CN118280606A - Intelligent accompanying equipment control method and system - Google Patents

Abstract

The present invention discloses a control method and system of intelligent accompanying equipment, and relates to the field of intelligent accompanying technology. The method comprises: performing data regularization and time series coding on the time series of physiological state parameters according to the parameter sample dimension respectively to obtain the implicit feature vector associated with the time series of blood pressure and the implicit feature vector associated with the time series of blood sugar; then the implicit feature vector associated with the time series of blood pressure and the implicit feature vector associated with the time series of blood sugar are fused by a feature fusion module guided by Gaussian prior distribution to obtain the time series associated feature vector under the prior constraint of blood sugar and blood pressure, so as to determine whether to generate an emergency warning prompt signal of the physiological state to the community medical center. In this way, not only can the problems of underreporting, false alarm and hysteresis caused by the threshold monitoring alarm method of the traditional scheme be avoided, but also personalized physiological state monitoring services can be provided for different elderly subjects to better meet the health management needs of users.

Description

Intelligent accompanying equipment control method and system

Technical Field

The present invention relates to the technical field of intelligent accompanying technology, and in particular to an intelligent accompanying equipment control method and a system thereof.

Background technique

As the population ages, the health management and care needs of the elderly are becoming increasingly prominent. As a monitoring and management device, the accompanying device can provide continuous monitoring, health management and emergency rescue services for the elderly, patients or people who need special care.

However, traditional accompanying equipment can usually only realize simple user physiological data monitoring and threshold alarm functions, lacking efficient data processing and analysis capabilities, and cannot provide personalized health management and physiological status emergency warning services based on individual differences of users, and often has false alarms and missed alarms. In addition, the intelligence level of traditional accompanying equipment is low, and the threshold monitoring and alarm methods will lead to a lag in alarms. In other words, the alarm will only be issued when the elderly user has an abnormal physiological state, and it is unable to respond to the user's emergency in time, thus lacking a timely and effective rescue mechanism.

Therefore, a smart accompanying equipment control solution is desired.

Summary of the invention

This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

In a first aspect, the present invention provides a method for controlling an intelligent accompanying device, the method comprising:

Receiving a time series of physiological state parameters of a monitored elderly subject collected by a smart wearable device, wherein the physiological state parameters include blood pressure value and blood sugar value;

Regularizing the time series of the physiological state parameters according to the parameter sample dimensions to obtain a time series of blood pressure values and a time series of blood sugar values;

Performing time series coding on the time series of the blood pressure value and the time series of the blood sugar value respectively to obtain a blood pressure time series associated implicit feature vector and a blood sugar time series associated implicit feature vector;

The blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector are passed through a feature fusion module guided by Gaussian prior distribution to obtain a time series associated feature vector under blood sugar-blood pressure prior constraints;

Based on the time series correlation feature vector under the blood sugar-blood pressure prior constraint, determining whether to generate an emergency warning prompt signal of the physiological state to the community medical center;

The blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector are fused by a feature fusion module guided by Gaussian prior distribution to obtain a time series associated feature vector under blood sugar-blood pressure prior constraints, including:

Respectively calculating the prior factors of the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector to obtain the blood pressure time series associated prior feature vector and the blood sugar time series associated prior feature vector;

The position-based sum of the blood pressure time series association priori feature vector and the blood sugar time series association priori feature vector is calculated to obtain the time series association feature vector under the blood sugar-blood pressure prior constraint.

Optionally, the time series of the blood pressure values and the time series of the blood sugar values are respectively time-series encoded to obtain a blood pressure time series associated implicit feature vector and a blood sugar time series associated implicit feature vector, including: passing the time series of the blood pressure values through a blood pressure sequence encoder based on an RNN model to obtain the blood pressure time series associated implicit feature vector; passing the time series of the blood sugar values through a blood sugar sequence encoder based on an RNN model to obtain the blood sugar time series associated implicit feature vector.

Optionally, the prior factors of the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector are calculated respectively to obtain the blood pressure time series associated prior feature vector and the blood sugar time series associated prior feature vector, including: multiplying the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector by predetermined weight hyperparameters by position respectively to obtain weight modulated blood pressure time series associated implicit feature vector and weight modulated blood sugar time series associated implicit feature vector; using each position feature value in the weight modulated blood pressure time series associated implicit feature vector and the weight modulated blood sugar time series associated implicit feature vector as the exponent of the natural constant to calculate the exponential function value with the natural constant as the base by position to obtain the weight modulated blood pressure time series associated class support feature vector and the weight modulated blood sugar time series associated class support feature vector; multiplying the weight modulated blood pressure time series associated class support feature vector by the first Gaussian distribution random number function value to obtain the blood pressure time series associated prior feature vector; multiplying the weight modulated blood sugar time series associated class support feature vector by the second Gaussian distribution random number function value to obtain the blood sugar time series associated prior feature vector.

