Intraocular pressure monitoring method, intraocular pressure monitoring device, apparatus, and storage medium

Abstract

The embodiment of the application provides an intraocular pressure monitoring method, an intraocular pressure monitoring device, equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring an initial frequency signal and an initial amplitude signal of a target human eye; performing null value screening processing on the initial frequency signal and the initial amplitude signal respectively to obtain a preliminary frequency signal and a preliminary amplitude signal, filtering processing on the preliminary frequency signal to obtain a secondary frequency signal, and filtering processing on the preliminary amplitude signal to obtain a secondary amplitude signal; performing segmented filtering processing on the secondary frequency signal to obtain a target frequency signal, and performing segmented filtering processing on the secondary amplitude signal to obtain a target amplitude signal; performing feature extraction on the target frequency signal and the target amplitude signal respectively to obtain a frequency feature and an amplitude feature; and performing intraocular pressure analysis on the frequency feature and the amplitude feature by using a preset intraocular pressure monitoring model to obtain a target intraocular pressure value. The embodiment of the application can improve the accuracy of intraocular pressure monitoring of the human eye.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to an intraocular pressure monitoring method, an intraocular pressure monitoring device, equipment and a storage medium. BACKGROUND

[0002] At present, the intraocular pressure monitoring method using contact lenses with embedded inductive coils mainly uses pig eyes or rubber balls for simulation monitoring. The dielectric on the surface of the pig eyes or rubber balls is stable and there is no signal interference caused by blinking. However, the surface environment of the human eye is more complex than the dielectric on the surface of the pig eyes or rubber balls, and there is interference caused by blinking. Therefore, the method of monitoring the intraocular pressure by using pig eyes or rubber balls is not suitable for continuous intraocular pressure monitoring of the human eye. SUMMARY

[0003] The main purpose of the embodiments of the present application is to provide an intraocular pressure monitoring method, an intraocular pressure monitoring device, equipment and a storage medium, which are used for collecting the frequency signal and the amplitude signal of the human eye for intraocular pressure analysis, so as to be suitable for intraocular pressure monitoring of the human eye and improve the accuracy of intraocular pressure monitoring of the human eye.

[0004] To achieve the above-mentioned purpose, the first aspect of the embodiments of the present application provides an intraocular pressure monitoring method, which comprises:

[0005] obtaining a monitoring signal of a target human eye; wherein the monitoring signal comprises an initial frequency signal and an initial amplitude signal;

[0006] performing null value screening processing on the initial frequency signal to obtain a preliminary frequency signal, and performing null value screening processing on the initial amplitude signal to obtain a preliminary amplitude signal;

[0007] performing filtering processing on the preliminary frequency signal to obtain a secondary frequency signal, and performing filtering processing on the preliminary amplitude signal to obtain a secondary amplitude signal;

[0008] performing segmented filtering processing on the secondary frequency signal to obtain a target frequency signal, and performing segmented filtering processing on the secondary amplitude signal to obtain a target amplitude signal;

[0009] performing feature extraction on the target frequency signal to obtain a frequency feature, and performing feature extraction on the target amplitude signal to obtain an amplitude feature;

[0010] performing intraocular pressure analysis according to the frequency feature and the amplitude feature through a preset intraocular pressure monitoring model to obtain a target intraocular pressure value.

[0011] In some embodiments, after the preliminary frequency signal is filtered to obtain a secondary frequency signal, and the preliminary amplitude signal is filtered to obtain a secondary amplitude signal, the method further comprises:

[0012] The secondary frequency signal is pruned, specifically including:

[0013] A preset frequency signal of a preset model is obtained; wherein the preset model represents a blinking model;

[0014] The secondary frequency signal is filtered according to the preset frequency signal, to update the secondary frequency signal.

[0015] In some embodiments, the null value is excluded from the initial frequency signal to obtain a preliminary frequency signal, and the null value is excluded from the initial amplitude signal to obtain a preliminary amplitude signal, including:

[0016] The initial frequency signal is partitioned to obtain a frequency interval;

[0017] The initial amplitude signal is partitioned to obtain an amplitude interval;

[0018] The initial frequency signal with null value in the frequency interval is removed to obtain the preliminary frequency signal;

[0019] The initial amplitude signal with null value in the amplitude interval is removed to obtain the preliminary amplitude signal.

[0020] In some embodiments, the secondary frequency signal is filtered to obtain a target frequency signal, and the secondary amplitude signal is filtered to obtain a target amplitude signal, including:

[0021] The secondary frequency signal is segmented to obtain a frequency segment;

[0022] The secondary amplitude signal is segmented to obtain an amplitude segment;

[0023] The secondary frequency signal of the frequency segment is calculated for standard deviation and mean value to obtain a frequency reference value;

[0024] The secondary amplitude signal of the amplitude segment is calculated for standard deviation and mean value to obtain an amplitude reference value;

[0025] The secondary frequency signal is filtered according to the frequency reference value to obtain the target frequency signal;

[0026] The secondary amplitude signal is filtered according to the amplitude reference value to obtain the target amplitude signal.

[0027] In some embodiments, the frequency feature is extracted from the target frequency signal, and the amplitude feature is extracted from the target amplitude signal, including:

[0028] extracting a maximum value, a minimum value, a mean value, a median value and a first reference value of the target frequency signal to obtain the frequency feature; the first reference value is a mean value of absolute values of signal difference values of adjacent sites of the signal set;

[0029] extracting a maximum value, a minimum value, a mean value, a median value and a second reference value of the target amplitude signal to obtain the amplitude feature; the second reference value is a mean value of absolute values of signal difference values of adjacent sites of the signal set.

[0030] In some embodiments, before performing intraocular pressure analysis according to the frequency feature and the amplitude feature through a preset intraocular pressure monitoring model to obtain a target intraocular pressure value, the method further comprises:

[0031] pre-training the intraocular pressure monitoring model, specifically comprising:

[0032] obtaining sample data of a target human eye; the sample data comprises sample features and an intraocular pressure verification value;

[0033] inputting the sample features into a preset monitoring model to obtain an intraocular pressure prediction value;

[0034] performing parameter adjustment on the preset monitoring model according to the intraocular pressure verification value and the intraocular pressure prediction value to obtain the intraocular pressure monitoring model.

