Intelligent equipment for ophthalmologic postoperative body position monitoring

Abstract

The invention discloses an intelligent device for ophthalmologic post-operation body position monitoring, and relates to the technical field of ophthalmologic post-operation body position monitoring, the intelligent device comprises an ear-hanging type shell, the interior of the ear-hanging type shell is provided with a human body wearing detection module, a three-axis acceleration sensor module, a voice reminding module and a data storage module, the human body wearing detection module comprises an infrared sensor detection module and a temperature detection module. According to the intelligent equipment for ophthalmologic postoperative body position monitoring, an infrared sensor detection module judges whether the intelligent equipment is in a wearing state or not, and in order to avoid the situation that the infrared sensor detection module is blocked by foreign matter and misjudgment occurs, a temperature detection module, namely a temperature sensor, is added for multi-sensor fusion judgment; the temperature sensor is installed at the position, close to the ear, of the patient, and when the infrared sensor detection module is switched on and detects that the temperature is within a preset threshold value, it is judged that the patient is in an effective wearing state, so that it is ensured that the device is effectively worn, and the accuracy of body position monitoring is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of postoperative body position monitoring in ophthalmology, and in particular to an intelligent device for postoperative body position monitoring in ophthalmology. Background Art

[0002] The smart device for postoperative ophthalmic position monitoring is a wearable device designed to help patients maintain the correct position after ophthalmic surgery to promote recovery and prevent complications. This device can greatly improve the quality of postoperative recovery after ophthalmic surgery, help doctors better manage postoperative care, and also make it easier for patients to follow postoperative care recommendations.

[0003] Existing smart devices for postoperative body position monitoring in ophthalmology are prone to inaccurate body position monitoring due to improper wearing method, which can cause errors in postoperative recovery due to inaccurate body position monitoring, and in severe cases can have negative effects.

[0004] Therefore, in view of this, the existing structure and deficiencies are studied and improved, and an intelligent device for postoperative body position monitoring in ophthalmology is proposed. Summary of the invention

[0005] In view of the deficiencies of the prior art, the present invention provides an intelligent device for monitoring body position after ophthalmic surgery, which solves the problems raised in the above background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent device for postoperative body position monitoring in ophthalmology, comprising an ear-hook housing, wherein a human body wearing detection module, a three-axis acceleration sensor module, a voice reminder module and a data storage module are arranged inside the ear-hook housing, wherein the human body wearing detection module comprises an infrared sensor detection module and a temperature detection module, wherein the infrared sensor detection module specifically comprises:

[0007] Transmitter: Select an infrared LED as the transmitter, which emits infrared light of a specified wavelength;

[0008] Receiver: Use an infrared light sensor such as a photodiode or phototransistor as a receiver, which senses infrared light and converts it into an electrical signal;

[0009] Transmitting signal: ESP32 outputs 1kHz square wave through GPIO pin to drive infrared LED to emit infrared light;

[0010] Received signal: When infrared light hits the human body or other objects and is reflected back to the receiver, the receiver performs cross-correlation analysis on the received signal and the 1kHz drive signal. The reflected infrared signal is extracted using the cross-correlation function, the same frequency is correlated, and the different frequencies are uncorrelated. The interference of the environment is filtered out to avoid interference caused by other infrared light such as sunlight. The algorithm formula is as follows:

[0011]

[0012] Signal processing: h(t) and gt are the emission light function and the receiving light function respectively. From the above formula, we can know that the cross-correlation function is equivalent to the convolution operation of two functions in the time domain, which is equivalent to the multiplication of two signals in the frequency domain. First, the emission function and the infrared receiving function are discrete Fourier transformed, and then multiplied, that is, the collected signal and the emission signal are cross-correlated to filter out the signal components with different emission frequencies;

[0013] The temperature detection module specifically includes:

[0014] Temperature sensor: Use a constant current source to drive the NTC thermistor. As the temperature changes, the NTC resistance changes, causing the voltage across the NTC to change. The ADC collects different voltage values ​​to calculate the sensed temperature.

[0015] The collected data is subjected to a digital filtering algorithm to perform sliding average on the collected data to filter out the noise and random components in the signal, as shown in the following formula:

[0016] y n =(x n +x n+1 +x n+2 +…+x n+m-2 +x n+m-1 ) / m

[0017] Where m is the number of sliding average points, and 20 sampling points are selected in sequence for averaging to filter out interference components.

