Earphone mistaken touch prevention control method and system based on fingerprint identification

Abstract

The invention discloses an earphone mistaken touch prevention control method and system based on fingerprint identification, and relates to the technical field of fingerprint identification, and the method comprises the steps: collecting static fingerprint data and dynamic fingerprint data of a user, carrying out the preprocessing, and storing the data in a fingerprint database; generating an elliptical dynamic fingerprint window based on user dynamic fingerprint data collected in real time; converting the elliptical dynamic fingerprint window into a rectangular dynamic fingerprint window, and performing fingerprint feature point matching; collecting earphone use data of a user, and constructing a touch scene analysis model to obtain an earphone use scene; and dynamically adjusting the operation logic of the earphone according to the use scene of the earphone. By generating the rectangular dynamic fingerprint window and accurately capturing the dynamic change of the finger of the user in the touch process, the method can adapt to the change of the finger in different operations, realizes effective tracking and identification of real-time dynamic fingerprints, improves the accuracy of fingerprint matching, reduces mistaken touch, and enhances the adaptability of the system to complex touch operations.

Description

Technical Field

[0001] The present invention relates to the technical field of fingerprint recognition, and in particular to a method and system for preventing accidental touch of an earphone based on fingerprint recognition. Background Art

[0002] With the rapid development of wireless communication technology and portable audio devices, headphones have become an indispensable device in people's daily life. Early headphones were mainly used for wired connection devices. With the popularization of Bluetooth technology, wireless headphones have gradually replaced traditional wired headphones, providing a more free usage experience. However, with the continuous increase of headphone functions, such as touch operation, voice assistant and noise cancellation, the use of headphones has become more complex and intelligent. In this case, the convenience and accuracy of touch operation have become one of the important criteria for judging user experience. Existing touch headphones mainly rely on static touch sensors to control the headphones by detecting touch actions.

[0003] However, due to the diversity and complexity of users' touch methods, the existing technology has certain shortcomings in the accuracy and sensitivity of fingerprint recognition. How to effectively prevent false touches and improve the accuracy of fingerprint recognition and user satisfaction has become a difficult problem that needs to be solved urgently in the current technical field. Summary of the invention

[0004] In view of the problems existing in the above-mentioned existing earphone anti-mistouch control method based on fingerprint recognition, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that identity verification is not accurate enough.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a method for preventing accidental touch of earphones based on fingerprint recognition, which includes collecting static fingerprint data and dynamic fingerprint data of users, preprocessing and storing them in a fingerprint database; generating an elliptical dynamic fingerprint window based on the dynamic fingerprint data of users collected in real time; converting the elliptical dynamic fingerprint window into a rectangular dynamic fingerprint window for fingerprint data matching; collecting user earphone usage data, constructing a touch scenario analysis model, and obtaining the earphone usage scenario; and dynamically adjusting the operation logic of the earphone according to the earphone usage scenario.

[0007] As a preferred solution of the earphone anti-mistouch control method based on fingerprint recognition described in the present invention, wherein: the collecting of user static fingerprint data and dynamic fingerprint data for preprocessing and storing in the fingerprint database means that when the user uses the earphone for the first time, the earphone supporting application is used to collect the user's fingerprint image, the noise in the fingerprint image is removed by a filter, the contrast of the fingerprint image is enhanced by using image enhancement technology, and the grayscale image is converted into a binary image;

[0008] The Zhang-Suen thinning algorithm is used to thin the ridges in the binary image to a single pixel width, and static feature points including ridge endpoints and bifurcation points are extracted from the thinned fingerprint image, and description information is generated for each static feature point, including position and direction;

[0009] Integrate the extracted static feature point information into a unified format, including the position, direction and type of each static feature point, and generate a static fingerprint data feature vector, wherein the static fingerprint data feature vector includes the position coordinates, direction angle and number of the static feature points;

[0010] Installing capacitive touch sensors and pressure sensors on the touch area of ​​the headset surface;

[0011] When the user uses the headset, dynamic fingerprint data is collected in real time. The dynamic fingerprint data includes time series data generated during the user operation, and the current fingerprint image, finger position, pressure intensity and touch type are recorded at each time point. The touch type includes light touch, long press and slide.

[0012] Normalizing the fingerprint position coordinates and pressure values ​​in the dynamic fingerprint data to generate a dynamic fingerprint data feature vector, wherein the dynamic fingerprint data feature vector includes the dynamic fingerprint position, pressure value and timestamp;

[0013] The static fingerprint data feature vector and the dynamic fingerprint data feature vector are normalized and concatenated to form a multi-dimensional fusion data vector. A fingerprint feature template is generated based on the multi-dimensional fusion data vector and stored in a database.

