Informationized wound ticket endowing system based on facial recognition

Abstract

The invention provides an informatization wound ticket giving system based on facial recognition, and relates to the technical field of identity verification. The system comprises a physiological status monitoring module, a permission adjustment control module, an identity adaptability matching module, a gait behavior verification module and a terminal data linkage module. By analyzing eyeball movement, blinking frequency, pupil change and facial muscle activity and monitoring the physiological state of an individual, dynamic permission adjustment during identity verification is achieved, matching precision is optimized through micro-expression analysis, mismatching caused by emotion fluctuation is reduced, the adaptability of identity verification is enhanced through behavior data in gait analysis, high accuracy is maintained, and the identity verification efficiency is improved. The real-time performance of bill management and access control is improved through a data linkage mechanism among multiple devices, and the verification safety and the remote operation stability are enhanced in combination with multi-dimensional biological characteristics.

Description

Technical Field

[0001] The present invention relates to the technical field of identity authentication, and particularly to an information-based injury ticket granting system based on facial recognition. Background Art

[0002] The technical field of identity authentication includes technical means for confirming personal identity based on biometrics, passwords, tokens, etc. Among them, biometric-based identity authentication mainly includes fingerprint recognition, iris recognition, facial recognition, etc. Relying on computer vision, pattern recognition, and artificial intelligence technologies, it realizes the extraction, analysis, and comparison of individual characteristics to confirm the user's identity. As an important part of it, facial recognition technology captures face images and uses feature point analysis and deep learning models for matching and discrimination to achieve identity recognition and permission verification. This technology is widely used in many fields such as financial payment, security monitoring, access management, and public transportation. While improving the verification efficiency and security, it also puts forward higher requirements for device performance, algorithm optimization, and data security.

[0003] Among them, an information-based injury ticket granting system based on facial recognition refers to a device that uses facial recognition technology to verify the identity of a specific group and grants electronic or physical tickets after successful verification. The system obtains face information through an image acquisition unit, and uses facial feature extraction and comparison methods to perform identity matching based on a preset database to complete the identity verification process. After successful verification, the system combines with the ticket management system to generate or retrieve corresponding ticket information, and completes ticket granting in the form of electronic storage or physical printing. This system usually uses image processing technology for face detection and feature point recognition, and uses classification algorithms to complete identity matching to ensure the accuracy and uniqueness of the ticket granting process. At the same time, it combines database query logic to realize ticket distribution and management.

[0004] The prior art relies on a single biometric for identity authentication and lacks the perception of user state changes, which may affect the verification accuracy in cases of distracted attention, fatigue, or emotional fluctuations. The permission management uses fixed rules and fails to make dynamic adjustments according to the user's current state, which may still open sensitive operation permissions in inappropriate situations, increasing the risk of misoperation or security. Facial recognition technology mainly relies on static feature comparison and is difficult to effectively adapt to individual micro-expression changes, and is prone to matching failures or misidentifications due to short-term facial abnormalities. Gait verification is mostly based on single comparison and does not combine user behavior characteristics for dynamic correction, and it is difficult to maintain accuracy when environmental factors change. In addition, the prior art has limited data synchronization capabilities between devices, and the results of identity authentication and permission adjustment cannot be quickly shared to other terminals, affecting the security and consistency of cross-device operations and increasing management complexity. Summary of the Invention

[0005] The object of the present invention is to solve the disadvantages existing in the prior art, and to propose an information-based injury ticket granting system based on face recognition.

[0006] To achieve the above object, the present invention adopts the following technical solutions: An information-based injury ticket granting system based on face recognition includes:

[0007] The physiological state monitoring module acquires facial data, calculates the eyeball trajectory direction rate, blink rate and closing duration, pupil diameter change and response time, analyzes the facial muscle activity degree, calculates the mouth corner sagging ratio and the eye surrounding muscle stretching rate, and finally obtains the physiological state level;

[0008] The permission adjustment control module calls the physiological state level, divides the permission level according to the threshold, adjusts the injury ticket modification and information change permissions, controls the remote scheduling access, and calculates the recovery condition to obtain the injury ticket operation permission;

[0009] The identity adaptability matching module, based on the injury ticket operation permission, acquires micro-expression data, calculates the inner corner of the eye contraction, forehead stretching, mouth corner change ratio, analyzes the matching error, and adjusts the matching parameters according to the emotional state to obtain the identity matching adjustment value;

[0010] The gait behavior verification module calls the identity matching adjustment value, acquires gait data to calculate the step length, step frequency stability, center of gravity offset angle, analyzes the gait trajectory deviation, and obtains the gait verification matching value;

[0011] The terminal data linkage module calls the injury ticket permission and the gait matching value, calculates the device permission and the synchronization state, sends a permission update instruction to the logged-in device, and obtains the terminal synchronization state.

[0012] Optionally, the physiological state level includes the eyeball movement state, blink mode, pupil response characteristics, and facial muscle activity degree, the injury ticket operation permission includes the permission level, executable operation range, and recovery condition, the identity matching adjustment value includes the micro-expression matching error, emotional matching parameter, and identity adaptability correction value, the gait verification matching value includes the step characteristics, step frequency stability, center of gravity offset range, and trajectory matching coefficient, and the terminal synchronization state includes device permission synchronization, identity matching update, and logged-in device state.

