Training method and device for controlling intelligent mouse, equipment, storage medium and program product

Abstract

The invention discloses a training method and device for controlling an intelligent mouse, equipment, a storage medium and a program product, and relates to the technical field of game operation training. In the invention, a new game operation training method is provided, mouse operation content of a top player in a target game segment is recorded in advance, and then the target game segment is trained according to a training template composed of a game scene of the target game segment and the corresponding mouse operation content. The method comprises the steps that a target game segment is obtained, a game scene of the target game segment is reconstructed, mouse operation content is prompted, mouse operation triggered by a to-be-trained person and a learner of the game operation under the prompt of the mouse operation content is received, and next-step training guidance corresponding to the current mouse operation is further fed back. Compared with traditional electronic sports training, long-term repeated training does not need to be performed depending on a large number of random game scenes, and the target game operation in the to-be-trained target game scene is directly trained, so that the game operation training efficiency and training effect are improved.

Description

Technical Field

[0001] The present application relates to the technical field of game operation training, and in particular to a training method for controlling an intelligent mouse, a training device for controlling an intelligent mouse, a training equipment for controlling an intelligent mouse, a storage medium and a computer program product. Background Art

[0002] At present, the existing game operation training methods often rely on watching game videos or coaching guidance, and it is difficult to reproduce game scenes. It is necessary to rely on a large number of random game scenes for long-term repeated training in order to train the target game operations in the target game scenes to be trained, resulting in low game operation training efficiency and poor training results.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a training method for controlling an intelligent mouse, a training device for controlling an intelligent mouse, a training equipment for controlling an intelligent mouse, a storage medium and a computer program product, aiming to solve the technical problems of low efficiency and poor training effect of game operation training.

[0005] To achieve the above object, the present application proposes a training method for controlling an intelligent mouse, the training method for controlling an intelligent mouse comprising: Obtaining a training template for mouse operation, wherein the mouse operation content of the top players in the target game segment is pre-recorded, and the game scene of the target game segment and the corresponding mouse operation content are used as the training template; Based on the training template, reconstruct the game scene of the target game clip and provide prompts for the mouse operation content; Receive the mouse operation triggered by the prompt of the mouse operation content, and feedback the next step training guidance corresponding to the current mouse operation.

[0006] In one embodiment, the step of obtaining a training template for mouse operation includes: Get players' historical game performance data; Predicting the player's gaming weaknesses based on the historical gaming performance data, or determining the gaming differences from top players based on the historical gaming performance data; Determine a target training template targeting the game operation weaknesses or the game operation differences.

[0007] In one embodiment, the training method for controlling the intelligent mouse further includes: In real-time game battles, obtain the palm temperature and / or grip strength of the mouse; When the real-time game battle enters a preset intense scene, the mouse temperature is maintained at a preset temperature based on the palm temperature and / or the mouse sensitivity is maintained at a preset sensitivity based on the grip strength.

[0008] In one embodiment, the step of maintaining the mouse temperature at a preset temperature based on the palm temperature and / or maintaining the mouse sensitivity at a preset sensitivity based on the gripping force includes: If the palm temperature is higher than a preset upper temperature limit or lower than a preset lower temperature limit, maintaining the mouse temperature at a preset temperature; and / or, If the gripping force is greater than a preset upper pressure limit or lower than a preset lower pressure limit, the mouse sensitivity is maintained at the preset sensitivity.

[0009] In one embodiment, the training method for controlling the intelligent mouse further includes: The physiological signal and / or biomechanical signal of the user holding the mouse when using the mouse is collected by using the physiological signal sensor and / or biomechanical signal sensor preset in the mouse; wherein the physiological signal includes one or more of the electromyographic signal, neural electrical signal, hemodynamic signal, and skin electrical activity signal related to the use of the mouse, and the biomechanical signal includes one or more of the tendon vibration signal, joint angle signal, and pressure signal related to the use of the mouse; Based on the movement direction prediction model, the mouse movement direction corresponding to the physiological signal and / or the biomechanical signal is predicted.

[0010] In one embodiment, the step of predicting the mouse movement direction corresponding to the physiological signal and / or the biomechanical signal based on the movement direction prediction model comprises: Acquiring training data, wherein the training data includes historical physiological signals and / or historical biomechanical signals of a mouse holder when using the mouse within a historical period, and historical mouse movement directions corresponding to the historical physiological signals and / or historical biomechanical signals; Based on the training data, a moving direction prediction model is trained.

[0011] In addition, to achieve the above-mentioned purpose, the present application also proposes a training device for controlling an intelligent mouse, the training device for controlling an intelligent mouse comprising: An acquisition module, used to acquire a training template for mouse operation, wherein the mouse operation content of the top players in the target game segment is pre-recorded, and the game scene of the target game segment and the corresponding mouse operation content are used as the training template; A guiding module, used for reconstructing the game scene of the target game clip based on the training template, and providing prompts for the mouse operation content; The receiving module is used to receive the mouse operation triggered by the prompt of the mouse operation content, and to feed back the next step training instruction corresponding to the current mouse operation.

