Mouse sensitivity adjusting method and mouse

Abstract

The invention provides a mouse sensitivity adjusting method and a mouse, and relates to the field of mouses.The mouse is in communication connection with at least two upper computers, and the mouse sensitivity adjusting method comprises the steps that based on the cursor position of the mouse, the upper computer controlled by the mouse is determined and recorded as a target upper computer; according to the real-time movement data of the mouse and the operation data of the target upper computer, determining the use scene type of the mouse on the target upper computer; and matching a sensitivity adjustment strategy corresponding to the use scene category of the target upper computer from a pre-constructed sensitivity adjustment strategy library, and adjusting the sensitivity of the mouse according to the sensitivity adjustment strategy. It is ensured that the sensitivity of the mouse is adaptive to the current operation environment of the target upper computer, and the risk of misoperation during cross-system operation of a user is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of mouse, in particular to a mouse sensitivity adjustment method and mouse. BACKGROUND

[0002] Generally, one mouse can only control one computer, but some users need to perform cross-screen operation or cross-control system operation, and hope that one mouse can control two or more computers. In related technologies, this can be realized by hardware devices such as a copy line or a KVM switch, or by Synergy software within the same local area network.

[0003] Some users need the mouse to have different sensitivities on different computers when performing cross-system operation. For example, the mouse needs to have low sensitivity on a computer for software testing to prevent the mouse from being too sensitive and causing false touch, and the mouse needs to have normal sensitivity or high sensitivity on a computer for document editing and document viewing. The existing mouse has the same sensitivity when switching between different computers, which is easy to cause user misoperation and reduces the user experience. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a mouse sensitivity adjustment method and mouse, which solves the problem of poor adaptive sensitivity adjustment capability of the mouse when performing cross-system operation, which is easy to cause user misoperation.

[0005] In a first aspect, the present application provides a mouse sensitivity adjustment method, wherein the mouse is in communication connection with at least two host computers, and the method comprises the following steps: Based on the cursor position of the mouse, a host computer controlled by the mouse is determined and recorded as a target host computer; According to the real-time movement data of the mouse and the running data of the target host computer, the use scenario category of the mouse on the target host computer is determined; From a pre-constructed sensitivity adjustment strategy library, a sensitivity adjustment strategy corresponding to the use scenario category of the target host computer is matched, and the sensitivity of the mouse is adjusted according to the sensitivity adjustment strategy.

[0006] In an embodiment, the use scenario category of the mouse on the target host computer is determined according to the real-time movement data of the mouse and the running data of the target host computer, specifically comprising the following steps: Extracting first scene features with scene distinguishing degree in the real-time movement data; the real-time movement data includes displacement amount, movement direction, click pressure and scroll wheel speed per unit time; Extracting second scene features with scene distinguishing degree in the running data; the running data includes hardware resource occupation data, software running environment data and system state data; The first scene feature and the second scene feature are taken as inputs to determine a use scene category of the target host computer through a pre-established scene classification model.

[0007] In an embodiment, the first scene feature with scene distinguishability in the real-time movement data is extracted, specifically including: The real-time movement data is processed through a sliding window technique, and time domain features are extracted from the processed real-time movement data; the time domain features include a displacement vector module length, a speed standard deviation, an acceleration change rate, a click interval time and a click duration in a preset sliding window; A frequency spectrum matrix of the real-time movement data is determined through a Fourier transform, and time-frequency features are extracted based on the frequency spectrum matrix; A trajectory point sequence of the mouse is determined according to the real-time movement data, and trajectory features are extracted based on the trajectory point sequence; The first scene feature is constructed according to the time domain features, the time-frequency features and the trajectory features.

[0008] In an embodiment, the time-frequency features are extracted based on the frequency spectrum matrix, specifically including: A frequency component with the largest energy proportion in the frequency spectrum matrix is determined as a main frequency; A frequency band energy distribution of the frequency spectrum matrix is determined according to a preset frequency distribution rule; The frequency spectrum matrix is segmented into multiple levels through a wavelet decomposition technique, and energy proportions of the levels are calculated; The time-frequency features are constructed according to the main frequency, the frequency band energy distribution and the energy proportions of the levels.

[0009] In an embodiment, the trajectory features are extracted based on the trajectory point sequence, specifically including: A curvature of a mouse trajectory is determined based on the trajectory point sequence through a three-point circle method; The trajectory point sequence is segmented into multiple displacement vectors according to a preset time interval, and an angle change rate of the trajectory point sequence is determined according to an included angle of adjacent two displacement vectors; The trajectory features are constructed according to the curvature and the angle change rate.

[0010] In an embodiment, the second scene feature with scene distinguishability in the running data is extracted, specifically including: Hardware resource features are extracted from the hardware resource occupation data; the hardware resource features include a CPU occupation rate, a GPU occupation rate, a temperature change rate and a video memory bandwidth utilization rate; extracting software environment features from the software running environment data; the software environment features include application category encoding, window rendering frame rate, logical resolution and physical resolution; extracting system state features from the system state data; the system state features include task switching frequency and background process quantity; constructing second scene features according to the hardware resource features, the software environment features and the system state features.

[0011] In an embodiment, the matching of the sensitivity adjustment strategy corresponding to the use scene category of the target host computer from the pre-constructed sensitivity adjustment strategy library specifically includes: if the use scene category of the target host computer is an office scene, adjusting the sensitivity of the mouse to a first target sensitivity; and / or if the use scene category of the target host computer is a test scene, adjusting the sensitivity of the mouse to a second target sensitivity; and / or if the use scene category of the target host computer is an audio / video scene, adjusting the sensitivity of the mouse to a third target sensitivity; and / or if the use scene category of the target host computer is a game scene, adjusting the sensitivity of the mouse to a fourth target sensitivity.

