Head wearable device, eye fatigue monitoring method, device and storage medium

Abstract

The present application discloses a head-worn device, an eye fatigue monitoring method, an apparatus and a storage medium, the method comprising: collecting target blink data and eye usage duration of a target object through a first tilt sensor, a second tilt sensor and a forehead electroencephalogram sensor, the target blink data including left eye blink data and right eye blink data; collecting head posture data of the target object through a third tilt sensor; performing left eye fatigue detection based on left eye blink data, eye usage duration and head posture data to obtain left eye fatigue information of the target object; performing right eye fatigue detection based on right eye blink data, eye usage duration and head posture data to obtain right eye fatigue information of the target object; performing eye fatigue analysis based on left eye fatigue information and right eye fatigue information to obtain eye fatigue information and eye difference information of the target object. The technical solution provided by the present application can improve the accuracy of eye fatigue monitoring while distinguishing the fatigue degree of the left and right eyes.

Description

Technical Field

[0001] The present invention relates to the field of wearable technology, and in particular to a head wearable device, an eye fatigue monitoring method, an apparatus and a storage medium. Background Art

[0002] In daily life, when working or studying at close range, if you stare at a computer screen or book for a long time, your eyes will feel dry and tired. Severe visual fatigue may even seriously affect your daily work and study. How to effectively monitor eye fatigue has begun to attract attention.

[0003] The existing eye fatigue monitoring method collects the electromyographic signals generated by the user's eye movement through a signal collector, determines the user's eye feature data from the electromyographic signals, and thus determines the eye fatigue state. However, the existing method, on the one hand, cannot distinguish the fatigue degree of the left and right eyes, and on the other hand, the accuracy of judging the eye fatigue state through a single feature is low. Therefore, there is a need to provide a more accurate technical solution. Summary of the invention

[0004] In view of the above-mentioned problems in the prior art, the purpose of the present application is to provide a head-worn device, an eye fatigue monitoring method, an apparatus and a storage medium, which can improve the accuracy of eye fatigue monitoring while distinguishing the fatigue degree of the left and right eyes.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] A head wearable device, the device comprising: a wearable body and a nose pad structure, the nose pad structure being connected to the wearable body, the left and right sides of the nose pad structure comprising a first tilt sensor and a second tilt sensor respectively, the wearable body comprising: a controller, a forehead EEG sensor, a third tilt sensor and a communication module, the controller being electrically connected to the first tilt sensor, the second tilt sensor, the forehead EEG sensor, the third tilt sensor and the communication module respectively.

[0007] The present application also discloses a method for monitoring eye fatigue, which is implemented based on the head-worn device as described above, and comprises:

[0008] Collect target blink data and eye use duration of the target object through the first tilt sensor, the second tilt sensor and the forehead electroencephalogram sensor, wherein the target blink data includes left eye blink data and right eye blink data;

[0009] collecting head posture data of the target object through a third inclination sensor;

[0010] Perform left eye fatigue detection based on the left eye blink data, the eye usage time and the head posture data to obtain left eye fatigue information of the target object;

[0011] Perform right eye fatigue detection based on the right eye blink data, the eye usage time and the head posture data to obtain right eye fatigue information of the target object;

[0012] Eye fatigue analysis is performed based on the left eye fatigue information and the right eye fatigue information to obtain the eye fatigue information and eye difference information of the target object.

[0013] The present application also discloses a device for monitoring eye fatigue, which is implemented based on the head wearable device as described above, and comprises:

[0014] A first acquisition module is used to acquire target blink data and eye use duration of the target object through a first tilt sensor, a second tilt sensor and a forehead electroencephalogram sensor, wherein the target blink data includes left eye blink data and right eye blink data;

[0015] A second acquisition module, used for acquiring head posture data of the target object through a third tilt sensor;

[0016] A left eye fatigue detection module, used to perform left eye fatigue detection based on the left eye blink data, the eye use time and the head posture data, and obtain left eye fatigue information of the target object;

[0017] A right eye fatigue detection module, used to perform right eye fatigue detection based on the right eye blink data, the eye use time and the head posture data, and obtain right eye fatigue information of the target object;

[0018] The eye fatigue analysis module is used to perform eye fatigue analysis based on the left eye fatigue information and the right eye fatigue information to obtain the eye fatigue information and eye difference information of the target object.

[0019] The present application also discloses a computer-readable storage medium, in which at least one instruction or at least one program is stored. The at least one instruction or the at least one program is loaded and executed by a processor to implement the eye fatigue monitoring method as described above.

[0020] The head wearable device, eye fatigue monitoring method, device and storage medium provided by this application have the following technical effects:

[0021] The technical solution provided in the present application collects the target blink data and eye usage time of the target object through a first tilt sensor, a second tilt sensor and a forehead EEG sensor, the target blink data including left eye blink data and right eye blink data, and collects the head posture data of the target object through a third tilt sensor; on the one hand, based on the left eye blink data, the eye usage time and the head posture data, the left eye fatigue information of the target object is obtained; based on the right eye blink data, the eye usage time and the head posture data, the right eye fatigue information of the target object is obtained by detecting the right eye fatigue, and the fatigue degree of the left and right eyes can be distinguished; on the other hand, based on the left eye fatigue information and the right eye fatigue information, the eye fatigue information and eye difference information of the target object are obtained, thereby improving the accuracy of eye fatigue monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments or prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 is a schematic diagram of an application environment provided by an embodiment of the present application;

[0024] Figure 2 This is a structural block diagram of a head wearable device provided in an embodiment of the present application;

[0025] Figure 3 is a structural block diagram of another head wearable device provided in an embodiment of the present application;

[0026] Figure 4 is a structural block diagram of another head wearable device provided in an embodiment of the present application;

[0027] Figure 5 It is a flowchart of a method for monitoring eye fatigue provided by an embodiment of the present application;

[0028] Figure 6 This is a flow chart of collecting target blink data and eye use time of a target object by using a first tilt sensor, a second tilt sensor and a forehead electroencephalogram sensor, provided by an embodiment of the present application;

[0029] Figure 7 This is a flow chart of an embodiment of the present application, which provides a method for analyzing eye status based on EEG signal data, first inclination angle data, and second inclination angle data to obtain target blink data within a preset time period;

[0030] Figure 8It is a flowchart of left eye fatigue detection, right eye fatigue detection and eye fatigue analysis provided by an embodiment of the present application;

[0031] Fig. 9 It is a flowchart of a training method for a left eye fatigue detection network, a right eye fatigue detection network and an eye fatigue analysis network provided in an embodiment of the present application;

[0032] Fig.10 is a schematic diagram of an eye fatigue monitoring network provided by an embodiment of the present application;

[0033] Fig.11 is a flow chart of another eye fatigue monitoring method provided in an embodiment of the present application;

[0034] Fig.12 An eye fatigue monitoring device is provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0036] In several embodiments provided in this application, the described system embodiments are only schematic, for example, the division of the above modules is only a logical function division, and there may be other division methods in actual implementation, for example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection of modules or units, which may be electrical or other forms.

