A gamepad power management method and system

Abstract

The application discloses a gamepad power management method, comprising: acquiring power consumption data of a gamepad in different game scenes, and constructing a power consumption model; according to the power consumption model, analyzing the influence of player operation habits on power consumption, and generating an operation habit classification label; according to the operation habit classification label and the game scene change trend, dynamically adjusting the time interval threshold of the standby mode; monitoring the vibration function use, light flicker frequency and key operation frequency of the gamepad when the game scene is switched, judging the power consumption trend of the current scene; if the power consumption trend of the current scene is lower than a preset threshold, triggering a low-power mode; according to the time interval threshold of the standby mode, combining the environmental information of the gamepad to judge whether to exit the low-power standby mode; in the low-power standby mode, monitoring the operation signal of the gamepad, and distributing power resources according to the current game scene and the operation habits of the player.

Description

Technical Field

[0001] This invention relates to the field of entertainment equipment management technology, and in particular to a power management method and system for game controllers. Background Technology

[0002] Power management of game controllers is a complex technical issue involving multiple aspects. First, the power consumption of game controllers varies greatly depending on the game scenario. For example, in some large 3D games, game controllers need to vibrate and flash lights frequently, which consumes a lot of power; while in some casual puzzle games, game controllers may only need to press a few buttons occasionally, resulting in lower power consumption. Second, different players' gaming habits and operation methods also affect the power consumption of game controllers. Some players like to play for long periods of time continuously, while others like to frequently turn the controller on and off. These behavioral patterns all pose challenges to power management.

[0003] Furthermore, the power management of game controllers must also consider the design of standby modes. Since players are not constantly playing, game controllers must have an intelligent way to automatically enter a low-power standby mode after the player pauses the game for a period of time to extend battery life. However, this standby mode design also faces a dilemma: if the interval between switching to standby mode is set too short, players will feel that the controller is unresponsive; if the interval is set too long, it will waste power. Therefore, finding a suitable interval that saves power without affecting the gaming experience is a technical challenge. Summary of the Invention

[0004] In order to solve the above-mentioned technical problems, the present invention provides a power management method for game controllers.

[0005] The technical solution of this invention is implemented as follows:

[0006] A power management method for a game controller includes the following steps:

[0007] S1. Obtain power consumption data of the game controller in different game scenarios and build a power consumption model;

[0008] S2. Based on the power consumption model, analyze the impact of player operation habits on power consumption and generate operation habit classification tags;

[0009] S3. Based on user habits, categorized tags, and changing trends in game scenarios, dynamically adjust the time interval threshold of standby mode.

[0010] S4. Monitor the use of the controller's vibration function, the frequency of light flashing, and the frequency of button operation when switching game scenes to determine the power consumption trend of the current scene.

[0011] S5. If the power consumption trend of the current scene is lower than the preset threshold, the low power mode is triggered to reduce the power supply of the vibration function and the light flashing.

[0012] S6. Based on the time interval threshold of the standby mode and the environmental information of the controller, determine whether to exit the low-power standby mode.

[0013] S7. In low-power standby mode, monitor the controller's operation signals and allocate power resources according to the current game scene and the player's operation habits.

[0014] Furthermore, the process of constructing the power consumption model in step S1 is specifically as follows:

[0015] Data on the vibration frequency, light flashing frequency, and button operation frequency of the game controller in different game scenarios are acquired, and the data is preprocessed.

[0016] Based on the preprocessed power consumption data of the game controller, an initial power consumption model is constructed. The vibration frequency, light flashing frequency, and button operation frequency are used as independent variables, and power consumption is used as the dependent variable. The coefficients of the regression model are fitted by the least squares method.

[0017] The initial power consumption model is evaluated by calculating the mean square error and coefficient of determination to determine the model's fit and predictive ability. If the model performance does not meet the requirements, a regularization term is introduced to control the model complexity, and a support vector machine is attempted. By comparing the performance of different algorithms, the modeling method is selected.

[0018] Furthermore, the process of generating operation habit classification labels in step S2 is specifically as follows:

[0019] Based on the power consumption model, obtain the player's operation record data, and for each player's operation record data, calculate the frequency of various operations to obtain the operation frequency distribution;

[0020] Based on the operation frequency distribution, determine whether each type of operation is a high-frequency operation or a low-frequency operation. If the operation frequency is higher than a preset threshold, it is determined to be a high-frequency operation; otherwise, it is determined to be a low-frequency operation.

[0021] For the high-frequency and low-frequency operations, operation features are extracted respectively to obtain a high-frequency operation feature set and a low-frequency operation feature set;

[0022] Based on the high-frequency operation feature set and the low-frequency operation feature set, the player's operation habits are classified to obtain the operation habit classification result;

[0023] For each operation habit category, the average power consumption of players in that category is calculated to obtain the power consumption level of each operation habit category.

[0024] Furthermore, the process of dynamically adjusting the time interval threshold of the standby mode in step S3 is specifically as follows:

[0025] Based on the pre-established correspondence between operation frequency and time interval threshold, the player's real-time operation data is obtained, and the player's current operation frequency is determined through data analysis;

[0026] Determine whether the player's operation frequency is high-frequency or low-frequency. If it is high-frequency, set the standby mode time interval to a longer interval; if it is low-frequency, set the standby mode time interval to a shorter interval.

[0027] Clustering algorithms are used to classify the players' operating habits and obtain typical behavior patterns under different operating habits;

[0028] For each typical behavior pattern, the association rule mining algorithm is used to analyze its correlation with changes in the game scene, and to obtain the scene change trend under different behavior patterns;

[0029] The time interval threshold of the standby mode is dynamically adjusted according to the changing trend of the scenario.

[0030] Furthermore, the process of determining the power consumption trend of the current scenario in step S4 is specifically as follows:

[0031] Acquire the trigger signal for game scene switching. If the scene switching signal is detected, start real-time monitoring of the controller vibration frequency, light flashing frequency, and button operation frequency.

[0032] Based on preset vibration frequency thresholds, light flashing frequency thresholds, and button operation frequency thresholds, determine whether the current controller vibration frequency, light flashing frequency, and button operation frequency exceed the thresholds.

[0033] If at least one of the controller vibration frequency, light flashing frequency, and button operation frequency exceeds a preset threshold, the current game scene is determined to be a high power consumption scene.

[0034] Specifically, for game scenarios identified as having high power consumption, a support vector machine algorithm is used to train a high power consumption scenario prediction model based on controller vibration frequency, light flashing frequency, and button operation frequency data from historical high power consumption scenarios.

[0035] Furthermore, the process of triggering the low-power mode in step S5 is specifically as follows:

[0036] Obtain power consumption data for the current scenario and compare it with a preset threshold. If the power consumption is lower than the threshold, trigger a low-power mode.

[0037] Based on the preset low-power strategy, the reduction range of vibration function and light flashing effect is determined, and the function degradation is achieved by controlling the power supply.

[0038] Gradually reduce the vibration frequency and light brightness until the lowest power consumption level is reached, while monitoring the trend of power consumption changes.

[0039] By fitting the functional relationship between power consumption, vibration frequency, and light brightness using the least squares method, a frequency reduction and dimming scheme is obtained.

[0040] By using a decision tree algorithm, and taking into account current scene characteristics and user habits, the trigger threshold of the low-power mode is dynamically adjusted.

[0041] A Markov model is constructed based on historical power consumption data to predict electricity consumption trends over a future period and make energy-saving decisions.