[0012] In addition, to achieve the above-mentioned purpose, the present application also proposes a training device for controlling an intelligent mouse, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the training method for controlling an intelligent mouse as described above.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the training method for controlling the intelligent mouse as described above are implemented.

[0014] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the training method for controlling an intelligent mouse as described above are implemented.

[0015] One or more technical solutions proposed in this application have at least the following technical effects: In the present application, a training method for controlling an intelligent mouse, i.e., a new game operation training method, is proposed. The mouse operation content of top players in a target game segment is pre-recorded. Then, based on a training template composed of the game scene of the target game segment and the corresponding mouse operation content, the game scene of the target game segment is reconstructed and prompts for the mouse operation content are given. Then, the mouse operation triggered by the trainee or learner of the game operation under the prompt of the mouse operation content is received, and further feedback is given on the next training instruction corresponding to the current mouse operation.

[0016] Therefore, by collecting the operation data of top players and reconstructing the corresponding scenes, real-time feedback and guidance are given to the mouse operations of the trainees during their learning, allowing the trainees to learn the mouse operations of the top players in the target game clips. Compared with traditional e-sports training, there is no need to rely on a large number of random game scenes for long-term repetitive training, but direct training on the target game operations in the target game scenes to be trained, thereby improving the efficiency and training effect of game operation training. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 A flowchart diagram of the first embodiment of the training method for controlling an intelligent mouse according to the present application; Figure 2 A flowchart diagram of a second embodiment of a training method for controlling an intelligent mouse according to the present application; Figure 3 A flowchart diagram of a third embodiment of a training method for controlling an intelligent mouse according to the present application; Figure 4 This is a schematic diagram of the module structure of a training device for controlling an intelligent mouse according to an embodiment of the present application; Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the training method for controlling an intelligent mouse in an embodiment of the present application.

[0020] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0022] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0023] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a training device for controlling an intelligent mouse, etc. The following takes a training device for controlling an intelligent mouse as an example to illustrate this embodiment and the following embodiments.

[0024] Based on this, the present application embodiment provides a training method for controlling an intelligent mouse, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the training method for controlling an intelligent mouse of the present application.

[0025] In this embodiment, the training method for controlling the intelligent mouse includes steps S10 to S30: Step S10, obtaining a training template for mouse operation, wherein the mouse operation content of the top players in the target game segment is pre-recorded, and the game scene of the target game segment and the corresponding mouse operation content are used as the training template; Regarding the target game clip, the mouse operation content of the top player in the target game clip can be recorded, and the game scene and mouse operation content of the target game clip can be used as a training template; it can also be a clip in a game competition, or a clip in a game played by the top player in a relaxed state. In this embodiment, the selection and recording method of the target game clip is not limited.

[0026] Regarding mouse operation content, when recording the operation rhythm of top players to generate training templates, the following indicators related to mouse operation can be used as mouse operation content: 1. Mouse movement indicators, such as mouse movement speed: The mouse movement speed of top players is usually fast and stable. It is necessary to accurately record their movement speed in different operation scenarios in order to analyze their operation rhythm and reaction ability. For example, mouse movement trajectory: including straight lines, curves, broken lines, etc., as well as transition trajectories between different operations, which helps to understand the operation habits and strategies of top players. For example, the acceleration and deceleration of the mouse: When top players operate the mouse, the changes in their acceleration and deceleration also have certain regularity. It is necessary to record these data to analyze the fluency and rhythm of their operations.

[0027] 2. Mouse click indicators, such as mouse click frequency: record the number of mouse clicks of top players in a unit of time, which can reflect the activity and rhythm of their operations. For example, mouse click position: the specific position where the top players click the mouse, especially the click position when performing precise operations, is very important for analyzing their operating skills and accuracy. For example, mouse click force: although the smart mouse cannot directly measure the click force, it can be inferred through some indirect methods, such as the sound when clicking, the vibration of the mouse, etc., which can reflect the operating style and habits of the top players.

[0028] 3. Operation consistency indicators, such as operation interval time: record the interval time between different operations of top players, which can reflect the consistency and rhythm of their operations. For example, operation sequence: the operation sequence of top players, especially the operation sequence when performing complex operations, helps to understand their operation strategies and skills.

[0029] 4. Other relevant indicators, such as equipment and environmental factors: Consider the impact of equipment and environmental factors on the player's operation, such as mouse sensitivity, screen resolution, game frame rate, etc., which can help analyze the player's operation performance more comprehensively.

[0030] The training template may be recorded by a top player on a first game operating device and then read by a trainee, a learner or a player on a second game operating device; there may be a template library for storing various training templates that meet the top player or highlight operation judgment criteria, so that any game operating device can read the training template from the template library. In this embodiment, the definition and production method of the training template are not limited.