[0037] See also Figure 1 , Figure 1 is a schematic diagram of an application environment provided by an embodiment of the present application, such as Figure 1 As shown, the above application environment includes a head-worn device 01 and a mobile terminal 02 of the target object.

[0038] Specifically, the head-worn device 01 may include: a controller, a first tilt sensor, a second tilt sensor, a forehead EEG sensor, a third tilt sensor, a communication module, a storage module, etc. Specifically, the head-worn device 01 may be used to collect target blink data and eye usage time of the target object through the first tilt sensor, the second tilt sensor and the forehead EEG sensor, the target blink data including left eye blink data and right eye blink data; collect head posture data of the target object through the third tilt sensor; perform left eye fatigue detection based on left eye blink data, eye usage time and head posture data to obtain left eye fatigue information of the target object; perform right eye fatigue detection based on right eye blink data, eye usage time and head posture data to obtain right eye fatigue information of the target object; perform eye fatigue analysis based on left eye fatigue information and right eye fatigue information to obtain eye fatigue information and eye difference information of the target object; push eye fatigue information and eye difference information to the mobile terminal 02.

[0039] Specifically, the mobile terminal 02 may include: a smart phone, a vehicle-mounted terminal, a computer (such as a desktop computer, a tablet computer, a laptop computer), a digital assistant, an intelligent voice interaction device (such as an intelligent speaker), an intelligent wearable device and other types of physical devices, or it may be software running in a physical device, such as a computer program. Specifically, the mobile terminal 02 is used to receive the eye fatigue information and eye difference information pushed by the head wearable device 01.

[0040] In actual applications, the head-mounted device 01 and the mobile terminal 02 can exchange information, and the head-mounted device 01 can push eye fatigue information and eye difference information to the mobile terminal 02 in real time to realize eye fatigue monitoring.

[0041] The following describes a head wearable device provided in an embodiment of the present application, such as Figure 2 As shown, specifically, the above-mentioned device may include: a wearable body 1 and a nose pad structure 2, the nose pad structure 2 is connected to the wearable body 1, the left and right sides of the nose pad structure 2 respectively include a first tilt sensor 3 and a second tilt sensor 4, the wearable body 1 includes: a controller 5, a forehead EEG sensor 6, a third tilt sensor 7 and a communication module 8, and the controller 5 is electrically connected to the first tilt sensor 3, the second tilt sensor 4, the forehead EEG sensor 6, the third tilt sensor 7 and the communication module 8 respectively.

[0042] In a specific embodiment, the nose pad structure may be a flexible nose pad structure. When the target object wears the above-mentioned head wearable device, the flexible nose pad structure may be attached to both sides above the bridge of the nose at the corners of the eyes of the target object.

[0043] In a specific embodiment, the first inclination sensor and the second inclination sensor may be three-axis inclination sensors. Specifically, the first inclination sensor and the second inclination sensor may be used to collect inclination data on both sides of the eye corners and above the nose bridge of the target object, respectively.

[0044] In a specific embodiment, the third tilt sensor may include: a tilt sensor and a gyroscope. Specifically, the third tilt sensor may be used to collect head posture data of the target object.

[0045] In a specific embodiment, the forehead EEG sensor may include: a forehead single-channel EEG sensor. Specifically, the forehead EEG sensor may be used to collect EEG signal data of a target object.

[0046] In a specific embodiment, the communication module may include but is not limited to: Bluetooth communication and WiFi communication.

[0047] It can be seen from the above embodiments that the first inclination sensor and the second inclination sensor in the nose pad structure can collect inclination data on both sides of the target object's eye corners above the nose bridge, distinguish the blinking data of the left and right eyes, and thus monitor the fatigue of the left and right eyes.

[0048] In an optional embodiment, if Figure 3 As shown, the wearable body 1 may further include a vibration module 9, and the controller 5 is electrically connected to the vibration module 9.

[0049] In a specific embodiment, the vibration module is used to vibrate and remind the target object.

[0050] In an optional embodiment, if Figure 4 As shown, the wearable body 1 may further include: a light sensor 10 and a distance sensor 11, and the controller 5 is electrically connected to the light sensor 10 and the distance sensor 11 respectively.

[0051] In a specific embodiment, the light sensor may be used to collect light data of the environment where the target object is located.

[0052] In a specific embodiment, the distance measuring sensor may include: an infrared laser distance measuring sensor. Specifically, the distance measuring sensor may be used to collect the eye distance of the target object.

[0053] In the embodiments of the present specification, the wearable body may further include: a storage module, which is electrically connected to the controller.

[0054] It can be seen from the above embodiments that the illumination data and eye distance of the environment where the target object is located can be collected by the illumination sensor and the distance measuring sensor, and further eye monitoring can be performed.

[0055] The following describes a method for monitoring eye fatigue provided by an embodiment of the present application. The method is implemented based on the above-mentioned head wearable device. Figure 5 A flowchart of a method for monitoring eye fatigue provided in an embodiment of the present application. It should be noted that this specification provides method operation steps as described in the embodiment or flowchart, but may include more or fewer operation steps based on routine or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many orders, and does not represent the only order of execution. When the system or product is executed in practice, it can be executed in sequence or in parallel (for example, in a parallel processor or multi-threaded processing environment) according to the method shown in the embodiment or the accompanying drawings. Specifically, Figure 5 As shown, the above method may include:

[0056] S501, collecting target blink data and eye usage duration of a target object through a first tilt sensor, a second tilt sensor and a forehead electroencephalogram sensor, wherein the target blink data includes left eye blink data and right eye blink data.

[0057] In the embodiment of the present specification, the target blink data may be statistical data associated with the blinking action of the target object, and the eye use time may be the total blinking time of the target object within a preset statistical time period. Specifically, the target blink data may include left eye blink data and right eye blink data, the left eye blink data may be statistical data associated with the left eye blink action of the target object, and the right eye blink data may be statistical data associated with the right eye blink action of the target object.

[0058] In the embodiments of this specification, Figure 6 As shown, the above-mentioned collection of target blink data and eye use duration of the target object through the first tilt sensor, the second tilt sensor and the forehead EEG sensor may include:

[0059] S601 , collecting first inclination data and second inclination data of a target object within a preset time period respectively by using a first inclination sensor and a second inclination sensor.

[0060] In the embodiment of this specification, the preset time period can be set in combination with the monitoring accuracy of eye fatigue. Optionally, the preset time period can be 60 seconds.

[0061] In actual applications, when the target object blinks, the nose pad structure will vibrate slightly, and the first tilt sensor and the second tilt sensor in the nose pad structure can collect the angle change in the three-dimensional (XYZ axis) direction caused by the slight vibration. Specifically, the first initial signal collected by the first tilt sensor is filtered and amplified to obtain a first amplified signal, and the first amplified signal is converted by A / D (analog-to-digital converter) to obtain first tilt data; the second initial signal collected by the second tilt sensor is filtered and amplified to obtain a second amplified signal, and the second amplified signal is converted by A / D to obtain second tilt data.