[0042] Furthermore, the process of determining whether to exit the low-power standby mode in step S6, based on the environmental information of the controller, specifically involves:

[0043] Obtain the current environmental information of the controller, including temperature, humidity, light intensity, and noise data;

[0044] Based on the pre-set threshold ranges of environmental data in various dimensions, determine whether the current environment of the controller meets the normal working conditions;

[0045] If the current environment does not meet the conditions for the controller to work normally, the controller's low-power standby mode will be activated.

[0046] In the low-power standby mode, the controller's environmental data is periodically collected, and the environmental status of the controller in the future is predicted based on the trend of environmental data changes.

[0047] A correlation model between environmental data and controller power consumption is established using machine learning algorithms, and the standby time threshold of the low power mode is dynamically adjusted.

[0048] When the controller's continuous standby time exceeds the standby time threshold, and the environmental prediction results indicate that the controller will remain in an unusable environment for some time to come, the controller will exit the low-power standby mode and enter a sleep state.

[0049] Furthermore, the process of allocating power resources in step S7 is specifically as follows:

[0050] The controller receives operation signals and determines whether it is in low-power standby mode. If so, it enters continuous monitoring mode; otherwise, it remains in normal working mode.

[0051] Under continuous monitoring, a convolutional neural network algorithm is used to extract features from the handle operation signals to obtain operation feature vectors.

[0052] Based on the pre-established game scene model and player operation habit model, the operation feature vectors are classified to determine the current game scene type and player operation habit type;

[0053] For different game scenario types and player operation habits, a decision tree algorithm is used to generate corresponding power resource allocation strategies;

[0054] The power resource allocation strategy is converted into control commands and sent to the power management module of the controller through the controller's communication interface;

[0055] The power management module adjusts the operating voltage and clock frequency of each hardware module according to the received control commands;

[0056] When the controller exits low-power standby mode, restore the default operating parameters of each hardware module;

[0057] Acquire historical operation data and real-time power consumption data of the device to build a training dataset for continuous training and optimization of machine learning algorithms;

[0058] Through continuous training and iterative optimization of machine learning algorithms, the intelligence level of power management strategies is continuously improved.

[0059] Furthermore, this method also includes:

[0060] S8. Dynamically adjust the time interval threshold of the standby mode, and optimize the power management strategy by combining historical operation data and current power consumption trends.

[0061] The process of optimizing the power management strategy in step S8 is as follows:

[0062] Acquire historical operation data and real-time power consumption data of the device to construct a training dataset;

[0063] The decision tree algorithm is used to dynamically adjust the time interval threshold of the standby mode based on the historical operation data and real-time power consumption trend, so as to obtain the optimized threshold parameter.

[0064] By using the support vector machine algorithm, historical data and real-time trends are comprehensively analyzed to determine the current usage status and power consumption level of the device, and to determine whether to trigger standby mode.

[0065] If the current idle time of the device exceeds the optimized time interval threshold and the power consumption level is low, it will automatically enter standby mode to reduce power consumption.

[0066] In the standby mode, the device's operation behavior and power consumption changes are continuously monitored. If user operation or a sudden increase in power consumption is detected, the device is woken up and exits the standby mode.

[0067] A game controller power management system includes a power management module, a data acquisition and processing module, and a data analysis and model building module;

[0068] The power management module controls the power on and off of the controller and the switching of different power consumption states according to the triggering and exiting conditions of the low power mode.

[0069] According to the preset low-power strategy, the power supply of vibration function and light flashing is reduced, and the operating voltage and clock frequency of each hardware module are adjusted.

[0070] Dynamically adjust the time interval threshold of standby mode to optimize power management strategy;

[0071] The data acquisition and processing module collects power consumption data of the game controller in different game scenarios, as well as player operation record data and environmental information of the controller, and preprocesses the collected data.

[0072] The processed data is transmitted to the power management module and the data analysis and model building module to provide data support for the formulation and optimization of power management strategies.

[0073] The data analysis and model building module constructs an initial power consumption model based on the preprocessed game controller power consumption data and evaluates the model performance.

[0074] Based on the power consumption model, we analyze the impact of players' operating habits on power consumption and statistically analyze the power consumption levels of each category.

[0075] Analyze the correlation between player operating habits and changes in game scenarios;

[0076] Construct a Markov model to assist the power management module in making energy-saving decisions;

[0077] Establish a correlation model between environmental data and controller power consumption to support dynamic adjustment of the standby time threshold of low power mode.

[0078] Compared with the prior art, the present invention has the following advantages:

[0079] This invention acquires power consumption data of the controller in different game scenarios, establishes a power consumption model, analyzes the impact of player operation habits on power consumption, classifies operation habits according to labels, analyzes player behavior patterns and game scenario change trends in real time, presets a standby mode time interval threshold, monitors the controller's vibration, lighting and button operation frequency in real time when switching game scenarios, judges the power consumption trend, and triggers a low power mode when the consumption trend is lower than the preset threshold, reducing the power supply of vibration and lighting.

[0080] This invention also dynamically adjusts the standby mode time interval threshold through machine learning algorithms and adjusts the power supply intensity based on real-time battery life data to ensure that the gaming experience is not affected. This achieves intelligent power management of the game controller, effectively extends battery life, and ensures a good gaming experience. Attached Figure Description

[0081] Figure 1 This is a flowchart illustrating the steps of a game controller power management method according to Example 1.

[0082] Figure 2 This is a framework diagram of a game controller power management system as shown in Example 2. Detailed Implementation

[0083] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0084] Example 1

[0085] like Figure 1 As shown, this embodiment provides a game controller power management method, including the following steps:

[0086] S1. Obtain power consumption data of the game controller in different game scenarios and build a power consumption model;

[0087] S2. Based on the power consumption model, analyze the impact of player operation habits on power consumption and generate operation habit classification tags;

[0088] S3. Based on user habits, categorized tags, and changing trends in game scenarios, dynamically adjust the time interval threshold of standby mode.

[0089] S4. Monitor the use of the controller's vibration function, the frequency of light flashing, and the frequency of button operation when switching game scenes to determine the power consumption trend of the current scene.

[0090] S5. If the power consumption trend of the current scene is lower than the preset threshold, the low power mode is triggered to reduce the power supply of the vibration function and the light flashing.

[0091] S6. Based on the time interval threshold of the standby mode and the environmental information of the controller, determine whether to exit the low-power standby mode.

[0092] S7. In low-power standby mode, monitor the controller's operation signals and allocate power resources according to the current game scene and the player's operation habits.

[0093] Furthermore, the process of constructing the power consumption model in step S1 is specifically as follows:

[0094] Data on the vibration frequency, light flashing frequency, and button operation frequency of the game controller in different game scenarios are acquired, and the data is preprocessed.

[0095] Based on the preprocessed power consumption data of the game controller, an initial power consumption model is constructed. The vibration frequency, light flashing frequency, and button operation frequency are used as independent variables, and power consumption is used as the dependent variable. The coefficients of the regression model are fitted by the least squares method.

[0096] The initial power consumption model is evaluated by calculating the mean square error and the coefficient of determination to determine the model's fit and predictive ability. If the model performance does not meet the requirements, a regularization term is introduced to control the model complexity, and a support vector machine is attempted. The modeling method is selected by comparing the performance of different algorithms.

[0097] Acquire power consumption data of the game controller in different game scenarios, including vibration function usage frequency, light flashing frequency, and button operation frequency. Preprocess the acquired data, including data cleaning and normalization, for subsequent modeling use.

[0098] Based on the preprocessed power consumption data, a power consumption model for the game controller is established. The model parameters are obtained through training, and the power consumption pattern of the game controller under different game scenarios is determined.

