Energy-saving control method and system for gamepad based on intelligent analysis

Abstract

The present invention discloses an energy-saving control method and system for a game controller based on intelligent analysis, including: obtaining the operation monitoring information of the controller, preprocessing the operation monitoring information of the controller to obtain the multi-modal fusion features of the target game controller; constructing a user operation analysis model to analyze the operation behavior of the target user using the game controller to obtain user operation analysis information; constructing an operation state transition matrix based on the multi-modal fusion features of the target game controller to predict the operation intention of the target user; constructing an energy-saving control strategy database, obtaining energy-saving control parameters matching the current operation scenario in the energy-saving control strategy database, and establishing a dynamic regulation mechanism to dynamically regulate the energy-saving control parameters; if there is no matching combination of energy-saving control parameters in the energy-saving control strategy database, then formulate an energy-saving control strategy. It realizes intelligent energy-saving control with dynamic power consumption regulation to improve the energy efficiency performance and user experience of the game controller.

Description

Technical Field

[0001] The present invention relates to the technical field of handle energy-saving control, and particularly to a game handle energy-saving control method and system based on intelligent analysis. Background Art

[0002] With the rapid development of the electronic game industry, as the core device for human-computer interaction, the functions of game handles have become increasingly complex, and the energy consumption problem has become increasingly prominent. Traditional game handles usually adopt a fixed power consumption mode and cannot dynamically adjust the energy consumption strategy according to the actual operation behavior of users, resulting in a large amount of energy waste. For example, when the user is browsing the menu or waiting for loading, the handle still maintains high-frequency sensor sampling and wireless data transmission, which not only shortens the battery life but also increases the heat generation of the device, affecting the user experience. In addition, the existing energy-saving strategies of handles are mostly based on a simple timeout mechanism and lack intelligent analysis of the user's operation intention, which is prone to misjudgment. For example, when the user pauses briefly, it enters the sleep state by mistake, resulting in a delay in operation response.

[0003] At the hardware level, with the improvement of the integration of game handles, the number of internal sensors and the sampling frequency have been increasing continuously, further exacerbating the energy consumption pressure. For example, modern handles usually are equipped with 9-axis IMUs, high-precision tactile sensors, and multi-channel force feedback motors, and the power consumption of these components can reach hundreds of milliwatts when operating at full load. However, existing energy-saving solutions mostly adopt simple hardware switch control and lack a fine-grained power consumption management mechanism, and cannot dynamically adjust the working state of each module according to real-time requirements. Therefore, there is an urgent need for an intelligent energy-saving control method that can deeply integrate multi-source perception data, accurately predict the user's intention, and achieve dynamic power consumption regulation to improve the energy efficiency performance and user experience of game handles. Summary of the Invention

[0004] The present invention overcomes the defects of the prior art and provides a game handle energy-saving control method and system based on intelligent analysis, and an important purpose thereof is to improve the energy efficiency performance and user experience of game handles.

[0005] To achieve the above object, the first aspect of the present invention provides a game handle energy-saving control method based on intelligent analysis, including:

[0006] Monitoring a target game handle to obtain handle operation monitoring information, and preprocessing the handle operation monitoring information to obtain multi-modal fusion features of the target game handle;

[0007] Constructing a user operation analysis model, inputting the multi-modal fusion features of the target game handle to analyze the operation behavior of the target user using the game handle, and obtaining user operation analysis information;

[0008] Construct an operation state transition matrix based on the multi-modal fusion features of the target game controller, and combine it with a Bayesian inference network to predict the operation intention of the target user, obtaining operation intention prediction information;

[0009] Construct an energy-saving control strategy database, obtain energy-saving control parameters matching the current operation scenario in the energy-saving control strategy database based on user operation analysis information and operation intention prediction information, and establish a dynamic regulation mechanism for dynamic regulation of energy-saving control parameters;

[0010] If there is no matching combination of energy-saving control parameters in the energy-saving control strategy database, formulate an energy-saving control strategy based on the NSGA algorithm.

[0011] In this solution, the monitoring of the target game controller to obtain the operation monitoring information of the controller, and the preprocessing of the operation monitoring information of the controller to obtain the multi-modal fusion features of the target game controller specifically include:

[0012] Set a sensor array in the target game controller, and monitor the target game controller through the sensor array to obtain the operation monitoring information of the controller. The operation monitoring information of the controller includes motion monitoring data, tactile monitoring data, and environmental monitoring data;

[0013] Perform time series processing on the operation monitoring information of the controller to obtain the operation monitoring time series sequence of the controller, and use the cubic spline interpolation method to upsample and align the operation monitoring time series sequence of the controller to eliminate time series misalignment, obtaining time series alignment information;

[0014] Import the time series alignment information into an extended Kalman filter for dynamic correction. Obtain the motion state equation through a preset controller coordinate system, use the acceleration measurement value as the observation, iteratively calculate the Jacobian matrix to update the attitude rotation matrix, and output the corrected body acceleration through the updated attitude rotation matrix to eliminate spatial deviation, obtaining spatio-temporal alignment information;

[0015] Perform data cleaning processing on the spatio-temporal alignment information to eliminate outliers, and perform feature extraction based on the cleaned spatio-temporal alignment information to obtain the operation monitoring features of the target game controller, constituting an initial feature vector;

[0016] Introduce an attention mechanism for multi-modal feature fusion, map the initial feature vector to a query vector, a key matrix, and a value matrix for attention score calculation, and perform weighted fusion through the calculated attention scores to obtain the multi-modal fusion features of the target game controller.

