CN113270186B

CN113270186B - Data processing system, method and server based on heart failure exercise rehabilitation

Info

Publication number: CN113270186B
Application number: CN202110543090.9A
Authority: CN
Inventors: 李磊; 何竟; 王娇; 喻鹏铭; 霍彩铃
Original assignee: West China Hospital of Sichuan University
Current assignee: West China Hospital of Sichuan University
Priority date: 2021-05-19
Filing date: 2021-05-19
Publication date: 2022-06-10
Anticipated expiration: 2041-05-19
Also published as: CN113270186A

Abstract

When the method is applied, the types of the related movement data can be accurately analyzed, for example, the related movement data are divided into an aerobic movement type and an anaerobic movement type, and then the error generated by the movement data corresponding to each movement type is determined, so that the error is accurately corrected in a multi-dimensional mode, the high matching between the related movement data and the real movement situation can be ensured as much as possible, the simulation degree of the movement data is improved, and the movement data is restored as much as possible.

Description

Data processing system, method and server based on heart failure exercise rehabilitation

Technical Field

The application relates to the technical field of medical data processing, in particular to a data processing system, a method and a server based on heart failure exercise rehabilitation.

Background

Thanks to the continuous progress of science and technology, intelligent medical treatment is also continuously perfected and optimized. Wisdom medical treatment is with the internet as relying on, through infrastructure build and the collection of data, is applied to artificial intelligence technique and big data service a novel medical treatment mode in the medical industry, and wisdom medical treatment can show and promote medical treatment efficiency.

One of the features of the intelligent medical treatment is information digitization, for example, in some examination items (such as heart failure exercise rehabilitation items), the occupation of medical resources can be effectively reduced by acquiring and digitizing exercise data.

When rehabilitation exercise data processing is carried out, how to ensure the authenticity and accuracy of the exercise data is a technical problem which needs to be considered at present.

Disclosure of Invention

In order to solve the technical problems in the related art in the background art, the present application provides a data processing system, a method and a server based on heart failure exercise rehabilitation.

The application provides a data processing system based on heart failure exercise rehabilitation, which comprises a data processing server and an exercise data acquisition end which are in communication connection with each other;

the motion data acquisition end is used for acquiring motion data of the target heart failure patient and uploading the motion data to the data processing server;

the data processing server is configured to:

acquiring motion data of a target heart failure patient to be corrected; respectively carrying out aerobic type motion recognition and anaerobic type motion recognition on a plurality of motion data segments in the motion data of the target heart failure patient to obtain an aerobic type motion recognition result set and an anaerobic type motion recognition result set;

carrying out first heart rate data identification processing on the aerobic exercise identification result set through a first preset heart rate data identification strategy to obtain a first heart failure patient exercise data set comprising an aerobic exercise identifier; performing second heart rate data identification processing on the oxygen-free exercise identification result set through a second preset heart rate data identification strategy to obtain a second heart failure patient exercise data set comprising oxygen-free exercise identification;

performing global analysis processing based on the first heart failure patient motion data set and the second heart failure patient motion data set to obtain a reference motion data set matched with target motion in the target heart failure patient motion data; the target motion comprises at least one of an aerobic motion and an anaerobic motion, and the reference motion data set is used for correcting the motion data of the target heart failure patient.

Further, the aerobic exercise recognition and the anaerobic exercise recognition are respectively performed on a plurality of exercise data segments in the exercise data of the target heart failure patient to obtain an aerobic exercise recognition result set and an anaerobic exercise recognition result set, and the data processing server is configured to:

respectively carrying out aerobic exercise recognition on a plurality of exercise data segments in the exercise data of the target heart failure patient to obtain aerobic exercise recognition states in the exercise data segments and initial exercise types corresponding to the aerobic exercise recognition states;

determining an aerobic exercise identification result set based on the aerobic exercise identification state and the corresponding initial exercise type in each exercise data segment;

and respectively carrying out anaerobic motion recognition on a plurality of motion data segments in the motion data of the target heart failure patient to obtain an anaerobic motion recognition result set.