Optionally, the first Gaussian distribution random number function value and the second Gaussian distribution random number function value are both generated by a Gaussian distribution random number function with a mean of 0 and a variance of 1.

Optionally, based on the time series correlation feature vector under the blood sugar-blood pressure prior constraint, determining whether to generate an emergency warning prompt signal for a physiological state to the community medical center includes: passing the time series correlation feature vector under the blood sugar-blood pressure prior constraint through a classifier-based controller to obtain a control instruction, and the control instruction is used to indicate whether to generate an emergency warning prompt signal for a physiological state to the community medical center.

Optionally, the time-series correlation feature vector under the blood sugar-blood pressure prior constraint is passed through a classifier-based controller to obtain a control instruction, and the control instruction is used to indicate whether to generate a physiological state emergency warning prompt signal to the community medical center, including: using multiple fully connected layers of the classifier-based controller to fully connect encode the time-series correlation feature vector under the blood sugar-blood pressure prior constraint to obtain a coded classification feature vector; passing the coded classification feature vector through the Softmax classification function of the classifier-based controller to obtain the control instruction.

In a second aspect, the present invention provides an intelligent accompanying equipment control system, the system comprising:

A physiological state parameter acquisition module, used to receive a time series of physiological state parameters of a monitored elderly subject acquired by a smart wearable device, wherein the physiological state parameters include blood pressure and blood sugar values;

A data regularization module, used for regularizing the time series of the physiological state parameters according to the parameter sample dimension to obtain a time series of blood pressure values and a time series of blood sugar values;

A time series encoding module, used for performing time series encoding on the time series of the blood pressure value and the time series of the blood sugar value respectively to obtain a blood pressure time series associated implicit feature vector and a blood sugar time series associated implicit feature vector;

A feature fusion module, used for combining the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector through a feature fusion module guided by Gaussian prior distribution to obtain a time series associated feature vector under blood sugar-blood pressure prior constraints;

An emergency warning prompt determination module is used to determine whether to generate an emergency warning prompt signal of a physiological state to a community medical center based on the time series correlation feature vector under the blood sugar-blood pressure prior constraint;

Wherein, the feature fusion module includes:

A priori factor calculation unit, used to calculate the priori factors of the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector respectively to obtain the blood pressure time series associated priori feature vector and the blood sugar time series associated priori feature vector;

The position-based summation calculation unit is used to calculate the position-based summation between the blood pressure time series associated priori feature vector and the blood sugar time series associated priori feature vector to obtain the time series associated feature vector under the blood sugar-blood pressure prior constraint.

Optionally, the timing encoding module includes: a blood pressure sequence encoding unit, used to pass the time series of the blood pressure values through a blood pressure sequence encoder based on an RNN model to obtain an implicit feature vector associated with the blood pressure time series; and a blood glucose sequence encoding unit, used to pass the time series of the blood glucose values through a blood glucose sequence encoder based on an RNN model to obtain an implicit feature vector associated with the blood glucose time series.

By adopting the above technical solution, the time series of physiological state parameters are data regularized and time-series encoded according to the parameter sample dimension to obtain the implicit feature vector of blood pressure time series association and the implicit feature vector of blood sugar time series association; then the implicit feature vector of blood pressure time series association and the implicit feature vector of blood sugar time series association are obtained through the feature fusion module guided by Gaussian prior distribution to obtain the time series association feature vector under the prior constraint of blood sugar-blood pressure, so as to determine whether to generate an emergency warning signal of physiological state to the community medical center. In this way, not only can the problems of underreporting, false alarm and hysteresis caused by the threshold monitoring alarm method of the traditional solution be avoided, but also personalized physiological state monitoring services can be provided for different elderly subjects to better meet the health management needs of users.

Other features and advantages of the present invention will be described in detail in the following detailed description.

BRIEF DESCRIPTION OF THE DRAWINGS

The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

Fig. 1 is a flow chart showing a method for controlling an intelligent accompanying device according to an exemplary embodiment.

Fig. 2 is a block diagram showing a control system of an intelligent accompanying device according to an exemplary embodiment.

Fig. 3 is a block diagram of an electronic device according to an exemplary embodiment.