[0017] In this solution, the construction of the user operation analysis model, input the multi-modal fusion features of the target game controller to analyze the operation behavior of the target user using the game controller, obtaining user operation analysis information, specifically including:

[0018] Construct a user operation analysis model based on a dual-channel neural network. The user operation analysis model includes a temporal convolutional channel and a graph attention channel. Among them, the temporal channel is constructed by a stacked temporal convolutional network, and the graph attention channel is constructed by a graph attention network;

[0019] Obtain the multi-modal fusion features of the target game controller and input them into the user operation analysis model for analysis. The temporal convolutional channel extracts temporal features from the input multi-modal fusion features;

[0020] Convert the input multi-modal fusion features into a time window sequence, and capture local patterns and extract periodic laws from the time window sequence based on the stacked multi-layer temporal convolutional layers to generate temporal extraction features;

[0021] Based on the graph attention channel, perform user interaction topology modeling according to the input multi-modal fusion features. Define the operation type and intensity as graph nodes, and define the edge weights according to the time features;

[0022] Calculate the cosine similarity matrix between nodes in the graph embedding space, generate a soft clustering assignment matrix through the Sinkhorn algorithm to obtain the clustering membership probability, and splice the clustering membership probability as an auxiliary feature into the node embedding to generate an interaction topology graph;

[0023] Use the interaction topology graph to obtain the adjacency matrix to represent the operation interaction features of the target user, and combine the temporal extraction features for feature integration to analyze the operation habits and laws of the target user, and obtain user operation analysis information.

[0024] In this solution, construct an operation state transition matrix based on the multi-modal fusion features of the target game controller, and combine the Bayesian inference network to predict the operation intention of the target user to obtain operation intention prediction information, which specifically includes:

[0025] Obtain the multi-modal fusion features of the target game controller, and select the multi-modal fusion features within the preset time step range based on the multi-modal fusion features of the target game controller, which are defined as historical multi-modal fusion features;

[0026] Input the historical multi-modal fusion features into the user operation analysis model for analysis to obtain historical user operation analysis information, combine the historical user operation analysis information training data with the Markov algorithm to calculate the operation state transition probability of the target user, and construct an operation state transition matrix;

[0027] Obtain user operation analysis information, generate the operation state sequence of the target user at the current moment according to the user operation analysis information, and combine the operation state transition matrix to analyze the operation state transition situation of the target user at the next moment to generate several operation state transition sequences of the target user at the next moment;

[0028] Introduce a Bayesian inference network, train the Bayesian inference network using the historical user operation analysis information to output a transient prior distribution and a probability likelihood function, calculate the operation state sequence of the target user at the current moment, and obtain a transient posterior distribution;

[0029] Take the operation state transition sequence of the target user at the next moment as the input of the trained Bayesian inference network, and infer the transition probability values of each operation state transition sequence in the Bayesian network according to the transient posterior distribution;

[0030] Sort through the transition probability values corresponding to each operation state transition sequence, and select the operation state transition sequence with the highest transition probability as the prediction result of the operation intention of the target user at the next moment to obtain operation intention prediction information.

[0031] In this solution, the construction of the energy-saving control strategy database, obtaining energy-saving control parameters matching the current operation scenario in the energy-saving control strategy database based on user operation analysis information and operation intention prediction information, and establishing a dynamic regulation mechanism for dynamic regulation of energy-saving control parameters, specifically includes:

[0032] Obtain historical gamepad energy-saving control instances based on data retrieval, extract features from the historical gamepad energy-saving control instances, and obtain the energy-saving control parameter features and corresponding historical gamepad operation monitoring features of each historical gamepad energy-saving control instance;

[0033] Define energy-saving control scenario types through the historical gamepad operation monitoring features corresponding to each historical gamepad energy-saving control instance, and generate several feature subsets according to the historical gamepad operation monitoring features;

[0034] Calculate the Euclidean distance values between each feature subset, use the Euclidean distance values as subset merging indicators, and if the Euclidean distance value between two feature subsets is greater than a preset threshold, then merge the corresponding two feature subsets;

[0035] Obtain the merged feature subsets, define energy-saving control scenario categories based on the merged feature subsets, associate the energy-saving control parameter features with the energy-saving control scenario categories to obtain several association sets, and construct an energy-saving control strategy database with the path of energy-saving control scenario type - energy-saving control scenario type feature - energy-saving control parameter based on the several association sets;

[0036] Obtain user operation analysis information and operation intention prediction information, and generate a gamepad usage portrait of the target user at the current moment according to the user operation analysis information and operation intention prediction information;

[0037] Import the target gamepad usage image at the current moment into the energy-saving control strategy database, use the cosine metric algorithm to match the energy-saving control scenario type, and select the energy-saving control parameters of the energy-saving control scenario type with the highest similarity as the final energy-saving management and control plan, and generate a regulation instruction to perform energy-saving regulation on the target gamepad;

[0038] Establish a dynamic regulation mechanism. By analyzing the operation data of the target gamepad in real time, monitor the difference between the predicted result of the operation intention and the real-time operation characteristics in the real situation. If it is greater than the preset difference degree threshold, correct the gamepad usage image of the target user through the real-time operation characteristics, and dynamically select new energy-saving control parameters based on the corrected gamepad usage image of the target user.

[0039] In this solution, if there is no matching energy-saving control parameter combination in the energy-saving control strategy database, the energy-saving control strategy is formulated based on the NSGA algorithm, which specifically includes:

[0040] If there is no energy-saving control scenario in the energy-saving control strategy database that matches the gamepad usage image of the target user at the current moment, obtain the three energy-saving control parameter combinations with the highest similarity between the current energy-saving control strategy database and the gamepad usage image of the target user at the current moment, and formulate the energy-saving control strategy;

[0041] Generate an energy-saving control parameter interval based on the three obtained energy-saving control parameter combinations. According to the energy-saving control parameter interval, construct a search space, and introduce the NSGA algorithm to generate an initial population based on the search space;

[0042] Preset the objective function and constraints. Calculate the fitness value of each individual in the initial population through the objective function, and perform non-dominated sorting on all individuals in the population according to the fitness value to obtain several non-dominated levels;

[0043] Calculate the crowding distance for the individuals in each non-dominated level, use the tournament selection method to select elite individuals using the non-dominated sorting level and the crowding distance, and perform crossover and mutation operations on the selected elite individuals;

[0044] Merge the parent generation and the offspring generation, re-perform non-dominated sorting and crowding distance calculation on all candidate solutions, and select a preset number of elite individuals according to the Pareto front level and the crowding distance to form the next generation population for iterative evolution;

[0045] When the convergence criterion is met or the preset number of iterations is reached, output the non-dominated solution set, generate the energy-saving control parameter combination at the current moment according to the non-dominated solution set, and generate a regulation instruction to regulate the target gamepad.