[0035] In some embodiments, the preset monitoring model comprises a decision tree model, a linear regression model, a random forest model and an iterative model; and the parameter adjustment on the preset monitoring model according to the intraocular pressure verification value and the intraocular pressure prediction value to obtain the intraocular pressure monitoring model comprises:

[0036] performing parameter adjustment on the decision tree model, the linear regression model, the random forest model and the iterative model according to the intraocular pressure verification value and the intraocular pressure prediction value to make the intraocular pressure prediction value approximate to the intraocular pressure verification value, so as to obtain the intraocular pressure monitoring model.

[0037] To achieve the above object, a second aspect of the embodiment of the present application proposes an intraocular pressure monitoring device, which comprises:

[0038] a contact lens, wherein the contact lens is provided with a monitoring coil for collecting a monitoring signal of a target human eye;

[0039] an antenna receiving system, wherein the antenna receiving system is connected with the contact lens to transmit the monitoring signal;

[0040] a server, wherein the server is wirelessly connected with the antenna receiving system to receive the monitoring signal transmitted by the antenna receiving system; and the server comprises:

[0041] The signal acquisition module is configured to acquire a monitoring signal of a target human eye, wherein the monitoring signal comprises an initial frequency signal and an initial amplitude signal.

[0042] The screening module is configured to perform null value screening on the initial frequency signal to obtain a preliminary frequency signal and perform null value screening on the initial amplitude signal to obtain a preliminary amplitude signal.

[0043] The primary filtering module is configured to perform filtering on the preliminary frequency signal to obtain a secondary frequency signal and perform filtering on the preliminary amplitude signal to obtain a secondary amplitude signal.

[0044] The secondary filtering module is configured to perform segmented filtering on the secondary frequency signal to obtain a target frequency signal and perform segmented filtering on the secondary amplitude signal to obtain a target amplitude signal.

[0045] The feature extraction module is configured to perform feature extraction on the target frequency signal to obtain a frequency feature and perform feature extraction on the target amplitude signal to obtain an amplitude feature.

[0046] The intraocular pressure analysis module is configured to perform intraocular pressure analysis according to the frequency feature and the amplitude feature by using a preset intraocular pressure monitoring model to obtain a target intraocular pressure value.

[0047] To achieve the above object, a third aspect of the embodiment of the present application provides an electronic device, which comprises a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the method of the first aspect.

[0048] To achieve the above object, a fourth aspect of the embodiment of the present application provides a storage medium, which is a computer readable storage medium for computer readable storage, and the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to realize the method of the first aspect.

[0049] The intraocular pressure monitoring method, the intraocular pressure monitoring device, the equipment and the storage medium provided by the present application can remove abnormal and interference signals by performing null value screening and secondary filtering on the collected initial frequency signal and initial amplitude signal of the target human eye, and then perform feature extraction on the target frequency signal and the target amplitude signal to obtain a frequency feature and an amplitude feature, and perform intraocular pressure analysis according to the frequency feature and the amplitude feature by using a trained intraocular pressure monitoring model to obtain a target intraocular pressure value, so as to realize continuous intraocular pressure value monitoring of the human eye. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1is a flow chart of the intraocular pressure monitoring method provided by an embodiment of the present application;

[0051] Figure 2 is Figure 1 is a flow chart of step S102 in

[0052] Figure 3 is a flow chart of the intraocular pressure monitoring method provided by another embodiment of the present application;

[0053] Figure 4 is Figure 1 is a flow chart of step S104 in

[0054] Figure 5 is Figure 1 is a flow chart of step S105 in

[0055] Figure 6 is a flow chart of the intraocular pressure monitoring method provided by another embodiment of the present application;

[0056] Figure 7 is a flow chart of step S603 in Figure 6

[0057] Figure 8 is a structural schematic diagram of the intraocular pressure monitoring device provided by an embodiment of the present application;

[0058] Figure 9 is a hardware structural schematic diagram of the electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not intended to limit the present application.

[0060] It should be noted that although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flow chart, in some cases, the steps shown or described can be executed in a manner different from the module division in the device or the order in the flow chart. The terms "first", "second", etc. in the specification and claims and the above-described drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application, and are not intended to limit the present application.

[0062] First, the several terms involved in the present application are analyzed: ​

[0063] Artificial intelligence (AI): is a new technical science of studying, developing the theory, method, technology and application system for simulating, extending and expanding human intelligence; artificial intelligence is a branch of computer science, artificial intelligence attempts to understand the essence of intelligence, and produce a new intelligent machine that can react in a similar way to human intelligence, the research in this field includes robots, language recognition, image recognition, natural language processing and expert system, etc. Artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is also the theory, method, technology and application system of using digital computer or digital computer controlled machine to simulate, extend and expand human intelligence, perceive environment, acquire knowledge and use knowledge to obtain the best results.

[0064] Intraocular pressure: intraocular pressure is the pressure of the interaction between the contents of the eyeball and the wall of the eyeball. The normal intraocular pressure is stable within a certain range to maintain the normal shape of the eyeball and keep the refractive state of each refractive medium interface in good condition. The contents of the eye include aqueous humor, lens and vitreous body, among which the aqueous humor has the greatest impact on intraocular pressure. The total amount of aqueous humor is 0.13mL-0.3mL, and its main component is water, in addition to protein, electrolyte, ascorbic acid, lactic acid, glucose, lipid, enzyme and so on, and the pH value is 7.3-7.5. Aqueous humor is produced by ciliary processes in the ciliary body, then enters the posterior chamber, and flows into the anterior chamber through the pupil, and then is discharged to the outside of the eyeball through some channels through the anterior chamber angle. In general, the production and excretion of aqueous humor maintain a dynamic balance, that is, the amount of aqueous humor produced and excreted is equal within a certain period of time.

[0065] Tukey's test: an outlier is a value that is significantly different from other sample data. This word is often used in statistics, which can represent data anomaly or measurement error. The method of outliers is very useful for correctly understanding data and will lead to more accurate conclusions.

