Health management intervention method and device, electronic equipment and nonvolatile storage medium

Abstract

The invention discloses a health management intervention method and device, electronic equipment and a nonvolatile storage medium. The method comprises the following steps: acquiring health state data of an intervention object; determining a risk portrait type corresponding to the intervention object and an individual risk factor according to the health state data, and determining a health management plan corresponding to the intervention object according to the individual risk factor; determining the video type of an intervention video planned to be pushed according to the individual risk factor, and determining a pushing parameter corresponding to each video type according to the risk portrait type and the completion condition of the health management plan; and sending the intervention video of the video type to a terminal device of the intervention object according to the push parameter. According to the method and the device, the technical problem of insufficient accuracy and individuation of the health propaganda video pushed for the cardiovascular disease high-risk object in the related technology is solved.

Description

Technical Field

[0001] This application relates to the technical field of health management. Specifically, it relates to a health management intervention method, device, electronic device, and non-volatile storage medium. Background Art

[0002] Regarding cardiovascular problems, in addition to improving genetic and environmental factors, it is also necessary to take active lifestyle interventions, such as increasing physical activity, having a reasonable diet, quitting smoking and limiting alcohol, and controlling weight. Therefore, a way can be adopted to develop a health plan for high-risk subjects with cardiovascular diseases and push health promotion videos to manage and intervene in their lifestyles. However, due to the high incidence, complexity of cardiovascular problems, and the diversity of the population, the health management effect on high-risk subjects for such problems in related technologies is not good. For example, there are problems such as insufficient accuracy and personalization in pushing health promotion videos to high-risk subjects.

[0003] In response to the above problems, no effective solution has been proposed yet. Summary of the Invention

[0004] Embodiments of this application provide a health management intervention method, device, electronic device, and non-volatile storage medium to at least solve the technical problem of insufficient accuracy and personalization of the health promotion videos pushed to high-risk subjects with cardiovascular diseases in related technologies.

[0005] According to one aspect of the embodiments of this application, a health management intervention method is provided, including: obtaining health status data of an intervention object, where the health status data is used to characterize the physiological state and behavioral status of the intervention object; based on the health status data, determining the risk profile type and individual risk factors corresponding to the intervention object, and based on the individual risk factors, determining the health management plan corresponding to the intervention object, where the risk profile type is the group category to which the intervention object belongs and has the most similar health characteristics and cardiovascular disease risk levels, and the individual risk factors are the health risk factors that the intervention object has and will cause cardiovascular diseases; based on the individual risk factors, determining the video type of the intervention video to be pushed, and based on the risk profile type and the completion status of the health management plan, determining the push parameters corresponding to each video type; sending the intervention video of the video type to the terminal device of the intervention object according to the push parameters.<##

[0006] Optionally, determining the risk profile type corresponding to the intervention object includes: obtaining a first data set, where the first data set contains the health status data of multiple cardiovascular disease individual objects, and the health status data includes at least one of the following: blood pressure data, blood glucose data, blood lipid data, height and weight data, waist circumference data, smoking frequency data, alcohol consumption frequency data, exercise frequency data, diet status data, sleep status data, medication compliance data, electrocardiogram data, ultrasonic imaging data; clustering the health status data of the individual objects in the first data set to obtain multiple clustering clusters, where each clustering cluster corresponds to a risk profile type; determining the similarity parameters between the feature vector corresponding to the health status data of the intervention object and the feature vectors in each clustering cluster, and determining the risk profile type corresponding to the clustering cluster with the largest similarity parameter as the risk profile type corresponding to the intervention object.

[0007] Optionally, clustering the health status data of the individual objects in the first data set includes: converting the health status data of the individual objects into corresponding feature vectors, using a first clustering algorithm to perform preliminary clustering on the feature vectors corresponding to the individual objects in the first data set, and determining the first quantity of the clustering categories obtained after the preliminary clustering, where the first clustering algorithm includes: the umbrella clustering algorithm; randomly sampling from the first data set in a replacement manner to generate multiple second data sets, where the number of samples in the second data set is the same as the number of samples in the first data set; randomly selecting the first quantity of initial clustering centers in the second data set, and using a second clustering algorithm to perform clustering based on the initial clustering centers, where each second data set obtains the first quantity of clustering clusters after clustering, and the second clustering algorithm includes: the mini-batch K-means clustering algorithm; converting the feature vectors in the clustering clusters corresponding to each second data set into classification description texts with medical significance, and determining multiple risk profile types based on the classification description texts.

[0008] Optionally, determining the health management plan corresponding to the intervention object according to individual risk factors includes: determining the health standards corresponding to the health status data of the intervention object, and determining the health status data items that do not meet the health standards as individual risk factors; according to the intervention cycle corresponding to the intervention object, determining the phased intervention objectives of the individual risk factors to obtain a preliminary health management plan, where the intervention objectives include at least one of the following: blood pressure management objective, blood sugar management objective, blood lipid management objective, weight management objective, smoking cessation objective, alcohol restriction objective, exercise objective; sending the preliminary health management plan to the terminal device of the medical management personnel in the area corresponding to the intervention object, where the medical management personnel include the resident doctors in the community or village where the intervention object is located, and the medical management personnel are used to adjust the preliminary health management plan according to their understanding of the daily lifestyle and physical condition of the intervention object; obtaining the adjusted health management plan returned by the terminal device of the medical management personnel, and sending the adjusted health management plan to the terminal device of the intervention object.

[0009] Optionally, determining the push parameters corresponding to each video type includes: determining the risk level corresponding to the risk profile type to which the intervention object belongs, and the influence coefficients corresponding to the health status data items in the risk profile type, where the risk level is used to characterize the probability of people belonging to the risk profile type suffering from cardiovascular diseases, and the influence coefficient is used to characterize the influence degree of each health status data item on causing cardiovascular diseases for people belonging to the risk profile type; according to the risk level, determining the total number of intervention videos pushed to the intervention object within a video push cycle; according to the influence coefficients of the health status data corresponding to the individual risk factors, determining the push weights of the video types corresponding to each individual risk factor of the intervention object, where the influence coefficient is positively correlated with the push weight; according to the total number of intervention videos and the push weights, determining the initial push parameters of each video type, where the push parameters include at least one of the following: the push quantity, push frequency, and push priority of the intervention videos of the video type.

[0010] Optionally, the method further includes: monitoring the completion status and progress of each intervention objective corresponding to the intervention cycle in the health management plan, where the completion status includes: over-completion, completion, and non-completion; using a prediction model to predict the management progress of each individual risk factor of the intervention object in the next intervention cycle based on the completion status and progress of the intervention objective in the current intervention cycle, and determining the intervention objective for the next intervention cycle based on the prediction result, where the prediction model is trained based on the health status data of the intervention object and the completion status of the intervention objective in the historical intervention cycle; and using a causal inference model to analyze the completion status and progress of the intervention objective in the current intervention cycle, as well as the acceptance tendency data of the intervention object for the intervention measures, to obtain the causal effect relationship between the intervention measures and the completion status, and adjusting the push parameters of the video type based on the causal effect relationship, where the intervention measures include: pushing intervention videos to the intervention object, and the acceptance tendency data includes at least one of the following: the number of views of the intervention video, the duration, whether it is liked, and whether it is collected.

