Multi-user collaborative motion sensing game control method and system based on intelligent equipment

Abstract

The invention relates to the technical field of intelligent interaction, and discloses a multi-user collaborative motion sensing game control method and system based on intelligent equipment, and the method comprises the steps: collecting a real-time physical environment of a target game player to simulate a motion sensing game region of the target game player; querying the number of the target game players to construct a single stereoscopic game area, performing somatosensory simulation on the target game players, collecting somatosensory data, analyzing the somatosensory ability of the target game players by using the somatosensory data, and performing game area optimization on the single stereoscopic game area to obtain an optimized game area; the task completion rate of the target game player is calculated, the game execution ability of the target game player is analyzed, a preliminary cooperation strategy of the target game player is constructed, and the action cooperation angle and the interaction complexity of the target game player are analyzed; and constructing a final cooperative control strategy of the target game player to perform cooperative control on the target game player. According to the invention, the control coordination of the multi-user collaborative motion sensing game can be improved.

Description

Technical Field

[0001] The present invention relates to a control method and system for multi - player collaborative somatosensory games based on intelligent devices, belonging to the field of intelligent interaction technology. Background Art

[0002] Multi - player collaborative somatosensory games are a new type of game that combines intelligent device technology and somatosensory interaction technology, aiming to provide multiple players with a brand - new, highly interactive and collaborative gaming experience. Different from the traditional way of using devices such as gamepads, keyboards and mice for game operations, multi - player collaborative somatosensory games mainly collect the somatosensory data of players through devices such as cameras and somatosensory sensors, and convert the players' limb movements into operation instructions in the game in real time, enabling players to control the game in a more natural and intuitive way. They are widely used in offline game venues and some online entertainment platforms.

[0003] Currently, for the control of multi - player collaborative somatosensory games, the action data of players is mostly collected through devices such as cameras and somatosensory sensors, and then transmitted to the game host or terminal device through wireless communication technologies such as Bluetooth and Wi - Fi. The data is analyzed and processed by means of fixed game algorithms, and then the actions of game characters are controlled. Such a method generally has a pre - defined action pattern, and the action instructions are output by matching the character actions with the actions in the database. However, in actual operation, due to the uncontrollability of players and the complexity of the game scenario, situations of player action conflicts or collisions often occur, resulting in low control coordination for multiple players. Summary of the Invention

[0004] The present invention provides a control method and system for multi - player collaborative somatosensory games based on intelligent devices, and its main purpose is to improve the control coordination of multi - player collaborative somatosensory games.

[0005] To achieve the above - mentioned purpose, the control method for multi - player collaborative somatosensory games based on intelligent devices provided by the present invention includes:

[0006] Deploy intelligent devices in the multi - player collaborative somatosensory game area, and establish a communication connection between the intelligent devices and the multi - player collaborative somatosensory game area, so as to use the intelligent devices to collect the real - time physical environment of the target game player, perform 3D modeling on the real - time physical environment to simulate the somatosensory game area of the target game player;

[0007] Query the number of the target game players to construct corresponding independent somatosensory game areas in the somatosensory game area, conduct somatosensory simulation on the target game players in the independent somatosensory game areas to collect the somatosensory data of the target game players, analyze the somatosensory ability of the target game players by using the somatosensory data, and optimize the game areas of the independent somatosensory game areas by using the somatosensory data to obtain optimized game areas;

[0008] Calculate the task completion rate of the target game players by using the somatosensory data, analyze the game execution ability of the target game players according to the task completion rate, construct a preliminary cooperation strategy for the target game players based on the somatosensory ability and the game execution ability, conduct preliminary cooperation control on the target game players by using the preliminary cooperation strategy to obtain cooperation control data, and analyze the action cooperation angle and interaction complexity of the target game players by using the cooperation control data;

[0009] Construct a final cooperation control strategy for the target game players based on the action cooperation angle, the interaction complexity and the optimized game areas to conduct cooperation control on the target game players.

[0010] Optionally, the 3D modeling of the real physical environment to simulate the somatosensory game area of the target game players includes:

[0011] Collect the point cloud data of the real physical environment;

[0012] Conduct 3D modeling on the real physical environment by using the point cloud data to obtain a game visual environment;

[0013] Conduct virtual-physical space alignment processing on the game visual environment to obtain a virtual mapping area;

[0014] Conduct edge detection on the virtual mapping area to divide a safety boundary for the virtual environment to obtain a somatosensory game area.

[0015] Optionally, the conducting somatosensory simulation on the target game players in the independent somatosensory game areas to collect the somatosensory data of the target game players includes:

[0016] Conduct game guidance on the target game players by using a pre-configured game library to capture the game actions of the target game players and collect the mechanical data of the target game players;

[0017] Conduct action modeling on the game actions to obtain a simulated game model;

[0018] Conduct timestamp alignment processing on the mechanical data and the simulated game model to obtain aligned data;

[0019] Perform data fusion on the alignment data to obtain somatosensory data.

[0020] Optionally, analyzing the somatosensory ability of the target game player by using the somatosensory data includes:

[0021] Calculate the movement speed and reaction speed of the target game player by using the somatosensory data;

[0022] Construct the movement trajectory of the target game player by using the somatosensory data;

[0023] Analyze the movement accuracy of the target game player based on the movement trajectory;

[0024] Analyze the movement coordination of the target game player by using the somatosensory data;

[0025] Perform comprehensive motion analysis on the target game player based on the movement speed, the reaction speed, the movement accuracy, and the movement coordination to evaluate the somatosensory ability of the target game player.

[0026] Optionally, analyzing the movement coordination of the target game player by using the somatosensory data includes:

[0027] Extract the movement data from the somatosensory data, perform time series processing on the movement data to obtain time series movements, and calculate the movement coordination coefficient of the time series movements by using the following formula:

[0028]

[0029] where ρ(X,Y) represents the movement coordination coefficient, X represents the Xth time series movement in the time series movements, Y represents the Yth time series movement in the time series movements, x i represents the ith data point in X, y i represents the ith data point in Y, represents the average value of X, represents the average value of Y, and n represents the data length of the time series movements;

[0030] Evaluate the movement synchronization of the target game player based on the movement coordination coefficient;

[0031] Identify the movement coordination of the target game player based on the movement synchronization.