Further, the non-oxygen type motion recognition is performed on a plurality of motion data segments in the motion data of the target heart failure patient to obtain a non-oxygen type motion recognition result set, and the data processing server is configured to:

respectively carrying out free weight training recognition on a plurality of motion data segments in the target motion data segment to obtain free weight training recognition results respectively corresponding to the motion data segments;

respectively carrying out fixed instrument training recognition on a plurality of motion data segments in the target motion data segment to obtain fixed instrument training recognition results corresponding to the motion data segments;

associating the free weight training recognition results corresponding to the same heart failure patients with the fixed instrument training recognition results;

and carrying out anaerobic type motion recognition processing based on the fixed instrument training recognition result associated with the target free weight training recognition result in the target motion data segment to obtain an anaerobic type motion recognition result set.

Further, the first heart rate data recognition processing is performed on the aerobic exercise recognition result set through a first preset heart rate data recognition strategy to obtain a first heart failure patient exercise data set including an aerobic exercise identifier, and the data processing server is configured to:

respectively screening the motion types of each motion data segment in the aerobic motion identification result set to obtain the unique motion type corresponding to each motion data segment;

respectively updating the identification state based on the motion state description information of the aerobic motion identification state corresponding to the corresponding unique motion type in each motion data segment to obtain an updated aerobic motion identification result set;

performing iterative update processing on the updated aerobic exercise identification result set to obtain a plurality of first candidate heart failure patient exercise data sets including aerobic exercise identifiers;

and performing data integration on the first candidate heart failure patient motion data sets belonging to the same aerobic motion type according to the aerobic motion types to which the first candidate heart failure patient motion data sets respectively belong to obtain a first heart failure patient motion data set comprising an aerobic motion identifier.

Further, the step of respectively performing exercise type screening on each exercise data segment in the aerobic exercise identification result set to obtain a unique exercise type corresponding to each exercise data segment includes that the data processing server is configured to:

for each exercise data segment in the aerobic exercise identification result set, when the number of the initial exercise types of the exercise data segment is at least two, acquiring the exercise type heat of each initial exercise type;

when the initial motion type with the highest heat degree of the motion type is one, taking the initial motion type with the highest heat degree of the motion type as the unique motion type of the corresponding motion data segment;

when the number of the initial motion types with the highest heat degree is at least two, acquiring the corresponding recognition state heat degree of the aerobic motion recognition state for each initial motion type with the highest heat degree;

and determining the unique motion type corresponding to the corresponding motion data segment according to the initial motion type corresponding to the highest recognition state heat.

Further, the identification state updating process is performed based on the motion state description information of the aerobic exercise identification state corresponding to the corresponding unique motion type in each motion data segment, so as to obtain an updated aerobic exercise identification result set, and the data processing server is configured to:

for each motion data segment, obtaining a motion index value of an aerobic motion identification state corresponding to the corresponding unique motion type in each motion data segment;

when the exercise index value is within a preset exercise index value interval, reserving a corresponding aerobic exercise identification result, wherein the reserved aerobic exercise identification result comprises an aerobic exercise identification state and a unique exercise type corresponding to the aerobic exercise identification state; when the motion index value is not within the preset motion index value interval, setting the aerobic motion identification result of the corresponding motion data segment as a real-time identification result;

and obtaining an updated aerobic exercise identification result set based on the aerobic exercise identification result corresponding to each exercise data segment.

Further, the updated aerobic exercise identification result set is iteratively updated to obtain a plurality of first candidate heart failure patient exercise data sets including aerobic exercise identifiers, and the data processing server is configured to:

performing iterative update processing on the updated aerobic exercise identification result set to obtain multiple groups of first heart rate curve graph data and second heart rate curve graph data;

determining an index of change of the heart failure patient motion data set between each set of first heart rate graph data and second heart rate graph data;

when the change index of the heart failure patient motion data set is greater than or equal to a first preset index, taking a heart failure patient motion data set formed by the first heart rate graph data and the second heart rate graph data of the corresponding group as a first candidate heart failure patient motion data set;

for each first candidate heart failure patient motion data set, determining a target aerobic motion type with the largest occurrence frequency according to the updated unique motion type corresponding to each motion data segment in the first candidate heart failure patient motion data set;

