CN-120335631-A - AI-based mouse direction high-precision control method and device and mouse

CN120335631ACN 120335631 ACN120335631 ACN 120335631ACN-120335631-A

Abstract

The invention relates to the technical field of direction control, in particular to a mouse direction high-precision control method and device based on AI and a mouse. The method comprises the steps of obtaining mouse basic position data, tracking a moving path of a mouse based on the mouse basic position data to generate mouse moving path data, carrying out two-dimensional vector decomposition on a path point plane of the mouse moving path data to generate a mouse plane moving horizontal coordinate and a mouse plane moving vertical coordinate, obtaining mouse display resolution data, and calculating a direction change angle and direction reversal times of the mouse according to the mouse plane moving horizontal coordinate and the mouse plane moving vertical coordinate. The invention effectively solves the problems of path error, insufficient jitter recognition and unstable response in the traditional mouse direction control by multi-sensor data fusion and AI self-adaptive compensation, and realizes high-precision mouse direction control.

Inventors

XU RENSONG
WANG PING

Assignees

KECHUANG TECH SHENZHEN CO LTD

Dates

Publication Date: 20250718
Application Date: 20250619
Priority Date: 20250619

Claims (10)

1. The high-precision mouse direction control method based on the AI is characterized by comprising the following steps of: Step S1, acquiring mouse basic position data, tracking a moving path of a mouse based on the mouse basic position data to generate mouse moving path data, and decomposing a path point plane two-dimensional vector of the mouse moving path data to generate a mouse plane moving abscissa and a mouse plane moving ordinate; step S2, acquiring mouse display resolution data, calculating a direction change angle and direction reversal times of a mouse according to a horizontal coordinate of the movement of a mouse plane and a vertical coordinate of the movement of the mouse plane, extracting moving edge saw tooth display characteristics of the mouse display resolution data to obtain mouse movement saw tooth change characteristic data, and performing mouse shake detection on the mouse movement saw tooth change characteristic data through the direction change angle and the direction reversal times to obtain a mouse shake detection result; Step S3, collecting user pressing data and myoelectric signals of the metacarpophalangeal joints by utilizing a pressure sensor and a myoelectric sensor which are arranged in a mouse according to a mouse shake detection result; And S4, performing self-adaptive compensation on the mouse movement direction of the mouse shake detection result through the mouse control data of the user so as to execute the high-precision mouse direction control operation based on the AI.
2. The AI-based mouse direction high-precision control method according to claim 1, wherein the step S1 includes the steps of: s11, sampling the position of a mouse pointer in real time by using an input interface of user equipment, and capturing screen coordinate values under each frame or time slice to acquire basic position data of the mouse; Step S12, performing time sequence reconstruction, missing point interpolation and path fitting analysis on the mouse basic position data, extracting a continuous path sequence of a mouse motion track, and generating mouse movement path data; step S13, vectorizing any two continuous point coordinate differences in the mouse moving path data to form a displacement vector set between adjacent points, and generating path two-dimensional plane vector data; And S14, decomposing the abscissa of the path two-dimensional plane vector data to generate a mouse plane movement abscissa and a mouse plane movement ordinate.
3. The AI-based mouse direction high-precision control method according to claim 1, wherein step S2 includes the steps of: Step S21, automatically detecting and calibrating pixel density of a resolution parameter of a display connected with a user terminal to obtain display resolution data of a mouse; S22, carrying out coordinate sequence difference and inverse cosine calculation on a mouse plane movement abscissa and a mouse plane movement ordinate to generate a mouse direction change angle; S23, carrying out symbol gradient analysis on the direction change angle, and counting the times of direction reversal by detecting positive and negative changes of continuous direction vectors to generate the times of direction reversal; s24, analyzing the minimum discernable unit of the mouse display resolution data, and extracting an edge zigzag movement mode of the horizontal coordinate of the mouse plane movement and the vertical coordinate of the mouse plane movement according to the minimum discernable unit to generate mouse movement zigzag change characteristic data; and S25, performing abnormal movement fitting analysis on the mouse movement saw tooth change characteristic data through the mouse direction change angle and the direction reversal times to generate a mouse shake detection result.
4. The AI-based mouse direction high-precision control method according to claim 3, characterized in that step S25 includes the steps of: Step S251, performing first derivative calculation on the mouse direction change angle according to the time stamp, extracting the angle change rate, identifying the abrupt direction change behavior, and generating angular speed change characteristic data; step S252, counting the number of direction reversal times in unit time, performing sliding window clustering, extracting short-time high-frequency reversal characteristics, and generating direction reversal density distribution data; step S253, calculating frequency domain energy distribution of the mouse moving saw tooth change characteristic data; And S254, normalizing the angular velocity change characteristic data, the direction reversal density distribution data and the frequency domain energy distribution, fitting the normalized angular velocity change characteristic data, the direction reversal density distribution data and the frequency domain energy distribution to a shake judgment logic curve, and detecting curve change of the shake judgment logic curve based on a preset shake change threshold value to obtain a mouse shake detection result.