[0066] Adaboost: Adaboost is an iterative algorithm, the core idea of which is to train different classifiers (weak classifiers) for the same training set, and then combine these weak classifiers to form a stronger final classifier (strong classifier). In the implementation process, the sample weight is initialized according to the size of the training set, so as to meet the uniform distribution. In the subsequent operation, the sample weight after the algorithm iteration is changed and normalized by the formula. The sample is misclassified, which leads to an increase in the weight, and vice versa. This indicates that the misclassified training sample set includes a higher weight. This will make the training sample set pay more attention to the difficult-to-identify samples in the next round, and further learning of the misclassified samples will obtain the next weak classifier, until the samples are correctly classified. When the specified number of iterations or the expected error rate is reached, the strong classifier is constructed.

[0067] Voting algorithm: The integrated method combines the results of two or more individual machine learning algorithms together and tries to produce more accurate results than any single algorithm. The voting algorithm is also called voting algorithm. For example, if algorithm 1 predicts that the object is a rock with a probability of 40%, and algorithm 2 predicts that it is a rock with a probability of 80%, then the integration will predict that the object is a rock with a probability of (80+40) / 2=60%.

[0068] In the related art, the electromechanical signal generated by the deformation of the contact lens coil is converted into a pressure signal to monitor the intraocular pressure. However, the test objects are generally pig eyes or rubber balls. Since the dielectric on the surface of the pig eye or the rubber ball is more stable than the living human eye, and the pig eye or the rubber ball does not have signal interference caused by blinking. However, the surface environment of the human eye is more complex, and there will be a large signal interference caused by blinking. Therefore, the traditional intraocular pressure monitoring method is not suitable for the human eye, so that the continuous intraocular pressure monitoring of the human eye is difficult to realize, and the accuracy of the intraocular pressure output value is reduced.

[0069] Therefore, the embodiment of the present application provides an intraocular pressure monitoring method, an intraocular pressure monitoring device, equipment and a storage medium, which aims to realize continuous intraocular pressure monitoring of the human eye and improve the accuracy of the intraocular pressure monitoring of the personnel.

[0070] The intraocular pressure monitoring method, the intraocular pressure monitoring device, the equipment and the storage medium provided by the embodiment of the present application are specifically explained by the following embodiments. First, the intraocular pressure monitoring method in the embodiment of the present application is described.

[0071] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. The artificial intelligence (AI) is a theory, method, technology and application system for simulating, extending and expanding human intelligence by using a digital computer or a machine controlled by a digital computer, perceiving an environment, acquiring knowledge and using the knowledge to obtain optimal results.

[0072] The artificial intelligence basic technology generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. The artificial intelligence software technology mainly includes computer vision technology, robot technology, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc.

[0073] The intraocular pressure monitoring method provided by the embodiments of the present application relates to the field of artificial intelligence. The intraocular pressure monitoring method provided by the embodiments of the present application can be applied in a terminal, can be applied in a server end, and can also be software running in a terminal or a server end. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc.; the server end can be configured as an independent physical server, can be configured as a server cluster or a distributed system composed of multiple physical servers, can also be configured as a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and big data and artificial intelligence platform; and the software can be an application for implementing the intraocular pressure monitoring method, etc., but is not limited to the above forms.

[0074] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment in which tasks are performed by remote processing devices connected by a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0075] It should be noted that in various specific embodiments of the present application, when relevant processing needs to be performed on data related to the identity or characteristics of the user, such as user information, user behavior data, user history data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of such data will comply with relevant national and regional laws, regulations, and standards. In addition, when the embodiments of the present application need to obtain sensitive personal information of the user, the separate permission or separate consent of the user will be obtained through a pop-up window or a jump to a confirmation page, and after obtaining the separate permission or separate consent of the user, the necessary user-related data for the normal operation of the embodiments of the present application will be obtained.

[0076] Figure 1 is an optional flowchart of an intraocular pressure monitoring method provided by the embodiments of the present application, Figure 1 The method in the method can include but is not limited to steps S101-S106.

[0077] Step S101, obtaining a monitoring signal of a target eye; wherein the monitoring signal includes an initial frequency signal and an initial amplitude signal;

[0078] Step S102, performing null value screening on the initial frequency signal to obtain a preliminary frequency signal, and performing null value screening on the initial amplitude signal to obtain a preliminary amplitude signal;

[0079] Step S103, performing filtering processing on the preliminary frequency signal to obtain a secondary frequency signal, and performing filtering processing on the preliminary amplitude signal to obtain a secondary amplitude signal;

[0080] Step S104, performing segmented filtering processing on the secondary frequency signal to obtain a target frequency signal, and performing segmented filtering processing on the secondary amplitude signal to obtain a target amplitude signal;

[0081] Step S105, performing feature extraction on the target frequency signal to obtain a frequency feature, and performing feature extraction on the target amplitude signal to obtain an amplitude feature;

[0082] Step S106, performing intraocular pressure analysis according to the frequency feature and the amplitude feature through a preset intraocular pressure monitoring model to obtain a target intraocular pressure value.

[0083] The steps S101 to S106 shown in the embodiments of the present application are applied to an intraocular pressure monitoring method applied to an intraocular pressure monitoring device. After the user wears the contact lens, the intraocular pressure monitoring device monitors the target eye of the user to obtain the initial frequency signal and the initial amplitude signal generated by the target eye, and the initial frequency signal and the initial amplitude signal are subjected to null screening to obtain the preliminary frequency signal and the preliminary amplitude signal, so as to screen out the null values in the initial frequency signal and the initial amplitude signal and reduce the influence of the null values. Then, the preliminary frequency signal is subjected to filtering processing to obtain the secondary frequency signal, and the preliminary amplitude signal is subjected to filtering processing to obtain the secondary amplitude signal. The secondary frequency signal and the secondary amplitude signal are subjected to filtering processing to filter out abnormal signals to obtain the target frequency signal and the target amplitude signal, and the target frequency signal and the target amplitude signal are subjected to feature extraction to extract the frequency feature and the amplitude feature of each segment. Then, the intraocular pressure is analyzed according to the frequency feature and the amplitude feature by using a preset intraocular pressure monitoring model to obtain the target intraocular pressure value. Therefore, the initial frequency signal and the initial amplitude signal of the target eye collected are subjected to null screening and secondary filtering processing to remove abnormal and interfering signals, and the target frequency signal and the target amplitude signal are subjected to feature extraction to obtain the frequency feature and the amplitude feature, and the intraocular pressure is analyzed according to the frequency feature and the amplitude feature by using the trained intraocular pressure monitoring model to obtain the target intraocular pressure value, so that the intraocular pressure monitoring of the eye is more accurate.

