Health monitoring platform based on CCRC and application thereof

Abstract

The invention discloses a CCRC-based health monitoring platform and application thereof, and belongs to the technical field of health monitoring, and the CCRC-based health monitoring platform comprises a data acquisition module, a monitoring item recommendation module, a CCRC management module, a CCRC management module, a CCRC management module and a CCRC management module, and the monitoring item recommendation module is used for establishing a monitoring item recommendation module to carry out detection items of health monitoring data based on personal preferences on the platform user so as to update health information. According to the invention, after the basic information of the user platform is acquired in real time through the data acquisition module, health monitoring can be carried out based on the user information, and preference pushing can be carried out on the information of the user to be subjected to health monitoring based on the personal information and the acquired user preference data; a health monitoring plan can be established according to the conditions and preferences of the user, the quality of pension service is improved, precise monitoring of the health of the elderly is expected to be realized, and the manpower and material resource cost is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of health monitoring, and in particular relates to a CCRC-based health monitoring platform and application thereof. Background Art

[0002] The CCRC model, or "continuing care retirement community", is a comprehensive model of elderly care. This model combines the advantages of home-based elderly care, community-based elderly care and institutional elderly care, and aims to provide a full range of elderly care services and care for the elderly. The CCRC model originated in the United States. With the aging of the population, this model has gradually attracted the attention of the Chinese elderly care industry. By 2020, the number of elderly people aged 60 and above in China will reach 245 million, and it is expected to exceed 400 million by 2050. Faced with the contradiction between the growing demand for elderly care services and the limited supply of resources, the CCRC model provides a more reasonable and effective way to allocate elderly care resources.

[0003] The patent document with application publication number CN114708129A discloses a new type of CCRC composite health care complex, which is a community with two types of land, namely, land for elderly care services and land for construction. A smart community system, a smart elderly care system, a smart medical system, a health management system, a smart financial system, a community life supporting system, and a service operation management system are built on the land for elderly care services; residential property-type home health care houses that can be sold or leased are built on the construction land, and a smart family system is built in the health care houses. The present invention combines a socialized elderly care center that combines medical care and health care with a property-type elderly care community, so that the elderly can live in a familiar environment and receive care services. However, in actual use, the above platform lacks the ability to monitor the elderly's own health status in real time in the service for the elderly, resulting in the elderly's physical health in the elderly care environment relying on the judgment of the elderly's autonomous consciousness, or the detection of health data under the guidance of a health physician, which will consume a lot of manpower and material resources, and there is room for improvement. Summary of the invention

[0004] The purpose of the present invention is to propose a health monitoring platform based on CCRC and its application in order to solve the problem that the physical health of the elderly in a nursing environment depends on the elderly's autonomous judgment or the detection of health data under the guidance of a health physician, which will consume a lot of manpower and material resources.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A health monitoring platform based on CCRC, including a data collection module, which is used to collect and maintain basic information of users of the monitoring platform at regular intervals according to user information recorded on the platform;

[0007] The health monitoring module is used to monitor the health information of platform users through their basic personal information;

[0008] Personal information storage module, used to store basic personal information and health information of platform users;

[0009] The monitoring project recommendation module is used to establish a monitoring project recommendation module to conduct testing projects for health monitoring data based on personal preferences of platform users in order to update health information.

[0010] As a further description of the above technical solution:

[0011] The data preprocessing module includes a data preprocessing module, which is in communication with the data acquisition module. The data preprocessing module processes the collected basic information data of the platform users, and extracts data feature information corresponding to the platform users.

[0012] As a further description of the above technical solution:

[0013] The data preprocessing module extracts data feature information corresponding to platform users, specifically including:

[0014] Data cleaning, by removing missing values ​​and outliers and performing data standardization;

[0015] Data conversion, converting text data into numerical features and health monitoring items into feature vectors.

[0016] As a further description of the above technical solution:

[0017] The project recommendation process of the monitoring project recommendation module is as follows: after setting the types of health monitoring projects of platform users to a given project set, after obtaining the sorting function through training, the sorting function generates a project ranking list for the target user, and recommends the list content to the user, and completes the recommendation of monitoring projects through the sorting learning model.