[0062] Specifically, the first inclination data may be the three-dimensional inclination data of the left side of the nose pad structure, and the second inclination data may be the three-dimensional inclination data of the right side of the nose pad structure, wherein the three-dimensional inclination data may include X-axis inclination data, Y-axis inclination data and Z-axis inclination data, and accordingly, the first inclination data may include: first X-axis inclination data, first Y-axis inclination data and first Z-axis inclination data, and the second inclination data may include: second X-axis inclination data, second Y-axis inclination data and second Z-axis inclination data.

[0063] S602, collecting EEG signal data of the target object within a preset time period through a forehead EEG sensor.

[0064] Specifically, the EEG signal data may be amplitude statistics of the frontal EEG signal, and the amplitude statistics may include amplitude standard deviation. In practical applications, the sampling frequency of the frontal EEG signal may be set according to the sampling accuracy, and in an optional embodiment, the sampling frequency may be 1KHz.

[0065] S603: The time length during which the EEG signal data is greater than the blink signal threshold within the preset time period is used as the eye use time.

[0066] Specifically, it is determined whether the current EEG signal data is greater than the blink signal threshold at a preset judgment frequency. When the current EEG signal data is greater than the blink signal threshold, it is determined that the state corresponding to the current EEG signal data is a blink state, and the length of time of the blink state within the preset time period is used as the eye usage time.

[0067] In a specific embodiment, the method for determining the blink signal threshold may include:

[0068] 1) Acquire the first EEG signal data of the target object during the process of closing eyes and the second EEG signal data of the target object during the process of blinking eyes;

[0069] Specifically, the first EEG signal data may be the standard deviation of the amplitude of the frontal EEG signal when the target object closes its eyes, and the second EEG signal data may be the standard deviation of the amplitude of the frontal EEG signal when the target object blinks. In an optional embodiment, the first EEG signal data is obtained when the target object closes its eyes for 10 seconds, and the second EEG signal data is obtained when the target object blinks for 10 seconds.

[0070] 2) Determine a blink signal threshold based on the first EEG signal data and the second EEG signal data.

[0071] Specifically, the average of the first EEG signal data and the second EEG signal data may be calculated, and the average may be used as the blink signal threshold.

[0072] S604, performing eye status analysis based on the EEG signal data, the first inclination angle data and the second inclination angle data to obtain target blinking data within a preset time period.

[0073] In a specific embodiment, eye status analysis is performed based on the EEG signal data, the first inclination angle data and the second inclination angle data to obtain left eye blink data and right eye blink data. Specifically, the left eye blink data may include: the left eye blinking frequency and the duration of each blink intensity under a plurality of left eye blink intensities; the right eye blink data may include: the right eye blinking frequency and the duration of each blink intensity under a plurality of right eye blink intensities.

[0074] In a specific embodiment, Figure 7 As shown, the above-mentioned eye state analysis based on the EEG signal data, the first inclination angle data and the second inclination angle data to obtain the target blink data within the preset time period may include:

[0075] S701, traversing EEG signal data at multiple moments in a preset time period.

[0076] Specifically, the multiple moments can be set in combination with the monitoring accuracy of eye fatigue. In an optional embodiment, the multiple moments can include every second within 60 seconds.

[0077] S702, when the currently traversed EEG signal data is greater than the blink signal threshold, performing an inclination change analysis on the first inclination data and the second inclination data at the corresponding moment of the currently traversed EEG signal data to obtain an inclination change analysis result.

[0078] S703, determining the target blinking state corresponding to the currently traversed EEG signal data according to the inclination angle change analysis result.

[0079] In a specific embodiment, in the case where the first inclination data includes: first X-axis inclination data, first Y-axis inclination data and first Z-axis inclination data, and the second inclination data includes: second X-axis inclination data, second Y-axis inclination data and second Z-axis inclination data, the above-mentioned inclination change analysis of the first inclination data and the second inclination data at the corresponding moment of the currently traversed EEG signal data to obtain the inclination change analysis result may include: performing angle comparison on the first X-axis inclination data and the second X-axis inclination data at the corresponding moment of the currently traversed EEG signal data to obtain a first comparison result; performing angle comparison on the first Y-axis inclination data and the second Y-axis inclination data at the corresponding moment of the currently traversed EEG signal data to obtain a second comparison result; performing angle comparison on the first Z-axis inclination data and the second Z-axis inclination data at the corresponding moment of the currently traversed EEG signal data to obtain a third comparison result; and obtaining the inclination change analysis result based on the first comparison result, the second comparison result and the third comparison result;

[0080] Correspondingly, the target blinking state may include: left eye blinking and right eye blinking. The above-mentioned determination of the target blinking state corresponding to the currently traversed EEG signal data according to the analysis result may include: when the inclination angle change analysis result satisfies the first angle change condition, the target blinking state corresponding to the currently traversed EEG signal data is left eye blinking; when the inclination angle change analysis result satisfies the second angle change condition, the target blinking state corresponding to the currently traversed EEG signal data is right eye blinking. In actual applications, the first angle change condition and the second angle change condition may be set in combination with a large amount of experimental data.

[0081] S704: When the target blinking state is a left eye blink, the currently traversed EEG signal data is added to the first data group.

[0082] S705, when the target blinking state is right eye blinking, adding the currently traversed EEG signal data to the second data group.

[0083] S706, after traversing the EEG signal data at multiple moments in the preset time period, statistically analyze the EEG signal data in the first data group to obtain the left eye blinking frequency and the first duration corresponding to multiple blinking intensities of the left eye.

[0084] S707, performing statistical analysis on the EEG signal data in the second data group to obtain the blinking frequency of the right eye and the second durations corresponding to the various blinking intensities of the right eye.

[0085] S708: Use the left eye blinking frequency and the first duration as left eye blinking data.

[0086] S709: Use the right eye blinking frequency and the second duration as right eye blinking data.

[0087] Specifically, the number of left eye blinks and the number of right eye blinks in the target blink state corresponding to the EEG signal data at multiple moments within a preset time period are counted respectively, so as to obtain the left eye blinking frequency and the right eye blinking frequency.

[0088] Specifically, multiple intensity thresholds can be set between the blink signal threshold and the above-mentioned second EEG signal data. In practical applications, the values ​​of the multiple intensity thresholds can be set in combination with the accuracy of distinguishing blink intensity. In an optional embodiment, the multiple intensity thresholds may include a first intensity threshold and a second intensity threshold, wherein the first intensity threshold is less than the second intensity threshold, and when the EEG signal data is greater than the blink signal threshold and less than or equal to the first intensity threshold, it is considered that the target blink state corresponding to the EEG signal data is a low-intensity blink, and when the EEG signal data is greater than the first intensity threshold and less than or equal to the second intensity threshold, it is considered that the target blink state corresponding to the EEG signal data is a medium-intensity blink, and when the EEG signal data is greater than the second intensity threshold and less than or equal to the second EEG signal data, it is considered that the target blink state corresponding to the EEG signal data is a high-intensity blink;

[0089] Correspondingly, the target blinking state corresponding to the EEG signal data within the preset time period is the first time length of left eye blinking, and then the duration of low-intensity blinking of the left eye, the duration of medium-intensity blinking of the left eye, and the duration of high-intensity blinking of the left eye in the first time length are determined; the target blinking state corresponding to the EEG signal data within the preset time period is the second time length of right eye blinking, and then the duration of low-intensity blinking of the right eye, the duration of medium-intensity blinking of the right eye, and the duration of high-intensity blinking of the right eye in the second time length are determined.

