the set of path points, the terrain type and elevation data of two adjacent path points can be determined. Based on this, the cost impact of terrain and elevation on the enemy operator being observed when moving between two adjacent path points can be determined. The process is shown in steps S34c to S34f below.

[0067] S34c. For the i-th path point and the (i+1)-th path point in the path point set, determine the terrain type and elevation data of the i-th path point, as well as the terrain type and elevation data of the (i+1)-th path point, based on the terrain elevation data and terrain data.

[0068] S34d. Based on the terrain type of the i-th path point and the terrain type of the (i+1)-th path point, determine the terrain influence factor between the i-th path point and the (i+1)-th path point for the observed enemy operator. In this embodiment, a coefficient value can be pre-assigned to each terrain type, but is not limited to, and these coefficient values ​​can be stored in a terrain coefficient lookup table. For example, the coefficient value for road-road is 0.5, the coefficient value for open land-grassland is 1, the coefficient value for jungle-jungle is 1.5, the coefficient value for jungle-residential area is 2, and so on. Thus, after determining the terrain type of the i-th path point and the terrain type of the (i+1)-th path point, the terrain influence factor between the i-th path point and the (i+1)-th path point can be obtained by looking up the terrain coefficient lookup table.

[0069] After determining the terrain influence factor, the elevation influence factor between the two can be calculated based on the elevation difference between them, as shown in step S34e below.

[0070] S34e. Calculate the second elevation difference between the elevation data of the i-th path point and the elevation data of the (i+1)-th path point, and based on the second elevation difference, determine the elevation influence factor of the enemy operator to be observed moving from the i-th path point to the (i+1)-th path point. In this embodiment, corresponding influence coefficients are also pre-set for different elevation differences (the larger the elevation difference, the greater the ascent, and the larger the influence coefficient), and stored in the elevation difference-coefficient lookup table. Therefore, after obtaining the second elevation difference, the elevation influence factor of the enemy operator to be observed moving from the i-th path point to the (i+1)-th path point can be obtained by looking up the table.

[0071] After obtaining the elevation influence factor, the local movement cost of the enemy operator to be observed moving from the i-th path point to the (i+1)-th path point can be calculated by combining the aforementioned terrain influence factor. The process is shown in step S34f below.

[0072] S34f. Obtain the basic movement cost, and use the terrain influence factor, elevation influence factor and basic movement cost to calculate the local movement cost of the enemy operator to be observed moving from the i-th path point to the (i+1)-th path point; in this embodiment, the product of the basic movement cost, the terrain influence factor and the elevation influence factor is used as the local movement cost of the enemy operator to be observed moving from the i-th path point to the (i+1)-th path point.

[0073] Thus, by processing the remaining path points in the aforementioned manner, the local movement cost of the enemy operator being observed when it moves can be obtained, as shown in step S34g below.

[0074] S34g. Increment i by 1, and reacquire the terrain type and elevation data of the i-th path point, as well as the terrain type and elevation data of the (i+1)-th path point, until i equals n-1, to obtain multiple local movement costs, where the initial value of i is 1, and n is the total number of path points.

[0075] After calculating the costs of multiple local moves, summing them together yields the total move cost to move to any hexagonal cell, as shown in step S34h below.

[0076] S34h. Summing multiple local movement costs to obtain the movement cost of the observed enemy operator moving to any hexagonal cell.

[0077] In this embodiment, the maneuver cost is the shortest path cost calculated by the path planning algorithm. Its value directly reflects the distance (i.e., the longer the path, the higher the accumulated cost), the terrain passability (by introducing a terrain influence factor, the obstacles of different terrain surfaces to movement are quantified, i.e., the cost of crossing jungle is much higher than the cost of traveling on roads), and the terrain undulation (by introducing an elevation influence factor, the impact of uphill and downhill slopes on maneuver is quantified, i.e., the cost of climbing slopes is much higher than the cost of moving on flat ground). Therefore, the smaller the maneuver cost, the more readily accessible the location is at present. The enemy is more inclined to choose an easily accessible location rather than those places that require a long detour and a long time to reach.