[0018] As a further description of the above technical solution:

[0019] Through the adversarial foraging method of bird flock foraging, different basic recommendation models are established to correspond to individual birds in the bird flock. The foraging behavior of individual birds is corresponded to the predicted value of each item by a single user, and the predicted value of the basic recommendation model is constructed into a feature matrix through feature fusion, that is, a data set of auxiliary information. According to the adversarial foraging characteristics, at least two feeders that simulate the foraging behavior of bird flocks are established. The foraging simulation of bird flocks is carried out under the interaction of the two feeders. By monitoring the foraging behavior of individual birds, the ranking recommendation of optimized monitoring items is obtained.

[0020] As a further description of the above technical solution:

[0021] The monitoring project recommendation module also includes a discriminator and a parameter updating module. The discriminator is used to evaluate the quality of the recommendation sequence obtained from the foraging behavior of individual birds. After obtaining the evaluation result of the discriminator, the feeder updates the current recommendation sequence of the feeder to optimize the recommendation result. The parameter updating module is used to update the parameters of the discriminator according to the number of evaluation copies of the discriminator.

[0022] As a further description of the above technical solution:

[0023] The monitoring project recommendation module also includes an alternating training module, which completes the project after the stop condition is met by alternately training the feeder and the discriminator.

[0024] As a further description of the above technical solution:

[0025] The basic information of the platform users includes age, gender, health status, interests and hobbies, and past records of participation in health monitoring and care activities.

[0026] As a further description of the above technical solution:

[0027] After the health monitoring module collects health information exceeding a set threshold through the data collection module, the health monitoring module transmits the information to the monitoring item recommendation module for data weighting.

[0028] As a further description of the above technical solution:

[0029] An application of a health monitoring platform based on CCRC, wherein the health monitoring platform is arranged on a mobile terminal, and the mobile terminal comprises an interactive module, and a data acquisition module and a personal information storage module in the health monitoring platform can be modified, viewed or used through the interactive module, and the health status of the user can be fed back through the interactive module for application in health monitoring of the elderly in a retirement community who are continuously cared for.

[0030] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0031] 1. In the present invention, after the basic information of the user platform is collected in real time through the data collection module, health monitoring can be performed based on the user information, and based on the personal information and the collected user preference data, the user's information to be monitored can be pushed according to the user's preferences, which is conducive to establishing a health monitoring plan according to the user's own situation and preferences, improving the quality of elderly care services, and is expected to achieve accurate monitoring of the health of the elderly and reduce manpower and material costs.

[0032] 2. In the present invention, the monitoring project recommendation module is designed to simulate the foraging behavior detection of bird flocks to achieve signal recommendation for different individuals. It can be targeted at the situation where the characteristics of the elderly's preferences are insufficient. The recommendation accuracy is improved through the adversarial interaction between the discriminator and the feeder. The discriminator can evaluate the matching degree between the currently recommended health monitoring project and the actual needs of the elderly. The discriminator is conducive to continuously learning and optimizing the recommendation strategy based on the feedback and historical data of the elderly. The feeder is responsible for generating new monitoring project recommendation plans and interacting adversarially with the discriminator. The feeder tries to generate recommendation plans that are closer and closer to the actual needs of the elderly, while the discriminator strives to identify and filter out inappropriate plans. The adversarial interaction helps to improve the recommendation accuracy and is conducive to synchronous optimization through different algorithms to obtain the most matching monitoring project recommendation sequence for individual health data. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a schematic diagram of the overall structure of a health monitoring platform based on CCRC proposed by the present invention;

[0034] Figure 2 This is a schematic diagram of the data preprocessing module structure of a CCRC-based health monitoring platform proposed in the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] See also Figure 1-Figure 2 ,The present invention provides a technical solution: a health monitoring platform based on CCRC, including a data acquisition module, which is used to collect and maintain basic information of users of the monitoring platform at regular intervals according to user information recorded by the platform;

[0037] The health monitoring module is used to monitor the health information of platform users through their basic personal information;

[0038] The basic information of the platform users includes age, gender, health status, hobbies and interests, and past records of participation in health monitoring and care activities. After the health monitoring module collects health information that exceeds the set threshold through the data acquisition module, the health monitoring module transmits the information to the monitoring project recommendation module for data weighting.