[0031] In the training template, the game scene and the mouse operation content at each moment of the target game clip correspond in time sequence, that is, each frame of the game screen corresponds one-to-one with the mouse operation content at the corresponding moment.

[0032] In a feasible implementation manner, the step S10 includes: Get players' historical game performance data; Predicting a player's gaming weaknesses based on historical gaming performance data, or determining differences in gaming performance from top players based on historical gaming performance data; Identify targeted training templates that target game play weaknesses or game play differences.

[0033] To obtain training templates for mouse operations, each training template may be labeled in advance, and players may select a template based on the labeled label. Alternatively, training templates may be actively recommended to players based on their historical game performance data, wherein the aforementioned labels may be relied upon in the recommendation.

[0034] The player's historical game performance data may include the following aspects (the statistical dimensions and inspection dimensions of the player's historical game performance data are different for different games): 1. Operational details data. For example, APM (operations per minute): including the proportion of effective operations (such as attack commands, skill releases) and invalid operations (such as repeated clicks, wrong operations). For example, skill release accuracy: for example, the hit rate of key skills in MOBA games, or the headshot rate in FPS games. For example, movement trajectory: through heat maps, analyze whether the player's movement path in specific scenarios (such as team battles, retreats) exposes habitual loopholes (such as fixed detours that are easy to predict). For example, click accuracy: the number of misclicks per unit time (such as accidentally touching non-target units or terrain). For example, multi-threaded operation capabilities: in RTS games, the efficiency of controlling multiple units or fronts at the same time.

[0035] 2. Tactical and strategic data. For example, the response time to key events: how long it takes to place a ward for reconnaissance after the enemy hero disappears, or the speed of team assembly when the boss refreshes. For example, the rationality of resource allocation: economic conversion rate, resource waste rate (such as skill cooldowns or props that are not used in time). For example, map control ability: vision coverage, wild area / resource point occupation efficiency. For example, target priority: whether the choice of pushing towers, grabbing dragons, and killing is in line with the optimal strategy (compared with the decision tree model of top players).

[0036] 3. Competitive performance data. For example, 1v1 win rate: the laning suppression power of a specific hero / character. For example, survivability: the average number of deaths per game, the success rate of escaping from ganks. For example, team battle participation rate and contribution value: output ratio, control skill coverage, treatment / shield timeliness. For example, communication efficiency: the timeliness and accuracy of voice / signal marking.

[0037] 4. Psychological and stability data. For example, operational fluctuations in unfavorable situations: the rate of decision-making errors when the economy is lagging behind (such as blindly starting a team fight or conservatively avoiding a fight). For example, psychological inertia of winning streaks / losing streaks: whether there are overly aggressive operations after consecutive wins, or conservative operations after failures. For example, the speed of mastering tactics in new versions: for example, whether the change in the hero's win rate after the version update is higher than the average level. For example, the response to the opponent's targeted strategy: such as the speed of improving anti-gank awareness after being frequently ganked.

[0038] Regarding the player's historical game performance data, the real-time operation stream can be obtained through data collection tools, and then the player's operation habits can be classified through the K-means algorithm (such as "aggressive charge" or "conservative development"), or the LSTM network can be used to predict the player's operation tendency at a specific point in time.

[0039] When predicting a player's game operation weaknesses based on historical game performance data, first, define the weakness labels in the historical game performance data. This can be done through supervised learning labels such as those based on expert rules (such as "positioning error" is defined as "being hit by non-directional skills more than 3 times within 10 seconds") or player feedback annotations, or through unsupervised clustering: using K-means or DBSCAN to find groups with abnormal operation patterns (such as a group of players who frequently "greedyly attack" and die), and then select a model such as supervised learning, reinforcement learning, or graph neural network and train it to predict the player's game operation weaknesses corresponding to the historical game performance data.

[0040] When determining the difference in game operation with top players based on historical game performance data, the difference in game operation between the two can be determined through the mouse operation content in the same game clip. Generally, the game operation difference between players is determined based on the operation of top players.

[0041] In this embodiment, the method of predicting the player's game operation weaknesses based on historical game performance data and determining the difference in game operation from top players based on historical game performance data is not limited. The player's historical data can be combined to predict his or her operation weaknesses and push targeted training content (such as quick turn, micro-operation correction). A dynamic training plan can also be generated based on the difference between the player's real-time operation data and the template of the top player, such as special training for reaction speed or accuracy.

[0042] After determining the game operation weaknesses of the player or the differences between the player and the top players, a targeted training template for improving the game operation weaknesses or reducing the game operation differences can be determined based on the game operation weaknesses of the player or the differences between the player and the top players. In this way, the player can be trained based on the target training template.