[0046] In a second aspect of the present invention, there is provided an energy-saving control system for a game controller based on intelligent analysis. The system includes: a memory and a processor. The memory contains a program for an energy-saving control method for a game controller based on intelligent analysis. When the program for the energy-saving control method for a game controller based on intelligent analysis is executed by the processor, the following steps are implemented:

[0047] Monitor the target game controller to obtain the operation monitoring information of the controller, and preprocess the operation monitoring information of the controller to obtain the multi-modal fusion features of the target game controller;

[0048] Construct a user operation analysis model, input the multi-modal fusion features of the target game controller, analyze the operation behavior of the target user using the game controller, and obtain the user operation analysis information;

[0049] Construct an operation state transition matrix based on the multi-modal fusion features of the target game controller, and combine it with a Bayesian inference network to predict the operation intention of the target user, and obtain the operation intention prediction information;

[0050] Construct an energy-saving control strategy database, obtain the energy-saving control parameters matching the current operation scenario in the energy-saving control strategy database based on the user operation analysis information and the operation intention prediction information, and establish a dynamic regulation mechanism to dynamically regulate the energy-saving control parameters;

[0051] If there is no matching combination of energy-saving control parameters in the energy-saving control strategy database, an energy-saving control strategy is formulated based on the NSGA algorithm.

[0052] The present invention discloses an energy-saving control method and system for a game controller based on intelligent analysis, including: obtaining the operation monitoring information of the controller, preprocessing the operation monitoring information of the controller to obtain the multi-modal fusion features of the target game controller; constructing a user operation analysis model, analyzing the operation behavior of the target user using the game controller, and obtaining the user operation analysis information; constructing an operation state transition matrix based on the multi-modal fusion features of the target game controller, predicting the operation intention of the target user; constructing an energy-saving control strategy database, obtaining the energy-saving control parameters matching the current operation scenario in the energy-saving control strategy database, and establishing a dynamic regulation mechanism to dynamically regulate the energy-saving control parameters; if there is no matching combination of energy-saving control parameters in the energy-saving control strategy database, an energy-saving control strategy is formulated. Intelligent energy-saving control with dynamic power consumption regulation is realized to improve the energy efficiency performance and user experience of the game controller. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] To more clearly illustrate the technical solutions in the embodiments or exemplary examples of the present invention, the following will briefly introduce the drawings required for use in the description of the embodiments or exemplary examples. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the ones shown in these drawings.

[0054] Figure 1 Flowchart of a game controller energy-saving control method based on intelligent analysis provided by an embodiment of the present invention;

[0055] Figure 2 Flowchart of a game controller energy-saving control strategy formulation method provided by an embodiment of the present invention;

[0056] Figure 3 Block diagram of a game controller energy-saving control system based on intelligent analysis provided by an embodiment of the present invention;

[0057] The realization, functional characteristics, and advantages of the objectives of the present invention will be further described in conjunction with the embodiments with reference to the drawings. Detailed implementation manners

[0058] In order to be able to more clearly understand the above objectives, features, and advantages of the present invention, the present invention will be further described in detail below in conjunction with the drawings and specific implementation manners. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0059] Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0060] Figure 1 Flowchart of a game controller energy-saving control method based on intelligent analysis provided by an embodiment of the present invention;

[0061] As Figure 1 shown, the present invention provides a flowchart of a game controller energy-saving control method based on intelligent analysis, including:

[0062] S102, monitoring the target game controller to obtain the controller operation monitoring information, and preprocessing the controller operation monitoring information to obtain the multi-modal fusion features of the target game controller;

[0063] S104, constructing a user operation analysis model, inputting the multi-modal fusion features of the target game controller to analyze the operation behavior of the target user using the game controller, and obtaining user operation analysis information;

[0064] S106. Construct an operation state transition matrix based on the multi-modal fusion features of the target game controller, and combine it with the Bayesian inference network to predict the operation intention of the target user to obtain operation intention prediction information;

[0065] S108. Construct an energy-saving control strategy database, obtain energy-saving control parameters matching the current operation scenario in the energy-saving control strategy database based on the user operation analysis information and the operation intention prediction information, and establish a dynamic regulation mechanism to dynamically regulate the energy-saving control parameters;

[0066] S110. If there is no matching combination of energy-saving control parameters in the energy-saving control strategy database, formulate an energy-saving control strategy based on the NSGA algorithm.

[0067] Further, in a preferred embodiment of the present invention, the monitoring of the target game controller to obtain the controller operation monitoring information, and the preprocessing of the controller operation monitoring information to obtain the multi-modal fusion features of the target game controller specifically include:

[0068] Set a sensor array in the target game controller, and monitor the target game controller through the sensor array to obtain the controller operation monitoring information, where the controller operation monitoring information includes motion monitoring data, tactile monitoring data, and environmental monitoring data;

[0069] Perform time series processing on the controller operation monitoring information to obtain a controller operation monitoring time series sequence, and use the cubic spline interpolation method to upsample and align the controller operation monitoring time series sequence to eliminate time series misalignment to obtain time series alignment information;

[0070] Import the time series alignment information into an extended Kalman filter for dynamic correction, obtain a motion state equation through a preset controller coordinate system, use the acceleration measurement value as an observation, iteratively calculate the Jacobian matrix to update the attitude rotation matrix, and output the corrected body acceleration through the updated attitude rotation matrix to eliminate spatial deviation to obtain spatio-temporal alignment information;

[0071] Perform data cleaning processing on the spatio-temporal alignment information to eliminate outliers, and perform feature extraction based on the cleaned spatio-temporal alignment information to obtain the operation monitoring features of the target game controller, forming an initial feature vector;

[0072] Introduce an attention mechanism for multi-modal feature fusion, map the initial feature vector into a query vector, a key matrix, and a value matrix for attention score calculation, and perform weighted fusion through the calculated attention scores to obtain the multi-modal fusion features of the target game controller.

