Eye pressure monitoring self-adaptive adjusting system based on edge calculation

Abstract

The invention discloses an eye pressure monitoring self-adaptive adjusting system based on edge calculation. The system comprises an acquisition device module, a signal acquisition module, a signal preprocessing module, a signal transmission module, a host calculation module, a dynamic monitoring control module and a pressure regulation and control module, according to the eye pressure monitoring self-adaptive adjusting system based on edge calculation, the air pressure and the water pressure at the tail end of the pipeline are monitored in real time through the pressure sensor arranged at the position 10 cm away from the eyeball, the pressure sensor is provided with the microprocessor, and the feature compression algorithm is used for achieving self-adaptive adjustment of the eye pressure at the tail end of the pipeline. Data can be directly compressed at the far end, a self-adaptive regulation and control algorithm is provided, the parameter control coefficient of the pressure regulation and control device is optimized, and the eyeball end pressure is controlled in real time.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical care, and in particular to an eye pressure monitoring and adaptive adjustment system based on edge computing. Background Art

[0002] With the rapid development of information technology, especially the rapid progress of the Internet of Things (IoT), edge computing and big data technology, smart medical devices are being used more and more widely in various fields. Especially in the field of eye health, the monitoring and regulation of intraocular pressure is crucial to the prevention of eye diseases such as glaucoma. Glaucoma is a disease that causes damage to the optic nerve due to excessive intraocular pressure. If not treated in time, it may cause irreversible eye damage and seriously affect the patient's quality of life.

[0003] At present, many researchers and medical device manufacturers have begun to explore new technologies for monitoring eye pressure. Traditional intraocular pressure measurement usually relies on manual testing in hospitals, using equipment such as applanation tonometers and non-contact tonometers, which usually require professional medical staff to operate, and the accuracy and real-time performance of the measurement results are poor. In recent years, the emergence of portable medical devices has provided new ideas for intraocular pressure monitoring. These devices combine sensor technology with wireless communication technology to improve the accuracy and portability of monitoring. For example, some smartphone-based applications can be used with Bluetooth-connected sensors to help monitor eye pressure in real time. However, these portable devices still have problems with data processing and feedback delays, and cannot achieve real-time adaptive adjustment. And the existing eye pressure monitoring system still has some shortcomings. Many devices have not yet reached the ideal level in terms of data accuracy, real-time performance, and adaptive adjustment capabilities. Although some systems can record changes in patients' intraocular pressure, they lack intelligent analysis and feedback mechanisms and cannot automatically adjust intraocular pressure, which may cause delays in practical applications and threaten patients' health.

[0004] As edge computing continues to develop and mature, it provides new solutions for the application of medical monitoring equipment. Edge computing refers to data processing and analysis near the source of data generation, which reduces the time and bandwidth required for data transmission and helps improve real-time performance and reliability. In eye pressure monitoring, edge computing can quickly analyze the data collected by sensors, thereby achieving real-time monitoring and automatic adjustment of intraocular pressure. By introducing edge computing in devices used for eye pressure monitoring, rapid data processing and response can be achieved, which can effectively improve the performance and user experience of the eye monitoring system.

[0005] In this context, an innovative eye pressure monitoring and adaptive adjustment system is needed, which can not only monitor eye pressure in real time, but also automatically adjust the monitoring and adjustment parameters through adaptive adjustment algorithms according to the needs and eye conditions of different patients, so as to achieve precise control of eye pressure.

[0006] In summary, with the continuous advancement of science and technology, especially the widespread application of technologies such as sensors, wireless communications and edge computing, the construction of a real-time monitoring and adaptive adjustment system for eye pressure has become an inevitable trend. The development of this system can not only improve the quality of life and safety of patients, but also has great social value in medical and health management. It meets the actual needs of current medical technology development and provides new ideas and directions for future eye health management. Summary of the invention

[0007] The purpose of the present invention is to provide an eye pressure monitoring and adaptive adjustment system based on edge computing, aiming to solve the problems mentioned in the above background.

