Mini computer operation status information interactive control method and system

Abstract

The present invention discloses a method and system for interactive control of mini computer operation status information, which relates to the technical field of computer information interactive control, including the PC end collecting system hardware data through an application, the secondary screen end collecting biometric data through a sensor, and driving fusion according to the quality of the biometric data to perform user identity recognition; the secondary screen end receives the system hardware data and analyzes the system operation status; the secondary screen end receives the user touch command to generate a control command and transmits it to the PC end for system control. The present invention collects the user's hard biometric data and soft biometric data to obtain a fusion score respectively and calculates the biometric data fusion score to perform user identity recognition, and then controls the locking state of the connected serial port, which greatly improves the accuracy and flexibility of user identity recognition and ensures the security of data. The secondary screen end recognizes the user's touch signal and converts it into a control command for execution, which improves the convenience of user operation.

Description

Technical Field

[0001] The present invention relates to the technical field of computer information interactive control, and in particular to a method and system for interactive control of running status information of a mini computer. Background Art

[0002] With the rapid development of information technology, computers have become an indispensable tool in people's daily life and work. Especially in recent years, with the improvement of hardware performance and the advancement of software technology, the application areas of computers have continued to expand. Traditional computer systems mainly rely on users to interact through keyboards and mice, while modern computers are increasingly introducing a variety of human-computer interaction methods, such as touch screens, voice recognition, biometric recognition, etc., which greatly improve user experience and system security. However, there are still problems in the existing technology. Existing biometric recognition is mostly a single mode, which cannot fully utilize the advantages of multimodal biometric data. In addition, the collection and processing of system operation status information is mainly concentrated on the PC side, which increases the operation burden of the PC side. Summary of the invention

[0003] In view of the problems existing in the above-mentioned existing mini computer operation status information interactive control method and system, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is that there are still problems in the prior art. Existing biometric recognition is mostly single mode, which cannot fully utilize the advantages of multimodal biometric data, and the collection and processing of system operation status information are mainly concentrated on the PC side, which increases the operation burden of the PC side.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a method for interactively controlling the operating status information of a mini computer, which comprises: a PC side collects system hardware data through an application, a sub-screen side collects biometric data through a sensor, and performs user identity recognition based on the quality-driven fusion of the biometric data; the sub-screen side receives the system hardware data and analyzes the system operating status; the sub-screen side receives user touch instructions to generate control commands and transmits them to the PC side for system control.

[0006] As a preferred solution of the mini computer running status information interactive control method described in the present invention, wherein: the PC end collects system hardware data through an application, and the secondary screen end collects biometric data through a sensor, which means that the PC end collects system hardware data through an application, and the secondary screen end collects user biometric data through a sensor, and the data collection and transmission interval is set to 1s. The PC end transmits the collected system hardware data to the secondary screen end through the connection serial port according to the data transmission protocol packet. The secondary screen end locks the connection serial port and refuses to accept system hardware data before performing user identity recognition. The biometric data collected by the secondary screen end includes hard biometric data and soft biometric data. The hard biometric data includes fingerprint images, facial images and sound samples, and the soft biometric data includes skin color images, gender recognition images and touch habit data. The secondary screen end stores the user biometric data collected for the first time as a user identity template.

[0007] As a preferred solution of the minicomputer operation status information interactive control method of the present invention, wherein: the user identity recognition based on the biometric data quality driven fusion includes calculating the hard biometric data fusion score S y and soft biometric data fusion score S r , and define the biometric data fusion score S as:

[0008] ;

[0009] Where a and b are the fusion weights of the hard biometric data fusion score and the soft biometric data fusion score respectively;

[0010] The training set and Adam optimizer are used to optimize the optimal fusion weights a and b, and the biometric data fusion score S is obtained based on the optimal fusion weights a and b;

[0011] The secondary screen sets the identity recognition threshold Z. When S is greater than or equal to Z, the secondary screen recognizes the user identity, unlocks the serial port to receive the system hardware data transmitted by the PC, unpacks it according to the data transmission protocol, and displays the unpacked system hardware data.

[0012] When S is less than Z, the secondary screen fails to pass the user identity recognition, and automatically sends an identity recognition failure notification to the PC. The PC stops transmitting the packaged system hardware data to the secondary screen and temporarily stores it in the local database.