[0090] It can be seen from the above embodiments that the first inclination data and the second inclination data of the target object are respectively collected by the first inclination sensor and the second inclination sensor, and the inclination change analysis is performed on the first inclination data and the second inclination data to obtain the inclination change analysis result; and based on the inclination change analysis result and the EEG signal data, the left and right eye blink data are distinguished to facilitate subsequent left and right eye fatigue detection.

[0091] S502: Collect head posture data of the target object through a third tilt sensor.

[0092] In a specific embodiment, collecting the head posture data of the target object through the third tilt sensor may include: collecting the head tilt data of the target object through the third tilt sensor; and performing head posture analysis on the head tilt data to obtain the head posture data.

[0093] Specifically, the head tilt angle data may be the angle of the current head position relative to the head upright position, and the head posture data may include an upward-looking state, a downward-looking state, and a level-looking state.

[0094] In a specific embodiment, the head inclination angle data corresponding to the upright head position is 0°, and the head posture data at this time is in a level looking state; when the head inclination angle data is greater than 0°, the head posture data at this time is in a lowered head state; when the head inclination angle data is less than 0°, the head posture data at this time is in a raised head state.

[0095] S503, performing left eye fatigue detection based on the left eye blink data, eye usage time and head posture data to obtain left eye fatigue information of the target object.

[0096] S504, performing right eye fatigue detection based on the right eye blink data, eye usage time and head posture data to obtain right eye fatigue information of the target object.

[0097] S505, performing eye fatigue analysis based on the left eye fatigue information and the right eye fatigue information to obtain the eye fatigue information and eye difference information of the target object.

[0098] In the embodiment of the present specification, the left eye fatigue information may be the left eye fatigue degree characterizing the left eye fatigue state, the right eye fatigue information may be the right eye fatigue degree characterizing the right eye fatigue state, the eye fatigue information may be the eye fatigue degree characterizing the fatigue state of both eyes, and the eye difference information may be the left and right eye fatigue difference degree characterizing the difference in left and right eye fatigue.

[0099] In a specific embodiment, the left eye fatigue information may include a left eye fatigue value after quantifying the left eye fatigue degree according to certain rules, the right eye fatigue information may include a right eye fatigue value after quantifying the right eye fatigue degree according to certain rules, the eye fatigue information may include an eye fatigue value after quantifying the fatigue degrees of both eyes according to certain rules, and the eye difference information may include the difference between the left eye fatigue value and the right eye fatigue value.

[0100] In a specific embodiment, the fatigue level corresponding to the eye fatigue value can be determined based on the comparison result of the eye fatigue value and the eye fatigue threshold. Optionally, the eye fatigue threshold may include a first fatigue threshold and a second fatigue threshold, wherein the first fatigue threshold is less than the second fatigue threshold. Specifically, when the eye fatigue value is less than the first fatigue threshold, the fatigue level corresponding to the eye fatigue value is mild eye fatigue; when the eye fatigue value is greater than or equal to the first fatigue threshold and less than the second fatigue threshold, the fatigue level corresponding to the eye fatigue value is moderate eye fatigue; when the eye fatigue value is greater than or equal to the second fatigue threshold, the fatigue level corresponding to the eye fatigue value is severe eye fatigue.

[0101] In practical applications, the first fatigue threshold and the second fatigue threshold can be preset in combination with the accuracy of eye fatigue monitoring and the range of eye fatigue values.

[0102] In a specific embodiment, Figure 8 As shown, the left eye fatigue detection based on the left eye blink data, the eye usage time and the head posture data, and the left eye fatigue information of the target object may include:

[0103] S801, input the left eye blink data, eye usage time and head posture data into the left eye fatigue detection network to perform left eye fatigue detection and obtain left eye fatigue information.

[0104] The above-mentioned detection of right eye fatigue based on right eye blink data, eye usage time and head posture data may include:

[0105] S802, inputting the right eye blink data, eye usage time and head posture data into the right eye fatigue detection network to perform right eye fatigue detection and obtain right eye fatigue information.

[0106] The fatigue analysis based on the left eye fatigue information and the right eye fatigue information to obtain the eye fatigue information and eye difference information of the target object may include:

[0107] S803, inputting the left eye fatigue information and the right eye fatigue information into an eye fatigue analysis network to perform eye fatigue analysis, and obtaining eye fatigue information and eye difference information.

[0108] Specifically, the above-mentioned left eye fatigue detection network may include but is not limited to GRU (Gated Recurrent Unit Network), RNN (Recurrent Neural Network) or LSTM (Long Short-Term Memory Network).

[0109] Specifically, the above right eye fatigue detection network may include but is not limited to: GRU, RNN or LSTM.

[0110] Specifically, the above-mentioned eye fatigue analysis network may include but is not limited to: GRU, SVM (support vector machine), BP (feedforward neural network), K-means (K-means clustering algorithm).

[0111] It can be seen from the above embodiments that, on the one hand, inputting the left eye blink data, eye usage time and head posture data into the left eye fatigue detection network for left eye fatigue detection and inputting the right eye blink data, eye usage time and head posture data into the right eye fatigue detection network for right eye fatigue detection can distinguish the fatigue information of the left and right eyes. On the other hand, inputting the left eye fatigue information and the right eye fatigue information into the eye fatigue analysis network for eye fatigue analysis can improve the accuracy of eye fatigue analysis.

[0112] In an embodiment of the present specification, a preset left eye fatigue detection network, a preset right eye fatigue detection network and a preset eye fatigue analysis network can be jointly trained using sample eye data of sample objects to obtain the above-mentioned left eye fatigue detection network, the above-mentioned right eye fatigue detection network and the above-mentioned eye fatigue analysis network.

[0113] In a specific embodiment, the above-mentioned head-mounted device or other similar devices can be used to collect the original eye data of the sample object, and the original eye data can be preprocessed and feature extracted to obtain the sample eye processing. Specifically, the preprocessing method may include: resampling, filtering processing, normalization processing, etc., and the feature extraction method may include but is not limited to: a feature extraction method based on a convolutional neural network and a feature extraction method similar to steps S601 to S604 and steps S701 to S709.

[0114] In a specific embodiment, Fig. 9 As shown, the training method of the left eye fatigue detection network, the right eye fatigue detection network and the eye fatigue analysis network may include:

[0115] S901, obtaining sample blink data, sample eye usage duration, and sample head posture data of a sample object, wherein the sample blink data includes sample left eye blink data and sample right eye blink data.

[0116] S902, obtaining the marking eye fatigue information and the marking eye difference information corresponding to the sample object.

[0117] In practical applications, before conducting network training, the training data can be determined first. Specifically, in an embodiment of the present application, sample eye data of a sample object containing labeled eye fatigue information and labeled eye difference information can be obtained as training data, wherein the sample eye data can include sample blink data, sample eye duration, and sample head posture data.