[0008] In order to achieve the above-mentioned purpose, the present invention proposes an eye pressure monitoring and adaptive adjustment system based on edge computing, which is characterized in that it includes an acquisition device module, a signal acquisition module, a signal preprocessing module, a signal transmission module, a host computing module, a dynamic monitoring and control module, and a pressure control module; the acquisition device module sets a pressure sensor at the eyeball position; the signal acquisition module monitors and collects water pressure and air pressure through the pressure sensor at the eyeball position; the signal preprocessing module proposes a feature compression algorithm to compress the collected signal data; in the signal transmission module, a signal data transmission channel is established in a wired manner to transmit the signal data; in the host computing module, data analysis and calculation processing are performed through a computing processor; in the dynamic monitoring and control module, an adaptive control algorithm is proposed to construct a multi-level adjustment optimization network to optimize the parameter control coefficient of the pressure control device; in the pressure control module, according to the pressure control instruction, the pressure control device actively controls the pressure of the perfusion bottle.

[0009] Furthermore, the pressure sensor is a device with a microprocessor capable of monitoring pressure. The pressure sensor is set at a position 10 cm away from the eyeball, and the microprocessor can compress the data collected by monitoring.

[0010] Furthermore, the signal acquisition module monitors the air pressure and water pressure at the end of the pipeline in real time through the pressure sensor, and collects the air pressure and water pressure at the end of the monitored pipeline.

[0011] Furthermore, the feature compression algorithm dynamically decomposes the collected signal data, smoothes the obtained dynamic components, constructs a filter function for filtering, and obtains a dynamic component compression feature vector.

[0012] Furthermore, a filtering function is constructed to filter and obtain the dynamic component compression feature vector. The detailed process is as follows:

[0013] The air pressure and water pressure at the end of the pipeline collected by the pressure sensor are discrete time series signals. The discrete time series signals collected over a period of time are combined into a pressure signal data set, which is defined as , which is expressed as follows:

[0014]

[0015] in, They represent the first period of pressure signal in the pressure signal data set, the second period of pressure signal in the pressure signal data set, and the first period of pressure signal in the pressure signal data set. The pressure signal of the time period, the first The time period pressure signal, the pressure signal data is first dynamically decomposed, the decomposition formula is as follows:

[0016]

[0017] in, Respectively represent Dynamic component of pressure signal during the period, The dynamic component of the time period pressure signal, Expressed as Dynamic decomposition coefficient of time period pressure signal, Expressed as Dynamic decomposition coefficient of time period pressure signal, Represented as the first Then, the dynamic component of the pressure signal is smoothed, and the calculation formula is as follows:

[0018]

[0019] in, Indicates The dynamic component of the pressure signal of the time period elements, After smoothing, The dynamic component of the pressure signal of the time period elements, Indicates The number of dynamic components of the pressure signal in the time period is used to construct a filtering function to filter the dynamic components after smoothing. The filtering operation is expressed as follows:

[0020]

[0021] in, Represents the first The dynamic component of the pressure signal of the time period elements, represents the first filter coefficient, Represents the second filter coefficient. Analyze the dynamic component characteristics after filtering. First, sort the elements in the vector and then select the first elements, construct the feature compression vector, the formula is as follows:

[0022]

[0023] in, The dimension is The dynamic component compressed eigenvector of Respectively represent the dimensions The first element of the dynamic component compression feature vector has a dimension of The second element of the dynamic component compression feature vector has a dimension of The dynamic component compression eigenvector elements, Represents the first The dynamic component of the pressure signal during the period is compressed into a characteristic vector for transmission. The characteristic compression algorithm proposed by the present invention first dynamically decomposes the collected signal data to obtain the dynamic component of the pressure signal, then smoothes the dynamic component to reduce the fluctuation of the signal data, constructs a filter function to filter the dynamic component, analyzes the characteristics of the dynamic component after filtering, and obtains the compressed characteristic vector of the dynamic component; the characteristic compression algorithm proposed by the present invention is operated at the remote end of the pressure sensor, and only transmits the compressed characteristic vector of the dynamic component of the signal data, thereby reducing the amount of signal data transmission and improving the transmission efficiency of the signal data.

[0024] Furthermore, the signal transmission module establishes a signal data transmission channel between the pressure sensor, the computing processor, and the pressure control device through a wired connection. The pressure sensor transmits the signal data to the computing processor, and the computing processor outputs a pressure control instruction to the pressure control device.

[0025] Furthermore, the host computing module performs data storage, data analysis, algorithm calculation, and output of pressure control instructions through a computing processor.