[0011] Optionally, the method further includes: in the case where the intervention objective in the current intervention cycle is not completed, obtaining the reasons for non-completion fed back by the terminal device of the medical management personnel, where the reasons for non-completion include at least one of the following: the target is set too high, there is a lack of sufficient support or resources, personal health status changes, lack of motivation or poor compliance, and external environmental factors; adjusting the intervention objective based on the reasons for non-completion, and obtaining the corresponding intervention video and pushing it to the terminal device of the intervention object according to the reasons for non-completion.

[0012] Optionally, the method further includes: determining the geographical area where the intervention object is located, and obtaining the geographical characteristics and climate information of the geographical area, where the geographical characteristics include at least one of the following: topographical and morphological characteristics, dietary culture characteristics, and the climate information includes at least one of the following: temperature data, humidity data, seasonal change conditions, and extreme weather frequency; adjusting the video content of the intervention video and the intervention objective in the health management plan based on the geographical characteristics and climate information.

[0013] According to another aspect of the embodiments of the present application, a health management intervention device is further provided, including: a data acquisition module, configured to acquire health status data of an intervention object, where the health status data is used to characterize the physiological state and behavior status of the intervention object; a plan determination module, configured to determine the risk profile type and individual risk factors corresponding to the intervention object according to the health status data, and determine the health management plan corresponding to the intervention object according to the individual risk factors, where the risk profile type is the group category to which the intervention object belongs and has the most similar health characteristics and cardiovascular disease risk levels, and the individual risk factors are the health risk factors that the intervention object has and will cause cardiovascular disease; a push setting module, configured to determine the video type of the intervention video to be pushed according to the individual risk factors, and determine the push parameters corresponding to each video type according to the risk profile type and the completion status of the health management plan; a video intervention module, configured to send the intervention video of the video type to the terminal device of the intervention object according to the push parameters.

[0014] According to yet another aspect of the embodiments of the present application, an electronic device is further provided, including: a memory and a processor, where the processor is configured to run a program stored in the memory, and when the program runs, it executes the health management intervention method.

[0015] According to still another aspect of the embodiments of the present application, a non-volatile storage medium is further provided, where the non-volatile storage medium includes a stored computer program, and the device where the non-volatile storage medium is located executes the health management intervention method by running the computer program.

[0016] According to still another aspect of the embodiments of the present application, a computer program product is further provided, including a computer program, and when the computer program is executed by a processor, it implements the steps of the health management intervention method.

[0017] In the embodiments of the present application, health status data of an intervention object is acquired, where the health status data is used to characterize the physiological state and behavior status of the intervention object; according to the health status data, a risk portrait type and individual risk factors corresponding to the intervention object are determined, and according to the individual risk factors, a health management plan corresponding to the intervention object is determined, where the risk portrait type is the group category to which the intervention object belongs and has the most similar health characteristics and cardiovascular disease risk levels, and the individual risk factors are the health risk factors that the intervention object has and will cause cardiovascular disease; according to the individual risk factors, the video type of the intervention video to be pushed is determined, and according to the risk portrait type and the completion status of the health management plan, the push parameters corresponding to each video type are determined; in the manner of sending the intervention video of the video type to the terminal device of the intervention object according to the push parameters, through the formulation of a refined risk portrait and an individualized health management plan, combined with an intelligent push mechanism, the purpose of effectively improving the pertinence and efficiency of health management intervention is achieved, and thus the technical problem of insufficient accuracy and personalization of the health promotion videos pushed to high-risk objects for cardiovascular disease in the related art is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The illustrative embodiments and descriptions thereof of the present application are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings:

[0019] Figure 1 is a hardware structure block diagram of a computer terminal (or electronic device) for implementing a method for health management intervention according to an embodiment of the present application;

[0020] Figure 2 is a schematic diagram of a method flow for health management intervention according to an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of a method flow for health management and dynamic intelligent intervention for high-risk objects for cardiovascular disease according to an embodiment of the present application;

[0022] Figure 4 is a schematic diagram of the structure of a health management intervention device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] To enable those skilled in the art to better understand the solution of this application, the following will clearly and completely describe the technical solution in the embodiments of this application in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned accompanying drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0025] The health management of high-risk subjects with cardiovascular diseases is crucial for promoting the improvement of their lifestyle and enhancing medication compliance, and is the main measure for preventing the occurrence and development of cardiovascular diseases in high-risk populations. In some rural areas, the main health management methods for high-risk subjects with cardiovascular diseases in the related technologies mainly include:

[0026] 1) Village doctor management mode: That is, completely relying on village doctors to organize and implement the health management of the residents in the village. Benefiting from the population stability in the grass-roots rural communities, as well as the trust and familiarity established in the long-term interaction between village doctors and villagers, the health management under this mode often has a higher frequency, better service continuity, and fully personalized management content. However, there are also many problems in this mode. For example, the educational levels, medical knowledge, and service capabilities of village doctors vary widely. Compared with professional hospital doctors, they often lack the learning and understanding of the chronic disease management guidelines updated year by year, and this knowledge gap seriously impairs the accuracy of their health education and health guidance, and they cannot provide strong medical protection for local patients, and make outdated or incorrect medical information solidify at the grass-roots level.

[0027] 2) Mass health communication mode on new media platforms: That is, medical experts from hospitals directly preach health knowledge to the public and carry out health management by means of online social media platforms. This method can ensure the scientificity and accuracy of the publicity information. However, the health communication for the public cannot achieve the formulation of personalized content for the patient himself, and cannot play the role of targeted management and intervention for high-risk subjects with cardiovascular diseases.

[0028] To solve the above problems, relevant solutions are provided in the embodiments of the present application, which are described in detail below.

[0029] According to the embodiments of the present application, a method embodiment of a health management intervention device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0030] The method embodiments provided by the embodiments of the present application can be executed on a mobile terminal, a computer terminal, or a similar computing device. Figure 1 A hardware structure block diagram of a computer terminal (or electronic device) for implementing a health management intervention method is shown. As Figure 1 shown, the computer terminal 10 (or electronic device) may include one or more processors 102 (illustrated as 102a, 102b,..., 102n in the figure) (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may further include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply, and / or a camera. Those of ordinary skill in the art can understand that Figure 1 the structure shown is only schematic and does not limit the structure of the above-mentioned electronic device. For example, the computer terminal 10 may further include more or fewer components than Figure 1 shown, or have a different configuration from Figure 1 shown.

[0031] It should be noted that the above one or more processors 102 and / or other data processing circuits are generally referred to as "data processing circuits" in this article. The data processing circuit may be embodied in software, hardware, firmware, or any combination thereof, in whole or in part. In addition, the data processing circuit may be a single independent processing module, or be incorporated in whole or in part into any one of the other elements in the computer terminal 10 (or electronic device). As involved in the embodiments of the present application, the data processing circuit is a processor control (such as the selection of a variable resistance terminal path connected to an interface).

[0032] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the health management intervention method in the embodiments of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, to implement the above health management intervention method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely provided with respect to the processor 102, and these remote memories can be connected to the computer terminal 10 through a network. Examples of the above network include but are not limited to the Internet, enterprise intranets, local area networks, mobile communication networks, and combinations thereof.

[0033] The transmission device 106 is used to receive or send data via a network. Specific examples of the above network may include the wireless network provided by the communication provider of the computer terminal 10. In one instance, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station and thus can communicate with the Internet. In one instance, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] The display can be, for example, a touch-screen liquid crystal display (LCD), and the liquid crystal display enables a user to interact with the user interface of the computer terminal 10 (or electronic device).