[0078] After calculating the aforementioned movement cost through the aforementioned steps S34a to S34h, the movement intention feature of the enemy operator to be observed relative to any hexagonal grid can be constructed by combining the aforementioned observation range and observation degree, as shown in step S35 below.

[0079] S35. Using the observation range, the observation degree, and the movement cost, construct the movement intention feature of the enemy operator to be observed relative to any hexagonal grid.

[0080] Based on the aforementioned steps S31 to S35, the movement intention features of the enemy operator to be observed relative to each hexagonal grid in the movement area can be extracted; then, based on this, the probability of the enemy operator to be observed moving to each hexagonal grid in the movement area can be calculated, as shown in step S4 below.

[0081] S4. Based on the movement intention characteristics of the enemy operator to be observed relative to each hexagonal grid in the movement area, calculate the probability of the enemy operator to be observed moving to each hexagonal grid; in this embodiment, for example, but not limited to, the following steps S41 to S43 can be used to calculate the aforementioned probability of each intention.

[0082] S41. For any hexagonal grid, based on the observation range, observation degree, and movement cost corresponding to any hexagonal grid, calculate the movement intention evaluation value of the enemy operator to be observed relative to any hexagonal grid, and after polling all hexagonal grids, obtain the movement intention evaluation value of the enemy operator to be observed relative to each hexagonal grid; in this embodiment, for example, but not limited to, the following formula can be used to calculate the movement intention evaluation value of the enemy operator to be observed relative to the k-th hexagonal grid.

[0083] ; In the formula, This represents the evaluation value of the observed enemy operator's intention to move relative to the k-th hexagonal grid. These represent the observation range, observation degree, and movement cost corresponding to the k-th hexagonal grid, respectively. These represent the observation range weight, observation degree weight, and cost weight, respectively (the sum of the three is 1, which can be preset).

[0084] After calculating the movement intention evaluation value of the enemy operator to be observed relative to each hexagonal grid based on the aforementioned formula, the movement intention control factor of the enemy operator to be observed can be calculated, as shown in step S42 below.

[0085] S42. Based on the wargame battlefield situation data, calculate the movement intention control factor of the enemy operator to be observed; in specific implementation, it is possible, but not limited to, obtaining the attribute type of the enemy operator to be observed (the type of unit represented by the enemy operator to be observed), obtaining the historical movement position coordinates and historical speed of the enemy operator to be observed during each movement from the wargame battlefield situation data, as well as obtaining the terrain type and elevation data of each hexagonal grid in the movement area; then, based on the historical movement position coordinates and historical speed of the enemy operator to be observed during each movement, calculate the movement intention factor; next, based on the terrain type and elevation data of each hexagonal grid in the movement area, calculate the terrain complexity factor; finally, based on the attribute type of the enemy operator to be observed, determine the unit type factor, and calculate the movement intention control factor based on the movement intention factor, terrain complexity factor, and unit type factor.

[0086] Optionally, the formula for calculating the motion intention factor is: ; In the formula, Indicates the motion intention factor. This represents the angle between the coordinates of the m-th and (m+1)-th historical movement positions of the observed enemy operator (calculated based on the coordinates of the m-th and (m+1)-th historical movement positions). This represents the velocity of the enemy operator being observed as it moves from the m-th historical position coordinate to the (m+1)-th historical position coordinate (the displacement is calculated based on the two position coordinates, and the time of movement between the two positions is expressed using bit shifting), where M is the total number of historical position coordinates of the enemy operator being observed. This represents the historical moving average velocity of the enemy operator to be observed.

[0087] Thus, the motion intention factor represents the degree of fluctuation in the enemy's motion direction and speed, reflecting the randomness of its behavior.