[0026] Furthermore, an adaptive control algorithm is used to construct a multi-level control optimization network. Through parameter adjustment relationship functions, the input and output between layers in the multi-level control optimization network are utilized to optimize the parameter control coefficient of the pressure control device and adaptively adjust the pressure of the perfusion bottle.

[0027] Furthermore, the parameter control coefficient of the pressure control device is optimized, and the detailed process is as follows:

[0028] Based on the compressed eigenvector of the dynamic component of the pressure obtained by processing, the pressure is adaptively adjusted. First, a multi-level adjustment optimization network is constructed, including an input layer, an intermediate layer, and an output layer. Through the multi-level adjustment optimization network, the parameters of the perfusion bottle pressure control device are adjusted, and the parameter adjustment relationship function is constructed. The objective function is expressed as follows:

[0029]

[0030] in, represents the dynamic component eigenvector elements, The dynamic component eigenvector elements, express The working parameters of the pressure control device at all times, express The working parameters of the pressure control device at all times, express The parameter control coefficient at time, express The parameter control coefficient at the moment is used to smoothly adjust the pressure of the perfusion bottle based on the parameter adjustment relationship function. Through the multi-level adjustment optimization network, the dynamic component compression feature vector is input to the input layer of the multi-level adjustment optimization network. After the activation function, the input of the middle layer is obtained, which is expressed as follows:

[0031]

[0032] in, represents the dynamic component eigenvector elements, Indicates The input of the middle layer neurons is input to the output layer. The output layer performs the output of the output layer through the full connection operation. The output layer is represented as follows:

[0033]

[0034] in, Represents the output layer The optimization weights of neurons are obtained through the outputs of all neurons in the output layer, and the parameter control coefficients of the pressure control device are obtained, and the parameter control coefficients of the pressure control device are output as pressure control instructions. The adaptive control algorithm proposed in the present invention constructs a multi-level adjustment optimization network of input layer, middle layer and output layer, and inputs the dynamic component compression feature vector to the input layer of the multi-level adjustment optimization network through the parameter adjustment relationship function, and obtains the input of the middle layer through the activation function. The full connection operation of the output layer is used to optimize the parameter control coefficients of the pressure control device, and the pressure of the perfusion bottle is adaptively adjusted. The adaptive control algorithm proposed in the present invention realizes the gradual adaptive adjustment of the pressure of the perfusion bottle by the pressure control device based on the dynamic changes of the dynamic component compression feature vector at each moment, thereby improving the comfort of the patient's eyeball.

[0035] Furthermore, in the pressure control module, the computing processor outputs a pressure control instruction, and the pressure control device receives the pressure control instruction and actively controls the infusion bottle to complete the adaptive pressure adjustment operation.

[0036] Beneficial Effects

[0037] 1. The feature compression algorithm proposed in the present invention first dynamically decomposes the collected signal data to obtain the dynamic component of the pressure signal, then smoothes the dynamic component to reduce the fluctuation of the signal data, constructs a filter function to filter the dynamic component, and analyzes the characteristics of the dynamic component after filtering to obtain the dynamic component compression feature vector; the feature compression algorithm proposed in the present invention is operated at the remote end of the pressure sensor, and only transmits the dynamic component compression feature vector of the signal data, thereby reducing the amount of signal data transmission and improving the transmission efficiency of the signal data. In addition, the pressure monitored by the present invention is the pressure at the end of the pipeline, which is not affected by the length of the pipeline and the data is more accurate.

[0038] 2. The adaptive control algorithm proposed in the present invention constructs a multi-level adjustment optimization network of input layer, middle layer and output layer. Through the parameter adjustment relationship function, the dynamic component compression feature vector is input to the input layer of the multi-level adjustment optimization network. After the activation function, the input of the middle layer is obtained. The full connection operation of the output layer is used to optimize the parameter control coefficient of the pressure control device and adaptively adjust the pressure of the perfusion bottle. The adaptive control algorithm proposed in the present invention realizes the gradual adaptive adjustment of the pressure of the perfusion bottle by the pressure control device based on the dynamic changes of the dynamic component compression feature vector at each moment, thereby improving the patient's eye comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings in the following description are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 is a system schematic diagram of the present invention; DETAILED DESCRIPTION

[0041] 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 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 creative work are within the scope of protection of the present invention.

