WO2020181807A1

WO2020181807A1 - Health prompting method and apparatus, and computer device and storage medium

Info

Publication number: WO2020181807A1
Application number: PCT/CN2019/117258
Authority: WO
Inventors: 绳立淼; 李响; 康延妮; 贾晓雨; 马欣玥; 王帅
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-03-08
Filing date: 2019-11-11
Publication date: 2020-09-17
Also published as: CN110033866A; CN110033866B; SG11202008414VA

Abstract

A health prompting method and apparatus, and a computer device and a storage medium. By inputting health data information and behavior habit information into a neural network model for analysis, a disease type and a degree of association are obtained; if the degree of association is greater than a preset threshold, the health data information and the behavior habit information are input into a feature comparison model corresponding to the disease type for comparative analysis, and preset health prompting information is selected according to an analysis result, so as to prompt a user.

Description

Health reminding method, device, computer equipment and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office, the application number is 201910174003.X, and the invention title is "health reminder methods, devices, computer equipment and storage media" on March 8, 2019. The reference is incorporated in this application.

Technical field

This application relates to the field of medical technology, in particular to a health reminder method, device, computer equipment and storage medium.

Background technique

With the acceleration of social aging and urbanization, residents’ unhealthy lifestyles, etc., the prevalence of Chinese residents’ related diseases such as cardiovascular and cerebrovascular diseases continues to rise, showing a trend of rapid growth among younger age groups and low-income groups, as well as individual gathering trends. Most patients are basically ill at the time of discovery, and there is currently a lack of effective and timely comprehensive monitoring of related diseases. Although related devices, such as smart wearable devices, can monitor the user-related physiological characteristics, they can only measure and analyze the user's single physiological characteristics one by one, and only the relevant single physiological characteristics can be fed back to the user, instead of comprehensive analysis. And processing, so the result of processing is more one-sided.

Summary of the invention

This application provides a health reminder method, device, computer equipment and storage medium, and a health reminder device capable of comprehensive analysis and processing.

In the first aspect, this application provides a computer device, the computer device includes a memory and a processor; the memory is used to store a computer program;

The processor is configured to execute the computer program and realize when the computer program is executed:

Obtain user's health data and behavior information;

Inputting the health data information and the behavior habit information into a neural network model for analysis, so as to obtain the user's disease type and the first degree of association with the disease type;

If the first degree of association is greater than a preset threshold, select a feature comparison model corresponding to the disease type;

Inputting the health data information and the behavioral habit information into the feature comparison model for comparative analysis to obtain the second degree of association between the user and the disease type;

Select preset health prompt information according to the second degree of association to remind the user.

In the second aspect, this application also provides a health reminder device, the health reminder device comprising:

The acquisition module is used to acquire the user's health data information and behavioral habits information;

The first analysis module is configured to input the health data information and the behavioral habit information into a neural network model for analysis to obtain the user's disease type and the first degree of association with the disease type;

The first selection module is configured to select a feature comparison model corresponding to the disease type when the first degree of association is greater than a preset threshold;

The second analysis module is configured to input the health data information and the behavior habit information into the feature comparison model for comparative analysis, so as to obtain the second degree of association between the user and the disease type;

The second selection module is configured to select preset health prompt information according to the second degree of association to remind the user.

In a third aspect, the present application also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor realizes:

Obtain user's health data and behavior information;

In a fourth aspect, this application also provides a health reminder method, and the health reminder method includes:

Obtain user's health data and behavior information;

This application discloses a computer device, a device, and a storage medium. The computer device includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and execute the The computer program realizes: obtain the user's health data information and behavioral habit information; input the health data information and the behavioral habit information into the neural network model for analysis, so as to obtain the user's disease type and the related disease type The first degree of association; if the first degree of association is greater than the preset threshold, select the feature comparison model corresponding to the disease type; input the health data information and the behavior habit information into the feature comparison model Perform comparative analysis to obtain a second degree of association between the user and the disease type; select preset health prompt information according to the second degree of association to remind the user. The computer device can comprehensively analyze the user's health data information and behavioral habit information, and select prompt information to the user according to the analysis result, so that the user can learn his own health status in time.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings needed in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. Ordinary technicians can obtain other drawings based on these drawings without creative work.

FIG. 1 is a schematic diagram of a health reminder scenario provided by an embodiment of the application;

2 is a schematic block diagram of the structure of a computer device according to an embodiment of the application;

3 is a schematic flowchart of steps of a health reminding method provided by an embodiment of the application;

4 is a schematic flowchart of sub-steps of the health reminding method in FIG. 2 provided by an embodiment of the application;

FIG. 5 is a schematic flowchart of the steps of another health reminding method provided by an embodiment of this application;

6 is a schematic flowchart of sub-steps of the health reminding method in FIG. 5 provided by an embodiment of the application;

FIG. 7 is a schematic block diagram of the structure of a health reminder device provided by an embodiment of the application;

FIG. 8 is a schematic block diagram of the sub-module structure of the health reminder device in FIG. 7 provided by an embodiment of the application;

FIG. 9 is a schematic block diagram of the sub-module structure of the health reminder device in FIG. 7 provided by an embodiment of the application;

Fig. 10 is a schematic block diagram of the sub-module structure of the health reminder device in Fig. 7 provided by an embodiment of the application.

detailed description

The technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

The flowchart shown in the drawings is merely an illustration, and does not necessarily include all contents and operations/steps, nor does it have to be executed in the described order. For example, some operations/steps can also be decomposed, combined or partially combined, so the actual execution order may be changed according to actual conditions.