[0039] Among them, the data collection module collects user information including the acquisition of user information of the detection data in the cloud, and the wearable monitoring unit, by wearing the monitoring unit on the designated position of the patient's body through the prefabricated wearable device, so that the monitoring unit can monitor the patient's heart rate, body temperature and blood pressure in real time. After that, the monitoring unit transmits the collected user health information to the platform server and stores the information through the personal information storage module;

[0040] At the same time, a blockchain publicity and distribution system can be established when storing user personal information, and the public and private keys of the blockchain can be used to protect the user's personal privacy data. The health monitoring module monitors the health information of the monitoring platform users based on personal basic information. Specifically, the platform server compares the patient health information stored internally, and then sends the difference analyzed after comparison to the platform server through wireless communication. The information is then sent to the individual user's mobile terminal and related mobile devices of related family members through the platform server. When the monitoring unit detects that the patient's health indicators are too low or when the position sensor and posture sensor data sense that the user has fallen, the wearable terminal sends the patient's current status to the platform through the wireless communication unit. The platform calls on the personnel of the CCRC service community for timely treatment to improve the safety of the patient.

[0041] Personal information storage module, used to store basic personal information and health information of platform users;

[0042] The monitoring project recommendation module is used to establish a monitoring project recommendation module to conduct testing projects for health monitoring data based on personal preferences of platform users in order to update health information.

[0043] It also includes a data preprocessing module, which is in communication with the data acquisition module, processes the collected basic information data of the platform users through the data preprocessing module, and extracts data feature information corresponding to the platform users through the data preprocessing module;

[0044] The data preprocessing module extracts data feature information corresponding to platform users, specifically including:

[0045] Data cleaning, by removing missing values ​​and outliers and performing data standardization;

[0046] Data conversion, converting text data into numerical features and health monitoring items into feature vectors;

[0047] The monitoring project recommendation module is trained by the data of the data preprocessing module to construct a monitoring project recommendation model, which specifically includes:

[0048] When recommending monitoring items to platform users, the types of health monitoring items for platform users are set to a given set of items. After the sorting function is obtained through training, the sorting function generates a project ranking list for the target user and recommends the list content to the user. The recommendation of monitoring items is completed through the sorting learning model.

[0049] By using the adversarial foraging method of bird flocks, different recommendation models are used to correspond to individual birds in the flock, and the foraging behavior of individual birds is matched to obtain the prediction value of each project for a single user. The prediction value of the basic recommendation model is constructed through feature fusion to construct a feature matrix, that is, a data set of auxiliary information. According to the adversarial foraging characteristics, the foraging behavior of the optimal individual bird is judged to obtain the recommendation of the optimal monitoring project.

[0050] Initialization: Initialize the parameters of the bird flock foraging algorithm, such as flock size, maximum number of iterations, step size, etc.

[0051] Build basic models: Build multiple basic recommendation models as individual birds, and fuse their predicted score vectors to build a feature matrix.

[0052] Construct a ranking learning recommendation dataset: Group users, activities, and predicted rating vectors into four-tuples to form a ranking learning recommendation dataset, and divide the dataset into training set, validation set, and test set.

[0053] Simulate the foraging behavior of bird flocks: Establish at least two feeders that simulate the foraging behavior of bird flocks, and find the foraging behavior of the individual bird with the best foraging ability in the flock, that is, the optimal recommended sequence, by iteratively updating the recommended sequence;

[0054] After the feeder obtains the optimal recommended sequence through simulation, it uses the discriminator to determine whether the current foraging behavior is optimal.

[0055] Evaluate the quality of recommendation sequences: The recommendation sequences generated by the feeder are fed into the discriminator to evaluate their quality.

[0056] Update the recommended sequence: According to the evaluation results of the discriminator, update the recommended sequence to make it closer to the optimal sequence.

[0057] Training the discriminator: Evaluate the quality of the recommended sequence. The discriminator gives an evaluation score based on the quality of the recommended sequence. During training, the discriminator judges the quality of the current sequence by ranking the recommended dataset.