[0042] In order to achieve the above-mentioned purpose, the present invention proposes an eye pressure monitoring and adaptive adjustment system based on edge computing, which is characterized in that it includes an acquisition device module, a signal acquisition module, a signal preprocessing module, a signal transmission module, a host computing module, a dynamic monitoring and control module, and a pressure control module; the acquisition device module sets a pressure sensor at the eyeball position; the signal acquisition module monitors and collects water pressure and air pressure through the pressure sensor at the eyeball position; the signal preprocessing module proposes a feature compression algorithm to compress the collected signal data; in the signal transmission module, a signal data transmission channel is established in a wired manner to transmit the signal data; in the host computing module, data analysis and calculation processing are performed through a computing processor; in the dynamic monitoring and control module, an adaptive control algorithm is proposed to construct a multi-level adjustment optimization network to optimize the parameter control coefficient of the pressure control device; in the pressure control module, according to the pressure control instruction, the pressure control device actively controls the pressure of the perfusion bottle.

[0043] Specifically, the pressure sensor is a device with a microprocessor capable of monitoring pressure. The pressure sensor is arranged at a position 10 cm away from the eyeball, and the microprocessor can compress the data collected by monitoring.

[0044] Specifically, the signal acquisition module monitors the air pressure and water pressure at the end of the pipeline in real time through a pressure sensor, and collects the air pressure and water pressure at the end of the monitored pipeline.

[0045] Specifically, the feature compression algorithm dynamically decomposes the collected signal data, smoothes the obtained dynamic components, constructs a filter function for filtering, obtains a dynamic component compression feature vector, and constructs a filter function for filtering to obtain a dynamic component compression feature vector. The detailed process is as follows:

[0046] The air pressure and water pressure at the end of the pipeline collected by the pressure sensor are discrete time series signals. The discrete time series signals collected over a period of time are combined into a pressure signal data set, which is defined as , which is expressed as follows:

[0047]

[0048] in, They represent the first period of pressure signal in the pressure signal data set, the second period of pressure signal in the pressure signal data set, and the first period of pressure signal in the pressure signal data set. The pressure signal of the time period, the first The time period pressure signal, the pressure signal data is first dynamically decomposed, the decomposition formula is as follows:

[0049]

[0050] in, Respectively represent Dynamic component of pressure signal during the period, The dynamic component of the time period pressure signal, Expressed as Dynamic decomposition coefficient of time period pressure signal, Expressed as Dynamic decomposition coefficient of time period pressure signal, Represented as the first Then, the dynamic component of the pressure signal is smoothed, and the calculation formula is as follows:

[0051]

[0052] in, Indicates The dynamic component of the pressure signal of the time period elements, After smoothing, The dynamic component of the pressure signal of the time period elements, Indicates The number of dynamic components of the pressure signal in the time period is used to construct a filtering function to filter the dynamic components after smoothing. The filtering operation is expressed as follows:

[0053]

[0054] in, Represents the first The dynamic component of the pressure signal of the time period elements, represents the first filter coefficient, Represents the second filter coefficient. Analyze the dynamic component characteristics after filtering. First, sort the elements in the vector and then select the first elements, construct the feature compression vector, the formula is as follows:

[0055]

[0056] in, The dimension is The dynamic component compressed eigenvector of Respectively represent the dimensions The first element of the dynamic component compression feature vector has a dimension of The second element of the dynamic component compression feature vector has a dimension of The dynamic component compression eigenvector elements, Represents the first The dynamic component of the time period pressure signal is compressed into a feature vector for transmission.

[0057] Specifically, the signal transmission module establishes a signal data transmission channel between the pressure sensor, the computing processor, and the pressure control device through a wired connection. The pressure sensor transmits the signal data to the computing processor, and the computing processor outputs a pressure control instruction to the pressure control device.

[0058] Specifically, the host computing module performs data storage, data analysis, algorithm calculations, and output of pressure control instructions through a computing processor.