[0013] As a preferred solution of the minicomputer operation status information interactive control method of the present invention, wherein: the calculation of the hard biometric data fusion score S y include,

[0014] The fingerprint image is segmented into fingerprint image blocks, the gradient strength of the fingerprint image block pixels is calculated using the Sobel operator, and the fingerprint image quality score Q1 is calculated:

[0015] ;

[0016] Among them I i is the i-th fingerprint image block, is the gradient strength of the pixel of the ith fingerprint image block, is the gradient strength of the j pixels adjacent to the ith fingerprint image block, M is the number of adjacent pixels, and N is the number of fingerprint image blocks;

[0017] The facial image is divided into facial image blocks, and the LBP histogram of each facial image block is calculated using the local binary pattern, and the LBP feature vector H of the facial image is obtained by summarizing:

[0018] ;

[0019] where h i is the frequency of the ith facial image block, and P is the number of facial image blocks;

[0020] Calculate the mean and standard deviation of the LBP feature vector of the facial image and calculate the facial image quality score Q2 by comprehensive weighting:

[0021] ;

[0022] Among them is is the mean of the LBP feature vector, is the standard deviation of the LBP feature vector, α and β are the weights of the mean and standard deviation;

[0023] The sound sample power and noise sample power are calculated by averaging the squares and summing them, and the signal-to-noise ratio (SNR) of the sound sample and the noise sample is calculated. The sound sample quality score Q3 is calculated based on the signal-to-noise ratio (SNR):

[0024] ;

[0025] The texture features of fingerprint images are extracted using Gabor filters, the facial features of facial images are extracted using principal component analysis, the sound features of sound samples are extracted through short-time Fourier transform and Mel-frequency cepstral coefficients, and the noise samples are identified, and the corresponding features of the user identity template are extracted simultaneously;

[0026] Use the Euclidean algorithm to calculate the matching scores s1, s2 and s3 of the texture features of the fingerprint image, the facial features of the facial image and the sound features in the sound sample with the corresponding features of the user identity template respectively;

[0027] The hard biometric data fusion weights and are calculated based on the fingerprint image quality score Q1, the facial image quality score Q2, and the voice sample quality score Q3:

[0028] ;

[0029] Calculate the total score Q based on Q1, Q2 and Q3, and obtain the proportion of Q1, Q2 and Q3 in the total score Q respectively. Multiply the proportion of Q1, Q2 and Q3 by the fusion weight and obtain the weights w1, w2 and w3 of Q1, Q2 and Q3. Calculate the hard biometric data fusion score S based on the obtained weights. y :

[0030] .

[0031] As a preferred solution of the minicomputer operation status information interactive control method of the present invention, wherein: the calculation of the soft biometric data fusion score S r include,

[0032] Perform white balance processing on the skin color image, convert the skin color image from RGB space to YCbCr space, and extract the skin color area:

[0033] ;

[0034] Where Sk(x, y) is the skin color judgment value of the point (x, y) in the skin color image, 1 is the skin color area, 0 is the non-skin color area, Cb(x, y) is the blue chromaticity component of the point (x, y), and Cr(x, y) is the red chromaticity component of the point (x, y);

[0035] Calculate the skin color image quality score Q4 based on the extracted skin color area:

[0036] ;

[0037] Where N p is the total number of pixels in the skin color image;

[0038] The gender features in the gender recognition image are extracted through the image recognition algorithm, and the gender classification is performed using the support vector machine to obtain the gender classification male probability P m and the probability of being female P f , and the gender classification probability is used as the gender recognition image quality score Q5 according to the user's gender:

[0039] ;

[0040] Extract touch features from touch habit data and calculate the consistency and diversity of touch features:

[0041] ;

[0042] Where Co is the touch feature consistency, Va is the touch feature diversity, K is the number of touch features, T k is the kth touch feature, is the standard deviation of the touch feature, is the mean value of the touch feature, is the maximum value of the touch feature, is the minimum value of the touch feature;

[0043] The ratio of touch feature consistency to touch feature diversity is used as the touch habit data quality score Q6:

[0044] ;

[0045] Extract skin color features from the skin color image, combine gender features and touch features, and also extract corresponding features of the user identity template. Calculate matching scores s4, s5, and s6 of the skin color image, gender recognition image, and touch habit data based on the Euclidean algorithm.

[0046] Similarly, the soft biometric data fusion weights and are calculated. Based on the soft biometric data fusion weights and, the skin color image quality score, gender recognition image quality score, and touch habit data quality score are calculated, and the soft biometric data fusion score S is further calculated. r .