Fig. 4 is an application scenario diagram of a method for controlling an intelligent accompanying device according to an exemplary embodiment.

Detailed ways

Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and/or in parallel. In addition, the method embodiments may include additional steps and/or omit the steps shown. The scope of the present invention is not limited in this respect.

The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

Traditional accompanying devices have some limitations in user physiological monitoring and alarms. They mainly provide basic physiological data tracking and simple threshold crossing alarms, but these functions usually do not have in-depth data analysis capabilities. Therefore, it is difficult for these devices to provide customized health management solutions based on the user's personal health status, and it is also difficult to achieve early warning of specific health risks of users, which may lead to false alarms or missed alarms, affecting the user's experience and health safety.

In addition, the intelligence level of traditional accompanying devices is relatively low. They usually issue alarms only when the user's physiological indicators exceed the preset threshold, which may cause delays in alarm. In other words, the device will only trigger the alarm mechanism when the elderly user's physiological state has become obviously abnormal, which is not conducive to rapid response to emergency health situations and timely rescue.

In order to improve the effectiveness and accuracy of accompanying equipment, the following improvement directions can be considered:

1. Improve the ability to interpret users’ physiological data by applying advanced data analysis techniques, such as machine learning and data mining, thereby providing more accurate health assessments.

2. Design personalized monitoring plans and health management plans based on individual differences such as age, health status, and living habits of users.

3. Develop a system that can monitor the user’s physiological status in real time and issue early warnings so that action can be taken at the early stages of a health crisis.

4. Improve the alarm mechanism so that it is not only based on threshold judgment, but also combines the user's historical data and pattern recognition to reduce false positives and false negatives.

5. Combine the accompanying device with emergency response services to immediately contact medical service providers or family members once an abnormality is detected.

6. Design a user interface that is easy to understand and operate to ensure that elderly users can use the device conveniently.

Through these improvements, accompanying equipment can be more intelligent and personalized, providing users with more accurate and timely health management services.

In order to solve the above problems, the present invention provides a smart accompanying equipment control method and system thereof, which regularizes the time series of physiological state parameters according to the parameter sample dimension and performs time series encoding to obtain the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector; then the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector are passed through a feature fusion module guided by Gaussian prior distribution to obtain the time series associated feature vector under the blood sugar-blood pressure prior constraint, so as to determine whether to generate a physiological state emergency warning prompt signal to the community medical center. In this way, not only can the problems of underreporting, false alarm and hysteresis caused by the threshold monitoring alarm method of the traditional solution be avoided, but also personalized physiological state monitoring services can be provided for different elderly objects to better meet the health management needs of users.

The specific implementation modes of the present invention are described in detail below with reference to the accompanying drawings.

FIG. 1 is a flow chart of a method for controlling an intelligent accompanying device according to an exemplary embodiment. As shown in FIG. 1 , the method includes:

Step 101: receiving a time series of physiological state parameters of a monitored elderly subject collected by a smart wearable device, wherein the physiological state parameters include blood pressure and blood sugar levels;

Step 102: Regularize the time series of the physiological state parameters according to the parameter sample dimensions to obtain a time series of blood pressure values and a time series of blood sugar values;

Step 103, respectively performing time series coding on the time series of the blood pressure value and the time series of the blood sugar value to obtain a blood pressure time series associated implicit feature vector and a blood sugar time series associated implicit feature vector;

Step 104: The blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector are fused through a feature fusion module guided by Gaussian prior distribution to obtain a time series associated feature vector under blood sugar-blood pressure prior constraints;

Step 105: Determine whether to generate an emergency warning signal of a physiological state to the community medical center based on the time series correlation feature vector under the blood sugar-blood pressure prior constraint.

In view of the above technical problems, in the technical solution of the present invention, a control method of intelligent accompanying equipment is proposed, which can monitor and collect the physiological state parameters of the elderly subject, including blood pressure and blood sugar values, in real time through intelligent wearable devices, and use data processing and analysis algorithms based on artificial intelligence and deep learning in the back end to perform time series collaborative correlation analysis of these physiological state parameter time series data, so as to learn and capture the time series change patterns and characteristics of the blood pressure and blood sugar of the elderly subject, so as to use the blood pressure time series characteristics and blood sugar time series characteristics as prior information to perform physiological state monitoring and emergency warning of the elderly subject. This can not only avoid the problems of underreporting, false alarms and hysteresis caused by the threshold monitoring and alarm method of the traditional solution, but also provide personalized physiological state monitoring services for different elderly subjects to better meet the health management needs of users.