[0013] Optionally, the physiological state monitoring module includes:

[0014] The eyeball movement sub-module acquires the eyeball position parameters in the facial area data, calculates the eyeball displacement direction vector and the instantaneous rate, screens the rate fluctuation interval based on the angular velocity change between consecutive frames, analyzes the rate change mean value and deviation range, and combines the trajectory offset direction to judge the movement trend to obtain the trajectory offset dynamic change rate;

[0015] The blink rate sub-module calls the trajectory deviation dynamic change rate to detect the eyelid opening and closing states of consecutive frames, calculates the number of blinks and the closing duration within a unit time, screens abnormal closing duration intervals, judges the fluctuation characteristics of blink frequency and closing time, and obtains the eye closing rate interval.

[0016] The pupil change sub-module calls the eye closing rate interval, extracts pupil diameter change data, calculates the ratio of contraction amplitude to dilation time, screens the response time interval based on the diameter change gradient of consecutive time periods, calculates the mean values of contraction and dilation response times, and obtains the pupil contraction dynamic ratio.

[0017] The facial muscle activity sub-module calls the pupil contraction dynamic ratio, obtains the angle of mouth drooping and the stretching displacement of the periorbital muscles, calculates the mouth displacement rate and stretching ratio within a unit time, screens abnormal stretching rate intervals, calculates the overall facial muscle activity trend, and obtains the physiological state level.

[0018] Optionally, the calculation formula for the eyeball displacement direction vector and instantaneous rate is specifically:

[0019] ;

[0020] Among them, represents the eyeball displacement direction vector and instantaneous rate, represents the number of frames within the calculation time window, represents the instantaneous rate of the frame, represents the weight factor of the frame, represents the weighted average rate, represents the angular acceleration of the frame, represents the mean value of angular acceleration, represents the variance of angular acceleration, represents the motion direction angle of the frame, represents the motion direction angle of the frame, represents the total sum of direction changes within the entire time window,

[0021] Optionally, the permission adjustment control module includes:

[0022] The permission classification sub-module calls the physiological state level, sets the boundary values of high permission, restricted permission, and minimum permission according to the permission threshold range corresponding to the physiological state, calculates the permission category corresponding to the current physiological state, and obtains the physiological state permission level.

[0023] The permission calculation sub-module calls the physiological state permission level, obtains the injury ticket permission configuration data, filters the executable operations that meet the current permission level, calculates the current adjustable injury ticket modification permission, information change permission, and remote scheduling access permission, and filters the adjustment range based on the permission configuration table to obtain the injury ticket adjustment permission set;

[0024] The permission recovery sub-module calls the injury ticket adjustment permission set, calculates the change trend of the physiological state level, filters the physiological state change interval corresponding to the recovery condition, judges the recoverable permission category according to the permission recovery threshold, and obtains the injury ticket operation permission.

[0025] Optionally, the identity adaptability matching module includes:

[0026] The micro-expression feature sub-module calls the injury ticket operation permission, obtains the facial micro-expression data, extracts the degree of corner of the eye contraction, the forehead stretching amplitude, and the mouth corner change ratio, calculates the feature change rate within a unit time, filters the feature mean range in the stable state, and judges the deviation trend of the feature to obtain the micro-expression feature deviation value;

[0027] The matching error calculation sub-module calls the micro-expression feature deviation value, obtains the injury ticket holder's identity data, extracts the facial expression parameters in the identity record, calculates the numerical difference between the current micro-expression feature and the identity data, filters the error interval of the feature, and calculates the overall matching deviation mean to obtain the micro-expression matching error;

[0028] The matching parameter adjustment sub-module calls the micro-expression matching error, extracts the matching error correction parameters according to the relaxation, tension, and anxiety states, calculates the adjustment amplitude of the matching parameters in each state, filters the applicable correction interval, calculates the change trend of the corrected matching parameters, and obtains the identity matching adjustment value.

[0029] Optionally, the specific formula for the feature change rate within a unit time is:

[0030] ;

[0031] Where represents the feature change rate within a unit time, represents the number of frames within the calculation time window, represents the frame's degree of corner of the eye contraction, represents the frame's timestamp, represents the frame's forehead stretching amplitude, represents the average forehead stretching within the calculation time window, represents the forehead stretching variance, represents the The corner change ratio of the frame, represents the corner change ratio of the previous frame, represents the total change amount of the corner change ratio within the calculation time window.

[0032] Optionally, the gait behavior verification module includes:

[0033] The gait parameter calculation sub-module calls the identity matching adjustment value, obtains gait behavior data, extracts the step length, the range of step frequency change, and the center of gravity offset angle, calculates the time series change rate of the gait parameters, screens the step adjustment interval in the stable state, calculates the gait feature mean value and the fluctuation trend, and obtains the gait feature parameter set;

[0034] The trajectory deviation calculation sub-module calls the gait feature parameter set, obtains the verification terminal interaction data, extracts the gait trajectory deviation value, calculates the displacement error between the gait movement trajectory and the standard gait path, screens the abnormal deviation points in the gait change, calculates the overall deviation mean value of the trajectory and the gait continuity change trend, and obtains the gait trajectory deviation value;

[0035] The matching stability evaluation sub-module calls the gait trajectory deviation value, extracts the gait parameter fluctuation range, calculates the joint stability index of the step frequency, step amplitude, and trajectory deviation, screens the matching stable parameter range, calculates the overall stability coefficient of the gait behavior, and obtains the gait verification matching value.