[0047] As a preferred solution of the mini computer operation status information interactive control method of the present invention, wherein: the secondary screen receives the system hardware data and analyzes the system operation status, which means that the secondary screen receives the system hardware data packet transmitted by the PC end through the serial port after user identity recognition, and unpacks it to obtain the system hardware data;

[0048] Use convolutional neural networks to build an anomaly recognition model, set the input layer format to the system hardware data format, and the output layer format to the system operation status analysis results, including abnormal and normal. Obtain historical system hardware data from the PC as a model training set to train the anomaly recognition model;

[0049] The secondary screen inputs the unpacked system hardware data into the abnormal recognition model to obtain the system operation status. If it is normal, the secondary screen sends a normal signal to the PC to continuously collect system hardware data for system operation status detection. If it is abnormal, the secondary screen sends an abnormal detection signal to the PC. After receiving the abnormal detection signal, the PC starts system self-check and sends an abnormal notification to the user.

[0050] As a preferred solution of the method for interactively controlling the operating status information of a mini computer described in the present invention, wherein: the secondary screen receives a user touch command to generate a control command and transmits it to the PC for system control, the secondary screen receives a user touch signal through an operation interface, and converts the touch signal into a control command, the secondary screen identifies the implementation subject of the control command, if the implementation subject is the secondary screen, the control command is directly executed by the secondary screen, if the implementation subject is the PC, the secondary screen transmits the control command to the PC through the serial port for implementation, the secondary screen monitors the execution status of the PC command in real time and notifies the user of the execution status through the operation interface.

[0051] Another object of the present invention is to provide a mini computer operation status information interactive control system, which comprises:

[0052] A data collection module, used to collect system hardware data and user biometric data, and store the user biometric data collected for the first time as a user identity template;

[0053] An identity recognition module, used to perform user identity recognition based on the collected user biometric data and user identity template, and control the locking state of the connection serial port based on the recognition result;

[0054] The anomaly recognition module is used to build an anomaly recognition model, identify the system operation status based on the collected system hardware data, and implement processing measures based on the recognition results;

[0055] The touch control module is used to convert the user's touch signal into a control command and implement it.

[0056] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned mini computer running status information interactive control method when executing the computer program.

[0057] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned mini-computer operation status information interactive control method.

[0058] The beneficial effects of the present invention are as follows: the present invention collects the user's hard biometric data and soft biometric data to obtain fusion scores respectively and calculates the biometric data fusion score to perform user identity identification, thereby controlling the locking state of the connection serial port, thereby greatly improving the accuracy and flexibility of user identity identification and ensuring data security. At the same time, by collecting system hardware data to identify the system operation state, the stability of the system operation is improved, and the secondary screen recognizes the user's touch signal and converts it into a control instruction for implementation, thereby improving the convenience of user operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] 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.

[0060] Figure 1 The figure is a flowchart of a method for interactively controlling the operation status information of a mini computer.

[0061] Figure 2 A flowchart of user identification.

[0062] Figure 3 This is a structural diagram of the mini computer operation status information interactive control system. DETAILED DESCRIPTION

[0063] 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.

[0064] 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.

[0065] 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. Example 1

[0066] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and which provides a mini computer operation status information interactive control method, the mini computer operation status information interactive control method comprising:

[0067] S1. The PC side collects system hardware data through the application, and the secondary screen side collects biometric data through sensors, and drives fusion based on the quality of biometric data to identify the user;

[0068] Specifically, the PC collects system hardware data through the application, and the sub-screen collects biometric data through the sensor. This means that the PC collects system hardware data through the application, and the sub-screen collects user biometric data through the sensor. The data collection and transmission interval is set to 1s. The PC transmits the collected system hardware data to the sub-screen through the connection serial port in a data transmission protocol packet. The sub-screen locks the connection serial port and refuses to receive system hardware data before performing user identity recognition. The biometric data collected by the sub-screen includes hard biometric data and soft biometric data. The hard biometric data includes fingerprint images, facial images, and voice samples. The soft biometric data includes skin color images, gender recognition images, and touch habit data. The sub-screen stores the user biometric data collected for the first time as a user identity template.

[0069] The PC application can collect system hardware data in real time, including CPU temperature, usage rate, memory status, etc., to ensure comprehensive monitoring of the system operation status. The sensor on the secondary screen can collect the user's biometric data in real time, including fingerprints, faces and voices, to ensure the accuracy of identity recognition. The 1-second collection and transmission interval can ensure the real-time nature of the data, while avoiding the occupation of system resources by frequent data transmission. The data transmission protocol packet can ensure the integrity and security of the data during the transmission process. Transmission through the serial port connection can improve the speed and stability of data transmission. The secondary screen locks the connection serial port to prevent unauthorized data transmission, ensuring that system hardware data is received only after the user identity is authenticated. By combining hard biometric data and soft biometric data, the system can perform more accurate and comprehensive user identity recognition, improve the reliability and accuracy of identity recognition, and effectively prevent identity impersonation and forgery. The user's biometric data collected for the first time is stored as an identity template, which can provide a reference in the subsequent identity authentication process to ensure the efficiency and accuracy of identity authentication.