[0014] As a preferred solution of the earphone anti-mistouch control method based on fingerprint recognition described in the present invention, wherein: the generation of an elliptical dynamic fingerprint window based on the user dynamic fingerprint data collected in real time includes:

[0015] Calculate the dynamic fingerprint window parameters and set the current touch point position of the user's finger to (x i-1 ,y i-1 ), the next touch point position is (x i ,y i );

[0016] Collect historical touch data of the user's headset and collect data of N touch points;

[0017] Calculate the distance difference between each touch:

[0018]

[0019] Among them, (x i ′,y i ′) is the position of the finger's i-th touch in the user's headset historical touch data;

[0020] Calculate the average distance between all touch points

[0021]

[0022] Use the PDR algorithm to predict the next touch point after the user's finger moves (x i ,y i )Location:

[0023]

[0024] Among them, θ i is the direction angle of the user's finger movement;

[0025] Calculate the straight-line distance c between the two touch points i :

[0026]

[0027] Use your finger to move distance c i and unit time interval Δt to calculate the current speed V i :

[0028]

[0029] Calculate all speed values ​​during the finger movement and record the maximum value V max ;

[0030] Calculate the minor semiaxis b i :

[0031] b i =(V max -V i )×Δt+e

[0032] Among them, b i is the vertical distance of the user touch point position change at the current speed, V max is the maximum speed, V i is the current speed, e is the empirical error;

[0033] Calculate the major semiaxis a i :

[0034]

[0035] Among them, a i is the maximum expansion distance of the elliptical window;

[0036] According to the semi-major axis a i , minor semi-axis b i and focal length c i, generating an elliptical dynamic fingerprint window, the center of which is (x i ,y i ).

[0037] As a preferred solution of the headphone anti-mistouch control method based on fingerprint recognition described in the present invention, wherein: the conversion of the elliptical dynamic fingerprint window into a rectangular dynamic fingerprint window includes:

[0038] The range of calculating the rectangular dynamic fingerprint window includes the number of left-shifted grids, the number of right-shifted grids, the number of upward-shifted grids and the number of downward-shifted grids;

[0039] Shift left by number of grids:

[0040]

[0041] Shift right by number of grids:

[0042]

[0043] Move up the grid number:

[0044]

[0045] Move down the number of grids:

[0046]

[0047] Among them, N ileft is the number of grid cells on the left boundary, N iright is the number of grid cells on the right boundary, N ibottom is the number of grid cells on the upper boundary, N itop is the number of grids at the lower boundary, α is the rotation angle, and cellsize is the size of the grid;

[0048] According to the boundary of the rectangular dynamic fingerprint window, the elliptical dynamic fingerprint window data is mapped into the rectangular dynamic fingerprint window to generate a rectangular dynamic fingerprint window containing the elliptical dynamic fingerprint window.

[0049] As a preferred solution of the earphone anti-mistouch control method based on fingerprint recognition described in the present invention, the fingerprint feature point matching includes:

[0050] Collect real-time dynamic fingerprint data, build a rectangular dynamic fingerprint window, record all rectangular dynamic fingerprint windows that change with the finger, select the rectangular dynamic fingerprint window whose corner is closest to the center point, and record the coordinates of the upper left corner (x min ,y min ) and the lower right corner coordinate (x max ,y max ), check the extracted feature point coordinates, and satisfy x min <x<xmax and min <y<y max The feature points that meet the conditions are retained, and the feature points that do not meet the conditions are filtered out;

[0051] Extract fingerprint feature points p and each fingerprint template feature point q from real-time dynamic fingerprint data and fingerprint database respectively, calculate the Euclidean distance between each feature point p and feature point q, select the feature point pair with the smallest Euclidean distance as the final matching feature point pair, and calculate the fingerprint matching degree S based on the Euclidean distance between the final matching feature point pairs:

[0052]

[0053] Where M is the number of matching feature point pairs, dist(p f ,q f ) is the matching feature point pair (p f ,q f ), p f is the real-time dynamic fingerprint data feature point in the fth matching feature point pair, q f is the fingerprint feature template feature point in the fth matching feature point pair;

[0054] Set the fingerprint matching threshold St and compare it with the fingerprint matching S:

[0055] If S≥St, the user identity authentication is determined to be successful, and the verification result is sent to the mobile application via Bluetooth. The mobile application displays a verification success message, allowing the user to continue the operation;

[0056] If S<St, the user identity authentication is determined to have failed, and the headset automatically triggers the anti-mistouch mechanism, locks the touch operation, restores the touch function after 5 seconds, and sends the verification information to the mobile phone application via Bluetooth to warn the user.