Specifically, in the technical solution of the present invention, first, a time series of physiological state parameters of the monitored elderly object collected by the smart wearable device is received, wherein the physiological state parameters include blood pressure values and blood sugar values. Next, considering that the physiological state parameters of the monitored elderly object include blood pressure values and blood sugar values, and the blood pressure values and blood sugar values will continue to change over time in the time dimension. Therefore, in order to be able to analyze and capture the time series change patterns and trends of the blood pressure values and blood sugar values of the elderly object in the time dimension respectively, so as to more accurately perform personalized physiological state monitoring and physiological state emergency warning of the elderly object, in the technical solution of the present invention, it is necessary to regularize the time series of the physiological state parameters according to the parameter sample dimension to obtain the time series of blood pressure values and the time series of blood sugar values.

It should be understood that the temporal variation patterns and characteristics of physiological parameters of different individuals in the time dimension may have individual differences, so personalized health management becomes particularly important. Blood pressure and blood sugar values are important indicators of human health status. In order to be able to perform personalized feature analysis and capture of the blood pressure time series pattern and blood sugar time series pattern of the monitored elderly object, so as to perform personalized physiological state monitoring and early warning for the monitored elderly object, in the technical solution of the present invention, it is necessary to extract the blood pressure time series characteristics and blood sugar time series characteristic information in the time series of the blood pressure value and the time series of the blood sugar value. Specifically, in the technical solution of the present invention, the time series of the blood pressure value is encoded by a blood pressure sequence encoder based on the RNN model to extract the time series dynamic implicit correlation characteristics of the blood pressure value in the time dimension, reflecting the time series pattern and change trend of the blood pressure, thereby obtaining the blood pressure time series correlation implicit feature vector. In addition, the time series of the blood sugar value is encoded by a blood sugar sequence encoder based on the RNN model to extract the time series dynamic implicit correlation characteristics of the blood sugar value in the time dimension, reflecting the time series pattern and change trend of the blood sugar, thereby obtaining the blood sugar time series correlation implicit feature vector.

In one embodiment of the present invention, the time series of the blood pressure values and the time series of the blood sugar values are respectively time-series encoded to obtain a blood pressure time series associated implicit feature vector and a blood sugar time series associated implicit feature vector, including: passing the time series of the blood pressure values through a blood pressure sequence encoder based on an RNN model to obtain the blood pressure time series associated implicit feature vector; passing the time series of the blood sugar values through a blood sugar sequence encoder based on an RNN model to obtain the blood sugar time series associated implicit feature vector.

Furthermore, since blood pressure and blood sugar values are important indicators of human health, there is a certain correlation and mutual influence between them, and the temporal change patterns and characteristics of the physiological parameters of different elderly individuals in the time dimension also have individual differences. Therefore, in order to more accurately monitor the physiological state of the monitored elderly object and provide emergency warnings, in the technical solution of the present invention, the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector are further combined through a feature fusion module guided by a Gaussian prior distribution to obtain a time series associated feature vector under the blood sugar-blood pressure prior constraint. Through the processing of the feature fusion module guided by the Gaussian prior distribution, the temporal dynamic implicit association features of the blood pressure value and the temporal dynamic implicit association features of the blood sugar value can be interactively and associated, so as to learn and mine the temporal pattern features and correlation relationship between the blood pressure and blood sugar of the monitored elderly object, thereby using these learned and captured characteristic Gaussian prior distributions as prior knowledge to guide the constraint expression of the blood pressure-blood sugar temporal association pattern and features of the elderly object. In this way, it is possible to maintain certain constraints and smoothness in the process of associating and fusing the blood pressure time series characteristics and blood sugar time series characteristics of the monitored elderly subject, which helps to use the known blood pressure time series pattern and blood sugar time series pattern information to better characterize the physiological state time series pattern and change trend of the individual elderly subject, thereby improving the comprehensiveness and integration of the physiological state time series feature representation, which helps to improve the model's understanding and inference ability of individual health status, help to detect abnormal change patterns or trends early, warn of possible health risks in advance, and take corresponding intervention measures.

The blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector are processed by the feature fusion module guided by Gaussian prior distribution according to the following fusion formula to obtain the blood sugar-blood pressure time series associated feature vector under the prior constraint;

Among them, the fusion formula is:

;

in, is the blood pressure time series associated implicit feature vector, is the blood glucose time series associated implicit feature vector, and is the weight hyperparameter, and The Gaussian distribution function with a mean of 0 and a variance of 1 is used as the hyperparameter of the Gaussian distribution function coefficient. is vector addition, It is the time series correlation feature vector under the blood glucose-blood pressure prior constraint.