[0099] The system acquires the trigger signal for game scene switching. If a scene switching signal is detected, it starts to monitor the controller vibration frequency, light flashing frequency, and button operation frequency in real time, and inputs the real-time monitoring data into the power consumption model.

[0100] Based on preset vibration frequency thresholds, light flashing frequency thresholds, and button operation frequency thresholds, determine whether the current controller vibration frequency, light flashing frequency, and button operation frequency exceed the thresholds. If at least one exceeds the preset threshold, the current game scene is determined to be a high power consumption scene.

[0101] For game scenarios identified as having high power consumption, a support vector machine algorithm is used to train a high power consumption scenario prediction model based on the controller vibration frequency, light flashing frequency, and button operation frequency data of historical high power consumption scenarios, and obtain the prediction model parameters.

[0102] When switching game scenes, the current controller vibration frequency, light flashing frequency, and button operation frequency are input into the high power consumption scene prediction model. The model then predicts the probability that the current scene is a high power consumption scene.

[0103] Based on the probability of high power consumption scenarios, different power consumption trend levels are set. The power consumption trend level of the current game scenario is calculated through the membership function. The power consumption trend level is fed back to the game. Based on the power consumption trend level, the game dynamically optimizes the power consumption by adjusting parameters such as the intensity of special effects rendering and the quality of background music in the game scenario.

[0104] Continuously monitor the power consumption data of the game controller, and continuously update the power consumption model and the high power consumption scenario prediction model based on new data. Improve the accuracy and adaptability of the model through incremental learning to achieve dynamic optimization of the game controller's power consumption.

[0105] Specifically, as shown in the following example, when acquiring power consumption data of the game controller, data such as controller vibration frequency, light flashing frequency, and button operation frequency can be collected by sensors. For example, if 10 times per second are collected continuously for 5 minutes, 3000 data points can be obtained.

[0106] Then the data is cleaned to remove outliers and invalid data, and the data is normalized to scale the numerical range to between 0 and 1.

[0107] When building a power consumption model, you can choose the support vector machine algorithm, use the Gaussian kernel function, set the penalty coefficient C to 10, optimize the model parameters through grid search, and finally obtain a power consumption model with an accuracy of 95%.

[0108] When game scenes change, the scene switching features are detected by image recognition algorithm. If the scene brightness changes by more than 30%, it is judged as a scene switch. According to preset thresholds, such as vibration frequency exceeding 5 times per second, light flashing frequency exceeding 3 times per second, and button operation frequency exceeding 10 times per second, it is judged as a high power consumption scene.

[0109] Feature extraction was performed on high power consumption scenario data, selecting features such as the average vibration frequency, the average light flashing frequency, and the average button operation frequency. A prediction model for high power consumption scenarios was trained, and a prediction model with an accuracy of 90% was obtained by using the support vector machine algorithm and 5-fold cross-validation.

[0110] When switching scenes, the current features are input into the prediction model to obtain the probability of high power consumption scenes. If the probability exceeds 0.8, it is judged as a high power consumption scene. Based on the probability of high power consumption scenes, fuzzy logic rules are set, such as a probability between 0.8 and 1 indicating a high power consumption trend, 0.6 to 0.8 indicating a medium power consumption trend, and 0.4 to 0.6 indicating a low power consumption trend. The power consumption trend level is calculated through a membership function. Finally, the game dynamically adjusts game parameters according to the power consumption trend level. For example, when there is a high power consumption trend, the special effects rendering intensity is reduced by 30% and the background music sound quality is reduced by 20% to optimize the game's power consumption.

[0111] Furthermore, the process of generating operation habit classification labels in step S2 is specifically as follows:

[0112] Based on the power consumption model, obtain the player's operation record data, and for each player's operation record data, calculate the frequency of various operations to obtain the operation frequency distribution;

[0113] Based on the operation frequency distribution, determine whether each type of operation is a high-frequency operation or a low-frequency operation. If the operation frequency is higher than a preset threshold, it is determined to be a high-frequency operation; otherwise, it is determined to be a low-frequency operation.

[0114] For the high-frequency and low-frequency operations, operation features are extracted respectively to obtain a high-frequency operation feature set and a low-frequency operation feature set;

[0115] Based on the high-frequency operation feature set and the low-frequency operation feature set, the player's operation habits are classified to obtain the operation habit classification result;

[0116] For each operation habit category, the average power consumption of players in that category is calculated to obtain the power consumption level of each operation habit category;

[0117] Based on the power consumption level of each operation habit category, a decision tree algorithm is used to generate operation habit category labels, resulting in an operation habit category label set. The player's operation habit category results are then matched with the operation habit category label set to obtain the operation habit category label for each player.

[0118] Based on the player's operation habit classification tags, the association rule algorithm is used to mine the frequent operation patterns under different operation habits, obtain the operation habit-frequent operation pattern mapping relationship, and store the operation habit-frequent operation pattern mapping relationship in the knowledge base. When the operation record data of new players arrives, their operation habit type can be quickly determined and their possible frequent operation patterns can be predicted, thereby realizing the real-time analysis of the impact of operation habits on power consumption.

[0119] Specifically, as shown in the following example, based on a pre-established power consumption model, the operation record data of 1000 players for a continuous week is obtained. For the operation record data of each player, the frequency of various operations is statistically analyzed to obtain the operation frequency distribution.

[0120] Based on the operation frequency distribution, a frequency threshold of 0.6 is set. If the operation frequency is higher than 0.6, it is identified as a high-frequency operation; otherwise, it is identified as a low-frequency operation. For high-frequency and low-frequency operations, 100-dimensional operation feature vectors are extracted respectively to obtain the high-frequency operation feature set and the low-frequency operation feature set.

[0121] Based on the high-frequency operation feature set and the low-frequency operation feature set, the K-Means clustering algorithm is used to classify the players' operation habits. The number of clusters is set to K=4, resulting in 4 categories of operation habits. For each operation habit category, the average power consumption of players in that category is calculated to obtain the power consumption level of each operation habit category.

[0122] Based on the power consumption levels of each operation habit category, the CART decision tree algorithm is used to generate operation habit category labels, resulting in a set of operation habit category labels, including heavy players, medium players, light players, and casual players. The operation habit category results of players are matched with the operation habit category label set to obtain the operation habit category label for each player.

[0123] Based on the player's operation habits, the Apriori association rule algorithm is used to mine frequent operation patterns under different operation habits. The minimum support is set to 0.5 and the minimum confidence is set to 0.8 to obtain the mapping relationship between operation habits and frequent operation patterns. For example, heavy players are used to playing games continuously for more than 3 hours, and moderate players are used to playing games for 1-2 hours each time.

[0124] The mapping relationship between operation habits and frequent operation patterns is stored in the Redis knowledge base. When the operation record data of a new player arrives, the operation habit type is quickly determined, and the possible frequent operation patterns are predicted by combining the mapping relationship in the knowledge base, thereby realizing real-time analysis of the impact of operation habits on power consumption.

[0125] Furthermore, the process of dynamically adjusting the time interval threshold of the standby mode in step S3 is specifically as follows:

[0126] Based on the pre-established correspondence between operation frequency and time interval threshold, the player's real-time operation data is obtained, and the player's current operation frequency is determined through data analysis;

[0127] Determine whether the player's operation frequency is high-frequency or low-frequency. If it is high-frequency, set the standby mode time interval to a longer interval; if it is low-frequency, set the standby mode time interval to a shorter interval.