[0084] In step S101 of some embodiments, after the user wears the contact lens, a coil for monitoring the target eye is arranged on the contact lens to collect monitoring signals. The calibration of the intraocular pressure is started, that is, the intraocular pressure monitoring is started to obtain the initial frequency signal and the initial amplitude signal of the target eye, and the single-point intraocular pressure measuring device is used for intraocular pressure calibration. Then, the monitoring signals are transmitted to the server by the antenna receiving system for intraocular pressure value prediction. The initial frequency signal and the initial amplitude signal of the target eye in a preset time period are obtained, and the length of the preset time period is 1 hour or 1 day. The length of the preset time period is defined by the user and is not limited herein.

[0085] It should be noted that the intraocular pressure monitoring method is applied to an intraocular pressure monitoring device, and the intraocular pressure monitoring device collects the initial frequency signal and the initial amplitude signal according to the preset time period.

[0086] In step S102 of some embodiments, since the monitoring signals may be missing in a certain interval during signal collection, the initial frequency signal and the initial amplitude signal need to be subjected to null screening processing, that is, whether the signal is missing is analyzed, so as to screen out the null signals to obtain the preliminary frequency signal and the preliminary amplitude signal, thereby improving the accuracy of intraocular pressure monitoring.

[0087] In step S103 of some embodiments, the preliminary frequency signal and the preliminary amplitude signal are respectively subjected to overall filtering to filter out obvious abnormal signals to obtain a secondary frequency signal and a secondary amplitude signal, thereby improving the accuracy of the intraocular pressure monitoring.

[0088] It should be noted that the preliminary frequency signal and the preliminary amplitude signal are filtered by Tukey's test method.

[0089] Specifically, the preliminary frequency signal is sorted in ascending order, and then the preliminary frequency signal is divided into four segments in ascending order, and the value of the first quarter of the preliminary frequency signal is Q1, the value of the second quarter of the preliminary frequency signal is Q2, the value of the third quarter of the preliminary frequency signal is Q3, and the difference between the fourth quarter is IQR = Q3-Q1. Therefore, according to the values of Q1, Q2 and Q3, the preset frequency threshold interval is set as Q1-1.5IQR~Q3+1.5IQR. If the value of the preliminary frequency signal is within the preset frequency threshold interval, it indicates that the preliminary frequency signal is a normal signal. If the value of the preliminary frequency signal is not within the preset frequency threshold interval, it indicates that the preliminary frequency signal is an abnormal signal. The preliminary frequency signal outside the preset frequency threshold interval is removed to obtain the secondary frequency signal.

[0090] The preset amplitude threshold interval is set in the same way as the preset frequency threshold interval. The value of the initial amplitude signal is compared with the preset amplitude threshold interval to remove the preliminary amplitude signal that does not belong to the preset amplitude threshold interval to obtain the secondary amplitude signal, thereby removing the abnormal preliminary amplitude signal and reducing the interference of abnormal signals to improve the accuracy of the intraocular pressure monitoring.

[0091] In step S104 of some embodiments, after signal filtering, the secondary frequency signal and the secondary amplitude signal are respectively subjected to filtering processing again to remove each abnormal secondary frequency signal and secondary amplitude signal to remove the interference signals affecting the intraocular pressure monitoring, so that the intraocular pressure monitoring is more accurate. In step S105 of some embodiments, the frequency feature is obtained by feature extraction of each segment of the target frequency signal, and the amplitude feature is obtained by feature extraction of each segment of the target amplitude signal, so as to extract the frequency feature and the amplitude feature. The intraocular pressure value is analyzed by the frequency feature and the amplitude feature.

[0092] In step S106 of some embodiments, the frequency feature and the amplitude feature are input into a preset intraocular pressure monitoring model, and the intraocular pressure monitoring model is a trained model. The target intraocular pressure value is obtained by the intraocular pressure monitoring model according to the frequency feature and the amplitude feature for intraocular pressure analysis, so that the intraocular pressure monitoring is suitable for the intraocular pressure monitoring of the human eye, and the intraocular pressure monitoring of the human eye is more simple and accurate.

[0093] Referring to Figure 2 In some embodiments, the monitoring signal includes an initial frequency signal and an initial amplitude signal, so that the collected monitoring signal has two types of "frequency" and "amplitude", and the corresponding intervals are divided according to the signal types. Step S102 can include but is not limited to steps S201 to S204:

[0094] Step S201, the initial frequency signal is partitioned to obtain a frequency interval;

[0095] Step S202, the initial amplitude signal is partitioned to obtain an amplitude interval;

[0096] Step S203, the initial frequency signal with null value in the frequency interval is removed to obtain a preliminary frequency signal;

[0097] Step S204, the initial amplitude signal with null value in the amplitude interval is removed to obtain a preliminary amplitude signal.

[0098] In step S201 of some embodiments, the initial frequency signal is partitioned to obtain a frequency interval. Three frequency intervals are set, and the three frequency intervals are defined as a first frequency interval, a second frequency interval and a third frequency interval, the first frequency interval is a low frequency interval, the second frequency interval is a medium frequency interval, and the third frequency interval is a high frequency interval, and the numerical value of the preliminary frequency signal corresponding to each frequency interval is high frequency interval> medium frequency interval> low frequency interval.