The embodiments of the present application provide a health reminder method, computer equipment, device, and storage medium. The computer equipment, device and storage medium can be used in homes, hospitals, social health, physical examination institutions, government disease prevention departments and other institutions to remind users of health.

Hereinafter, some embodiments of the present application will be described in detail with reference to the accompanying drawings. In the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

FIG. 1 is a schematic diagram of a health reminder scenario provided by an embodiment of the application. Please refer to FIG. 1. The computer device 10, the server 20, the smart wearable device 30, and the smart terminal device 40 have established connections. The computer device 10 may be other servers or terminals, and the smart wearable device 30 may be a smart bracelet or the like. The computer device 10 can obtain the user's health data information and behavior habit information stored by the server 20. The computer device 10 can also obtain the user's health data information monitored by the smart wearable device 30 and obtain the user's behavior habit information monitored by the smart terminal device. Of course, the smart wearable device 30 can be replaced with other terminal devices that can monitor the user's health data information, which is not limited here. After the computer device 10 obtains the health data information and behavior habit information of the user of the server 20 or the smart wearable device 30 or the smart terminal device, it alerts the user to health according to the obtained health data information and behavior habit information.

Based on the application scenario provided in FIG. 1, the use of the computer device 10 provided in the embodiment of the present application for health reminders is described in more detail. Please refer to Fig. 2, which is a schematic block diagram of a computer device according to an embodiment of the present application.

Referring to FIG. 2, the computer device 10 includes a processor 101, a memory, and a network interface 103 connected through a system bus 105. The memory may include a non-volatile storage medium 1021 and an internal memory 1022. The non-volatile storage medium 1021 can store an operating system and a computer program. The computer program includes program instructions. When the program instructions are executed, the processor 101 can perform the prediction of cardiovascular and cerebrovascular diseases.

The processor 101 is used to provide computing and control capabilities and support the operation of the entire computer equipment.

The internal memory 1022 provides an environment for the operation of a computer program in a non-volatile storage medium. When the computer program is executed by the processor, the processor 101 can execute a health reminder.

The network interface 103 is used for network communication, such as sending assigned tasks. Those skilled in the art can understand that the structure shown in FIG. 2 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.

It should be understood that the processor 101 may be a central processing unit (Central Processing Unit, CPU), and the processor may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSPs), and application specific integrated circuits (Application Specific Integrated Circuits). Integrated Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor.

Wherein, the processor 101 is used to run a computer program stored in the memory to implement the following health reminding steps, please refer to FIG. 3, which is implemented when the processor 101 is used to run a computer program stored in the memory Schematic diagram of the steps of health reminder, including the following steps:

Step S101: Obtain the user's health data information and behavior habit information.

Specifically, the user's health data information includes health information such as age, gender, medical history, step counting information, heart rate, pulse, blood pressure and so on. The user's behavior habit information includes: smoking, drinking, eating habits, sleeping habits, exercise habits, etc. The user's health data information can be obtained in real time through a smart wearable device worn by the user, such as a smart bracelet for real-time acquisition, and the smart wearable device can upload the user's health data information to the computer device 10 after obtaining the user's health data information. Or when the computer device 10 needs to obtain the user's health data information, it may send a request for obtaining the user's health data information to the server 20, and the server 20 sends the health data information of the corresponding user to the computer device 10. The server 20 pre-stores the user's health data information examined by a hospital or a medical examination center, the user's health data information examined by a home examination device, or the user's health data information obtained by the user through a smart wearable device.

User behavior and habits information can be obtained according to related applications (APP). For example, exercise habits can be obtained through Gudong Sports APP or Lepower APP, and users’ eating habits can be obtained through Shise APP, etc., or through the user’s third-party payment system. The payment content is obtained through statistical analysis, and the obtained user behavior habit information is actively or passively sent to the computer device 10. Or when the computer device 10 needs to obtain user behavior habit information, it can send a request for obtaining user behavior habit information to the server 20 pre-stored with user behavior habit information, and the server 20 sends the corresponding user behavior habit information to the computer device 10.

Step S102: Input the health data information and the behavior habit information into a neural network model for analysis, so as to obtain the user's disease type and the first degree of association with the disease type.