[0036] Optionally, the terminal data linkage module includes:

[0037] The permission status calculation sub-module calls the injury ticket operation permission and the gait verification matching value, obtains the terminal device information, extracts the current device permission configuration and the synchronization status parameters, calculates the joint weight of the device permission and the identity matching status, screens the range of executable permissions of the current device, calculates the permission status adjustment parameter, and obtains the terminal permission synchronization parameter;

[0038] The device data synchronization sub-module calls the terminal permission synchronization parameter, sends a data update instruction for the injury ticket permission and identity matching to the logged-in device, extracts the device response delay and the data update status, calculates the device response stability index, screens the data interval with successful synchronization, calculates the synchronization deviation between the terminal permission and the identity matching, and obtains the terminal synchronization status data;

[0039] The terminal linkage evaluation sub-module calls the terminal synchronization status data, calculates the synchronization consistency index of the multi-device linkage state, screens the permission conflict intervals that occur during the terminal data linkage process, analyzes the dynamic adjustment coefficient of the permission and identity matching between devices, screens the range of linkage matching, and obtains the terminal synchronization status.

[0040] Optionally, the specific formula for the synchronization consistency index is:

[0041] ;

[0042] Calculate the synchronization consistency index, analyze the dynamic adjustment coefficient of the permission and identity matching between devices, screen the range of linkage matching, and obtain the terminal synchronization status;

[0043] Among them, represents the synchronization consistency index, represents the total number of terminals analyzed, represents the th terminal's permission value, represents the average permission value of all terminals, represents the standard deviation of the permission value, represents the conflict determination threshold.

[0044] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0045] In the present invention, by analyzing eye movement, blink frequency, pupil change and facial muscle activity, the physiological state of an individual is monitored, dynamic permission adjustment during identity verification is realized, micro-expression analysis optimizes the matching accuracy, reduces mis-matching caused by emotional fluctuations, gait analysis strengthens the adaptability of identity verification through behavioral data, maintains a high accuracy rate, the data linkage mechanism between multiple devices improves the real-time performance of bill management and access control, combines multi-dimensional biometric features, and enhances the security of verification and the stability of remote operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0047] Figure 1 is the system flowchart of the present invention;

[0048] Figure 2 is the sub-module flowchart of the present invention;

[0049] Figure 3 is the flowchart of the physiological state monitoring module of the present invention;

[0050] Figure 4 is the flowchart of the permission adjustment control module of the present invention;

[0051] Figure 5 is the flowchart of the identity adaptability matching module of the present invention;

[0052] Figure 6Flowchart of the gait behavior verification module of the present invention;

[0053] Figure 7 Flowchart of the terminal data linkage module of the present invention. Specific embodiments

[0054] The following describes the technical solutions in the present invention with reference to the accompanying drawings.

[0055] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or more advantageous than other embodiments or design solutions. Rather, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two can be selected.

[0056] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same.

[0057] In the embodiments of the present invention, sometimes subscripts such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meanings they express are the same.

[0058] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0059] Please refer to Figure 1 , an information-based injury ticket granting system based on facial recognition includes:

[0060] S100. The physiological state monitoring module obtains facial area data, calls the calculation of the direction rate change of the eyeball movement trajectory, calls the calculation of the blinking rate to calculate the blinking frequency and the closing duration, calls the calculation of the pupil diameter change to calculate the contraction amplitude and the response time, calls the calculation of the facial muscle activity to calculate the ratio of the mouth corner sagging and the stretching rate of the periorbital muscles, and obtains the physiological state level;

[0061] S200. The permission adjustment control module calls the physiological state level, divides the high permission, restricted permission, and minimum permission according to the threshold, obtains the injury ticket permission configuration data to calculate the current executable operation, adjusts the injury ticket modification, information change, and remote scheduling access permissions, and calculates the recovery condition based on the physiological state change trend to obtain the injury ticket operation permission;

[0062] In S300, the identity adaptability matching module invokes the injury ticket operation permission, obtains facial micro-expression data, calculates the degree of corner of the eye contraction, the stretching amplitude of the forehead, and the change ratio of the corners of the mouth, obtains the identity data of the injury ticket holder to calculate the micro-expression data matching error, and calculates the matching parameter based on the relaxed, tense, and anxious states to obtain the identity matching adjustment value;

[0063] In S400, the gait behavior verification module invokes the identity matching adjustment value, obtains gait behavior data to calculate the step length, step frequency stability, and center of gravity offset angle, obtains the verification terminal interaction data, calculates the gait trajectory deviation, and calculates the matching stability coefficient based on the gait parameter fluctuation range to obtain the gait verification matching value;

[0064] In S500, the terminal data linkage module invokes the injury ticket operation permission and the gait verification matching value, obtains the terminal device information to calculate the permission and synchronization status, sends an injury ticket permission and identity matching data update instruction to the logged-in device, and obtains the terminal synchronization status.

[0065] The physiological state level includes the eye movement state, blink pattern, pupil response characteristics, and facial muscle activity. The injury ticket operation permission includes the permission level, executable operation range, and recovery conditions. The identity matching adjustment value includes the micro-expression matching error, emotion matching parameter, and identity adaptability correction value. The gait verification matching value includes the step characteristics, step frequency stability, center of gravity offset range, and trajectory matching coefficient. The terminal synchronization status includes device permission synchronization, identity matching update, and logged-in device status.

[0066] Please refer to Figure 3 and Figure 2 , the physiological state monitoring module includes:

[0067] In S110, the eye movement sub-module obtains the eye position parameters in the facial area data, calculates the eye displacement direction vector and instantaneous rate, filters the rate fluctuation interval based on the angular velocity change between consecutive frames, analyzes the rate change mean and deviation range, and combines the trajectory offset direction to judge the movement trend to obtain the trajectory offset dynamic change rate;

[0068] The specific calculation formulas for the eye displacement direction vector and instantaneous rate are as follows:

[0069] ;

[0070] Among them, represents the eye displacement direction vector and instantaneous rate, represents the number of frames within the calculation time window, represents the instantaneous rate of the frame, represents the weight factor of the represents the weighted average rate, represents the angular acceleration of the frame, represents the mean value of the angular acceleration, represents the variance of the angular acceleration, represents the motion direction angle of the frame, represents the motion direction angle of the frame, represents the total sum of direction changes within the entire time window, represents the total duration of the calculation time window:

[0071] This formula is used to adjust the fluctuations of the eye movement rate and integrate the changes in eye rate, acceleration, and angular velocity. The parameters considered include the instantaneous rate , the angular change between frames , and the acceleration between frames . The following is the detailed explanation of the parameters and the formula derivation process:

[0072] Rate adjustment calculation:

[0073] Assume that within the time window there are frame data.