[0070] Further, the user identification is performed based on the biometric data quality driven fusion, including calculating the hard biometric data fusion score S y and soft biometric data fusion score S r , and define the biometric data fusion score S as:

[0071] ;

[0072] Where a and b are the fusion weights of the hard biometric data fusion score and the soft biometric data fusion score respectively;

[0073] The training set and Adam optimizer are used to optimize the optimal fusion weights a and b, and the biometric data fusion score S is obtained based on the optimal fusion weights a and b;

[0074] The secondary screen sets the identity recognition threshold Z, which is set based on the comprehensive analysis of the user's biometric data. When S is greater than or equal to Z, the secondary screen recognizes the user's identity, unlocks the serial port to receive the system hardware data transmitted by the PC, unpacks it according to the data transmission protocol, and displays the unpacked system hardware data;

[0075] When S is less than Z, the secondary screen fails to pass the user identity recognition, and automatically sends an identity recognition failure notification to the PC. The PC stops transmitting the packaged system hardware data to the secondary screen and temporarily stores it in the local database.

[0076] By calculating the fusion scores of hard biometric data and soft biometric data separately, we can make full use of data of different types of biometrics to improve the accuracy of user identification. Hard biometric data is highly unique and can provide reliable identity authentication; soft biometric data can provide additional auxiliary information to improve the overall recognition effect. Using the training set and Adam optimizer, we can automatically adjust the fusion weights of hard biometric data and soft biometric data to find the optimal weight combination and improve the accuracy of identity recognition. Adam optimizer can quickly converge to the optimal solution, reduce training time, and improve the generalization ability of the model. The fusion score is calculated by the optimal fusion weight. By comprehensively considering the weights of hard biometrics and soft biometrics data, the final score is more representative and reliable, the accuracy of recognition is improved, the false recognition rate is reduced, and the security of the system is enhanced. By setting the identity recognition threshold, the sensitivity of recognition can be adjusted according to actual needs to balance the recognition accuracy and false recognition rate. When the fusion score is greater than or equal to the threshold, the secondary screen unlocks the connection serial port to ensure that only users who have passed the identity authentication can access the system hardware data, thereby improving the system security. When the user identity recognition fails, the secondary screen automatically sends an identity recognition failure notification to the PC, and the PC stops data transmission and temporarily stores data, which can effectively prevent unauthorized users from obtaining system information.

[0077] It should be noted that the calculation of the hard biometric data fusion score S y include,

[0078] The fingerprint image is segmented into fingerprint image blocks, the gradient strength of the fingerprint image block pixels is calculated using the Sobel operator, and the fingerprint image quality score Q1 is calculated:

[0079] ;

[0080] Among them I i is the i-th fingerprint image block, is the gradient strength of the pixel of the ith fingerprint image block, is the gradient strength of the j pixels adjacent to the ith fingerprint image block, M is the number of adjacent pixels, and N is the number of fingerprint image blocks;

[0081] The facial image is divided into facial image blocks, and the LBP histogram of each facial image block is calculated using the local binary pattern, and the LBP feature vector H of the facial image is obtained by summarizing:

[0082] ;

[0083] where h i is the frequency of the ith facial image block, and P is the number of facial image blocks;

[0084] Calculate the mean and standard deviation of the LBP feature vector of the facial image and calculate the facial image quality score Q2 by comprehensive weighting:

[0085] ;

[0086] Among them is is the mean of the LBP feature vector, is the standard deviation of the LBP feature vector, α and β are the weights of the mean and standard deviation;

[0087] The sound sample power and noise sample power are calculated by averaging the squares and summing them, and the signal-to-noise ratio (SNR) of the sound sample and the noise sample is calculated. The sound sample quality score Q3 is calculated based on the signal-to-noise ratio (SNR):

[0088] ;

[0089] The texture features of fingerprint images are extracted using Gabor filters, the facial features of facial images are extracted using principal component analysis, the sound features of sound samples are extracted through short-time Fourier transform and Mel-frequency cepstral coefficients, and the noise samples are identified, and the corresponding features of the user identity template are extracted simultaneously;

[0090] The Euclidean algorithm is used to calculate the matching scores s1, s2 and s3 of the texture features of the fingerprint image, the facial features of the facial image and the sound features in the sound sample with the corresponding features of the user identity template. The Euclidean algorithm obtains the matching scores between the features by calculating the distance between the points of the feature vectors.