[0012] In an embodiment, after the adjusting of the sensitivity of the mouse according to the sensitivity adjustment strategy, further includes: generating corresponding operation data in response to the operation behavior of the user on the mouse; if the error data of the operation data exceeds a preset error threshold within a preset time period, adjusting the sensitivity of the mouse according to the parameter configuration optimization of the target host computer.

[0013] In a second aspect, the present application provides a mouse, comprising a processor and a memory; wherein the memory stores a computer program, and the computer program is used to load and execute the mouse sensitivity adjustment method according to any one of the first aspect.

[0014] In a third aspect, the present application provides a computer readable storage medium, characterized in that the computer readable storage medium stores instructions, and the instructions are used to load and execute the mouse sensitivity adjustment method according to any one of the first aspect by a processor.

[0015] In the mouse sensitivity adjustment method and the mouse, the target host computer controlled by the user is determined through the cursor position of the mouse, and after the use scene category of the target host computer is determined, the sensitivity of the target host computer is adjusted according to the sensitivity adjustment strategy matched with the use scene category, so that the sensitivity of the mouse is adapted to the current running environment of the target host computer, and the risk of misoperation of the user in cross-system operation is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0017] Figure 1 The connection relationship diagram of the mouse and the plurality of host computers provided for an embodiment of the present application.

[0018] Figure 2 The flowchart of the mouse sensitivity adjustment method provided for an embodiment of the present application.

[0019] Figure 3 The structural diagram of an electronic device provided for an embodiment of the present application. DETAILED DESCRIPTION

[0020] The specific embodiments of the present application will be described in detail below with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the description of the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0021] In the description of the present application, unless otherwise explicitly specified and limited, the terms "arrangement", "installation", "connection" and the like should be understood broadly, for example, can be fixedly connected, or can be detachably connected, or integrally connected; can be mechanically connected, or can be electrically connected; can be directly connected, or can be indirectly connected through an intermediate medium. For those skilled in the art, the specific meanings of the above terms can be understood according to the specific circumstances.

[0022] The terms "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the application is usually placed during use, and are only for the convenience of description and simplification of the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the application.

[0023] The terms "first", "second", "third" and the like are merely for distinguishing similar attributes, and do not indicate or imply relative importance or a particular order.

[0024] The terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, in addition to including the listed elements, other elements not explicitly listed can also be included.

[0025] Figure 1 The connection relationship of the mouse 20 and the plurality of host computers 10 of the embodiment is shown in the schematic diagram, the plurality of host computers 10 and the mouse 20 are connected to the same local area network, each host computer 10 is installed with Synergy software, the mouse 20 is connected to one of the host computers 10 through Bluetooth wireless connection (or wired connection), and the mouse 20 is equipped with a synchronous processing accelerometer, a gyroscope and a pressure sensor, and can calculate the trajectory area, pressure change and other data of the mouse 20 in real time.

[0026] As shown in Figure 2 The mouse sensitivity adjustment method provided by the embodiment includes: Step S100: determining a host computer controlled by the mouse based on the cursor position of the mouse, and recording the host computer as a target host computer; Step S200: determining the use scenario category of the mouse on the target host computer according to the real-time movement data of the mouse and the running data of the target host computer; Step S300: matching the sensitivity adjustment strategy corresponding to the use scenario category of the target host computer from the pre-constructed sensitivity adjustment strategy library, and adjusting the sensitivity of the mouse according to the sensitivity adjustment strategy.

[0027] In the mouse sensitivity adjustment method of the embodiment, the target host computer controlled by the user is determined through the cursor position of the mouse, and after the use scenario category of the target host computer is determined, the sensitivity of the target host computer is adjusted according to the sensitivity adjustment strategy matched with the use scenario category, so as to ensure that the sensitivity of the mouse is adapted to the current running environment of the target host computer, and the risk of misoperation of the user during cross-system operation is reduced.

[0028] Step S100: Based on the cursor position of the mouse, determine the host computer controlled by the mouse and record it as the target host computer.

[0029] The cursor position is the coordinate information of the mouse in the display interface, represented by the screen coordinate system or the physical coordinate system. The current cursor coordinate data in the host computer screen can be obtained through the communication protocol between the mouse and the host computer (such as USB, wireless protocol or network protocol).

[0030] A host computer is a computer system operated via a mouse, including but not limited to personal computers, servers, or other terminal devices. The target host computer is the actual host computer entity currently being controlled by the mouse. This can be achieved through real-time coordinate monitoring and area comparison, such as matching the cursor position with the screen area of ​​each host computer using a multi-screen coordinate system or independent screen ID recognition. When the cursor position falls within the screen area of ​​a particular host computer, that host computer is marked as the target host computer. Coordinate mapping algorithms can be used to determine the cursor position and the target host computer, ensuring that mouse control commands are accurately associated with the currently operating computer system and avoiding accidental cross-device operations.

[0031] Furthermore, a cursor position spatiotemporal correlation algorithm can be used to determine the target host computer. This algorithm combines cursor position information with temporal and spatial factors for analysis and processing, comprehensively considering the spatial position of the cursor at different times. This can resolve the ambiguity of ownership when multiple systems coexist, thereby improving the success rate of target host computer recognition. The calculation formula for the cursor position spatiotemporal correlation algorithm is as follows:

[0032] Among them, the This indicates the numerical value of the cursor's position on the target host computer (the range of this numerical value varies depending on the host computer); the... Indicates the position coordinates of the mouse cursor; Indicates the first The coordinate information of the host computer; This represents the time weighting coefficient, with a value ranging from 0.01 to 1.5; The time deviation between the response to mouse cursor position information and the display of the mouse cursor on the host computer screen.

[0033] Step S200: Determine the usage scenario category of the mouse on the target host computer based on the real-time movement data of the mouse and the operation data of the target host computer.