[0059] Specifically, the adaptive control algorithm constructs a multi-level adjustment optimization network, adjusts the relationship function through parameters, uses the input and output between layers in the multi-level adjustment optimization network, optimizes the parameter control coefficient of the pressure control device, and adaptively adjusts the pressure of the perfusion bottle. The detailed process is as follows:

[0060] Based on the compressed eigenvector of the dynamic component of the pressure obtained by processing, the pressure is adaptively adjusted. First, a multi-level adjustment optimization network is constructed, including an input layer, an intermediate layer, and an output layer. Through the multi-level adjustment optimization network, the parameters of the perfusion bottle pressure control device are adjusted, and the parameter adjustment relationship function is constructed. The objective function is expressed as follows:

[0061]

[0062] in, represents the dynamic component eigenvector elements, represents the dynamic component eigenvector elements, express The working parameters of the pressure control device at all times, express The working parameters of the pressure control device at all times, express The parameter control coefficient at time, express The parameter control coefficient at the moment is used to smoothly adjust the pressure of the perfusion bottle based on the parameter adjustment relationship function. Through the multi-level adjustment optimization network, the dynamic component compression feature vector is input to the input layer of the multi-level adjustment optimization network. After the activation function, the input of the middle layer is obtained, which is expressed as follows:

[0063]

[0064] in, represents the dynamic component eigenvector elements, Indicates The input of the middle layer neurons is input to the output layer. The output layer performs the output of the output layer through the full connection operation. The output layer is represented as follows:

[0065]

[0066] in, Represents the output layer The optimized weights of the neurons are obtained through the outputs of all the neurons in the output layer to obtain the parameter control coefficients of the pressure control device, and the parameter control coefficients of the pressure control device are output as pressure control instructions.

[0067] Specifically, in the pressure control module, the computing processor outputs a pressure control instruction, and the pressure control device receives the pressure control instruction, actively controls the perfusion bottle, and completes the pressure adaptive adjustment operation.

[0068] In a specific embodiment, first, the user monitors and collects the air pressure and water pressure at the end of the pipeline in real time through a pressure sensor set ten centimeters away from the eyeball. Then, a signal data transmission channel is constructed between the pressure sensor, the computing processor, and the pressure control device through a wired connection to realize data transmission among the three. Then, the user uses a feature compression algorithm to process the pressure signal data at the far end of the pressure sensor to obtain a dynamic component compression feature vector, and transmits the dynamic component compression feature vector to the computing processor through the signal data transmission channel. After that, the user uses an adaptive control algorithm to optimize the parameter control coefficient of the pressure control device. Finally, the computing processor outputs the parameter control coefficient of the pressure control device as a control instruction to the pressure control device. The pressure control device receives the pressure control instruction, actively controls the infusion bottle, and completes the adaptive pressure adjustment operation.

[0069] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0070] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0071] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. An eye pressure monitoring and adaptive adjustment system based on edge computing, characterized in that: It includes a collection device module, a signal collection module, a signal preprocessing module, a signal transmission module, a host computing module, a dynamic monitoring control module, and a pressure control module; the collection device module sets a pressure sensor at the eyeball position; the signal collection module monitors and collects water pressure and air pressure through the pressure sensor at the eyeball position; The signal preprocessing module proposes a feature compression algorithm to compress the collected signal data; in the signal transmission module, a signal data transmission channel is established through a wired method to transmit signal data; in the host computing module, data analysis and calculation processing are performed through a computing processor; in the dynamic monitoring and control module, an adaptive control algorithm is proposed to build a multi-level adjustment optimization network to optimize the parameter control coefficient of the pressure control device; In the pressure control module, the pressure control device actively controls the pressure of the perfusion bottle according to the pressure control instruction.

2. The eye pressure monitoring and adaptive adjustment system based on edge computing according to claim 1 is characterized in that: The pressure sensor is a device with a microprocessor capable of monitoring pressure. The pressure sensor is arranged at a position 10 cm away from the eyeball. The microprocessor can compress the data collected by monitoring.

3. The eye pressure monitoring and adaptive adjustment system based on edge computing according to claim 1 is characterized in that: The signal acquisition module monitors the air pressure and water pressure at the end of the pipeline in real time through the pressure sensor, and collects the air pressure and water pressure at the end of the monitored pipeline.

4. The eye pressure monitoring and adaptive adjustment system based on edge computing according to claim 1, characterized in that: The feature compression algorithm dynamically decomposes the collected signal data, performs smoothing on the obtained dynamic components, constructs a filter function for filtering, and obtains a dynamic component compression feature vector.