[0091] The hard biometric data fusion weights and are calculated based on the fingerprint image quality score Q1, the facial image quality score Q2, and the voice sample quality score Q3:

[0092] ;

[0093] Calculate the total score Q based on Q1, Q2 and Q3, and obtain the proportion of Q1, Q2 and Q3 in the total score Q respectively. Multiply the proportion of Q1, Q2 and Q3 by the fusion weight and obtain the weights w1, w2 and w3 of Q1, Q2 and Q3. Calculate the hard biometric data fusion score S based on the obtained weights. y :

[0094] .

[0095] By fusing the feature data of fingerprint images, facial images and voice samples, the accuracy and robustness of user identification can be improved. Single biometric data may be affected by factors such as the environment and equipment, resulting in a decrease in recognition accuracy. Fusion of multiple biometric data can improve the stability and reliability of recognition. The fingerprint image is segmented into fingerprint image blocks, and the Sobel operator is used to calculate the gradient intensity of the fingerprint image block pixels to refine the fingerprint image analysis and improve the accuracy of image quality assessment. The overall image quality assessment may ignore details. Through block segmentation and gradient intensity calculation, the fingerprint image quality can be more accurately assessed to ensure the accuracy of feature extraction. The texture features of facial images are described by LBP to improve the accuracy of facial image quality assessment and feature extraction. The quality and feature extraction of facial images are affected by lighting, posture, etc. The use of LBP can effectively resist these interferences and improve the robustness of recognition. The overall quality and detail features of facial images are comprehensively considered to improve the accuracy of image quality assessment. A single quality indicator may not be able to fully reflect the overall quality of the facial image. The image quality can be reflected by weighted calculation of mean and standard deviation to more comprehensively evaluate the quality of facial images. The quality of sound samples can be evaluated by signal-to-noise ratio to ensure the accuracy of sound feature extraction. Advanced feature extraction methods can be used to improve the extraction and matching accuracy of various types of biometric data. Different biometric data require different feature extraction methods. By combining a variety of advanced feature extraction technologies, the extraction quality of various types of biometric data can be comprehensively improved. The distance between feature vectors is calculated by Euclidean algorithm to obtain matching scores to ensure the accuracy and repeatability of the recognition process. The fusion weight is calculated by quality score to ensure that each biometric data is reasonably weighted during the fusion process. By calculating the total score and the proportion of each quality score in the total score, the weight of each biometric data is reasonably allocated to ensure the fairness and accuracy of the fusion result. Directly using the quality score of each biometric data for fusion may be unfair. By calculating the total score and the proportion distribution, the rationality and accuracy of the fusion result can be improved.

[0096] It should also be noted that the calculation of the soft biometric data fusion score S r include,

[0097] Perform white balance processing on the skin color image, convert the skin color image from RGB space to YCbCr space, and extract the skin color area:

[0098] ;

[0099] Where Sk(x, y) is the skin color judgment value of the point (x, y) in the skin color image, 1 is the skin color area, 0 is the non-skin color area, Cb(x, y) is the blue chromaticity component of the point (x, y), and Cr(x, y) is the red chromaticity component of the point (x, y);

[0100] Calculate the skin color image quality score Q4 based on the extracted skin color area:

[0101] ;

[0102] Where N p is the total number of pixels in the skin color image;

[0103] The gender features in the gender recognition image are extracted through the image recognition algorithm, and the gender classification is performed using the support vector machine to obtain the gender classification male probability P m and the probability of being female P f , and the gender classification probability is used as the gender recognition image quality score Q5 according to the user's gender:

[0104] ;

[0105] Extract touch features from touch habit data and calculate the consistency and diversity of touch features:

[0106] ;

[0107] Where Co is the touch feature consistency, Va is the touch feature diversity, K is the number of touch features, T k is the kth touch feature, is the standard deviation of the touch feature, is the mean value of the touch feature, is the maximum value of the touch feature, is the minimum value of the touch feature;

[0108] The ratio of touch feature consistency to touch feature diversity is used as the touch habit data quality score Q6:

[0109] ;

[0110] Extract skin color features from the skin color image, combine gender features and touch features, and also extract corresponding features of the user identity template. Calculate matching scores s4, s5, and s6 of the skin color image, gender recognition image, and touch habit data based on the Euclidean algorithm.

[0111] Similarly, the soft biometric data fusion weights and are calculated. Based on the soft biometric data fusion weights and, the skin color image quality score, gender recognition image quality score, and touch habit data quality score are calculated, and the soft biometric data fusion score S is further calculated. r .