[0032] Optionally, performing comprehensive motion analysis on the target game player based on the movement speed, the reaction speed, the movement accuracy, and the movement coordination to evaluate the somatosensory ability of the target game player includes:

[0033] Query the simulation game types played by the target game player;

[0034] Based on the simulation game types, assign weights to the action speed, reaction speed, action accuracy, and action coordination to obtain an action speed weight, a reaction speed weight, an action accuracy weight, and an action coordination weight;

[0035] Based on the action speed weight, the reaction speed weight, the action accuracy weight, and the action coordination weight, use the following formula to calculate the somatosensory ability value of the target game player:

[0036] S = w V ×V + w R ×R + w A ×A + w C ×C

[0037] Where S represents the somatosensory ability value, w V represents the action speed weight, V represents the action speed, w R represents the reaction speed weight, R represents the reaction speed, w A represents the action accuracy weight, A represents the action accuracy, w C represents the action coordination weight, and C represents the action coordination;

[0038] Based on the somatosensory ability value, evaluate the somatosensory ability of the target game player.

[0039] Optionally, using the somatosensory data to optimize the game area of the independent somatosensory game area to obtain an optimized game area includes:

[0040] Perform a sliding window process on the somatosensory data to obtain denoised time series data;

[0041] Use the denoised time series data to identify the action peaks of the target game player;

[0042] Use the action peaks to construct an ability profile of the target game player;

[0043] Based on the ability profile, analyze the actionable movement paths of the target game player;

[0044] Based on the actionable movement paths, optimize the game area of the independent somatosensory game area to obtain an optimized game area.

[0045] Optionally, constructing the preliminary cooperation strategy of the target game player based on the somatosensory ability and the game execution ability includes:

[0046] Quantify the somatosensory ability and the game execution ability to obtain a quantified ability;

[0047] Query the pre-output game mode to perform dynamic weight allocation on the quantified ability to obtain a dynamically weighted ability;

[0048] Based on the dynamically weighted ability, perform dynamic game character matching on the target game player to obtain a dynamically matched player;

[0049] Configure the action logic for the dynamically matched player to obtain a preliminary cooperation strategy for the target game player.

[0050] Optionally, constructing the preliminary cooperation strategy for the target game player based on the somatosensory ability and the game execution ability includes:

[0051] Quantify the somatosensory ability and the game execution ability to obtain a quantified ability;

[0052] Query the pre-output game mode to perform dynamic weight allocation on the quantified ability to obtain a dynamically weighted ability;

[0053] Based on the dynamically weighted ability, perform dynamic game character matching on the target game player to obtain a dynamically matched player;

[0054] Configure the action logic for the dynamically matched player to obtain a preliminary cooperation strategy for the target game player.

[0055] To solve the above problems, the present invention also provides a multi-player cooperative somatosensory game control system based on an intelligent device, and the system includes:

[0056] A game area simulation module, configured to deploy intelligent devices in a multi-player cooperative somatosensory game area, establish a communication connection between the intelligent devices and the multi-player cooperative somatosensory game area, collect the real-time physical environment of the target game player by using the intelligent devices, perform 3D modeling on the real-time physical environment to simulate the somatosensory game area of the target game player;

[0057] A game area optimization module, configured to query the number of target game players, construct corresponding independent somatosensory game areas in the somatosensory game area, perform somatosensory simulation on the target game players in the independent somatosensory game areas to collect the somatosensory data of the target game players, analyze the somatosensory ability of the target game players by using the somatosensory data, and optimize the game area by using the somatosensory data to obtain an optimized game area;

[0058] A user somatosensory analysis module, which is used to calculate the task completion rate of the target game player by using the somatosensory data, analyze the game execution ability of the target game player according to the task completion rate, construct a preliminary cooperation strategy for the target game player based on the somatosensory ability and the game execution ability, perform preliminary cooperation control on the target game player by using the preliminary cooperation strategy to obtain cooperation control data, and analyze the action cooperation angle and interaction complexity of the target game player by using the cooperation control data;

[0059] A game cooperation control module, which is used to construct a final cooperation control strategy for the target game player based on the action cooperation angle, the interaction complexity and the optimized game area, so as to perform cooperation control on the target game player.

[0060] Compared with the problems described in the background art, in the embodiments of the present invention, first, intelligent devices are deployed in a multi-player cooperative somatosensory game area and communication connections are established to collect real-time physical environments for 3D modeling, which can ensure effective data collection, and then provide a real environment basis for game simulation and control. Then, independent game areas are divided for each player, and the simulated game data of the players are collected to analyze the somatosensory data of different players, and further, the somatosensory ability of the somatosensory game players is analyzed according to the somatosensory data to optimize the game areas of the game players; further, the present invention measures the game performance of the game players by analyzing the task completion rate and game execution ability of the game players, and then understands the advantages and disadvantages of the game players in the somatosensory game, and then formulates a cooperation strategy, and then analyzes the action cooperation angle and interaction complexity of the somatosensory game players by using the cooperation control strategy, so as to understand the difficulty of the target game player system; furthermore, the present invention constructs a final cooperation control strategy based on the action cooperation angle, the interaction complexity and the optimized game area to perform cooperation control on the players, so that the game players can better participate in the somatosensory game, thereby improving the control coordination of the multi-player cooperative somatosensory game. Brief Description of the Drawings

[0061] Figure 1 It is a schematic flow chart of a multi-player cooperative somatosensory game control method based on intelligent devices provided by an embodiment of the present invention;

[0062] Figure 2 It is a schematic module diagram for implementing the multi-player cooperative somatosensory game control method based on intelligent devices provided by an embodiment of the present invention.

[0063] The implementation, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0064] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0065] Embodiments of the present application provide a multi - person collaborative somatosensory game control method based on intelligent devices. The execution subject of the multi - person collaborative somatosensory game control method based on intelligent devices includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiments of the present application. In other words, the multi - person collaborative somatosensory game control method can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc.