[0018] Furthermore, the three-axis acceleration sensor module is worn on the patient's ear through an ear-hook shell. The three-axis acceleration sensor module reads the acceleration values ​​in the spatial XYZ directions to obtain the patient's facial angle and motion information. When it is detected that the patient's facial angle information exceeds 20% in the horizontal direction, the voice module issues a voice reminder to remind the patient to correct his facial posture.

[0019] Furthermore, the data storage module is used to store data during the patient's wearing process, including but not limited to wearing time, wearing angle, and movement status.

[0020] Furthermore, a core processing module is also provided inside the ear-hook shell, and the core processing module is connected to the human wearing detection module, the three-axis acceleration sensor module, the voice reminder module and the data storage module. The core processing module is used to communicate with the peripheral modules for data recording and comprehensive analysis.

[0021] Furthermore, the core processing module controls the peripheral modules and reads data, detects the patient's wearing status and movement status, filters the collected data, predicts the patient's condition based on information such as wearing time and single wearing period, and compares it with the medical rehabilitation model, and guides the patient on the precautions needed at the current stage through voice.

[0022] Furthermore, the core processing module performs the following specific operations when predicting the patient's condition:

[0023] Analyze the collected data, including wearing period, wearing time, wearing angle, gender, age and other information, and combine the rehabilitation cases of previous patients to guide the current patients to have better rehabilitation. The specific method is described as using linear regression to analyze a large amount of data based on the rehabilitation cases of previous patients using machine learning algorithms to obtain relevant weight values, and derive a prediction data model. The formula is input into the ESP32 main controller, and the main controller uses the rehabilitation model to predict based on the collected data to obtain the maximum expected value, and guides the patient through voice.

[0024] The large model formula is expressed as: y = w1x1 + w2x2 + ... + w n x n

[0025] Among them, "y" is the target value of the prediction model. The closer the value of y is to 1, the faster the patient's recovery time will be. x is the characteristic value, that is, the relevant influencing factors, including wearing period, duration, angle and other information; w is the weight of the relevant influencing factors, that is, the proportion of such information as wearing period, wearing duration and wearing angle in the patient's recovery process.

[0026] Furthermore, an ear post is fixedly provided on the side surface of the ear-hook housing, and a colloid ear plug is arranged on the outer wall of the end of the ear post.

[0027] Furthermore, an adapter ring is fixedly mounted on the outer wall of the ear post, and the outer side of the adapter ring fits the inner side of the colloid earplug. An arc-shaped transition groove is formed on the outer side of the adapter ring, and micro balls are embedded in the surfaces of the outer side of the adapter ring and the arc-shaped transition groove.

[0028] Furthermore, an elastic sheet is provided between the arc-shaped transition groove and the inner side surface of the colloid earplug, and a disc is fixed to the end of the elastic sheet. The disc is rotatably connected to the ear-hook housing, and the ear post passes through the middle of the disc.

[0029] Furthermore, a transmission gear is fixed to the side of the disc away from the elastic sheet, and one side of the transmission gear is meshedly connected with a driving gear, a side surface of the driving gear is connected to a micro motor, and the micro motor is fixedly connected to the ear-hook housing.

[0030] The present invention provides an intelligent device for monitoring body position after ophthalmic surgery, which has the following beneficial effects:

[0031] 1. This intelligent device for monitoring body position after ophthalmological surgery, when the patient wears it, the transmitter emits infrared light that is reflected through the patient's ear to the receiver, and the infrared sensor detection module is turned on to determine whether it is in a wearing state. In order to avoid the infrared sensor detection module being blocked by foreign objects and causing misjudgment, a temperature detection module, i.e., a temperature sensor, is added to perform multi-sensor fusion judgment. The temperature sensor is installed close to the patient's ear. When the infrared sensor detection module is turned on and the temperature is detected to be within the preset threshold, it is determined that the patient is in an effective wearing state, thereby ensuring that the device is effectively worn to ensure the accuracy of body position monitoring.