[0074] The instantaneous rate is extracted from the video frames by the image recognition software. The rate of each frame may be as follows (taking the first 5 data examples):

[0075] ;

[0076] The weight is set to be inversely related to the rate. Calculate the weight of each frame. For example , the first 5 data may be:

[0077] ;

[0078] The weighted average rate is calculated as:

[0079] ;

[0080] Calculate the rate fluctuation adjustment value :

[0081] ;

[0082] Angular acceleration variance calculation:

[0083] Assume the angular acceleration (taking the first 5 data examples) is:

[0084] ;

[0085] Mean of angular acceleration Calculated as:

[0086] ;

[0087] Variance of angular acceleration Calculated as:

[0088] ;

[0089] Total angular change:

[0090] Assumed angle changes (taking the first 5 data examples) are:

[0091] ;

[0092] Total angular change is calculated as:

[0093] ;

[0094] Angular change term Calculated as:

[0095] ;

[0096] Substitute the above calculation results into the original formula to calculate the final value, which indicates that the overall volatility of the eye movement rate is adjusted to accurately evaluate the dynamic change trend of eye movement.

[0097] S120. The blink rate sub-module calls the trajectory deviation dynamic change rate to detect the eyelid opening and closing states of consecutive frames, calculates the number of blinks and the closing duration per unit time, filters the abnormal closing duration intervals, and judges the blink frequency and closing time fluctuation characteristics to obtain the eye closing rate interval;

[0098] Using the detection model of the eyelid opening and closing degree, perform binary processing on the eye region of consecutive frames to extract the eyelid distance , calculate the standardized eyelid opening and closing state index , where and are the eyelid distances of an individual in the closed-eye and open-eye states respectively. According to the set closed-eye determination threshold , filter frames as closed-eye frames, calculate the number of closed-eye blinks and the closed-eye duration . Given the frame interval , the blink frequency can be calculated, where is the observation duration. For example, in a 10-second sampling window, if 20 blinks are detected, then Hz. For the anomaly detection of the closed-eye duration, calculate its mean and standard deviation , filter the closed-eye events outside the interval , and calculate its distribution. Combining the fluctuation characteristics of the blink frequency and the closed-eye time, filter the interval data of the eye closure rate.

[0099] S130. The pupil change sub-module calls the eye closure rate interval, extracts the pupil diameter change data, calculates the contraction amplitude and the dilation time ratio, filters the response time interval based on the diameter change gradient in consecutive time periods, calculates the mean of the contraction and dilation response times, and obtains the pupil contraction dynamic ratio;

[0100] Using the facial video data adjusted by the illumination environment normalization, extract the pupil diameters of consecutive frames , calculate the diameter change amount between each frame , define the contraction amplitude as the maximum change amount , calculate the dilation time ratio as , where is the contraction time period, is the dilation time period. For example, in a 5-second sampling window, if the pupil contraction lasts for 1.2 seconds and the dilation lasts for 2.8 seconds, then , based on the diameter change gradient in consecutive time periods calculate the response time interval, filter the time periods with the absolute value of the gradient greater than the set threshold , calculate the contraction response time and the dilation response time , and finally obtain the pupil contraction dynamic ratio data.

[0101] S140. The facial muscle activity sub-module calls the pupil contraction dynamic ratio, obtains the angle of the drooping mouth and the stretching displacement of the periorbital muscles, calculates the mouth displacement rate and the stretching ratio per unit time, filters the abnormal stretching rate interval, calculates the overall facial muscle activity trend, and obtains the physiological state level;

[0102] Analyze the dynamic changes of the mouth displacement and the periorbital muscle stretching. First, extract the coordinates of the key points of the mouth calculate the mouth displacement , calculate the mouth displacement rate per unit time , extract the stretching deformation amount of the periorbital muscles , define the stretching ratio as , where Taking the maximum stretching amount as a reference, screening the abnormal stretching rate range, calculating the overall facial muscle activity trend, and obtaining the final physiological state level data.

[0103] Please refer to Figure 4 and Figure 2 , the permission adjustment control module includes:

[0104] S210. The permission grading sub-module calls the physiological state level, sets the boundary values of high permission, restricted permission, and minimum permission according to the permission threshold range corresponding to the physiological state, calculates the permission category corresponding to the current physiological state, and obtains the physiological state permission level;

[0105] First, read the physiological state parameters of the current individual. This parameter is the comprehensive calculation result of multiple indicators such as facial muscle activity, pupil contraction ratio, and blinking rate, and is stored in the physiological state database. Subsequently, set the permission threshold range, and divide the boundary values of high permission, restricted permission, and minimum permission according to the fluctuation of the individual's historical physiological state data. Among them, the permission threshold is set in the way of adding a deviation range to the reference value. For example, in the monitoring data of the past month, the average value of the physiological state value is set as , the standard deviation is set as , then the high permission threshold can be set as , the restricted permission range is , the minimum permission range is less than interval. Next, calculate the permission category corresponding to the current physiological state. By comparing the real-time physiological state value with the preset threshold range, if the current state value falls within the high permission range, it is set as high permission; if it falls within the restricted permission range, it is set as restricted permission; if it is less than the minimum permission threshold, it is set as minimum permission. For example, if the current physiological state value is , then its permission category is determined to be restricted permission, and finally the physiological state permission level is obtained.