[0128] Clustering algorithms are used to classify the players' operating habits and obtain typical behavior patterns under different operating habits;

[0129] For each typical behavior pattern, the association rule mining algorithm is used to analyze its correlation with changes in the game scene, and to obtain the scene change trend under different behavior patterns;

[0130] The time interval threshold of the standby mode is dynamically adjusted according to the changing trend of the scenario;

[0131] The adjusted time interval setting is applied to the standby mode to adaptively adjust the standby mode time interval according to the dynamic changes in player operation habits and game scene. In standby mode, the player's operation behavior and changes in game scene are continuously monitored. If the player is detected to re-enter high-frequency operation or the scene changes significantly, the device is immediately woken up and exits standby mode.

[0132] Based on players' actual operation and game experience feedback, reinforcement learning algorithms are used to continuously optimize the trigger conditions and time interval thresholds of standby mode, forming an adaptive game power saving strategy that minimizes device power consumption while ensuring player experience.

[0133] Specifically, as shown in the following example, players are divided into three categories: casual, moderate, and heavy players using the K-means clustering algorithm. Casual players operate less than 10 times per minute, moderate players operate between 10 and 30 times per minute, and heavy players operate more than 30 times per minute.

[0134] Using the Apriori association rule mining algorithm to analyze the operational behavior of different types of players in different game scenarios, we found that casual players have an average operation interval of 15 seconds in exploration scenarios, which shortens to 5 seconds in combat scenarios; moderate players have an average operation interval of 10 seconds in exploration scenarios, which shortens to 3 seconds in combat scenarios; and hardcore players have an average operation interval of 5 seconds in exploration scenarios, which shortens to 1 second in combat scenarios.

[0135] Based on the player's real-time operation data, the player's current operation frequency is calculated. If the operation frequency is less than 15 times per minute, it is judged as low-frequency operation, and the standby interval is set to 30 seconds; if the operation frequency is more than 15 times per minute, it is judged as high-frequency operation, and the standby interval is set to 60 seconds.

[0136] By comprehensively analyzing the player's operation frequency, behavior patterns, and scene change trends using the decision tree algorithm, the standby interval is extended to 2 minutes when the player is in a low-frequency operation state for 5 consecutive minutes and the scene does not change; when the player's operation frequency suddenly increases and the scene changes frequently, the standby interval is shortened to 10 seconds.

[0137] In standby mode, if a sudden increase in the player's operation frequency is detected to exceed 20 times per minute or a change in the scene is detected, the device is immediately woken up and the standby time interval is reset to the default value. Using the Q-learning reinforcement learning algorithm, the trigger threshold and time interval of standby mode are continuously adjusted based on the player's actual operation and game experience feedback. Through 1000 rounds of iterative training, the optimal standby strategy is obtained, which reduces device power consumption by 20% while ensuring 95% player experience.

[0138] Furthermore, the process of determining the power consumption trend of the current scenario in step S4 is specifically as follows:

[0139] Acquire the trigger signal for game scene switching. If the scene switching signal is detected, start real-time monitoring of the controller vibration frequency, light flashing frequency, and button operation frequency.

[0140] Based on preset vibration frequency thresholds, light flashing frequency thresholds, and button operation frequency thresholds, determine whether the current controller vibration frequency, light flashing frequency, and button operation frequency exceed the thresholds.

[0141] If at least one of the controller vibration frequency, light flashing frequency, and button operation frequency exceeds a preset threshold, the current game scene is determined to be a high power consumption scene.

[0142] Specifically, for game scenarios identified as having high power consumption, a support vector machine algorithm is used to train a high power consumption scenario prediction model based on the controller vibration frequency, light flashing frequency, and button operation frequency data of historical high power consumption scenarios.

[0143] When switching game scenes, the current controller vibration frequency, light flashing frequency, and button operation frequency are input into the high power consumption scene prediction model to obtain the probability that the current scene is a high power consumption scene.

[0144] Based on the probability of high power consumption scenarios, different power consumption trend levels are set to obtain the power consumption trend level of the current game scenario. The power consumption trend level is then fed back to the game, and the game's power consumption is dynamically optimized by adjusting the intensity of special effects rendering and the quality of background music in the game scenario.

[0145] Acquire power consumption data of the game controller in different game scenarios, including vibration frequency, light flashing frequency, and button operation frequency, establish a power consumption model, and dynamically adjust the vibration intensity, light brightness, and button sensitivity of the game controller based on the power consumption model to reduce the power consumption of the game controller and extend the usage time of the game controller.

[0146] Specifically, as illustrated in the following example, when the game scene changes, the vibration frequency, light flashing frequency, and button operation frequency of the controller are monitored in real time and compared with preset thresholds. For example, the vibration frequency threshold is set to 100 times per minute, the light flashing frequency threshold is set to 50 times per minute, and the button operation frequency threshold is set to 200 times per minute. If any frequency exceeds the threshold, it is determined to be a high power consumption scene. Based on historical data, such as scenes with a vibration frequency of 120 times per minute, a light flashing frequency of 60 times per minute, and a button operation frequency of 250 times per minute, a high power consumption scene prediction model is trained using the support vector machine algorithm.

[0147] After the frequency data of the current scene is input into the model, the probability of a high power consumption scene is obtained, such as 0.8. Then, using a fuzzy logic algorithm, 0.8 is mapped to a preset power consumption trend level, such as "high". This level is fed back to the game, triggering optimization measures such as reducing the intensity of special effects rendering by 20% and the quality of background music by 30%. At the same time, power consumption data under different scenes is collected to build a power consumption model. For example, in a high power consumption scene, vibration intensity is reduced by 15%, light brightness is reduced by 10%, and button sensitivity is reduced by 5% to extend the gamepad's usage time.

[0148] Furthermore, the process of triggering the low-power mode in step S5 is specifically as follows:

[0149] Obtain power consumption data for the current scenario and compare it with a preset threshold. If the power consumption is lower than the threshold, trigger a low-power mode.

[0150] Based on the preset low-power strategy, the reduction range of vibration function and light flashing effect is determined, and the function degradation is achieved by controlling the power supply.

[0151] Gradually reduce the vibration frequency and light brightness until the lowest power consumption level is reached, while monitoring the trend of power consumption changes.

[0152] By fitting the functional relationship between power consumption, vibration frequency, and light brightness using the least squares method, a frequency reduction and dimming scheme is obtained.

[0153] By using a decision tree algorithm, and taking into account current scene characteristics and user habits, the trigger threshold of the low-power mode is dynamically adjusted.

[0154] Construct a Markov model to predict electricity consumption trends over a future period based on historical power consumption data, and make energy-saving decisions.

[0155] Continuously record user experience feedback in low power mode, use reinforcement learning algorithms to continuously optimize frequency reduction and dimming strategies, and seek a balance between energy saving and experience. If a game scene switching signal is detected, start real-time monitoring of the controller vibration frequency, light flashing frequency and button operation frequency to determine whether the current scene is a high power consumption scene.

[0156] Based on the probability of high power consumption scenarios, different power consumption trend levels are set, and the power consumption trend levels are fed back to the game. By adjusting the special effects rendering intensity and background music sound quality in the game scene, the power consumption of the game is dynamically optimized.

[0157] Specifically, as illustrated in the following example, a low-power mode is triggered when the power consumption data is below a preset threshold of 80%.

[0158] According to the preset strategy, the vibration frequency is reduced by 20% and the light brightness is reduced by 30%, and the function is degraded through PWM control.