Specifically, the neural network model is a pre-trained model. Optionally, a large number of health data information and behavioral habit information of patients with various diseases are input to a neural network for model training, and the neural network includes: a convolutional layer, a nonlinear unit, a pooling layer, and a fully connected layer. The feature map is obtained by convolution, and then the feature map is corrected by a non-linear unit, and the corrected feature map is pooled to obtain a dimensionality-reduced feature map. Specifically, it can be through maximum pooling, average pooling and summation Pooling: Finally, the pooled feature map is input to the fully connected layer and the user's disease type and the first degree of association with the disease type are output through the activation function. Disease types include: cardiovascular and cerebrovascular diseases, tumors, gynecological diseases, etc., and the first degree of association with the disease type can be expressed in percentage or other numerical values. The filter of the convolutional layer is updated through output error adjustment until the error is within the target range. At this point, the training of the convolutional neural network prediction model for various types of diseases is completed, and the trained neural network model is obtained.

The user's health data information and user behavior habit information obtained in step S101 are input into the neural network model to obtain the user's disease type and the first degree of association with the disease type. For example, through neural network model analysis, the user’s cardio-cerebrovascular disease and the first degree of association with the cardio-cerebrovascular disease are 60%.

Step S103: If the first degree of association is greater than a preset threshold, select a feature comparison model corresponding to the disease type.

Specifically, when it is found in step S102 that the first degree of association between the user and the disease type is greater than the preset threshold, the feature comparison model corresponding to the disease type is selected to make a detailed assessment of the user's health progress. For example, the foregoing example shows that the degree of association between the user and the cardiovascular and cerebrovascular diseases is 60%, and if the preset threshold is 50%, the feature comparison model corresponding to the cardiovascular and cerebrovascular diseases is selected. When the first degree of association is greater than the preset threshold, it indicates that the user has a relatively large degree of association with the disease type, and may have a greater risk of suffering from this type of disease. It is necessary to further determine which diseases are related to and the degree of correlation. Therefore, when the first degree of association is greater than the preset threshold, the feature comparison model corresponding to the disease type is selected to further analyze the user's health status.

Step S104: Input the health data information and the behavior habit information into the feature comparison model for comparative analysis, so as to obtain a second degree of association between the user and the disease type.

In this embodiment, after the processor 101 implements the feature comparison model corresponding to the selected disease type, it is also used to implement the input of the health data information and the behavior habit information into the feature comparison model for comparison. Analysis to obtain a second degree of association between the user and the disease type. For example, the foregoing example selects the feature comparison model corresponding to the cardio-cerebrovascular disease, and the processor 101 realizes inputting the health data information and the behavior habit information into the feature comparison model corresponding to the cardio-cerebrovascular disease. When the processor 101 realizes that the health data information and the behavioral habit information are input into the feature comparison model for comparison and analysis, so as to obtain the second degree of association between the user and the disease type, it is also specifically Used to implement the sub-steps shown in Figure 4.

Specifically, referring to FIG. 4, FIG. 4 is an example of inputting the health data information and the behavioral habit information into the feature comparison model selected in step S103 for comparative analysis to obtain the second degree of association between the user and the disease type Schematic flowchart, step S104 includes the following sub-steps:

Step S1041. The index information in the health data information is compared with the pre-stored normal index information to filter out abnormal index information in the health data information.

In this embodiment, the index information includes index items and corresponding characteristic values. The index items include: blood pressure, heart rate, total cholesterol, low-density lipoprotein cholesterol, serum triglycerides, etc., and the corresponding characteristic values are the above-mentioned index items. For example, the characteristic value corresponding to blood pressure is 90/60mmHg～130/90mmHg. Optionally, the index item can also be an image, such as an electrocardiogram, a CT image, etc., and the corresponding feature value can be image feature information, such as a normal electrocardiogram. The P wave time is generally less than 0.12s, and the P wave amplitude is generally in the limb leads. Less than 0.25mV, chest leads are generally less than 0.2mV. As described in Table 1, normal index information is pre-stored in the computer device 10 in the form of a data table.

Table 1 Normal index information data table

The acquired index information in the user's health data information is compared with the pre-stored normal index information to screen out abnormal index information in the health data information. The index information in the user's health data information also includes index items and corresponding characteristic values. For example, if the index item in the index information in the user's health data information is blood pressure, and the corresponding characteristic value, that is, the blood pressure value is 140/90mmHg, then the abnormal index information in the health data information is filtered out as the blood pressure index item . Of course, according to the actual situation of the indicator information in the user's health data information, the selected abnormal indicator information of the user may be one or more items.

Step S1042, according to the indicator items of the abnormal indicator information, screen out the associated diseases from the pre-stored list of disease types.

Specifically, as in the foregoing example of cardiovascular and cerebrovascular diseases, the pre-stored list of types of cardiovascular and cerebrovascular diseases is shown in Table 2. Table 2 stores various types of cardiovascular and cerebrovascular diseases and various index information. The index information includes index items. And the corresponding characteristic value. For example, the index items and characteristic values corresponding to the disease type of hypertension are: age and corresponding age range, weight and corresponding weight range, genetic history and characteristic values (1 means a genetic history, 0 means no genetic history), etc. .