[0066] Embodiment 1:

[0067] Refer to Figure 1 As shown, it is a flowchart of a multi - person collaborative somatosensory game control method based on intelligent devices provided by an embodiment of the present invention. In this embodiment, the multi - person collaborative somatosensory game control method includes:

[0068] S1. Deploy intelligent devices in the multi - person collaborative somatosensory game area, and establish a communication connection between the intelligent devices and the multi - person collaborative somatosensory game area, so as to use the intelligent devices to collect the real - time physical environment of the target game player, perform 3D modeling on the real - time physical environment, and simulate the somatosensory game area of the target game player.

[0069] In the embodiments of the present invention, by deploying intelligent devices in the multi - person collaborative somatosensory game area, intelligent devices can be reasonably placed in the game area, serving as the hardware basis for subsequent data collection and interaction, ensuring that the entire game area can be covered, realizing the effective collection of data such as players' actions and environmental information, and establishing a communication connection between the intelligent devices and the multi - person collaborative somatosensory game area. By using the intelligent devices to collect the real - time physical environment of the target game player, while ensuring that the data collected by the intelligent devices can be smoothly transmitted to the subsequent processing unit, through various sensors (such as cameras, environmental sensors, etc.) installed on the intelligent devices, environmental information in the game area, such as spatial layout, light conditions, and object distribution, can be collected, providing a real environmental basis for subsequent game simulation and control.

[0070] Among them, the multi - person collaborative somatosensory game area refers to a specific spatial range within which multiple players can jointly participate in somatosensory games, such as an indoor game venue or a specific outdoor activity area, etc. The intelligent devices refer to various devices installed and deployed in the multi - person collaborative somatosensory game area for data collection and interaction, such as cameras (used to capture visual information such as players' actions and postures), accelerometers (detecting the acceleration changes of players' actions), and gyroscopes (measuring the rotation angles of players' bodies, etc.). The real - time physical environment refers to the real environment where the game player is located.

[0071] Furthermore, in the embodiment of the present invention, by performing 3D modeling on the real physical environment to simulate the somatosensory game area of the target gamer, the real environment of the player can be simulated, so that the size of the simulation area and the movable range of the player can be determined during game simulation.

[0072] The somatosensory game area refers to the game area corresponding to the multi-player collaborative somatosensory game area where the player is located in reality.

[0073] As an embodiment of the present invention, the performing 3D modeling on the real physical environment to simulate the somatosensory game area of the target gamer includes:

[0074] Collecting point cloud data of the real physical environment;

[0075] Performing 3D modeling on the real physical environment by using the point cloud data to obtain a game visual environment;

[0076] Performing virtual-physical space alignment processing on the game visual environment to obtain a virtual mapping area;

[0077] Performing edge detection on the virtual mapping area to divide a safety boundary for the virtual environment and obtain a somatosensory game area.

[0078] The point cloud data refers to a set of a series of three-dimensional coordinate points collected by sensors such as depth cameras or lidars in intelligent devices. The game visual environment refers to a three-dimensional virtual environment obtained after processing and modeling using point cloud data. The virtual mapping area refers to the area obtained after aligning the game visual environment with the virtual space.

[0079] Optionally, the point cloud data can be obtained by using sensors such as depth cameras or lidars to emit detection signals to the game area and receive reflected signals. The game visual environment can be obtained by performing three-dimensional modeling on the real physical environment through three-dimensional modeling technology. The virtual mapping area can be formed by setting a virtual space coordinate system in the game system, marking characteristic reference points in the physical space, establishing the correspondence between the virtual space and the physical space through visual recognition technology, and then accurately mapping the game visual environment to the virtual space. The somatosensory game area can be obtained by using the Canny algorithm to identify the boundary contours of objects in the virtual mapping area and dividing a safe area where players can move and interact in the virtual environment.

[0080] S2. Query the number of the target game players, and construct corresponding independent somatosensory game areas in the somatosensory game area. Conduct somatosensory simulation on the target game players in the independent somatosensory game areas to collect the somatosensory data of the target game players. Use the somatosensory data to analyze the somatosensory ability of the target game players, and use the somatosensory data to optimize the game areas of the independent somatosensory game areas to obtain optimized game areas.

[0081] In the embodiment of the present invention, by querying the number of the target game players and constructing corresponding independent somatosensory game areas in the somatosensory game area, each player can have his own exclusive space for somatosensory games, which helps to improve the participation and concentration of players. At the same time, it is also convenient for the system to accurately capture and analyze the actions of each player.

[0082] Optionally, the independent somatosensory game areas can be set according to the specific game players and the size of the target area. For example, if the number of target players is five, five game areas can be set. If the size of the somatosensory game area is 20 square meters, it can be divided into five areas of four square meters. Of course, in actual applications, it needs to be divided according to the specific situation, such as considering the obstacles on the site, etc. In short, it is necessary to ensure that each game player has a safe activity range.

[0083] Furthermore, in the embodiment of the present invention, by conducting somatosensory simulation on the target game players in the independent somatosensory game areas to collect the somatosensory data of the target game players, various data during the somatosensory simulation process of the players can be collected, including information such as the amplitude, speed, and frequency of actions, etc., which is convenient for understanding the behavior patterns and characteristics of each player.

[0084] Among them, the somatosensory data refers to a data set obtained by fusing mechanical data and a simulated game model after a series of processes.

[0085] As an embodiment of the present invention, conducting somatosensory simulation on the target game players in the independent somatosensory game areas to collect the somatosensory data of the target game players includes:

[0086] Using a pre-configured game library to guide the target game players to play games to capture the game actions of the target game players and collect the mechanical data of the target game players;

[0087] Conduct action modeling on the game actions to obtain a simulated game model;

[0088] Perform timestamp alignment processing on the mechanical data and the simulated game model to obtain aligned data;

[0089] Fuse the aligned data to obtain somatosensory data.