[0112] By fusing the features of skin color images, gender recognition images, and touch habit data, comprehensive user identity recognition information is provided to improve the accuracy and robustness of recognition. Single soft biometric data may be affected by changes in the environment and personal behavior. By fusing multiple soft biometric data, the stability and reliability of recognition can be improved. White balance processing and YCbCr space conversion can improve the accuracy and robustness of skin color detection. Light changes can affect the accuracy of skin color detection. White balance processing can eliminate the influence of light. YCbCr space can better separate brightness and chromaticity information and extract accurate skin color areas. The quality score of the skin color image is calculated to evaluate the clarity and accuracy of the skin color image. The quality of the skin color image affects the subsequent feature extraction and matching. The quality score evaluation can ensure high-quality skin color images and improve recognition accuracy. By extracting gender features and performing gender classification, the accuracy of gender recognition can be improved. The accuracy of gender feature extraction and classification directly affects the recognition effect. Using SVM for classification can improve classification accuracy. Taking gender classification probability as a quality score can evaluate the credibility of gender recognition images. By calculating the consistency and diversity of touch features, the user's touch habits can be evaluated and reliable touch feature information can be provided. The user's touch behavior has individual differences. The consistency and diversity evaluation can accurately reflect the user's touch habits and improve the accuracy of recognition. The Euclidean algorithm is used to calculate the matching score of each feature and the user's identity template to ensure the accuracy and repeatability of the recognition process. By calculating the fusion weight, the quality scores of each soft biometric data are combined to obtain a comprehensive soft biometric data fusion score to improve the overall performance of recognition.

[0113] S2, the secondary screen receives the system hardware data and analyzes the system operation status;

[0114] Specifically, the secondary screen receives the system hardware data and analyzes the system operation status, which means that the secondary screen receives the system hardware data packet transmitted by the PC through the serial port after user identification, and unpacks it to obtain the system hardware data;

[0115] Use convolutional neural networks to build an anomaly recognition model, set the input layer format to the system hardware data format, and the output layer format to the system operation status analysis results, including abnormal and normal. Obtain historical system hardware data from the PC as a model training set to train the anomaly recognition model;

[0116] The secondary screen inputs the unpacked system hardware data into the abnormal recognition model to obtain the system operation status. If it is normal, the secondary screen sends a normal signal to the PC to continuously collect system hardware data for system operation status detection. If it is abnormal, the secondary screen sends an abnormal detection signal to the PC. After receiving the abnormal detection signal, the PC starts system self-check and sends an abnormal notification to the user.

[0117] Through user identity recognition and data packet transmission, it is ensured that only verified users can access system hardware data, thereby improving the security of data transmission. Through convolutional neural network processing of system hardware data, it is able to efficiently extract data features and identify abnormalities in system operating status. Historical data is used for model training so that the model can learn the characteristics of normal and abnormal system states, thereby improving the accuracy of abnormality identification. Real-time input data is used for operating status detection to ensure the timeliness and accuracy of system status monitoring. Through the feedback mechanism of normal signals, it is ensured that the system runs stably under normal conditions. Continuous monitoring improves the operating efficiency of the system. When an abnormality is detected, the user is immediately notified and the system self-check is started to quickly locate and solve the problem and reduce system downtime.

[0118] S3, the secondary screen receives the user's touch command to generate a control command and transmits it to the PC to control the system;

[0119] Specifically, the secondary screen receives the user's touch command, generates a control command, and transmits it to the PC for system control. The secondary screen receives the user's touch signal through the operation interface, and converts the touch signal into a control command. The secondary screen identifies the implementation subject of the control command. If the implementation subject is the secondary screen, the control command is directly executed by the secondary screen. If the implementation subject is the PC, the secondary screen transmits the control command to the PC through the connected serial port for implementation. The secondary screen monitors the execution status of the PC command in real time and notifies the user of the execution status through the operation interface.

[0120] The touch interface is used to realize the interaction between the user and the system, which is convenient for the user to input control signals and generate corresponding control instructions. The secondary screen identifies the implementing subject of the control instruction. If the implementing subject is the secondary screen, the secondary screen directly executes the control instruction, reducing the delay in instruction transmission and improving the system response speed. If the implementing subject is the PC, the secondary screen transmits the control instruction to the PC through the serial port for implementation. For operations that require PC resources or permissions, the control instructions are transmitted to the PC through the serial port for execution to ensure the safety and effectiveness of the operation. Some control instructions require the use of PC computing resources or require PC permissions to execute. Transmitting control instructions through the serial port can ensure that these operations are executed on the correct subject, ensuring the safety and effectiveness of the operation, and real-time monitoring and feedback of PC instruction execution to ensure that users can understand the progress and results of the operation in a timely manner, thereby improving users' sense of control and satisfaction. Example 2

[0121] Reference Figure 3 , which is the second embodiment of the present invention, and which is different from the previous embodiment, provides a mini computer operation status information interactive control system, which includes:

[0122] A data collection module, used to collect system hardware data and user biometric data, and store the user biometric data collected for the first time as a user identity template;

[0123] An identity recognition module, used to perform user identity recognition based on the collected user biometric data and user identity template, and control the locking state of the connection serial port based on the recognition result;

[0124] The anomaly recognition module is used to build an anomaly recognition model, identify the system operation status based on the collected system hardware data, and implement processing measures based on the recognition results;

[0125] The touch control module is used to convert the user's touch signal into a control command and implement it.