Table 2 List of types of cardiovascular and cerebrovascular diseases

The cardio-cerebrovascular disease of the corresponding type is selected from a pre-stored cardio-cerebrovascular disease type list according to the index item of the abnormal index information. For example, if the user’s abnormal indicators are blood pressure and total cholesterol, the cardio-cerebrovascular disease type that contains at least one of the two indicators, blood pressure or total cholesterol, is selected from the pre-stored cardio-cerebrovascular disease type list As shown in Table 2, the types of cardiovascular and cerebrovascular diseases that contain the index items blood pressure or total cholesterol are hypertension and hyperlipidemia. In this way, the cardio-cerebrovascular disease associated with the user is screened out, that is, the specific type of the cardio-cerebrovascular disease.

Step S1043: Compare the feature values of the health data information and the behavioral habit information with the pre-stored feature values corresponding to the associated diseases to obtain a comparison result.

Specifically, after the processor 101 implements step S1042 to screen out the types of cardiovascular and cerebrovascular diseases that the user may have, the processor 101 then implements to compare the health data information and the feature values corresponding to the behavior habit information with all pre-stored The feature values corresponding to the related diseases are compared to obtain the comparison result.

For example, the obtained feature values of the user's health data information and behavioral habit information are: X ₁ , X ₂ ......X _n , X ₁ , X ₂ ......X _n represents the corresponding feature The numerical value of the value, for example, X ₁ means age 40 years old, X ₂ means blood pressure 140/90mmHg, X _n means not drinking, it can be represented by 0. The pre-stored health data information of related diseases (such as high blood pressure, hyperlipidemia) and the characteristic values corresponding to behavioral habit information are recorded as Y ₁ , Y ₂ ...... Y _n , Y ₁ , Y ₂ .. .... Y _n is a numerical range, for example, Y ₁ means that the corresponding age range is >=35 years old, Y ₂ means that the corresponding blood pressure range is >=140/90mmHg,..., Y _n means drinking The frequency is >= 2 times/day. Compare X ₁ , X ₂ ...... X _n with Y ₁ , Y ₂ ...... Y _n , C ₁ , C ₂ ...... C _{n are} recorded as the comparison result value, When X _i ∈ Y _i , C _i = 1, when

When C _i = 0, where 1≤i≤n. For another example, X _n means not drinking, X _n is 0, and Y _n means that the frequency of drinking >= 2 times/day, then C _n =0.

Step S1044: Determine a second degree of association between the user and the associated disease according to the comparison result.

According to the comparison result, the second degree of association between the user and the associated disease is calculated using an association formula, and the association formula is:

Among them, the comparison result

a _j represents a second degree of association of the user with a disease associated with j, n is the number of characteristic values represents, X _i represents the i-th feature value information to the health data and information corresponding to the behavior, Y _i represents a predetermined The i-th characteristic value corresponding to the stored cardio-cerebrovascular disease type, λ _i is the weight of the comparison result C _i , 0≤λ _i ≤1. λ _i can be specifically set according to the corresponding health data information and behavior habits to the extent of the impact of this type of disease. In this way, a comprehensive and specific analysis of the user's health data information and behavioral habits information is combined with the user's degree of association with specific related diseases.

Step S105: Select preset health prompt information according to the second degree of association to remind the user.

Specifically, the processor 101 in this embodiment implements selection of preset health prompt information according to the second degree of association to remind the user. The preset health reminder information can be stored in the form of a list, including related diseases, the second degree of relevance, and the health reminder information content, as shown in Table 3:

Table 3 Correspondence between the second degree of association and the health prompt information

As in the previous example, if the second degree of association between the user and high blood pressure is calculated to be 65%, then select the health reminder message "Hypertensive risk level is higher, it is recommended to go to the hospital for examination..." in the corresponding list . The computer device 10 may send the selected health reminder information to the smart wearable device 30 and/or the smart terminal device 40 of the user. Specifically, it can be sent via APP, or sent via email, SMS, etc. And can remind users regularly, such as voice reminders, text reminders, etc.

In this embodiment of the application, the user’s health data information and behavioral habit information are analyzed through the neural network model to obtain the user’s disease type and the first degree of association, and then the feature comparison model corresponding to the disease type is selected to analyze the user’s health data again Information and behavioral habits information, the specific related diseases under the above-mentioned disease types and the second degree of association with the related diseases are obtained, and health reminder information is generated according to the second degree of association to remind the user. In this way, by comprehensively analyzing the user's health data information and behavioral habit information, the degree of association between the user and the relevant disease is obtained, and the user is reminded in time, so that the user can understand their own health status in time and play a role in timely prevention of related diseases.

In another embodiment, the processor of the computer device 10 runs a computer program stored in the memory to implement the health reminder steps shown in FIG. 5, and FIG. 5 shows that the processor 101 is used to run the computer program stored in the memory. Please refer to Figure 5 for the step flow diagram of the health reminder implemented by the computer program in the computer program, which specifically includes the following steps:

Step S201: Obtain the user's health data information and behavior habit information.