[0090] Among them, the pre-configured game library refers to a collection that is pre-set and prepared, containing various game programs and related resources. The game actions refer to various specific action performances made by the body of the target game player in the process of participating in a somatosensory game in order to complete the game tasks, such as jogging, leg swinging, and waving. The mechanical data refers to data such as acceleration, speed, force, and torque generated by the movement of various parts of the player's body. The simulated game model refers to a digital model established based on the analysis and modeling of the player's game actions.

[0091] Optionally, the game actions can be displayed to the target game player in an independent somatosensory game area through means such as screen display and voice prompts to show the game rules and action demonstrations. Then, devices such as depth cameras and motion capture sensors installed in the area are used to capture the actions made by the player in real time. The mechanical data can be obtained by using devices such as pressure sensors and accelerometers to collect the mechanical data of the player during the game, such as foot pressure and hand movement acceleration. The simulated game model can be constructed by using bone animation technology to abstract the player's body into a bone structure and then combining the collected player actions. The alignment data can add timestamp information to each data point in the mechanical data and the simulated game model. By comparing the timestamps of the two, the data at the corresponding time points are found, and the mechanical data is matched and aligned with the action data in the simulated game model. The somatosensory data can be obtained by using multi-sensor data fusion technology to integrate the mechanical data and the simulated game model data that have been timestamp-aligned.

[0092] In an embodiment of the present invention, by using the somatosensory data to analyze the somatosensory ability of the target game player, it is convenient for the game system to adjust the game difficulty, task settings, etc. according to the actual ability of the player, realizing personalized customization of the game.

[0093] As an embodiment of the present invention, using the somatosensory data to analyze the somatosensory ability of the target game player includes:

[0094] Using the somatosensory data to calculate the action speed and reaction speed of the target game player;

[0095] Using the somatosensory data to construct the action trajectory of the target game player;

[0096] Based on the action trajectory, analyzing the action accuracy of the target game player;

[0097] Using the somatosensory data to analyze the action coordination of the target game player;

[0098] Based on the action speed, reaction speed, action accuracy, and action coordination, perform a comprehensive motion analysis on the target game player to evaluate the somatosensory ability of the target game player.

[0099] Among them, the action speed refers to the speed at which various parts of the body of the target game player complete actions when playing a somatosensory game. The reaction speed refers to the time interval between the appearance of stimulus information in the game and the target game player making a corresponding action. For example, in a somatosensory shooting game, when an enemy appears, the shorter the time it takes for the player to see the enemy and press the shooting button or make a corresponding shooting action, the faster the reaction speed. The action accuracy refers to the degree of conformity between the actual actions made by the target game player in the somatosensory game and the standard actions set in the game. The action coordination refers to the ability of various parts of the body of the target game player to cooperate and move synergistically when playing a somatosensory game.

[0100] Optionally, the action speed can be obtained by extracting the timestamp information and spatial displacement data of the player's actions from the somatosensory data and calculating the displacement distance of the body part per unit time. The reaction speed can be obtained by recording the time points when the stimulus appears in the game and the time points when the player makes corresponding actions, and then calculating the difference between the two. The action trajectory can be obtained by connecting the three-dimensional coordinate information of each body joint point in the somatosensory data at different times in chronological order. The action accuracy can be evaluated by using the dynamic time warping algorithm to compare the actual action trajectory of the player with the standard action trajectory set in the game and calculating the overlap or deviation value between the two.

[0101] Exemplarily, the analysis of the action coordination of the target game player using the somatosensory data includes:

[0102] Extract the action data from the somatosensory data, perform time series processing on the action data to obtain time series actions, and calculate the action coordination coefficient of the time series actions using the following formula:

[0103]

[0104] Among them, ρ(X,Y) represents the action coordination coefficient, X represents the Xth time series action in the time series actions, Y represents the Yth time series action in the time series actions, x i represents the ith data point in X, y i represents the ith data point in Y, represents the average value of X, represents the average value of Y, and n represents the data length of the time series actions;

[0105] Evaluate the action synchronization of the target game player based on the action coordination coefficient;

[0106] Identify the action coordination of the target game player based on the action synchronization.

[0107] Wherein, the action coordination coefficient is an index used to evaluate the action coordination degree of different somatosensory game players when playing somatosensory games.

[0108] It should be further noted that in the formula for calculating the action coordination coefficient, X and Y represent two different time series data. For example, X can be a data series of the angle of the player's arm joint changing with time, and Y can be a data series of the angle of the player's leg joint changing with time. And x i and y i are respectively the data values at the i-th time point in X and Y. For example, x i is the angle value of the arm joint at the i-th moment, and y i is the angle value of the leg joint at the i-th moment. n represents the data length of the time series action, that is, the number of data points, and it is required that the data lengths of the two time series are the same. For example, if the angle data of the arm and leg joints at 100 time points are collected, then n = 100. Therefore, in a multi-player cooperative somatosensory game, by calculating the action coordination coefficient of the time series of the arm and leg action data, it is possible to determine whether the actions of these two parts are synchronized. If the coefficient is close to 1, it indicates that the arm and leg actions are highly positively correlated in time, that is, the action synchronization is good; if it is close to -1, it is highly negatively correlated; if it is close to 0, it means that the two actions lack synchronization. Therefore, the action synchronization of the target game player can be evaluated according to the action coordination coefficient, and then the action coordination of the game player can be distinguished. For example, when playing a dance somatosensory game, analyze the time series data of the arm swing action and the leg step action, and observe whether they cooperate with each other rhythmically, and then analyze the action coordination of different game players in this game or evaluate the limb coordination of the player.

[0109] Further, as another optional embodiment of the present invention, the comprehensive motion analysis of the target game player based on the action speed, the reaction speed, the action accuracy, and the action coordination to evaluate the somatosensory ability of the target game player includes:

[0110] Query the type of simulation game played by the target game player;

[0111] Based on the type of simulation game, weight assignments are made to the action speed, the reaction speed, the action accuracy, and the action coordination to obtain an action speed weight, a reaction speed weight, an action accuracy weight, and an action coordination weight;

[0112] Based on the action speed weight, the reaction speed weight, the action accuracy weight, and the action coordination weight, use the following formula to calculate the somatosensory ability value of the target game player:

[0113] S = w V ×V + w R ×R + w A ×A + w C ×C

[0114] where S represents the somatosensory ability value, w V represents the action speed weight, V represents the action speed, w R represents the reaction speed weight, R represents the reaction speed, w A represents the action accuracy weight, A represents the action accuracy, w C represents the action coordination weight, C represents the action coordination;

[0115] Based on the somatosensory ability value, evaluate the somatosensory ability of the target game player.

