Remote triage method and device, storage medium and chip

Abstract

The invention is suitable for the technical field of computers, and the embodiment of the invention provides a remote triage method and device, a storage medium and a chip, and the remote triage method comprises the steps: obtaining first data and second data, the first data is a body disease assessment result determined according to a body disease risk questionnaire filled by the target user, and the second data is a body disease detection result of the target user; based on the first data and the second data, determining a shunting strategy of the target user according to a first deep machine learning model, determining real body data of the user through the first data and the second data, determining a shunting strategy for the user through the deep machine learning model according to the real body data of the user, and shunting the user. Existing medical resources are reasonably allocated, and the doctor seeing time of a user is saved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a remote triage method, device, storage medium and chip. Background Art

[0002] In populous areas such as the Hong Kong Special Administrative Region of the People's Republic of China and other Asian countries, the existing healthcare system is overwhelmed by the high demand for medical care. Take myopia, for example, which has become an epidemic, affecting about 40% of school-age children aged 8-12 years. Recent surveys show that myopia rates in the same population have surged to more than 70%. In addition, one in three children surveyed has impaired vision due to uncorrected refractive error, highlighting the lack of appropriate and timely eye care. The underlying problem is twofold: parents often rely on children to self-report vision problems, but children may find it difficult to explain their vision status, delaying eye treatment. In addition, early myopia often leads to increased myopia. If not treated in time, myopia may develop into high myopia (-6.00D or higher), greatly increasing the risk of serious eye diseases such as retinal detachment, glaucoma, macular degeneration and cataracts. With about 200,000 school children in Hong Kong, China, there is a great need for pediatric eye care. Unfortunately, the existing health system has only 309 ophthalmologists and 1,075 optometrists, which cannot meet the growing demand. The lack of ophthalmic health care providers also affects myopia management around the world.

[0003] Given that current medical resources are limited, especially outpatient medical resources, how to use limited outpatient resources to meet the medical needs of a large number of users is an urgent problem that needs to be solved. Summary of the invention

[0004] The present application provides a remote triage method, device, storage medium and chip to obtain the user's real body data, and based on the user's real body data, determine a diversion strategy for the user through a deep machine learning model, and by diverting the user, rational allocation of existing medical resources can be achieved, and the user's medical treatment time can be saved.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions:

[0006] In a first aspect, a remote triage method is provided, the remote triage method comprising:

[0007] Acquire first data and second data, wherein the first data is a physical disease assessment result determined based on a physical disease risk questionnaire filled out by a target user, and the second data is a physical disease detection result of the target user;

[0008] Based on the first data and the second data, a diversion strategy for the target user is determined according to a first deep machine learning model.

[0009] In a possible implementation manner of the first aspect, acquiring the first data and the second data includes:

[0010] Obtaining physical disease risk questionnaire data filled out by the target user;

[0011] The physical disease risk questionnaire data is evaluated according to the second deep machine learning model to obtain the first data and acquire the second data.

[0012] In a possible implementation manner of the first aspect, the detection result is obtained by performing a physical examination of the target user through an online testing tool.

[0013] In a possible implementation manner of the first aspect, acquiring the first data and the second data includes:

[0014] Acquire the test data of the target user's physical examination through the online testing tool;

[0015] The detection data is evaluated according to the third deep machine learning model to obtain the second data and acquire the first data.

[0016] In a possible implementation of the first aspect, the physical disease risk questionnaire is a vision risk questionnaire, and the second data is a vision test result of the target user.

[0017] In a possible implementation manner of the first aspect, determining the diversion strategy for the target user based on the first data and the second data according to a first deep machine learning model includes:

[0018] Based on the first data and the second data, determining the risk of vision loss of the target user according to a first deep machine learning model;

[0019] A triage strategy is determined based on the risk of vision loss.

[0020] In a possible implementation manner of the first aspect, the method further includes:

[0021] Acquire historical information of the target user, wherein the historical information includes a medical history of a physical disease of the target user;

[0022] Based on the first data, the second data and the historical information, determine the physical risk of the target user according to a fourth deep machine learning model; and determine corresponding medical advice based on the physical risk.