[0032] 2. The intelligent device for monitoring postoperative body position of ophthalmology, when the infrared sensor detection module and the temperature detection module detect that the device is away from the ear, determines that the device is removed. At this time, the micro motor drives the driving gear to rotate to drive the transmission gear to make the disk carry the elastic sheet to rotate, and the elastic sheet moves along the outer side surface of the adapter ring and the surface of the arc-shaped transition groove. The wavy structure of the outer side surface of the adapter ring and the surface of the arc-shaped transition groove makes the elastic sheet continuously vibrate during the rotation process to exert a shaking effect on the colloidal earplug. The colloidal earplug is affected by the shaking to shake off impurities in the ear canal attached to its surface, so as to prevent impurities from being attached to the surface of the colloidal earplug after it is removed, and at the same time, avoid the long-term attachment of impurities due to the patient taking off the colloidal earplug without checking whether there are impurities on the surface. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a schematic diagram of the device workflow of an intelligent device for postoperative body position monitoring in ophthalmology according to the present invention;

[0034] Figure 2 A schematic diagram of the cross-linking relationship between system modules of an intelligent device for postoperative body position monitoring in ophthalmology according to the present invention;

[0035] Figure 3 This is a schematic diagram of the outer side structure of an ear-hook housing of an intelligent device for postoperative body position monitoring in ophthalmology according to the present invention;

[0036] Figure 4 This is a schematic diagram of the inner side structure of an ear-hook housing of an intelligent device for monitoring body position after ophthalmological surgery according to the present invention;

[0037] Figure 5 This is a schematic diagram of the driving gear structure of an intelligent device for postoperative body position monitoring in ophthalmology according to the present invention;

[0038] Figure 6 This is a schematic diagram of the transmission gear structure of an intelligent device for monitoring body position after ophthalmological surgery according to the present invention;

[0039] Figure 7 This is a schematic diagram of the internal structure of a colloid earplug of an intelligent device for monitoring body position after ophthalmological surgery according to the present invention;

[0040] Figure 8 This is a schematic diagram of the adapter ring structure of an intelligent device for postoperative body position monitoring in ophthalmology according to the present invention.

[0041] In the figure: 1. ear-hook housing; 2. ear post; 3. colloid ear plug; 4. adapter ring; 5. arc transition groove; 6. micro ball; 7. elastic sheet; 8. disc; 9. transmission gear; 10. drive gear; 11. micro motor. DETAILED DESCRIPTION

[0042] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0043] like Figure 1-Figure 4 As shown, the present invention provides a technical solution: an intelligent device for postoperative body position monitoring in ophthalmology, comprising an ear-hook housing 1, wherein a human body wearing detection module, a three-axis acceleration sensor module, a voice reminder module and a data storage module are arranged inside the ear-hook housing 1, wherein the human body wearing detection module comprises an infrared sensor detection module and a temperature detection module, wherein the infrared sensor detection module specifically comprises:

[0044] Transmitter: Select an infrared LED as the transmitter, which emits infrared light of a specified wavelength;

[0045] Receiver: Use an infrared light sensor such as a photodiode or phototransistor as a receiver, which senses infrared light and converts it into an electrical signal;

[0046] Transmitting signal: ESP32 outputs 1kHz square wave through GPIO pin to drive infrared LED to emit infrared light;

[0047] Received signal: When infrared light hits the human body or other objects and is reflected back to the receiver, the receiver performs cross-correlation analysis on the received signal and the 1kHz drive signal. The reflected infrared signal is extracted using the cross-correlation function, the same frequency is correlated, and the different frequencies are uncorrelated. The interference of the environment is filtered out to avoid interference caused by other infrared light such as sunlight. The algorithm formula is as follows:

[0048]

[0049] Signal processing: h(t) and gt are the emission light function and the receiving light function respectively. From the above formula, we can know that the cross-correlation function is equivalent to the convolution operation of two functions in the time domain, which is equivalent to the multiplication of two signals in the frequency domain. First, the emission function and the infrared receiving function are discrete Fourier transformed, and then multiplied, that is, the collected signal and the emission signal are cross-correlated to filter out the signal components with different emission frequencies;

[0050] The temperature detection module specifically includes:

[0051] Temperature sensor: Use a constant current source to drive the NTC thermistor. As the temperature changes, the NTC resistance changes, causing the voltage across the NTC to change. The ADC collects different voltage values ​​to calculate the sensed temperature.