[0106] S220. The permission calculation sub-module calls the physiological state permission level, obtains the injury ticket permission configuration data, screens the executable operations that meet the current permission level, calculates the current adjustable injury ticket modification permission, information change permission, and remote scheduling access permission, and screens the adjustment range based on the permission configuration table to obtain the injury ticket adjustment permission set;

[0107] After reading the current permission level, obtain the injury ticket permission configuration data. This configuration data contains a list of operations executable for each permission level and is stored in the permission database. Filter the executable operations that match the current permission level according to the permission level, set the filtering conditions, traverse the permission configuration data table, and find the matching items of the permission category. For example, in the permission table, high permissions allow modification of all injury ticket information, restricted permissions allow partial modification, and the lowest permissions only allow viewing. When the current permission level is restricted, the executable operation filtered out is the partial injury ticket modification permission. Next, calculate the currently adjustable injury ticket modification permission, information change permission, and remote scheduling access permission, respectively call the configuration items of each permission category, and confirm the current user's permission scope. For example, for the injury ticket modification permission, if the modification permission level corresponding to the current permission level is 2 (where level 1 represents only viewing, level 2 represents partial modification, and level 3 represents full modification), then the currently executable injury ticket modification operation is limited to partial adjustment. The remote scheduling access permission is also filtered according to the same rule, and set the benchmark permission level value , calculate the permission adjustment range , where is the threshold of the permission adjustment range. For example, for a certain user, the benchmark permission level is 2, , then the adjustment range is . Combine with the permission configuration table for filtering, and finally obtain the injury ticket adjustment permission set.

[0108] S230. The permission recovery sub-module calls the injury ticket adjustment permission set, calculates the change trend of the physiological state level, filters the physiological state change interval corresponding to the recovery condition, judges the recoverable permission category according to the permission recovery threshold, and obtains the injury ticket operation permission;

[0109] Read the physiological state level data of the current user and calculate its change trend, and define the physiological state change rate , and the calculation formula is , where and represent the physiological state values at the current and previous moments respectively, represents the time interval. For example, if a user's physiological state has changed from to in the past 10 minutes, then . Subsequently, filter the physiological state change interval corresponding to the recovery condition and set the recovery threshold . When exceeds this threshold, it is judged to be a recoverable state. For example, set . If the current physiological state change rate is , the recovery condition is met. Then, according to the privilege recovery threshold, the recoverable privilege category is judged. By comparing the current privilege category with the privilege recovery threshold range, if the current privilege category is a restricted privilege but the recovery condition is met, the privilege can be upgraded to a high privilege, and finally the injury ticket operation privilege is obtained.

[0110] Please refer to Figure 5 and Figure 2 , the identity adaptability matching module includes:

[0111] S310. The micro-expression feature sub-module calls the injury ticket operation privilege, obtains the facial micro-expression data, extracts the degree of corner of the eye contraction, the forehead stretching amplitude, and the mouth corner change ratio, calculates the feature change rate within a unit time, screens the feature mean range in the stable state, judges the deviation trend of the feature, and obtains the micro-expression feature deviation value;

[0112] The specific calculation formula for the feature change rate within a unit time is:

[0113] ;

[0114] Among them, represents the feature change rate within a unit time, represents the number of frames within the calculation time window, represents the degree of corner of the eye contraction of the frame, represents the time stamp of the frame, represents the forehead stretching amplitude of the frame, represents the mean value of forehead stretching within the calculation time window, represents the mouth corner change ratio of the frame, represents the previous frame's

[0115] This formula is used to calculate the feature change rate within a unit time, comprehensively considering the dynamic changes of the degree of corner of the eye contraction, the forehead stretching amplitude, and the mouth corner change ratio. The frame data within the time window is used to calculate the change trend of the micro-expression features and screen the stable state range.

[0116] Parameter acquisition method and numerical setting:

[0117] Number of frames is determined by the frame rate and sampling time of the monitoring device. For example, if the frame rate is set to 30fps and the sampling duration is set to 5 seconds, then . Time stamp is obtained by accumulating the frame time. For example

[0118] , , …… 。

[0119] Degree of corner of the eye contraction Calculated by the change of facial key point coordinates. For example, some data is measured within the sampling frame 。

[0120] Degree of forehead stretching Calculated by the vertical distance of key points on the forehead. For example, some data is measured in the sampling frame 。

[0121] Ratio of corner of the mouth change Calculated by the relative displacement of the corners of the mouth. For example, some data is measured 。

[0122] Calculation process:

[0123] Calculate the feature change rate term

[0124] ;

[0125] Calculate some data:

[0126] ;

[0127] ;

[0128] Take the average value after calculating the complete frame:

[0129] ;

[0130] Calculate the forehead stretching fluctuation term Average value:

[0131] ;

[0132] Variance:

[0133] ;

[0134] ;

[0135] Calculate the cumulative term of the corner of the mouth change

[0136] ;

[0137] Calculate some data:

[0138] ;

[0139] ;

[0140] Calculate the final value:

[0141] ;

[0142] Analysis of calculation results:

[0143] Calculation results represents the change rate of micro-expression features. The larger the value, the more intense the dynamic change of facial micro-expressions. A smaller value indicates that the features are more stable. This value is directly related to the micro-expression feature offset value and can be used to judge the trend of micro-expression changes.