[0023] In a second aspect, a remote triage device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the remote triage method in any optional implementation of the first aspect are implemented.

[0024] In a third aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the remote triage method as described in any one of the first aspects are implemented.

[0025] In a fourth aspect, a chip is provided, comprising a processor and an interface; the processor is used to read instructions to execute the steps of any one of the methods described in the first aspect.

[0026] The remote triage method, device, storage medium, and chip provided in the embodiments of the present application have the following effective effects:

[0027] The remote triage method provided in the present application requires the user to fill out a physical disease risk questionnaire and undergo a physical disease test to obtain the user's actual physical information, and then provides the user with a corresponding diversion strategy based on the user's actual physical information combined with a deep machine learning model. By assigning corresponding medical treatment methods to users with different physical information, the rational use of medical resources can be achieved to avoid one medical treatment method being squeezed out while the other medical treatment method is idle for a long time. The corresponding diversion strategy is determined for the user based on the different physical information of the user, so that the user can receive targeted medical treatment and the user's medical efficiency is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A flowchart of a remote triage method provided in an embodiment of the present application;

[0029] Figure 2 A flowchart of another remote triage method provided in an embodiment of the present application;

[0030] Figure 3 A schematic diagram of the structure of a remote triage device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] It should be noted that the terms used in the embodiments of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application. In the description of the embodiments of the present application, unless otherwise specified, "multiple" refers to two or more than two, and "at least one", "one or more" refers to one, two or more. The terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, it is defined that the "first" and "second" features can explicitly or implicitly include one or more of the features.

[0032] References to "one embodiment" or "some embodiments" etc. described in this specification mean that a particular feature, structure or characteristic described in conjunction with the embodiment is included in one or more embodiments of the present application. Thus, the phrases "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear at different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0033] To facilitate understanding, the terms involved in the embodiments of the present application are first briefly introduced.

[0034] 1. Home-based Digital Eye Test

[0035] A home digital vision test is a digital vision test that is performed at home. It uses an electronic device (such as a smartphone, tablet, or computer) and a specific app or website to assess visual ability and eye health.

[0036] This testing usually includes a series of visual acuity, astigmatism, color blindness, and contrast tests, which can vary depending on the functionality and design of the app or website. The test may ask you to observe and identify patterns, letters, or numbers of different sizes, distances, or colors, and your response will be used to assess your eye health.

[0037] 2. Myopia Risk Electronic Questionnaire

[0038] The Myopia Risk Electronic Questionnaire is an electronic questionnaire designed to assess an individual's risk of developing myopia. This questionnaire is usually designed by professional ophthalmologists or researchers to collect information and risk factors related to myopia.

[0039] 3. Visual function threshold

[0040] The visual function threshold refers to the critical point of the human eye's perception of visual stimuli such as light intensity, color, and contrast. The visual function threshold can be used to measure the sensitivity of the human eye to different stimuli.

[0041] 4. Anti-aliasing technology

[0042] Anti-aliasing is a graphics processing technique used to reduce the jagged edges of images or graphics. Aliasing occurs when the edges of an image or graphic are represented as a jagged array of pixels at low resolution or with limited sampling. Anti-aliasing aims to smooth out edges to make them appear smoother and more natural. Anti-aliasing can significantly improve the visual quality of images and graphics, making them look smoother and more realistic. It is widely used in computer graphics, game development, image processing and other fields.

[0043] As people's living standards improve, their health awareness becomes stronger and stronger. When they feel unwell or feel unwell, they usually go to the hospital to seek treatment. However, due to limited medical resources, especially outpatient resources, for example, in the case of myopia, about 200,000 students in Hong Kong may suffer from myopia. The existing medical system in Hong Kong has only 309 ophthalmologists and 1,075 optometrists, and outpatient resources are far from meeting the huge demand for myopia consultation.