taking the target aerobic exercise type as an aerobic exercise type to which aerobic exercise included in the corresponding first candidate heart failure patient exercise data set belongs;

wherein, the data integration is performed on the first candidate heart failure patient motion data sets belonging to the same aerobic exercise type according to the aerobic exercise type to which each first candidate heart failure patient motion data set belongs respectively, so as to obtain a first heart failure patient motion data set including an aerobic exercise identifier, and the method includes:

determining the aerobic exercise type of each first candidate heart failure patient exercise data set;

when more than one first candidate heart failure patient motion data sets which are adjacent in time sequence all belong to the same aerobic motion type, merging the more than one first candidate heart failure patient motion data sets to obtain first heart failure patient motion data sets corresponding to the same aerobic motion type.

Further, the aerobic exercise identification result in the aerobic exercise identification result set includes a real-time identification result and a delay identification result, the updated aerobic exercise identification result set is iteratively updated to obtain multiple sets of first heart rate graph data and second heart rate graph data, and the data processing server is configured to:

taking the motion data segment corresponding to the first delay identification result in the current cycle as the first heart rate curve diagram data of the current group in the updated aerobic motion identification result set;

traversing a segment of motion data subsequent to the current set of first heart rate graph data; when the traversed current group corresponds to a real-time identification result and the aerobic motion identification results corresponding to the motion data segments in the second preset index starting from the current group are all real-time identification results, taking the current group as second heart rate curve graph data of the current group; taking the motion data segment corresponding to the first delay identification result after the second heart rate curve graph data of the current group as the first heart rate curve graph data of the current group of the next circulation, and returning to the step of traversing the motion data segment after the first heart rate curve graph data of the current group to continue to execute until a plurality of groups of first heart rate curve graph data and second heart rate curve graph data are obtained;

wherein, when the traversed current group corresponds to the real-time recognition result and the aerobic exercise recognition results corresponding to the second preset intra-exponential exercise data segment starting from the current group are all real-time recognition results, before the current group is taken as the second heart rate graph data of the current group, the data processing server is further configured to:

when the change index of the motion data set of the heart failure patient, which is determined by the traversed current group and the first heart rate curve diagram data of the current group, is smaller than a third preset index, determining whether the aerobic motion recognition result corresponding to the current group is a real-time recognition result;

when the current group corresponds to a delay identification result, taking the current group as one of the motion data sets of the heart failure patients corresponding to the current group; when the current group corresponds to a real-time identification result and an aerobic exercise identification result in a second preset index from the current group comprises a delay identification result, taking an exercise data segment corresponding to a first delay identification result in the second preset index from the current group as a traversed next current group, and returning to the step of determining whether the aerobic exercise identification result corresponding to the current group is the real-time identification result when a change index of an exercise data set of the heart failure patient determined by the traversed current group and first heart rate curve diagram data of the current group is smaller than a third preset index;

wherein, the step of using the motion data segment corresponding to the first delayed recognition result in the current loop in the updated aerobic motion recognition result set as the first heart rate graph data of the current group includes:

determining a target motion data segment corresponding to the first delay identification result in the current cycle in the updated aerobic motion identification result set;

when the aerobic exercise identification result corresponding to the next group of the target exercise data segment is a real-time identification result, setting the aerobic exercise identification result corresponding to the target exercise data segment as a real-time identification result;

and when the oxygen type motion identification result corresponding to the next group of the target motion data segment is a delay identification result, taking the target motion data segment as the first heart rate curve graph data of the current group.

The application provides a data processing method based on heart failure motor rehabilitation, which comprises the following steps:

The application provides a data processing server, comprising a processor and a memory which are communicated with each other, wherein the processor is used for retrieving a computer program from the memory and realizing the method by running the computer program.

The technical scheme provided by the embodiment of the application can have the following beneficial effects: the method comprises the steps of obtaining motion data of a target heart failure patient to be corrected, and respectively carrying out aerobic motion recognition and anaerobic motion recognition on a plurality of motion data segments in the motion data of the target heart failure patient, so that the integrity and the discrimination of an aerobic motion recognition result set and an anaerobic motion recognition result set are ensured as much as possible, the types of data sets are effectively expanded, and sufficient analysis basis is provided for subsequent data correction. In addition, the first heart rate data and the second heart rate data can be identified to obtain a first heart failure patient motion data set and a second heart failure patient motion data set, and then global analysis processing is performed on the basis of the first heart failure patient motion data set and the second heart failure patient motion data set to obtain a reference motion data set matched with the target motion. Wherein the reference motion data set is used for correcting the motion data of the target heart failure patient.