[0052] The collected data is subjected to a digital filtering algorithm to perform sliding average on the collected data to filter out the noise and random components in the signal, as shown in the following formula:

[0053] y n =(x n +x n+1 +x n+2 +…+x n+m-2 +x n+m-1 ) / m

[0054] Where m is the number of sliding average points, and 20 sampling points are selected in sequence for averaging to filter out interference components;

[0055] The three-axis acceleration sensor module is worn on the patient's ear through the ear-hook housing 1, and the Z-axis direction is always kept consistent with the vertical direction of the patient's ear, and the Y-axis direction is consistent with the patient's face direction. When the patient's face is perpendicular to the ground plane, the Z-axis acceleration value is the largest, and when the patient's face is horizontal to the ground plane, the Y-axis acceleration is the largest. When the sensor data is detected to have a periodic jump with the same frequency as the step frequency (60-120 times / minute), it is judged that the patient is in a moving state. Therefore, the patient's facial angle and movement information are obtained by reading the acceleration value in the spatial XYZ direction. When it is detected that the patient's facial angle information exceeds the horizontal direction by 20%, the voice module issues a voice reminder to remind the patient to correct the facial posture, which is specifically implemented through the following steps:

[0056] Hardware interface: Use 3.3V to power ADXL345. ESP32 communicates with the ADXL345 chip through the SPI interface. The IO levels are all LVCMOS levels to realize the reading of acceleration values ​​in three directions.

[0057] Data processing: To avoid abnormal jitter in the collected data due to interference, the median filter algorithm is used to remove abnormal values ​​in the collected data. The main algorithm is described as collecting 10 data, sorting the data from small to large, and selecting the middle value for recording and judgment to avoid misjudgment due to abnormal data jumps;

[0058] The data storage module uses NORFLASH with SPI interface, which has a storage capacity of 32MB. It records data once a minute, writes by page, and writes 256 bytes of data each time. It can record continuously for 50 days and is used to store the data during the patient's wearing process, including but not limited to wearing time, wearing angle, and movement status;

[0059] A core processing module is also provided inside the ear-hook housing 1, and the core processing module is connected to the human body wearing detection module, the three-axis acceleration sensor module, the voice reminder module and the data storage module. The core processing module adopts an ESP32 module, integrates 2.4GWIFI, dual-core processing, and has a main frequency of up to 240MHz. It has a peripheral interface and can communicate with peripheral modules, collect three-axis acceleration sensor data through an SPI interface, collect human body wearing detection data through a general GPIO interface, control voice output, and record data in real time in the data storage module through an SPI interface. It can also access the wireless LAN through 2.4GWiFi to communicate with the wireless terminal to realize data download for data recording and comprehensive analysis;

[0060] The core processing module controls and reads data from peripheral modules, detects the patient's wearing status and movement status, filters the collected data, and predicts the patient's condition based on information such as wearing time and single wearing period, and compares it with the medical rehabilitation model. It guides the patient's current precautions through voice, and better helps the patient recover.

[0061] The core processing module performs the following operations when predicting the patient's condition:

[0062] Analyze the collected data, including wearing period, wearing time, wearing angle, gender, age and other information, and combine the rehabilitation cases of previous patients to guide the current patients to have better rehabilitation. The specific method is described as using linear regression to analyze a large amount of data based on the rehabilitation cases of previous patients using machine learning algorithms to obtain relevant weight values, and derive a prediction data model. The formula is input into the ESP32 main controller, and the main controller uses the rehabilitation model to predict based on the collected data to obtain the maximum expected value, and guides the patient through voice.

[0063] The large model formula is expressed as: y = w1x1 + w2x2 + ... + w n x n

[0064] Among them, "y" is the target value of the prediction model. The closer the value of y is to 1, the faster the patient's recovery time will be. x is the characteristic value, that is, the relevant influencing factors, including wearing period, duration, angle and other information; w is the weight of the relevant influencing factors, that is, the proportion of such information as wearing period, wearing duration and wearing angle in the patient's recovery process;

[0065] Based on the above description, the infrared sensor detection module and the temperature detection module are used to detect whether the patient is wearing the device effectively. The infrared sensor detection module includes an infrared transmitter and a receiver. The transmitter and the receiver are installed close to the patient's ear. When the patient wears it, the transmitter emits infrared light that is reflected by the patient's ear to the receiver. The infrared sensor detection module is turned on to determine whether it is in a wearing state. In order to avoid the infrared sensor detection module being blocked by foreign objects and making misjudgments, a temperature detection module, i.e., a temperature sensor, is added to perform multi-sensor fusion judgment. The temperature sensor is installed close to the patient's ear. When the infrared sensor detection module is turned on and the temperature is detected to be between 32°C and 38°C, it is determined that the patient is in an effective wearing state, thereby ensuring that the device is effectively worn to ensure the accuracy of body position monitoring.