[0118] Specifically, the annotated eye fatigue information may be preset eye fatigue information annotated in advance for the sample eye data, and the annotated eye difference information may be preset eye difference information annotated in advance for the sample eye data.

[0119] S903, inputting the sample left eye blink data, the sample eye usage time and the sample head posture data into a preset left eye fatigue detection network to perform left eye fatigue detection, and obtaining the sample left eye fatigue information of the sample object.

[0120] S904, inputting the sample right eye blink data, the sample eye usage time and the sample head posture data into a preset right eye fatigue detection network to perform right eye fatigue detection, and obtaining the sample right eye fatigue information of the sample object.

[0121] S905, inputting the sample left eye fatigue information and the sample right eye fatigue information into a preset eye fatigue analysis network to perform eye fatigue analysis, and obtaining the sample eye fatigue information and sample eye difference information of the sample object.

[0122] S906 , determining target loss information based on the sample eye fatigue information and the sample eye difference information as well as the labeled eye fatigue information and the labeled eye difference information.

[0123] S907, based on the target loss information, train a preset left eye fatigue detection network, a preset right eye fatigue detection network and a preset active eye fatigue analysis network to obtain a left eye fatigue detection network, a right eye fatigue detection network and an active eye fatigue analysis network.

[0124] In an optional embodiment, the target loss information may include eye fatigue information loss and eye difference information loss;

[0125] Accordingly, the above-mentioned determination of the target loss information based on the sample eye fatigue information and the sample eye difference information and the annotated eye fatigue information and the annotated eye difference information may include:

[0126] The loss of eyes fatigue information is determined based on the annotated eyes fatigue information and the sample eyes fatigue information; the loss of eyes difference information is determined based on the annotated eyes difference information and the sample eyes difference information.

[0127] In a specific embodiment, the above-mentioned determination of the eye fatigue information loss based on the annotated eye fatigue information and the sample eye fatigue information may include determining the eye fatigue information loss between the annotated eye fatigue information and the sample eye fatigue information based on a first preset loss function; the above-mentioned determination of the eye difference information loss based on the annotated eye difference information and the sample eye difference information may include: determining the eye difference information loss between the annotated eye difference information and the sample eye difference information based on a second preset loss function. Optionally, the first preset loss function and the second preset loss function may be the same loss function or different loss functions.

[0128] In a specific embodiment, the loss of eye fatigue information can represent the difference between the labeled eye fatigue information and the sample eye fatigue information, and the loss of eye difference information can represent the difference between the labeled eye difference information and the sample eye difference information.

[0129] In a specific embodiment, the first preset loss function may include but is not limited to a cross entropy loss function, a logical loss function, an exponential loss function, etc., and the second preset loss function may include but is not limited to a cross entropy loss function, a logical loss function, an exponential loss function, etc.

[0130] In an optional embodiment, based on the target loss information, training a preset left eye fatigue detection network, a preset right eye fatigue detection network and a preset eye fatigue analysis network to obtain the left eye fatigue detection network, the right eye fatigue detection network and the eye fatigue analysis network may include: based on the target loss information, updating the network parameters of the preset left eye fatigue detection network, the preset right eye fatigue detection network and the preset eye fatigue analysis network; based on the updated preset left eye fatigue detection network, the preset right eye fatigue detection network and the preset eye fatigue analysis network, repeating the media content label recognition training iteration operation of step S903 to update the network parameters of the preset feature fusion network based on the target loss information, until the eye fatigue monitoring training iteration operation is performed to update the network parameters of the preset left eye fatigue detection network, the preset right eye fatigue detection network and the preset eye fatigue analysis network based on the target loss information, until the eye fatigue monitoring convergence condition is reached; the preset left eye fatigue detection network, the preset right eye fatigue detection network and the preset eye fatigue analysis network obtained when the eye fatigue monitoring convergence condition is reached are used as the left eye fatigue detection network, the right eye fatigue detection network and the eye fatigue analysis network.

[0131] In an optional embodiment, the above-mentioned convergence condition for achieving eye fatigue monitoring can be that the number of training iteration operations reaches a preset number of training times. Optionally, the convergence condition for achieving eye fatigue monitoring can also be that the target loss information is less than a specified threshold. In the embodiments of this specification, the preset number of training times and the specified threshold can be pre-set in combination with the training speed and accuracy of the network in actual applications.

[0132] In a specific embodiment, Fig.10 As shown, an eye fatigue monitoring network including the left eye fatigue detection network, the right eye fatigue detection network and the eye fatigue analysis network is established, and the target blink data, eye use time and head posture data of the target object are input into the eye fatigue monitoring network for eye fatigue monitoring to obtain the target object's eye fatigue information and eye difference information.

[0133] It can be seen from the above embodiments that, on the one hand, based on the machine learning training of the sample blink data of the sample object and the corresponding annotated eye fatigue information and the annotated eye difference information, an eye fatigue monitoring network with high generalization ability is obtained; on the other hand, by jointly training the preset left eye fatigue detection network, the preset right eye fatigue detection network and the preset eye fatigue analysis network, the training efficiency can be improved while the accuracy of the network in monitoring eye fatigue can be better improved.

[0134] In an optional embodiment, the method may further include: controlling the vibration module to perform vibration reminder according to the vibration mode corresponding to the eye fatigue information.

[0135] Specifically, the vibration pattern includes a target vibration frequency and a target vibration duration.

[0136] In an optional embodiment, when the eyes fatigue information is mild eyes fatigue, the target vibration frequency can be 2 Hz, and the target vibration duration can be 1 second; when the eyes fatigue information is moderate eyes fatigue, the target vibration frequency can be 5 Hz, and the target vibration duration can be 2 seconds; when the eyes fatigue information is severe eyes fatigue, the target vibration frequency can be 10 Hz, and the target vibration duration can include a single vibration duration and an interval vibration duration. Optionally, the single vibration duration can be 2 seconds, and the interval vibration duration can be 5 seconds.

[0137] It can be seen from the above embodiments that by controlling the vibration module to perform vibration reminders corresponding to eye fatigue information, the target object is reminded to pay attention to eye health, avoid excessive fatigue, and improve the user experience.

[0138] In an optional embodiment, if Fig.11 As shown, the above method may also include:

[0139] S506, collecting illumination data of the environment where the target object is located through an illumination sensor.

[0140] Specifically, the lighting data may include, but is not limited to: illumination, strobe, color rendering, and color temperature.

[0141] S507, collecting the eye distance of the target object through a distance measuring sensor.

[0142] Specifically, the eye distance may be the distance between the gaze direction of the target object's eyes and the obstructing object in front of the target object.

[0143] S508, performing angle calibration based on the head tilt angle data and the preset calibration tilt angle data to obtain the eye angle of the target object.

[0144] Specifically, the eye angle here is the angle between the eye's gaze direction and the vertical plane of space.

[0145] Specifically, the angle difference between the head tilt angle data and the preset calibration tilt angle data is used as the eye angle of the target object.

[0146] In actual applications, when the target object wears the above-mentioned head-worn device for the first time, the collected data of the head-worn device can be initialized. When the target object enters the standard sitting state, the head inclination data at this time is collected through the third inclination angle, and the head inclination data at this time is used as the preset calibration inclination data.