[0057] As a preferred solution of the headphone anti-mistouch control method based on fingerprint recognition described in the present invention, wherein: the collecting of user headphone usage data, building a touch scenario analysis model, and obtaining the headphone usage scenario include:

[0058] Collect the headset history usage data of the mobile phone application, generate the headset history usage data set and divide it into a training set and a test set, the headset history usage data set includes feature parameters and label data, the feature parameters include average acceleration, angular velocity of headset rotation, ambient light intensity, ambient noise level and heart rate change, the label data refers to the headset usage scenario corresponding to each touch event, including emergency scenario, sports scenario and static scenario;

[0059] Extract the headphone history and use the characteristic parameters in the dataset to form a high-dimensional feature matrix Q:

[0060]

[0061] in is the average acceleration, w is the angular velocity of the headset rotation, O is the ambient light intensity, U is the ambient noise level, ΔHR is the heart rate change, and m is the number of samples;

[0062] Use convolutional neural network to build a touch scene analysis model, including input layer, convolution layer, pooling layer, fully connected layer and output layer;

[0063] The input content of the input layer is a high-dimensional feature matrix Q;

[0064] The convolution layer extracts features through multiple convolution layers, each of which is composed of multiple convolution kernels and activation functions to generate a feature map;

[0065] The pooling layer pools the feature map output by the convolution layer, reduces the dimension of the feature map, and extracts the main features;

[0066] The fully connected layer flattens the output of the pooling layer and performs feature combination and classification through the fully connected layer;

[0067] The output layer uses a Softmax activation function to perform multi-classification and outputs a probability distribution of headphone usage scenarios;

[0068] Use the training set data to train the model, use the cross entropy loss function to calculate the model error, and use the Adam optimizer to update the parameters;

[0069] Use the test set to evaluate the performance of the model and optimize the model through hyperparameter tuning and cross-validation;

[0070] The real-time collected user headphone usage data is input into the trained model to obtain the headphone usage scenario.

[0071] As a preferred solution of the headphone anti-mistouch control method based on fingerprint recognition described in the present invention, the dynamically adjusting the operation logic of the headphone according to the headphone usage scenario includes:

[0072] The earphone usage scenarios include riding, driving, walking, running and quiet scenarios, and the earphone usage scenarios are prioritized;

[0073] When the user is riding or driving, it is an emergency situation and has the highest priority. The user focuses on the road and traffic conditions, disables touch control, enables voice control, and turns on the headphone ambient sound mode;

[0074] When the user is walking or running, it is a sports scenario, which has the second highest priority. The user's body and hands are in motion, and the sports mode is turned on. When the user starts to exercise, the music will be automatically played, and when the user stops exercising, the music will be automatically paused.

[0075] When the user is at rest, it is a quiet scenario with general priority, and the user uses the headset normally.

[0076] As a preferred solution of the headphone anti-mistouch control system based on fingerprint recognition described in the present invention, it includes:

[0077] The data collection and preprocessing module is used to collect user static fingerprint data and dynamic fingerprint data and preprocess the fingerprint;

[0078] A window conversion module, used for generating an elliptical dynamic fingerprint window according to the collected user fingerprint data and converting the elliptical dynamic fingerprint window into a rectangular dynamic fingerprint window;

[0079] Fingerprint matching module, used to match fingerprint feature points of dynamic fingerprint data collected in real time with fingerprint data in the fingerprint database;

[0080] Data analysis module, used to build a touch dynamic analysis model and analyze the user's headphone usage scenario;

[0081] The dynamic adjustment module is used to dynamically adjust the operating logic of the headset according to the usage scenario of the headset.

[0082] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of a method and system for preventing accidental touch of earphones based on fingerprint recognition when executing the computer program.

[0083] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method and system for preventing accidental touch of earphones based on fingerprint recognition.

[0084] The beneficial effects of the present invention are as follows: the present invention accurately captures the dynamic changes of the user's finger during the touch process by generating a rectangular dynamic fingerprint window. The generated rectangular dynamic fingerprint window can adapt to the changes of the finger in different operations, thereby realizing effective tracking and identification of real-time dynamic fingerprints, improving the accuracy and real-time performance of fingerprint matching, reducing the possibility of false touches, and enhancing the system's adaptability to complex touch operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0086] Figure 1 The figure is a flow chart of a method for preventing accidental touch of earphones based on fingerprint recognition.

[0087] Figure 2 The figure is a flowchart of fingerprint matching.