[0099] In step S202 of some embodiments, the initial amplitude signal is partitioned to obtain an amplitude interval. Three amplitude intervals are set, and the three amplitude intervals are defined as a first amplitude interval, a second amplitude interval and a third amplitude interval, the first amplitude interval is a low amplitude interval, the second amplitude interval is a medium amplitude interval, and the third amplitude interval is a high amplitude interval. If there is no negative signal in the amplitude signal, the numerical value of the initial amplitude signal corresponding to each amplitude interval is | high amplitude interval | < | medium amplitude interval | < | low amplitude interval |.

[0100] In step S203 of some embodiments, the initial frequency signal in the frequency interval is searched for null value, and if the initial frequency signal with null value is found, it is removed, so that the preliminary frequency signal is obtained by removing the initial frequency signal with null value in each frequency interval, to reduce the influence of the initial frequency signal with null value on the subsequent filtering operation.

[0101] In step S204 of some embodiments, the initial amplitude signals in the amplitude interval are subjected to a null search, and the null initial amplitude signals are removed, that is, the initial amplitude signals that are null in each amplitude interval are removed to obtain the preliminary amplitude signals, so as to reduce the influence of the null initial amplitude signals on the subsequent filtering operation.

[0102] After step S102 of some embodiments, the intraocular pressure monitoring method further comprises: pruning the secondary frequency signals. Since the preset time period for collecting the initial frequency signals of the target human eye is relatively long, the target human eye may blink during the collection. Therefore, it is necessary to remove the signals of the secondary frequency signals that belong to the blink mode, so as to improve the accuracy of the intraocular pressure monitoring and reduce the interference of the secondary frequency signals corresponding to the blink mode.

[0103] Please refer to Figure 3 In some embodiments, pruning the secondary frequency signals can include but is not limited to steps S301 to S302:

[0104] In step S301, a preset frequency signal of a preset mode is obtained; wherein the preset mode is represented as a blink mode.

[0105] In step S302, the secondary frequency signals are subjected to screening processing according to the preset frequency signal, so as to update the secondary frequency signals.

[0106] In step S301 of some embodiments, after the frequency signal interval is obtained by completing the partition of the secondary frequency signals, the preset frequency signal corresponding to the blink mode is obtained, so as to determine whether the secondary frequency signal corresponding to the blink mode exists in the secondary frequency signals according to the preset frequency signal, so as to remove the secondary frequency signal of the blink mode and reduce the influence of the secondary frequency signal of the blink mode, thereby improving the accuracy of the intraocular pressure monitoring.

[0107] In step S302 of some embodiments, the secondary frequency signals that are consistent with the preset frequency signals are removed to update the secondary frequency signals by subjecting the secondary frequency signals to screening processing according to the preset frequency signal. After removing the secondary frequency signals that are consistent with the preset frequency signals, the preset specific signal is replaced to remove the secondary frequency signal corresponding to the blink mode.

[0108] Please refer to Figure 4 In some embodiments, step S104 includes but is not limited to steps S401 to S406:

[0109] In step S401, the secondary frequency signals are subjected to segmentation processing to obtain frequency segments.

[0110] In step S402, the secondary amplitude signals are subjected to segmentation processing to obtain amplitude segments.

[0111] Step S403, the standard deviation and mean value of the secondary frequency signal of the frequency segment are calculated to obtain a frequency reference value;

[0112] Step S404, the standard deviation and mean value of the secondary amplitude signal of the amplitude segment are calculated to obtain an amplitude reference value;

[0113] Step S405, the secondary frequency signal is filtered according to the frequency reference value to obtain a target frequency signal;

[0114] Step S406, the secondary amplitude signal is filtered according to the amplitude reference value to obtain a target amplitude signal.

[0115] In step S401 of some embodiments, after the null signal of the secondary frequency signal and the secondary amplitude signal is screened out, since the intraocular pressure of the target human eye does not change dramatically in a short time, the signal fluctuation in a short time is obviously caused by other interference factors. Therefore, the secondary frequency signal is processed by segmentation to obtain a frequency segment, so as to divide the corresponding secondary frequency signal of each frequency segment in time sequence. In this embodiment, the time period corresponding to the frequency segment is 1 minute, so as to divide the secondary frequency signal into a frequency segment of 1 minute.

[0116] In step S402 of some embodiments, in order to judge whether there is obvious interference factor in a short time, the secondary signal is processed by segmentation to obtain an amplitude segment, so as to divide the secondary amplitude signal into small segments, so as to judge whether there is abnormal signal in the secondary amplitude signal of each amplitude segment. In this embodiment, the time period of each amplitude segment is 1 minute, and the time period of the amplitude segment is not limited.

[0117] In step S403 of some embodiments, after each frequency segment is divided, the standard deviation and mean value of the secondary frequency signal of each frequency segment are calculated to obtain a frequency reference value, so as to filter the secondary frequency signal according to the frequency reference value, so as to obtain a more accurate target frequency signal.

[0118] In step S404 of some embodiments, after each amplitude segment is divided, the standard deviation and mean value of the secondary amplitude signal of each amplitude segment are calculated to obtain an amplitude reference value, so as to filter the secondary amplitude signal according to the amplitude reference value, so as to obtain a more accurate target amplitude signal.

[0119] In step S405 of some embodiments, the secondary frequency signal is filtered according to the frequency reference value, that is, the difference between the secondary frequency signal and the average of the secondary frequency signal is calculated, and the absolute value of the difference is taken to obtain a first standard deviation. It is determined whether the first standard deviation is greater than the frequency reference value. If the first standard deviation is greater than the frequency reference value, the frequency reference value is used to replace the secondary frequency signal. Otherwise, if the first standard deviation is less than the frequency reference value, the secondary frequency signal is retained, so as to screen out a more accurate target frequency signal, so that the intraocular pressure monitoring is more accurate.

[0120] In step S406 of some embodiments, the secondary amplitude signal is filtered according to the amplitude reference value, so as to determine whether the standard deviation of the secondary amplitude signal is greater than the amplitude reference value. The difference between the secondary amplitude signal and the average of the secondary amplitude signal is calculated, and the absolute value of the difference is taken to obtain a second standard deviation. If the second standard deviation is greater than the amplitude reference value, the amplitude reference value is used to replace the secondary amplitude signal. Otherwise, if the second standard deviation is less than the amplitude reference value, the secondary amplitude signal is retained, so as to screen out a more accurate target amplitude signal, and improve the accuracy of the intraocular pressure monitoring.