[0088] Furthermore, the calculation process for the terrain complexity factor is as follows: Based on the elevation data of each hexagonal grid, the elevation variance is calculated, and according to the terrain type of each hexagonal grid, the total number of terrain types in the movement area is counted; then, the elevation variance and the total number of terrain types are normalized (elevation variance divided by the maximum elevation equation of the entire wargame map, and the total number of terrain types divided by the total number of terrain types in the entire wargame map), and summed to obtain the terrain complexity factor; thus, this terrain complexity factor reflects the degree of drastic terrain changes within the movement area. The more complex the terrain, the more paths the enemy can choose, and the higher the uncertainty.

[0089] Furthermore, based on the attribute type of the enemy operator to be observed, its corresponding unit type factor can be determined. Among them, the uncertainty coefficients of various operators (such as infantry > tank > helicopter) can be predefined, and their uncertainty coefficients can be used as the corresponding unit type factors.

[0090] Finally, for example, but not limited to, weighted summation of motion intention factor, terrain complexity factor and unit type factor can be performed to obtain a weighted sum; then, by adding the weighted sum to the basic intention coefficient (which is a preset value), the movement intention control factor of the enemy operator to be observed can be obtained.

[0091] After calculating the movement intention control factor, the probability of the observed enemy operator moving to each hexagonal grid can be calculated by combining the various movement intention evaluation values. The process is shown in step S43 below.

[0092] S43. Based on the movement intention control factor and each movement intention evaluation value, calculate the probability of the observed enemy operator moving to each hexagonal grid.

[0093] In this embodiment, for example, but not limited to, the probability of the observed enemy operator moving to each hexagonal grid can be calculated according to the following formula.

[0094] ; In the formula, This represents the probability that the observed enemy operator intends to move to the k-th hexagonal grid. This represents the evaluation value of the observed enemy operator's intention to move relative to the k-th hexagonal grid. The movement intention control factor is represented by K, where K represents the total number of hexagonal grids in the movement area.

[0095] After calculating the probability of the enemy operator's intention to move to each hexagonal grid through the aforementioned steps S41 to S43, the movement intention recognition result of the enemy operator can be generated based on this, as shown in step S5 below.

[0096] S5. Using the probability of the enemy operator's intention to move to each hexagonal grid, generate the movement intention recognition result of the enemy operator and visualize the movement intention recognition result. In this embodiment, for example, but not limited to, the hexagonal grid with the highest intention probability can be used as the predicted movement position of the enemy operator and the predicted movement position can be used as the movement intention recognition result. Then, visualize it to assist the commander in making confrontation decisions.

[0097] Therefore, through the wargame target intent recognition method described in detail in steps S1 to S5 above, this invention automatically determines the movement area of ​​the enemy operator to be observed based on wargame battlefield situation data, and extracts its movement intent features relative to each hexagonal cell in the movement area. Then, based on these movement intent features, it calculates the probability of the enemy operator's intention to move to each hexagonal cell. Finally, based on each intent probability, it generates the movement intent recognition result of the enemy operator. In this way, this invention achieves a quantitative representation of the enemy operator's movement intent and can output fine-grained probabilistic prediction results. It not only solves the limitation of manual judgment in comprehensively considering multi-dimensional complex factors in massive data, but also effectively overcomes the uncertainty and poor real-time performance caused by the subjective judgment of commanders relying entirely on human experience in traditional methods. It improves the objectivity, accuracy, and real-time performance of intent recognition. Therefore, this invention facilitates commanders to quickly understand and grasp the battlefield situation, significantly improves the depth of perception of the battlefield situation and decision support capabilities, and meets the comprehensive requirements of modern wargame simulation for real-time performance and accuracy. Therefore, it is very suitable for large-scale application and promotion.