[0088] Figure 3 The figure is a schematic diagram of the structure of a headphone anti-mistouch control system based on fingerprint recognition. DETAILED DESCRIPTION

[0089] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0090] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0091] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0092] Example 1

[0093] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a method and system for preventing accidental touch of earphones based on fingerprint recognition. The method for preventing accidental touch of earphones based on fingerprint recognition includes:

[0094] S1, collect user static fingerprint data and dynamic fingerprint data, pre-process them and store them in the fingerprint database;

[0095] Furthermore, collecting the user's static fingerprint data and dynamic fingerprint data for preprocessing and storing in the fingerprint database means that when the user uses the headset for the first time, the user's fingerprint image is collected using the headset supporting application, the noise in the fingerprint image is removed by a filter, the contrast of the fingerprint image is enhanced by using an image enhancement technology, and the grayscale image is converted into a binary image;

[0096] The Zhang-Suen thinning algorithm is used to thin the ridges in the binary image to a single pixel width, and static feature points including ridge endpoints and bifurcation points are extracted from the thinned fingerprint image, and description information is generated for each static feature point, including position and direction;

[0097] Integrate the extracted static feature point information into a unified format, including the position, direction and type of each static feature point, and generate a static fingerprint data feature vector, wherein the static fingerprint data feature vector includes the position coordinates, direction angle and number of the static feature points;

[0098] Installing capacitive touch sensors and pressure sensors on the touch area of ​​the headset surface;

[0099] When the user uses the headset, dynamic fingerprint data is collected in real time. The dynamic fingerprint data includes time series data generated during the user operation, and the current fingerprint image, finger position, pressure intensity and touch type are recorded at each time point. The touch type includes light touch, long press and slide.

[0100] Normalizing the fingerprint position coordinates and pressure values ​​in the dynamic fingerprint data to generate a dynamic fingerprint data feature vector, wherein the dynamic fingerprint data feature vector includes the dynamic fingerprint position, pressure value and timestamp;

[0101] The static fingerprint data feature vector and the dynamic fingerprint data feature vector are normalized and concatenated to form a multi-dimensional fusion data vector. A fingerprint feature template is generated based on the multi-dimensional fusion data vector and stored in a database.

[0102] By collecting the user's static fingerprint data and dynamic fingerprint data and preprocessing them, the user's fingerprint information can be efficiently stored in the fingerprint database, achieving high-precision collection and storage of user fingerprint data, providing a basis for subsequent fingerprint matching and dynamic adjustment. Through high-precision data storage, it is ensured that the system can provide stable and reliable fingerprint recognition performance in different environments, thereby achieving the effect of reducing false touches.

[0103] S2, generating an elliptical dynamic fingerprint window based on the user dynamic fingerprint data collected in real time;

[0104] Furthermore, based on the user dynamic fingerprint data collected in real time, generating an elliptical dynamic fingerprint window includes:

[0105] Calculate the dynamic fingerprint window parameters and set the current touch point position of the user's finger to (x i-1 ,y i-1 ), the next touch point position is (x i ,y i );

[0106] Collect historical touch data of the user's headset and collect data of N touch points;

[0107] Calculate the distance difference between each touch:

[0108]

[0109] Among them, (x i ′,y i ′) is the position of the finger's i-th touch in the user's headset historical touch data;

[0110] Calculate the average distance between all touch points

[0111]

[0112] Use the PDR algorithm to predict the next touch point after the user's finger moves (x i ,y i )Location:

[0113]

[0114] Among them, θ i is the direction angle of the user's finger movement;

[0115] Calculate the straight-line distance c between the two touch points i :

[0116]

[0117] Use your finger to move distance c i and unit time interval Δt to calculate the current speed V i :

[0118]

[0119] Calculate all speed values ​​during the finger movement and record the maximum value V max ;

[0120] Calculate the minor semiaxis b i :

[0121] b i =(V max -V i )×Δt+e

[0122] Among them, b i is the vertical distance of the user touch point position change at the current speed, V max is the maximum speed, V i is the current speed, e is the empirical error;

[0123] Calculate the major semiaxis a i :

[0124]

[0125] Among them, a i is the maximum expansion distance of the elliptical window;

[0126] According to the semi-major axis a i , minor semi-axis b i and focal length c i , generating an elliptical dynamic fingerprint window, the center of which is (x i ,y i ).

[0127] The user's dynamic fingerprint data is collected in real time through the headset touch sensor, and an elliptical dynamic fingerprint window is generated based on the real-time dynamic fingerprint data to predict the movement trajectory of the finger, thereby achieving accurate tracking and identification of the user's dynamic finger behavior, and facilitating the user to monitor and dynamically adjust the touch action in real time. The elliptical dynamic fingerprint window can adapt to fingerprint contacts at various angles, avoiding recognition errors caused by fingerprint contact angles, thereby enhancing the system's adaptability to complex touch operations, improving the accuracy and real-time performance of fingerprint matching, reducing the occurrence of misoperation, and effectively preventing attacks from fake fingerprints, thereby improving the user's convenience and satisfaction when using headphones.