[0066] like Figure 3-Figure 8 As shown, an ear post 2 is fixedly provided on the side of the ear-hook housing 1, and a colloid ear plug 3 is provided on the outer wall of the end of the ear post 2, an adapter ring 4 is fixedly sleeved on the outer wall of the ear post 2, and the outer side of the adapter ring 4 fits the inner side of the colloid ear plug 3, an arc-shaped transition groove 5 is provided on the outer side of the adapter ring 4, and micro balls 6 are embedded on the surface of the outer side of the adapter ring 4 and the surface of the arc-shaped transition groove 5, an elastic sheet 7 is provided between the arc-shaped transition groove 5 and the inner side of the colloid ear plug 3, and a disc 8 is fixed on the end of the elastic sheet 7, the disc 8 is rotatably connected to the ear-hook housing 1, and the ear post 2 passes through the middle of the disc 8, a transmission gear 9 is fixed on the side of the disc 8 away from the elastic sheet 7, and a driving gear 10 is meshedly connected to one side of the transmission gear 9, a micro motor 11 is connected to the side of the driving gear 10, and the micro motor 11 is fixedly connected to the ear-hook housing 1;

[0067] The specific operation is as follows: when the ear-hook housing 1 is hung on the ear, the device is worn, and the colloid earplug 3 is located in the ear canal. At this time, the two circular holes on the inner side of the ear-hook housing 1 are respectively used for the infrared sensor detection module and the temperature detection module to be close to the surrounding area of ​​the ear for detection operation;

[0068] When the device is taken off after each use, the infrared sensor detection module and the temperature detection module detect that the device is away from the ear and determine that the device is taken off. At this time, the micro motor 11 drives the driving gear 10 to rotate to drive the transmission gear 9 to make the disk 8 carry the elastic sheet 7 to rotate, and the elastic sheet 7 moves along the outer side surface of the adapter ring 4 and the surface of the arc-shaped transition groove 5. The wavy structure of the outer side surface of the adapter ring 4 and the surface of the arc-shaped transition groove 5 makes the elastic sheet 7 constantly shake during the rotation process to exert a shaking effect on the colloid earplug 3. The colloid earplug 3 is affected by the shaking to shake off impurities in the ear canal attached to its surface, so as to prevent impurities from being attached to the surface of the colloid earplug 3 after the colloid earplug 3 is removed, and at the same time, it is prevented that the patient does not check whether there are impurities on the surface of the colloid earplug 3 after taking it off, resulting in long-term attachment of impurities;

[0069] When the elastic sheet 7 moves along the outer side surface of the adapter ring 4 and the surface of the arc-shaped transition groove 5, the sliding friction is converted into rolling friction through the in-situ rolling action of the micro balls 6 to avoid wear of the elastic sheet 7 or the adapter ring 4. The smooth surfaces of the elastic sheet 7 and the colloid earplug 3 can also reduce friction.

[0070] In summary, when the intelligent device for postoperative body position monitoring of ophthalmology is used, it first detects whether the patient is wearing the device effectively through the infrared sensor detection module and the temperature detection module, wherein the infrared sensor detection module includes an infrared transmitter and a receiver, and both the transmitter and the receiver are installed close to the patient's ear. When the patient wears it, the transmitter emits infrared light that is reflected to the receiver through the patient's ear. The infrared sensor detection module is turned on to determine whether it is in the wearing state. In order to avoid the infrared sensor detection module being blocked by foreign objects and causing misjudgment, a temperature detection module, i.e., a temperature sensor, is added to perform multi-sensor fusion judgment. The temperature sensor is installed close to the patient's ear. When the infrared sensor detection module is turned on and the temperature is detected to be between 32°C and 38°C, it is determined that the patient is in the effective wearing state.