[0147] S509: Acquire historical eye fatigue information of the target object.

[0148] Specifically, the historical eyestrain information may be eyestrain information of the target object at historical moments.

[0149] In an optional embodiment, the historical eye fatigue information of the target object can be obtained from the storage module of the head-mounted device.

[0150] In another optional embodiment, historical eye fatigue information of the target object may be obtained from the cloud.

[0151] S510, generating fatigue change information of the target object based on the historical eye fatigue information and the eye fatigue information.

[0152] Specifically, the fatigue change information may represent changes in the target object's eye fatigue.

[0153] In a specific embodiment, when the historical eyestrain information includes the historical eyestrain value a, and the eyestrain information includes the eyestrain value b, the fatigue change information=(ab) / a×100%.

[0154] S511, generating eye fatigue monitoring information based on lighting data, eye distance, eye angle, eye usage time, and fatigue change information.

[0155] S512: Push the eye fatigue monitoring information to the mobile terminal corresponding to the target object through the communication module.

[0156] In the embodiments of this specification, the mobile terminal corresponding to the target object may include, but is not limited to, physical devices such as smart phones, vehicle-mounted terminals, computers (such as desktop computers, tablet computers, laptops), digital assistants, intelligent voice interaction devices (such as smart speakers), smart wearable devices, etc., and may also be software running in physical devices, such as computer programs and APPs (applications).

[0157] It can be seen from the above embodiments of the present application that, by utilizing the technical solution provided in the embodiments of the present application, on the one hand, the head posture data of the target object is collected through the third tilt sensor, and the first tilt data and the second tilt data of the target object are collected respectively through the first tilt sensor and the second tilt sensor, and the first tilt data and the second tilt data are analyzed for tilt change to obtain the tilt change analysis result; and based on the tilt change analysis result and the EEG signal data, the left and right eye blink data are distinguished to facilitate the subsequent left and right eye fatigue detection; on the other hand, the left eye blink data, the eye use time and the head posture data are input into the left eye fatigue detection network to perform left eye fatigue detection, and the right eye blink data, the eye use time and the head posture data are input into the left eye fatigue detection network to perform left eye fatigue detection, and the right eye blink data, the eye use time and the head posture data are input into the left eye fatigue detection network to perform left eye fatigue detection. The duration and head posture data are input into the right eye fatigue detection network for right eye fatigue detection, which can distinguish the fatigue information of the left and right eyes. On the other hand, the left eye fatigue information and the right eye fatigue information are input into the eye fatigue analysis network for eye fatigue analysis, which can improve the accuracy of eye fatigue analysis; on the other hand, by jointly training the preset left eye fatigue detection network, the preset right eye fatigue detection network and the preset eye fatigue analysis network, the training efficiency can be improved while the accuracy of the network's eye fatigue monitoring can be better improved; on the other hand, by controlling the vibration module to perform vibration reminders corresponding to the eye fatigue information, the target object can be reminded to pay attention to eye health, avoid excessive fatigue, and improve the user experience.

[0158] The embodiment of the present application provides an eye fatigue monitoring device, which is implemented based on the head wearable device as described above. Fig.12 As shown, the above device comprises:

[0159] The first acquisition module 1210 is used to collect target blink data and eye use duration of the target object through the first tilt sensor, the second tilt sensor and the forehead electroencephalogram sensor, where the target blink data includes left eye blink data and right eye blink data;

[0160] The second acquisition module 1220 is used to acquire head posture data of the target object through a third tilt sensor;

[0161] The left eye fatigue detection module 1230 is used to perform left eye fatigue detection based on left eye blink data, eye usage time and head posture data to obtain left eye fatigue information of the target object;

[0162] A right eye fatigue detection module 1240 is used to perform right eye fatigue detection based on right eye blink data, eye usage time and head posture data to obtain right eye fatigue information of the target object;

[0163] The eye fatigue analysis module 1250 is used to perform eye fatigue analysis based on the left eye fatigue information and the right eye fatigue information to obtain the eye fatigue information and eye difference information of the target object.

[0164] In the embodiment of this specification, the first acquisition module 1210 may include:

[0165] An inclination acquisition unit, used to respectively acquire first inclination data and second inclination data of a target object within a preset time period through a first inclination sensor and a second inclination sensor;

[0166] An EEG signal data acquisition unit, used to acquire EEG signal data of a target object within a preset time period through a forehead EEG sensor;

[0167] The eye use time unit is used to take the time length of the electroencephalogram signal data greater than the blink signal threshold within a preset time period as the eye use time;

[0168] The eye state analysis unit is used to perform eye state analysis based on the EEG signal data, the first inclination angle data and the second inclination angle data to obtain target blinking data within a preset time period.

[0169] In a specific embodiment, the eye status analysis unit may include:

[0170] A traversal unit, used to traverse the EEG signal data at multiple moments within a preset time period;

[0171] The tilt angle change analysis unit is used to perform tilt angle change analysis on the first tilt angle data and the second tilt angle data at the corresponding moment of the currently traversed EEG signal data when the currently traversed EEG signal data is greater than the blink signal threshold, and obtain the tilt angle change analysis result;

[0172] A target blinking state determination unit, used to determine the target blinking state corresponding to the currently traversed EEG signal data according to the inclination change analysis result;

[0173] A first data group unit, configured to add the currently traversed EEG signal data to a first data group when the target blinking state is a left eye blink;

[0174] A second data group unit, for adding the currently traversed EEG signal data to a second data group when the target blinking state is a right eye blink;

[0175] A first statistical analysis unit is used to perform statistical analysis on the EEG signal data in the first data group after traversing the EEG signal data at multiple moments in a preset time period, so as to obtain the left eye blinking frequency and the first duration corresponding to multiple blinking intensities of the left eye;

[0176] A second statistical analysis unit is used to perform statistical analysis on the EEG signal data in the second data group to obtain the blinking frequency of the right eye and the second durations corresponding to the multiple blinking intensities of the right eye;

[0177] a left eye blink data unit, used for taking the left eye blink frequency and the first duration as the left eye blink data;

[0178] The right eye blink data unit is used to use the blink frequency and the second duration of the right eye as the right eye blink data.

[0179] In a specific embodiment, the second acquisition module 1220 may include:

[0180] A head tilt angle data acquisition unit, used for acquiring head tilt angle data of a target object through a third tilt angle sensor;

[0181] The head posture analysis unit is used to perform head posture analysis on the head tilt angle data to obtain head posture data.

[0182] In a specific embodiment, the left eye fatigue detection module 1230 may include:

[0183] A left eye fatigue detection network unit is used to input left eye blink data, eye usage time and head posture data into a left eye fatigue detection network to perform left eye fatigue detection and obtain left eye fatigue information;

[0184] The above-mentioned right eye fatigue detection module 1240 may include:

[0185] A right eye fatigue detection network unit is used to input right eye blink data, eye use time and head posture data into a right eye fatigue detection network to perform right eye fatigue detection and obtain right eye fatigue information;

[0186] The eye fatigue analysis module 1250 may include:

[0187] The eye fatigue analysis network unit is used to input left eye fatigue information and right eye fatigue information into the eye fatigue analysis network to perform eye fatigue analysis and obtain eye fatigue information and eye difference information.