Among them, the first Gaussian distribution random number function value and the second Gaussian distribution random number function value are both generated by a Gaussian distribution random number function with a mean of 0 and a variance of 1.

In one embodiment of the present invention, the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector are passed through a feature fusion module guided by Gaussian prior distribution to obtain a time series associated feature vector under a blood sugar-blood pressure prior constraint, including: respectively calculating the prior factors of the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector to obtain a blood pressure time series associated prior feature vector and a blood sugar time series associated prior feature vector, where the prior factor refers to a parameter or variable determined based on prior knowledge when performing probability inference; calculating the positional sum between the blood pressure time series associated prior feature vector and the blood sugar time series associated prior feature vector to obtain the time series associated feature vector under the blood sugar-blood pressure prior constraint.

Furthermore, the prior factors of the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector are calculated respectively to obtain the blood pressure time series associated prior feature vector and the blood sugar time series associated prior feature vector, including: multiplying the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector by predetermined weight hyperparameters by position respectively to obtain the weight modulated blood pressure time series associated implicit feature vector and the weight modulated blood sugar time series associated implicit feature vector; using the characteristic values of each position in the weight modulated blood pressure time series associated implicit feature vector and the weight modulated blood sugar time series associated implicit feature vector as the exponent of the natural constant to calculate the exponential function value with the natural constant as the base by position to obtain the weight modulated blood pressure time series associated class support feature vector and the weight modulated blood sugar time series associated class support feature vector; multiplying the weight modulated blood pressure time series associated class support feature vector by the first Gaussian distribution random number function value to obtain the blood pressure time series associated prior feature vector; multiplying the weight modulated blood sugar time series associated class support feature vector by the second Gaussian distribution random number function value to obtain the blood sugar time series associated prior feature vector.

Then, the time series correlation feature vector under the blood sugar-blood pressure prior constraint is passed through a classifier-based controller to obtain a control instruction, and the control instruction is used to indicate whether to generate a physiological state emergency warning prompt signal to the community medical center. In other words, the time series correlation feature information between the blood pressure time series characteristics and the blood sugar time series characteristics of the monitored elderly subject under the pattern prior information constraint is used for classification processing, so as to perform physiological state monitoring and emergency warning of the elderly subject. In this way, the intelligence level of the accompanying equipment can be improved, not only can the problems of underreporting, false alarms and hysteresis caused by the threshold monitoring and alarm method of the traditional solution be avoided, but also personalized physiological state monitoring services can be provided for different elderly subjects to better meet the health management needs of users.

In one embodiment of the present invention, based on the time series correlation feature vector under the blood sugar-blood pressure prior constraint, determining whether to generate an emergency warning prompt signal of a physiological state to a community medical center includes: passing the time series correlation feature vector under the blood sugar-blood pressure prior constraint through a classifier-based controller to obtain a control instruction, and the control instruction is used to indicate whether to generate an emergency warning prompt signal of a physiological state to the community medical center.

Among them, the time series correlation feature vector under the blood sugar-blood pressure prior constraint is passed through a classifier-based controller to obtain a control instruction, and the control instruction is used to indicate whether to generate an emergency warning prompt signal of a physiological state to the community medical center, including: using multiple fully connected layers of the classifier-based controller to fully connect encode the time series correlation feature vector under the blood sugar-blood pressure prior constraint to obtain a coded classification feature vector; passing the coded classification feature vector through the Softmax classification function of the classifier-based controller to obtain the control instruction.

In a preferred embodiment of the above technical solution, the time series correlation feature vector under the blood sugar-blood pressure prior constraint is passed through a classifier-based controller to obtain a control instruction, which includes:

Calculating the position-by-position mean of the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector to obtain a blood pressure-blood sugar time series associated implicit feature mean vector;

Calculate the position-based exponential function of each eigenvalue of the blood pressure-blood sugar time series associated latent feature mean vector with the natural constant as the base to obtain the blood pressure-blood sugar time series associated latent feature class regression vector;

Determine a blood pressure time series correlation feature matrix and a blood sugar time series correlation feature matrix of the classifier for the blood pressure time series correlation implicit feature vector and the blood sugar time series correlation implicit feature vector;

The blood pressure-blood sugar time series association latent feature class regression vector is matrix-multiplied with the blood pressure time series association feature matrix, and then matrix-multiplied with the blood sugar time series association feature matrix, and the feature vector obtained after the multiplication is dotted with the blood pressure-blood sugar time series association latent feature class regression vector to obtain a blood pressure-blood sugar time series association correction vector;

Performing point multiplication fusion on the blood pressure-blood sugar time series correlation correction vector and the blood sugar-blood pressure time series correlation feature vector under prior constraints to obtain an optimized blood sugar-blood pressure time series correlation feature vector under prior constraints;

The optimized time series correlation feature vector under the blood sugar-blood pressure prior constraint is passed through a classifier-based controller to obtain a control instruction.