[0058] Among them, the feeder and the discriminator are both neural networks, and the sorting results can be fitted through the neural network, so as to calculate the loss function and the probability distribution list, and at the same time retain the feedback information, which can provide auxiliary feedback to the two feeders;

[0059] Through the setting of two feeders, at least one feeder is externally connected with the discriminator for information feedback to become the second feeder, and the feeder is internally connected with the other feeder called the first feeder through the feeder. The internal feedback connection between the first feeder and the second feeder can optimize the transmission of recommended items, enhance the sorting ability, and feed back the training information and content to each other, which is conducive to the probability distribution exploration through the feeder combined with the discriminator and improve the performance of the second feeder itself;

[0060] The input of the discriminator is real data, and the output is the interest level of platform users in the project. The discriminator continuously judges the optimization content provided by the second feeder, and updates it after feedback;

[0061] The internal objective function of the feeder improves the performance of the feeder fed back by the discriminator by maximizing the cross entropy loss. During training, the first feeder samples the production samples:

[0062]

[0063] Among them, i represents the sample input to the network, un represents the user, n is the user number, r represents the sample category, if r is 1, it is real, if r is 0, it represents a production sample;

[0064] p true (i|u n , r) is the probability distribution of the real sample i, To generate the probability distribution of sample i, y and θ are the parameters of the first feeder and the second feeder respectively;

[0065] First, the parameter θ is fixed, and the second feeder parameter is not updated. The first feeder is optimized and only updated When r = 0, the first feeder generates sample i, and it is hoped that the scoring function G(i|u n , r) evaluate the high score to make the overall expected value smaller, then, fix the parameter y, do not update the first feeder, and repeat the above steps to optimize the second feeder;

[0066] Update the discriminator parameters: Based on the evaluation score, update the discriminator parameters so that it can more accurately evaluate the quality of the recommended sequence;

[0067] The external objective function of the discriminator is to improve the discriminator performance by maximizing the cross entropy loss, hoping that the discriminator can discriminate the real sample as 1 and the generated sample as 0;

[0068] Specific:

[0069]

[0070] Among them, i represents the input network sample, un represents the platform user, n is the response code generated for the user, r represents the input sample category, r is 1 for a real sample, and r is 0 for a generated fake sample;

[0071] And ptrue(i|u n , r) is the probability distribution of the real sample i, p θ (i|u n , r) is the probability distribution of the generated samples of the second feeder, θ and δ are the parameters of the second feeder and the discriminator respectively, D(i|u n ) represents the score given to the user, and the output result is [0, 1], so and The value range of is [-∞, 0];

[0072] After parameter sampling, the training process:

[0073] Training the First Feeder:

[0074] Using LambdaRank as the basic model, combining the loss function of LambdaRank and the generation probability of the first feeder, we form the objective function, denoted as g γscore (i, u);

[0075] make but

[0076]

[0077] Through the Gγ (u n ) Find the partial derivative of γ, and the optimal parameter γ is approximately:

[0078]

[0079] Among them, N is the inverse of the maximum cumulative loss gain, and the loss function of the first feeder is Pointloss, which is used to generate the probability:

[0080]

[0081] Among them, K is the preference number of the characteristic user.

[0082] Repeat the above steps to train the second feeder, and receive the difficult samples from the first feeder, and provide false samples for the discriminator, fitting function g γscore (i,u) generation probability, p θ (i|u n , r);

[0083] Through information feedback, the optimal parameter θ* is found. The second feeder may perform poorly in the early training, so the first feeder is introduced to assist in training.

[0084] Training the Discriminator (DiScriminator):

[0085] Minimize the objective function by fitting the Dδscore(i,u) function;

[0086]

[0087] Among them, ptrue(i|u n , r) is the potential correlation distribution, representing the true probability, pθ(i|u n ,r) is the estimated probability of the second feeder. Through the interaction between models, the optimal δ is obtained. The discriminator uses Ranknet as the bottom-side model and pairloss as the loss function;

[0088]

[0089] By training the second feeder, it is possible to generate fake items that are of interest to the current user. After generating the items, the discriminator is used to adversarially determine whether the items actually exist.

[0090] Alternating training: The feeder and the discriminator are trained alternately until the stopping condition is met, the number of iterations reaches the maximum value, or the model performance no longer improves, that is, the model training is completed.

[0091] Generate recommendation list: Take the recommendation sequence generated by the trained feeder as the final recommendation result.