[0098] like Figure 2 As shown, the second aspect of this embodiment provides a hardware device for implementing the wargame target intent recognition method described in the first aspect of the embodiment, comprising: The operator determination unit is used to acquire wargame battlefield situation data and determine the enemy operator to be observed based on the wargame battlefield situation data.

[0099] The movement area prediction unit is used to determine the movement area of ​​the enemy operator to be observed on the wargame map based on the wargame battlefield situation data.

[0100] The intent feature extraction unit is used to extract the movement intent features of the enemy operator to be observed relative to each hexagonal cell in the movement area using the wargame battlefield situation data.

[0101] The intent recognition unit is used to calculate the probability of the intent of the enemy operator to move to each hexagonal grid based on the movement intent characteristics of the enemy operator to be observed relative to each hexagonal grid in the movement area.

[0102] The intent recognition unit is also used to generate the movement intent recognition result of the observed enemy operator by using the intent probability of the enemy operator moving to each hexagonal grid, and to visualize the movement intent recognition result.

[0103] The working process, working details and technical effects of the system provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0104] like Figure 3 As shown, the third aspect of this embodiment provides another wargame target intent recognition device. Taking the device as an electronic device as an example, it includes: a memory, a processor, and a transceiver that are connected in sequence. The memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the wargame target intent recognition method as described in the first aspect of the embodiment.

[0105] For specific examples, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory, etc.; specifically, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor, also known as the CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state.

[0106] In some embodiments, the processor may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. For example, the processor may not be limited to microprocessors of the STM32F105 series, reduced instruction set computer (RISC) microprocessors, x86 architecture processors, or processors with integrated neural network processing units (NPUs). The transceiver may be, but is not limited to, a Wi-Fi transceiver, a Bluetooth transceiver, a General Packet Radio Service (GPRS) transceiver, a ZigBee (a low-power LAN protocol based on the IEEE 802.15.4 standard) transceiver, a 3G transceiver, a 4G transceiver, and / or a 5G transceiver. Furthermore, the device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0107] The working process, working details and technical effects of the electronic device provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0108] The fourth aspect of this embodiment provides a storage medium that stores instructions containing the wargame target intent recognition method described in the first aspect of the embodiment. That is, the storage medium stores instructions that, when executed on a computer, perform the wargame target intent recognition method as described in the first aspect of the embodiment.

[0109] The storage medium refers to a carrier for storing data, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or memory sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0110] The working process, working details, and technical effects of the storage medium provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0111] The fifth aspect of this embodiment provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the wargame target intent recognition method as described in the first aspect of the embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0112] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for recognizing the intent of a wargame target, characterized in that, include: Acquire wargame battlefield situation data, and based on the wargame battlefield situation data, determine the enemy operator to be observed; Based on the wargame battlefield situation data, the movement area of ​​the enemy operator to be observed on the wargame map is determined; Using the wargame battlefield situation data, the movement intention features of the enemy operator to be observed relative to each hexagonal cell in the movement area are extracted; Based on the movement intention characteristics of the enemy operator to be observed relative to each hexagonal grid in the movement area, the probability of the enemy operator's intention to move to each hexagonal grid is calculated. Using the probability of the enemy operator's intention to move to each hexagonal grid, the movement intention recognition result of the enemy operator is generated, and the movement intention recognition result is visualized.

2. The method according to claim 1, characterized in that, The wargame battlefield situation data includes: historical movement data and real-time dynamic data of the enemy operator, wherein the historical movement data includes the coordinates of each historical movement position of the enemy operator, and the real-time dynamic data includes the current position coordinates of the enemy operator. Among them, based on the wargame battlefield situation data, the movement area of ​​the enemy operator to be observed on the wargame map is determined, including: The current position coordinates of the enemy operator to be observed are determined from the real-time dynamic data of the enemy operator; Based on the current position coordinates of the enemy operator to be observed, the most recent movement position coordinates of the enemy operator to be observed are determined from the historical movement data of the enemy operator. The most recent movement position coordinates are the historical movement position coordinates of the enemy operator to be observed that are in the previous time step of the time step corresponding to the current position coordinate. The movement direction of the enemy operator to be observed is determined based on its current position coordinates and its most recently moved position coordinates. Obtain the maximum maneuver speed and prediction time window of the enemy operator to be observed; The maximum maneuver distance of the enemy operator to be observed is calculated based on the maximum maneuver speed and the prediction time window. On the wargame map, a fan-shaped region is constructed with the current position coordinates of the enemy operator to be observed as the center, the movement direction as the center line, and the radius as the maximum maneuver distance, so as to use the fan-shaped region as the movement area.