[0116] Among them, the somatosensory ability value refers to the score obtained by evaluating the somatosensory ability of the target game player.

[0117] Optionally, the simulated game type can be queried from the database of the game system.

[0118] It should be further noted that the weight assignment for the somatosensory data of the target game player needs to be determined according to the characteristics and requirements of the game. For example, in a shooting game that emphasizes quick response, the weight w R of the reaction speed can be relatively high; while in a game that focuses on dance skills, the weight w A of the action accuracy will be greater. Suppose for a comprehensive somatosensory game, the action speed weight w V = 0.2, the reaction speed weight w R = 0.3, the action accuracy weight w A = 0.3, the action coordination weight w C = 0.2. Suppose a certain somatosensory game player's action speed score V = 80 points, reaction speed score R = 85 points, action accuracy score A = 75 points, and action coordination score C = 82 points. Then the somatosensory ability value of this somatosensory game player is:

[0119] S = 0.2×80 + 0.3×85 + 0.3×75 + 0.2×82 = 80.4

[0120] Further, the target game players can be classified according to their somatosensory ability values. For example, 75 - 80 is poor, 80 to 85 is average, 85 - 90 is good, and above 90 is excellent. Specifically, it can be set according to the actual application.

[0121] Furthermore, in the embodiment of the present invention, by using the somatosensory data to optimize the game area of the independent somatosensory game area, the optimized game area can be obtained according to the somatosensory data of the players, and the independent somatosensory game area of each player can be adjusted and optimized. For example, the positions of obstacles and the distribution of props in the game scene can be adjusted, so that the game area better conforms to the physical ability and game habits of the players.

[0122] As an embodiment of the present invention, the method of using the somatosensory data to optimize the game area of the independent somatosensory game area to obtain an optimized game area includes:

[0123] Performing a sliding window process on the somatosensory data to obtain denoised time - series data;

[0124] Identifying the action peaks of the target game player by using the denoised time - series data;

[0125] Constructing an ability portrait of the target game player by using the action peaks;

[0126] Analyzing the actionable movement paths of the target game player based on the ability portrait;

[0127] Optimizing the game area of the independent somatosensory game area based on the actionable movement paths to obtain an optimized game area.

[0128] Wherein, the action peak refers to the relative maximum point reached by the relevant data when the player performs an action. For example, in the action of waving a virtual sword, the speed of the arm swing reaches the maximum value at a certain moment or the maximum angle that the arm can swing to. The ability portrait is a comprehensive description and visual presentation of various abilities demonstrated by the player in the game, constructed based on relevant data such as the action peaks of the player. The actionable movement path refers to a series of trajectories obtained by analyzing the ability portrait of the player, combined with the game scene and task requirements, through which the player can successfully complete actions in the game.

[0129] Optionally, the denoised time-series data can be obtained by sliding on the somatosensory data sequence using the NumPy library in Python, calculating the statistical features of the data within each window, such as the mean, median, etc., and then replacing the original data within the window with these statistical features. The action peaks can be obtained by performing a difference operation on the denoised time-series data to find the points with a relatively large data change rate. The ability profile can be constructed by analyzing the features such as the amplitude, frequency, and duration of the action peaks, and mapping these features to different ability dimensions of the player, such as strength, speed, or endurance, in combination with the specific requirements and rules of the game. The action path that the player can successfully complete under the current ability can be inferred using the A* algorithm based on the ability profile to determine the player's advantages and disadvantages in different ability dimensions, combined with the layout of the game area and the requirements of the game tasks. The optimized game area can adjust the positions and layouts of elements such as obstacles and props within the game area according to the actionable action path, and optimize the boundaries and spatial size of the game area (which can be based on the player's body size, for example, a larger independent somatosensory game area for a somatosensory game player with a larger body size).

[0130] S3. Use the somatosensory data to calculate the task completion rate of the target game player. According to the task completion rate, analyze the game execution ability of the target game player. Based on the somatosensory ability and the game execution ability, construct a preliminary cooperation strategy for the target game player. Use the preliminary cooperation strategy to perform preliminary cooperation control on the target game player to obtain cooperation control data. Use the cooperation control data to analyze the action cooperation angle and interaction complexity of the target game player.

[0131] In the embodiment of the present invention, by using the somatosensory data to calculate the task completion rate of the target game player, the actual performance of the player in the game can be measured, so as to intuitively understand the player's execution degree of the game tasks.

[0132] Among them, the task completion rate refers to the ratio of the number of tasks completed by the target game player to the total number of tasks during the game process.

[0133] Optionally, the task completion rate can be obtained by calculating the ratio of the number of effective somatosensory actions successfully triggered by the target game player within a specified time to the total number of tasks in the somatosensory data (number of effective times / total number of times × 100%).

[0134] Furthermore, in the embodiment of the present invention, by analyzing the game execution ability of the target game player according to the task completion rate, the advantages and disadvantages of the player in the game can be understood, providing a reference for formulating targeted strategies. For example, in the "whack-a-mole" game, the number of "moles" to be "whacked" can be allocated according to the player's game ability.

[0135] Among them, the game execution ability refers to the comprehensive ability demonstrated by the target game player in the process of participating in the somatosensory game to complete various game tasks.

[0136] Optionally, the game execution ability can be evaluated by comparing the player's task completion rate with their historical data and the average value of players in the same group, and combining the task difficulty coefficient (such as enemy strength, time limit) for weighted correction calculation of the standardized execution ability score to quantify the deviation degree relative to the benchmark level.

[0137] Furthermore, in the embodiment of the present invention, by constructing the preliminary cooperation strategy of the target game player based on the somatosensory ability and the game execution ability, the player's physical ability and the game task execution situation can be combined, providing a more effective game method for the player, promoting the player to better complete the game task, and enhancing the game experience.