[0159] The vibration frequency and light brightness were gradually reduced with a learning rate of 0.05 until the power consumption was reduced to below 50%. At the same time, the power consumption trend was monitored every 100ms. The power consumption was fitted with the function relationship between the vibration frequency and light brightness by the least squares method to obtain the optimal solution when the vibration frequency was reduced to 60Hz and the light brightness was reduced to 40%.

[0160] Using a decision tree algorithm, taking into account factors such as the current scene brightness and user operation frequency, the low power mode trigger threshold is dynamically adjusted to between 75% and 85%.

[0161] A Markov model is constructed to predict the power consumption trend in the next 30 minutes based on the power consumption data of the past hour. If the predicted power consumption drops below 60%, an energy-saving decision is initiated 5 minutes in advance.

[0162] Continuously recording user feedback in low-power mode, the system uses a Q-Learning reinforcement learning algorithm, with energy consumption and user experience as reward functions, to continuously optimize frequency reduction and dimming strategies, seeking a balance between energy saving and user experience. If a game scene switching signal is detected, the system monitors the controller vibration frequency, light flashing frequency, and button operation frequency in real time. A high-power-consumption scenario is identified when any one of the following exceeds 5Hz: vibration frequency, light flashing frequency, or button operation frequency. Based on the probability of high-power-consumption scenarios, three power consumption trend levels (low, medium, and high) are set and fed back to the game. By adjusting the intensity of special effects rendering and background music quality in the game scene, the system dynamically optimizes the game's power consumption.

[0163] Furthermore, the process of determining whether to exit the low-power standby mode in step S6, based on the environmental information of the controller, specifically involves:

[0164] Obtain the current environmental information of the controller, including temperature, humidity, light intensity, and noise data;

[0165] Based on the pre-set threshold ranges of environmental data in various dimensions, determine whether the current environment of the controller meets the normal working conditions;

[0166] If the current environment does not meet the conditions for the controller to work normally, the controller's low-power standby mode will be activated.

[0167] In the low-power standby mode, the controller's environmental data is periodically collected, and the environmental status of the controller in the future is predicted based on the trend of environmental data changes.

[0168] A correlation model between environmental data and controller power consumption is established using machine learning algorithms, and the standby time threshold of the low power mode is dynamically adjusted.

[0169] When the continuous standby time of the controller exceeds the standby time threshold, and the environmental prediction results indicate that the controller will remain in an unusable environment for a period of time in the future, the controller will exit the low-power standby mode and enter a sleep state.

[0170] If the environmental prediction results meet the normal working conditions of the controller and the current standby time does not exceed the threshold, then exit the low power standby mode and restore the normal working state of the controller.

[0171] Acquire historical operation data and real-time power consumption data of the controller to build a training dataset for training and optimizing machine learning algorithms;

[0172] Based on the actual usage and power consumption feedback of the controller, a reinforcement learning algorithm is used to continuously optimize the triggering conditions and time interval thresholds of the standby mode, forming an adaptive power management strategy to maximize the controller's battery life while ensuring a good user experience.

[0173] Specifically, as illustrated in the following example, the handle collects environmental data in real time through built-in temperature and humidity sensors, light sensors, and noise sensors, such as a temperature range of -10℃ to 50℃, a humidity range of 20% to 80%, a light intensity range of 100 lux to 1000 lux, and a noise range of 30 dB to 80 dB.

[0174] Based on preset temperature thresholds of -5℃ to 45℃, humidity thresholds of 30% to 70%, light intensity thresholds of 200 lux to 800 lux, and noise thresholds of 40 dB to 70 dB, the system determines whether the current environment meets the normal operating conditions of the controller. If the environmental data exceeds the threshold range, such as a temperature of -8℃, humidity of 85%, light intensity of 50 lux, and noise of 90 dB, a low-power standby mode is triggered.

[0175] In standby mode, the controller collects environmental data every 10 minutes. The data change trend is analyzed by the moving average algorithm to predict the environmental state in the next 30 minutes. At the same time, the decision tree algorithm is used to establish a correlation model between environmental data and controller power consumption. According to the statistical analysis of historical data, the average power consumption of the controller is 0.5W in an environment with temperature below -5℃, humidity above 80%, light intensity below 100 lux, and noise above 80dB. Based on this, the standby time threshold is dynamically adjusted to 30 minutes.

[0176] If the controller remains in standby mode for more than 30 minutes and the environmental prediction results indicate that the controller will remain in an unusable environment for the next 30 minutes, the controller will enter a deep sleep state and the power consumption will drop to 0.1W. If the environmental prediction results indicate that the controller can resume normal operation within the next 30 minutes and the current standby time has not exceeded 30 minutes, the controller will exit the low power standby mode and resume normal operation.

[0177] By sampling historical operation data and real-time power consumption data of the controller, a training set and a test set are constructed. The gradient boosting decision tree algorithm is used for training to obtain an optimized low-power standby strategy.

[0178] Based on the actual usage and power consumption feedback of the controller, the Q-Learning reinforcement learning algorithm is adopted to optimize the controller's power management by extending battery life and ensuring user experience. Through continuous trial and learning, the low-power standby strategy is dynamically adjusted.

[0179] Furthermore, the process of allocating power resources in step S7 is specifically as follows:

[0180] The controller receives operation signals and determines whether it is in low-power standby mode. If so, it enters continuous monitoring mode; otherwise, it remains in normal working mode.

[0181] Under continuous monitoring, a convolutional neural network algorithm is used to extract features from the handle operation signals to obtain operation feature vectors.

[0182] Based on the pre-established game scene model and player operation habit model, the operation feature vectors are classified to determine the current game scene type and player operation habit type;

[0183] For different game scenario types and player operation habits, a decision tree algorithm is used to generate corresponding power resource allocation strategies;

[0184] The power resource allocation strategy is converted into control commands and sent to the power management module of the controller through the controller's communication interface;

[0185] The power management module adjusts the operating voltage and clock frequency of each hardware module according to the received control commands;

[0186] When the controller exits low-power standby mode, restore the default operating parameters of each hardware module;

[0187] Acquire historical operation data and real-time power consumption data of the device to build a training dataset for continuous training and optimization of machine learning algorithms;

[0188] Through continuous training and iterative optimization of machine learning algorithms, the intelligence level of power management strategies is continuously improved.

[0189] Specifically, as described in the following example, the operation signal of the controller can be obtained by a sensor with a sampling frequency of 1000Hz. If the average value of the sampled data is less than 0.1, the controller is determined to be in a low-power standby mode and enters a continuous monitoring state. In the continuous monitoring state, a 5-layer convolutional neural network is used to extract features from the controller operation signal to obtain a 128-dimensional operation feature vector.

[0190] Based on a pre-established model containing 100 game scenarios and 50 player operation habits, the operation feature vectors are classified to determine the current game scenario type and player operation habit type. For different game scenario types and player operation habit types, a decision tree algorithm with a maximum depth of 5 is used to generate corresponding power resource allocation strategies. For example, for shooting games and aggressive players, 80% of the power resources are allocated to the GPU and CPU.

[0191] The power resource allocation strategy is converted into 16-byte control commands and sent to the controller's power management module via a 2.4GHz wireless communication interface. Based on the received control commands, the power management module adjusts the GPU's operating voltage to 1.2V and its clock frequency to 1.5GHz, achieving intelligent power resource allocation. When the controller exits low-power standby mode, the operating voltage and clock frequency of each hardware module are restored to their default values, such as the GPU's default operating voltage of 0.9V and default clock frequency of 1GHz.

[0192] We acquire the device's operation data and real-time power consumption data from the past week, and construct a training dataset containing 10,000 records for continuous training and optimization of support vector machine and reinforcement learning algorithms.