[0044] Based on the above technical problems, the embodiment of the present application provides a remote triage method, in which the user first fills in the corresponding physical disease risk questionnaire (i.e., questionnaire), determines the first data based on the physical disease risk questionnaire filled in by the user, and then the user performs a physical examination to obtain the second data; then based on the first data and the second data, the user's diversion strategy is predicted according to the first deep machine learning model, and the user performs a physical disease questionnaire survey and physical examination related data to determine the user's true physical state, and provides the user with a corresponding diversion strategy based on the user's physical state information combined with the deep machine learning model. The diversion strategy is a medical treatment method that the user can adopt. By providing different medical treatment methods for users with different physical conditions, targeted initial consultation suggestions can be provided to the user, so that the user can go to the doctor according to the initial consultation suggestions to save the user's medical treatment time. Further, in addition to providing outpatient treatment, medical institutions or social medical resources also provide other ways of medical treatment or consultation, such as online treatment, remote resources, etc. Many users simply misjudge their own physical condition or have a low level of disease risk. In this case, the user does not need to consult with the doctor in the clinic, but only needs to consult with the doctor remotely or consult with the doctor to solve their doubts or provide corresponding suggestions to the user. In this way, by diverting users, we can achieve rational allocation of existing medical resources and ensure that outpatient resources are allocated to users who really need them.

[0045] See also Figure 1 , is a flow chart of a remote triage method provided in an embodiment of the present application, and the remote triage method may include the following steps:

[0046] S101. Obtain first data and second data, where the first data is an assessment result determined based on a physical disease risk questionnaire filled out by a target user, and the second data is a test result of the target user.

[0047] Specifically, by having the target user fill out a physical disease risk questionnaire, the user's physical disease information from the target user's perspective can be obtained. For example, if the user wants to inquire about his or her eyesight, the user's eyesight status can be obtained through the physical disease risk file, where the eyesight status can include whether the user is nearsighted, the user's myopia degree, etc.; by having the user perform a physical examination, the user's physical examination results can be obtained; in this way, the first data is obtained from the user's perspective, and the second data is obtained by testing the user's body, and the user's actual physical condition can be determined through the two data.

[0048] S102. Based on the first data and the second data, determine the user's diversion strategy according to the first deep machine learning model, where the diversion strategy is the user's medical treatment method.

[0049] Specifically, based on the first data and the second data as the input of the first deep machine learning model, the diversion strategy corresponding to the user is determined according to the first deep machine learning model, that is, the corresponding medical treatment method is recommended to the user according to the user's actual physical condition, so as to divert the user to the medical resources corresponding to the allocated medical treatment method.

[0050] In this way, the user fills out a physical disease risk questionnaire and undergoes physical disease testing to obtain the user's actual physical information. Then, based on the user's actual physical information and combined with a deep machine learning model, a corresponding diversion strategy is provided to the user. By assigning corresponding medical treatment methods to users with different physical information, the rational use of medical resources can be achieved to avoid one medical treatment method being squeezed out while the other medical treatment method is idle for a long time. The corresponding diversion strategy is determined for the user based on the different physical information of the user, so that the user can receive targeted medical treatment and the user's medical efficiency is improved.

[0051] In particular, for the appointment process of online consultation or clinic consultation, before the user makes an online appointment for medical treatment, the user's actual physical information is obtained based on the first data and the second data, and the user's actual physical information is combined with the deep machine learning model to determine the corresponding medical treatment method for the user, so as to achieve user diversion and ensure the rational and effective use of medical resources. And most of the existing appointment processes can be carried out online, so the user determines the corresponding medical treatment method before the medical treatment to save the user's medical treatment time.

[0052] Furthermore, the first deep machine learning model is trained based on the deep machine learning algorithm and the real database of a specific area. Since the first deep machine learning model can be continuously trained through a dynamic database (such as data of users in a specific area), the first deep machine learning model is in different learning and improvement stages, thereby ensuring that the first deep machine learning model becomes more effective over time.