[0121] Please refer to Figure 5 In some embodiments, step S105 can further include but is not limited to steps S501 to S502:

[0122] Step S501, the maximum value, the minimum value, the average value, the median value and the first reference value of the target frequency signal are extracted to obtain the frequency feature; wherein the first reference value is the average value of the absolute value of the signal difference of the adjacent points of the signal set;

[0123] Step S502, the maximum value, the minimum value, the average value, the median value and the second reference value of the target amplitude signal are extracted to obtain the amplitude feature; wherein the second reference value is the average value of the absolute value of the signal difference of the adjacent points of the signal set.

[0124] In step S501 of some embodiments, the maximum value, the minimum value, the average value, the median value and the first reference value of each target frequency signal are extracted by performing feature extraction on each target frequency signal, so as to obtain the frequency feature, and the first reference value is the average value of the absolute value of the signal difference of the adjacent points of the signal set. Then, the intraocular pressure value can be more accurately analyzed according to the frequency feature.

[0125] In step S502 of some embodiments, the maximum value, the minimum value, the median value and the second reference value of each target amplitude signal are extracted by performing feature extraction on each target amplitude signal set, and the second reference value is the average value of the absolute value of the signal difference of the adjacent points of the signal set. Then, the intraocular pressure value can be more accurately analyzed according to the amplitude feature.

[0126] In some embodiments, before step S106, the intraocular pressure monitoring method further comprises:

[0127] The intraocular pressure monitoring model is pre-trained.

[0128] It should be noted that the intraocular pressure monitoring model needs to be constructed in advance, so that the intraocular pressure analysis is performed by the intraocular pressure monitoring model according to the frequency characteristics and the amplitude characteristics, and the intraocular pressure value calculation is more simple.

[0129] Referring to Figure 6 In some embodiments, the intraocular pressure monitoring model is pre-trained, including but not limited to steps S601 to S603:

[0130] In step S601, sample data of a target eye is obtained; wherein the sample data includes sample characteristics and an intraocular pressure verification value;

[0131] In step S602, the sample characteristics are input into a preset monitoring model to obtain an intraocular pressure prediction value;

[0132] In step S603, the preset monitoring model is adjusted in parameters according to the intraocular pressure verification value and the intraocular pressure prediction value to obtain an intraocular pressure monitoring model.

[0133] In step S601 of some embodiments, sample characteristics and an intraocular pressure verification value of a target eye are obtained, wherein the sample characteristics include sample frequency characteristics and sample amplitude characteristics, so as to train the preset monitoring model according to the sample data, adjust the model parameters, and obtain an accurate intraocular pressure monitoring model.

[0134] In step S602 of some embodiments, the sample characteristics are input into a preset monitoring model, the preset monitoring model performs intraocular pressure prediction according to the sample frequency characteristics and the sample amplitude characteristics to obtain an intraocular pressure prediction value, and the accuracy of intraocular pressure analysis of the preset monitoring model is judged according to the intraocular pressure prediction value and the intraocular pressure verification value.

[0135] In step S603 of some embodiments, the preset monitoring model is adjusted in parameters according to the intraocular pressure verification value and the intraocular pressure prediction value, the intraocular pressure prediction value is approximated to the intraocular pressure verification value, an accurate intraocular pressure monitoring model is constructed, and the target intraocular pressure value obtained by analyzing the frequency characteristics and the amplitude characteristics through the intraocular pressure monitoring model is more accurate.

[0136] Referring to Figure 7 In some embodiments, the preset monitoring model includes a decision tree model, a linear regression model, a random forest model, and an iterative model, and step S603 can include but is not limited to step S701:

[0137] Step S701, according to the intraocular pressure verification value and the intraocular pressure prediction value, the parameters of the decision tree model, the linear regression model, the random forest model and the iteration model are adjusted to make the intraocular pressure prediction value approach the intraocular pressure verification value, and an intraocular pressure monitoring model is obtained.

[0138] In step S701 of some embodiments, since the preset monitoring model is formed by the decision tree model, the linear regression model, the random forest model and the iteration model, when adjusting the parameters of the preset monitoring model, that is, the parameters of each of the decision tree model, the linear regression model, the random forest model and the iteration model need to be adjusted to make the intraocular pressure prediction value approach the intraocular pressure verification value. The iteration model is an Adaboost model, and the decision tree model, the linear regression model, the random forest model and the Adaboost model are put into the Voting algorithm to obtain the intraocular pressure prediction value, and the parameters of each model are adjusted according to the intraocular pressure prediction value and the intraocular pressure verification value to construct the intraocular pressure monitoring model, so that the target intraocular pressure value output by the intraocular pressure monitoring model is more accurate.

[0139] Please refer to Figure 8 The embodiment of the present application also provides an intraocular pressure monitoring device, which can realize the above-mentioned intraocular pressure monitoring method, and the device comprises:

[0140] The contact lens 801 is provided with a monitoring coil for collecting monitoring signals of the target human eye;

[0141] The antenna receiving system 802 is connected with the contact lens to transmit the monitoring signals;

[0142] The server 803 is wirelessly connected with the antenna receiving system to receive the monitoring signals transmitted by the antenna receiving system; the server comprises:

[0143] The null value screening module 804 performs null value screening processing on the initial frequency signal to obtain a preliminary frequency signal, and performs null value screening processing on the initial amplitude signal to obtain a preliminary amplitude signal;

[0144] The primary filtering module 805 is used for filtering processing on the preliminary frequency signal to obtain a secondary frequency signal, and filtering processing on the preliminary amplitude signal to obtain a secondary amplitude signal;

[0145] The screening module 806 is used for null value screening processing on the preliminary frequency signal to obtain a secondary frequency signal, and null value screening processing on the preliminary amplitude signal to obtain a secondary amplitude signal;

[0146] The secondary filtering module 807 is used for segment filtering processing on the secondary frequency signal to obtain a target frequency signal, and segment filtering processing on the secondary amplitude signal to obtain a target amplitude signal;

[0147] The feature extraction module 808 is configured to perform feature extraction on the target frequency signal to obtain a frequency feature, and perform feature extraction on the target amplitude signal to obtain an amplitude feature.