3. The method according to claim 1, characterized in that, Using the wargame battlefield situation data, the movement intention features of the enemy operator to be observed relative to each hexagonal cell in the movement area are extracted, including: Based on the wargame map, all capture points on the wargame map are determined; For any hexagonal grid in the moving area, based on the wargame battlefield situation data, the observation range of the enemy operator to be observed for all capture points is calculated after the enemy operator to be observed moves to any hexagonal grid. Based on the wargame battlefield situation data, the observation degree of our operator on the enemy operator to be observed after the enemy operator to be observed moves to any of the hexagonal squares is calculated; Based on the wargame battlefield situation data, the movement cost of the enemy operator to be observed moving to any of the hexagonal squares is calculated; Using the observation range, the observation degree, and the movement cost, the movement intention feature of the enemy operator to be observed relative to any hexagonal grid is constructed.

4. The method according to claim 3, characterized in that, The wargame battlefield situation data includes: terrain elevation data and terrain data on the wargame map; Specifically, based on wargame battlefield situation data, the observation range of the enemy operator to be observed over all capture points is calculated after the enemy operator moves to any of the hexagonal squares, including: Based on the terrain elevation data, the elevation data of each control point and the elevation data of any hexagonal grid are determined; For any point of control, establish an observation line between any hexagonal grid and any point of control; Determine whether the elevation data of any hexagonal grid is greater than the elevation data of any control point; If so, then correct the elevation data of any hexagonal grid to obtain the corrected elevation data; From the wargame map, determine the hexagonal grid that the observation line passes through, and use it as the target grid; Based on the corrected elevation data and the elevation data of any control point, the line-of-sight height of each target grid along the observation line is calculated. Based on the terrain elevation data and the terrain data, the effective elevation data of each target cell is determined; Determine whether the line-of-sight height of each target cell is greater than the effective elevation data of each target cell; If so, it is determined that after the enemy operator to be observed moves to any of the hexagonal grids, any capture point is exposed within the observation field of the enemy operator to be observed. The observation feature value is incremented by 1, and after all capture points have been polled, the final observation feature value is obtained. The final observation feature value is used as the observation range, wherein the initial value of the observation feature value is 0.

5. The method according to claim 4, characterized in that, Based on the corrected elevation data and the elevation data of any control point, the line-of-sight height of each target grid traversed by the observation line is calculated, including: For any target grid, calculate the first elevation difference between the corrected elevation data and the elevation data of any control point, and sum the first elevation difference and the elevation data of any control point to obtain the elevation parameter; Calculate the first horizontal distance between any control point and any target grid, and the second horizontal distance between any control point and any hexagonal grid; The ratio between the first horizontal distance and the second horizontal distance is calculated, and the product of the ratio and the elevation parameter is used as the line-of-sight height of any target grid.