The method can accurately analyze the types of the related movement data (for example, the related movement data is divided into aerobic movement and anaerobic movement), and further determine the error generated by the movement data corresponding to each movement type, so that the error is accurately corrected in a multi-dimensional mode, the high matching between the related movement data and the real movement situation can be ensured as much as possible, the fidelity of the movement data is improved, and the movement data is restored as much as possible.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.

Fig. 1 is a schematic architecture diagram of a data processing system based on heart failure exercise rehabilitation according to an embodiment of the present application;

fig. 2 is a flowchart of a data processing method based on heart failure exercise rehabilitation according to an embodiment of the present application;

fig. 3 is a functional block diagram of a data processing device based on heart failure exercise rehabilitation according to an embodiment of the present application.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

To facilitate the explanation of the data processing method and apparatus based on heart failure exercise rehabilitation, please refer to fig. 1, which provides a schematic view of a communication architecture of a data processing system 100 based on heart failure exercise rehabilitation disclosed in the embodiments of the present application. The data processing system 100 based on the heart failure motor rehabilitation can comprise a motor data acquisition end 200 and a data processing server 300, wherein the motor data acquisition end 200 is in communication connection with the data processing server 300.

In a specific embodiment, the data processing server 300 may be a desktop computer, a tablet computer, a notebook computer, a mobile phone, or other data processing servers capable of implementing data processing and data communication, which is not limited herein.

On the basis of the above, please refer to fig. 2 in combination, which is a flowchart illustrating a data processing method based on heart failure and exercise rehabilitation provided in an embodiment of the present application, the data processing method based on heart failure and exercise rehabilitation may be applied to the data processing server 300 in fig. 1, and further, the data processing method based on heart failure and exercise rehabilitation may specifically include the contents described in the following steps S21 to S23.

Step S21, acquiring motion data of a target heart failure patient to be corrected; and respectively carrying out aerobic type motion recognition and anaerobic type motion recognition on a plurality of motion data segments in the motion data of the target heart failure patient to obtain an aerobic type motion recognition result set and an anaerobic type motion recognition result set.

In this embodiment, the motion data of the target heart failure patient is split to obtain a plurality of data segments for analysis, so that the accurate data can be classified.

In order to improve the above technical problem, the step of performing aerobic exercise recognition and anaerobic exercise recognition on the plurality of exercise data segments in the exercise data of the target heart failure patient to obtain an aerobic exercise recognition result set and an anaerobic exercise recognition result set may specifically include the following steps S211 to S213.

Step S211, performing aerobic exercise recognition on the plurality of exercise data segments in the exercise data of the target heart failure patient, to obtain aerobic exercise recognition states in the exercise data segments and initial exercise types corresponding to the aerobic exercise recognition states.

Illustratively, the initial motion type is used to characterize a real-time motion type of a heart failure patient.

Step S212, determining an aerobic exercise recognition result set based on the aerobic exercise recognition status and the corresponding initial exercise type in each exercise data segment.

Illustratively, the same motion data is combined into one data set, which facilitates the query of the relevant motion data, thereby effectively reducing the workload of the query.

Step S213, respectively carrying out anaerobic motion recognition on a plurality of motion data segments in the motion data of the target heart failure patient to obtain an anaerobic motion recognition result set.

For example, when the plurality of motion data segments in the motion data of the target heart failure patient are respectively subjected to the anaerobic motion recognition, there is a technical problem of segment recognition error, so that it is difficult to reliably obtain an anaerobic motion recognition result set, and in order to improve the technical problem, the step of respectively performing the anaerobic motion recognition on the plurality of motion data segments in the motion data of the target heart failure patient to obtain the anaerobic motion recognition result set, which is described in step S213, may specifically include the following steps a 1-a 4.