[0128] S3, converting the elliptical dynamic fingerprint window into a rectangular dynamic fingerprint window to perform fingerprint data matching;

[0129] Furthermore, converting the elliptical dynamic fingerprint window into a rectangular dynamic fingerprint window includes:

[0130] The range of calculating the rectangular dynamic fingerprint window includes the number of left-shifted grids, the number of right-shifted grids, the number of upward-shifted grids and the number of downward-shifted grids;

[0131] Shift left by number of grids:

[0132]

[0133] Shift right by number of grids:

[0134]

[0135] Move up the grid number:

[0136]

[0137] Move down the number of grids:

[0138]

[0139] Among them, N ileft is the number of grid cells on the left boundary, N iright is the number of grid cells on the right boundary, N ibottom is the number of grid cells on the upper boundary, N itop is the number of grids at the lower boundary, α is the rotation angle, and cellsize is the size of the grid;

[0140] According to the boundary of the rectangular dynamic fingerprint window, the elliptical dynamic fingerprint window data is mapped into the rectangular dynamic fingerprint window to generate a rectangular dynamic fingerprint window containing the elliptical dynamic fingerprint window.

[0141] By converting the elliptical dynamic fingerprint window into a rectangular dynamic fingerprint window, the fingerprint matching process can be simplified, the speed and accuracy of fingerprint matching can be improved, and the delay in the recognition process can be reduced. Through this conversion, the calculation complexity is reduced, the processing efficiency is improved, the consumption of system resources, the pressure of data transmission and storage are reduced, fast and accurate fingerprint matching is achieved, and the waiting time of users in touch operations is reduced. At the same time, by mapping data to a rectangular window, the consistency and standardization of data processing are enhanced, the reliability and stability of the system are improved, and an efficient anti-mistouch function is ensured, thereby improving user experience and satisfaction.

[0142] Furthermore, fingerprint data matching is performed;

[0143] Fingerprint feature point matching includes:

[0144] Collect real-time dynamic fingerprint data, build a rectangular dynamic fingerprint window, record all rectangular dynamic fingerprint windows that change with the finger, select the rectangular dynamic fingerprint window whose corner is closest to the center point, and record the coordinates of the upper left corner (x min ,y min ) and the lower right corner coordinate (x max ,y max ), check the extracted feature point coordinates, and satisfy x min <x<x max and min <y<y max The feature points that meet the conditions are retained, and the feature points that do not meet the conditions are filtered out;

[0145] Extract fingerprint feature points p and each fingerprint template feature point q from real-time dynamic fingerprint data and fingerprint database respectively, calculate the Euclidean distance between each feature point p and feature point q, select the feature point pair with the smallest Euclidean distance as the final matching feature point pair, and calculate the fingerprint matching degree S based on the Euclidean distance between the final matching feature point pairs:

[0146]

[0147] Where M is the number of matching feature point pairs, dist(p f ,q f ) is the matching feature point pair (p f ,q f ), p f is the real-time dynamic fingerprint data feature point in the fth matching feature point pair, q f is the fingerprint feature template feature point in the fth matching feature point pair;

[0148] Set the fingerprint matching threshold St and compare it with the fingerprint matching S:

[0149] If S≥St, the user identity authentication is determined to be successful, and the verification result is sent to the mobile application via Bluetooth. The mobile application displays a verification success message, allowing the user to continue the operation;

[0150] If S<St, the user identity authentication is determined to have failed, and the headset automatically triggers the anti-mistouch mechanism, locks the touch operation, restores the touch function after 5 seconds, and sends the verification information to the mobile phone application via Bluetooth to warn the user.

[0151] By matching fingerprint data in a rectangular dynamic fingerprint window, an efficient fingerprint verification process is achieved. Feature points are extracted from real-time dynamic fingerprint data and confined to a rectangular window. The matching degree is calculated with the fingerprint template in the database, thereby improving the accuracy of fingerprint recognition and reducing the possibility of mismatching. The fingerprints of different users can be distinguished, ensuring high accuracy and efficiency of fingerprint recognition, preventing access by unauthorized users, and ensuring user data security and privacy protection. In addition, rapid response to user operations and efficient identity authentication are achieved, reducing the consumption of computing resources, improving the operating efficiency of the headset system, extending the service life of the headset, reducing maintenance costs, and enhancing the user experience of the headset.

[0152] S4, collecting user headphone usage data, building a touch scenario analysis model, and obtaining the headphone usage scenario;

[0153] Furthermore, the user's headphone usage data is collected, and a touch scenario analysis model is constructed to obtain the headphone usage scenarios including:

[0154] Collect the headset history usage data of the mobile phone application, generate the headset history usage data set and divide it into a training set and a test set, the headset history usage data set includes feature parameters and label data, the feature parameters include average acceleration, angular velocity of headset rotation, ambient light intensity, ambient noise level and heart rate change, the label data refers to the headset usage scenario corresponding to each touch event, including emergency scenario, sports scenario and static scenario;

[0155] Extract the headphone history and use the characteristic parameters in the dataset to form a high-dimensional feature matrix Q:

[0156]

[0157] in is the average acceleration, w is the angular velocity of the headset rotation, O is the ambient light intensity, U is the ambient noise level, ΔHR is the heart rate change, and m is the number of samples;