[0138] Among them, the preliminary cooperation strategy refers to a set of initial action plans or guidelines formulated based on the somatosensory ability and the game execution ability of the target game player.

[0139] As an embodiment of the present invention, constructing the preliminary cooperation strategy of the target game player based on the somatosensory ability and the game execution ability includes:

[0140] Quantify the somatosensory ability and the game execution ability to obtain the quantified ability;

[0141] Query the pre-output game mode to perform dynamic weight allocation on the quantified ability to obtain the dynamic weight ability;

[0142] Based on the dynamic weight ability, perform dynamic game role matching on the target game player to obtain the dynamically matched player;

[0143] Configure the action logic for the dynamically matched player to obtain the preliminary cooperation strategy of the target game player.

[0144] Among them, the quantified ability refers to the result of digitally representing the somatosensory ability and the game execution ability of the target game player through a certain method. The dynamic weight ability refers to the ability value obtained by dynamically adjusting the quantified ability in combination with the pre-output game mode. The dynamically matched player refers to finding the most suitable game role for the player in the game according to the player's dynamic weight ability.

[0145] Optionally, the quantization ability first determines the sub-ability indicators included in the somatosensory ability and the game execution ability. For example, the somatosensory ability covers action speed, reaction speed, etc., and the game execution ability includes task completion rate, task completion quality, etc. Then, a scoring standard and range are set for each sub-ability indicator, and based on the actual performance of the player in the simulated game, scores are obtained for each sub-ability indicator. The dynamic weight ability can query the currently available game modes from the database of the game system, analyze the demand degree of each game mode for different abilities, and then, according to these demands, assign different weights to the various sub-ability indicators in the quantization ability. After multiplying the quantization ability by the weights, the dynamic matching player can use the cosine similarity algorithm or the Euclidean distance algorithm to calculate the similarity between the dynamic weight ability and the character ability characteristics, and define the required ability characteristics for each character in the game. For example, in a shooting game, player A is responsible for "taking the initiative to attack", player B is responsible for "observing", and player C is responsible for "guarding the stronghold". The action logic configuration for the dynamic matching player can generate a collaborative action sequence according to the role assignment. For example, in a somatosensory game, a sword-swinging attack action is assigned to the main attacker A, a throwing buff item action is assigned to the assistant B, and a shield-holding cover action is assigned to the defender C.

[0146] In the embodiment of the present invention, by using the preliminary collaborative strategy to perform preliminary collaborative control on the target game player and obtaining collaborative control data, the implementation effect of the preliminary collaborative strategy can be understood, and then a better game collaborative control strategy can be formulated.

[0147] Among them, the collaborative control data refers to the relevant data used to realize the collaborative cooperation between game elements and the actions of the target game player during the game process, such as somatosensory data, game scene information, etc.

[0148] Optionally, using the preliminary collaborative strategy to perform preliminary collaborative control on the target game player can be achieved through the game collaboration according to the control parameters of the preliminary collaborative strategy and the corresponding game character of the target player.

[0149] Furthermore, in the embodiment of the present invention, by using the collaborative control data to analyze the action collaboration angle and interaction complexity of the target game player, the cooperation situation of each part of the player's body when executing the collaborative strategy and the interaction challenges faced can be understood.

[0150] Among them, the action collaboration angle refers to the angle or direction presented by the coordination and cooperation relationship between the actions of each part of the game player's body and between the player's actions and the virtual characters or environment in the game. The interaction complexity is an index used to measure the complexity of the interaction process between the player and the somatosensory game.

[0151] As an embodiment of the present invention, the step of analyzing the action coordination angle and interaction complexity of the target game player by using the collaborative control data includes:

[0152] Using the collaborative control data to identify the motion vector of the target game player's joint point;

[0153] Constructing a three-dimensional action vector of the target game player according to the action vector;

[0154] Analyzing the action coordination angle of the target game player using the action three-dimensional vector;

[0155] Using the collaborative control data, constructing an action interaction graph of the target game player;

[0156] The action interaction graph is used to analyze the interaction complexity of the target game player.

[0157] Among them, the action vector refers to a quantitative description method of the action of the target game player's body joints, and the action interaction diagram refers to a graphical tool for intuitively displaying the interaction relationship between the target game player and various elements in the game environment.

[0158] Optionally, the action vector can extract the position coordinate information of each joint of the target game player at different time points from the collaborative control data, and be obtained by calculating the changes in the positions of the joints at adjacent time points and determining the displacement direction and distance of the joints in space. The action three-dimensional vector can use spatial coordinate transformation technology to integrate the action vectors of each joint according to the body structure and movement rules, and take a specific joint (such as the waist joint) as a reference to obtain the action vectors of other joints after spatial transformation and superposition. The action coordination angle can be determined by analyzing the angular relationship between the components in the action three-dimensional vector and the angle between different action three-dimensional vectors. For example, in a somatosensory game simulating basketball shooting, when the player makes a shooting action, we can obtain the action three-dimensional vectors of his hand, elbow and shoulder joints. Assuming that the hand vector is (1, 2, 3), the elbow vector is (2, 1, 4), and the shoulder vector is (3, 2, 1), the angle between these vectors is calculated by the vector dot product formula. The action interaction graph can abstract the player action sequence into a directed graph, where nodes represent actions (such as "attack" and "defense") and edges represent trigger relationships (such as "attack→drop props→pick up"). The interaction complexity can be determined by calculating indicators such as the number of nodes, the number of edges, and the shortest path length in the action interaction graph, combined with a preset complexity evaluation model.

[0159] S4. Based on the action coordination angle, the interaction complexity, and the optimized game area, construct the final cooperative control strategy for the target game player to perform cooperative control on the target game player.

[0160] In the embodiment of the present invention, by constructing the final cooperative control strategy for the target game player based on the action coordination angle, the interaction complexity, and the optimized game area to perform cooperative control on the target game player, the optimal control strategy can be utilized to enable the game player to better participate in the somatosensory game, thereby improving the control coordination of the multi-player cooperative somatosensory game.