[0188] In a specific embodiment, the above device may further include:

[0189] A sample data acquisition module is used to acquire sample blink data, sample eye use duration and sample head posture data of a sample object, wherein the sample blink data includes sample left eye blink data and sample right eye blink data;

[0190] A labeling data acquisition module, used to acquire labeling eye fatigue information and labeling eye difference information corresponding to the sample object;

[0191] A preset left eye fatigue detection network module is used to input sample left eye blink data, sample eye use time and sample head posture data into a preset left eye fatigue detection network to perform left eye fatigue detection, and obtain sample left eye fatigue information of the sample object;

[0192] A preset right eye fatigue detection network module is used to input sample right eye blink data, sample eye use time and sample head posture data into a preset right eye fatigue detection network to perform right eye fatigue detection, and obtain sample right eye fatigue information of the sample object;

[0193] A preset eye fatigue analysis network module is used to input the sample left eye fatigue information and the sample right eye fatigue information into a preset eye fatigue analysis network for eye fatigue analysis, and obtain the sample eye fatigue information and the sample eye difference information of the sample object;

[0194] A target loss information determination module, used to determine target loss information based on the sample eye fatigue information and the sample eye difference information and the annotation eye fatigue information and the annotation eye difference information;

[0195] The training module is used to train a preset left eye fatigue detection network, a preset right eye fatigue detection network and a preset active eye fatigue analysis network based on target loss information to obtain a left eye fatigue detection network, a right eye fatigue detection network and an active eye fatigue analysis network.

[0196] In an optional embodiment, the above device may further include:

[0197] The vibration module is used to control the vibration module to perform vibration reminder according to the vibration mode corresponding to the eye fatigue information.

[0198] In an optional embodiment, the above device may further include:

[0199] A light data acquisition module is used to collect light data of the environment where the target object is located through a light sensor;

[0200] The eye distance acquisition module is used to acquire the eye distance of the target object through a distance measurement sensor;

[0201] The eye angle calibration module is used to perform angle calibration based on the head tilt angle data and the preset calibration tilt angle data to obtain the eye angle of the target object;

[0202] A historical eye fatigue information acquisition module is used to acquire the historical eye fatigue information of the target object;

[0203] A fatigue change information generating module, used for generating fatigue change information of a target object based on historical eye fatigue information and eye fatigue information;

[0204] An eye fatigue monitoring information generation module is used to generate eye fatigue monitoring information based on illumination data, eye distance, eye angle, eye duration, and fatigue change information;

[0205] The information push module is used to push eye fatigue monitoring information to the mobile terminal corresponding to the target object through the communication module.

[0206] The device and method embodiments in the above device embodiments are based on the same inventive concept and will not be described one by one here.

[0207] An embodiment of the present application also provides a storage medium, which can be set in a head-worn device to store at least one instruction or at least one program related to an eye fatigue monitoring method for implementing one of the method embodiments. The at least one instruction or the at least one program is loaded and executed by the processor to implement the eye fatigue monitoring method provided by the above method embodiment.

[0208] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: various media that can store program codes, such as read-only memory (ROM), random access memory (RAM), etc.

[0209] It can be seen from the embodiments of the head-worn device, eye fatigue monitoring method, device and storage medium provided by the above-mentioned application that, using the technical solution provided by the embodiments of the present application, on the one hand, the head posture data of the target object is collected through the third tilt sensor, and the first tilt data and the second tilt data of the target object are collected through the first tilt sensor and the second tilt sensor respectively, and the first tilt data and the second tilt data are analyzed for tilt change to obtain the tilt change analysis result; and based on the tilt change analysis result and the EEG signal data, the left and right eye blink data are distinguished to facilitate the subsequent left and right eye fatigue detection; on the other hand, the left eye blink data, the eye use time and the head posture data are input into the left eye fatigue detection network to perform left eye fatigue detection. On the other hand, by measuring and inputting the right eye blink data, eye usage time and head posture data into the right eye fatigue detection network for right eye fatigue detection, it can distinguish the fatigue information of the left and right eyes. On the other hand, by inputting the left eye fatigue information and the right eye fatigue information into the eye fatigue analysis network for eye fatigue analysis, it can improve the accuracy of eye fatigue analysis; on the other hand, by jointly training the preset left eye fatigue detection network, the preset right eye fatigue detection network and the preset eye fatigue analysis network, the training efficiency can be improved while the accuracy of the network's eye fatigue monitoring can be better improved; on the other hand, by controlling the vibration module to perform vibration reminders corresponding to the eye fatigue information, the target object can be reminded to pay attention to eye health, avoid excessive fatigue, and improve the user experience.

[0210] It should be noted that, for the convenience of description, the aforementioned method embodiments are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, some steps can be performed in other sequences or simultaneously. In addition, the above embodiments can be arbitrarily combined to obtain other embodiments.

[0211] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in certain embodiments, please refer to the relevant description of other embodiments. Those skilled in the art may also understand that the various illustrative logical blocks, units, and steps listed in the embodiments of the present invention may be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly demonstrate the interchangeability of hardware and software, the various illustrative components, units, and steps mentioned above have generally described their functions. Whether such functions are implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the above functions for each specific application, but such implementation should not be understood as exceeding the scope of protection of the embodiments of the present invention.

[0212] The above description has fully disclosed the specific embodiments of the present invention. It should be pointed out that any changes made by those skilled in the art to the specific embodiments of the present invention do not deviate from the scope of the claims of the present invention. Accordingly, the scope of the claims of the present invention is not limited to the above specific embodiments.

Claims

1. A head wearable device, characterized in that: The device comprises: a wearable body and a nose pad structure, the nose pad structure is connected to the wearable body, the left and right sides of the nose pad structure respectively comprise a first tilt sensor and a second tilt sensor, the wearable body comprises: a controller, a forehead EEG sensor, a third tilt sensor and a communication module, the controller is respectively electrically connected to the first tilt sensor, the second tilt sensor, the forehead EEG sensor, the third tilt sensor and the communication module, wherein: When the target object wears the head wearable device, the forehead EEG sensor is used to collect EEG signal data of the target object within a preset time period, and the first tilt sensor and the second tilt sensor are respectively used to collect the first tilt data and the second tilt data on both sides of the corners of the eyes and above the bridge of the nose of the target object within the preset time period to distinguish the left and right eye blink data of the target object; the left eye blink data of the target object is obtained by statistically analyzing the EEG signal data within the preset time period that is greater than the blink signal threshold and the angle change result at the corresponding moment meets the first angle change condition; the right eye blink data of the target object is obtained by statistically analyzing the EEG signal data within the preset time period that is greater than the blink signal threshold and the angle change result at the corresponding moment meets the second angle change condition; the angle change result at the corresponding moment is the tilt change analysis result between the first tilt data and the second tilt data at the corresponding moment.