[0148] The intraocular pressure analysis module 809 is configured to perform intraocular pressure analysis on the frequency feature and the amplitude feature according to a preset intraocular pressure monitoring model to obtain a target intraocular pressure value.

[0149] The specific implementation of the intraocular pressure monitoring device is basically the same as the specific embodiments of the intraocular pressure monitoring method described above, and will not be repeated here.

[0150] The embodiments of the present application also provide an electronic device, which includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the intraocular pressure monitoring method described above. The electronic device can be any smart terminal including a tablet computer, a vehicle-mounted computer, etc.

[0151] Please refer to Figure 9 , Figure 9 The hardware structure of the electronic device of another embodiment is illustrated, which includes:

[0152] The processor 901 can be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, etc., and is used to execute related programs to realize the technical solutions provided by the embodiments of the present application.

[0153] The memory 902 can be implemented in the form of a ROM (ReadOnly Memory), a static storage device, a dynamic storage device, or a RAM (Random Access Memory), etc. The memory 902 can store an operating system and other application programs, and when the technical solutions provided by the embodiments of the present application are implemented by software or firmware, the related program codes are saved in the memory 902 and are called and executed by the processor 901 to realize the intraocular pressure monitoring method of the embodiments of the present application.

[0154] The input / output interface 903 is used to realize information input and output.

[0155] The communication interface 904 is used to realize the communication interaction between the device and other devices, which can realize communication through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.).

[0156] A bus 905 transmits information between various components (for example, the processor 901, the memory 902, the input / output interface 903, and the communication interface 904) in the device.

[0157] The processor 901, the memory 902, the input / output interface 903, and the communication interface 904 are communicatively connected to each other within the device through the bus 905.

[0158] The embodiment of the present application also provides a storage medium, which is a computer readable storage medium, used for computer readable storage, and stores one or more programs, which can be executed by one or more processors to implement the intraocular pressure monitoring method.

[0159] The memory, as a non-transitory computer readable storage medium, can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory remotely arranged relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0160] The intraocular pressure monitoring method, the intraocular pressure monitoring device, the equipment and the storage medium provided by the embodiment of the present application are used for carrying out null value screening processing on the initial frequency signal and the initial amplitude signal to obtain a preliminary frequency signal and a preliminary amplitude signal. Then, the preliminary frequency signal is filtered to obtain a secondary frequency signal, and the preliminary amplitude signal is filtered to obtain a secondary amplitude signal, so as to filter the preliminary frequency signal and the preliminary amplitude signal as a whole, so as to remove the obviously abnormal signal. Then, the secondary frequency signal and the secondary amplitude signal are filtered, so as to filter out the abnormal signal to obtain a target frequency signal and a target amplitude signal, and the target frequency signal and the target amplitude signal are subjected to feature extraction, so as to extract the frequency feature and the amplitude feature of each segment. Then, the target intraocular pressure value is obtained by performing intraocular pressure analysis on the frequency feature and the amplitude feature according to the preset intraocular pressure monitoring model. Therefore, by carrying out null value screening and twice filtering processing on the initial frequency signal and the initial amplitude signal of the collected target human eye, the abnormal and interference signals are removed, and the frequency feature and the amplitude feature are obtained by carrying out feature extraction on the target frequency signal and the target amplitude signal, and the target intraocular pressure value is obtained by performing intraocular pressure analysis on the frequency feature and the amplitude feature according to the trained intraocular pressure monitoring model, so that the intraocular pressure value monitoring of the human eye is more accurate.

[0161] The embodiments described in the specification of the present application are intended to more clearly illustrate the technical solutions of the present application, and do not constitute a limitation on the technical solutions provided by the present application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the present application are also applicable to similar technical problems.

[0162] Those skilled in the art can understand that, Figures 1-7 The technical solutions shown in the above description do not constitute a limitation on the present application, and can include more or fewer steps than shown, or combine certain steps, or different steps.

[0163] The device embodiments described above are merely illustrative, and units described as separate components can or can not be physically separated, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment.

[0164] Those skilled in the art can understand that all or some of the steps in the above disclosed method, the function modules / units in the system and the device can be implemented as software, firmware, hardware and their appropriate combinations.

[0165] The terms "first", "second", "third", "fourth" and the like (if any) in the specification of the present application and the above description are used to distinguish similar objects, and do not necessarily indicate a specific order or chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0166] It should be understood that, in the application, "at least one" refers to one or more, and "multiple" refers to two or more. "And / or" is used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, "A and / or B" can represent three cases of only A, only B, and A and B existing at the same time, wherein A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can represent a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, and c can be single or multiple.

[0167] In several embodiments provided in the application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the above units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed mutual ones can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0168] The units described above as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment scheme.

[0169] In addition, each functional unit in each embodiment of the application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0170] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media.

[0171] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, and are not limited to the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. A method of intraocular pressure monitoring, characterized by, The method comprises: obtaining a monitoring signal of a target human eye; wherein the monitoring signal comprises an initial frequency signal and an initial amplitude signal; performing null value screening processing on the initial frequency signal to obtain a preliminary frequency signal, and performing null value screening processing on the initial amplitude signal to obtain a preliminary amplitude signal; performing filtering processing on the preliminary frequency signal to obtain a secondary frequency signal, and performing filtering processing on the preliminary amplitude signal to obtain a secondary amplitude signal; performing segmented filtering processing on the secondary frequency signal to obtain a target frequency signal, and performing segmented filtering processing on the secondary amplitude signal to obtain a target amplitude signal; performing feature extraction on the target frequency signal to obtain a frequency feature, and performing feature extraction on the target amplitude signal to obtain an amplitude feature; performing intraocular pressure analysis according to the frequency feature and the amplitude feature through a preset intraocular pressure monitoring model to obtain a target intraocular pressure value. The filtering processing on the preliminary frequency signal to obtain a secondary frequency signal comprises: sorting the preliminary frequency signal in ascending order, and setting a preset frequency threshold interval according to the value of the preliminary frequency signal; performing filtering processing on the preliminary frequency signal according to the preset frequency threshold interval to obtain the secondary frequency signal.