5. The AI-based mouse direction high-precision control method according to claim 1, wherein step S3 includes the steps of: step S31, collecting user pressing data and myoelectric signals of metacarpophalangeal joints of a user by utilizing a pressure sensor and a myoelectric sensor which are arranged in a mouse according to a mouse shake detection result; Step S32, carrying out spatial hot zone clustering on the user pressing data to generate a user palm contact thermodynamic diagram, extracting isotherms of the palm contact thermodynamic diagram, and carrying out regional gradient analysis on the user palm contact thermodynamic diagram according to the isotherms to generate user static holding gesture characteristic data; Step S33, carrying out Fourier transformation on the user pressing pressure data to generate user pressing frequency domain data, calculating the peak interval of the user pressing frequency domain data, and carrying out user pressing tremor identification on the user pressing pressure data according to the peak interval so as to generate periodic tremor mode data; Step S34, synchronous window registration is carried out on the periodic tremor mode data and the electromyographic signals to generate interference fit correction data, and time window stability analysis is carried out on the user pressing data and the electromyographic signals through the interference fit correction data to generate multichannel stability evaluation data; And step S35, performing joint behavior modeling through the static holding gesture characteristic data and the multi-channel stability evaluation data to generate user mouse control data.
6. The AI-based mouse direction high-precision control method according to claim 5, characterized in that step S35 includes the steps of: S351, carrying out multi-dimensional thermal distribution gradient reconstruction on static holding gesture feature data to generate gesture thermal flow tensor data, and carrying out frequency-amplitude-phase compound domain nonlinear deconstruction on multi-channel stability evaluation data to generate stability mixed feature tensor data; Step S352, performing three-mode tensor cross fusion on the gesture heat flow direction tensor data and the stability mixed characteristic tensor data by adopting a tensor cross gating network to generate a user thermomyocoupler behavior characteristic map, wherein three modes comprise thermal inertia, myoelectric displacement and behavior intention; Step S353, performing behavior intention decoding modeling on the user thermal muscle coupling behavior feature map to generate a nonlinear control state mapping diagram; Step S354, matching the current gesture control state of the user according to the nonlinear control state mapping diagram, and generating user mouse control data.
7. The AI-based mouse direction high-precision control method according to claim 1, wherein step S4 includes the steps of: S41, performing time sequence dynamic direction fitting analysis on user mouse control data to generate high-resolution direction control track data; s42, carrying out nonlinear error inversion analysis on the high-resolution direction control track data and the direction error interference data to generate compensation vector field data; Step S43, analyzing the mouse control state of the user mouse control data, and predicting the multi-branch path of the mouse direction control state based on the compensation vector field data to generate direction decision fusion data; and S44, performing mouse direction self-adaptive compensation based on the direction decision fusion data, and generating an AI direction control response instruction to perform AI-based mouse direction high-precision control operation.
8. The AI-based mouse direction high-precision control method according to claim 7, characterized in that step S43 includes the steps of: step S431, identifying a path branching point of the compensation vector field data; step S432, constructing a path candidate diagram of the mouse control state based on the path branching point to generate direction evolution map data; S433, carrying out path feasibility prediction modeling on the directional evolution map data to generate path prediction confidence coefficient matrix data; and S434, performing confidence weighted aggregation analysis on the path prediction confidence matrix data to generate direction decision fusion vector data.
9. An AI-based mouse direction high-precision control apparatus for executing the AI-based mouse direction high-precision control method according to claim 1, the AI-based mouse direction high-precision control apparatus comprising: The mouse moving path analysis module is used for acquiring mouse basic position data, tracking a moving path of a mouse based on the mouse basic position data to generate mouse moving path data, and decomposing a two-dimensional vector of a path point plane of the mouse moving path data to generate a horizontal coordinate of the movement of the mouse plane and a vertical coordinate of the movement of the mouse plane; the mouse display module is used for acquiring mouse display resolution data, calculating the direction change angle and the direction reversal times of the mouse according to the horizontal coordinate and the vertical coordinate of the movement of the mouse plane, extracting the sawtooth display characteristics of the moving edge of the mouse display resolution data to obtain mouse movement sawtooth change characteristic data, and carrying out mouse shake detection on the mouse movement sawtooth change characteristic data according to the direction change angle and the direction reversal times to obtain a mouse shake detection result; The mouse control module is used for acquiring user pressing data and myoelectric signals of the metacarpophalangeal joints by utilizing a pressure sensor and a myoelectric sensor which are arranged in the mouse according to a mouse shake detection result; And the self-adaptive adjustment module is used for carrying out self-adaptive compensation on the mouse movement direction of the mouse shake detection result through the mouse control data of the user so as to execute the high-precision mouse direction control operation based on the AI.
10. A mouse comprising an array of pressure sensors and an array of myoelectric sensors, coupled to a microcontroller, for performing the AI-based mouse directional high-precision control method of claims 1-8.