[0144] S320. The matching error calculation sub-module calls the micro-expression feature offset value, obtains the identity data of the injury ticket holder, extracts the facial expression parameters in the identity record, calculates the numerical difference between the current micro-expression feature and the identity data, filters the error interval of the feature, calculates the average value of the overall matching deviation, and obtains the micro-expression matching error;

[0145] First, obtain the identity data of the injury ticket holder. This data includes historical facial expression records and corresponding status parameters. Read the facial expression parameters in the identity record and extract the historical feature means of the corners of the eyes, forehead, and mouth and the standard deviation , calculate the numerical difference between the current micro-expression feature and the identity data, and define the error as , where represents the feature value of the current frame. For example, if the current degree of eye corner contraction is 0.8, the historical mean is 0.6, and the standard deviation is 0.1, then . Next, filter the error interval of the feature, set the error determination range , where is the error threshold. For example, take . If exceeds this threshold, it is determined as an abnormal error. Finally, calculate the average value of the overall matching deviation, set the error weights of different features , calculate the weighted average , and finally obtain the micro-expression matching error.

[0146] S330. The matching parameter adjustment sub-module calls the micro-expression matching error, extracts the matching error correction parameters according to the relaxed, tense, and anxious states, calculates the adjustment amplitude of the matching parameters in each state, filters the applicable correction interval, calculates the change trend of the corrected matching parameters, and obtains the identity matching adjustment value;

[0147] Extract the matching error correction parameters according to the relaxed, tense, and anxious states, and set the error adjustment factors for each state Calculate the adjustment amplitude of the matching parameter in each state and define the adjustment amount , where Set according to the individual's historical data. For example, take in the relaxed state and in the tense state and in the anxious state. Screen the applicable correction intervals, calculate the change trend of the corrected matching parameter, and define the corrected matching parameter , and finally obtain the identity matching adjustment value.

[0148] Please refer to Figure 6 and Figure 2 . The gait behavior verification module includes:

[0149] S410. The gait parameter calculation sub-module calls the identity matching adjustment value, obtains the gait behavior data, extracts the step length, step frequency change range, and center of gravity offset angle, calculates the time series change rate of the gait parameter, screens the step adjustment interval in the stable state, calculates the gait feature mean and fluctuation trend, and obtains the gait feature parameter set;

[0150] [[ID=2б]]After obtaining the gait behavior data, first call the gait detection system to obtain the individual's movement trajectory, extract the step length, step frequency change range, and center of gravity offset angle. The step length is calculated by the Euclidean distance between the coordinates of adjacent foot landing points , where represents the current step point coordinate, and the step frequency change range is calculated by the change rate of the number of steps over time , where is the number of steps per unit time,

[0151] ​​​​​​​​​​S420. The trajectory deviation calculation sub-module calls the gait feature parameter set, obtains the verification terminal interaction data, extracts the gait trajectory offset value, calculates the displacement error between the gait movement trajectory and the standard gait path, screens the abnormal offset points in the gait change, calculates the overall offset mean value of the trajectory and the gait continuity change trend, and obtains the gait trajectory deviation value;

[0152] Obtain the verification terminal interaction data, extract the gait trajectory offset value, calculate the displacement error between the gait movement trajectory and the standard gait path, and define the error , where is the standard trajectory point coordinate, is the current trajectory point coordinate, screen the abnormal offset points in the gait change, and calculate the change rate of the offset amount during the gait movement process , set the abnormal threshold . If , then mark it as an abnormal offset point, calculate the overall offset mean value of the trajectory, and define the mean value as where is the total number of trajectory points, calculate the gait continuity change trend, and define the trend index , and finally obtain the gait trajectory deviation value.

[0153] S430. The matching stability evaluation sub-module calls the gait trajectory deviation value, extracts the gait parameter fluctuation range, calculates the joint stability index of the step frequency, step amplitude and trajectory offset, screens the matching stable parameter range, calculates the overall stability coefficient of the gait behavior, and obtains the gait verification matching value;

[0154] Extract the gait parameter fluctuation range, calculate the joint stability index of the step frequency, step amplitude and trajectory offset, and define the joint stability index , where is the weight coefficient of different parameters. For example, set , , , screen the matching stable parameter range, set the stable interval , calculate the overall stability coefficient of the gait behavior Obtain the matching degree through normalization processing, and finally obtain the gait verification matching value.

[0155] Please refer to Figure 7 and Figure 2 , the terminal data linkage module includes:

[0156] S510. The permission status calculation sub-module calls the injury ticket operation permission and the gait verification matching value, obtains the terminal device information, extracts the current device permission configuration and synchronization status parameters, calculates the joint weight of the device permission and the identity matching status, screens the executable permission range of the current device, calculates the permission status adjustment parameter, and obtains the terminal permission synchronization parameter;

[0157] First, obtain the terminal device information, read the identity identification code of the current device, and extract the current permission configuration parameters of the device, including the device access level, executable operation set, data modification permission, and remote control permission. Set the permission mapping rule to match the device permission configuration table with the user permission level. Then, extract the synchronization status parameters, obtain the connection status between the current device and the management server and the permission synchronization delay value, calculate the combined weight of the device permission and identity matching status, and define the combined weight as , where represents the user permission level, represents the device permission level, is the weight coefficient. For example, when , , , , the combined weight is calculated as . Subsequently, filter the executable permission range of the current device and set the device permission range threshold and . Determine whether is within this interval. If it exceeds the range, perform permission adjustment and calculate the permission status adjustment parameter , where is the set permission reference value. For example, when , then . Finally, obtain the terminal permission synchronization parameter.