[0053] In an optional implementation, before S102, it further includes: obtaining existing medical resources, where the medical resources are medical resources that can be provided by the current medical institution, such as the number of appointments that can be made for each doctor in the outpatient clinic, the number of available remote consultations, etc.; then S102 includes:

[0054] Based on the first data, the second data and the existing medical resources, a diversion strategy for the user is determined according to the first deep machine learning model, and the diversion strategy is the user's medical treatment method.

[0055] In this way, by acquiring existing medical resources and combining them with the user's actual physical condition, a corresponding diversion strategy is determined for the target user through the first deep machine learning model to improve the accuracy of the allocation of the diversion strategy.

[0056] It can be understood that the actual data of the user's physical disease obtained through S101 may be the overall physical condition of the user, such as multiple parts of the user's body that need to be checked, such as hands, feet, etc., or the local physical condition of the user, such as the user's vision data, the user's dental condition, the user's hand or foot flexibility data, etc., before obtaining the user's physical data through S101, it also includes:

[0057] The user indication information is obtained, and the indication information carries a detection target, which is at least one part of the user's body, for example, the detection target may be eyesight, teeth, etc. In this way, the user's medical treatment target is determined through the user's indication information.

[0058] Optionally, the user can be reminded to enter instruction information through a prompt box or the like. After the user enters the instruction information, the corresponding physical disease risk questionnaire and / or detection tool is determined based on the user's instruction information, so that the user can fill in the assigned physical disease risk questionnaire and perform physical tests based on the assigned detection tool.

[0059] Exemplarily, if the user indication information determines the eye vision of the user's target of medical treatment, a vision risk questionnaire is assigned to the user to fill out to obtain information such as whether the user is myopic and whether there is a recent trend of decline in the user's vision; and the user's current vision, astigmatism, color sensitivity and other information are detected based on the vision detection tool.

[0060] Optionally, the physical disease risk questionnaire is an electronic questionnaire, and the target users can conduct instant online assessments through devices such as mobile phones or desktop computers, which is convenient for users.

[0061] Optionally, each question in the physical disease risk questionnaire is selected and determined by scientific publications or industry experts, so that the user's physical information can be determined based on the questions in the physical disease risk questionnaire and the user's answers.

[0062] In an optional implementation, S101 includes:

[0063] Obtain physical disease risk questionnaire data filled out by target users;

[0064] The physical disease risk questionnaire data is evaluated according to the second deep machine learning model to obtain the first data and acquire the second data.

[0065] That is, after the user completes the physical disease risk questionnaire, the second deep machine learning model is used to evaluate the physical disease questionnaire information filled out by the user to obtain the first data, that is, the user's evaluation result. In this way, the physical disease risk questionnaire information filled out by the user is evaluated in combination with the deep machine learning model to obtain the corresponding evaluation result, and the second deep machine learning model is used to perform a scientific evaluation to improve the accuracy of the evaluation result. And because the evaluation result is obtained by the second deep machine learning model, no human participation is required, which reduces the time and effort required for the evaluation result, improves the efficiency of the evaluation process, and reduces the probability of errors in the evaluation process.

[0066] Optionally, the second deep machine learning model is trained based on the deep machine learning algorithm and the real database of the specific region to improve the accuracy of the evaluation results. For example, in order to be applicable to the vision diseases of users in Hong Kong, model training can be performed based on the deep machine learning algorithm and the vision data of users in Hong Kong. Since the second deep machine learning model is trained based on the user data of the specific region, the users in the specific region are evaluated by the second deep machine learning model, which can improve the accuracy of the evaluation results.

[0067] Optionally, the deep machine learning model can also be replaced by other means, for example, a support vector machine (SVM), a decision tree model, or an ensemble method such as a random forest or gradient boosting can be used to evaluate the physical disease risk questionnaire information filled out by the user.

[0068] Furthermore, the model used to evaluate the physical disease risk questionnaire information filled out by the user can be determined based on the data used (such as the type or category of database), the accuracy of the evaluation results, and the computational efficiency.

[0069] Optionally, the testing tool is an online testing tool, which is installed in terminals such as mobile phones and desktop computers, so that users can perform physical disease detection anytime and anywhere.