[0161] As an embodiment of the present invention, constructing the final cooperative control strategy for the target game player based on the action coordination angle, the interaction complexity, and the optimized game area to perform cooperative control on the target game player includes:

[0162] Configure the cooperative control optimization model for the target game player;

[0163] Define the state space, action space, and reward function of the cooperative control optimization model to train the model of the cooperative control optimization model to obtain a trained model;

[0164] When the cumulative reward of the trained model reaches a convergence state, obtain the target optimization model;

[0165] Utilize the target optimization model to construct the control strategy parameters for the target game player;

[0166] Utilize the control strategy parameters to construct the final cooperative control strategy for the target game player, and perform cooperative control on the target game player by using the final cooperative control strategy.

[0167] Wherein, the cooperative control optimization model refers to, the state space refers to, the action space refers to, the reward function refers to, and the control strategy parameters refer to

[0168] Optionally, the collaborative control optimization model can be built using a deep learning framework such as TensorFlow. The training model can first define the state space, that is, various states of the target game player in the game, such as action postures, positions, task progress, etc., as elements of the state space, and then define the action space, that is, all possible actions that the player can take in the game, such as attacking, defending, and moving. Then, a reward function is designed to give corresponding rewards according to the contribution of the player's actions to the game goal, such as giving a positive reward for completing a task. Finally, it is obtained by combining historical data for model training. During the training process of the training model, the target optimization model can continuously record the cumulative reward value of the model. When the fluctuation of the cumulative reward value within a certain number of training steps is less than the preset convergence threshold, it is considered that the model has reached the convergence state, and at this time, the training is stopped to obtain the final model. The control strategy parameters can input the current state of the target game player into the target optimization model, and then the model will output corresponding action suggestions according to its own parameters and structure, such as the intensity, frequency, and timing of the actions. Then, these action suggestions are converted into actual operation parameters to obtain them.

[0169] Embodiment 2:

[0170] As Figure 2 shown, it is a functional module diagram of the multi-person collaborative somatosensory game control system based on intelligent devices of the present invention.

[0171] The multi-person collaborative somatosensory game control system 200 based on intelligent devices of the present invention can be installed in an electronic device. According to the functions implemented, the multi-person collaborative somatosensory game control system based on intelligent devices can include a game area simulation module 201, a game area optimization module 202, a user somatosensory analysis module 203, and a game collaborative control module 204. The modules of the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, and are stored in the memory of the electronic device.

[0172] In the embodiments of the present invention, the functions of each module / unit are as follows:

[0173] The game area simulation module 201 is used to deploy intelligent devices in the multi-person collaborative somatosensory game area, establish a communication connection between the intelligent devices and the multi-person collaborative somatosensory game area, collect the real physical environment of the target game player using the intelligent devices, perform 3D modeling on the real physical environment, and simulate the somatosensory game area of the target game player;

[0174] The game area optimization module 202 is configured to query the number of the target game players, build corresponding independent somatosensory game areas in the somatosensory game area, perform somatosensory simulation on the target game players in the independent somatosensory game areas to collect the somatosensory data of the target game players, analyze the somatosensory ability of the target game players by using the somatosensory data, and optimize the game areas of the independent somatosensory game areas by using the somatosensory data to obtain optimized game areas;

[0175] The user somatosensory analysis module 203 is configured to calculate the task completion rate of the target game players by using the somatosensory data, analyze the game execution ability of the target game players according to the task completion rate, build a preliminary cooperation strategy of the target game players based on the somatosensory ability and the game execution ability, perform preliminary cooperation control on the target game players by using the preliminary cooperation strategy to obtain cooperation control data, and analyze the action cooperation angle and interaction complexity of the target game players by using the cooperation control data;

[0176] The game cooperation control module 204 is configured to build a final cooperation control strategy of the target game players based on the action cooperation angle, the interaction complexity and the optimized game areas, so as to perform cooperation control on the target game players.

[0177] Specifically, each module in the multi-player cooperation somatosensory game control system 200 based on an intelligent device in the embodiment of the present invention adopts the same technical means as those in the Figure 1 multi-player cooperation somatosensory game control method based on an intelligent device described above, and can produce the same technical effects, which will not be elaborated here.

[0178] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention.

[0179] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for controlling a multi - person collaborative somatosensory game based on an intelligent device, characterized in that, The method includes: Deploying intelligent devices in the multi - person collaborative somatosensory game area, and establishing a communication connection between the intelligent devices and the multi - person collaborative somatosensory game area, so as to collect the real - time physical environment of the target game player by using the intelligent devices, performing 3D modeling on the real - time physical environment to simulate the somatosensory game area of the target game player; Querying the number of the target game players, constructing corresponding independent somatosensory game areas in the somatosensory game area, performing somatosensory simulation on the target game players in the independent somatosensory game areas to collect the somatosensory data of the target game players, analyzing the somatosensory ability of the target game players by using the somatosensory data, and optimizing the game area of the independent somatosensory game areas by using the somatosensory data to obtain an optimized game area; Calculating the task completion rate of the target game player by using the somatosensory data, analyzing the game execution ability of the target game player according to the task completion rate, constructing a preliminary cooperation strategy of the target game player based on the somatosensory ability and the game execution ability, performing preliminary cooperation control on the target game player by using the preliminary cooperation strategy to obtain cooperation control data, and analyzing the action cooperation angle and interaction complexity of the target game player by using the cooperation control data; Constructing a final cooperation control strategy of the target game player based on the action cooperation angle, the interaction complexity and the optimized game area to perform cooperation control on the target game player.

2. The method for controlling a multi - person collaborative somatosensory game based on an intelligent device according to claim 1, wherein, The performing 3D modeling on the real - time physical environment to simulate the somatosensory game area of the target game player includes: Collecting the point cloud data of the real - time physical environment; Performing 3D modeling on the real - time physical environment by using the point cloud data to obtain a game visual environment; Performing virtual - physical space alignment processing on the game visual environment to obtain a virtual mapping area; Performing edge detection on the virtual mapping area to divide the safety boundary of the virtual environment and obtain a somatosensory game area.