Specifically, the user's health data information includes health information such as age, gender, medical history, step counting information, heart rate, pulse, blood pressure and so on. The user's behavior habit information includes: smoking, drinking, eating habits, sleeping habits, exercise habits, etc.

Optionally, in this embodiment, the processor is implementing the acquisition of the user's health data information and behavioral habit information, so as to determine the sampling time or sampling frequency according to the user's current exercise state and/or health state; The sampling time or sampling frequency obtains the user's health data information and behavior habit information.

For example, adjust the collection time or sampling frequency according to the current user's motion state. For example, the smart terminal device 40 obtains exercise information through the exercise APP to determine whether it is exercising. If it is exercise, it can be divided into the acquisition of the user’s health data and behavior information during exercise, and the acquisition of the user’s health half an hour after exercise Data information and behavioral habits information, so that the information during and after exercise can be compared and analyzed.

For another example, when an indicator of the user's health data information monitored in real time by the smart wearable device 30 suddenly changes, it means that the user may be abnormal, and the sampling frequency will be increased. For example, if there is a sudden change in heart rate or blood pressure, then the sampling frequency should be increased. For example, the original sampling frequency was once a day. When the health is abnormal, the frequency can be increased three times a day or once every hour, etc. Then obtain the user's health data information and behavioral habit information according to the increased sampling frequency, so that the user's health data information and behavioral habit information can be obtained in real time according to the user's health status, which can achieve the purpose of real-time monitoring and analysis.

Step S202: Input the health data information and the behavior habit information into a neural network model for analysis to obtain the user's disease type and the first degree of association with the disease type.

The user health data information and user behavior habit information obtained in step S201 are input into a pre-trained neural network model to obtain the user's disease type and the first degree of association with the disease type. For example, through neural network model analysis, the user’s cardio-cerebrovascular disease and the first degree of association with the cardio-cerebrovascular disease are 60%.

Step S203: If the first degree of association is greater than a preset threshold, select a feature comparison model corresponding to the disease type.

Specifically, when the analysis in step S202 shows that the first degree of association between the user and the disease type is greater than the preset threshold, the feature comparison model corresponding to the disease type is selected to make a detailed assessment of the user's health progress. For example, the foregoing example shows that the degree of association between the user and the cardiovascular and cerebrovascular diseases is 60%, and if the preset threshold is 50%, the feature comparison model corresponding to the cardiovascular and cerebrovascular diseases is selected.

Step S204: Input the health data information and the behavior habit information into the feature comparison model for comparative analysis, so as to obtain a second degree of association between the user and the disease type.

In this embodiment, the processor 101 is implementing the input of the health data information and the behavioral habit information into the feature comparison model for comparison and analysis, so as to obtain the first occurrence of the user suffering from the corresponding type of cardiovascular and cerebrovascular diseases. In the case of a probability, it is also specifically used to implement the sub-steps shown in FIG. 6. Specifically, referring to FIG. 6, FIG. 6 is a schematic flowchart of inputting the health data information and the behavioral habit information into the feature comparison model for comparison and analysis to obtain the second degree of association. Step S204 includes the following sub-steps:

Step S2041. The index information in the health data information is compared with the pre-stored normal index information to filter out abnormal index information in the health data information.

Step S2042, according to the indicator items of the abnormal indicator information, screen out the associated diseases from the pre-stored list of disease types.

Step S2043: Compare the feature values of the health data information and the behavioral habit information with the pre-stored feature values corresponding to the associated diseases to obtain a comparison result.

The feature values of the health data information and the behavioral habit information are compared with the pre-stored feature values corresponding to the associated disease, and if the feature values of the health data information and the behavioral habit information fall into When the characteristic value corresponding to the associated disease is reached, the comparison result can be set to 1, otherwise it is 0.

Step S2044: Determine the weight of the comparison result according to the degree of influence of the health data information and the behavior habit information on the associated disease.

Specifically, the health data information and the behavior habit information have multiple index items, and each index item has a different degree of influence on related diseases. For example, for hypertension, the blood pressure in the health data information One index item has a greater impact on hypertension than other index items. Therefore, when comparing the characteristic values of blood pressure, the weight of the comparison result can be set to 0.8, and the comparison result of other items can be set to 0 or 0.2 And so on... The weight is a value greater than or equal to 0 and less than or equal to 1.

Step S2045: Determine a second degree of association between the user and the associated disease according to the comparison result.

Specifically, according to the comparison result, an association formula is used to calculate the second degree of association between the user and the associated disease, and the association formula is:

Among them, the comparison result

a _j represents a second degree of association of the user with a disease associated with j, n is the number of characteristic values represents, X _i represents the i-th feature value information to the health data and information corresponding to the behavior, Y _i represents a predetermined The i-th characteristic value corresponding to the stored cardio-cerebrovascular disease type, λ _i is the weight of the comparison result C _i , 0≤λ _i ≤1. λ _i is the weight of the comparison result C _i , which can be specifically set according to the corresponding health data information and behavior habits. In this way, a comprehensive and specific analysis of the user's health data information and behavioral habits information is combined with the user's degree of association with specific related diseases.