[0071] The three-axis acceleration sensor module is worn on the patient's ear through an ear-hook housing 1, and the Z-axis direction is always kept consistent with the vertical direction of the patient's ear, and the Y-axis direction is consistent with the patient's face direction. When the patient's face is perpendicular to the ground plane, the Z-axis acceleration value is the largest, and when the patient's face is horizontal to the ground plane, the Y-axis acceleration value is the largest. When the sensor data is detected to have a periodic jump with the same frequency as the step frequency of 60-120 times / minute, it is judged that the patient is in a moving state, so the patient's facial angle and movement information are obtained by reading the acceleration value in the spatial XYZ direction. When it is detected that the patient's facial angle information exceeds 20% in the horizontal direction, the voice module issues a voice reminder to remind the patient to correct the facial posture;

[0072] The core processing module analyzes the collected data when predicting the patient's condition, including the wearing period, wearing time, wearing angle, gender, age and other information, and combines the rehabilitation cases of previous patients to guide the current patient to have a better rehabilitation. The specific method is described as using linear regression to analyze a large amount of data based on the rehabilitation cases of previous patients using machine learning algorithms to obtain relevant weight values, derive a prediction data model, and input the formula into the ESP32 main controller. The main controller uses the rehabilitation model to predict based on the collected data to obtain the maximum expected value, and guides the patient through voice.

[0073] When the ear-hook housing 1 is hung on the ear, the device is worn. At this time, the colloid earplug 3 is located in the ear canal, and at this time, the two circular holes on the inner side of the ear-hook housing 1 are respectively used for the infrared sensor detection module and the temperature detection module to perform detection operations close to the surrounding area of ​​the ear;

[0074] Each time the device is taken off after use, the infrared sensor detection module and the temperature detection module detect that the device is away from the ear and determine that the device is taken off. At this time, the micro motor 11 drives the driving gear 10 to rotate to drive the transmission gear 9 to make the disk 8 carry the elastic sheet 7 to rotate, and the elastic sheet 7 moves along the outer side surface of the adapter ring 4 and the surface of the arc-shaped transition groove 5. The wavy structure of the outer side surface of the adapter ring 4 and the surface of the arc-shaped transition groove 5 makes the elastic sheet 7 continuously shake during the rotation process to exert a shaking effect on the colloid earplug 3. The colloid earplug 3 is affected by the shaking to shake off impurities in the ear canal attached to its surface, so as to prevent impurities from being attached to the surface of the colloid earplug 3 after the colloid earplug 3 is taken off.

[0075] The embodiments of the present invention are given for the purpose of illustration and description, and are not intended to be exhaustive or to limit the invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

Claims

1. An intelligent device for postoperative body position monitoring in ophthalmology, comprising an ear-hook housing (1), characterized in that: The ear-hook housing (1) is provided with a human body wearing detection module, a three-axis acceleration sensor module, a voice reminder module and a data storage module. The human body wearing detection module includes an infrared sensor detection module and a temperature detection module. The infrared sensor detection module specifically includes: Transmitter: Select an infrared LED as the transmitter, which emits infrared light of a specified wavelength; Receiver: Use an infrared light sensor such as a photodiode or phototransistor as a receiver, which senses infrared light and converts it into an electrical signal; Transmitting signal: ESP32 outputs 1kHz square wave through GPIO pin to drive infrared LED to emit infrared light; Received signal: When infrared light hits the human body or other objects and is reflected back to the receiver, the receiver performs cross-correlation analysis on the received signal and the 1kHz drive signal. The reflected infrared signal is extracted using the cross-correlation function, the same frequency is correlated, and the different frequencies are uncorrelated. The interference of the environment is filtered out to avoid interference caused by other infrared light such as sunlight. The algorithm formula is as follows: Signal processing: h(t) and g(t) are the emission light function and the receiving light function respectively. From the above formula, we can know that the cross-correlation function is equivalent to the convolution operation of two functions in the time domain, which is equivalent to the multiplication of two signals in the frequency domain. First, the emission function and the infrared receiving function are discrete Fourier transformed, and then multiplied, that is, the collected signal and the emission signal are cross-correlated to filter out the signal components with different emission frequencies; The temperature detection module specifically includes: Temperature sensor: Use a constant current source to drive the NTC thermistor. As the temperature changes, the NTC resistance changes, causing the voltage across the NTC to change. The ADC collects different voltage values ​​to calculate the sensed temperature. The collected data is subjected to a digital filtering algorithm to perform sliding average on the collected data to filter out the noise and random components in the signal, as shown in the following formula: y n =(x n +x n+1 +x n+2 +…+x n+m-2 +x n+m-1 ) / m Where m is the number of sliding average points, and 20 sampling points are selected in sequence for averaging to filter out interference components.