Step a1, performing free weight training recognition on a plurality of motion data segments in the target motion data segment respectively to obtain free weight training recognition results corresponding to the motion data segments respectively.

Illustratively, the free weight training recognition is used for recognizing that a part of force needs to be separated to control balance during training, namely free weight training, and only force needs to be generated, namely the instrument training without controlling balance, for example, a patient pushes on a bench (the patient pushes up the bench to control balance by three heads and a small arm to prevent barbell shaking) and pushes up the smith machine (the patient only needs to generate force and does not need to consider other parts), namely the difference between the two.

Step a2, performing fixed instrument training recognition on a plurality of motion data segments in the target motion data segment respectively to obtain fixed instrument training recognition results corresponding to the motion data segments respectively.

Illustratively, the fixed instrument training recognition is used for recognizing that the fixed instrument has set a motion track according to a patient, and the executed action is limited to a single preset plane. For example, it is equivalent to laying a foundation for using barbells and dumbbells later, and the like, and will not be described in detail herein.

Step a3, associating the free weight training recognition result and the fixed instrument training recognition result corresponding to the same heart failure patient.

Illustratively, the degree of association with the patient is determined through the free weight training recognition result and the fixed instrument training recognition, and the patient is guaranteed to be matched with the optimal motion mode.

Step a4, performing anaerobic type motion recognition processing based on the fixed instrument training recognition result associated with the target free weight training recognition result in the target motion data segment to obtain an anaerobic type motion recognition result set.

Illustratively, the concept of the anaerobic exercise, which is derived from the classification of the metabolic processes of skeletal muscles during human exercise, is also based on the principle of anaerobic metabolic energy supply system, for example, the anaerobic exercise refers to the exercise performed by the muscles of human body under the anaerobic metabolic state. However, in daily life, anaerobic exercise is considered to mean a high-speed and vigorous exercise of muscles in an "anoxic" state. Most of the anaerobic exercises are exercises with high load strength and strong immediacy, so that the anaerobic exercises are difficult to last for a long time and the fatigue elimination time is slow.

It can be understood that when the content described in the above steps a 1-a 4 is executed, when the anaerobic motion recognition is performed on the plurality of motion data segments in the motion data of the target heart failure patient, the technical problem of segment recognition errors is avoided, so that the anaerobic motion recognition result set can be reliably obtained.

It can be understood that, when performing the contents described in the above steps S211 to S213, when performing aerobic type exercise recognition and anaerobic type exercise recognition on the plurality of exercise data segments in the exercise data of the target heart failure patient, respectively, the problem of inaccurate data recognition is avoided, so that the aerobic type exercise recognition result set and the anaerobic type exercise recognition result set can be accurately obtained.

Step S22, performing first heart rate data recognition processing on the aerobic exercise recognition result set through a first preset heart rate data recognition strategy to obtain a first heart failure patient exercise data set including an aerobic exercise identifier; and carrying out second heart rate data identification processing on the oxygen-free type exercise identification result set through a second preset heart rate data identification strategy to obtain a second heart failure patient exercise data set comprising oxygen-free type exercise identification.

In this embodiment, the heart rate refers to the number of heartbeats per minute of a normal person in a quiet state, which is also called a quiet heart rate, and is generally 60 to 100 beats/minute, and may cause individual differences due to age, gender, or other physiological factors. Generally, the smaller the age, the faster the heart rate, the slower the elderly than the young, and the faster the heart rate in women than in men of the same age, are normal physiological phenomena. In a resting state, the normal heart rate of an adult is 60-100 times/min, the ideal heart rate is 55-70 times/min (the heart rate of an athlete is slower than that of an ordinary adult and is about 50 times/min generally), and the motion type of a patient can be accurately determined through the change of the heart rate.

In order to improve the above technical problem, the step of performing the first heart rate data identification processing on the aerobic exercise recognition result set through the first preset heart rate data identification policy to obtain the first heart failure patient exercise data set including the aerobic exercise identifier described in step S22 may specifically include the following steps S221 to S224.

Step S221, motion type screening is respectively carried out on each motion data segment in the aerobic motion identification result set, and a unique motion type corresponding to each motion data segment is obtained.

Illustratively, the unique motion type is determined by each motion data segment, which effectively improves the accuracy of the unique motion type.