[0043] Step S20, based on the training template, reconstructing the game scene of the target game clip and providing prompts for the mouse operation content; When reconstructing the game scene of the target game clip based on the training template, the top player's operation can be retained or excluded. If the key operation game scene and the highlight operation game scene before the top player's operation are retained and the influence of the top player's operation is eliminated, the top player's operation will not interfere or affect the player during training.

[0044] In addition, the trainees, learners or players can also play against the top players simulated by AI in real time in the reconstructed scene. That is, the trainees, learners or players can imitate the top players, or they can play against the top players. In other words, they can learn from the top players in the process of imitating them, or they can learn from the top players in the process of playing against them.

[0045] The prompts for the mouse operation content can be based on text, animation, explanation video in the game screen, voice prompts, mouse vibration, temperature change, light change, weak current, etc. Among them, tactile feedback such as mouse vibration can be added to prompt operation deviation, and sound prompts such as rhythm to guide click frequency and visual overlays such as trajectory lines to mark the optimal path can be added. In this embodiment, the prompt method is not limited.

[0046] Step S30, receiving the mouse operation triggered by the prompt of the mouse operation content, and feeding back the next step training guidance corresponding to the current mouse operation.

[0047] Regarding feedback, it can automatically determine whether the current mouse operation is similar or identical to the mouse operation in the training template, or it can assess whether the operation result of the current mouse operation reaches the operation result of the template mouse operation. At this time, the scoring model can score and determine whether retraining is needed or whether the next step of training can be entered based on the score. In addition, it is also possible to receive personalized customization of the scoring criteria. For example, if the training goal is to basically master the operations of top players, the passing score for entering the next step of training can be appropriately lowered. If the training goal is to fully master it, the passing score can be raised.

[0048] At present, in the existing game operation training methods, 1. It is often passive learning. Traditional e-sports training relies on watching game recordings or verbal guidance from coaches. Learners cannot practice operations in real game scenes and lack an immersive training environment for hand-eye coordination. For example, it is difficult to master the emergency stop and gun pressing skills of top players through video analysis. 2. Operation data is disconnected. Although existing analysis tools (such as Overwolf) can record macro data such as kill heat maps, they cannot accurately record mouse trajectories at the frame level, making it difficult for trainers to reproduce micro-operation details. 3. Technical bottlenecks in scene reproduction. Traditional game replay systems are limited by engine mechanisms and cannot achieve dynamic reconstruction of scenes. When trainers want to repeat exercises for specific situations, they can only rely on random matching. 4. Real-time feedback delay defects. Existing AI coaching systems (such as FPS Aim Trainer) use preset training modules and cannot dynamically adjust guidance strategies according to real-time operations. For example, when a trainer has a pre-aim deviation, the system can often only give post-statistics rather than immediate correction suggestions. 5. Inefficient muscle memory cultivation. Traditional training relies on a large number of repetitive battles and lacks decomposed training modules for specific operation chains, resulting in a long skill formation cycle.

[0049] In this embodiment, 1. Players can conduct active learning, allowing learners to practice operations in real game scenes reconstructed by training templates, and conduct immersive training environments for hand-eye coordination. 2. The linked operation data can record the mouse trajectory accurately at the frame level, and for the trainer, the micro-operation details can be reproduced. 3. When the trainer wants to repeat the practice for a specific situation, there is no need to rely on random matching, and dynamic reconstruction of the scene can be achieved. 4. Based on the real-time prompts of the mouse operation content, the operation guidance strategy can be dynamically adjusted, and timely correction suggestions can be made to the operation. 5. There is no need to rely on a large number of repeated battles. Decomposed training or continuous training can be carried out for specific operations. The skill formation cycle is short, and muscle memory is efficiently cultivated.

[0050] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the first embodiment can refer to the above introduction, and will not be repeated in the following. Figure 2 , Figure 2This is a flow chart of a second embodiment of the training method for controlling an intelligent mouse of the present application.

[0051] In this embodiment, the training method for controlling the intelligent mouse includes steps T10 to T20: Step T10: in a real-time game, obtaining the palm temperature and / or grip strength of a hand holding the mouse; Step T20: When the real-time game battle enters a preset intense scene, the mouse temperature is maintained at a preset temperature based on the palm temperature and / or the mouse sensitivity is maintained at a preset sensitivity based on the grip strength.

[0052] The temperature of the palm holding the mouse can be obtained through a temperature measurement solution integrated in the mouse, or through a professional temperature measurement device or a smart wearable device. In this embodiment, the method of obtaining the temperature of the palm holding the mouse is not limited.