[0158] Use convolutional neural network to build a touch scene analysis model, including input layer, convolution layer, pooling layer, fully connected layer and output layer;

[0159] The input content of the input layer is a high-dimensional feature matrix Q;

[0160] The convolution layer extracts features through multiple convolution layers, each of which is composed of multiple convolution kernels and activation functions to generate a feature map;

[0161] The pooling layer pools the feature map output by the convolution layer, reduces the dimension of the feature map, and extracts the main features;

[0162] The fully connected layer flattens the output of the pooling layer and performs feature combination and classification through the fully connected layer;

[0163] The output layer uses a Softmax activation function to perform multi-classification and outputs a probability distribution of headphone usage scenarios;

[0164] Use the training set data to train the model, use the cross entropy loss function to calculate the model error, and use the Adam optimizer to update the parameters;

[0165] Use the test set to evaluate the performance of the model and optimize the model through hyperparameter tuning and cross-validation;

[0166] The real-time collected user headphone usage data is input into the trained model to obtain the headphone usage scenario.

[0167] By collecting the user's headphone usage data and building a touch scenario analysis model, the operating logic of the headphones can be dynamically adjusted according to different usage scenarios. The historical usage data of the headphones is collected, and the convolutional neural network is used for model training and optimization. Through this scenario analysis model, the user's current scenario can be intelligently identified, and intelligent identification and classification of user usage scenarios can be achieved. It provides a personalized headphone control experience and effectively reduces accidental touches. Especially in sports or emergency situations, scenario perception ability is particularly important, thereby improving the intelligence level of the headphones.

[0168] S5. Dynamically adjust the operation logic of the headset according to the usage scenario of the headset;

[0169] Furthermore, according to the usage scenario of the headset, the operation logic of the headset is dynamically adjusted, including:

[0170] The earphone usage scenarios include riding, driving, walking, running and quiet scenarios. The earphone usage scenarios are prioritized, and the user's safety, practicality and needs are used as the principles for setting the scenario priorities.

[0171] When the user is riding or driving, it is an emergency situation and has the highest priority. The user focuses on the road and traffic conditions, disables touch control and enables voice control, and turns on the headset ambient sound mode. The ambient sound mode can adjust the amount of ambient sound received according to the user's needs. Turning on the ambient sound mode will also weaken the noise reduction function of the headset and enhance the human voice for clear calls and voice communication;

[0172] When the user is walking or running, it is a sports scenario, which has the second highest priority. The user's body and hands are in motion, and the sports mode is turned on. When the user starts to exercise, the music will be automatically played, and when the user stops exercising, the music will be automatically paused.

[0173] When the user is in a stationary state, it is a quiet scenario and has a general priority. The user uses the headset normally and all headset functions are open. The user can use the complete headset functions.

[0174] By dynamically adjusting the operating logic according to different headphone usage scenarios, a more intelligent and user-friendly headphone control experience is provided, ensuring that users get the best feedback in different scenarios. When users are riding or driving, the headphones will disable touch control to avoid accidental touches, and enable voice control and ambient sound mode to improve safety. In sports scenarios, the headphones will simplify touch control, automatically play or pause music, and enhance ease of use. The headphone operation logic is dynamically adjusted according to the user's usage scenario, which significantly reduces the occurrence of accidental touches, improves the safety and convenience of the headphones, and enhances user satisfaction.

[0175] Example 2, reference Figure 3, which is the second embodiment of the present invention, and which is different from the previous embodiment, provides a headphone anti-mistouch control system based on fingerprint recognition, which includes:

[0176] The data collection and preprocessing module is used to collect user static fingerprint data and dynamic fingerprint data and preprocess the fingerprint;

[0177] A window conversion module, used for generating an elliptical dynamic fingerprint window according to the collected user fingerprint data and converting the elliptical dynamic fingerprint window into a rectangular dynamic fingerprint window;

[0178] Fingerprint matching module, used to match fingerprint feature points of dynamic fingerprint data collected in real time with fingerprint data in the fingerprint database;

[0179] Data analysis module, used to build a touch dynamic analysis model and analyze the user's headphone usage scenario;

[0180] The dynamic adjustment module is used to dynamically adjust the operating logic of the headset according to the usage scenario of the headset.

[0181] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0182] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0183] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0184] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0185] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for preventing accidental touch of earphones based on fingerprint recognition, characterized in that: include, Collect user static fingerprint data and dynamic fingerprint data for pre-processing and store in the fingerprint database; Generate an elliptical dynamic fingerprint window based on the user's dynamic fingerprint data collected in real time; Convert the elliptical dynamic fingerprint window into a rectangular dynamic fingerprint window to perform fingerprint feature point matching; Collect user headphone usage data, build a touch scenario analysis model, and obtain the headphone usage scenario; Dynamically adjust the operating logic of the headphones according to the usage scenario of the headphones.