Step S205: Determine the user's disease risk according to the second degree of association.

Specifically, for example, if the second degree of association is above 80%, it is recorded as a high-risk category. For example, it can be divided according to the following list 4.

Table 4 Correspondence between the second degree of association and disease risk

第二关联程度Second degree of relevance	疾病风险Disease risk
a _j≥80％ a _j ≥80%	高风险high risk
60％≤a _j＜80％ 60%≤a _j ＜80%	较高风险 Higher risk
50％≤a _j＜60％ 50%≤a _j ＜60%	一般风险General risk
a _j＜50％ a _j ＜50%	低风险low risk

Step S206: Select a preset health report according to the disease risk, and send the health report to the user.

Specifically, the disease risk corresponds to a preset health report template one to one, as described in Table 5, the preset health report is selected according to the disease risk.

Table 5 Correspondence between disease risk and health report

疾病disease	疾病风险Disease risk	健康报告Health report
高血压hypertension	高风险high risk	高血压健康报告1Hypertension Health Report 1
高血压hypertension	较高风险Higher risk	高血压健康报告2Hypertension Health Report 2
高血压hypertension	一般风险General risk	高血压健康报告3Hypertension Health Report 3
……...	……...	……...

If the risk of hypertension is a higher risk, select Hypertension Health Report 2. Optionally, the health report can describe the risk factors that affect the prediction results to inform users. For example, the heart rate is 140bmp, which is the main factor leading to myocardial infarction and coronary heart disease. If the heart rate is normal 60-100bmp, the risk of myocardial infarction and coronary heart disease can reduce a certain probability. It is recommended to seek medical treatment Or adjust the heart rate in other ways.

The computer device 10 may send the selected health report to the smart wearable device 30 and/or the smart terminal device 40 of the user. In order to remind the user in time, the user can also check it at any time.

Step S207: Modify the health report according to the user behavior habit information, and send the modified health report to the user.

Specifically, after selecting the preset health report, in order to improve the health report, the health report can be modified according to the user's behavior and habits, reminding the user of the matters that need to be paid attention to (such as living habits, eating habits, exercise habits, etc.), and then Then send it to the user, so that after receiving the health report, the user can pay attention to living habits, exercise habits, etc. as required to reduce the risk and achieve the effect of effective prevention.

This application also provides a health reminder device. Please refer to FIG. 7. FIG. 7 is a schematic structural diagram of a health reminder device 50 provided in this application. The health reminder device 50 is used to perform any of the aforementioned health reminder methods. Among them, the health reminder device 50 can be configured in a server or a terminal. Among them, the server can be an independent server or a server cluster. The terminal can be an electronic device such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device. Please refer to FIG. 7, the health reminding device 50 includes:

The obtaining module 51 is used to obtain the user's health data information and behavioral habit information;

The first analysis module 52 is configured to input the health data information and the behavioral habit information into a neural network model for analysis to obtain the user's disease type and the first degree of association with the disease type.

The first selection module 53 is configured to select a feature comparison model corresponding to the disease type if the first degree of association is greater than a preset threshold;

The second analysis module 54 is configured to input the health data information and the behavioral habit information into the feature comparison model for comparative analysis, so as to obtain the second degree of association between the user and the disease type;

The second selection module 55 is configured to select preset health prompt information according to the second degree of association to remind the user.

Referring to FIG. 8, in the embodiment of the present application, the second analysis module 54 further includes:

The first comparison sub-module 541 is configured to compare the index information in the health data information with pre-stored normal index information to screen out abnormal index information in the health data information. The index information includes index items and corresponding characteristic values; a first screening sub-module 542, configured to screen out related diseases from a list of disease types stored in advance according to the index items of the abnormal index information; second comparison The sub-module 543 compares the characteristic values of the health data information and the behavioral habit information with the pre-stored characteristic values corresponding to the associated diseases to obtain a comparison result;

The first determining sub-module 544 determines the second degree of association between the user and the associated disease according to the comparison result.

The first determination sub-module 544 also includes a calculation sub-module 5441, configured to calculate a second degree of association between the user and the associated disease by using an association formula according to the comparison result, and the association formula is:

Among them, the comparison result

a _j represents a second degree of association of the user with a disease associated with j, n is the number of characteristic values represents, X _i represents the health data and the information of the i-th feature value corresponding to behavior information, Y _i Represents the i-th feature value corresponding to the pre-stored associated disease j, λ _i is the weight of the comparison result C _i , 0≤λ _i ≤1.

In another embodiment, the second analysis module 54 further includes a second determination sub-module 545, configured to determine the comparison result according to the health data information and the degree of influence of the behavior habit information on the associated disease The weight of.