[0070] It can be understood that the user can perform a physical examination through an online testing tool to determine the corresponding test result, i.e., the second data, based on the data fed back by the user's physical examination. In some embodiments, the test data detected by the user through the online testing tool is the second data. For example, if the user performs a vision test through the online testing tool, the test result is the user's vision, and the result is the second data corresponding to the user. In other embodiments, the test data determined after the user performs the test through the online testing tool is evaluated based on the third deep machine learning model to obtain the corresponding test result. For example, in order to detect the cause of the user's physical discomfort, the user is tested by blood, and the blood test data is input into the third deep machine learning model to determine that the user has a viral cold, and the second data is a viral cold.

[0071] Optionally, the third deep machine learning model is trained based on the deep machine learning algorithm and the collected data set.

[0072] Optionally, if the physical disease risk questionnaire is a myopia risk questionnaire and the second data is a vision test result, the above remote triage method is used to divert users who are about to seek medical treatment for vision-related diseases. Since the online detection tool can detect the user's vision level by selecting an online picture, and obtain the user's myopia status through the myopia questionnaire, the combination of the two can obtain the user's real vision data, and then the user can be diverted based on the vision data and the deep machine learning model.

[0073] Furthermore, the first data can be obtained by the user by filling out an online physical disease risk questionnaire, and the second data can be obtained by the user by testing through an online testing tool. In this way, before the user sees a doctor, the user can complete the physical disease risk questionnaire and perform a physical test through the online testing tool at any time, such as a vision test, so as to determine the corresponding diversion strategy for the user based on the first data and the second data and according to the first deep machine learning model, which is convenient for the user to complete it anytime and anywhere, without being restricted by time and space.

[0074] In an optional implementation, the online testing tool is implemented through a home-based digital eye test (Home-based Digital Eye Test). Since the home-based digital eye test (Home-based Digital Eye Test) can be installed in a mobile phone or a desktop computer, it is convenient for users to test anytime and anywhere.

[0075] Furthermore, the online test tool uses Bayesian statistics to determine the user's visual function threshold based on user input, and adjusts the visual stimulation intensity of the test image based on the visual function threshold, thereby speeding up the test process. Providing users with visual stimulation images through the Bayesian model helps to avoid user bias, thereby ensuring the accuracy of the test results. In addition, the online test tool only requires fewer experiments to obtain the user's test results, saving test time and improving usability.

[0076] Furthermore, the online test tool also uses anti-aliasing technology to optimize the test image. Anti-aliasing technology improves the spatial resolution of the display unit and overcomes the problem of display unit resolution in visual function testing. By changing the brightness of the pixel, the system can obtain additional spatial resolution, thereby improving the accuracy of the visual test.

[0077] The online testing tool can improve the accuracy and efficiency of users' online vision testing by combining Bayesian models and anti-aliasing technology.

[0078] In an optional implementation, the first data includes data filled out by a user in a physical disease risk questionnaire and a physical disease assessment result determined based on the filled-in data, thereby improving the accuracy of determining the diversion strategy by improving the richness of the input of the first deep machine learning model.

[0079] Furthermore, the second data includes the user's physical disease detection results and physical disease detection data. For example, if the user undergoes a blood test, the physical disease detection data is the blood test results; the physical disease detection results are the physical disease detection results determined based on the test results.

[0080] It can be understood that each user can fill in the physical disease risk questionnaire or perform physical examination through the online testing tool at different times or places, then multiple sets of first data or\ and second data of each user can be obtained, and the multiple sets of first data or\ and second data can be used as inputs of the first deep machine learning model to improve the accuracy of determining the user's diversion strategy, then S102 is:

[0081] Based on the first data and the second data in a preset time period or a preset group, a diversion strategy for the target user is determined according to the first deep machine learning model. In this way, the user diversion strategy is determined by the first data and the second data in the preset time period or the preset group to improve the accuracy of the diversion strategy determination.