[0073] It should be noted that deploying a sensor array in the target game controller is the infrastructure for achieving refined energy consumption control. This array usually includes multiple sensing devices such as a six-axis inertial measurement unit (accelerometer + gyroscope), a linear resonant actuator (LRA) tactile sensor, and a surface capacitive pressure sensor. The motion monitoring data covers physical quantities such as three-dimensional acceleration vectors, angular velocity change rates, and attitude Euler angles. The tactile monitoring data includes interaction parameters such as key trigger force gradients, vibration motor current waveforms, and tactile feedback frequencies. The environmental monitoring data involves peripheral information such as the temperature distribution on the surface of the controller, the capacitance change in the holding area, and the ambient light intensity. These heterogeneous data streams are generated asynchronously at different sampling frequencies (such as 100 Hz for the accelerometer and 1 kHz for tactile feedback), and a hardware interrupt coordination and DMA transfer mechanism is required to ensure the complete capture of the original monitoring data.

[0074] It should be noted that the time series alignment process aims to eliminate the sampling time difference and clock drift problems of multi-source sensors. After mapping the original data streams of each sensor to a unified time series coordinate system according to the physical timestamps, for low-frequency data channels (such as the temperature sensor at 10 Hz), cubic spline interpolation is used for upsampling. Its mathematical essence is to construct a piecewise cubic polynomial function that satisfies the continuity constraints of function values, first-order derivatives, and second-order derivatives at adjacent data points, and while maintaining data smoothness, the sampling rate is increased to be synchronized with the highest-frequency sensor (such as 1 kHz). This process ensures that transient features such as high-frequency vibration signals are not overly smoothed by minimizing the integral square error between the interpolation curve and the original data. The dynamic correction based on the Extended Kalman Filter (EKF) is the core link to solve the non-linear errors in sensor fusion. A quaternion attitude motion model is established with the handle body coordinate system as the reference, and the state vector includes position, velocity, attitude quaternion, and gyroscope bias, etc. By calculating the Jacobian determinant of the state transition matrix in real time, the non-linear motion equation is linearized at the latest estimation point, and the covariance matrix is iteratively updated. In particular, for the centrifugal acceleration interference existing in the accelerometer data, a compensation mechanism based on gravity vector observation is designed: when the handle is in a non-free motion state (such as when the user suddenly shakes it), it automatically switches to the angular velocity integration mode dominated by the gyroscope to avoid the accumulation of inertial navigation errors. In the data cleaning stage, improved Grubbs test and DBSCAN clustering algorithms can be used to identify global outliers (such as acceleration spikes caused by transient sensor failures), and then local context-incoherent outliers (such as abnormal vibration signals occurring in the stationary state) are eliminated through density clustering. The multi-modal attention fusion mechanism maps the initial feature vector to a 128-dimensional query vector space through a learnable feature projection matrix, and at the same time constructs a cross-modal key-value matrix to capture the implicit associations between sensors. A gated cross-attention layer is designed to calculate the saliency weights of tactile features on motion features considering the dot product similarity between features. The finally generated fusion feature vector provides a highly discriminative feature representation for dynamically adjusting the sensor power supply strategy.

[0075] Furthermore, in a preferred embodiment of the present invention, for the construction of the user operation analysis model, the multi-modal fusion features of the target game handle are input to analyze the operation behavior of the target user using the game handle, and user operation analysis information is obtained, which specifically includes:

[0076] A user operation analysis model is constructed based on a dual-channel neural network. The user operation analysis model includes a time series convolution channel and a graph attention channel, where the time series channel is constructed by a stacked time series convolution network, and the graph attention channel is constructed by a graph attention network;

[0077] Obtain the multi-modal fusion features of the target gamepad and input them into the user operation analysis model for analysis. Perform temporal feature extraction on the input multi-modal fusion features through a temporal convolutional channel;

[0078] Convert the input multi-modal fusion features into a time window sequence, and perform local pattern capture and periodic law extraction on the time window sequence based on a stacked multi-layer temporal convolutional layer to generate temporal extraction features;

[0079] Based on the graph attention channel, perform user interaction topology modeling according to the input multi-modal fusion features. Define the operation type and intensity as graph nodes, and define the edge weights according to the time features;

[0080] Calculate the cosine similarity matrix between nodes in the graph embedding space, generate a soft clustering assignment matrix through the Sinkhorn algorithm to obtain the clustering membership probability, and splice the clustering membership probability as an auxiliary feature into the node embedding to generate an interaction topology graph;

[0081] Use the interaction topology graph to obtain the adjacency matrix to represent the operation interaction features of the target user, and combine the temporal extraction features for feature integration, analyze the operation habits and rules of the target user, and obtain user operation analysis information.

[0082] It should be noted that the user operation analysis model is constructed based on a dual-channel neural network to synergistically mine the temporal laws and interaction topology characteristics of user operation behaviors. The temporal convolutional channel uses a stacked dilated causal convolutional network as the core structure. Its multi-layer dilated convolutional kernels gradually expand the temporal receptive field through an exponential expansion factor (such as 1, 2, 4, 8). The bottom convolutional layer captures the microscopic operation rhythm, and the high-level network identifies the macroscopic tactical cycle. The input multi-modal fusion features are first segmented into a time window sequence of a fixed length (such as a 256-frame window with a frame interval of 10 ms). After zero-phase filtering and normalization preprocessing of the data within each window, the gating linear unit (GLU) is used to control the propagation intensity of the feature flow at different time scales, and finally a temporal feature vector containing local operation mode signatures (such as the joystick steering acceleration waveform) and global behavior period identifiers (such as the Fourier coefficients of the shooting frequency) is output. The parallel graph attention channel focuses on modeling the complex association network between operation events. Abstract the discrete operation events (such as button triggers, joystick deflections) within each time window as graph nodes, and the node attributes include operation type encoding and intensity quantization values (normalized pressure, displacement amount, etc.). The edge weights between nodes are dynamically determined by two factors: the exponential decay function based on the operation interval in the time dimension reflects the temporal tightness between operations, and the tactical logic association is characterized by the pre-trained operation transition probability in the semantic dimension. The graph attention network adopts a multi-head mechanism, and each attention head learns a different interaction mode projection space. By calculating the adaptive attention coefficients between nodes, it aggregates the neighborhood features to generate node embeddings rich in interaction semantics.