Please refer to FIG. 9, which is a schematic block diagram of the second selection module 55. The second selection module 55 also includes:

The third determining submodule 551 is used to determine the user’s disease risk according to the second degree of association,

The first selection submodule 552 is configured to select a preset health report according to the disease risk, and send the health report to the user.

Optionally, the second selection module 55 further includes: a modification module 553, configured to modify the health report according to the user behavior habit information.

Please refer to FIG. 10, which is a schematic block diagram of the structure of the obtaining module 51. The obtaining module 51 further includes:

The fourth determining sub-module 511 is configured to determine the sampling time or the sampling frequency according to the user's current motion state and/or health state;

The obtaining sub-module 512 is configured to obtain the user's health data information and behavior habit information according to the sampling time or sampling frequency.

It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the health reminding device described above can refer to the corresponding process in the foregoing computer device embodiment, which will not be omitted here. Repeat.

The embodiments of the present application also provide a computer-readable storage medium, the computer-readable storage medium stores a computer program, the computer program includes program instructions, and the processor executes the program instructions to implement the above Describe the steps of the health reminder method provided.

The computer-readable storage medium may be the internal storage unit of the computer device described in the foregoing embodiment, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk equipped on the computer device, a smart memory card (Smart Media Card, SMC), or a Secure Digital (SD) ) Card, Flash Card, etc.

The above are only specific implementations of this application, but the protection scope of this application is not limited to this. Anyone familiar with the technical field can easily think of various equivalents within the technical scope disclosed in this application. Modifications or replacements, these modifications or replacements shall be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

A computer device, wherein the computer device includes a memory and a processor; the memory is used to store a computer program;

The processor is configured to execute the computer program and realize when the computer program is executed:

Obtain user's health data and behavior information;

Inputting the health data information and the behavior habit information into a neural network model for analysis, so as to obtain the user's disease type and the first degree of association with the disease type;

If the first degree of association is greater than a preset threshold, select a feature comparison model corresponding to the disease type;

The index information in the health data information is compared with the pre-stored normal index information to filter out abnormal index information in the health data information. The index information includes index items and corresponding characteristic values ；

Screening out related diseases from a pre-stored list of disease types according to the indicator items of the abnormal indicator information;

Comparing the feature values of the health data information and the behavioral habit information with the feature values corresponding to the associated diseases stored in advance to obtain a comparison result;

According to the comparison result, the second degree of association between the user and the associated disease is calculated using an association formula, and the association formula is:

Among them, the comparison result
a j represents a second degree of association of the user with a disease associated with j, n is the number of characteristic values represents, X i represents the health data and the information of the i-th feature value corresponding to behavior information, Y i Represents the i-th characteristic value corresponding to the pre-stored associated disease j, λ i is the weight of the comparison result C i , 0≤λ i ≤1;

Select preset health prompt information according to the second degree of association to remind the user.
The computer device according to claim 1, wherein the processor is configured to implement the following when executing the acquiring health data information and behavioral habit information of the user:

Determine the sampling time or sampling frequency according to the user's current exercise status and/or health status;

Obtain health data information and behavior habit information of the user according to the sampling time or sampling frequency.
4. The computer device according to claim 1, wherein the processor is further configured to calculate the second degree of association between the user and the associated disease according to the comparison result using an association formula before executing achieve:

The weight value of the comparison result is determined according to the degree of influence of the health data information and the behavior habit information on the associated disease.
The computer device according to claim 1, wherein when the processor executes selecting preset health prompt information according to the second degree of association to remind the user, the processor is configured to implement:

Determine the user’s disease risk according to the second degree of association,

Select a preset health report according to the disease risk, and send the health report to the user.
The computer device according to claim 4, wherein, after the processor executes the selection of a preset health report according to the disease risk, it is further configured to implement:

Modify the health report according to the user's behavior habit information.
A health reminder device, wherein the health reminder device comprises:

The acquisition module is used to acquire the user's health data information and behavioral habits information;

The first analysis module is configured to input the health data information and the behavioral habit information into a neural network model for analysis to obtain the user's disease type and the first degree of association with the disease type;

The first selection module is configured to select a feature comparison model corresponding to the disease type when the first degree of association is greater than a preset threshold;

The second analysis module is used to compare the index information in the health data information with pre-stored normal index information to screen out abnormal index information in the health data information, where the index information includes Index items and corresponding characteristic values; and the index items used to screen out the associated diseases from a pre-stored list of disease types according to the abnormal index information; and used to combine the health data information and the behavior The feature value of the habit information is compared with the feature value corresponding to the associated disease stored in advance to obtain a comparison result; and used to calculate the user and the associated disease based on the comparison result using an association formula The second degree of association, the association formula is:

Among them, the comparison result
a j represents a second degree of association of the user with a disease associated with j, n is the number of characteristic values represents, X i represents the health data and the information of the i-th feature value corresponding to behavior information, Y i Represents the i-th characteristic value corresponding to the pre-stored associated disease j, λ i is the weight of the comparison result C i , 0≤λ i ≤1;