[0053] Regarding the holding strength of the mouse, a thin-film pressure sensor array can be embedded in the surface of the mouse shell or the side button area to detect the pressure distribution of the finger contact points in real time, such as using a piezoelectric ceramic sensor (sensitivity can reach 0.1N) or a capacitive pressure sensor. It is also possible to collect electromyographic signals of the forearm muscles through a wristband device to infer the holding strength, such as decoding bioelectric signals through a machine learning model. It is also possible to use an infrared / optical sensor array to scan the palm contact surface morphology based on grip posture recognition technology, and combine a deep learning algorithm to establish a mapping relationship between grip strength and contact area. In this embodiment, the method of obtaining the holding strength of the mouse is not limited.

[0054] In this embodiment, a heating or cooling element, such as a small electric heater or a semiconductor cooling element, can be embedded inside the mouse to adjust the temperature of the mouse surface. When adjusting the temperature, the working state of the heating or cooling element is automatically adjusted by the preset temperature target value to ensure that the mouse temperature remains at the preset temperature or within the set range of the preset temperature. In addition, the palm temperature change trend can be analyzed to predict and adjust the mouse temperature in advance. By adjusting the mouse temperature, the overshoot and excitement of the player when the real-time game battle enters the preset intense scene can be avoided. At the same time, maintaining the mouse temperature can keep the hand comfortable and reduce sweating and fatigue. The comfortable feel brought by temperature adjustment helps players focus more on the game, improves operation accuracy and reaction speed, and thus optimizes game performance.

[0055] In this embodiment, a thin-film pressure sensor array is embedded in the mouse grip area (side skirts, under the buttons) to capture the grip strength of the thumb, ring finger / little finger area in real time and identify the user's operation intention (such as "light grip to move" vs. "heavy pressure to aim"). Furthermore, when the grip force is too strong, the mouse sensitivity is appropriately reduced, and when the grip force is too weak, the mouse sensitivity is appropriately increased, and the target is adjusted to the preset sensitivity. By dynamically adjusting the sensitivity of the mouse grip force, it is possible to avoid overshoot and excitement of players when the real-time game battle enters a preset intense scene, thereby significantly improving the operation accuracy and game performance.

[0056] In a feasible implementation manner, the step T20 includes: Step T201: if the palm temperature is higher than a preset upper temperature value or lower than a preset lower temperature value, maintaining the mouse temperature at a preset temperature; and / or, Step T202: If the gripping force is greater than the preset upper pressure limit or lower than the preset lower pressure limit, the mouse sensitivity is maintained at the preset sensitivity.

[0057] If the palm temperature is outside the preset temperature range, that is, higher than the preset temperature upper limit or lower than the preset temperature lower limit, the mouse temperature is maintained at the preset temperature; if the grip force is outside the preset pressure range, that is, greater than the preset pressure upper limit or lower than the preset pressure lower limit, the mouse sensitivity is maintained at the preset sensitivity.

[0058] In one embodiment, if the change rate of the palm temperature is higher than the preset temperature change rate, the mouse temperature is maintained at the preset temperature; and / or, if the change rate of the grip force is greater than the preset pressure change rate, the mouse sensitivity is maintained at the preset sensitivity.

[0059] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment can refer to the above introduction, and will not be repeated later. Figure 3 , Figure 3 This is a flow chart of a third embodiment of the training method for controlling an intelligent mouse of the present application.

[0060] In this embodiment, the training method for controlling the intelligent mouse includes steps P10 to P20: Step P10: collecting physiological signals and / or biomechanical signals of the user when using the mouse through the physiological signal sensor and / or biomechanical signal sensor preset in the mouse; wherein the physiological signal includes one or more of the electromyographic signal, neural electrical signal, hemodynamic signal, and skin electrical activity signal related to the use of the mouse, and the biomechanical signal includes one or more of the tendon vibration signal, joint angle signal, and pressure signal related to the use of the mouse; Step P20: Based on the movement direction prediction model, the mouse movement direction corresponding to the physiological signal and / or biomechanical signal is predicted.

[0061] Regarding physiological signals and myoelectric signals related to the use of a mouse, there is an action triggering sequence: about 50-200ms before muscle contraction, motor neurons release electrical pulses (action potentials), and related sensors can detect these microcurrents earlier than hand movements visible to the naked eye. In addition, there is also a directional correlation, and the activation patterns of different finger / wrist muscle groups are direction-specific. For example: the increase in the activity of the radial extensor carpi indicates that the mouse is moving to the right, and the increase in the signal of the ulnar flexor carpi may correspond to a trend of moving to the left.

[0062] Regarding physiological signals and neural electrical signals related to using a mouse, movement commands are transmitted from the brain to the muscles through nerve fibers. Implanting an ENG sensor at the wrist can capture signals 10-30ms earlier than EMG. For example, the pulse frequency of the median nerve is related to the index finger's clicking intention, and the ulnar nerve signal strength can predict the action of the little finger pressing the roller.