[0158] S520. The device data synchronization sub-module calls the terminal permission synchronization parameter, sends a data update instruction for matching the ticket permission and identity to the logged-in device, extracts the device response delay and data update status, calculates the device response stability index, filters the data interval with successful synchronization, calculates the synchronization deviation of the terminal permission and identity matching, and obtains the terminal synchronization status data;

[0159] Send a data update instruction for matching the ticket permission and identity to the logged-in device, and extract the response delay of the device and the data update status , calculate the device response stability index through calculation, where is the set response threshold. For example . If , then . Filter the data interval with successful synchronization, set the success rate threshold , calculate the synchronization success rate , where is the number of requests with successful synchronization, is the total number of requests. For example , , then , if exceeds , it is determined that the synchronization is successful, and the synchronization deviation of the terminal permission and identity matching is calculated , where is the permission weight value stored in the device. For example , then , and finally the terminal synchronization status data is obtained.

[0160] S530. The terminal linkage evaluation sub-module calls the terminal synchronization status data, calculates the synchronization consistency index of the multi-device linkage status, filters the permission conflict intervals that occur during the terminal data linkage process, analyzes the dynamic adjustment coefficient of the permission and identity matching between devices, filters the range of linkage matching, and obtains the terminal synchronization status;

[0161] The specific formula for the synchronization consistency index is:

[0162] ;

[0163] Calculate the synchronization consistency index, analyze the dynamic adjustment coefficient of the permission and identity matching between devices, filter the range of linkage matching, and obtain the terminal synchronization status;

[0164] Among them, represents the synchronization consistency index, represents the total number of terminals analyzed, represents the th terminal's permission value, represents the average permission value of all terminals, represents the standard deviation of the permission value, represents the conflict determination threshold;

[0165] Explanation of formula parameters: is the number of terminals. For example, in a network environment, there may be terminals connected; is obtained in real time from the security systems of each terminal. The permission value of each terminal may be recorded during a one-month monitoring, such as ; Calculate the average value from , such as ; Calculate the standard deviation from , such as ; Set based on historical data analysis. Assume , which means that when the standardized deviation is greater than 1.5, it will be identified as a permission conflict.

[0166] Calculation example: Assume , permission value , the calculation is as follows:

[0167]

[0168] Check the value of each terminal, such as:

[0169] If it is not satisfied, so there is no conflict.

[0170] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An information-based injury ticket granting system based on facial recognition, characterized in that: The system includes: The physiological state monitoring module obtains facial data, calculates the eye movement trajectory direction rate, blink rate and closing duration, pupil diameter change and response time, analyzes the facial muscle activity degree, calculates the mouth corner sag ratio and the eye surrounding muscle stretching rate, and finally obtains the physiological state level; The permission adjustment control module calls the physiological state level, divides the permission level according to the threshold, adjusts the injury ticket modification and information change permissions, controls the remote scheduling access, and calculates the recovery conditions to obtain the injury ticket operation permission; The identity adaptability matching module, based on the injury ticket operation permission, obtains micro-expression data, calculates the corner of the eye contraction, forehead stretching, and mouth corner change ratio, analyzes the matching error, and adjusts the matching parameters according to the emotional state to obtain the identity matching adjustment value; The gait behavior verification module calls the identity matching adjustment value, obtains gait data, calculates the step length, step frequency stability, and center of gravity offset angle, analyzes the gait trajectory deviation, and obtains the gait verification matching value; The terminal data linkage module calls the injury ticket permission and the gait matching value, calculates the device permission and the synchronization state, sends a permission update instruction to the logged-in device, and obtains the terminal synchronization state.

2. The information-based injury ticket granting system based on facial recognition according to claim 1, characterized in that: The physiological state level includes the eye movement state, blink mode, pupil response characteristics, and facial muscle activity degree. The injury ticket operation permission includes the permission level, the executable operation range, and the recovery conditions. The identity matching adjustment value includes the micro-expression matching error, the emotional matching parameter, and the identity adaptability correction value. The gait verification matching value includes the step characteristics, step frequency stability, center of gravity offset range, and trajectory matching coefficient. The terminal synchronization state includes device permission synchronization, identity matching update, and logged-in device state.

3. The information-based injury ticket granting system based on facial recognition according to claim 1, characterized in that: The physiological state monitoring module includes: The eye movement sub-module obtains the eye position parameters in the facial area data, calculates the eye displacement direction vector and the instantaneous rate, filters the rate fluctuation interval based on the angular velocity change between consecutive frames, analyzes the mean value and deviation range of the rate change, and combines the trajectory offset direction to judge the movement trend to obtain the trajectory offset dynamic change rate; The blink rate sub-module calls the trajectory offset dynamic change rate, detects the eyelid opening and closing state of consecutive frames, calculates the number of blinks and the closing duration per unit time, filters the abnormal closing duration interval, and judges the fluctuation characteristics of the blink frequency and closing time to obtain the eye closing rate interval; The pupil change sub-module calls the eye closing rate interval, extracts the pupil diameter change data, calculates the ratio of the contraction amplitude to the dilation time, filters the response time interval based on the diameter change gradient of consecutive time periods, and calculates the mean value of the contraction and dilation response times to obtain the pupil contraction dynamic ratio; The facial muscle activity sub-module calls the pupil contraction dynamic ratio, obtains the mouth corner sag angle and the eye surrounding muscle stretching displacement, calculates the mouth corner displacement rate and the stretching ratio per unit time, filters the abnormal stretching rate interval, and calculates the overall facial muscle activity trend to obtain the physiological state level.