[0193] Through continuous training and iterative optimization of machine learning algorithms, the average standby power consumption of the controller is reduced by 20% while ensuring the controller response time is below 50 milliseconds, thereby maximizing the device's battery life and ensuring a good user experience.

[0194] Furthermore, this method also includes:

[0195] S8. Dynamically adjust the time interval threshold of the standby mode, and optimize the power management strategy by combining historical operation data and current power consumption trends.

[0196] The process of optimizing the power management strategy in step S8 is as follows:

[0197] Acquire historical operation data and real-time power consumption data of the device to construct a training dataset;

[0198] The decision tree algorithm is used to dynamically adjust the time interval threshold of the standby mode based on the historical operation data and real-time power consumption trend, so as to obtain the optimized threshold parameter.

[0199] By using the support vector machine algorithm, historical data and real-time trends are comprehensively analyzed to determine the current usage status and power consumption level of the device, and to determine whether to trigger standby mode.

[0200] If the current idle time of the device exceeds the optimized time interval threshold and the power consumption level is low, it will automatically enter standby mode to reduce power consumption.

[0201] In the standby mode, the device's operation behavior and power consumption changes are continuously monitored. If user operation or a sudden increase in power consumption is detected, the device is woken up and exits the standby mode.

[0202] Based on the actual usage of the equipment and power consumption feedback, reinforcement learning algorithms are used to continuously optimize the triggering conditions and time interval thresholds of the standby mode, forming an adaptive power management strategy.

[0203] Through continuous training and iterative optimization of machine learning algorithms, the intelligence level of power management strategies is continuously improved, maximizing the battery life of devices while ensuring a good user experience.

[0204] Clustering algorithms are used to classify users' operating habits and obtain typical behavior patterns under different operating habits. For each typical behavior pattern, association rule mining algorithms are used to analyze its correlation with changes in device usage scenarios and obtain the scenario change trend under different behavior patterns.

[0205] The standby mode time interval threshold is dynamically adjusted according to the changing trend of the scenario. When the trend indicates that the user may enter a high-frequency operation scenario, the time interval is extended accordingly, and when the trend indicates that the user may enter a low-frequency operation scenario, the time interval is shortened accordingly. This achieves dynamic adjustment of the standby mode time interval based on the user's operating habits and usage scenarios, further optimizing the power management strategy.

[0206] Specifically, as illustrated in the following example, by collecting the device's operation data and power consumption records over the past month, sampling every 5 minutes, a training dataset containing 10,000 samples is constructed. Using the ID3 decision tree algorithm, with operation frequency and power consumption level as features and whether or not the device enters standby mode as the target variable, the optimal splitting attribute is selected through information gain ratio, and a decision tree is recursively constructed to obtain the optimal parameters when the standby time interval threshold is 10 minutes.

[0207] The SVM (Support Vector Machine) algorithm is used, with the operation data and power consumption data of the most recent hour as input. The data is mapped to a high-dimensional space through the Gaussian kernel function to find the maximum margin hyperplane and determine the current device status. If the idle time exceeds 10 minutes and the power consumption level is less than 20%, it will automatically enter standby mode.

[0208] In standby mode, the device status is checked every 30 seconds. If user operation or power consumption increases by more than 30%, the device will be woken up immediately.

[0209] Based on device usage and power consumption feedback, the Q-Learning reinforcement learning algorithm is adopted, with standby time interval and trigger conditions as actions and device usage experience and battery life as rewards. Through continuous trial and error and learning, the standby strategy is optimized, such as shortening the time interval to 5 minutes and adjusting the trigger condition to idle time exceeding 5 minutes and power consumption level below 15%.

[0210] Through seven consecutive days of algorithm training and parameter tuning, the accuracy of the power management strategy improved from 85% to 95%, the average standby time of the device increased by 20%, and the battery life improved by 10%. Using the K-Means clustering algorithm, based on the frequency and duration of user operations over a week, the operating habits of 1000 users were clustered to obtain three typical behavioral patterns: light use, moderate use, and heavy use. For each behavioral pattern, the Apriori association rule mining algorithm was used to analyze the correlation between operating habits and usage scenarios. It was found that in the light use mode, users often enter long standby periods at night, while in the heavy use mode, users frequently operate the device during the day and rarely enter standby.

[0211] Based on the association rules, the standby time interval is dynamically adjusted. For example, in light use mode, the interval is extended to 30 minutes, and in heavy use mode, the interval is shortened to 2 minutes, thus achieving adaptive power management.

[0212] This embodiment also includes:

[0213] S9: Based on real-time battery life data and combined with power management strategies, dynamically adjust the power supply intensity of vibration function and light flashing to ensure that the gaming experience is not affected.

[0214] The process of dynamically adjusting the power supply intensity for the vibration function and the flashing lights is as follows:

[0215] Obtain real-time battery life data, including current battery level, voltage, current and other parameters, and use machine learning algorithms such as support vector machines or neural networks, combined with historical data, to predict battery life under different usage scenarios.

[0216] Based on the predicted battery life, the power supply voltage and current of the vibration motor and LED lights are dynamically adjusted. When the battery life is short, the power supply intensity is reduced to weaken the vibration and lighting effects; when the battery life is sufficient, the power supply intensity is increased to enhance the vibration and lighting effects and ensure a good gaming experience.

[0217] By using machine learning algorithms such as decision trees or association rule mining, we can analyze players' preferences for vibration and lighting effects in different game scenarios, adjust power supply strategies accordingly, and enhance the effects in key scenarios to improve the gaming experience.

[0218] Establish a power management strategy knowledge base, and set corresponding vibration and lighting power supply strategies for different battery life states and gaming scenarios to achieve rapid matching and dynamic adjustment of strategies;

[0219] The system monitors battery level changes in real time during gameplay. When the battery level falls below a preset threshold, it triggers adjustments to the power management strategy, reducing vibration and lighting effects and extending gameplay time until the battery is depleted.

[0220] Record battery life data and power management strategies during each game session, and continuously optimize strategies through machine learning algorithms such as reinforcement learning to maximize battery life while ensuring a good gaming experience.

[0221] By analyzing user feedback and game data, we evaluate the effectiveness of power management strategies and their impact on vibration and lighting effects. We continuously improve the algorithm model and strategy knowledge base to achieve continuous optimization of power management. If the current idle time of the device exceeds the optimized time interval threshold and the power consumption level is low, it will automatically enter standby mode to reduce power consumption.

[0222] In standby mode, the device's operation behavior and power consumption changes are continuously monitored. If user operation or a sudden increase in power consumption is detected, the device is immediately woken up and exits standby mode.

[0223] Through continuous training and iterative optimization of machine learning algorithms, the intelligence level of power management strategies is continuously improved, maximizing the battery life of devices while ensuring a good user experience.

[0224] Specifically, as illustrated in the following example, by acquiring real-time battery life data, including parameters such as current battery level, voltage, and current, the support vector machine algorithm is used in conjunction with historical data to predict the battery life under different usage scenarios. For example, when the current is 500mA and the voltage is 3.7V, the predicted battery life is 3 hours.

[0225] Based on the predicted battery life, the power supply voltage and current of the vibration motor and LED lights are dynamically adjusted. When the battery life is less than 2 hours, the power supply voltage of the vibration motor is reduced from 3.3V to 2.5V, and the power supply current of the LED lights is reduced from 20mA to 10mA. When the battery life exceeds 4 hours, the power supply voltage of the vibration motor is increased to 3.7V, and the power supply current of the LED lights is increased to 30mA.