[0035] Under the above operating environment, the embodiments of the present application provide a health management intervention method. Figure 2 It is a schematic diagram of the method flow of a health management intervention device provided according to the embodiments of the present application, as Figure 2 shown, and the method includes the following steps:

[0036] Step S202, obtain the health status data of the intervention object, where the health status data is used to characterize the physiological state and behavior status of the intervention object;

[0037] Step S204, based on the health status data, determine the risk portrait type and individual risk factors corresponding to the intervention object, and based on the individual risk factors, determine the health management plan corresponding to the intervention object, where the risk portrait type is the group category to which the intervention object belongs with the most similar health characteristics and cardiovascular disease risk levels, and the individual risk factors are the health risk factors that the intervention object has and will cause cardiovascular disease;

[0038] Step S206: Determine the video type of the intervention video to be pushed according to individual risk factors, and determine the push parameters corresponding to each video type according to the risk portrait type and the completion status of the health management plan;

[0039] Step S208: Send the intervention video of the video type to the terminal device of the intervention object according to the push parameters.

[0040] Through the above steps, through the formulation of refined risk portraits and individualized health management plans, combined with the intelligent push mechanism, the purpose of effectively improving the pertinence and efficiency of health management interventions is achieved, thereby solving the technical problems of insufficient accuracy and personalization of the health promotion videos pushed to high-risk cardiovascular disease objects in the related technologies.

[0041] Next, the health management intervention method in steps S202 to S208 of the present application embodiment will be further introduced.

[0042] Figure 3 It is a schematic diagram of the method flow of a health management and dynamic intelligent intervention for high-risk cardiovascular disease objects provided according to the embodiment of the present application. As Figure 3 shown, through risk portrait classification and risk factor determination in the embodiment of the present application, personalized intervention goals and customized health education video pushes can be provided for each intervention object, so as to meet the health management needs of different individuals; at the same time, based on the dynamic change trend of individual feedback data, the intervention goals and video push parameters can be dynamically adjusted within a relatively long life cycle to achieve long-life-cycle health management. The following is a specific introduction.

[0043] First, obtain the health status data of the intervention object. In this embodiment, the acquisition methods of the health status data include but are not limited to: human-computer interaction input (such as web pages, APPs, etc.), institutional data interfaces (for example, docking relevant systems of medical examinations or community service centers), and wearable device data interfaces (for example, obtaining relevant data through the smart bracelet worn by the intervention object);

[0044] The obtained health status data may include but are not limited to: the individual basic information of the intervention object, various basic health risk factors (Risk factor, RF), other health risk factor data (such as dietary frequency, etc.), and other multimodal information (such as electrocardiogram, ultrasound image or report, etc.).

[0045] For example, the health status data collected in this embodiment are cardiovascular disease-related behavior data and metabolic risk factor data of high-risk cardiovascular disease objects, including: blood pressure, blood sugar, blood lipids, body weight, waist circumference, smoking, drinking, physical activity, diet, sleep, medication compliance, etc., as shown in the following table.

[0046]

[0047] After obtaining the health status data of the intervention object, it is possible to further determine the risk profile type to which the intervention object belongs, as follows.

[0048] In some embodiments of the present application, determining the risk profile type corresponding to the intervention object includes the following steps: obtaining a first data set, wherein the first data set contains the health status data of multiple cardiovascular disease individual objects, and the health status data includes at least one of the following: blood pressure data, blood glucose data, blood lipid data, height and weight data, waist circumference data, smoking frequency data, alcohol consumption frequency data, exercise frequency data, diet status data, sleep status data, medication compliance data, electrocardiogram data, ultrasound imaging data; clustering the health status data of the individual objects in the first data set to obtain a plurality of clustering clusters, wherein each clustering cluster corresponds to a risk profile type; determining the similarity parameter between the feature vector corresponding to the health status data of the intervention object and the feature vectors in each clustering cluster, and determining the risk profile type corresponding to the clustering cluster with the largest similarity parameter as the risk profile type corresponding to the intervention object.

[0049] Specifically, in this embodiment, a clustering algorithm can be first used to analyze a large amount of health status data (i.e., the population data of the first data set), automatically identify groups with similar cardiovascular disease risk characteristics, form risk profile types, and then determine which risk profile type the intervention object belongs to according to the input information of the intervention object. Based on the finally determined risk profile type of the intervention object, the push parameters of the subsequent intervention video can be determined. In addition, the relevant information of the risk profile type can also be directly fed back to the intervention object.

[0050] Among them, the specific steps of clustering the health status data of the individual objects in the first data set are as follows.

[0051] In some embodiments of the present application, clustering the health status data of individual objects in the first dataset includes the following steps: converting the health status data of individual objects into corresponding feature vectors, using a first clustering algorithm to perform preliminary clustering on the feature vectors corresponding to the individual objects in the first dataset, and determining the first number of clustering categories obtained after preliminary clustering, where the first clustering algorithm includes: the Canopy clustering algorithm; randomly sampling from the first dataset in a replacement manner to generate multiple second datasets, where the number of samples in the second dataset is the same as the number of samples in the first dataset; randomly selecting the first number of initial clustering centers in the second dataset, and using a second clustering algorithm to perform clustering based on the initial clustering centers, where each second dataset obtains the first number of clustering clusters after clustering, and the second clustering algorithm includes: the Mini-batch K-means clustering algorithm; converting the feature vectors in the clustering clusters corresponding to each second dataset into classification description texts with medical significance, and determining multiple risk profile types based on the classification description texts.

[0052] Specifically, first, unsupervised preliminary clustering can be performed on the individual data in the first dataset, that is, using a first clustering algorithm (taking the Canopy algorithm as an example) to roughly divide the population in the first dataset into several categories and determine the preliminary classification number K (i.e., the first number of the above-mentioned clustering categories); then, samples can be randomly drawn from the first dataset in a replacement manner by the Bootstrapping method to generate m groups of new second datasets (increasing data sample perturbation), and the sample size of each second dataset is the same as that of the first dataset.

[0053] After that, using the second clustering algorithm (taking the Mini-batch K-means clustering algorithm as an example) and the K value determined in the previous step, further precise clustering is performed on each of the i = 1~m groups respectively, and each i-th group can be clustered into K categories. The Mini-batch K-means method is especially suitable for large-scale data, sacrificing a little accuracy to improve computational efficiency. Based on each group of data with i = 1~m, a set of classification equations will be obtained.

[0054] Describe the characteristic variable situations of each of the K classifications obtained from the m groups of people respectively, and convert them into existing risk factor clustering characteristic descriptions (i.e., the above-mentioned classification description texts), such as high blood pressure cluster, smoking and drinking cluster, high blood pressure + high blood lipid cluster, etc. Thus, the numerically-based results obtained by clustering are converted into risk profile type classifications with medical significance and relatively certain (linked to subsequent intervention strategies).

[0055] For example, the first type of risk profile is the "hypertension type". Among this group of people, 95% of the individuals have high blood pressure, 40% are obese, 30% are smokers, and 30% have high blood lipids; the average CVD (Cardiovascular Disease) risk assessment score for this group of people is 45%, which is a high risk. Then, for the first type of individuals, 95%, 40%, 30%, and 30% are the weights of the defined risk factor characteristic variables; the second type is the "smoking and obesity type". Among this group of people, 30% of the individuals have high blood pressure, 80% are obese, 70% are smokers, and 20% have high blood lipids; the average CVD risk assessment score for this group of people is 15%, which is a medium risk.