[0063] Regarding physiological signals and hemodynamic signals related to the use of a mouse, near-infrared spectroscopy (NIRS) is used to monitor the blood oxygen saturation of the forearm muscles. An increase in local blood flow (increased metabolic demand) can be detected 100-300ms before muscle contraction. For example, the blood flow acceleration before rapid movement is about 200ms earlier than the actual action. Continuous low blood oxygen status may indicate the risk of misoperation due to fatigue. The start of an action can be predicted by blood flow changes before muscle activity, and local temperature changes before muscle contraction can be captured by micro infrared sensors.

[0064] Regarding physiological signals and skin electrodermal activity signals related to the use of a mouse, by detecting changes in hand skin conductivity, it reflects the impact of emotional or attention fluctuations on operations (such as prediction of false touches when nervous).

[0065] As described above, the corresponding mouse movement direction can be predicted based on the movement direction prediction model through the predictive effect of electromyographic signals, the foresight of neural electrical signals, the indirect prediction of hemodynamic signals and skin electrical activity signals.

[0066] Regarding the physiological signals and tendon vibration signals related to the use of the mouse, the piezoelectric sensor is used to capture the subtle vibrations before the tendon contracts (before the actual muscle movement). Furthermore, the tendon will produce tiny vibrations (frequency 5-50Hz) due to nerve excitement before the muscle contracts, and the piezoelectric sensor can capture this vibration pattern. For example: high-frequency low-amplitude vibrations (>30Hz) are often accompanied by instantaneous acceleration (such as sharp turns in games); low-frequency vibrations (<10Hz) may correspond to fine-tuning (such as pixel-level movement in graphic design).

[0067] Regarding physiological signals and joint angle signals related to the use of a mouse, flexible strain sensors can be used to monitor the bending angle of the finger / wrist joints to predict click or drag actions. Inertial measurement units (IMUs) such as accelerometers and gyroscopes can also be used to detect hand micro-movement trends (such as the tilt of the wrist before flipping). Furthermore, the flexion / extension angle change rate of the wrist joint is monitored by a flexible strain sensor, and the trajectory is predicted in combination with the inverse kinematics algorithm. For example, when the wrist extension angular velocity exceeds 15° / s, there is an 80% probability of triggering the mouse to move down; the radial deviation (bending toward the thumb side) angle is linearly related to the lateral movement distance.

[0068] Regarding physiological signals and pressure signals related to using a mouse, the capacitive tactile array monitors the changes in pressure distribution between the palm and the mouse contact surface in real time to identify the grip mode (such as "grasp → fast movement"). Furthermore, the capacitive tactile array can analyze the contact mechanics characteristics such as the center of gravity offset and pressure gradient of the palm pressure distribution in real time. For example, when the pressure center of gravity offsets more than 5% to the right side of the mouse, the probability of right shift is 92%; a sudden increase in pressure in the thumb area and a decrease in pressure in the ring finger area may indicate a drag operation (which needs to be verified in combination with the cursor position).

[0069] As described above, the corresponding mouse movement direction can be predicted based on the movement direction prediction model through the tendon vibration signal, joint angle signal and pressure signal.

[0070] In a feasible implementation manner, the step T20 includes: Acquiring training data, wherein the training data includes historical physiological signals and / or historical biomechanical signals of a mouse holder when using the mouse in a historical period, and historical mouse movement directions corresponding to the historical physiological signals and / or historical biomechanical signals; Based on the training data, a moving direction prediction model is trained.

[0071] In terms of model architecture selection, you can choose a time series model such as LSTM (Long Short-Term Memory Network) that is suitable for capturing long-term dependencies and continuous physiological signals, or Transformer that processes long sequence data and is suitable for capturing complex time series relationships. You can also choose a sliding window model to convert time series data into a fixed-length window and use traditional machine learning models (such as SVM and random forest) for classification.

[0072] In the training phase, the model is trained using the training set, and appropriate optimization algorithms (such as Adam, SGD) and loss functions (such as cross entropy loss) are used. At the same time, model parameters such as learning rate, batch size, number of layers, etc. are optimized through grid search or random search to achieve hyperparameter tuning. In addition, the validation set is used to evaluate the model performance and adjust the model structure or hyperparameters to improve the accuracy.

[0073] In this way, a movement direction prediction model is trained based on the training data consisting of the historical physiological signals and / or historical biomechanical signals of the mouse holder when using the mouse within a historical period, and the historical mouse movement directions corresponding to the historical physiological signals and / or historical biomechanical signals.

[0074] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the training method for controlling an intelligent mouse of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0075] This application also provides a training device for controlling an intelligent mouse, please refer to Figure 4 , the training device for controlling the intelligent mouse comprises: An acquisition module 10 is used to acquire a training template for mouse operation, wherein the mouse operation content of the top players in the target game segment is pre-recorded, and the game scene of the target game segment and the corresponding mouse operation content are used as the training template; A guidance module 20, for reconstructing the game scene of the target game clip based on the training template, and providing prompts for mouse operation content; The receiving module 30 is used to receive the mouse operation triggered by the prompt of the mouse operation content, and to feed back the next step training instruction corresponding to the current mouse operation.