2. The method of claim 1, wherein, After the filtering processing on the preliminary frequency signal to obtain a secondary frequency signal and the filtering processing on the preliminary amplitude signal to obtain a secondary amplitude signal, the method further comprises: performing pruning processing on the secondary frequency signal, specifically comprising: obtaining a preset frequency signal of a preset model; wherein the preset model is represented as a blink model; performing screening processing on the secondary frequency signal according to the preset frequency signal to update the secondary frequency signal.

3. The method of claim 1, wherein, The null value screening processing on the initial frequency signal to obtain a preliminary frequency signal and the null value screening processing on the initial amplitude signal to obtain a preliminary amplitude signal comprise: performing partition processing on the initial frequency signal to obtain a frequency interval; performing partition processing on the initial amplitude signal to obtain an amplitude interval; removing the initial frequency signal that is null in the frequency interval to obtain the preliminary frequency signal; removing the initial amplitude signal that is null in the amplitude interval to obtain the preliminary amplitude signal.

4. The method according to any one of claims 1 to 3, characterized in that, The segmented filtering processing on the secondary frequency signal to obtain a target frequency signal and the segmented filtering processing on the secondary amplitude signal to obtain a target amplitude signal comprise: performing segmented processing on the secondary frequency signal to obtain a frequency segment; performing segmented processing on the secondary amplitude signal to obtain an amplitude segment; performing standard deviation and mean value calculation on the secondary frequency signal of the frequency segment to obtain a frequency reference value; performing standard deviation and mean value calculation on the secondary amplitude signal of the amplitude segment to obtain an amplitude reference value; performing filtering processing on the secondary frequency signal according to the frequency reference value to obtain the target frequency signal; performing filtering processing on the secondary amplitude signal according to the amplitude reference value to obtain the target amplitude signal.

5. The method according to any one of claims 1 to 3, characterized in that, The feature extraction on the target frequency signal obtains a frequency feature, and the feature extraction on the target amplitude signal obtains an amplitude feature, including: extracting a maximum value, a minimum value, a mean value, a median value and a first reference value of the target frequency signal to obtain the frequency feature; wherein the first reference value is a mean value of absolute values of signal difference values of adjacent points of a signal set; extracting a maximum value, a minimum value, a mean value, a median value and a second reference value of the target amplitude signal to obtain the amplitude feature; wherein the second reference value is a mean value of absolute values of signal difference values of adjacent points of a signal set.

6. The method according to any one of claims 1 to 3, characterized in that, Before performing intraocular pressure analysis according to the frequency feature and the amplitude feature through a preset intraocular pressure monitoring model to obtain a target intraocular pressure value, the method further includes: pre-training the intraocular pressure monitoring model, specifically including: obtaining sample data of a target human eye; wherein the sample data includes sample features and an intraocular pressure verification value; inputting the sample features into a preset monitoring model to obtain an intraocular pressure prediction value; adjusting parameters of the preset monitoring model according to the intraocular pressure verification value and the intraocular pressure prediction value to obtain the intraocular pressure monitoring model.

7. The method of claim 6, wherein, The preset monitoring model includes a decision tree model, a linear regression model, a random forest model and an iterative model; and adjusting parameters of the preset monitoring model according to the intraocular pressure verification value and the intraocular pressure prediction value to obtain the intraocular pressure monitoring model includes: adjusting parameters of the decision tree model, the linear regression model, the random forest model and the iterative model according to the intraocular pressure verification value and the intraocular pressure prediction value to make the intraocular pressure prediction value approximate to the intraocular pressure verification value, thereby obtaining the intraocular pressure monitoring model.

8. An intraocular pressure monitoring device, characterized in that, The device includes: a contact lens, wherein a monitoring coil for collecting a monitoring signal of a target human eye is arranged on the contact lens; an antenna receiving system, wherein the antenna receiving system is connected with the contact lens to transmit the monitoring signal; a server, wherein the server is wirelessly connected with the antenna receiving system to receive the monitoring signal transmitted by the antenna receiving system; and the server includes: a signal acquisition module, wherein the signal acquisition module is configured to acquire a monitoring signal of a target human eye; and the monitoring signal includes an initial frequency signal and an initial amplitude signal; a null value screening module, wherein the null value screening module is configured to perform null value screening processing on the initial frequency signal to obtain a preliminary frequency signal, and perform null value screening processing on the initial amplitude signal to obtain a preliminary amplitude signal; a primary filtering module, wherein the primary filtering module is configured to perform filtering processing on the preliminary frequency signal to obtain a secondary frequency signal, and perform filtering processing on the preliminary amplitude signal to obtain a secondary amplitude signal; a secondary filtering module, wherein the secondary filtering module is configured to perform segmented filtering processing on the secondary frequency signal to obtain a target frequency signal, and perform segmented filtering processing on the secondary amplitude signal to obtain a target amplitude signal; a feature extraction module, wherein the feature extraction module is configured to perform feature extraction on the target frequency signal to obtain a frequency feature, and perform feature extraction on the target amplitude signal to obtain an amplitude feature. An intraocular pressure analysis module is configured to analyze intraocular pressure according to the frequency feature and the amplitude feature by a preset intraocular pressure monitoring model to obtain a target intraocular pressure value.

9. An electronic device, comprising: The electronic device includes a memory, a processor, a program stored on the memory and executable on the processor, and a data bus for realizing connection communication between the processor and the memory, and the program is executed by the processor to realize the steps of the method according to any one of claims 1 to 7.

10. A storage medium, the storage medium being a computer-readable storage medium for computer-readable storage, characterized in that, The storage medium stores one or more programs, and the one or more programs are executable by one or more processors to realize the steps of the method according to any one of claims 1 to 7.

Images