Here, the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector have different time series dimension feature representations of heterogeneous data on the model parallel branch pipeline. Therefore, in order to solve the problem of learning the high-order fusion representation of the regression specific features of the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector on the model parallel branch pipeline while maintaining the distinguishability of their heterogeneous data time series associated features, the above steps use the mean of the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector as the intermediate feature, and calculate their exponential function with natural constant as the base to obtain regression-like features, so as to perform query-support matching on the blood pressure time series associated feature matrix and the blood sugar time series associated feature matrix of the classifier, thereby strengthening the feature correspondence enrichment-type discrimination learning under the model parallel branch structure through feature class regression association under different representation dimensions. Then, by using the blood pressure-blood sugar time series correlation correction vector to correct the time series correlation feature vector under the blood sugar-blood pressure prior constraint, the generalization of the time series correlation feature vector under the blood sugar-blood pressure prior constraint during classification regression based on the distinguishing property of regression specific features can be improved, thereby improving the accuracy of the classification results during model inference. In this way, intelligent accompanying equipment can be used to more accurately monitor the physiological state of elderly subjects, so as to detect abnormal conditions in time and issue emergency warnings, which is conducive to taking corresponding measures in time to improve the quality of life and health level of the elderly.

In summary, the above scheme is adopted to monitor and collect the physiological state parameters of the elderly subjects in real time through smart wearable devices, including blood pressure and blood sugar values, and use data processing and analysis algorithms based on artificial intelligence and deep learning in the back end to perform time series collaborative correlation analysis of these physiological state parameter time series data, so as to learn and capture the time series change patterns and characteristics of the blood pressure and blood sugar of the elderly subjects, so as to use the blood pressure time series characteristics and blood sugar time series characteristics as prior information to monitor the physiological state of the elderly subjects and conduct emergency warnings. This can not only avoid the problems of underreporting, false alarms and hysteresis caused by the threshold monitoring and alarm method of the traditional scheme, but also provide personalized physiological state monitoring services for different elderly subjects to better meet the health management needs of users.

FIG2 is a block diagram of a smart accompanying device control system according to an exemplary embodiment. As shown in FIG2 , the system 200 includes:

A physiological state parameter collection module 201 is used to receive a time series of physiological state parameters of a monitored elderly subject collected by a smart wearable device, wherein the physiological state parameters include blood pressure and blood sugar values;

A data regularization module 202, configured to regularize the time series of the physiological state parameters according to the parameter sample dimension to obtain a time series of blood pressure values and a time series of blood sugar values;

A time series encoding module 203, used to perform time series encoding on the time series of the blood pressure value and the time series of the blood sugar value to obtain a blood pressure time series associated implicit feature vector and a blood sugar time series associated implicit feature vector;

A feature fusion module 204 is used to combine the blood pressure time series associated implicit feature vector and the blood glucose time series associated implicit feature vector through a feature fusion module guided by Gaussian prior distribution to obtain a time series associated feature vector under blood glucose-blood pressure prior constraints;

The emergency warning prompt determination module 205 is used to determine whether to generate a physiological state emergency warning prompt signal to the community medical center based on the time series correlation feature vector under the blood sugar-blood pressure prior constraint.

In one embodiment of the present invention, the timing encoding module 203 includes: a blood pressure sequence encoding unit, which is used to pass the time series of the blood pressure values through a blood pressure sequence encoder based on an RNN model to obtain the blood pressure time series associated implicit feature vector; a blood glucose sequence encoding unit, which is used to pass the time series of the blood glucose values through a blood glucose sequence encoder based on an RNN model to obtain the blood glucose time series associated implicit feature vector.

In one embodiment of the present invention, the feature fusion module 204 includes: a priori factor calculation unit, which is used to calculate the priori factors of the blood pressure time series associated implicit feature vector and the blood sugar time series associated implicit feature vector respectively to obtain the blood pressure time series associated prior feature vector and the blood sugar time series associated prior feature vector; a positional summation calculation unit, which is used to calculate the positional sum between the blood pressure time series associated prior feature vector and the blood sugar time series associated prior feature vector to obtain the time series association feature vector under the blood sugar-blood pressure prior constraint.