[0082] It can be understood that in order to improve the accuracy of risk assessment, the user's historical information can also be obtained, and the diversion strategy is determined by combining the user's historical information, the first data and the second data with the first deep machine learning model to improve the accuracy of determining the user's diversion strategy. Then S102 is:

[0083] Based on the first data, the second data and the historical information, a diversion strategy for the user is determined according to a first deep machine learning model. The historical information includes the user's medical history. The diversion strategy for the user is determined by combining the user's personal medical history with the first data and the second data to improve the sensitivity and specificity of risk assessment.

[0084] Furthermore, the historical information also includes first data and second data related to the user, namely, questionnaire information and online test information that the user has done, which improves the accuracy of line assessment by improving the input data of the deep machine learning model.

[0085] It can be understood that the user's body can be evaluated by combining the first data and the second data of the user with the first deep machine learning model. For example, if the user detects the vision of the target, the risk of vision loss of the user can be evaluated; and the corresponding diversion strategy is determined based on the risk of vision loss of the user obtained by the evaluation. Then S102 is:

[0086] Based on the first data and the second data, the risk of vision loss of the target user is determined according to the first deep machine learning model, and a diversion strategy is determined according to the risk of vision loss.

[0087] For example, if the user's detection target is vision, and the assessment result determined by the first deep machine learning model is that the risk of vision loss is high, the user is advised to go to a hospital outpatient clinic for more in-depth treatment; if the risk of vision loss is low, the user is advised to use remote resources to obtain corresponding consulting suggestions, such as looking at the phone less, using eye drops, etc.

[0088] It can be understood that in order to improve the risk assessment results, the first deep machine learning model can be trained in a targeted manner to improve the accuracy of the output results of the first deep machine learning model. The training process of the first deep machine learning model for evaluating user vision is used as an example to illustrate below.

[0089] See also Figure 2 , Figure 2 A flowchart of a remote triage method provided in an embodiment of the present application is shown in FIG. Figure 2 The first deep machine learning model training method includes:

[0090] S201. Obtain a data set, and divide the data set into a myopia group and a non-myopia group.

[0091] The reliability of the first deep machine learning model is ensured by grouping the dataset.

[0092] S202: Perform feature selection on the data set to obtain a feature set.

[0093] Optionally, feature selection is performed through univariate analysis and least absolute shrinkage and selection operator (LASSO) analysis, and feature selection is performed on the dataset in combination with the above analysis methods to reduce the dimension of the dataset and select the most relevant feature subset, thereby improving the accuracy and effectiveness of the first deep machine learning model.

[0094] S203: Perform training based on the feature set to obtain a first deep machine learning model.

[0095] Optionally, the first deep machine learning model is a binary classification model. Since the first deep machine learning model is used to evaluate the user's physical disease risk and determine the diversion strategy based on the risk, and the binary classification model is a machine learning model that divides input data into two categories, for example, the evaluation results can be divided into different categories so that corresponding diversion strategies can be determined based on different categories.

[0096] Optionally, validating the first deep machine learning model through a K-fold cross-validation method helps to avoid overfitting, optimize the prediction model, and build an accurate and robust model.

[0097] Optionally, after obtaining the first data and the second data, the first data and the second data can be stored to establish a profile of the target user, and the user can complete a physical disease risk questionnaire or perform a personal physical examination using an online test tool at a convenient time to enrich the data in the profile. Through the fourth deep machine learning model, the user's body is evaluated based on the changes in the personal physical state of the data in the user profile, an evaluation result is obtained, and corresponding medical advice is provided to the user based on the evaluation result. Then the above-mentioned remote triage method, after S101, also includes:

[0098] Acquire historical information of the user, where the historical information includes the user's medical history of physical diseases, such as the user's medical history of eye diseases;

[0099] Determining the user's physical risk according to a fourth deep machine learning model based on the historical information, the first data, and the second data;

[0100] Determine the appropriate medical advice based on your physical risk.

[0101] In this way, the user's historical information is compared with the user's current physical information to determine the changes in the user's physical information, and the user's physical disease risk is estimated by combining the changes in the user's physical information and the fourth deep machine learning model, and corresponding medical advice is provided to the user based on the physical disease risk.