[0056] After obtaining the risk clustering results based on a large amount of existing population data, the classification of intervention objects can be carried out. For example, for the intervention object with input individual information, the characteristic variables are input into the classification model to obtain the classification kij of the individual. i represents the i-th group in the m data groups, and j represents the j-th type in the meaningful labels. That is to say, in each of the m populations where i = 1 to m, based on the previously obtained classification equations, it is determined which category this new individual belongs to in the i-th group of people. After all the calculations are completed, the new individual will have m classification results in the m data groups; then result integration (Bagging) can be performed. Using the relative majority voting method, the m meaningful classifications obtained by the individual in the m groups of data are summarized. Each time it is selected, it gets one vote, and the one with the most votes is obtained. If there is a tie, one is randomly selected from the classifications as the final classification.

[0057] In the clustering analysis of this application embodiment, by combining the umbrella clustering algorithm and the mini-batch K-means clustering algorithm, it is not only possible to process a large amount of health status data, but also to improve the accuracy and stability of clustering. The umbrella clustering algorithm first performs a rough clustering to determine the approximate number of clustering categories, and the mini-batch K-means algorithm further refines the clustering results on this basis through multiple iterations and random sampling to ensure that each clustering cluster can accurately reflect a group with specific risk characteristics. This process solves the overfitting or underfitting problems that may exist in traditional clustering methods, making the division of risk profile types more scientific and reasonable. By converting the clustering results into medical descriptions, it can provide clear risk classification information for medical management personnel, facilitating them to provide more personalized health management suggestions according to the specific health conditions of individuals.

[0058] On the other hand, while determining the risk profile type corresponding to the intervention target, the individual risk factors corresponding to the intervention target can also be determined. Specifically, the health status data of the intervention target is compared with the corresponding health standards to identify the individual risk factors possessed by the intervention target. For example, if the BMI of a certain intervention target is 28 kg / m², then the risk factor of "obesity" is identified for it. Further, specific intervention goals can be formulated based on the identified individual risk factors to form a health management plan, as follows.

[0059] In some embodiments of the present application, determining the health management plan corresponding to the intervention target based on individual risk factors includes: determining the health standards corresponding to the health status data of the intervention target, and determining the health status data items that do not meet the health standards as individual risk factors; according to the intervention cycle corresponding to the intervention target, determining the phased intervention goals of the individual risk factors to obtain a preliminary health management plan, where the intervention goals include at least one of the following: blood pressure management goal, blood sugar management goal, blood lipid management goal, weight management goal, smoking cessation goal, alcohol restriction goal, exercise goal; sending the preliminary health management plan to the terminal device of the medical management personnel in the area corresponding to the intervention target, where the medical management personnel include the resident doctors in the community or village where the intervention target is located, and the medical management personnel are used to adjust the preliminary health management plan according to their understanding of the daily lifestyle and physical condition of the intervention target; obtaining the adjusted health management plan returned by the terminal device of the medical management personnel, and sending the adjusted health management plan to the terminal device of the intervention target.

[0060] Specifically, the system can automatically generate a preliminary health management plan and individualized intervention goal recommendations for high-risk cardiovascular disease subjects (i.e., intervention targets). The recommended ranges of the intervention goals are all based on the latest evidence in the guidelines for cardiovascular disease prevention and risk factor management. For example, the health management plan can include intervention goals such as blood pressure management, blood sugar management, blood lipid management, weight management, smoking cessation, alcohol restriction, and exercise improvement, as shown in the following table.

[0061]

[0062] When generating the preliminary health management plan, it is also possible to allow the medical management personnel in the area corresponding to the intervention target (taking village doctors as an example) and / or the intervention target itself to adjust the intervention goals according to the actual situation and wishes of the individual.

[0063] For example, assume a high-risk cardiovascular patient, female, 62 years old, with a 10-year history of hypertension, systolic blood pressure: 160 mmHg, diastolic blood pressure: 90 mmHg, no diabetes, fasting blood glucose 6.0 mmol / L, no dyslipidemia, total cholesterol 4.1 mmol / L, high-density lipoprotein cholesterol 1.8 mmol / L, height 160 cm, weight 80 kg, smokes daily, does not drink alcohol.

[0064] Based on the initial version of the health management plan automatically generated from her health status data, the individual risk factors that need to be focused on are: hypertension, obesity, and smoking. The individualized intervention goals recommended by the algorithm are: (1) Blood pressure control goal: <130 / 80 mmHg. (2) Weight loss goal: The total weight loss goal is 12 kg, with a 3-month stage, and the goal is completed in four stages. (3) Smoking cessation goal: With a 3-month stage, completely quit smoking. In addition, the following routine goals are still listed in the health management plan: (4) Blood glucose goal: Fasting blood glucose < 6.1 mmol / L; (5) Blood lipid goal: Non-HDL-C < 3.4 mmol / L; (6) Alcohol restriction goal: Keep not drinking alcohol; (7) Exercise goal: It is recommended to exercise at least 3 days a week, and the number of steps per day during exercise days should reach 6000 - 8000 steps.

[0065] According to the specific communication between the village doctor and the patient, the patient believes that she cannot directly quit smoking completely. Therefore, the smoking cessation goal is modified to: The total goal is to quit smoking, with a 3-month stage, and the goal is completed in two stages; in the first stage, change from smoking daily to smoking at most once a week; the second stage is to completely quit smoking. During the actual follow-up, in the first month (3 months is a stage, and it is not yet the first follow-up stage), this patient visited the doctor due to pneumonia caused by a cold. Therefore, her weight loss goal and exercise goal were suspended. After the body recovered, her weight was measured again, and the weight loss goal and exercise goal were recalculated.

[0066] In the embodiment of this application, by combining individual risk factors with the health management plan, the dynamic adjustment and personalized customization of health management are realized. For example, for blood pressure management, the system will set a reasonable blood pressure control goal based on the blood pressure data of the intervention object, and during the intervention period, according to the user's feedback and changes in health data, dynamically adjust the intervention measures, such as increasing the exercise frequency or adjusting the diet structure. This process solves the problem of overly rigid goal setting in health management, enabling the health management plan to more flexibly adapt to individual health changes and improving the efficiency and effectiveness of intervention. Through the participation and adjustment of medical management personnel, the system can combine professional medical knowledge and the actual situation of individuals to provide more scientific and reasonable health management suggestions, enhancing the user's trust and compliance.

[0067] In the embodiments of the present application, the video type of the intervention video to be pushed can also be determined according to individual risk factors, and the push parameters corresponding to each video type can be determined according to the risk portrait type and the completion status of the health management plan, so as to achieve targeted personalized video push. The following is a specific introduction.

[0068] In some embodiments of the present application, determining the push parameters corresponding to each video type includes the following steps: determining the risk level corresponding to the risk portrait type to which the intervention object belongs, and the influence coefficient corresponding to each piece of health status data in the risk portrait type, where the risk level is used to characterize the probability of people belonging to the risk portrait type suffering from cardiovascular disease, and the influence coefficient is used to characterize the degree of influence of each piece of health status data on causing cardiovascular disease for people belonging to the risk portrait type; determining the total number of intervention videos to be pushed to the intervention object within a video push cycle according to the risk level; determining the push weight of the video type corresponding to each individual risk factor of the intervention object according to the influence coefficient of the health status data corresponding to the individual risk factor, where the influence coefficient is positively correlated with the push weight; determining the initial push parameters of each video type according to the total number of intervention videos and the push weight, where the push parameters include at least one of the following: the push quantity, push frequency, and push priority of the intervention video of the video type.