[0034] The real-time movement data includes dynamic parameters such as displacement speed, acceleration, and movement trajectory of the mouse, and is usually collected by a sensor (such as an optical sensor or a laser sensor) built in the mouse. The running data is system status information of the target host computer, including the type of currently running application program, CPU load, memory occupancy, or screen display content features, and is obtained through a system monitoring interface, for example, by calling an API to obtain the process ID or application program name of the current active window.

[0035] The use scenario category is a predefined operation environment classification, such as "software testing", "document editing", "game mode", etc. The use scenario category can be determined by multi-dimensional data fusion analysis, for example, by inputting the real-time movement data and the running data into a classification model for processing. The classification model is generated based on a rule-based decision tree, a machine learning model, or a deep learning model. For example, if it is detected that the mouse movement speed is low and the current active window is a test tool, it is determined to be a "software testing" scenario.

[0036] In an embodiment, the use scenario category of the mouse on the target host computer is determined according to the real-time movement data of the mouse and the running data of the target host computer, specifically comprising: Step S201: extracting first scenario features with scenario distinguishing degree from the real-time movement data; the real-time movement data includes displacement amount per unit time, movement direction, click pressure, and scroll wheel speed; The first scene feature is a parameter set for representing the association of user operation behavior with a specific use scene, which can be determined by statistical methods or feature engineering algorithms. The displacement is the spatial displacement distance of the mouse in a unit of time, which can be calculated by the coordinate change collected by the sensor. For example, the displacement can include the displacement components in the X and Y axes, and the displacement in a unit of time can reflect the mouse movement speed. The movement direction is the azimuth or angle change of the mouse trajectory, which can be calculated by the vector direction of the coordinate point sequence. For example, the movement direction includes the included angle or turning angle of the continuous trajectory segment, and the movement direction in a unit of time can reflect the operation trajectory feature. The click pressure is the force value applied by the user when operating the mouse button, which can be obtained by the pressure sensor. For example, the click pressure can include the pressing degree or pressure duration, and the click pressure in a unit of time can record the user's button pressing force. The scroll wheel speed can be the angular velocity of the scroll wheel rotation or the scroll distance in a unit of time, which can be measured by an encoder or an optical sensor. For example, the scroll wheel speed can include the instantaneous speed or average speed, and the scroll wheel speed in a unit of time can be associated with the page browsing or zooming behavior. The real-time movement data can be converted into a quantifiable feature vector by calculating the standard deviation, mean value or Fourier transform analysis trajectory frequency, so as to facilitate the analysis of the use scene of the target host computer. For example, a fast straight-line moving trajectory can be associated with a game scene, and a small displacement can be associated with a software test scene.

[0037] In an embodiment, the extracting the first scene feature with scene differentiation degree in the real-time movement data specifically comprises: Step S2011: segmenting the real-time movement data by a sliding window technique, and extracting time domain features from the segmented real-time movement data; the time domain features include displacement vector module length, speed standard deviation, acceleration change rate, click interval time and click duration in a preset sliding window.

[0038] In the segmentation processing, a fixed length sliding window can be set to divide the real-time movement data. When the window moves each time, a certain overlap rate (such as 50%) can be set to ensure the continuity of data processing and the accuracy of feature extraction. For example, the data segmentation can be realized by setting the window length to 0.5 seconds and the sliding step to 0.1 seconds, and then calculating the displacement vector module length, speed standard deviation, acceleration change rate, click interval time and click duration in each window. The continuous trajectory point coordinates are calculated, wherein The displacement vector module length in the sliding window is This represents the difference in the mouse's X-axis coordinates within the sliding window. This represents the difference in the mouse's Y-axis coordinates within the sliding window. The speed standard deviation is a statistical measure reflecting the degree of fluctuation in the mouse's movement speed within the sliding window, and can be expressed by the formula... Confirmed, among which For the speed standard deviation, The number of sampling points within the sliding window. Indicates the first The speed of each sampling point ,in( ) is the first The coordinates of each sampling point, ( ) is the ( The coordinates of +1) sampling points, The sampling time interval, This represents the average velocity of multiple sampling points within the sliding window. The rate of change of acceleration is a parameter describing the magnitude of the change in acceleration value per unit time, which can be obtained through... Confirmed, among which For the rate of change of acceleration, Indicates the ( The acceleration of +1) sampling points, Indicates the first The acceleration at each sampling point, of which , Indicates the ( +1) velocity of sampling points. Click interval time represents the time interval between consecutive clicks by the user, and click duration represents the duration of a single click action by the user. Click interval time and click duration can be obtained directly from the sensor.

[0039] Step S2012: Determine the spectrum matrix of the real-time mobile data through Fourier transform, and extract time-frequency features based on the spectrum matrix; The spectrum matrix is ​​a multi-dimensional data structure obtained by converting a time-domain signal into a frequency-domain representation through Fourier transform. Its elements can correspond to the amplitude or phase information of different frequency components. Time-frequency characteristics include, but are not limited to, parameters such as the dominant frequency, frequency band energy distribution, or the energy proportion of a specific frequency band.

[0040] The spectrum matrix can be obtained through short-time Fourier transform, and the transform formula is as follows: ,in Represents the spectrum matrix, For time frame indexing, For frequency bin index, This represents the real-time motion data of the nth sampling time frame. This represents the Hanning window function. This represents the total number of sampling time frames, typically 1. The power spectrum density of the time-frequency point may be determined according to the spectrum matrix , that is .

[0041] In an embodiment, the extracting the time-frequency feature based on the spectrum matrix specifically comprises: determining a frequency component with the largest energy proportion in the spectrum matrix as a main frequency; determining a frequency band energy distribution of the spectrum matrix according to a preset frequency distribution rule; segmenting the spectrum matrix into multiple levels through wavelet decomposition technology, and calculating the energy proportion of each level; and constructing a time-frequency feature according to the main frequency, the frequency band energy distribution, and the energy proportion of each level.