The second selection module is configured to select preset health prompt information according to the second degree of association to remind the user.
The health reminder device according to claim 6, wherein the acquiring module is further used for:

Determine the sampling time or sampling frequency according to the user's current exercise status and/or health status;

Obtain health data information and behavior habit information of the user according to the sampling time or sampling frequency.
The health reminder device according to claim 6, wherein the second selection module is further used for:

The weight value of the comparison result is determined according to the degree of influence of the health data information and the behavior habit information on the associated disease.
The health reminder device according to claim 6, wherein the second selection module is further used for:

Determine the user’s disease risk according to the second degree of association,

Select a preset health report according to the disease risk, and send the health report to the user.
The health reminder device according to claim 9, wherein the health reminder device further comprises:

The modification module is used to modify the health report according to the user behavior habit information.
A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor realizes:

Obtain user's health data and behavior information;

Inputting the health data information and the behavior habit information into a neural network model for analysis, so as to obtain the user's disease type and the first degree of association with the disease type;

If the first degree of association is greater than a preset threshold, select a feature comparison model corresponding to the disease type;

The index information in the health data information is compared with the pre-stored normal index information to filter out abnormal index information in the health data information. The index information includes index items and corresponding characteristic values ；

Screening out related diseases from a pre-stored list of disease types according to the indicator items of the abnormal indicator information;

Comparing the feature values of the health data information and the behavioral habit information with the feature values corresponding to the associated diseases stored in advance to obtain a comparison result;

According to the comparison result, the second degree of association between the user and the associated disease is calculated using an association formula, and the association formula is:

Among them, the comparison result
a j represents a second degree of association of the user with a disease associated with j, n is the number of characteristic values represents, X i represents the health data and the information of the i-th feature value corresponding to behavior information, Y i Represents the i-th characteristic value corresponding to the pre-stored associated disease j, λ i is the weight of the comparison result C i , 0≤λ i ≤1;

Select preset health prompt information according to the second degree of association to remind the user.
11. The computer-readable storage medium according to claim 11, wherein, when the processor executes said obtaining the user's health data information and behavioral habit information, it is configured to:

Determine the sampling time or sampling frequency according to the user's current exercise status and/or health status;

Obtain health data information and behavior habit information of the user according to the sampling time or sampling frequency.
The computer-readable storage medium according to claim 11, wherein the processor is further configured to implement the second degree of association between the user and the associated disease before executing the determination according to the comparison result :

The weight value of the comparison result is determined according to the degree of influence of the health data information and the behavior habit information on the associated disease.
11. The computer-readable storage medium according to claim 11, wherein, when the processor executes selecting preset health prompt information according to the second degree of association to remind the user, the processor is configured to implement:

Determine the user’s disease risk according to the second degree of association,

Select a preset health report according to the disease risk, and send the health report to the user.
14. The computer-readable storage medium according to claim 14, wherein after the processor executes the selection of a preset health report according to the disease risk, it is further configured to implement:

Modify the health report according to the user's behavior habit information.
A health reminder method, the health reminder method includes:

Obtain user's health data and behavior information;

Inputting the health data information and the behavior habit information into a neural network model for analysis, so as to obtain the user's disease type and the first degree of association with the disease type;

If the first degree of association is greater than a preset threshold, select a feature comparison model corresponding to the disease type;

The index information in the health data information is compared with the pre-stored normal index information to filter out abnormal index information in the health data information. The index information includes index items and corresponding characteristic values ；

Screening out related diseases from a pre-stored list of disease types according to the indicator items of the abnormal indicator information;

Comparing the feature values of the health data information and the behavioral habit information with the feature values corresponding to the associated diseases stored in advance to obtain a comparison result;

According to the comparison result, the second degree of association between the user and the associated disease is calculated using an association formula, and the association formula is:

Among them, the comparison result
a j represents a second degree of association of the user with a disease associated with j, n is the number of characteristic values represents, X i represents the health data and the information of the i-th feature value corresponding to behavior information, Y i Represents the i-th characteristic value corresponding to the pre-stored associated disease j, λ i is the weight of the comparison result C i , 0≤λ i ≤1;

Select preset health prompt information according to the second degree of association to remind the user.
The health reminder method according to claim 16, wherein said obtaining the user's health data information and behavioral habit information comprises:

Determine the sampling time or sampling frequency according to the user's current exercise status and/or health status;

Obtain health data information and behavior habit information of the user according to the sampling time or sampling frequency.
The health reminder method according to claim 16, wherein before determining the second degree of association between the user and the associated disease according to the comparison result, the method further comprises:

The weight value of the comparison result is determined according to the degree of influence of the health data information and the behavior habit information on the associated disease.
The health reminder method according to claim 16, wherein the selecting preset health reminder information according to the second degree of association to remind the user comprises:

Determine the user’s disease risk according to the second degree of association,

Select a preset health report according to the disease risk, and send the health report to the user.
The health reminder method according to claim 19, wherein, after selecting a preset health report according to the disease risk, the method further comprises:

Modify the health report according to the user's behavior habit information.