[0069] Specifically, the total number of videos to be pushed to the intervention object in the video push cycle (such as weekly) can be determined according to the CVD risk level (i.e., the above-mentioned risk level) of the clustering group (risk portrait type) where the intervention individual is located. For example, if the group where the individual is located is a high-risk group, the maximum number of videos (such as 10) of the highest quantity level will be pushed per week; if the group where the individual is located is a medium-risk group, the second-highest number of videos (such as 7) of the quantity level will be pushed per week.

[0070] At the same time, the video type to be pushed can be determined according to the individual risk factors of the intervention object. For example, if the individual has three risk factor labels of high blood pressure, obesity, and smoking, it is determined to push the video groups corresponding to these three risk factors at this stage. In this embodiment, a library containing various health education videos can be established, and each video type corresponds to a different health theme, such as hypertension management, weight management, smoking cessation guidance, etc. The corresponding videos are selected from the video library according to the video type corresponding to the individual risk factor. For example, if the video types are "hypertension management" and "weight management", the videos of these two types are selected from the video library.

[0071] Moreover, based on the influence coefficients corresponding to the individual risk factors of the intervention object in the group of the corresponding risk profile types, the push weights of the video types corresponding to each individual risk factor can be determined. Combining the total number of videos to be pushed in the video push cycle plan, the video push parameters can be determined. For example, assume that the weights of risk factors 1-6 in the clustering group where individual A is located are 95%, 40%, 30%, 30%, 80%, and 70%, and the CVD risk level is high risk. The risk factors he himself has are 1 / 3 / 5. Then, as pre-set, 10 videos need to be pushed per week; according to the risk factor situation, 3 types of videos for risk factors 1 (w1 = 95%), 3 (w3 = 30%), and 5 (w5 = 80%) will be pushed to him. Since risk factor 3 does not meet the standard currently, the weight of w3 needs to be adjusted to 50%. Finally, the weights of video types 1 / 3 / 5 are 95%, 50%, and 80%, and the video quantities are n1 = 95 / (95 + 50 + 80) * 10 = 4.2 → 4, n2 = 50 / (95 + 50 + 80) * 10 = 2.2 → 2, n3 = 80 / (95 + 50 + 80) * 10 = 3.6 → 4; Np = Wp / ΣW * N, where p is the serial number of a certain risk factor, W is the weight, ΣW is the sum of the weights of several risk factors, and N is the total number of videos.

[0072] In the embodiment of the present application, the push parameters of the intervention videos are determined through an intelligent algorithm, realizing the intelligence and personalization of health management interventions. For example, for intervention objects with a high-risk level, the system will automatically increase the total number of video pushes to enhance the intervention effect; for health status data with a relatively high influence coefficient, such as hypertension, the system will correspondingly increase the push weight of the relevant video type to ensure that users can receive more targeted health education videos. This process solves the problem of lack of pertinence and personalization in information push in health management interventions, enabling the intervention videos to more accurately meet the health education needs of users and improving the intervention effect. By dynamically adjusting the push parameters, the system can optimize the intervention strategy in real time according to the user's feedback and changes in health data, further enhancing the flexibility and adaptability of health management interventions.

[0073] To further improve the effect of health interventions, the embodiment of the present application can also adaptively adjust the intervention goals in each stage of the health management plan and dynamically adjust the video push parameters accordingly by monitoring the completion of the intervention goals of the intervention object in each intervention cycle, as follows.

[0074] In some embodiments of the present application, the method further includes: monitoring the completion status and progress of each intervention objective corresponding to the intervention cycle in the health management plan, where the completion status includes: over-completion, completion, and non-completion; using a prediction model to predict the management progress of each individual risk factor of the intervention object in the next intervention cycle based on the completion status and progress of the intervention objective in the current intervention cycle, and determining the intervention objective for the next intervention cycle based on the prediction result, where the prediction model is trained based on the health status data of the intervention object and the completion status of the intervention objective in the historical intervention cycle; and using a causal inference model to analyze the completion status and progress of the intervention objective in the current intervention cycle, as well as the acceptance tendency data of the intervention object for the intervention measures, to obtain the causal effect relationship between the intervention measures and the completion status, and adjusting the push parameters of the video type based on the causal effect relationship, where the intervention measures include: pushing intervention videos to the intervention object, and the acceptance tendency data includes at least one of the following: the number of views, duration, whether liked, and whether collected of the intervention video.

[0075] Specifically, the progress of the intervention objective is evaluated by collecting and analyzing the health data of the intervention object in real time. For example, for the weight loss objective, the weekly weight change is monitored; for the blood pressure control objective, the daily blood pressure measurement data is monitored. On the other hand, a prediction model can be used to predict the management progress of the next intervention cycle. Specifically, the health data, intervention objective completion status, intervention measure execution status, and external factor data in the historical intervention cycle can be collected; machine learning algorithms (such as random forest, neural network, etc.) are used to train the prediction model to predict the management progress of each individual risk factor of the intervention object in the next intervention cycle; then, based on the prediction result, the intervention objective for the next intervention cycle can be determined. For example, if the prediction result shows that the intervention object may not be able to complete the weight loss objective in the next cycle, the weight loss objective is appropriately adjusted or support measures are increased.

[0076] In addition, the acceptance tendency data of the intervention object for the intervention measures can be collected, such as the number of views, viewing duration, whether liked, and whether collected of the intervention video; a causal inference model (such as propensity score matching, instrumental variable method, etc.) is used to analyze the causal effect relationship between the intervention measures and the completion status. For example, the impact of pushing intervention videos on the completion of the intervention objective is evaluated by the propensity score matching method; based on the causal effect relationship, the push parameters of the video type are adjusted. For example, if the analysis result shows that viewing the intervention video has a significant positive impact on the completion of the intervention objective, the push frequency and quantity of this type of video are increased; if it is found that the acceptance of a certain type of video by the intervention object is low, the push strategy of this type of video is adjusted.

[0077] In the embodiments of the present application, by monitoring the completion status of the intervention target and using prediction models and causal inference models, dynamic optimization and effect evaluation of health management interventions can be achieved. This process solves the problem of lag in effect evaluation and strategy adjustment in health management interventions, enabling the system to monitor intervention effects in real time, adjust intervention strategies in a timely manner, and improve the efficiency and effectiveness of interventions. By analyzing the relationship between intervention measures and completion status through a causal inference model, the system can more accurately identify effective intervention means, optimize the push strategy of intervention videos, and enhance user participation and compliance.

[0078] In addition, in the case where the intervention target of the current intervention cycle is not completed, a further specific analysis can be carried out on the reasons for the uncompleted target, as follows.

[0079] In some embodiments of the present application, the method further includes: in the case where the intervention target of the current intervention cycle is not completed, obtaining the reasons for non-completion feedback by the terminal device of the medical management personnel, where the reasons for non-completion include at least one of the following: the target is set too high, there is a lack of sufficient support or resources, personal health status changes, lack of motivation or poor compliance, external environmental factors; adjusting the intervention target according to the reasons for non-completion, and obtaining corresponding intervention videos for pushing to the terminal device of the intervention object according to the reasons for non-completion.