[0042] The main frequency is a frequency component with the most concentrated energy distribution in the frequency domain of real-time mobile data, and reflects the dominant rhythm or periodic characteristics of the mobile behavior. The main frequency can be obtained by traversing the energy values of the frequency components in the spectrum matrix, identifying the point where the spectrum gradient changes from positive to negative as a local maximum value point, and selecting the frequency corresponding to the maximum value point with the largest energy proportion as the main frequency. For example, the main frequency can include a low-frequency component corresponding to a straight-line movement in document editing or a high-frequency component corresponding to a rapid click in game operation.

[0043] The frequency band energy distribution is a parameter for calculating the energy proportion in each frequency band after the spectrum is divided into multiple predefined frequency bands. The spectrum matrix can be segmented into a low-frequency band L, a middle-frequency band M, and a high-frequency band H through a preset rule, and the energy proportion of each frequency band can be calculated through the formula E L = ∑ k ∈ L | X k | 2, E M = ∑ k ∈ M | X k | 2, and E H = ∑ k ∈ H | X k | 2, where E L represents the energy proportion of the low-frequency band L. The calculation formulas of the middle-frequency band and the high-frequency band are similar to that of the low-frequency band, and are not described herein.

[0044] The wavelet decomposition technology is a multi-resolution analysis method that decomposes the signal into frequency band information of different levels through stretching and shifting the wavelet base function. For example, the signal can be decomposed into 3 levels through a db4 wavelet base, and then the energy proportion of each level coefficient after decomposition is calculated. For example, the energy proportion of each level can include the energy proportion of the mutation feature captured by the high-frequency detail layer or the energy proportion of the overall trend reflected by the low-frequency approximation layer. For example, the first level can capture high-frequency transient changes, and the third level can reflect low-frequency long-term trends, thereby quantifying different time scale features.

[0045] ​​​​​The dominant frequency value, frequency band energy distribution parameters, and wavelet level energy proportions can be combined into a feature vector. For example, this feature vector may include parameters such as the dominant frequency value, a low-frequency energy proportion of 30%, a mid-frequency energy proportion of 40%, a high-frequency energy proportion of 30%, and the energy distribution ratio of each wavelet level. Through multi-dimensional frequency domain analysis, periodic patterns in different scenarios can be accurately distinguished. The multi-resolution characteristics of wavelet decomposition enhance noise resistance, and the combination of frequency band distribution and level energy parameters improves the robustness of scenario classification. Finally, through multi-source feature fusion, refined identification of complex operating modes is achieved, thus providing a more accurate decision-making basis for sensitivity adjustment.

[0046] Step S2013: Determine the trajectory point sequence of the mouse based on the real-time movement data, and extract trajectory features based on the trajectory point sequence; A trajectory point sequence is a two-dimensional coordinate sequence arranged in chronological order, consisting of consecutive mouse positions on the screen or in a planar coordinate system. Trajectory features include geometrically related parameters such as curvature, rate of change of direction, or trajectory closure. For example, curvature can be calculated from the second derivative of the trajectory point sequence or the rate of change of the vector angle, while the rate of change of direction can be determined by the ratio of the angle between the direction vectors of adjacent trajectory points to the time interval. The geometric calculation method and the definition of trajectory feature parameters for the trajectory point sequence remain consistent with previous schemes; for example, curvature calculation uses cubic spline interpolation or the finite difference method.

[0047] In one embodiment, the step of extracting trajectory features based on the trajectory point sequence specifically includes: determining the curvature of the mouse trajectory using the three-point circle method based on the trajectory point sequence; dividing the trajectory point sequence into multiple displacement vectors according to a preset time interval, and determining the angle change rate of the trajectory point sequence based on the angle between two adjacent displacement vectors; and constructing trajectory features based on the curvature and the angle change rate.

[0048] Curvature is a geometric parameter that reflects the degree of curvature of a trajectory. The three-point circle method involves fitting the smallest circular arc to three consecutive points on the trajectory and calculating its radius of curvature. For example, for three consecutive points on the trajectory... , and You can follow the formula Determine the first Curvature of a point Generally, a higher curvature indicates a greater degree of trajectory curvature.

[0049] A displacement vector is the coordinate difference vector between two adjacent points in a trajectory point sequence, and can be obtained by dividing the trajectory point sequence according to a preset time interval. For example, a displacement vector can include a vector sequence divided at 0.1-second intervals; for instance, at a sampling frequency of 100Hz, every 10 sampling points constitute a displacement vector. This can be expressed using the formula... Determine two adjacent displacement vectors and The included angle ,in ,in It is the first The coordinates of the dividing points It is the first The coordinates of the dividing points can be obtained through the formula. Calculate the rate of change of the included angle Where N is the total number of displacement vectors, For the first The dividing point and the first The included angles at each dividing point. Based on the curvature, the average curvature, standard deviation of curvature, maximum curvature, and curvature skewness of the trajectory can be determined. Combined with the included angle change rate, the average included angle change rate, maximum included angle change rate, and included angle change fluctuation rate can be determined to construct the trajectory features.

[0050] Compared with traditional methods, the three-point circle method captures local bending characteristics more accurately, distinguishes stable movement from frequent turning by the rate of change of the included angle, and comprehensively represents the operation mode by fusing geometric and dynamic parameters. This improves the expressive power of trajectory features, enhances the scene classification model's ability to distinguish different operation modes (such as games and document editing), and ultimately reduces the risk of accidental touches in cross-device operations and improves the user experience.

[0051] Step S2014: Construct a first scene feature based on the time-domain feature, the time-frequency feature, and the trajectory feature.

[0052] The first scene features can be combined by concatenating or weighted fusion of feature vectors. For example, a multi-dimensional feature vector can be formed by concatenating the parameters of time-domain features, time-frequency features, and trajectory features in a preset order.