[0083] It should be noted that, to further reveal the internal pattern structure of the operation behavior, a node similarity matrix is constructed in the graph embedding space, and a differentiable clustering technique based on the Sinkhorn-Knopp algorithm is adopted. This algorithm inputs the cosine similarity matrix between nodes into the doubly stochastic matrix constraint space, and generates a soft clustering assignment matrix through iterative row and column normalization operations, so that each node obtains a probability distribution on different tactical mode categories. Taking the clustering membership probability as an auxiliary feature, after splicing it with the original node embedding vector, position encoding information is injected through a non-linear transformation to form an enhanced graph representation. In the final feature integration stage, a cross-modal gating fusion mechanism is designed to adaptively weight the rhythm features extracted from the temporal convolutional channels and the topological features generated by the graph attention channels. Based on the fused feature vectors, the core rules of the user's operations are analyzed, including the operation intensity distribution histogram, key combination rules, etc., providing a quantitative basis for personalized energy efficiency regulation.

[0084] Furthermore, in a preferred embodiment of the present invention, an operation state transition matrix is constructed based on the multi-modal fusion features of the target gamepad, and combined with a Bayesian inference network to predict the operation intention of the target user, obtaining operation intention prediction information, specifically including:

[0085] Obtain the multi-modal fusion features of the target gamepad, and select the multi-modal fusion features within a preset time step range based on the multi-modal fusion features of the target gamepad, which are defined as historical multi-modal fusion features;

[0086] Input the historical multi-modal fusion features into the user operation analysis model for analysis to obtain historical user operation analysis information, combine the historical user operation analysis information training data with the Markov algorithm to calculate the operation state transition probability of the target user, and construct an operation state transition matrix;

[0087] Obtain user operation analysis information, generate the operation state sequence of the target user at the current moment according to the user operation analysis information, combine the operation state transition matrix to analyze the operation state transition situation of the target user at the next moment, and generate several operation state transition sequences of the target user at the next moment;

[0088] Introduce a Bayesian inference network, use the historical user operation analysis information to train the Bayesian inference network to output a transient prior distribution and a probability likelihood function, and calculate the operation state sequence of the target user at the current moment to obtain a transient posterior distribution;

[0089] Take the operation state transition sequence of the target user at the next moment as the input of the trained Bayesian inference network, and infer the transition probability values of each operation state transition sequence in the Bayesian network according to the transient posterior distribution;

[0090] Sort the transfer probability values corresponding to each operation state transition sequence, and select the operation state transition sequence with the highest transfer probability as the prediction result of the target user's operation intention at the next moment, so as to obtain the operation intention prediction information.

[0091] It should be noted that the operation intention prediction realizes accurate prediction by integrating historical behavior analysis and real-time state reasoning. First, the historical data within the preset time window is intercepted from the multi-modal fusion features, that is, the data before the preset time window. After normalization processing, it forms a tensor structure containing multi-dimensional parameters such as motion trajectory, key pressure, and device power consumption, and is input into the user operation analysis model for in-depth feature analysis. The temporal convolutional module extracts the rhythm pattern and periodic law in the user operation, and the graph attention network constructs the correlation topology between operation events (such as the strong causal relationship between "rolling" and "shooting"), and outputs a feature vector representing the user's key pressing habit and operation intensity preference, which serves as the basis for Markov state modeling. Based on the parsed feature vector cluster, the sliding window clustering algorithm is used to divide the discrete operation state space, and each state node encodes the multi-dimensional feature distribution of a specific operation mode (such as "precision sniper", "high-speed movement", etc.). The Markov transition probability matrix is constructed by statistically analyzing the historical state transition frequencies. The transition weight between states not only considers the explicit operation sequence, but also introduces a temporal decay factor (such as assigning higher weights to the transition records within the last 10 minutes) to strengthen the prediction influence of recent behavior patterns. When the operation state sequence at the current moment is obtained, a multi-step prediction path search is carried out in the transition matrix, and the Viterbi algorithm is used to select N (N = 5) maximum likelihood paths. Each path corresponds to a possible operation evolution trajectory within the future Δt time, and its basic confidence is determined by the product of the state transition probabilities on the path. To enhance the context adaptability of the prediction, a Bayesian network is constructed and trained by variational inference to obtain the state transition likelihood function, and the conditional probability table is dynamically updated based on real-time sensing data. The Markov path set is input into the Bayesian network for probability correction, and the posterior probability of each path in the current context is calculated to ensure that short-term predictions rely more on operation inertia and long-term predictions tend to general patterns, and the path with the highest comprehensive confidence is selected as the intention prediction result.

[0092] Furthermore, in a preferred embodiment of the present invention, the construction of the energy-saving control strategy database, obtaining the energy-saving control parameters matching the current operation scenario from the energy-saving control strategy database based on the user operation analysis information and the operation intention prediction information, and establishing a dynamic regulation mechanism for dynamic regulation of the energy-saving control parameters, specifically including:

[0093] Obtain historical gamepad energy-saving control instances based on data retrieval, extract features from the historical gamepad energy-saving control instances, and obtain the energy-saving control parameter features and corresponding historical gamepad operation monitoring features of each historical gamepad energy-saving control instance;

[0094] Define the energy-saving control scenario type based on the historical handle operation monitoring features corresponding to each historical game handle energy-saving control instance, and generate several feature subsets according to the historical handle operation monitoring features;

[0095] Calculate the Euclidean distance values between each feature subset, use the Euclidean distance value as the subset merging index, and if the Euclidean distance value between two feature subsets is greater than the preset threshold, merge the corresponding two feature subsets;

[0096] Obtain the merged feature subsets, define the energy-saving control scenario categories based on the merged feature subsets, associate the energy-saving control parameter features with the energy-saving control scenario categories to obtain several associated sets, and construct an energy-saving control strategy database with the path of energy-saving control scenario type - energy-saving control scenario type features - energy-saving control parameters;

[0097] Obtain the user operation analysis information and operation intention prediction information, and generate the handle usage portrait of the target user at the current moment according to the user operation analysis information and operation intention prediction information;

[0098] Import the handle usage portrait of the target at the current moment into the energy-saving control strategy database, use the cosine metric algorithm to match the energy-saving control scenario type, and select the energy-saving control parameters of the energy-saving control scenario type with the highest similarity as the final energy-saving management and control plan, and generate a control command to perform energy-saving regulation on the target game handle;

[0099] Establish a dynamic regulation mechanism, and monitor the difference between the operation intention prediction result and the real-time operation characteristics in real time by analyzing the operation data of the target handle. If it is greater than the preset difference degree threshold, correct the handle usage portrait of the target user through the real-time operation characteristics, and dynamically select new energy-saving control parameters based on the corrected handle usage portrait of the target user.