[0092] During the entire training process, the first feeder and the second feeder alternately generate recommendation sequences and perform adversarial training with the discriminator. Through continuous iterative optimization, the two feeders gradually improve the quality of generated recommendation sequences, and the discriminator gradually improves its ability to distinguish between real sequences and generated sequences. Finally, when the model reaches the predetermined stopping condition, such as the number of iterations reaches the maximum value or the model performance no longer improves significantly within a certain period of time, the training process ends and the model training is completed.

[0093] An application of a health monitoring platform based on CCRC, wherein the health monitoring platform is arranged on a mobile terminal, and the mobile terminal comprises an interactive module, and a data acquisition module and a personal information storage module in the health monitoring platform can be modified, viewed or used through the interactive module, and the health status of the user can be fed back through the interactive module for application in health monitoring of the elderly in a retirement community who are continuously cared for.

[0094] In the above embodiments, the personal information storage module applied to the health monitoring platform for executing the above method embodiments is a corresponding data storage system, which has at least one processor, a control module (chip set) coupled to at least one of the (at least one) processors, a memory coupled to the control module, a non-volatile memory (NVM) / storage device coupled to the control module, at least one input / output device coupled to the control module, and a network interface coupled to the control module.

[0095] The processor may include at least one single-core or multi-core processor, and the processor may include any combination of general-purpose processors or special-purpose processors (such as graphics processors, application processors, baseband processors, etc.). For some alternative implementations, the data storage system applied to the health monitoring platform can be used as the data storage system device applied to the health monitoring platform such as the gateway described in the embodiments of the present application.

[0096] For some alternative embodiments, a data storage system applied to a health monitoring platform may include at least one computer-readable medium (e.g., a memory or NVM / storage device) having instructions and at least one processor integrated with the at least one computer-readable medium and configured to execute the instructions to implement a module to perform the actions described in the present disclosure.

[0097] For one embodiment, the control module may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) and / or any suitable device or component in communication with the control module.

[0098] The control module may include a memory controller module to provide an interface to the memory. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0099] The memory may be used, for example, to load and store data and / or instructions for a data storage system applied to a health monitoring platform. For one embodiment, the memory may include any suitable volatile memory, for example, a suitable DRAM.

[0100] For one embodiment, the control module may include at least one input / output controller to provide an interface to the NVM / storage device and (at least one) input / output device.

[0101] For example, the NVM / storage device may be used to store data and / or instructions. The NVM / storage device may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable (at least one) non-volatile storage device (e.g., at least one hard disk drive (HDD), at least one compact disk (CD) drive, and / or at least one digital versatile disk (DVD) drive).

[0102] The NVM / storage device may include storage resources that are physically part of a device on which a data storage system for a health monitoring platform is installed, or that may be accessible to the device without being part of the device. For example, the NVM / storage device may be accessible via (at least one) input / output device over a network.

[0103] (At least one) input / output device may provide an interface for the data storage system applied to the health monitoring platform to communicate with any other appropriate device, and the input / output device may include a communication component, a pinyin component, a sensor component, etc. The network interface may provide an interface for the data storage system applied to the health monitoring platform to communicate based on at least one network, and the data storage system applied to the health monitoring platform may wirelessly communicate with at least one component of the wireless network based on any standard and / or protocol of at least one wireless network standard and / or protocol, such as accessing a wireless network based on a communication standard.

[0104] In the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance; the term "plurality" refers to two or more, unless otherwise clearly defined. The terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; "connected" can be a direct connection or an indirect connection through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0105] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A health monitoring platform based on CCRC, characterized in that: It includes a data collection module, which is used to collect and maintain basic information of users on the monitoring platform at regular intervals based on user information recorded on the platform; The health monitoring module is used to monitor the health information of platform users through their basic personal information; Personal information storage module, used to store basic personal information and health information of platform users; The monitoring project recommendation module is used to establish a monitoring project recommendation module to conduct testing projects for health monitoring data based on personal preferences of platform users in order to update health information.

2. A health monitoring platform based on CCRC according to claim 1, characterized in that: It also includes a data preprocessing module, which is in communication with the data acquisition module. The data preprocessing module processes the collected basic information data of the platform users and extracts data feature information corresponding to the platform users.