[0053] By employing the sliding window technique to extract time-domain features that characterize the volatility and temporal characteristics of the movement trajectory, and combining Fourier transform to capture periodic or random features in the frequency domain, while analyzing geometric morphological features based on trajectory point sequences, and forming a first scene feature that comprehensively characterizes the scene characteristics through multi-modal feature fusion, the scene recognition accuracy can be improved by utilizing the complementarity of multi-dimensional data features, providing a precise basis for subsequent dynamic adjustment of sensitivity.

[0054] Step S202: Extract second scene features with scene distinguishability from the running data; the running data includes hardware resource usage data, software running environment data, and system status data; The hardware resource occupation data includes system resource consumption indicators such as CPU usage, memory occupation rate, or GPU load, and can be obtained by reading through a system monitoring interface. Exemplarily, the hardware resource occupation data can include a resource occupation peak or a continuous occupation proportion of a current process. The software running environment data is a process name of an active window, an application type, or a window content keyword, and can be obtained through a system API or a process manager. Exemplarily, the software running environment data can include application program identifiers such as a document editor, a game client, or a test tool. The system state data is an interface parameter such as a screen resolution, a window focus state, or a full-screen mode flag, and can be read through a system registry or a display driver interface. Exemplarily, the system state data can include a resolution parameter or a windowed / full-screen state identifier of a current window.

[0055] In an embodiment, the extracting the second scene feature with scene differentiation in the running data specifically includes: Step S2021: extracting hardware resource features from the hardware resource occupation data; the hardware resource features include CPU occupation rate, GPU occupation rate, temperature change rate, and video memory bandwidth utilization rate.

[0056] The CPU occupation rate is a percentage of processor core usage, which can be collected in real time through a system monitoring interface (such as the Performance Monitor of Windows or the ` / proc / stat` file of Linux). The GPU occupation rate is a load proportion of a graphics processor, which can be obtained through an NVIDIA NvAPI or an AMD ROCm interface. The temperature change rate is a rising or falling rate of hardware temperature per unit time, which is determined through sensor data and a timestamp. The video memory bandwidth utilization rate is a percentage of video memory data read-write rate to total bandwidth, which is obtained through a counter of a video memory controller.

[0057] Step S2022: extracting software environment features from the software running environment data; the software environment features include application category coding, window rendering frame rate, logical resolution, and physical resolution. The application category coding is an identifier for classifying the type of an active process, such as “game” (code 1), “document editing” (code 2), etc., which is generated by matching a process name or a window title keyword with a predefined classification table. The window rendering frame rate is a refresh frequency of an application window, which can be obtained by capturing a VSync signal of a window exchange link or analyzing a graphics card driver log. Exemplarily, 60 FPS or more usually corresponds to a game or video playback scene. The logical resolution and the physical resolution are a parameter pair of a pixel ratio used internally by an application program and an actual number of pixels of a display, and the logical resolution can be queried through a system display setting, and the physical resolution can be obtained through a window attribute. A difference between the two can reflect a virtual desktop or a remote desktop operating environment.

[0058] Step S2023: extracting system state features from the system state data; the system state features include task switching frequency and background process quantity; The task switching frequency refers to the number of times that the process scheduler switches the active window or thread per unit time, which is obtained by counting the number of task switches and the time difference through a system kernel interface (such as ` / proc / loadavg` of Linux or `GetSystemTimes` of Windows). The background process quantity is the remaining process quantity after deducting the user-initiated interactive processes and the system critical processes, which can be obtained by a process filtering algorithm. For example, if the background process quantity exceeds 15, it may indicate that the system resource occupation is high.

[0059] Step S2024: constructing second scene features according to the hardware resource features, the software environment features and the system state features.

[0060] Different dimension parameters are converted to a unified range through normalization processing, and are spliced according to a preset weight (for example, hardware accounts for 40%, software accounts for 30%, and system accounts for 30%). For example, if the CPU occupancy rate is 75%, the application category code is "game", and the task switching frequency is 0.5 times per second, then the combined "intensive game scene" feature vector has a high confidence.

[0061] Based on the multi-dimensional parameter fusion feature vector, hardware load deep analysis, software environment fine modeling, system state dynamic perception and multi-dimensional feature collaborative optimization can be achieved, which significantly improves the comprehensiveness and accuracy of scene classification, especially in cross-system operations, which can effectively identify hardware load differences, application type changes and system interference states, realize fine adaptation of sensitivity adjustment, reduce the risk of misoperation and improve user experience.

[0062] Step S203: taking the first scene features and the second scene features as inputs, and determining the use scene category of the target host computer through a pre-established scene classification model.

[0063] The scene classification model is a machine learning model such as multilayer perceptron, support vector machine or convolutional neural network, which realizes multi-source data fusion by splicing the first scene features and the second scene features into a unified input vector. For example, the model input can include displacement vector length, frequency, curvature, CPU occupancy rate and active process type, etc. The model can learn the mapping relationship between features and scenes through training data, and can optimize parameters based on labeled scene category data, so as to achieve the technical effect of improving scene recognition accuracy through multi-dimensional feature fusion.

[0064] In steps S201 to S203, the time domain features of real-time mobile data are extracted by using the sliding window technique, the time-frequency features are obtained by analyzing the frequency spectrum matrix using the Fourier transform, the trajectory features are calculated based on the trajectory point sequence, and the multi-dimensional first scene features are constructed. Combined with the second scene features such as hardware resource occupation, software environment and interface state in the system running data, the scene category judgment is finally realized through the classification model, which can achieve the technical effect of multi-source data fusion of dynamic behavior mode and system state, improve the scene recognition accuracy and reduce the risk of misjudgment. Through the joint modeling of time domain, frequency domain and geometric features, the mobile behavior features of different scenes such as game operation, document editing and software testing can be effectively distinguished, and the sensitivity adaptation ability in cross-device operation is significantly enhanced through cross verification combined with application program type and hardware load state.