Referring to FIG3 below, it shows a schematic diagram of the structure of an electronic device 600 suitable for implementing an embodiment of the present invention. The terminal device in the embodiment of the present invention may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. The electronic device shown in FIG3 is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

As shown in FIG3 , the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to the bus 604.

Typically, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 608 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 609. The communication device 609 may allow the electronic device 600 to communicate wirelessly or wired with other devices to exchange data. Although FIG. 3 shows an electronic device 600 with various devices, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively.

In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present invention are executed.

It should be noted that the computer-readable medium of the present invention can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperTextTransferProtocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

Computer program code for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and/or flow chart, and the combination of the square boxes in the block diagram and/or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

The modules involved in the embodiments of the present invention may be implemented by software or hardware. The name of a module does not limit the module itself in some cases. For example, a test parameter acquisition module may also be described as a "module for acquiring device test parameters corresponding to a target device".

The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Fig. 4 is an application scenario diagram of a smart accompanying device control method according to an exemplary embodiment. As shown in Fig. 4, in this application scenario, first, a time series of physiological state parameters of the monitored elderly subject collected by the smart wearable device is received, wherein the physiological state parameters include blood pressure values (e.g., C1 as shown in Fig. 4) and blood sugar values (e.g., C2 as shown in Fig. 4); then, the acquired blood pressure values and blood sugar values are input into a server (e.g., S as shown in Fig. 4) deployed with a smart accompanying device control algorithm, wherein the server can process the blood pressure values and blood sugar values based on the smart accompanying device control algorithm to determine whether to generate a physiological state emergency warning prompt signal to the community medical center.

The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) by each other.

In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present invention. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

Although the subject matter has been described in language specific to structural features and/or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. With respect to the apparatus in the above-mentioned embodiments, the specific manner in which each module performs the operation has been described in detail in the embodiments related to the method, and will not be described in detail here.

Claims (8)

1. The intelligent accompanying equipment control method is characterized by comprising the following steps of:

Receiving a time sequence of physiological state parameters of a monitored elderly subject acquired by a smart wearable device, wherein the physiological state parameters include a blood pressure value and a blood glucose value;

the time sequence of the physiological state parameters is respectively subjected to data normalization according to the dimension of the parameter sample to obtain a time sequence of a blood pressure value and a time sequence of a blood sugar value;

respectively carrying out time sequence coding on the time sequence of the blood pressure value and the time sequence of the blood glucose value to obtain a blood pressure time sequence associated hidden characteristic vector and a blood glucose time sequence associated hidden characteristic vector;

The blood pressure time sequence association hidden feature vector and the blood glucose time sequence association hidden feature vector are subjected to a feature fusion module guided based on Gaussian prior distribution to obtain a time sequence association feature vector under the constraint of blood glucose-blood pressure prior;

Determining whether to generate a physiological state emergency early warning prompt signal to a community medical center based on the time sequence association feature vector under the blood sugar-blood pressure priori constraint;

The blood pressure time sequence association hidden feature vector and the blood sugar time sequence association hidden feature vector are subjected to a feature fusion module guided based on Gaussian prior distribution to obtain the time sequence association feature vector under the blood sugar-blood pressure prior constraint, which comprises the following steps:

Calculating prior factors of the blood pressure time sequence association hidden feature vector and the blood sugar time sequence association hidden feature vector respectively to obtain a blood pressure time sequence association prior feature vector and a blood sugar time sequence association prior feature vector;

And calculating the position-wise summation between the blood pressure time sequence association prior feature vector and the blood glucose time sequence association prior feature vector to obtain the time sequence association feature vector under the blood glucose-blood pressure prior constraint.

2. The intelligent accompanying apparatus control method according to claim 1, wherein time-series encoding the time-series of blood pressure values and the time-series of blood glucose values to obtain a blood pressure time-series-associated implicit feature vector and a blood glucose time-series-associated implicit feature vector, respectively, comprises:

the time sequence of the blood pressure value passes through a blood pressure sequence encoder based on an RNN model to obtain the blood pressure time sequence association implicit characteristic vector;

and (3) passing the time sequence of blood glucose values through a blood glucose sequence encoder based on an RNN model to obtain the blood glucose time sequence association implicit characteristic vector.