3. The method for controlling a multi-person collaborative somatosensory game based on an intelligent device according to claim 1, wherein, The performing somatosensory simulation on the target game player in the independent somatosensory game area to collect the somatosensory data of the target game player includes: Guiding the target game player to play games by using a pre - configured game library to capture the game actions of the target game player and collect the mechanical data of the target game player; Performing action modeling on the game actions to obtain a simulated game model; Performing timestamp alignment processing on the mechanical data and the simulated game model to obtain aligned data; Performing data fusion on the aligned data to obtain somatosensory data.

4. The method for controlling a multi-person collaborative somatosensory game based on an intelligent device according to claim 1, characterized in that, The analyzing the somatosensory ability of the target game player by using the somatosensory data includes: Calculating the action speed and reaction speed of the target game player by using the somatosensory data; Constructing the action trajectory of the target game player by using the somatosensory data; Analyzing the action accuracy of the target game player based on the action trajectory; Analyzing the action coordination of the target game player by using the somatosensory data; Based on the action speed, reaction speed, action accuracy, and action coordination, perform a comprehensive motion analysis on the target game player to evaluate the somatosensory ability of the target game player.

5. The method for controlling a multi-person collaborative somatosensory game based on an intelligent device according to claim 4, wherein Analyzing the action coordination of the target game player by using the somatosensory data includes: Extract the action data from the somatosensory data, perform time series processing on the action data to obtain time series actions, and calculate the action coordination coefficient of the time series actions by using the following formula: Among them, ρ(X,Y) represents the action coordination coefficient, X represents the Xth time series action in the time series actions, Y represents the Yth time series action in the time series actions, x i represents the ith data point in X, y i represents the ith data point in Y, represents the average value of X, represents the average value of Y, and n represents the data length of the time series actions; Based on the action coordination coefficient, evaluate the action synchronization of the target game player; Based on the action synchronization, identify the action coordination of the target game player.

6. The method for controlling a multi-person collaborative somatosensory game based on an intelligent device according to claim 4, characterized in that, Based on the action speed, reaction speed, action accuracy, and action coordination, perform a comprehensive motion analysis on the target game player to evaluate the somatosensory ability of the target game player, including: Query the type of simulation game played by the target game player; Based on the type of simulation game, assign weights to the action speed, reaction speed, action accuracy, and action coordination to obtain an action speed weight, a reaction speed weight, an action accuracy weight, and an action coordination weight; Based on the action speed weight, reaction speed weight, action accuracy weight, and action coordination weight, calculate the somatosensory ability value of the target game player by using the following formula: S = w V × V + w R × R + w A × A + w C × C Among them, S represents the somatosensory ability value, w V represents the action speed weight, V represents the action speed, w R represents the reaction speed weight, R represents the reaction speed, w A represents the action accuracy weight, A represents the action accuracy, w C represents the action coordination weight, C represents the action coordination; Based on the somatosensory ability value, evaluate the somatosensory ability of the target game player.

7. The method for controlling a multi-person collaborative somatosensory game based on an intelligent device according to claim 1, wherein Optimizing the game area of the independent somatosensory game area by using the somatosensory data to obtain an optimized game area, including: Perform sliding window processing on the somatosensory data to obtain denoised time series data; Use the denoised time series data to identify the action peaks of the target game player; Use the action peaks to construct an ability portrait of the target game player; Based on the ability portrait, analyze the actionable movement paths of the target game player; Based on the actionable movement paths, optimize the game area of the independent somatosensory game area to obtain an optimized game area.

8. The method for controlling a multi-person collaborative somatosensory game based on an intelligent device according to claim 1, characterized in that, Constructing the initial cooperation strategy of the target game player based on the somatosensory ability and the game execution ability, including: Quantify the somatosensory ability and the game execution ability to obtain quantified abilities; Query the pre-output game modes to perform dynamic weight assignment on the quantified abilities to obtain dynamically weighted abilities; Based on the dynamically weighted abilities, perform dynamic game character matching on the target game player to obtain a dynamically matched player; Configure the action logic for the dynamically matched player to obtain the initial cooperation strategy of the target game player.

9. The method for controlling a multi-person collaborative somatosensory game based on an intelligent device according to claim 1, characterized in that, Analyzing the action cooperation angle and interaction complexity of the target game player by using the cooperation control data, including: Use the cooperation control data to identify the action vectors of the joint points of the target game player; According to the action vectors, construct the action three-dimensional vector of the target game player; Use the action three-dimensional vector to analyze the action cooperation angle of the target game player; Use the cooperation control data to construct the action interaction graph of the target game player; Analyze the interaction complexity of the target game player by using the action interaction diagram.

10. A multi-person collaborative somatosensory game control system based on an intelligent device, characterized in that, The system includes: A game area simulation module, which is used to deploy intelligent devices in a multi-player collaborative somatosensory game area, establish a communication connection between the intelligent devices and the multi-player collaborative somatosensory game area, collect the real-time physical environment of the target game player by using the intelligent devices, perform 3D modeling on the real-time physical environment to simulate the somatosensory game area of the target game player; A game area optimization module, which is used to query the number of the target game players, construct corresponding independent somatosensory game areas in the somatosensory game area, perform somatosensory simulation on the target game players in the independent somatosensory game areas to collect the somatosensory data of the target game players, analyze the somatosensory ability of the target game players by using the somatosensory data, and optimize the game area of the independent somatosensory game areas by using the somatosensory data to obtain an optimized game area; A user somatosensory analysis module, which is used to calculate the task completion rate of the target game player by using the somatosensory data, analyze the game execution ability of the target game player according to the task completion rate, construct a preliminary collaboration strategy for the target game player based on the somatosensory ability and the game execution ability, perform preliminary collaborative control on the target game player by using the preliminary collaboration strategy to obtain collaborative control data, and analyze the action collaboration angle and interaction complexity of the target game player by using the collaborative control data; A game collaborative control module, which is used to construct a final collaborative control strategy for the target game player based on the action collaboration angle, the interaction complexity and the optimized game area to perform collaborative control on the target game player.

Images