2. The method for preventing accidental touch of earphones based on fingerprint recognition as claimed in claim 1, characterized in that: The collecting of static fingerprint data and dynamic fingerprint data of the user for preprocessing and storing in the fingerprint database means that when the user uses the headset for the first time, the user's fingerprint image is collected using the headset supporting application, the noise in the fingerprint image is removed by a filter, the contrast of the fingerprint image is enhanced by using image enhancement technology, and the grayscale image is converted into a binary image; The Zhang-Suen thinning algorithm is used to thin the ridges in the binary image to a single pixel width, and static feature points including ridge endpoints and bifurcation points are extracted from the thinned fingerprint image, and description information is generated for each static feature point, including position and direction; Integrate the extracted static feature point information into a unified format, including the position, direction and type of each static feature point, and generate a static fingerprint data feature vector, wherein the static fingerprint data feature vector includes the position coordinates, direction angle and number of the static feature points; Installing capacitive touch sensors and pressure sensors on the touch control area of ​​the headset surface; When the user uses the headset, dynamic fingerprint data is collected in real time. The dynamic fingerprint data includes time series data generated during the user operation, and the current fingerprint image, finger position, pressure intensity and touch type are recorded at each time point. The touch type includes light touch, long press and slide. Normalizing the fingerprint position coordinates and pressure values ​​in the dynamic fingerprint data to generate a dynamic fingerprint data feature vector, wherein the dynamic fingerprint data feature vector includes the dynamic fingerprint position, pressure value and timestamp; The static fingerprint data feature vector and the dynamic fingerprint data feature vector are normalized and concatenated to form a multi-dimensional fusion data vector. A fingerprint feature template is generated based on the multi-dimensional fusion data vector and stored in a database.

3. The method for preventing accidental touch of earphones based on fingerprint recognition as claimed in claim 2, characterized in that: The method of generating an elliptical dynamic fingerprint window based on the user dynamic fingerprint data collected in real time includes: Calculate the dynamic fingerprint window parameters and set the current touch point position of the user's finger to (x i-1 ,y i-1 ), the next touch point position is (x i ,y i ); Collect historical touch data of the user's headset and collect data of N touch points; Calculate the distance difference between each touch: Among them, (x i ′,y i ′) is the position of the finger's i-th touch in the user's headset historical touch data; Calculate the average distance between all touch points Use the PDR algorithm to predict the next touch point after the user's finger moves (x i ,y i )Location: Among them, θ i is the direction angle of the user's finger movement; Calculate the straight-line distance c between the two touch points i : Use your finger to move distance c i and unit time interval Δt to calculate the current speed V i : Calculate all speed values ​​during the finger movement and record the maximum value V max ; Calculate the minor semiaxis b i : b i =(V max -V i )×Δt+e Among them, b i is the vertical distance of the user touch point position change at the current speed, V max is the maximum speed, V i is the current speed, e is the empirical error; Calculate the major semiaxis a i : Among them, a i is the maximum expansion distance of the elliptical window; According to the semi-major axis a i , minor semi-axis b i and focal length c i , generating an elliptical dynamic fingerprint window, the center of which is (x i ,y i ).

4. The method for preventing accidental touch of earphones based on fingerprint recognition as claimed in claim 3, characterized in that: The converting of the elliptical dynamic fingerprint window into a rectangular dynamic fingerprint window comprises: The range of calculating the rectangular dynamic fingerprint window includes the number of left-shifted grids, the number of right-shifted grids, the number of upward-shifted grids and the number of downward-shifted grids; Shift left by number of grids: Shift right by number of grids: Move up the grid number: Move down the number of grids: Among them, N ileft is the number of grid cells on the left boundary, N iright is the number of grid cells on the right boundary, N ibottom is the number of grid cells on the upper boundary, N itop is the number of grids at the lower boundary, α is the rotation angle, and cellsize is the size of the grid; According to the boundary of the rectangular dynamic fingerprint window, the elliptical dynamic fingerprint window data is mapped into the rectangular dynamic fingerprint window to generate a rectangular dynamic fingerprint window containing the elliptical dynamic fingerprint window.