[0076] In one embodiment, the acquisition module 10 is further used for: Get players' historical game performance data; Predicting a player's gaming weaknesses based on historical gaming performance data, or determining differences in gaming performance from top players based on historical gaming performance data; Identify targeted training templates that target game play weaknesses or game play differences.

[0077] In one embodiment, the training device for controlling the intelligent mouse further includes an adjustment module for: In real-time game battles, obtain the palm temperature and / or grip strength of the mouse; When the real-time game battle enters a preset intense scene, the mouse temperature is maintained at a preset temperature based on the palm temperature and / or the mouse sensitivity is maintained at a preset sensitivity based on the grip strength.

[0078] In one embodiment, the adjustment module is further used for: If the palm temperature is higher than the preset upper temperature limit or lower than the preset lower temperature limit, maintaining the mouse temperature at the preset temperature; and / or, If the grip force is greater than the preset upper pressure limit or lower than the preset lower pressure limit, the mouse sensitivity is maintained at the preset sensitivity.

[0079] In one embodiment, the training device for controlling the intelligent mouse further includes a prediction module, which is used to: The physiological signals and / or biomechanical signals of the user holding the mouse when using the mouse are collected by using the physiological signal sensor and / or biomechanical signal sensor preset in the mouse; wherein the physiological signals include one or more of the electromyographic signals, neural electrical signals, hemodynamic signals, and skin electrical activity signals related to the use of the mouse, and the biomechanical signals include one or more of the tendon vibration signals, joint angle signals, and pressure signals related to the use of the mouse; Based on the movement direction prediction model, the mouse movement direction corresponding to the physiological signal and / or the biomechanical signal is predicted.

[0080] In one embodiment, the prediction module is further used for: Before the step of predicting the mouse movement direction corresponding to the physiological signal and / or biomechanical signal based on the movement direction prediction model: Acquiring training data, wherein the training data includes historical physiological signals and / or historical biomechanical signals of a mouse holder when using the mouse in a historical period, and historical mouse movement directions corresponding to the historical physiological signals and / or historical biomechanical signals; Based on the training data, a moving direction prediction model is trained.

[0081] The training device for controlling an intelligent mouse provided by the present application adopts the training method for controlling an intelligent mouse in the above-mentioned embodiment, and can solve the technical problems of low efficiency and poor training effect of game operation training. Compared with the prior art, the beneficial effects of the training device for controlling an intelligent mouse provided by the present application are the same as the beneficial effects of the training method for controlling an intelligent mouse provided by the above-mentioned embodiment, and other technical features in the training device for controlling an intelligent mouse are the same as the features disclosed in the above-mentioned embodiment method, and are not described in detail here.

[0082] The present application provides a training device for controlling an intelligent mouse, and the training device for controlling an intelligent mouse includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the training method for controlling the intelligent mouse in the above-mentioned embodiment.

[0083] Reference below Figure 5, which shows a schematic diagram of the structure of a training device for controlling an intelligent mouse suitable for implementing an embodiment of the present application. The training device for controlling an intelligent mouse in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The training device for controlling the intelligent mouse shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0084] like Figure 5 As shown, the training device for controlling the intelligent mouse may include a training device 1001 for controlling the intelligent mouse (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 to a random access memory 1004. In the random access memory 1004, various programs and data required for the operation of the training device for controlling the intelligent mouse are also stored. The training device 1001 for controlling the intelligent mouse, the read-only memory 1002, and the random access memory 1004 are connected to each other through a bus 1005. An input / output interface 1006 is also connected to the bus. Generally, the following systems can be connected to the input / output interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the training device for controlling the intelligent mouse to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows the training device for controlling the intelligent mouse with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have instead.

[0085] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the training device 1001 for controlling an intelligent mouse, the above functions defined in the method of the embodiments disclosed in the present application are executed.

[0086] The training device for controlling an intelligent mouse provided by the present application adopts the training method for controlling an intelligent mouse in the above embodiment, and can solve the technical problems of low efficiency and poor training effect of game operation training. Compared with the prior art, the beneficial effects of the training device for controlling an intelligent mouse provided by the present application are the same as the beneficial effects of the training method for controlling an intelligent mouse provided by the above embodiment, and other technical features of the training device for controlling an intelligent mouse are the same as those disclosed in the above embodiment method, and will not be described in detail here.

[0087] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0088] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0089] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, wherein the computer-readable program instructions are used to execute the training method for controlling an intelligent mouse in the above-mentioned embodiment.

[0090] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0091] The computer-readable storage medium may be included in the training device for controlling the intelligent mouse; or may exist independently without being assembled into the training device for controlling the intelligent mouse.