[0080] Specifically, the medical management personnel can be used to obtain the specific reasons for the intervention object not completing the intervention target, including but not limited to: 1) The target is set too high: The intervention target may exceed the current capabilities and actual situation of the intervention object, making it difficult to complete; 2) Lack of sufficient support or resources: The intervention object may not have sufficient external support (such as medical resources, community support, etc.) or personal resources (such as time, money, etc.) to achieve the target; 3) Personal health status changes: The health status of the intervention object may have changed during the intervention cycle, affecting the completion of the target; 4) Lack of motivation or poor compliance: The intervention object may lack sufficient motivation or compliance, resulting in the inability to continuously implement the intervention measures; 5) External environmental factors: External environmental factors (such as work pressure, family status, etc.) may affect the health management of the intervention object; 6) The intervention measures do not meet individual needs: The intervention measures may not fully consider the individual differences and needs of the intervention object, resulting in poor effects.

[0081] After that, the intervention goals can be adjusted and / or relevant videos can be pushed for adjustment according to the reasons for non-compliance. For example, if the goal is set too high, the goal difficulty can be reduced and the goal schedule can be adjusted to make it more in line with the actual situation of the intervention object; for the problem of lack of sufficient support or resources, a guidance video on how to obtain resources can be provided to help the intervention object understand how to obtain the necessary support and resources; for changes in personal health conditions, the intervention goals and measures can be adjusted according to the changes in health conditions to ensure their adaptability, and a strategy video for coping with changes in health conditions can be provided; for the situation of lack of motivation or poor compliance, an incentive video for improving motivation and compliance can be provided to help the intervention object maintain a positive attitude and continuous action; for the influence of external environmental factors, a suggestion video for coping with external environmental factors can be provided specifically to help the intervention object cope with external factors such as work pressure and family status.

[0082] Through the feedback of medical management personnel and the push of intervention videos in the embodiments of the present application, the problem of unreasonable goal setting in health management intervention is solved, enabling the system to adjust the intervention strategy more flexibly and improving the feasibility and effect of the intervention. Through the professional judgment of medical management personnel and the automatically pushed intervention videos of the system, the system can provide more comprehensive and personalized health management support for users, enhance the motivation and compliance of users, and thus improve the success rate of health management intervention.

[0083] In addition, as an optional implementation manner, the method further includes the following steps: determining the geographical region where the intervention object is located, and obtaining the geographical characteristics and climate information of the geographical region, where the geographical characteristics include at least one of the following: topographical and geomorphic characteristics, dietary culture characteristics, and the climate information includes at least one of the following: temperature data, humidity data, seasonal change conditions, and extreme weather frequency; adjusting the video content of the intervention video and the intervention goals in the health management plan according to the geographical characteristics and climate information.

[0084] Specifically, the geographical region where the intervention object is located can be determined through the registration information of the intervention object, mobile device positioning or user input, and then the geographical region can be divided into different types for subsequent analysis and adjustment. Specifically, the topographical and geomorphic features of the region where the intervention object is located, such as mountainous areas, plains, coastal areas, etc., which may affect the exercise plan and lifestyle suggestions, can be analyzed, and the dietary culture of the region where the intervention object is located, such as high-salt diet areas, high-fat diet areas, etc., can be understood to provide targeted dietary suggestions; and, factors such as the temperature range and humidity level of the region where the intervention object is located, which may affect physiological indicators and the arrangement of outdoor activities and exercise plans, can be obtained.

[0085] After that, the video content of the intervention video and the intervention goals in the health management plan can be adjusted according to geographical characteristics and climate information. For example, provide low-salt diet guidance videos for areas with high-salt diets, and provide seafood intake advice videos for coastal areas; provide exercise videos suitable for mountain environments for mountainous areas, and provide videos suitable for outdoor running for plain areas; adjust outdoor exercise goals in high-temperature seasons and recommend indoor exercise; provide health advice on moisture-proof and mildew-proof in rainy seasons.

[0086] By considering the geographical characteristics and climate information of the geographical area where the intervention object is located, the embodiments of the present application achieve regional and seasonal adjustments of health management interventions, solve the problem of lack of regional and seasonal considerations in health management interventions, enable the system to be closer to the user's living environment and health needs, and provide more scientific and reasonable intervention suggestions. Through the comprehensive analysis of geographical characteristics and climate information, a more personalized and practical health management plan can be provided for users, thereby improving the effect of health management interventions and the quality of life of users.

[0087] The solution of the present application can effectively improve the pertinence and efficiency of interventions through refined risk profiling and the formulation of individualized health management plans, combined with an intelligent push mechanism. It not only considers the physiological indicators and living habits of the intervention object, but also incorporates the influence of regional characteristics and climate conditions, making the intervention measures closer to the actual life scenarios of users, enhancing the user's sense of participation and compliance. In addition, the dynamic adjustment mechanism ensures the flexibility and adaptability of the health management plan, can respond in a timely manner to the health changes and needs of users, thereby achieving more effective health management interventions, significantly reducing the risk of cardiovascular diseases, and improving the overall level of health management and quality of life.

[0088] According to the embodiments of the present application, an embodiment of a health management intervention device is also provided. Figure 4 It is a schematic structural diagram of a health management intervention device provided according to the embodiments of the present application. As Figure 4 shown, the device includes:

[0089] A data acquisition module 40, configured to acquire the health status data of the intervention object, where the health status data is used to characterize the physiological state and behavior status of the intervention object;

[0090] A plan determination module 42, configured to determine the risk profile type and individual risk factors corresponding to the intervention object according to the health status data, and determine the health management plan corresponding to the intervention object according to the individual risk factors, where the risk profile type is the group category to which the intervention object belongs and has the most similar health characteristics and cardiovascular disease risk levels, and the individual risk factors are the health risk factors that the intervention object has and will cause cardiovascular diseases;

[0091] A push setting module 44, configured to determine the video type of the intervention video to be pushed according to individual risk factors, and determine the push parameters corresponding to each video type according to the risk profile type and the completion status of the health management plan;

[0092] A video intervention module 46, configured to send the intervention video of the video type to the terminal device of the intervention object according to the push parameters.

[0093] Optionally, determining the risk profile type corresponding to the intervention object includes: obtaining a first data set, where the first data set contains the health status data of multiple cardiovascular disease individual objects, and the health status data includes at least one of the following: blood pressure data, blood glucose data, blood lipid data, height and weight data, waist circumference data, smoking frequency data, drinking frequency data, exercise frequency data, diet status data, sleep status data, medication compliance data, electrocardiogram data, ultrasonic imaging data; clustering the health status data of the individual objects in the first data set to obtain multiple clustering clusters, where each clustering cluster corresponds to a risk profile type; determining the similarity parameter between the feature vector corresponding to the health status data of the intervention object and the feature vectors in each clustering cluster, and determining the risk profile type corresponding to the clustering cluster with the largest similarity parameter as the risk profile type corresponding to the intervention object.