5. The method for preventing accidental touch of earphones based on fingerprint recognition as claimed in claim 4, characterized in that: The fingerprint feature point matching includes: Collect real-time dynamic fingerprint data, build a rectangular dynamic fingerprint window, record all rectangular dynamic fingerprint windows that change with the finger, select the rectangular dynamic fingerprint window whose corner is closest to the center point, and record the coordinates of the upper left corner (x min ,y max ) and the lower right corner coordinate (x max ,y max ), check the extracted feature point coordinates, and satisfy x min <x<x max and min <y<y max The feature points that meet the conditions are retained, and the feature points that do not meet the conditions are filtered out; Extract fingerprint feature points p and each fingerprint template feature point q from real-time dynamic fingerprint data and fingerprint database respectively, calculate the Euclidean distance between each feature point p and feature point q, select the feature point pair with the smallest Euclidean distance as the final matching feature point pair, and calculate the fingerprint matching degree S based on the Euclidean distance between the final matching feature point pairs: Where M is the number of matching feature point pairs, dist(p f ,q f ) is the matching feature point pair (p f ,q f ), p f is the real-time dynamic fingerprint data feature point in the fth matching feature point pair, q f is the fingerprint feature template feature point in the fth matching feature point pair; Set the fingerprint matching threshold St and compare it with the fingerprint matching S: If S≥St, the user identity authentication is determined to be successful, and the verification result is sent to the mobile application via Bluetooth. The mobile application displays a verification success message, allowing the user to continue the operation; If S<St, the user identity authentication is determined to have failed, and the headset automatically triggers the anti-mistouch mechanism, locks the touch operation, restores the touch function after 5 seconds, and sends the verification information to the mobile phone application via Bluetooth to warn the user.

6. The method for preventing accidental touch of earphones based on fingerprint recognition as claimed in claim 5, characterized in that: The collecting of user headphone usage data, building a touch scenario analysis model, and obtaining headphone usage scenarios include: Collect the headset history usage data of the mobile phone application, generate the headset history usage data set and divide it into a training set and a test set, the headset history usage data set includes feature parameters and label data, the feature parameters include average acceleration, angular velocity of headset rotation, ambient light intensity, ambient noise level and heart rate change, the label data refers to the headset usage scenario corresponding to each touch event, including emergency scenario, sports scenario and static scenario; Extract the headphone history and use the characteristic parameters in the dataset to form a high-dimensional feature matrix Q: in is the average acceleration, w is the angular velocity of the headset rotation, O is the ambient light intensity, U is the ambient noise level, ΔHR is the heart rate change, and m is the number of samples; Use convolutional neural network to build a touch scene analysis model, including input layer, convolution layer, pooling layer, fully connected layer and output layer; The input content of the input layer is a high-dimensional feature matrix Q; The convolution layer extracts features through multiple convolution layers, each of which is composed of multiple convolution kernels and activation functions to generate a feature map; The pooling layer pools the feature map output by the convolution layer, reduces the dimension of the feature map, and extracts the main features; The fully connected layer flattens the output of the pooling layer and performs feature combination and classification through the fully connected layer; The output layer uses a Softmax activation function to perform multi-classification and outputs a probability distribution of headphone usage scenarios; Use the training set data to train the model, use the cross entropy loss function to calculate the model error, and use the Adam optimizer to update the parameters; Use the test set to evaluate the performance of the model and optimize the model through hyperparameter tuning and cross-validation; The real-time collected user headphone usage data is input into the trained model to obtain the headphone usage scenario.

7. The method for preventing accidental touch of earphones based on fingerprint recognition as claimed in claim 6, characterized in that: The dynamically adjusting the operation logic of the headset according to the usage scenario of the headset includes: The earphone usage scenarios include riding, driving, walking, running and quiet scenarios, and the earphone usage scenarios are prioritized; When the user is riding or driving, it is an emergency situation and has the highest priority. The user focuses on the road and traffic conditions, disables touch control, enables voice control, and turns on the headphone ambient sound mode; When the user is walking or running, it is a sports scenario, which has the second highest priority. When the user's body and hands are in motion, the sports mode is turned on. When the user starts exercising, the music will automatically play, and when the user stops exercising, the music will automatically pause. When the user is at rest, it is a quiet scenario with general priority, and the user uses the headset normally.

8. A headphone anti-mis-touch control system based on fingerprint recognition according to the headphone anti-mis-touch control method based on fingerprint recognition as claimed in any one of claims 1 to 7, characterized in that: include, The data collection and preprocessing module is used to collect user static fingerprint data and dynamic fingerprint data and preprocess the fingerprint; A window conversion module, used for generating an elliptical dynamic fingerprint window according to the collected user fingerprint data and converting the elliptical dynamic fingerprint window into a rectangular dynamic fingerprint window; Fingerprint matching module, used to match fingerprint feature points of dynamic fingerprint data collected in real time with fingerprint data in the fingerprint database; Data analysis module, used to build a touch dynamic analysis model and analyze the user's headphone usage scenario; The dynamic adjustment module is used to dynamically adjust the operating logic of the headset according to the usage scenario of the headset.

9. A computer device comprising: Memory and processor; The memory stores a computer program, wherein the processor implements the steps of the earphone anti-mistouch control method based on fingerprint recognition according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the earphone anti-mistouch control method based on fingerprint recognition according to any one of claims 1 to 7 are implemented.

Images