[0065] Step S300, matching the sensitivity adjustment strategy corresponding to the use scene category of the target host computer from the pre-constructed sensitivity adjustment strategy library, and adjusting the sensitivity of the mouse according to the sensitivity adjustment strategy.

[0066] The sensitivity adjustment strategy library is a database that stores the mapping relationship between different scenes and sensitivity parameters, which is usually organized in the form of key-value pairs, such as "software testing -> DPI400" and "document editing -> DPI1600". The sensitivity adjustment strategy is a specific parameter configuration scheme, including but not limited to mouse sampling rate, DPI, acceleration curve coefficient or report rate. The corresponding sensitivity adjustment strategy can be determined by querying the strategy library, for example, the use scene category determined in step S200 is used as a query key to retrieve the corresponding strategy parameters. If there is a matching item, the strategy is directly applied, for example, the mouse DPI is adjusted to a preset value; if no matching item is found, the default strategy or adaptive adjustment mechanism is triggered. Adjusting the DPI can be achieved by modifying the mouse firmware parameters or operating system driver settings, for example, by sending control instructions to adjust the DPI value through the HID protocol. By combining strategy retrieval and parameter configuration, dynamic adaptation of sensitivity parameters is realized, so that the mouse operation achieves the best precision and smoothness in different scenes.

[0067] In an embodiment, the matching of the sensitivity adjustment strategy corresponding to the use scene category of the target host computer from the pre-constructed sensitivity adjustment strategy library specifically includes: if the use scene category of the target host computer is an office scene, adjusting the sensitivity of the mouse to a first target sensitivity; and / or if the use scene category of the target host computer is a test scene, adjusting the sensitivity of the mouse to a second target sensitivity; and / or if the use scene category of the target host computer is an audio / video scene, adjusting the sensitivity of the mouse to a third target sensitivity; and / or if the use scene category of the target host computer is a game scene, adjusting the sensitivity of the mouse to a fourth target sensitivity.

[0068] The office scenario refers to an operation environment such as document editing, email processing, webpage browsing, etc. that requires accurate positioning and stable movement. Its typical characteristics include low-frequency trajectory, low-angle change rate, and active document editing software. The first target sensitivity is a preset low-sensitivity parameter combination, such as a DPI range of 400-800. By setting the mouse DPI to 600, adjusting the report rate to 125 Hz, and disabling the acceleration function, a linear relationship between movement distance and physical displacement is achieved. For example, in the office scenario, the cursor offset during fast movement can be reduced, such as achieving cell-level positioning in table editing or avoiding cursor jumping during text selection.

[0069] The test scenario refers to an operation environment such as software testing, interface debugging, etc. that requires extremely low fault tolerance. Its typical characteristics include small trajectory adjustment, high-frequency task switching, and active test tool software. The second target sensitivity is a lower sensitivity parameter than the office scenario, such as DPI ≤ 400, and a trajectory smoothing algorithm may be enabled to filter fine jitter. For example, in the test scenario, the DPI can be set to 400, the trajectory noise filter that ignores movements less than 1px is enabled, and the maximum speed threshold is limited to 16 inches per second. By using ultra-low sensitivity and filtering algorithms, the test scenario can meet the demand for absolute control of the cursor, such as accurately clicking on a pixel-level button in UI testing.

[0070] The audio / video scenario refers to an operation environment such as video editing, audio processing, etc. that requires smooth scrolling and precise frame positioning. Its typical characteristics include high-frequency scroll wheel scrolling, high rendering frame rate, and active media software. The third target sensitivity can be a medium sensitivity parameter, such as a DPI range of 800-1200, and the scroll wheel response speed and smoothness may be optimized. For example, the DPI can be set to 1000, the scroll wheel report rate is increased to 500 Hz, and the vertical scroll smoothing algorithm is enabled to dynamically adjust the scroll step size based on the scroll wheel speed. In the audio / video scenario, by balancing smoothness and accuracy, frame-level positioning of the video timeline or precise adjustment of the sound track in audio waveform editing can be achieved.

[0071] The game scenario refers to a game operation environment such as FPS, MOBA, etc. that requires fast response and large-scale movement. Its typical characteristics include high-frequency trajectory changes, high GPU occupancy, and active game engine software. The fourth target sensitivity is a high-sensitivity parameter, such as a DPI range of 1600-3200, and may be combined with a dynamic acceleration curve and adaptive sampling rate. For example, the DPI can be set to 1600, the ultra-high-speed mode with a sampling rate of 8000 Hz is enabled, and the acceleration curve is configured to maintain linearity for small amplitude movements and sharply increase sensitivity for large amplitude movements. In the game scenario, high sensitivity and fast response can meet the needs of games, such as precise aiming and fast positioning during "blind shot" in FPS games.

[0072] By directly binding the abstract scene category with the specific parameter value, combining the differentiated parameter design, and linking the operating system settings to form an end-to-end optimization link, the user's manual configuration complexity can be eliminated, the mainstream operation scene can be covered through the preset strategy library, seamless parameter switching under multi-task across devices can be realized, the risk of misoperation caused by scene switching can be reduced, the balance between accurate operation and smooth experience can be considered, and finally the operation efficiency and consistency of the user in different tasks can be improved.

[0073] In an embodiment, after adjusting the sensitivity of the mouse according to the sensitivity adjustment strategy, it further comprises: responding to the user's operation behavior on the mouse and generating corresponding operation data; if the error data of the operation data exceeds the preset error threshold within a preset time period, adjusting the sensitivity of the mouse according to the parameter configuration optimization adjustment of the target host computer.