[0100] It should be noted that adaptive regulation is achieved by constructing a historical strategy database and a real-time portrait matching mechanism. First, multi-dimensional energy-saving control instance data is extracted from historical operation logs. Each instance contains a set of regulation parameters (such as gyroscope sampling rate, haptic feedback intensity level) and the corresponding operation monitoring feature matrix, where the latter is composed of heterogeneous data such as six-axis inertial sensor waveforms, key pressure gradient spectra, and power consumption time series curves, forming a normalized feature vector to represent the unique pattern of each historical regulation case. Hierarchical clustering algorithm is used for scenario classification based on feature similarity. Initially, each historical instance is regarded as an independent feature subset, and the Euclidean distance between subsets is calculated. When the distance between subsets exceeds the preset threshold, a merge operation is triggered. The feature distribution statistics of each subset are retained during the merge process, and the merged feature distribution is refitted through a Gaussian mixture model. In the final set of scenario categories, each category corresponds to a specific operation mode and its typical energy consumption feature spectrum, and a strong association mapping is established with historical successful regulation parameters (such as when the gyroscope is reduced from 100Hz to 60Hz, the power consumption is reduced by 38%). A handle usage portrait of the target user at the current moment is constructed based on user operation analysis information and operation intention prediction information. Multidimensional features (such as operation frequency 32Hz, steering smoothness 0.87, etc.) are encoded into a 64-dimensional latent space vector through a deep feature projection network. The policy matching engine adopts a cosine similarity calculation framework. When retrieving scenario categories in the latent space, a 3-fold weight is applied to the feature dimensions with significant regulation effects (such as the slope of the power consumption curve) to amplify their influence.

[0101] It should be noted that for the dynamic regulation mechanism, in the short term, the morphological difference between the actual operation flow and the predicted sequence is detected through the sliding window DTW distance (window length 128 frames), and in the long term, the distribution shift degree of the user portrait is evaluated through KL divergence. When the comprehensive difference index exceeds the threshold, an incremental learning process is triggered: first, the current policy executor is frozen, then the parameters of the feature projection network are fine-tuned with the latest 500-frame data, the weights of the fully connected layer are updated, and then the new operation mode is mapped to the existing scenario categories or new categories are created through a fast clustering algorithm, and then the corresponding energy-saving control scheme is matched.

[0102] Figure 2 It is a flowchart of a method for formulating an energy-saving control strategy for a game handle provided by an embodiment of the present invention;

[0103] As Figure 2 shown, the present invention provides a flowchart of a method for formulating an energy-saving control strategy for a game handle, including:

[0104] S202, if an energy-saving control scenario that matches the handle usage portrait of the target user at the current moment cannot be found in the energy-saving control strategy database, then obtain the three energy-saving control parameter combinations with the highest similarity to the handle usage portrait of the target user at the current moment in the current energy-saving control strategy database, and formulate an energy-saving control strategy;

[0105] S204. Generate an energy-saving control parameter interval based on the obtained three combinations of energy-saving control parameters, form a search space according to the energy-saving control parameter interval, and introduce the NSGA algorithm to generate an initial population based on the search space;

[0106] S206. Preset the objective function and constraints, calculate the fitness value of each individual in the initial population through the objective function, perform non-dominated sorting on all individuals in the population according to the fitness value, and obtain several non-dominated levels;

[0107] S208. Calculate the crowding distance for the individuals in each non-dominated level, use the tournament selection method to select elite individuals using the non-dominated sorting level and crowding distance, and perform crossover and mutation operations on the selected elite individuals;

[0108] S210. Combine the parent generation and the offspring, re-perform non-dominated sorting and crowding distance calculation on all candidate solutions, and select a preset number of elite individuals according to the Pareto front level and crowding distance to form the next generation population for iterative evolution;

[0109] S212. When the convergence criterion is met or the preset number of iterations is reached, output the non-dominated solution set, generate the energy-saving control parameter combination at the current moment according to the non-dominated solution set, and generate a control command to control the target game handle.

[0110] It should be noted that in the scenario where the historical policy library does not match the current user profile, a multi-objective evolutionary optimization process is started to generate an adaptive control strategy. First, recall the three historical parameter combinations with the highest cosine similarity to the current handle usage profile from the database, and construct a multi-dimensional continuous search space by extracting the upper and lower boundaries of each parameter. For example, the gyroscope frequency range [40, 60] Hz forms a continuous solution domain, and the discrete level of tactile intensity is mapped to a linear interpolation interval of [20%, 45%]. Generate an initial population by sampling within the search space to ensure that individuals evenly cover the possible solution area. Define a two-objective optimization function: Objective one is the energy efficiency improvement rate, calculated as the ratio of the power consumption curve integral under the current policy to the benchmark policy; Objective two is the operation quality loss degree, quantified by the dynamic time warping (DTW) distance between the predicted intention sequence and the actual response. The constraint conditions cover the hardware safety threshold (such as the temperature not exceeding 45 °C) and the user experience red line (such as the operation delay < 25 ms). Obtain the two-objective fitness value of each individual, and use the non-dominated sorting algorithm to divide the population into multiple front levels. The first front contains all Pareto optimal solutions that are not dominated by other solutions, the second front is the solution set that is only dominated by the first front, and so on.