[0226] The decision tree algorithm was used to analyze players' preferences for vibration and lighting effects in different game scenarios. For example, in combat scenarios, 80% of players prefer strong vibration effects and bright lighting effects. Therefore, in this scenario, the power supply voltage of the vibration motor was increased by 20% and the power supply current of the LED lights was increased by 30%.

[0227] Establish a power management strategy knowledge base and set corresponding vibration and lighting power supply strategies for different battery life states and game scenarios. For example, when the battery power is below 30% and the game is in an exploration scenario, reduce the power supply voltage of the vibration motor by 30% and the power supply current of the LED light by 50%.

[0228] The system monitors battery level changes in real time during gameplay. When the battery level drops below 20%, it triggers an adjustment to the power management strategy, reducing the power supply voltage of the vibration motor by 50% and the power supply current of the LED lights by 80%, thereby extending gameplay time.

[0229] Record battery life data and power management strategies during each game session, and optimize the strategies through reinforcement learning algorithms, such as Q-learning, to continuously adjust the weights of vibration and lighting effects with battery life, so as to maximize battery life while ensuring the gaming experience.

[0230] By analyzing user feedback and game data, the effectiveness of power management strategies and their impact on vibration and lighting effects are evaluated. Using neural network algorithms, the strategy knowledge base is continuously improved to achieve continuous optimization of power management. If the device's idle time exceeds 10 minutes and its power consumption is below 50mW, it automatically enters standby mode to reduce power consumption.

[0231] In standby mode, the device's operation behavior and power consumption changes are monitored every 30 seconds. If user operation or power consumption increases by more than 100mW, the device is immediately woken up and exits standby mode.

[0232] Through continuous training and iterative optimization of machine learning algorithms, the power management strategy is automatically updated every 7 days to continuously improve the intelligence level of the strategy, maximize the battery life of the device, and ensure the user experience.

[0233] This embodiment achieves significant technical results through refined data analysis and intelligent decision-making. Firstly, by constructing a precise power consumption model, the system can accurately predict power consumption in different game scenarios, providing a scientific basis for subsequent power management strategies. This model is based on a multiple linear regression algorithm and is continuously optimized using techniques such as cross-validation, ensuring the reliability and accuracy of the prediction results.

[0234] Secondly, this method can deeply analyze players' operating habits and generate operation habit classification tags, thereby achieving personalized power management. The system dynamically adjusts the standby mode time interval threshold based on different players' operation frequency and habits, ensuring that power consumption is minimized without affecting the gaming experience. For example, for players with high-frequency operations, the system will appropriately extend the standby time interval to avoid power waste caused by frequent wake-ups; while for players with low-frequency operations, the standby time interval will be shortened to promptly enter low-power mode and save power.

[0235] Furthermore, by monitoring the controller's vibration frequency, light flashing frequency, and button operation frequency in real time during game scene transitions, the system can quickly determine the power consumption trend of the current scene. Once power consumption is detected to be below a preset threshold, the system will automatically trigger a low-power mode, reducing the power supply to the vibration function and light flashing, further optimizing power management. At the same time, the system will also determine whether to exit the low-power standby mode based on environmental information, ensuring that the controller maintains optimal power management in different environments.

[0236] In low-power standby mode, the system continuously monitors the controller's input signals and intelligently allocates power resources based on the current game scenario and the player's operating habits. Through convolutional neural network and decision tree algorithms, the system generates corresponding power resource allocation strategies to ensure the controller's basic functions operate normally while minimizing power consumption. Furthermore, the system continuously improves the intelligence of its power management strategies through ongoing training and optimization of machine learning algorithms to adapt to ever-changing usage scenarios and player needs.

[0237] In summary, this embodiment achieves efficient and intelligent management of the game controller's power supply through a series of innovative technologies and strategies. This not only extends the game controller's usage time and improves power utilization efficiency, but also enhances the player's gaming experience, demonstrating significant practical application value.

[0238] Example 2

[0239] like Figure 2 As shown, this embodiment provides a game controller power management system, including a power management module, a data acquisition and processing module, and a data analysis and model building module;

[0240] The power management module controls the power on and off of the controller and the switching of different power consumption states according to the triggering and exiting conditions of the low power mode.

[0241] According to the preset low-power strategy, the power supply of vibration function and light flashing is reduced, and the operating voltage and clock frequency of each hardware module are adjusted.

[0242] Dynamically adjust the time interval threshold of standby mode to optimize power management strategy;

[0243] The data acquisition and processing module collects power consumption data of the game controller in different game scenarios, as well as player operation record data and environmental information of the controller, and preprocesses the collected data.

[0244] The processed data is transmitted to the power management module and the data analysis and model building module to provide data support for the formulation and optimization of power management strategies.

[0245] The data analysis and model building module constructs an initial power consumption model based on the preprocessed game controller power consumption data and evaluates the model performance.

[0246] Based on the power consumption model, we analyze the impact of players' operating habits on power consumption and statistically analyze the power consumption levels of each category.

[0247] Analyze the correlation between player operating habits and changes in game scenarios;

[0248] Construct a Markov model to assist the power management module in making energy-saving decisions;

[0249] Establish a correlation model between environmental data and controller power consumption to support dynamic adjustment of the standby time threshold of low power mode.

[0250] This embodiment significantly improves the intelligence level of power management through precise power consumption modeling and real-time dynamic adjustment strategies, effectively reducing the power consumption of the controller and greatly extending standby and usage time. The system comprehensively considers environmental factors and player operating habits, providing personalized power management solutions that achieve energy saving while ensuring a smooth gaming experience. This enhances system adaptability and stability, continuously optimizing strategies to cope with usage changes, thereby significantly improving user experience and satisfaction. Players can enjoy a more stable, longer-lasting, and personalized gaming control experience without worrying about battery life.

[0251] The specific embodiments of the invention have been described in detail above, but these are merely examples. The invention is not limited to the specific embodiments described above. Those skilled in the art should understand that the embodiments and descriptions in the specification are only illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A power management method for a game controller, characterized in that, Includes the following steps: S1. Obtain power consumption data of the game controller in different game scenarios and build a power consumption model; S2. Based on the power consumption model, analyze the impact of player operation habits on power consumption and generate operation habit classification tags; S3. Based on user habits, categorized tags, and changing trends in game scenarios, dynamically adjust the time interval threshold of standby mode. S4. Monitor the use of the controller's vibration function, the frequency of light flashing, and the frequency of button operation when switching game scenes to determine the power consumption trend of the current scene. S5. If the power consumption trend of the current scene is lower than the preset threshold, the low power mode is triggered to reduce the power supply of the vibration function and the light flashing. S6. Based on the time interval threshold of the standby mode and the environmental information of the controller, determine whether to exit the low power mode. S7. In low power mode, monitor the controller's operation signals and allocate power resources according to the current game scenario and the player's operation habits; The process of dynamically adjusting the time interval threshold of the standby mode in step S3 is as follows: Based on the pre-established correspondence between operation frequency and time interval threshold, the player's real-time operation data is obtained, and the player's current operation frequency is determined through data analysis; Determine whether the player's operation frequency is high-frequency or low-frequency. If it is high-frequency, set the standby mode time interval to a longer interval; if it is low-frequency, set the standby mode time interval to a shorter interval. Clustering algorithms are used to classify the players' operating habits and obtain typical behavior patterns under different operating habits; For each typical behavior pattern, the association rule mining algorithm is used to analyze its correlation with changes in the game scene, and to obtain the scene change trend under different behavior patterns; The time interval threshold of the standby mode is dynamically adjusted according to the changing trend of the scenario.