[0094] Optionally, clustering the health status data of the individual objects in the first data set includes: converting the health status data of the individual objects into corresponding feature vectors, using a first clustering algorithm to perform preliminary clustering on the feature vectors corresponding to the individual objects in the first data set, and determining the first number of the clustering categories obtained after the preliminary clustering, where the first clustering algorithm includes: an umbrella clustering algorithm; randomly sampling from the first data set with replacement to generate multiple second data sets, where the number of samples in the second data set is the same as the number of samples in the first data set; randomly selecting the first number of initial clustering centers in the second data set, and using a second clustering algorithm to perform clustering based on the initial clustering centers, where each second data set obtains the first number of clustering clusters after clustering, and the second clustering algorithm includes: a mini-batch K-means clustering algorithm; converting the feature vectors in the clustering clusters corresponding to each second data set into classification description texts with medical significance, and determining multiple risk profile types according to the classification description texts.

[0095] Optionally, determining the health management plan corresponding to the intervention object based on individual risk factors includes: determining the health standards corresponding to the health status data of the intervention object, and determining the health status data items that do not meet the health standards as individual risk factors; determining the phased intervention goals for the individual risk factors according to the intervention cycle corresponding to the intervention object to obtain a preliminary health management plan, where the intervention goals include at least one of the following: blood pressure management goal, blood sugar management goal, blood lipid management goal, weight management goal, smoking cessation goal, alcohol restriction goal, exercise goal; sending the preliminary health management plan to the terminal device of the medical management personnel in the area corresponding to the intervention object, where the medical management personnel include the resident doctors in the community or village where the intervention object is located, and the medical management personnel are used to adjust the preliminary health management plan according to their understanding of the daily lifestyle and physical condition of the intervention object; obtaining the adjusted health management plan returned by the terminal device of the medical management personnel, and sending the adjusted health management plan to the terminal device of the intervention object.

[0096] Optionally, determining the push parameters corresponding to each video type includes: determining the risk level corresponding to the risk portrait type to which the intervention object belongs, and the influence coefficients corresponding to the health status data items in the risk portrait type, where the risk level is used to characterize the probability of people belonging to the risk portrait type suffering from cardiovascular diseases, and the influence coefficient is used to characterize the influence degree of each health status data item on causing cardiovascular diseases for people belonging to the risk portrait type; determining the total number of intervention videos to be pushed to the intervention object within a video push cycle according to the risk level; determining the push weight of the video type corresponding to each individual risk factor of the intervention object according to the influence coefficient of the health status data corresponding to the individual risk factors, where the influence coefficient is positively correlated with the push weight; determining the initial push parameters for each video type according to the total number of intervention videos and the push weight, where the push parameters include at least one of the following: the push number, push frequency, and push priority of the intervention videos of the video type.

[0097] Optionally, the health management intervention device is further configured to: monitor the completion status and progress of each intervention objective corresponding to the intervention period in the health management plan, where the completion status includes: over-completion, completion, and non-completion; use a prediction model to predict the management progress of each individual risk factor of the intervention object in the next intervention period based on the completion status and progress of the intervention objective in the current intervention period, and determine the intervention objective for the next intervention period based on the prediction result, where the prediction model is trained based on the health status data of the intervention object and the completion status of the intervention objective in the historical intervention period; and use a causal inference model to analyze the completion status and progress of the intervention objective in the current intervention period, as well as the acceptance tendency data of the intervention object for the intervention measures, to obtain the causal effect relationship between the intervention measures and the completion status, and adjust the push parameters of the video type based on the causal effect relationship, where the intervention measures include: pushing intervention videos to the intervention object, and the acceptance tendency data includes at least one of the following: the number of views of the intervention video, the duration, whether it is liked, and whether it is collected.

[0098] Optionally, the health management intervention device is further configured to: when the intervention objective in the current intervention period is not completed, obtain the reasons for non-completion feedback by the terminal device of the medical management personnel, where the reasons for non-completion include at least one of the following: the target is set too high, lack of sufficient support or resources, personal health status changes, lack of motivation or poor compliance, and external environmental factors; adjust the intervention objective based on the reasons for non-completion, and obtain the corresponding intervention video for pushing to the terminal device of the intervention object according to the reasons for non-completion.

[0099] Optionally, the health management intervention device is further configured to: determine the geographical area where the intervention object is located, and obtain the geographical characteristics and climate information of the geographical area, where the geographical characteristics include at least one of the following: topographical and geomorphic characteristics, dietary culture characteristics, and the climate information includes at least one of the following: temperature data, humidity data, seasonal change conditions, and extreme weather frequency; adjust the video content of the intervention video and the intervention objective in the health management plan based on the geographical characteristics and climate information.

[0100] It should be noted that each module in the above health management intervention device can be a program module (for example, a set of program instructions that implement a specific function), or a hardware module. For the latter, it can be presented in the following forms, but not limited to this: the manifestation form of each of the above modules is a processor, or the functions of each of the above modules are implemented by a processor.

[0101] It should be noted that the health management intervention device provided in this embodiment can be used to execute Figure 2The health management intervention method shown above. Therefore, the relevant explanations for the above health management intervention method also apply to the embodiments of the present application and will not be elaborated here.

[0102] The embodiments of the present application also provide a non-volatile storage medium. The non-volatile storage medium includes a stored computer program. Wherein, the device where the non-volatile storage medium is located executes the following health management intervention method by running the computer program: obtaining the health status data of the intervention object, where the health status data is used to characterize the physiological state and behavior status of the intervention object; based on the health status data, determining the risk portrait type and individual risk factors corresponding to the intervention object, and based on the individual risk factors, determining the health management plan corresponding to the intervention object, where the risk portrait type is the group category to which the intervention object belongs with the most similar health characteristics and cardiovascular disease risk levels, and the individual risk factors are the health risk factors that the intervention object has and will cause cardiovascular disease; based on the individual risk factors, determining the video type of the intervention video to be pushed in the plan, and based on the risk portrait type and the completion status of the health management plan, determining the push parameters corresponding to each video type; according to the push parameters, sending the intervention video of the video type to the terminal device of the intervention object.

[0103] The embodiments of the present application also provide a computer program product, including a computer program. When the computer program is executed by a processor, it implements the steps of the health management intervention method described in each embodiment of the present application: obtaining the health status data of the intervention object, where the health status data is used to characterize the physiological state and behavior status of the intervention object; based on the health status data, determining the risk portrait type and individual risk factors corresponding to the intervention object, and based on the individual risk factors, determining the health management plan corresponding to the intervention object, where the risk portrait type is the group category to which the intervention object belongs with the most similar health characteristics and cardiovascular disease risk levels, and the individual risk factors are the health risk factors that the intervention object has and will cause cardiovascular disease; based on the individual risk factors, determining the video type of the intervention video to be pushed in the plan, and based on the risk portrait type and the completion status of the health management plan, determining the push parameters corresponding to each video type; according to the push parameters, sending the intervention video of the video type to the terminal device of the intervention object.

[0104] The serial numbers of the above embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0105] In the above embodiments of the present application, the descriptions of each embodiment have their own focuses. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0106] In several embodiments provided by the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units can be a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of units or modules can be in electrical or other forms.

[0107] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0108] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0109] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0110] The above are only the preferred embodiments of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A health management intervention method, characterized in that, Including: Obtaining health status data of an intervention object, where the health status data is used to characterize the physiological state and behavior status of the intervention object; According to the health status data, determining the risk portrait type and individual risk factors corresponding to the intervention object, and according to the individual risk factors, determining the health management plan corresponding to the intervention object, where the risk portrait type is the group category of the intervention object with the most similar health characteristics and cardiovascular disease risk levels, and the individual risk factors are the health risk factors that the intervention object has and will cause cardiovascular disease; According to the individual risk factors, determining the video type of the intervention video to be pushed, and according to the risk portrait type and the completion status of the health management plan, determining the push parameters corresponding to each video type; Sending the intervention video of the video type to the terminal device of the intervention object according to the push parameters.