[0111] It should be noted that in the elite selection stage, the crowding distance metric is calculated for each individual within each non-dominated level. This metric ensures the preservation of the diversity of the front by measuring the density of the solution in the objective space relative to its neighboring solutions. A binary tournament selection mechanism is adopted: two individuals are randomly selected, and preference is given to the one with a higher front rank. If the ranks are the same, the one with a larger crowding distance is selected. Simulated binary crossover and polynomial mutation are performed on the selected elite individuals, with the crossover probability set to 0.9 and the mutation probability to 0.1. The distribution index is adjusted to 5 to balance exploration and exploitation. During the iterative optimization process, the parent population and the offspring are combined to form a temporary population (size 400), and non-dominated sorting and crowding distance calculation are re-performed. The top 200 optimal individuals are retained to form the new generation population. A dynamic convergence criterion is set: evolution is terminated when the change rate of the hypervolume metric of the front solution set is less than 1% for five consecutive generations or when the iteration limit of 50 generations is reached. The optimal control parameter combination is selected from the final output non-dominated solution set for regulation.

[0112] Furthermore, the objective function can be: ;

[0113] where, is the weight coefficient, used to balance the optimization priorities of energy efficiency and operation quality, is the energy efficiency improvement rate, i.e., the power consumption optimization effect, is the operation quality loss degree, constructed based on the average operation response delay between the current policy and the benchmark policy and the mis-triggering rate between the current policy and the benchmark policy.

[0114] Figure 3 A game controller energy-saving control system 3 based on intelligent analysis provided by an embodiment of the present invention includes: a memory 31 and a processor 32. The memory 31 contains a game controller energy-saving control method program based on intelligent analysis. When the game controller energy-saving control method program based on intelligent analysis is executed by the processor 32, the following steps are implemented:

[0115] Monitor the target game controller to obtain the handle operation monitoring information, and preprocess the handle operation monitoring information to obtain the multi-modal fusion features of the target game controller;

[0116] Construct a user operation analysis model, input the multi-modal fusion features of the target game controller to analyze the operation behavior of the target user using the game controller, and obtain user operation analysis information;

[0117] Based on the multi-modal fusion features of the target game controller, construct an operation state transition matrix, and combine it with the Bayesian inference network to predict the operation intention of the target user, and obtain operation intention prediction information;

[0118] Construct an energy-saving control strategy database, obtain energy-saving control parameters matching the current operation scenario from the energy-saving control strategy database based on user operation analysis information and operation intention prediction information, and establish a dynamic regulation mechanism to dynamically regulate the energy-saving control parameters;

[0119] If there is no matching combination of energy-saving control parameters in the energy-saving control strategy database, formulate an energy-saving control strategy based on the NSGA algorithm.

[0120] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces. The indirect coupling or communication connection of the devices or units can be electrical, mechanical, or other forms.

[0121] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0122] In addition, each functional unit in the embodiments of the present invention can be all integrated in a processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in one unit; the above-mentioned integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0123] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: various media that can store program codes such as removable storage devices, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks, or optical discs.

[0124] Alternatively, if the above integrated units of the present invention are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention essentially or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

[0125] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A game controller energy-saving control method based on intelligent analysis, characterized in that: include: Monitoring a target game controller to obtain controller operation monitoring information, and preprocessing the controller operation monitoring information to obtain multimodal fusion features of the target game controller; Build a user operation analysis model, input the multimodal fusion features of the target game controller to analyze the target user's operation behavior using the game controller, and obtain user operation analysis information; The operation state transfer matrix is ​​constructed based on the multimodal fusion features of the target game controller, and the operation intention of the target user is predicted by combining the Bayesian inference network to obtain the operation intention prediction information; Build an energy-saving control strategy database, obtain energy-saving control parameters matching the current operation scenario in the energy-saving control strategy database based on user operation analysis information and operation intention prediction information, and establish a dynamic control mechanism to dynamically control the energy-saving control parameters; If there is no matching energy-saving control parameter combination in the energy-saving control strategy database, the energy-saving control strategy is formulated based on the NSGA algorithm; The step of monitoring the target game controller to obtain controller operation monitoring information and preprocessing the controller operation monitoring information to obtain multimodal fusion features of the target game controller specifically includes: A sensor array is set in the target game controller, and the target game controller is monitored by the sensor array to obtain controller operation monitoring information, wherein the controller operation monitoring information includes motion monitoring data, tactile monitoring data and environmental monitoring data; Performing time sequence processing on the handle operation monitoring information to obtain a handle operation monitoring time sequence, and using a cubic spline interpolation method to perform upsampling and alignment on the handle operation monitoring time sequence to eliminate time sequence misalignment, thereby obtaining time sequence alignment information; The timing alignment information is imported into the extended Kalman filter for dynamic correction, the motion state equation is obtained through the preset handle coordinate system, the acceleration measurement value is used as the observation, the Jacobian matrix is ​​iteratively calculated to update the attitude rotation matrix, and the corrected body acceleration is output through the updated attitude rotation matrix to eliminate the spatial deviation and obtain the time-space alignment information; Performing data cleaning processing on the spatiotemporal alignment information to eliminate outliers, and performing feature extraction based on the cleaned spatiotemporal alignment information to obtain operation monitoring features of the target game controller to form an initial feature vector; An attention mechanism is introduced to perform multimodal feature fusion, and the initial feature vector is mapped into a query vector, a key matrix and a value matrix to calculate the attention score. The calculated attention scores are weightedly fused to obtain the multimodal fusion features of the target game controller.

2. The game controller energy saving control method based on intelligent analysis according to claim 1 is characterized in that: The user operation analysis model is constructed, and the multimodal fusion features of the target game controller are input to analyze the operation behavior of the target user using the game controller to obtain the user operation analysis information, which specifically includes: Building a user operation analysis model based on a dual-channel neural network, the user operation analysis model includes a temporal convolution channel and a graph attention channel, wherein the temporal convolution channel is built by a stacked temporal convolution network, and the graph attention channel is built by a graph attention network; Acquire the multimodal fusion features of the target game controller, input them into the user operation analysis model for analysis, and perform temporal feature extraction on the input multimodal fusion features through a temporal convolution channel; The input multimodal fusion features are converted into a time window sequence, and local patterns and periodic regularity are extracted from the time window sequence based on stacked multi-layer time series convolution layers to generate time series extraction features; Based on the graph attention channel, user interaction topology modeling is performed according to the input multimodal fusion features, the operation type and intensity are defined as graph nodes, and the edge weights are defined according to the time features; The cosine similarity matrix between nodes is calculated in the graph embedding space, and the soft clustering assignment matrix is ​​generated by the Sinkhorn algorithm to obtain the clustering probability. The clustering probability is spliced ​​into the node embedding as an auxiliary feature to generate an interactive topology graph. The interaction topology graph is used to obtain the adjacency matrix to characterize the target user's operation interaction characteristics, and the time series extraction features are combined for feature integration to analyze the target user's operation habits and rules to obtain user operation analysis information.