2. The intelligent device for postoperative body position monitoring in ophthalmology according to claim 1, characterized in that: The three-axis acceleration sensor module is worn on the patient's ear through an ear-hook housing (1). The three-axis acceleration sensor module reads acceleration values ​​in the spatial XYZ directions to obtain the patient's facial angle and motion information. When it is detected that the patient's facial angle information exceeds 20% in the horizontal direction, the voice module issues a voice reminder to remind the patient to correct his facial posture.

3. The intelligent device for postoperative body position monitoring in ophthalmology according to claim 1, characterized in that: The data storage module is used to store data during the patient's wearing process, including but not limited to wearing time, wearing angle, and movement status.

4. The intelligent device for postoperative body position monitoring in ophthalmology according to claim 1, characterized in that: The ear-hook housing (1) is also provided with a core processing module, and the core processing module is connected to the human body wearing detection module, the three-axis acceleration sensor module, the voice reminder module and the data storage module. The core processing module is used to communicate with the peripheral modules for data recording and comprehensive analysis.

5. The intelligent device for postoperative body position monitoring in ophthalmology according to claim 4, characterized in that: The core processing module controls the peripheral modules and reads data, detects the patient's wearing status and movement status, filters the collected data, predicts the patient's condition based on information such as wearing time and single wearing period and compares it with the medical rehabilitation model, and guides the patient through voice to pay attention to the things he needs to pay attention to at the current stage.

6. The intelligent device for postoperative body position monitoring in ophthalmology according to claim 5, characterized in that: The core processing module performs the following operations when predicting the patient's condition: Analyze the collected data, including wearing period, wearing time, wearing angle, gender, age and other information, and combine the rehabilitation cases of previous patients to guide the current patients to have better rehabilitation. The specific method is described as using linear regression to analyze a large amount of data based on the rehabilitation cases of previous patients using machine learning algorithms to obtain relevant weight values, and derive a prediction data model. The formula is input into the ESP32 main controller, and the main controller uses the rehabilitation model to predict based on the collected data to obtain the maximum expected value, and guides the patient through voice. The large model formula is expressed as: y = w1x1 + w2x2 + ... + w n x n Among them, "y" is the target value of the prediction model. The closer the value of y is to 1, the faster the patient's recovery time will be. x is the characteristic value, that is, the relevant influencing factors, including wearing period, duration, angle and other information; w is the weight of the relevant influencing factors, that is, the proportion of such information as wearing period, wearing duration and wearing angle in the patient's recovery process.

7. The intelligent device for postoperative body position monitoring in ophthalmology according to claim 1, characterized in that: An ear post (2) is fixedly mounted on the side of the ear-hook housing (1), and a colloid ear plug (3) is arranged on the outer wall of the end of the ear post (2).

8. The intelligent device for postoperative body position monitoring in ophthalmology according to claim 7, characterized in that: An adapter ring (4) is sleeved and fixed on the outer wall of the ear post (2), and the outer side surface of the adapter ring (4) fits the inner side surface of the colloid ear plug (3). An arc-shaped transition groove (5) is formed on the outer side surface of the adapter ring (4), and micro balls (6) are embedded in the surfaces of the outer side surface of the adapter ring (4) and the arc-shaped transition groove (5).

9. The intelligent device for postoperative body position monitoring in ophthalmology according to claim 8, characterized in that: An elastic sheet (7) is provided between the arc-shaped transition groove (5) and the inner side surface of the colloid earplug (3), and a disc (8) is fixed to the end of the elastic sheet (7). The disc (8) is rotatably connected to the ear-hook housing (1), and the ear post (2) passes through the middle of the disc (8).

10. The intelligent device for postoperative body position monitoring in ophthalmology according to claim 9, characterized in that: A transmission gear (9) is fixed to the side of the disk (8) away from the elastic sheet (7), and one side of the transmission gear (9) is meshingly connected to a driving gear (10), a side of the driving gear (10) is connected to a micro motor (11), and the micro motor (11) is fixedly connected to the ear-hook housing (1).

Images