2. The health management intervention method according to claim 1, wherein Determining the risk portrait type corresponding to the intervention object includes: Obtaining a first data set, where the first data set contains the health status data of multiple cardiovascular disease individual objects, and the health status data includes at least one of the following: blood pressure data, blood glucose data, blood lipid data, height and weight data, waist circumference data, smoking frequency data, drinking frequency data, exercise frequency data, diet status data, sleep status data, drug compliance data, electrocardiogram data, ultrasonic imaging data; Clustering the health status data of the individual objects in the first data set to obtain multiple clustering clusters, where each clustering cluster corresponds to a risk portrait type; Determining the similarity parameters between the feature vector corresponding to the health status data of the intervention object and the feature vectors in each clustering cluster, and determining the risk portrait type corresponding to the clustering cluster with the largest similarity parameter as the risk portrait type corresponding to the intervention object.

3. The health management intervention method according to claim 2, wherein Clustering the health status data of the individual objects in the first data set includes: Converting the health status data of the individual objects into corresponding feature vectors, using a first clustering algorithm to perform preliminary clustering on the feature vectors corresponding to the individual objects in the first data set, and determining the first number of clustering categories obtained after the preliminary clustering, where the first clustering algorithm includes: umbrella clustering algorithm; Randomly sampling from the first data set in a replacement manner to generate multiple second data sets, where the number of samples in the second data set is the same as the number of samples in the first data set; Randomly selecting the first number of initial clustering centers in the second data set, and using a second clustering algorithm to perform clustering based on the initial clustering centers, where each second data set obtains the first number of clustering clusters after clustering, and the second clustering algorithm includes: mini-batch K-means clustering algorithm; Convert the feature vectors in each of the clustering clusters corresponding to the second data set into classification description texts with medical significance, and determine multiple types of the risk portraits based on the classification description texts.

4. The health management intervention method according to claim 1, characterized in that, Determining the health management plan corresponding to the intervention object based on the individual risk factors includes: Determine the health standards corresponding to the health status data of the intervention object, and determine the health status data items that do not meet the health standards as the individual risk factors; According to the intervention cycle corresponding to the intervention object, determine the phased intervention objectives of the individual risk factors to obtain a preliminary health management plan, where the intervention objectives include at least one of the following: blood pressure management objective, blood sugar management objective, blood lipid management objective, weight management objective, smoking cessation objective, alcohol restriction objective, exercise objective; Send the preliminary health management plan to the terminal device of the medical management personnel in the area corresponding to the intervention object, where the medical management personnel include the resident doctors in the community or village where the intervention object is located, and the medical management personnel are used to adjust the preliminary health management plan based on their understanding of the daily lifestyle and physical condition of the intervention object; Obtain the adjusted health management plan returned by the terminal device of the medical management personnel, and send the adjusted health management plan to the terminal device of the intervention object.

5. The health management intervention method according to claim 4, wherein Determining the push parameters corresponding to each of the video types includes: Determine the risk level corresponding to the risk portrait type to which the intervention object belongs, and the influence coefficients corresponding to the health status data items in the risk portrait type, where the risk level is used to characterize the probability of people belonging to the risk portrait type suffering from cardiovascular diseases, and the influence coefficient is used to characterize the influence degree of each of the health status data items on causing cardiovascular diseases for people belonging to the risk portrait type; Determine the total number of intervention videos to be pushed to the intervention object within a video push cycle based on the risk level; Determine the push weight of the video type corresponding to each individual risk factor of the intervention object based on the influence coefficient of the health status data corresponding to the individual risk factor, where the influence coefficient is positively correlated with the push weight; Determine the initial push parameters of each video type based on the total number of intervention videos and the push weight, where the push parameters include at least one of the following: the push quantity, push frequency, and push priority of the intervention videos of the video type.

6. The health management intervention method according to claim 5, characterized in that, The method further includes: Monitor the completion status and progress of the intervention objectives corresponding to the intervention cycle in the health management plan, where the completion status includes: over-fulfilled, fulfilled, not fulfilled; Using a prediction model, based on the completion status and progress of the intervention target within the current intervention cycle, predict the management progress of each individual risk factor of the intervention object in the next intervention cycle, and based on the prediction result, determine the intervention target for the next intervention cycle, where the prediction model is trained based on the health status data of the intervention object and the completion status of the intervention target in the historical intervention cycle; In addition, use a causal inference model to analyze the completion status and progress of the intervention target within the current intervention cycle, as well as the acceptance tendency data of the intervention object towards the intervention measures, to obtain the causal effect relationship between the intervention measures and the completion status, and based on the causal effect relationship, adjust the push parameters of the video type, where the intervention measures include: pushing the intervention video to the intervention object, and the acceptance tendency data includes at least one of the following: the number of views, duration, whether liked, whether collected of the intervention video.

7. The health management intervention method according to claim 6, wherein The method further includes: In the case where the intervention target in the current intervention cycle is not completed, obtain the reasons for non-completion feedback by the terminal device of the medical management personnel, where the reasons for non-completion include at least one of the following: the target is set too high, lack of sufficient support or resources, changes in personal health status, lack of motivation or poor compliance, influence of external environmental factors; Based on the reasons for non-completion, adjust the intervention target, and for the reasons for non-completion, obtain the corresponding intervention video and push it to the terminal device of the intervention object.

8. The health management intervention method according to claim 1, wherein The method further includes: Determine the geographical area where the intervention object is located, and obtain the geographical characteristics and climate information of the geographical area, where the geographical characteristics include at least one of the following: topographical and geomorphic characteristics, dietary culture characteristics, and the climate information includes at least one of the following: temperature data, humidity data, seasonal change conditions, extreme weather frequency; Based on the geographical characteristics and the climate information, adjust the video content of the intervention video and the intervention target in the health management plan.

9. A health management intervention device, characterized in that It includes: A data acquisition module, configured to acquire the health status data of the intervention object, where the health status data is used to characterize the physiological state and behavioral status of the intervention object; A plan determination module, configured to determine the risk profile type and individual risk factors corresponding to the intervention object based on the health status data, and based on the individual risk factors, determine the health management plan corresponding to the intervention object, where the risk profile type is the group category to which the intervention object belongs and has the most similar health characteristics and cardiovascular disease risk levels, and the individual risk factors are the health risk factors that the intervention object has and will cause cardiovascular disease; A push setting module, configured to determine the video type of the intervention video to be pushed according to the individual risk factors, and determine the push parameters corresponding to each video type according to the risk profile type and the completion status of the health management plan; A video intervention module, configured to send the intervention video of the video type to the terminal device of the intervention object according to the push parameters.

10. An electronic device, characterized in that, It includes: A memory and a processor, where the processor is configured to run a program stored in the memory, and wherein, when the program runs, it executes the health management intervention method according to any one of claims 1 to 8.

11. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored computer program, and wherein, the device where the non-volatile storage medium is located executes the health management intervention method according to any one of claims 1 to 8 by running the computer program.

12. A computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the health management intervention method according to any one of claims 1 to 8.

Images