In the step of performing motion type screening on each motion data segment in the aerobic motion recognition result set, in order to improve the above technical problem, the step of performing motion type screening on each motion data segment in the aerobic motion recognition result set to obtain a unique motion type corresponding to each motion data segment described in step S221 may specifically include the following steps q 1-q 4.

And q1, for each motion data segment in the aerobic motion recognition result set, when the number of the initial motion types of the motion data segment is at least two, obtaining the motion type heat of each initial motion type.

Illustratively, the motion type heat of the initial motion types is used to characterize a probability value of occurrence of each initial motion type. (e.g., initial athletic activities include aerobic activities including walking, jogging, running, cycling, stepping, throwing, goal, ball, climbing, swimming, rowing, skating, roller skating, skiing, basketball, volleyball, football, badminton, table tennis, and tennis, etc.)

And step q2, when the initial motion type with the highest heat degree of motion type is one, taking the initial motion type with the highest heat degree of motion type as the unique motion type of the corresponding motion data segment.

And q3, when the initial motion types with the highest motion type heat degree are at least two, acquiring the corresponding recognition state heat degree of the oxygen type motion recognition state for each initial motion type with the highest motion type heat degree.

And step q4, determining the unique motion type corresponding to the corresponding motion data segment according to the initial motion type corresponding to the highest recognition state heat.

It can be understood that, when performing the content described in the foregoing step q 1-step q4, when performing the motion type screening on each motion data segment in the aerobic type motion recognition result set, the technical problem of inaccurate screening is avoided, so that the unique motion type corresponding to each motion data segment can be accurately obtained.

Step S222, respectively performing identification state updating processing based on the motion state description information of the aerobic exercise identification state corresponding to the corresponding unique motion type in each motion data segment, to obtain an updated aerobic exercise identification result set.

Illustratively, the motion state description information is used for representing statics, namely, the object in a static state or a uniform linear motion state is subjected to stress analysis, and the total external force borne by a researched object is zero in general; dynamics is the study of the relationship between the state of motion of an object and the forces it is subjected to, and mainly involves two classes of objects: the stress condition of the object is obtained according to the motion state of the known object; the motion state of the object is obtained according to the stress condition of the known object.

In the motion state description information based on the aerobic motion recognition state corresponding to the corresponding unique motion type in each motion data segment, there is a technical problem that description is not accurate, and it is difficult to accurately obtain an updated aerobic motion recognition result set when performing the recognition state updating process separately, in order to improve the above technical problem, the step of performing the recognition state updating process separately based on the motion state description information based on the aerobic motion recognition state corresponding to the corresponding unique motion type in each motion data segment described in step S222 to obtain an updated aerobic motion recognition result set may specifically include the contents described in the following step e1 to step e 3.

And e1, acquiring the motion index value of the oxygen type motion identification state corresponding to the corresponding unique motion type in each motion data segment for each motion data segment.

Illustratively, the motion indicator value is used to characterize the hemoglobin concentration as the amount of hemoglobin contained within a unit volume (L) of blood. Hemoglobin, also known as hemoglobin, is a pigment-containing binding protein that is the main component of red blood cells and can bind oxygen, transporting oxygen and carbon dioxide. The movement state of the patient can be reflected.

Step e2, when the exercise index value is within a preset exercise index value interval, reserving a corresponding aerobic exercise identification result, wherein the reserved aerobic exercise identification result comprises an aerobic exercise identification state and a unique exercise type corresponding to the aerobic exercise identification state; and when the motion index value is not within the preset motion index value interval, setting the aerobic motion identification result of the corresponding motion data segment as a real-time identification result.

And e3, obtaining an updated aerobic exercise identification result set based on the aerobic exercise identification result corresponding to each exercise data segment.

It can be understood that, when the above-mentioned contents described in steps e 1-e 3 are executed, the technical problem of inaccurate description is avoided when the motion state description information based on the aerobic motion recognition state corresponding to the corresponding unique motion type in each motion data segment is used, and the updated aerobic motion recognition result set can be accurately obtained when the recognition state updating processing is performed separately.