5. The eye pressure monitoring and adaptive adjustment system based on edge computing according to claim 4 is characterized in that: The filter function is constructed to filter and obtain the dynamic component compression feature vector. The detailed process is as follows: The air pressure and water pressure at the end of the pipeline collected by the pressure sensor are discrete time series signals. The discrete time series signals collected over a period of time are combined into a pressure signal data set, which is defined as , which is expressed as follows: in, They represent the first period of pressure signal in the pressure signal data set, the second period of pressure signal in the pressure signal data set, and the first period of pressure signal in the pressure signal data set. The pressure signal of the time period, the first The time period pressure signal, the pressure signal data is first dynamically decomposed, the decomposition formula is as follows: in, Respectively represent Dynamic component of pressure signal during the period, The dynamic component of the time period pressure signal, Expressed as Dynamic decomposition coefficient of time period pressure signal, Expressed as Dynamic decomposition coefficient of time period pressure signal, Represented as the first Time period pressure signal, Represents the current total period. Next, the dynamic component of the pressure signal is smoothed. The calculation formula is as follows: in, Indicates The dynamic component of the pressure signal of the time period elements, After smoothing, The dynamic component of the pressure signal of the time period elements, Indicates The number of dynamic components of the pressure signal in the time period is used to construct a filtering function to filter the dynamic components after smoothing. The filtering operation is expressed as follows: in, Represents the first The dynamic component of the pressure signal of the time period elements, represents the first filter coefficient, Represents the second filter coefficient. Analyze the dynamic component characteristics after filtering. First, sort the elements in the vector and then select the first elements, construct the feature compression vector, the formula is as follows: in, The dimension is The dynamic component compression eigenvector of Respectively represent the dimensions The first element of the dynamic component compression feature vector has a dimension of The second element of the dynamic component compression feature vector has a dimension of The dynamic component compression eigenvector elements, Represents the first The dynamic component of the time period pressure signal is compressed into a feature vector for transmission.

6. The eye pressure monitoring and adaptive adjustment system based on edge computing according to claim 1, characterized in that: The signal transmission module establishes a signal data transmission channel between the pressure sensor, the computing processor, and the pressure control device by means of a wired connection. The pressure sensor transmits the signal data to the computing processor, and the computing processor outputs a pressure control instruction to the pressure control device.

7. The eye pressure monitoring and adaptive adjustment system based on edge computing according to claim 1, characterized in that: The host computing module performs data storage, data analysis, algorithm calculation, and output of pressure control instructions through a computing processor.

8. The eye pressure monitoring and adaptive adjustment system based on edge computing according to claim 1, characterized in that: The adaptive control algorithm constructs a multi-level adjustment optimization network, adjusts the parameter relationship function, utilizes the input and output between layers in the multi-level adjustment optimization network, optimizes the parameter control coefficient of the pressure control device, and adaptively adjusts the perfusion bottle pressure.

9. The eye pressure monitoring and adaptive adjustment system based on edge computing according to claim 8, characterized in that: The detailed process of optimizing the parameter control coefficient of the pressure regulating device is as follows: Based on the compressed eigenvector of the dynamic component of the pressure obtained by processing, the pressure is adaptively adjusted. First, a multi-level adjustment optimization network is constructed, including an input layer, an intermediate layer, and an output layer. Through the multi-level adjustment optimization network, the parameters of the perfusion bottle pressure control device are adjusted, and the parameter adjustment relationship function is constructed. The objective function is expressed as follows: in, represents the dynamic component eigenvector elements, represents the dynamic component eigenvector elements, express The working parameters of the pressure control device at all times, express The working parameters of the pressure control device at all times, express The parameter control coefficient at time, express The parameter control coefficient at the moment is used to smoothly adjust the pressure of the perfusion bottle based on the parameter adjustment relationship function. Through the multi-level adjustment optimization network, the dynamic component compression feature vector is input to the input layer of the multi-level adjustment optimization network. After the activation function, the input of the middle layer is obtained, which is expressed as follows: in, represents the dynamic component eigenvector elements, Indicates The input of the middle layer neurons is input to the output layer. The output layer performs the output of the output layer through the full connection operation. The output layer is represented as follows: in, Represents the output layer The optimized weights of the neurons are obtained through the outputs of all the neurons in the output layer to obtain the parameter control coefficients of the pressure control device, and the parameter control coefficients of the pressure control device are output as pressure control instructions.

10. The eye pressure monitoring and adaptive adjustment system based on edge computing according to claim 1, characterized in that: The pressure control module and the computing processor output pressure control instructions. The pressure control device receives the pressure control instructions and actively controls the perfusion bottle to complete the pressure adaptive adjustment operation.

Images