[0074] The operation data refers to the original interaction information generated when the user uses the mouse, which can be continuously collected through the mouse sensor and the operating system event log. For example, the operation data can include cursor movement trajectory, click position, scroll wheel rolling amplitude, key duration, etc. The preset time period can be a fixed time window for statistical error data, for example, it can be set to 1 minute or 10% of the current scene duration. The error data can be an operation abnormality index caused by sensitivity mismatch, for example, it can include cursor positioning deviation exceeding the tolerance range, accidental triggering of non-target buttons, scrolling operation exceeding the expected step length, etc. The error threshold can be a preset error data trigger condition, for example, it can be set to "continuous 3 times click deviation exceeding 5 pixels" or "1 minute mis-touch rate exceeding 15%". The parameter configuration of the target host computer can be the adjustable range of the current sensitivity parameter and the hardware capability limit, for example, it can include DPI value, reporting rate, trajectory smoothing algorithm enable state, etc.

[0075] Responding to the user's operation behavior on the mouse and generating corresponding operation data, the offset of the cursor movement trajectory can be captured in real time through the mouse sensor, and the relative distance between the click position and the target window can be recorded in combination with the operating system event log. For example, in a document editing scene, the coordinate deviation when the user clicks the toolbar button can be monitored. By continuously collecting multi-dimensional operation features to construct real-time feedback data flow, a quantitative basis is provided for subsequent error judgment.

[0076] If the error data of the operation data exceeds the preset error threshold within the preset time period, the sensitivity of the mouse can be adjusted according to the parameter configuration of the target host computer after optimization. This can be achieved in the following ways: first, define the error determination rule, for example, determine that "the distance between the click position and the center of the target button is greater than 3 pixels" as a mis-touch; second, count the total amount of error data within the preset time period; when the mis-touch rate exceeds the threshold, call the current sensitivity parameter configuration and determine the adjustable range combined with the hardware capability, for example, reduce the DPI from 800 to 600; then adjust the parameters according to the optimization direction decision, for example, enable the trajectory smoothing filter or reduce the response coefficient of the scroll wheel; finally, use a gradual adjustment strategy to modify the parameter value in stages to avoid sudden changes that affect operation adaptability. Through real-time feedback, a closed-loop adjustment is formed, for example, gradually reducing the DPI when the mis-touch rate exceeds the standard, and re-evaluating the error rate after each adjustment, finally converging to a parameter combination that ensures accuracy and maintains smooth operation.

[0077] Through dynamic feedback closed loop, the traditional static preset mode is broken through, so that the sensitivity adjustment responds to the differences in individual user operation habits; with the help of multi-dimensional parameter linkage optimization, the fineness of the adjustment space is improved, the risk of sudden change is reduced through the gradual parameter modification strategy, and the dual driving adjustment mechanism of scene classification and user feedback is combined, which significantly improves the operation compatibility and accuracy across scenes and users.

[0078] In addition, when a user switches from one computer to another during cross-computer operation, the target sensitivity of the two computers may be different, and when the user switches to another host computer, the new DPI will be applied immediately, causing a sudden change in sensitivity. This sudden change can cause the cursor to jump or jitter on the screen. To avoid the situation where some users cannot quickly adapt to the new DPI and cause operation out of control, this embodiment introduces a transient response optimization algorithm to smoothly transition the discomfort caused by sensitivity switching within a certain period of time after switching.

[0079] Specifically, when the cursor position crosses the screen, the coordinate change rate of the cursor position is detected. If the coordinate change rate is greater than a preset threshold speed, a scene switching event is triggered, and the timestamp at this time is recorded as , the sensitivity of the host computer before switching , and the sensitivity of the target host computer after switching , and the sensitivity of the target host computer is adjusted through a time decay function, where the expression of the time decay function is:

[0080] wherein, is the time node to be adjusted is the sensitivity to be adjusted, is the decay coefficient, and the calculation formula is wherein is a base attenuation coefficient, and the value range is 0.01-0.5; is a sensitivity difference weight, and the value range is 0.2-0.4; is the maximum sensitivity of the target host computer, and the maximum sensitivity of the target host computer can be queried according to the factory setting.

[0081] The sensitivity transition is realized by the exponential attenuation function, the cursor acceleration mutation caused by the sensitivity mutation is eliminated, the sensitivity switching amplitude is automatically adjusted to the transition amplitude, the discomfort caused by the user due to the too large sensitivity change is avoided, and the user misoperation is prevented.

[0082] In summary, in the mouse sensitivity adjustment method of the embodiment, the target device is accurately positioned based on the cursor position to solve the instruction attribution problem in multi-device control, scene intelligent recognition is realized by combining multi-source data fusion analysis to avoid manual switching operation of the user, the automatic adjustment of the sensitivity is realized by the preset strategy library to meet the operation requirements of different scenes, the continuity and consistency of the user experience in cross-system operation are improved, the misoperation risk caused by the parameter mismatch is reduced, the cross-device control capability of the existing mouse is expanded without additional hardware devices, and the balance between operation accuracy and efficiency is considered.

[0083] Based on the same inventive concept as the above embodiments, the embodiment further provides a mouse including a processor and a memory; wherein the memory stores a computer program, and the computer program is used to load and execute the method as described above by the processor.

[0084] As Figure 3 shown, based on the same inventive concept as the above embodiments, the embodiment further provides a computer readable storage medium, which stores instructions for loading and executing the method as described above by the processor.

[0085] In the embodiments of the mobile terminal and the computer readable storage medium provided in the application, all the technical features of the above control method embodiments are included, the description expansion and explanation content are basically the same as those of the above method embodiments, and will not be repeated here.

[0086] The application embodiment further provides a computer program product, which includes computer program code, when the computer program code runs on the computer, so that the computer executes the method in various possible embodiments.

[0087] The embodiment of the present application further provides a chip comprising a memory and a processor, the memory is used for storing a computer program, and the processor is used for calling and running the computer program from the memory, so that a device installed with the chip executes the method in the various possible embodiments.