6. The method according to claim 3, characterized in that, The wargame battlefield situation data includes: terrain elevation data and terrain data on the wargame map. Based on the wargame battlefield situation data, the movement cost of moving the observed enemy operator to any of the hexagonal squares is calculated, including: Obtain the shortest path for the observed enemy operator to move to any of the hexagonal grids; On the wargame map, all hexagonal grids on the shortest path are identified, and a set of path points is formed using all the identified hexagonal grids. For the i-th path point and the (i+1)-th path point in the path point set, the terrain type and elevation data of the i-th path point, as well as the terrain type and elevation data of the (i+1)-th path point, are determined based on the terrain elevation data and terrain data. Based on the terrain type of the i-th path point and the terrain type of the (i+1)-th path point, determine the terrain influence factor between the i-th path point and the (i+1)-th path point for the enemy operator to be observed. Calculate the second elevation difference between the elevation data of the i-th path point and the elevation data of the (i+1)-th path point, and based on the second elevation difference, determine the elevation influence factor between the movement of the observed enemy operator from the i-th path point to the (i+1)-th path point. Obtain the basic movement cost, and use the terrain influence factor, elevation influence factor and basic movement cost to calculate the local movement cost of the observed enemy operator from the i-th path point to the (i+1)-th path point; Increment i by 1, and reacquire the terrain type and elevation data of the i-th path point, as well as the terrain type and elevation data of the (i+1)-th path point, until i equals n-1, to obtain multiple local movement costs, where the initial value of i is 1, and n is the total number of path points; Summing multiple local movement costs yields the movement cost of the observed enemy operator moving to any of the hexagonal grids.

7. The method according to claim 1, characterized in that, The movement intention characteristics of the enemy operator to be observed relative to any hexagonal grid in the movement area include: the observation range of the enemy operator to be observed on all capture points on the wargame map after the enemy operator to be observed moves to the hexagonal grid, the observation degree of our operator on the enemy operator to be observed, and the movement cost of the enemy operator to be observed moving to the hexagonal grid. Specifically, based on the movement intention characteristics of the observed enemy operator relative to each hexagonal grid in the movement region, the probability of the observed enemy operator's intention to move to each hexagonal grid is calculated, including: For any hexagonal grid, based on the observation range, observation degree and movement cost corresponding to any hexagonal grid, the movement intention evaluation value of the enemy operator to be observed relative to any hexagonal grid is calculated, and after all hexagonal grids have been polled, the movement intention evaluation value of the enemy operator to be observed relative to each hexagonal grid is obtained. Based on the wargame battlefield situation data, the movement intention control factor of the enemy operator to be observed is calculated; Based on the movement intention control factor and each movement intention evaluation value, the probability of the observed enemy operator moving to each hexagonal grid is calculated.

8. The method according to claim 7, characterized in that, Based on the movement intention control factor and each movement intention evaluation value, the probability of the observed enemy operator moving to each hexagonal grid is calculated, including: The probability of the observed enemy operator moving to each hexagonal grid is calculated using the following formula; ； In the formula, This represents the probability that the observed enemy operator intends to move to the k-th hexagonal grid. This represents the evaluation value of the observed enemy operator's intention to move relative to the k-th hexagonal grid. The movement intention control factor is represented by K, where K represents the total number of hexagonal grids in the movement area.

9. A wargame target intent recognition device, characterized in that, include: The operator determination unit is used to acquire wargame battlefield situation data and determine the enemy operator to be observed based on the wargame battlefield situation data. The movement area prediction unit is used to determine the movement area of ​​the enemy operator to be observed on the wargame map based on the wargame battlefield situation data. The intent feature extraction unit is used to extract the movement intent features of the enemy operator to be observed relative to each hexagonal cell in the movement area using the wargame battlefield situation data. An intent recognition unit is used to calculate the probability of the intent of the observed enemy operator to move to each hexagonal grid based on the movement intent characteristics of the enemy operator to be observed relative to each hexagonal grid in the movement area. The intent recognition unit is also used to generate the movement intent recognition result of the observed enemy operator by using the intent probability of the enemy operator moving to each hexagonal grid, and to visualize the movement intent recognition result.

10. A computer program product containing instructions, characterized in that, When the instructions are executed on the computer, the computer performs the wargaming target intent recognition method as described in any one of claims 1 to 8.

Images