[0126] 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 to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments 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.

[0127] 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.

[0128] 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.

[0129] 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, multiple 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, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit with a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0130] 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 interactively controlling the operation status information of a mini computer, characterized in that: include, The PC side collects system hardware data through the application, and the secondary screen side collects biometric data through sensors, and drives fusion based on the quality of the biometric data to perform user identity recognition; The secondary screen receives system hardware data and analyzes the system operation status; The secondary screen receives the user's touch command, generates a control command, and transmits it to the PC for system control; The PC end collects system hardware data through the application, and the secondary screen end collects biometric data through the sensor. The PC end collects system hardware data through the application, and the secondary screen end collects user biometric data through the sensor. The data collection and transmission interval is set to 1s. The PC end transmits the collected system hardware data to the secondary screen end through the connection serial port according to the data transmission protocol packet. The secondary screen end locks the connection serial port and refuses to receive system hardware data before user identity recognition. The biometric data collected by the secondary screen end includes hard biometric data and soft biometric data. The hard biometric data includes fingerprint images, facial images and sound samples. The soft biometric data includes skin color images, gender recognition images and touch habit data. The secondary screen end stores the user biometric data collected for the first time as a user identity template; The method of driving fusion according to the quality of biometric data to perform user identification includes calculating a hard biometric data fusion score S y and soft biometric data fusion score S r , and define the biometric data fusion score S as: S=a*S y +b*S r ; Where a and b are the fusion weights of the hard biometric data fusion score and the soft biometric data fusion score respectively; The training set and Adam optimizer are used to optimize the optimal fusion weights a and b, and the biometric data fusion score S is obtained based on the optimal fusion weights a and b; The secondary screen sets the identity recognition threshold Z. When S is greater than or equal to Z, the secondary screen recognizes the user identity, unlocks the serial port to receive the system hardware data transmitted by the PC, unpacks it according to the data transmission protocol, and displays the unpacked system hardware data. When S is less than Z, the secondary screen fails to pass the user identification, and automatically sends an identification failure notification to the PC. The PC stops transmitting the packaged system hardware data to the secondary screen and temporarily stores it in the local database. The calculation of the soft biometric data fusion score S r include, Perform white balance processing on the skin color image, convert the skin color image from RGB space to YCbCr space, and extract the skin color area: Where Sk(x, y) is the skin color judgment value of the point (x, y) in the skin color image, 1 is the skin color area, 0 is the non-skin color area, Cb(x, y) is the blue chromaticity component of the point (x, y), and Cr(x, y) is the red chromaticity component of the point (x, y); Calculate the skin color image quality score Q4 based on the extracted skin color area: Where N p is the total number of pixels in the skin color image; The gender features in the gender recognition image are extracted through the image recognition algorithm, and the gender classification is performed using the support vector machine to obtain the gender classification male probability P m and the probability of being female P f , and the gender classification probability is used as the gender recognition image quality score Q5 according to the user's gender: Extract touch features from touch habit data and calculate the consistency and diversity of touch features: Where Co is the touch feature consistency, Va is the touch feature diversity, K is the number of touch features, T k is the kth touch feature, σ(T k ) is the standard deviation of the touch feature, μ(T k ) is the mean value of the touch feature, max(T k ) is the maximum value of the touch feature, min(T k ) is the minimum value of the touch feature; The ratio of touch feature consistency to touch feature diversity is used as the touch habit data quality score Q6: Extract skin color features from the skin color image, combine gender features and touch features, and also extract corresponding features of the user identity template. Calculate matching scores s4, s5, and s6 of the skin color image, gender recognition image, and touch habit data based on the Euclidean algorithm. Similarly, the soft biometric data fusion weights and are calculated. Based on the soft biometric data fusion weights and, the skin color image quality score, gender recognition image quality score, and touch habit data quality score are calculated, and the soft biometric data fusion score S is further calculated. r .