Description

AI-based mouse direction high-precision control method and device and mouse Technical Field The invention relates to the technical field of direction control, in particular to a mouse direction high-precision control method and device based on AI and a mouse. Background The traditional mouse control depends on a mechanical sensor and an optical sensor, and has the problems of insufficient precision, response delay, susceptibility to interference and the like under a complex environment although higher sensitivity is achieved. By means of deep learning, computer vision and sensor fusion technology, researchers begin to explore a method for predicting and correcting a mouse motion track in real time through an AI model, so that the accuracy and stability of direction control are improved. Early researches mainly focused on gesture recognition and track prediction based on image recognition, and hand or mouse motion features are extracted through a Convolutional Neural Network (CNN) to realize rough judgment of directions. Subsequently, a cyclic neural network (RNN) and a long and short term memory network (LSTM) are introduced to capture the time series characteristics of mouse movements, significantly improving the continuity and accuracy of trajectory prediction. However, at present, the display of the cursor is affected by the screen resolution in the moving process of the mouse, so that misjudgment of the direction of the mouse control caused by the screen resolution and rendering saw teeth can be caused, and meanwhile, the current mouse direction control cannot accurately capture the dynamic capture of the actual control intention of the user, so that the stability and the accuracy of the control are lower. Disclosure of Invention Based on the above, there is a need to provide a method, a device and a mouse for high-precision control of a mouse direction based on AI, so as to solve at least one of the above technical problems. In order to achieve the above purpose, an AI-based mouse direction high-precision control method comprises the following steps: Step S1, acquiring mouse basic position data, tracking a moving path of a mouse based on the mouse basic position data to generate mouse moving path data, and decomposing a path point plane two-dimensional vector of the mouse moving path data to generate a mouse plane moving abscissa and a mouse plane moving ordinate; step S2, acquiring mouse display resolution data, calculating a direction change angle and direction reversal times of a mouse according to a horizontal coordinate of the movement of a mouse plane and a vertical coordinate of the movement of the mouse plane, extracting moving edge saw tooth display characteristics of the mouse display resolution data to obtain mouse movement saw tooth change characteristic data, and performing mouse shake detection on the mouse movement saw tooth change characteristic data through the direction change angle and the direction reversal times to obtain a mouse shake detection result; Step S3, collecting user pressing data and myoelectric signals of the metacarpophalangeal joints by utilizing a pressure sensor and a myoelectric sensor which are arranged in a mouse according to a mouse shake detection result; And S4, performing self-adaptive compensation on the mouse movement direction of the mouse shake detection result through the mouse control data of the user so as to execute the high-precision mouse direction control operation based on the AI. The invention realizes high-resolution analysis of the micro moving track through two-dimensional vector decomposition of the path points, and remarkably improves the accuracy of mouse control, especially in high-resolution or drawing scenes. And the user operation track is sensitively captured by utilizing the direction change angle and the direction reversal times, so that the comprehensive perception and understanding of the complex mouse motion behavior are realized. By means of the sawtooth edge characteristics and the direction data fusion judgment, mouse shake caused by non-autonomous factors can be effectively detected, and error input is eliminated. By means of signal acquisition of a pressure sensor and a myoelectric sensor arranged in the mouse, the discrimination capability of the system for conscious control and unconscious action is improved based on the muscle activity and pressing habit of the hand of a user. And learning different user operation modes through the AI model, so that self-adaptive direction compensation aiming at different physiological characteristics is realized, and the personalized man-machine interaction requirement is met. The system is particularly suitable for users such as parkinsonism and cerebral apoplexy sequelae, and can effectively make up for involuntary shake in the mouse control process, so that more stable input experience is realized. Even in complex use environments such as vibration desktops, low-stability supports and