3. A CCRC-based health monitoring platform according to claim 2, characterized in that: The data preprocessing module extracts data feature information corresponding to platform users, specifically including: Data cleaning, by removing missing values ​​and outliers and performing data standardization; Data conversion, converting text data into numerical features and health monitoring items into feature vectors.

4. A health monitoring platform based on CCRC according to claim 1, characterized in that: The project recommendation process of the monitoring project recommendation module is as follows: after setting the types of health monitoring projects of platform users to a given project set, after obtaining the sorting function through training, the sorting function generates a project ranking list for the target user, and recommends the list content to the user, and completes the recommendation of monitoring projects through the sorting learning model.

5. A CCRC-based health monitoring platform according to claim 4, characterized in that: Through the adversarial foraging method of bird flock foraging, different basic recommendation models are established to correspond to individual birds in the bird flock. The foraging behavior of individual birds is corresponded to the predicted value of each item by a single user, and the predicted value of the basic recommendation model is constructed into a feature matrix through feature fusion, that is, a data set of auxiliary information. According to the adversarial foraging characteristics, at least two feeders that simulate the foraging behavior of bird flocks are established. The foraging simulation of bird flocks is carried out under the interaction of the two feeders. By monitoring the foraging behavior of individual birds, the ranking recommendation of optimized monitoring items is obtained.

6. A CCRC-based health monitoring platform according to claim 5, characterized in that: The monitoring item recommendation module also includes a discriminator and a parameter updating module. The discriminator is used to evaluate the quality of the recommendation sequence obtained from the foraging behavior of individual birds. After obtaining the evaluation result of the discriminator, the feeder updates the current recommendation sequence of the feeder to optimize the recommendation result. The parameter updating module is used to update the parameters of the discriminator according to the evaluation number of the discriminator. Among them, the internal objective function of the feeder improves the performance of the feeder with feedback from the discriminator by maximizing the cross entropy loss. During the training process, the first feeder samples the production samples: Among them, i represents the sample input to the network, un represents the user, n is the user number, r represents the sample category, if r is 1, it is real, if r is 0, it represents a production sample; p true (i|u n , r) is the probability distribution of the real sample i, To generate the probability distribution of sample i, y and θ are the parameters of the first feeder and the second feeder respectively; First, the parameter θ is fixed, and the second feeder parameter is not updated. The first feeder is optimized and only updated When r = 0, the first feeder generates sample i, and it is hoped that the scoring function G(i|u n , r) evaluate the high score to make the overall expected value smaller, then, fix the parameter y, do not update the first feeder, and repeat the above steps to optimize the second feeder; The external objective function of the discriminator is to improve the discriminator performance by maximizing the cross entropy loss, hoping that the discriminator can discriminate the real sample as 1 and the generated sample as 0; Among them, i represents the input network sample, un represents the platform user, n is the response code generated for the user, r represents the input sample category, r is 1 for a real sample, and r is 0 for a generated fake sample; And ptrue(i|u n , r) is the probability distribution of the real sample i, p θ (i|u n , r) is the probability distribution of the generated samples of the second feeder, 0 and δ are the parameters of the second feeder and the discriminator respectively, D(i|u n ) represents the score given to the user, and the output result is [0, 1], so log D(i|u n ) and log(1-D(i|u n ) ranges from [-∞, 0].

7. A CCRC-based health monitoring platform according to claim 6, characterized in that: The monitoring project recommendation module also includes an alternating training module, which completes the project after the stop condition is met by alternately training the feeder and the discriminator.

8. A health monitoring platform based on CCRC according to claim 1, characterized in that: The basic information of the platform users includes age, gender, health status, interests and hobbies, and past records of participation in health monitoring and care activities.

9. A CCRC-based health monitoring platform according to claim 1, characterized in that: After the health monitoring module collects health information exceeding a set threshold through the data collection module, the health monitoring module transmits the information to the monitoring item recommendation module for data weighting.

10. An application of a health monitoring platform based on CCRC according to any one of claims 1 to 9, characterized in that: The health monitoring platform is arranged on a mobile terminal, which includes an interactive module. The data acquisition module and the personal information storage module in the health monitoring platform can be modified, viewed or used through the interactive module. The health status of the user can be fed back through the interactive module for application in the health monitoring of the elderly in the retirement community who are continuously cared for.

Images