2. The minicomputer operation status information interactive control method according to claim 1, characterized in that: The hard biometric data fusion score S is calculated y include, The fingerprint image is segmented into fingerprint image blocks, the gradient strength of the fingerprint image block pixels is calculated using the Sobel operator, and the fingerprint image quality score Q1 is calculated: Among them I i is the i-th fingerprint image block, G(I i ) is the gradient strength of the pixel of the ith fingerprint image block, G(I ij ) is the gradient strength of the j pixels adjacent to the ith fingerprint image block, M is the number of adjacent pixels, and N is the number of fingerprint image blocks; The facial image is divided into facial image blocks, and the LBP histogram of each facial image block is calculated using the local binary pattern, and the LBP feature vector H of the facial image is obtained by summarizing: H=[h0,h1,......,h P-1 ]; where h i is the frequency of the ith facial image block, and P is the number of facial image blocks; Calculate the mean and standard deviation of the LBP feature vector of the facial image and calculate the facial image quality score Q2 by comprehensive weighting: Q2=a*m LBP +b*s LBP ; where μ LBP is the mean of the LBP feature vector, σ LBP is the standard deviation of the LBP feature vector, α and β are the weights of the mean and standard deviation; The sound sample power and noise sample power are calculated by averaging the squares and summing them, and the signal-to-noise ratio (SNR) of the sound sample and the noise sample is calculated. The sound sample quality score Q3 is calculated based on the signal-to-noise ratio (SNR): The texture features of fingerprint images are extracted using Gabor filters, the facial features of facial images are extracted using principal component analysis, the sound features of sound samples are extracted through short-time Fourier transform and Mel-frequency cepstral coefficients, and the noise samples are identified, and the corresponding features of the user identity template are extracted simultaneously; Use the Euclidean algorithm to calculate the matching scores s1, s2 and s3 of the texture features of the fingerprint image, the facial features of the facial image and the sound features in the sound sample with the corresponding features of the user identity template respectively; The hard biometric data fusion weights and are calculated based on the fingerprint image quality score Q1, the facial image quality score Q2, and the voice sample quality score Q3: Calculate the total score Q based on Q1, Q2 and Q3, and get the proportion of Q1, Q2 and Q3 in the total score Q respectively. Multiply the proportion of Q1, Q2 and Q3 by the fusion weight and get the weights of Q1, Q2 and Q3. <h2 style=";text-align:left;direction:ltr">S<h2 style=";text-align:left;direction:ltr"> y <h2 style=";text-align:left;direction:ltr"> = w1*s1+w2*s2+w3*s3. w1, w2 and w3, calculate the hard biometric data fusion score S according to the obtained weights y :

3. The mini computer operation status information interactive control method as claimed in claim 2, characterized in that: The secondary screen receives the system hardware data and analyzes the system operation status, which means that the secondary screen receives the system hardware data packet transmitted by the PC through the serial port after user identification, and unpacks it to obtain the system hardware data; Use convolutional neural networks to build an anomaly recognition model, set the input layer format to the system hardware data format, and the output layer format to the system operation status analysis results, including abnormal and normal. Obtain historical system hardware data from the PC as a model training set to train the anomaly recognition model; The secondary screen inputs the unpacked system hardware data into the abnormal recognition model to obtain the system operation status. If it is normal, the secondary screen sends a normal signal to the PC to continuously collect system hardware data for system operation status detection. If it is abnormal, the secondary screen sends an abnormal detection signal to the PC. After receiving the abnormal detection signal, the PC starts system self-check and sends an abnormal notification to the user.

4. The minicomputer operation status information interactive control method as claimed in claim 3, characterized in that: The secondary screen receives the user's touch command, generates a control command, and transmits it to the PC for system control. The secondary screen receives the user's touch signal through the operation interface, and converts the touch signal into a control command. The secondary screen identifies the implementation subject of the control command. If the implementation subject is the secondary screen, the control command is directly executed by the secondary screen. If the implementation subject is the PC, the secondary screen transmits the control command to the PC through the serial port for implementation. The secondary screen monitors the execution status of the PC command in real time and notifies the user of the execution status through the operation interface.

5. A mini computer operation status information interactive control system according to any one of claims 1 to 4, characterized in that: include, A data collection module, used to collect system hardware data and user biometric data, and store the user biometric data collected for the first time as a user identity template; An identity recognition module, used to perform user identity recognition based on the collected user biometric data and user identity template, and control the locking state of the connection serial port based on the recognition result; The anomaly recognition module is used to build an anomaly recognition model, identify the system operation status based on the collected system hardware data, and implement processing measures based on the recognition results; The touch control module is used to convert the user's touch signal into a control command and implement it.

6. A computer device comprising: A memory and a processor; the memory stores a computer program, wherein the processor implements the steps of the minicomputer operation status information interactive control method described in any one of claims 1 to 4 when executing the computer program.

7. 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 minicomputer operation status information interactive control method described in any one of claims 1 to 4 are implemented.

Images