[0088] The serial numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0089] In the present application, for the same or similar term concept, technical solution and / or application scenario description, generally only the first time is described in detail, and when repeatedly appearing later, in order to be brief, generally no longer repeated, and when understanding the technical solutions and the like of the present application, the same or similar term concept, technical solution and / or application scenario description and the like which are not described in detail later can refer to the related description before.

[0090] In the present application, the description of each embodiment has its own emphasis, and the part not described or recorded in a certain embodiment can refer to the related description of other embodiments.

[0091] The technical features of the technical solutions of the present application can be combined arbitrarily, in order to make the description simple, not all possible combinations of the technical features in the above embodiments are described, however, as long as the combinations of the technical features do not exist contradictory, they should be considered as the range recorded in the present application.

[0092] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in the above-mentioned storage medium, and includes a plurality of instructions for making a terminal device execute the method of each embodiment of the present application. The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent flow transformation made by using the contents of the specification and drawings, or directly or indirectly applied to other related technical fields, are also included in the patent protection scope of the present application.

[0093] It should be noted that each embodiment in the present specification adopts a progressive manner for description, and each embodiment mainly describes the difference from other embodiments, and the same or similar parts between each embodiment can be referred to each other.

[0094] The above merely illustrates the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method of adjusting the sensitivity of a mouse, characterized by, The mouse is in communication connection with at least two host computers, and the method comprises: Based on the cursor position of the mouse, determining the host computer controlled by the mouse and recording as a target host computer; According to the real-time movement data of the mouse and the running data of the target host computer, determining the use scene category of the mouse on the target host computer; From the pre-constructed sensitivity adjustment strategy library, matching the sensitivity adjustment strategy corresponding to the use scene category of the target host computer, and adjusting the sensitivity of the mouse according to the sensitivity adjustment strategy.

2. The mouse sensitivity adjustment method of claim 1, wherein, According to the real-time movement data of the mouse and the running data of the target host computer, determining the use scene category of the mouse on the target host computer, specifically comprising: Extracting first scene features with scene distinguishing degree in the real-time movement data; the real-time movement data includes displacement, moving direction, click pressure and scroll wheel speed per unit time; Extracting second scene features with scene distinguishing degree in the running data; the running data includes hardware resource occupation data, software running environment data and system state data; Taking the first scene features and the second scene features as inputs, determining the use scene category of the target host computer through a pre-established scene classification model.

3. The mouse sensitivity adjustment method of claim 2, wherein, The first scene features with scene distinguishing degree in the real-time movement data are extracted, specifically comprising: Segmenting the real-time movement data through sliding window technology, and extracting time domain features from the segmented real-time movement data; the time domain features include displacement vector module length, velocity standard deviation, acceleration change rate, click interval time and click duration in a preset sliding window; Determining the frequency spectrum matrix of the real-time movement data through Fourier transform, and extracting time-frequency features based on the frequency spectrum matrix; Determining the trajectory point sequence of the mouse according to the real-time movement data, and extracting trajectory features based on the trajectory point sequence; Constructing first scene features according to the time domain features, the time-frequency features and the trajectory features.

4. The mouse sensitivity adjustment method of claim 3, wherein, The time-frequency features are extracted based on the frequency spectrum matrix, specifically comprising: Determining the frequency component with the largest energy proportion in the frequency spectrum matrix as the main frequency; Determining the frequency band energy distribution of the frequency spectrum matrix according to a preset frequency distribution rule; Dividing the frequency spectrum matrix into multiple levels through wavelet decomposition technology, and calculating the energy proportion of each level; Constructing time-frequency features according to the main frequency, the frequency band energy distribution and the energy proportion of each level.

5. The mouse sensitivity adjustment method of claim 3, wherein, The trajectory features are extracted based on the trajectory point sequence, specifically comprising: Determining the curvature of the mouse trajectory based on the trajectory point sequence through three-point circle method; Dividing the trajectory point sequence into multiple displacement vectors according to a preset time interval, and determining the angle change rate of the trajectory point sequence according to the included angle of adjacent two displacement vectors; Constructing trajectory features according to the curvature and the angle change rate.

6. The mouse sensitivity adjustment method of claim 2, wherein, The second scene features with scene distinguishing degree in the running data are extracted, specifically comprising: Extracting hardware resource features from the hardware resource occupation data; the hardware resource features include CPU occupation rate, GPU occupation rate, temperature change rate and video memory bandwidth utilization rate; extracting software environment features from software running environment data; the software environment features include application category code, window rendering frame rate, logical resolution and physical resolution; extracting system state features from system state data; the system state features include task switching frequency and background process number; constructing second scene features according to the hardware resource features, the software environment features and the system state features.

7. The mouse sensitivity adjustment method according to any one of claims 1-6, wherein, The sensitivity adjustment strategy corresponding to the use scene category of the target host computer is matched from a pre-constructed sensitivity adjustment strategy library, and the sensitivity adjustment strategy specifically includes: if the use scene category of the target host computer is an office scene, the sensitivity of the mouse is adjusted to a first target sensitivity; and / or if the use scene category of the target host computer is a test scene, the sensitivity of the mouse is adjusted to a second target sensitivity; and / or if the use scene category of the target host computer is an audio and video scene, the sensitivity of the mouse is adjusted to a third target sensitivity; and / or if the use scene category of the target host computer is a game scene, the sensitivity of the mouse is adjusted to a fourth target sensitivity.

8. The mouse sensitivity adjustment method according to any one of claims 1-6, wherein, After adjusting the sensitivity of the mouse according to the sensitivity adjustment strategy, it further includes: responding to the operation behavior of the user on the mouse and generating corresponding operation data; if the error data of the operation data exceeds the preset error threshold within a preset time period, adjusting the sensitivity of the mouse according to the parameter configuration optimization of the target host computer.

9. A mouse, characterized in that The computer readable storage medium stores instructions for loading and executing the mouse sensitivity adjustment method by the processor.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores instructions for loading and executing the mouse sensitivity adjustment method by the processor.

Images