2. The power management method for a game controller according to claim 1, characterized in that, The process of constructing the power consumption model in step S1 is as follows: Data on the vibration frequency, light flashing frequency, and button operation frequency of the game controller in different game scenarios are acquired, and the data is preprocessed. Based on the preprocessed power consumption data of the game controller, an initial power consumption model is constructed. The vibration frequency, light flashing frequency, and button operation frequency are used as independent variables, and power consumption is used as the dependent variable. The coefficients of the regression model are fitted by the least squares method. The initial power consumption model is evaluated by calculating the mean square error and coefficient of determination to determine the model's fit and predictive ability. If the model performance does not meet the requirements, a regularization term is introduced to control the model complexity, and a support vector machine is attempted. By comparing the performance of different algorithms, the modeling method is selected.

3. The power management method for a game controller according to claim 1, characterized in that, The process of generating operation habit classification tags in step S2 is as follows: Based on the power consumption model, obtain the player's operation record data, and for each player's operation record data, calculate the frequency of various operations to obtain the operation frequency distribution; Based on the operation frequency distribution, determine whether each type of operation is a high-frequency operation or a low-frequency operation. If the operation frequency is higher than a preset threshold, it is determined to be a high-frequency operation; otherwise, it is determined to be a low-frequency operation. For the high-frequency and low-frequency operations, operation features are extracted respectively to obtain a high-frequency operation feature set and a low-frequency operation feature set; Based on the high-frequency operation feature set and the low-frequency operation feature set, the player's operation habits are classified to obtain the operation habit classification result; For each operation habit category, the average power consumption of players in that category is calculated to obtain the power consumption level of each operation habit category.

4. The power management method for a game controller according to claim 1, characterized in that, The process of determining the power consumption trend of the current scenario in step S4 is as follows: Acquire the trigger signal for game scene switching. If the scene switching signal is detected, start real-time monitoring of the controller vibration frequency, light flashing frequency, and button operation frequency. Based on preset vibration frequency thresholds, light flashing frequency thresholds, and button operation frequency thresholds, determine whether the current controller vibration frequency, light flashing frequency, and button operation frequency exceed the thresholds. If at least one of the controller vibration frequency, light flashing frequency, and button operation frequency exceeds a preset threshold, the current game scene is determined to be a high power consumption scene. Specifically, for game scenarios identified as having high power consumption, a support vector machine algorithm is used to train a high power consumption scenario prediction model based on controller vibration frequency, light flashing frequency, and button operation frequency data from historical high power consumption scenarios.

5. The power management method for a game controller according to claim 1, characterized in that, The process of triggering the low-power mode in step S5 is as follows: Obtain power consumption data for the current scenario and compare it with a preset threshold. If the power consumption is lower than the threshold, trigger a low-power mode. Based on the preset low-power strategy, the reduction range of vibration function and light flashing effect is determined, and the function degradation is achieved by controlling the power supply. Gradually reduce the vibration frequency and light brightness until the lowest power consumption level is reached, while monitoring the trend of power consumption changes. By fitting the functional relationship between power consumption, vibration frequency, and light brightness using the least squares method, a frequency reduction and dimming scheme is obtained. By using a decision tree algorithm, and taking into account current scene characteristics and user habits, the trigger threshold of the low-power mode is dynamically adjusted. A Markov model is constructed based on historical power consumption data to predict electricity consumption trends over a future period and make energy-saving decisions.

6. The power management method for a game controller according to claim 1, characterized in that, The process of determining whether to exit the low-power mode in step S6, based on the environmental information of the controller, is as follows: Obtain the current environmental information of the controller, including temperature, humidity, light intensity, and noise data; Based on the pre-set threshold ranges of environmental data in various dimensions, determine whether the current environment of the controller meets the normal working conditions; If the current environment does not meet the conditions for the controller to work normally, the controller's low-power mode will be activated. In the low-power mode, the controller's environmental data is periodically collected, and the environmental state of the controller in the future is predicted based on the trend of environmental data changes. A correlation model between environmental data and controller power consumption is established using machine learning algorithms, and the standby time threshold of the low power mode is dynamically adjusted. When the controller's continuous standby time exceeds the standby time threshold, and the environmental prediction results indicate that the controller will remain in an unusable environment for some time to come, the controller will exit the low-power mode and enter a sleep state.

7. The power management method for a game controller according to claim 1, characterized in that, The process of allocating power resources in step S7 is as follows: The controller receives operation signals and determines whether it is in low-power mode. If so, it enters continuous monitoring mode; otherwise, it remains in normal working mode. Under continuous monitoring, a convolutional neural network algorithm is used to extract features from the handle operation signals to obtain operation feature vectors. Based on the pre-established game scene model and player operation habit model, the operation feature vectors are classified to determine the current game scene type and player operation habit type; For different game scenario types and player operation habits, a decision tree algorithm is used to generate corresponding power resource allocation strategies; The power resource allocation strategy is converted into control commands and sent to the power management module of the controller through the controller's communication interface; The power management module adjusts the operating voltage and clock frequency of each hardware module according to the received control commands; When the controller exits low-power mode, restore the default operating parameters of each hardware module; Acquire historical operation data and real-time power consumption data of the device to build a training dataset for continuous training and optimization of machine learning algorithms; Through continuous training and iterative optimization of machine learning algorithms, the intelligence level of power management strategies is continuously improved.

8. The power management method for a game controller according to claim 1, characterized in that, Also includes: S8. Dynamically adjust the time interval threshold of the standby mode, and optimize the power management strategy by combining historical operation data and current power consumption trends. The process of optimizing the power management strategy in step S8 is as follows: Acquire historical operation data and real-time power consumption data of the device to construct a training dataset; The decision tree algorithm is used to dynamically adjust the time interval threshold of the standby mode based on the historical operation data and real-time power consumption trend, so as to obtain the optimized threshold parameter. By using the support vector machine algorithm, historical data and real-time trends are comprehensively analyzed to determine the current usage status and power consumption level of the device, and to determine whether to trigger standby mode. If the current idle time of the device exceeds the optimized time interval threshold and the power consumption level is low, it will automatically enter standby mode to reduce power consumption. In the standby mode, the device's operation behavior and power consumption changes are continuously monitored. If user operation or a sudden increase in power consumption is detected, the device is woken up and exits the standby mode.

9. A game controller power management system, characterized in that: It includes a power management module, a data acquisition and processing module, and a data analysis and model building module; The power management module controls the power on and off of the controller and the switching of different power consumption states according to the triggering and exiting conditions of the low power mode. According to the preset low-power strategy, the power supply of vibration function and light flashing is reduced, and the operating voltage and clock frequency of each hardware module are adjusted. Dynamically adjust the time interval threshold of standby mode to optimize power management strategy; The data acquisition and processing module collects power consumption data of the game controller in different game scenarios, as well as player operation record data and environmental information of the controller, and preprocesses the collected data. The processed data is transmitted to the power management module and the data analysis and model building module to provide data support for the formulation and optimization of power management strategies. The data analysis and model building module constructs an initial power consumption model based on the preprocessed game controller power consumption data and evaluates the model performance. Based on the power consumption model, we analyze the impact of players' operating habits on power consumption and statistically analyze the power consumption levels of each category. Analyze the correlation between player operating habits and changes in game scenarios; Construct a Markov model to assist the power management module in making energy-saving decisions; Establish a correlation model between environmental data and controller power consumption to support dynamic adjustment of the standby time threshold of low power mode.

Images