3. The game controller energy saving control method based on intelligent analysis according to claim 1, characterized in that: The operation state transfer matrix is ​​constructed based on the multimodal fusion features of the target game controller, and the operation intention of the target user is predicted by combining the Bayesian inference network to obtain the operation intention prediction information, which specifically includes: Acquire the multimodal fusion features of the target game controller, and select the multimodal fusion features within a preset time step range based on the multimodal fusion features of the target game controller, and define them as historical multimodal fusion features; Input the historical multimodal fusion features into the user operation analysis model for analysis to obtain historical user operation analysis information, combine the historical user operation analysis information training data with the Markov algorithm to calculate the target user's operation state transition probability, and construct the operation state transition matrix; Acquire user operation analysis information, generate an operation state sequence of the target user at the current moment according to the user operation analysis information, analyze the operation state transition status of the target user at the next moment in combination with the operation state transition matrix, and generate several operation state transition sequences of the target user at the next moment; Introducing a Bayesian inference network, using the historical user operation analysis information to train the Bayesian inference network to output a transient prior distribution and a probability likelihood function, calculating the operation state sequence of the target user at the current moment, and obtaining a transient posterior distribution; The target user's operation state transition sequence at the next moment is used as the input of the trained Bayesian inference network, and the transition probability value of each operation state transition sequence is inferred in the Bayesian network according to the transient posterior distribution; By sorting the transition probability values ​​corresponding to each operation state transition sequence, the operation state transition sequence with the highest transition probability is selected as the operation intention prediction result of the target user at the next moment, and the operation intention prediction information is obtained.

4. The game controller energy saving control method based on intelligent analysis according to claim 1, characterized in that: The energy-saving control strategy database is constructed, and based on the user operation analysis information and the operation intention prediction information, energy-saving control parameters matching the current operation scenario are obtained from the energy-saving control strategy database, and a dynamic control mechanism is established to dynamically control the energy-saving control parameters, specifically including: Acquire historical game controller energy-saving control instances based on data retrieval, perform feature extraction on the historical game controller energy-saving control instances, and acquire energy-saving control parameter features of each historical game controller energy-saving control instance and corresponding historical controller operation monitoring features; Define the energy-saving control scenario type through the historical handle operation monitoring features corresponding to each historical game handle energy-saving control instance, and generate several feature subsets based on the historical handle operation monitoring features; Calculate the Euclidean distance between each feature subset and use the Euclidean distance as the subset merging index. If the Euclidean distance between two feature subsets is greater than a preset threshold, merge the corresponding two feature subsets. Obtain the merged feature subset, define the energy-saving control scenario category based on the merged feature subset, associate the energy-saving control parameter feature with the energy-saving control scenario category to obtain several association sets, and construct an energy-saving control strategy database with the energy-saving control scenario type-energy-saving control scenario type feature-energy-saving control parameter as the path based on the several association sets; Obtaining user operation analysis information and operation intention prediction information, and generating a handle usage portrait of the target user at the current moment according to the user operation analysis information and operation intention prediction information; Import the target game controller usage profile at the current moment into the energy-saving control strategy database, use the cosine metric algorithm to match the energy-saving control scene type, and select the energy-saving control parameters of the energy-saving control scene type with the highest similarity as the final energy-saving management and control plan, and generate control instructions to perform energy-saving control on the target game controller; A dynamic control mechanism is established to analyze the difference between the operation intention prediction results and the real-time operation characteristics under real-time conditions by monitoring the operation data of the target handle in real time. If the difference is greater than the preset difference threshold, the handle usage portrait of the target user is corrected according to the real-time operation characteristics, and new energy-saving control parameters are dynamically selected based on the corrected handle usage portrait of the target user.

5. The game controller energy saving control method based on intelligent analysis according to claim 1 is characterized in that: If there is no matching energy-saving control parameter combination in the energy-saving control strategy database, an energy-saving control strategy is formulated based on the NSGA algorithm, specifically including: If the energy-saving control strategy database fails to match the energy-saving control scenario that matches the handle usage profile of the target user at the current moment, then the three energy-saving control parameter combinations with the highest similarity between the current energy-saving control strategy database and the handle usage profile of the target user at the current moment are obtained to formulate an energy-saving control strategy; Based on the obtained three energy-saving control parameter combinations, an energy-saving control parameter interval is generated, a search space is formed according to the energy-saving control parameter interval, and the NSGA algorithm is introduced to generate an initial population based on the search space; Preset the objective function and constraint conditions, calculate the fitness value of each individual in the initial population through the objective function, sort all individuals in the population according to the fitness value, and obtain several non-dominated layers; The crowding distance is calculated for the individuals in each non-dominated layer, and the elite individuals are selected by the tournament selection method using the non-dominated sorting level and crowding distance, and the selected elite individuals are subjected to crossover and mutation operations. Merge the parent generation with the child generation, recalculate the non-dominated sorting and crowding distance of all candidate solutions, and select a preset number of elite individuals according to the Pareto frontier level and crowding distance to form the next generation population for iterative evolution; When the convergence criteria are met or the preset number of iterations is reached, a non-dominated solution set is output, and the energy-saving control parameter combination at the current moment is generated according to the non-dominated solution set, and a control instruction is generated to control the target game controller.

6. A game controller energy-saving control system based on intelligent analysis, characterized in that: The system includes: a memory and a processor, wherein the memory contains a game controller energy-saving control method program based on intelligent analysis, and when the game controller energy-saving control method program based on intelligent analysis is executed by the processor, the game controller energy-saving control method steps based on intelligent analysis as described in any one of claims 1-5 are implemented.

Images