4. The information-based injury ticket granting system based on facial recognition according to claim 3, characterized in that: The specific calculation formula for the eye displacement direction vector and the instantaneous rate is: ； in, Represents the eyeball displacement direction vector and instantaneous velocity, Represents the number of frames in the calculation time window, Representative The instantaneous frame rate, Representative The weight factor of the frame, represents the weighted average rate, Representative The angular acceleration of the frame, represents the mean angular acceleration, represents the variance of angular acceleration, Representative The frame's motion direction angle, Representative The frame's motion direction angle, Represents the total direction change in the entire time window, Represents the total duration of the calculation time window.

5. The information-based injury ticket granting system based on facial recognition according to claim 1, characterized in that: The permission adjustment control module includes: The permission grading sub-module calls the physiological state level, sets the boundary values of high permission, restricted permission, and minimum permission according to the permission threshold range corresponding to the physiological state, calculates the permission category corresponding to the current physiological state, and obtains the physiological state permission level. The permission calculation sub-module calls the physiological state permission level, obtains the injury ticket permission configuration data, filters the executable operations that meet the current permission level, calculates the current adjustable injury ticket modification permission, information change permission, and remote scheduling access permission, and filters the adjustment range based on the permission configuration table to obtain the injury ticket adjustment permission set. The permission recovery sub-module calls the injury ticket adjustment permission set, calculates the change trend of the physiological state level, filters the physiological state change interval corresponding to the recovery condition, determines the recoverable permission category according to the permission recovery threshold, and obtains the injury ticket operation permission.

6. The information-based injury ticket granting system based on facial recognition according to claim 1, characterized in that: The identity adaptability matching module includes: The micro-expression feature sub-module calls the injury ticket operation permission, obtains the facial micro-expression data, extracts the degree of corner of the eye contraction, the stretching amplitude of the forehead, and the change ratio of the mouth corner, calculates the feature change rate within a unit time, filters the feature mean range in the stable state, determines the deviation trend of the feature, and obtains the micro-expression feature deviation value. The matching error calculation sub-module calls the micro-expression feature deviation value, obtains the identity data of the injury ticket holder, extracts the facial expression parameters in the identity record, calculates the numerical difference between the current micro-expression feature and the identity data, filters the error interval of the feature, calculates the overall matching deviation mean, and obtains the micro-expression matching error. The matching parameter adjustment sub-module calls the micro-expression matching error, extracts the matching error correction parameters according to the relaxed, tense, and anxious states, calculates the adjustment amplitude of the matching parameters in each state, filters the applicable correction interval, calculates the change trend of the corrected matching parameters, and obtains the identity matching adjustment value.

7. The information-based injury ticket granting system based on facial recognition according to claim 6, characterized in that: The specific formula for the feature change rate within a unit time is: ； Among them, represents the rate of feature change per unit time, represents the number of frames within the calculation time window, represents the degree of corner of the eye contraction in the th frame, represents the timestamp of the th frame, represents the forehead stretching amplitude in the th frame, represents the mean value of forehead stretching within the calculation time window, represents the variance of forehead stretching, represents the ratio of mouth corner change in the th frame, represents the total change in the ratio of mouth corner change within the calculation time window.

8. The information-based injury ticket granting system based on facial recognition according to claim 1, characterized in that: The gait behavior verification module includes: The gait parameter calculation sub-module calls the identity matching adjustment value, obtains the gait behavior data, extracts the step length, the range of step frequency change, and the center of gravity offset angle, calculates the time series change rate of the gait parameters, filters the step adjustment interval in the stable state, calculates the gait feature mean and the fluctuation trend, and obtains the gait feature parameter set. The trajectory deviation calculation sub-module calls the gait feature parameter set, obtains the verification terminal interaction data, extracts the gait trajectory offset value, calculates the displacement error between the gait movement trajectory and the standard gait path, filters the abnormal offset points in the gait change, calculates the overall trajectory offset mean and the gait continuity change trend, and obtains the gait trajectory deviation value. The matching stability evaluation sub-module calls the gait trajectory deviation value, extracts the gait parameter fluctuation range, calculates the joint stability index of the step frequency, step amplitude, and trajectory offset, filters the matching stability parameter range, calculates the overall stability coefficient of the gait behavior, and obtains the gait verification matching value.

9. The information-based injury ticket granting system based on facial recognition according to claim 1, characterized in that: The terminal data linkage module includes: The permission status calculation sub-module calls the injury ticket operation permission and gait verification matching value, obtains the terminal device information, extracts the current device permission configuration and synchronization status parameters, calculates the combined weight of the device permission and identity matching status, filters the executable permission range of the current device, calculates the permission status adjustment parameter, and obtains the terminal permission synchronization parameter; The device data synchronization sub-module calls the terminal permission synchronization parameter, sends a data update instruction for the injury ticket permission and identity matching to the logged-in device, extracts the device response delay and data update status, calculates the device response stability index, filters the data interval with successful synchronization, calculates the synchronization deviation of the terminal permission and identity matching, and obtains the terminal synchronization status data; The terminal linkage evaluation sub-module calls the terminal synchronization status data, calculates the synchronization consistency index of the multi-device linkage status, filters the permission conflict intervals that occur during the terminal data linkage process, analyzes the dynamic adjustment coefficient of the permission and identity matching between devices, filters the linkage matching range, and obtains the terminal synchronization status.

10. The information-based injury ticket granting system based on facial recognition according to claim 9, characterized in that: The specific formula for calculating the synchronization consistency index is: ； Calculate the synchronization consistency index, analyze the dynamic adjustment coefficient of the permission and identity matching between devices, filter the linkage matching range, and obtain the terminal synchronization status; Among them, represents the synchronization consistency index, represents the total number of terminals analyzed, represents the permission value of the th terminal, represents the average permission value of all terminals, represents the conflict determination threshold.

Images