[0092] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the training device that controls the intelligent mouse, the training device that controls the intelligent mouse: obtains a training template for mouse operation, wherein the mouse operation content of top players in a target game segment is pre-recorded, and the game scene of the target game segment and the corresponding mouse operation content are used as a training template; based on the training template, the game scene of the target game segment is reconstructed, and the mouse operation content is prompted; the mouse operation triggered by the prompt of the mouse operation content is received, and the next step training instructions corresponding to the current mouse operation are fed back.

[0093] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0094] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0095] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0096] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned training method for controlling an intelligent mouse, and can solve the technical problems of low efficiency and poor training effect of game operation training. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the training method for controlling an intelligent mouse provided by the above-mentioned embodiment, and will not be described in detail here.

[0097] The present application also provides a computer program product, including a computer program, which implements the steps of the training method for controlling an intelligent mouse as described above when executed by a processor.

[0098] The computer program product provided by the present application can solve the technical problems of low efficiency and poor training effect of game operation training. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the training method for controlling the intelligent mouse provided by the above embodiment, which will not be described in detail here.

[0099] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A training method for controlling an intelligent mouse, characterized in that: The training method for controlling the intelligent mouse comprises: Obtaining a training template for mouse operation, wherein the mouse operation content of the top players in the target game segment is pre-recorded, and the game scene of the target game segment and the corresponding mouse operation content are used as the training template; Based on the training template, reconstruct the game scene of the target game clip and provide prompts for the mouse operation content; Receive the mouse operation triggered by the prompt of the mouse operation content, and feedback the next step training guidance corresponding to the current mouse operation.

2. The training method for controlling an intelligent mouse according to claim 1, wherein: The step of obtaining a training template for mouse operation includes: Get players' historical game performance data; Predicting the player's gaming weaknesses based on the historical gaming performance data, or determining the gaming differences from top players based on the historical gaming performance data; Determine a target training template targeting the game operation weaknesses or the game operation differences.

3. The training method for controlling an intelligent mouse according to claim 1, characterized in that: The training method for controlling the intelligent mouse also includes: In real-time game battles, obtain the palm temperature and / or grip strength of the mouse; When the real-time game battle enters a preset intense scene, the mouse temperature is maintained at a preset temperature based on the palm temperature and / or the mouse sensitivity is maintained at a preset sensitivity based on the grip strength.

4. The training method for controlling an intelligent mouse as claimed in claim 3, characterized in that: The step of maintaining the mouse temperature at a preset temperature based on the palm temperature and / or maintaining the mouse sensitivity at a preset sensitivity based on the gripping force comprises: If the palm temperature is higher than a preset upper temperature limit or lower than a preset lower temperature limit, maintaining the mouse temperature at a preset temperature; and / or, If the gripping force is greater than a preset upper pressure limit or lower than a preset lower pressure limit, the mouse sensitivity is maintained at the preset sensitivity.

5. The training method for controlling an intelligent mouse according to claim 1, characterized in that: The training method for controlling the intelligent mouse also includes: The physiological signal and / or biomechanical signal of the user holding the mouse when using the mouse is collected by using the physiological signal sensor and / or biomechanical signal sensor preset in the mouse; wherein the physiological signal includes one or more of the electromyographic signal, neural electrical signal, hemodynamic signal, and skin electrical activity signal related to the use of the mouse, and the biomechanical signal includes one or more of the tendon vibration signal, joint angle signal, and pressure signal related to the use of the mouse; Based on the movement direction prediction model, the mouse movement direction corresponding to the physiological signal and / or the biomechanical signal is predicted.

6. The training method for controlling an intelligent mouse as claimed in claim 5, characterized in that: The step of predicting the mouse movement direction corresponding to the physiological signal and / or the biomechanical signal based on the movement direction prediction model comprises: Acquiring training data, wherein the training data includes historical physiological signals and / or historical biomechanical signals of a mouse holder when using the mouse within a historical period, and historical mouse movement directions corresponding to the historical physiological signals and / or historical biomechanical signals; Based on the training data, a moving direction prediction model is trained.

7. A training device for controlling an intelligent mouse, characterized in that: The training device for controlling the intelligent mouse comprises: An acquisition module, used to acquire a training template for mouse operation, wherein the mouse operation content of the top players in the target game segment is pre-recorded, and the game scene of the target game segment and the corresponding mouse operation content are used as the training template; A guiding module, used for reconstructing the game scene of the target game clip based on the training template, and providing prompts for the mouse operation content; The receiving module is used to receive the mouse operation triggered by the prompt of the mouse operation content, and to feed back the next step training instruction corresponding to the current mouse operation.

8. A training device for controlling an intelligent mouse, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the training method for controlling an intelligent mouse according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the training method for controlling an intelligent mouse as described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the training method for controlling an intelligent mouse as claimed in any one of claims 1 to 6 are implemented.

Images