[0102] See also Figure 3 , is a schematic diagram of the structure of a remote triage device provided in an embodiment of the present application. Figure 3 As shown, the remote triage device 30 provided in this embodiment may include: a processor 340, a memory 341, and a computer program 342 stored in the memory 341 and executable on the processor 340, such as a program corresponding to the remote triage method. When the processor 340 executes the computer program 342, the steps applied to the remote triage method embodiment are implemented, such as Figure 1 to Figure 2 Steps shown.

[0103] Exemplarily, the computer program 342 may be divided into one or more modules / units, one or more modules / units are stored in the memory 341, and executed by the processor 340 to complete the present application. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 342 in the remote triage device 30.

[0104] Those skilled in the art will understand that Figure 3 The remote triage device 30 is merely an example and does not constitute a limitation of the remote triage device 30 , which may include more or fewer components than shown in the figure, or a combination of certain components, or different components.

[0105] The processor 340 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0106] The memory 341 may be an internal storage unit of the remote triage device 30, such as a hard disk or memory of the remote triage device 30. The memory 341 may also be an external storage device of the remote triage device 30, such as a plug-in hard disk, a smart memory card (SMC), a secure digital (SD) card, or a flash card, etc., equipped on an electronic device. Furthermore, the memory 341 may also include both an internal storage unit of the remote triage device 30 and an external storage device.

[0107] The memory 341 is used to store computer programs and other programs and data required by the electronic device. The memory 341 can also be used to temporarily store data that has been output or is to be output.

[0108] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional units as needed, that is, the internal structure of the power supply control device can be divided into different functional units to complete all or part of the functions described above. The functional units in the embodiment can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0109] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0110] An embodiment of the present application provides a chip, including a processor and an interface; the processor is used to read instructions to execute the steps in the above-mentioned various method embodiments.

[0111] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0112] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0113] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

[0114] Finally, it should be noted that the above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A remote triage method, characterized in that: The remote triage method comprises: Acquire first data and second data, wherein the first data is a physical disease assessment result determined based on a physical disease risk questionnaire filled out by a target user, and the second data is a physical disease detection result of the target user; Based on the first data and the second data, a diversion strategy for the target user is determined according to a first deep machine learning model.

2. The remote triage method according to claim 1, characterized in that: The obtaining of the first data and the second data comprises: Obtaining physical disease risk questionnaire data filled out by the target user; The physical disease risk questionnaire data is evaluated according to the second deep machine learning model to obtain the first data and acquire the second data.

3. The remote triage method according to claim 1 or 2, characterized in that: The detection result is obtained by performing a physical examination on the target user through an online testing tool.

4. The remote triage method according to claim 3, characterized in that: The obtaining of the first data and the second data comprises: Acquire the test data of the target user's physical examination through the online testing tool; The detection data is evaluated according to the third deep machine learning model to obtain the second data and acquire the first data.

5. The remote triage method according to claim 1, characterized in that: The physical disease risk questionnaire is a vision risk questionnaire, and the second data is the vision test result of the target user.

6. The remote triage method according to claim 5, characterized in that: The determining, based on the first data and the second data, a diversion strategy for the target user according to a first deep machine learning model includes: Based on the first data and the second data, determining the risk of vision loss of the target user according to a first deep machine learning model; A triage strategy is determined based on the risk of vision loss.

7. The remote triage method according to claim 1, characterized in that: The method further comprises: Acquire historical information of the target user, wherein the historical information includes a medical history of a physical disease of the target user; Determining the physical risk of the target user according to a fourth deep machine learning model based on the first data, the second data, and the historical information; Corresponding medical treatment recommendations are determined based on the physical risks.

8. A remote triage device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the remote triage method according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the remote triage method according to any one of claims 1 to 7 are implemented.

10. A chip, characterized in that: The method comprises a processor and an interface; the processor is used to read instructions to execute the steps of the method according to any one of claims 1 to 7.

Images