2. The device according to claim 1, characterized in that The wearable body also includes: a vibration module, and the controller is electrically connected to the vibration module.

3. The device according to claim 1 or 2, characterized in that The wearable body also includes: a light sensor and a distance sensor, and the controller is electrically connected to the light sensor and the distance sensor respectively.

4. A method for monitoring eye fatigue based on the head-worn device according to any one of claims 1 to 3, characterized in that: The method comprises: Collect target blink data and eye use duration of the target object through the first tilt sensor, the second tilt sensor and the forehead electroencephalogram sensor, wherein the target blink data includes left eye blink data and right eye blink data; collecting head posture data of the target object through a third inclination sensor; Perform left eye fatigue detection based on the left eye blink data, the eye usage time and the head posture data to obtain left eye fatigue information of the target object; Perform right eye fatigue detection based on the right eye blink data, the eye usage time and the head posture data to obtain right eye fatigue information of the target object; Eye fatigue analysis is performed based on the left eye fatigue information and the right eye fatigue information to obtain the eye fatigue information and eye difference information of the target object.

5. The method according to claim 4, characterized in that The method of collecting target blink data and eye use duration of the target object by using the first tilt sensor, the second tilt sensor and the forehead electroencephalogram sensor comprises: respectively collecting first inclination data and second inclination data of the target object within a preset time period by using the first inclination sensor and the second inclination sensor; Collecting EEG signal data of the target object within the preset time period by the forehead EEG sensor; The length of time during which the EEG signal data is greater than the blink signal threshold within the preset time period is used as the eye use time; The eye state analysis is performed based on the EEG signal data, the first inclination angle data and the second inclination angle data to obtain the target blinking data within the preset time period.

6. The method according to claim 5, characterized in that The performing eye state analysis based on the EEG signal data, the first tilt angle data, and the second tilt angle data to obtain the target blink data within the preset time period includes: Traversing the EEG signal data at multiple moments within the preset time period; When the currently traversed EEG signal data is greater than the blink signal threshold, performing an inclination change analysis on the first inclination data and the second inclination data at the corresponding moment of the currently traversed EEG signal data to obtain an inclination change analysis result; Determining the target blinking state corresponding to the currently traversed EEG signal data according to the inclination angle change analysis result; When the target blinking state is a left eye blink, adding the currently traversed EEG signal data to the first data group; When the target blinking state is a right eye blink, adding the currently traversed EEG signal data to the second data group; After traversing the EEG signal data at multiple moments within the preset time period, statistically analyzing the EEG signal data in the first data group to obtain the blinking frequency of the left eye and the first duration corresponding to the multiple blinking intensities of the left eye; Performing statistical analysis on the EEG signal data in the second data group to obtain the blinking frequency of the right eye and the second durations corresponding to the multiple blinking intensities of the right eye; Using the left eye blinking frequency and the first duration as the left eye blinking data; The blink frequency of the right eye and the second duration are used as the right eye blink data.

7. The method according to claim 4, characterized in that The collecting the head posture data of the target object by the third tilt sensor comprises: Collecting head tilt data of the target object by a third tilt sensor; Performing head posture analysis on the head tilt angle data to obtain the head posture data.

8. The method according to any one of claims 4 to 7, characterized in that: The left eye fatigue detection is performed based on the left eye blink data, the eye usage time and the head posture data to obtain the left eye fatigue information of the target object, including: Inputting the left eye blink data, the eye use time and the head posture data into a left eye fatigue detection network to perform left eye fatigue detection, and obtaining the left eye fatigue information; The performing right eye fatigue detection based on the right eye blink data, the eye use time and the head posture data to obtain the right eye fatigue information of the target object includes: Inputting the right eye blink data, the eye use time and the head posture data into a right eye fatigue detection network to perform right eye fatigue detection to obtain the right eye fatigue information; The performing fatigue analysis based on the left eye fatigue information and the right eye fatigue information to obtain the eye fatigue information and eye difference information of the target object includes: The left eye fatigue information and the right eye fatigue information are input into an eye fatigue analysis network to perform eye fatigue analysis to obtain the eye fatigue information and the eye difference information.

9. The method according to claim 8, characterized in that The method further comprises: Acquire sample blink data, sample eye use duration, and sample head posture data of the sample object, wherein the sample blink data includes sample left eye blink data and sample right eye blink data; Obtaining the marking eye fatigue information and the marking eye difference information corresponding to the sample object; Inputting the sample left eye blink data, the sample eye usage time and the sample head posture data into a preset left eye fatigue detection network to perform left eye fatigue detection, and obtaining the sample left eye fatigue information of the sample object; Inputting the sample right eye blink data, the sample eye usage time and the sample head posture data into a preset right eye fatigue detection network to perform right eye fatigue detection, and obtaining the sample right eye fatigue information of the sample object; Inputting the sample left eye fatigue information and the sample right eye fatigue information into a preset eye fatigue analysis network to perform eye fatigue analysis, thereby obtaining the sample eye fatigue information and sample eye difference information of the sample object; Determining target loss information based on the sample eye fatigue information and the sample eye difference information and the annotation eye fatigue information and the annotation eye difference information; Based on the target loss information, the preset left eye fatigue detection network, the preset right eye fatigue detection network and the preset active eye fatigue analysis network are trained to obtain the left eye fatigue detection network, the right eye fatigue detection network and the active eye fatigue analysis network.

10. The method according to any one of claims 4 to 7, characterized in that: The method further comprises: According to the vibration mode corresponding to the eye fatigue information, the vibration module is controlled to perform vibration reminder.

11. The method according to claim 7, characterized in that The method further comprises: Collecting illumination data of the environment where the target object is located through an illumination sensor; The eye distance of the target object is collected by a distance measuring sensor; Performing angle calibration based on the head tilt angle data and preset calibration tilt angle data to obtain the eye angle of the target object; Acquire historical eye fatigue information of the target object; generating fatigue change information of the target object based on the historical eye fatigue information and the eye fatigue information; Generate eye fatigue monitoring information based on the illumination data, the eye use distance, the eye use angle, the eye use time, and the fatigue change information; The eye fatigue monitoring information is pushed to a mobile terminal corresponding to the target object through a communication module.

12. A device for monitoring eye fatigue based on the head-worn device according to any one of claims 1 to 3, characterized in that: The device comprises: A first acquisition module is used to acquire target blink data and eye use duration of the target object through a first tilt sensor, a second tilt sensor and a forehead electroencephalogram sensor, wherein the target blink data includes left eye blink data and right eye blink data; A second acquisition module, used for acquiring head posture data of the target object through a third tilt sensor; A left eye fatigue detection module, used to perform left eye fatigue detection based on the left eye blink data, the eye use time and the head posture data, and obtain left eye fatigue information of the target object; A right eye fatigue detection module, used to perform right eye fatigue detection based on the right eye blink data, the eye use time and the head posture data, and obtain right eye fatigue information of the target object; The eye fatigue analysis module is used to perform eye fatigue analysis based on the left eye fatigue information and the right eye fatigue information to obtain the eye fatigue information and eye difference information of the target object.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the eye fatigue monitoring method as described in any one of claims 4 to 11.

Images