3. The intelligent accompanying device control method of claim 2, wherein calculating a priori factors of the blood pressure time sequence associated implicit feature vector and the blood glucose time sequence associated implicit feature vector to obtain a blood pressure time sequence associated priori feature vector and a blood glucose time sequence associated priori feature vector, respectively, comprises:

multiplying the blood pressure time sequence association hidden characteristic vector and the blood glucose time sequence association hidden characteristic vector by a preset weight super parameter according to positions to obtain a weight modulation blood pressure time sequence association hidden characteristic vector and a weight modulation blood glucose time sequence association hidden characteristic vector;

Taking each position characteristic value in the weight-modulation blood pressure time sequence related implicit characteristic vector and the weight-modulation blood glucose time sequence related implicit characteristic vector as an index of a natural constant to calculate an index function value based on the natural constant according to the position so as to obtain a weight-modulation blood pressure time sequence related support characteristic vector and a weight-modulation blood glucose time sequence related support characteristic vector;

multiplying the weight-modulated blood pressure time sequence association class support feature vector by a first Gaussian distribution random number function value to obtain the blood pressure time sequence association prior feature vector;

And multiplying the weight-modulated blood glucose time sequence association class support feature vector by a second Gaussian distribution random number function value to obtain the blood glucose time sequence association prior feature vector.

4. The intelligent career device control method according to claim 3, wherein the first gaussian distribution random number function value and the second gaussian distribution random number function value are generated as gaussian distribution random number functions with a mean value of 0 and a variance of 1.

5. The intelligent career device control method of claim 4, wherein determining whether to generate a physiological status emergency pre-warning prompt signal to a community medical center based on the time-sequence-associated feature vector under the blood glucose-blood pressure prior constraint comprises: and the time sequence associated feature vector under the prior constraint of blood sugar and blood pressure is passed through a classifier-based controller to obtain a control instruction, wherein the control instruction is used for indicating whether a physiological state emergency early warning prompt signal is generated to a community medical center.

6. The intelligent career device control method according to claim 5, wherein the time sequence association feature vector under the prior constraint of blood sugar and blood pressure is passed through a classifier-based controller to obtain a control instruction, the control instruction is used for indicating whether to generate a physiological state emergency early warning prompt signal to a community medical center, and the method comprises the following steps:

Performing full-connection coding on the time sequence associated feature vector under the prior constraint of blood sugar and blood pressure by using a plurality of full-connection layers of the classifier-based controller to obtain a coded classification feature vector;

And the coding classification feature vector is passed through a Softmax classification function of the classifier-based controller to obtain the control instruction.

7. An intelligent accompanying device control system, comprising:

the physiological state parameter acquisition module is used for receiving a time sequence of physiological state parameters of the monitored elderly object acquired by the intelligent wearable equipment, wherein the physiological state parameters comprise a blood pressure value and a blood glucose value;

The data normalization module is used for performing data normalization on the time sequence of the physiological state parameters according to the dimension of the parameter sample to obtain a time sequence of a blood pressure value and a time sequence of a blood sugar value;

the time sequence coding module is used for respectively carrying out time sequence coding on the time sequence of the blood pressure value and the time sequence of the blood glucose value so as to obtain a blood pressure time sequence associated hidden characteristic vector and a blood glucose time sequence associated hidden characteristic vector;

The feature fusion module is used for enabling the blood pressure time sequence related implicit feature vector and the blood glucose time sequence related implicit feature vector to be guided through the feature fusion module based on Gaussian prior distribution so as to obtain the time sequence related feature vector under the constraint of blood glucose-blood pressure prior;

The emergency early warning prompt determining module is used for determining whether to generate a physiological state emergency early warning prompt signal to a community medical center based on the time sequence association feature vector under the blood sugar-blood pressure priori constraint;

Wherein, the feature fusion module includes:

the prior factor calculating unit is used for calculating prior factors of the blood pressure time sequence association hidden characteristic vector and the blood sugar time sequence association hidden characteristic vector respectively to obtain a blood pressure time sequence association prior characteristic vector and a blood sugar time sequence association prior characteristic vector;

And the position-based addition calculation unit is used for calculating the position-based addition between the blood pressure time sequence association priori feature vector and the blood sugar time sequence association priori feature vector to obtain the time sequence association feature vector under the blood sugar-blood pressure priori constraint.

8. The intelligent companion device control system of claim 7, wherein the timing encoding module comprises:

The blood pressure sequence coding unit is used for enabling the time sequence of the blood pressure values to pass through a blood pressure sequence coder based on an RNN model to obtain the blood pressure time sequence association implicit characteristic vector;

and the blood glucose sequence coding unit is used for enabling the time sequence of the blood glucose values to pass through a blood glucose sequence coder based on an RNN model to obtain the blood glucose time sequence association implicit characteristic vector.