Step S223, performing iterative update processing on the updated aerobic exercise identification result set to obtain a plurality of first candidate heart failure patient exercise data sets including aerobic exercise identifiers.

Illustratively, the candidate heart failure patient motion data set is used to characterize a patient requiring a type of motion to be matched.

In order to improve the above technical problem, the step of performing iterative update processing on the updated aerobic exercise recognition result set to obtain a plurality of first candidate heart failure patient exercise data sets including an aerobic exercise identifier described in step S223 may specifically include the following steps l 1-l 5,

and step l1, performing iterative update processing on the updated aerobic exercise identification result set to obtain multiple groups of first heart rate curve diagram data and second heart rate curve diagram data.

Illustratively, the heart rate graph data is used to characterize a heart beat condition.

In order to improve the above technical problem, the aerobic exercise identification result in the aerobic exercise identification result set described in step l1 includes a real-time identification result and a delayed identification result, and the step of performing iterative update processing on the updated aerobic exercise identification result set to obtain multiple sets of first heart rate graph data and second heart rate graph data may specifically include the following steps n1 and n 2.

And step n1, collecting the updated aerobic exercise identification result, wherein the exercise data segment corresponding to the first delay identification result in the current cycle is used as the first heart rate curve chart data of the current group.

Illustratively, the first time delay identification result is used for representing the position of the fault of the data in the circulation process.

Step n2, traversing the motion data segment following the first heart rate graph data of the current set; when the traversed current group corresponds to a real-time identification result and the aerobic exercise identification results corresponding to the second preset exponential exercise data segment starting from the current group are all real-time identification results, taking the current group as second heart rate curve diagram data of the current group; and taking the motion data segment corresponding to the first delay identification result after the second heart rate curve graph data of the current group as the first heart rate curve graph data of the current group of the next circulation, and returning to the step of traversing the motion data segment after the first heart rate curve graph data of the current group to continue executing until obtaining multiple groups of the first heart rate curve graph data and the second heart rate curve graph data.

Illustratively, by the method, the multiple groups of first heart rate curve graph data and second heart rate curve graph data are obtained, so that sample data is increased, the situation that the data are inaccurate due to equipment problems is effectively avoided by monitoring the multiple groups of data, and the accuracy of the data is improved. It can be understood that, when the above-mentioned steps n1 and n2 are performed, the aerobic exercise identification result in the aerobic exercise identification result set includes a real-time identification result and a delayed identification result, and when the updated aerobic exercise identification result set is subjected to the iterative update process, the problem of drawing an error in the heart rate graph is avoided, so that multiple sets of the first heart rate graph data and the second heart rate graph data can be accurately obtained.

Step l2, determining an index of change of the heart failure patient motion data set between each set of first heart rate graph data and second heart rate graph data.

Illustratively, the accurate change index is effectively obtained through the mode of changing the first heart rate graph data and the second heart rate graph data, so that the accuracy of the index is improved.

And l3, when the index of change of the heart failure patient motion data set is greater than or equal to the first preset index, using the heart failure patient motion data set formed by the first heart rate graph data and the second heart rate graph data of the corresponding group as a first candidate heart failure patient motion data set.

Step l4, for each first candidate heart failure patient motion data set, determining the target aerobic motion type with the largest occurrence frequency according to the updated unique motion type corresponding to each motion data segment in the first candidate heart failure patient motion data set.

Illustratively, the most frequently occurring target aerobic exercise type is used for the body target aerobic exercise type heat.

Step l5, the target aerobic exercise type is used as the aerobic exercise type to which the aerobic exercise included in the corresponding first candidate heart failure patient exercise data set belongs.

It can be understood that, when the above-mentioned steps l 1-l 5 are performed, the iterative update process is performed on the updated aerobic exercise identification result set, so as to avoid the problem of iterative confusion, and thus, a plurality of first candidate heart failure patient exercise data sets including the aerobic exercise identifier can be reliably obtained.

Step S224, performing data integration on the first candidate heart failure patient motion data sets belonging to the same aerobic exercise type according to the aerobic exercise type to which each of the first candidate heart failure patient motion data sets respectively belongs, to obtain a first heart failure patient motion data set including an aerobic exercise identifier.

For example, when the first candidate heart failure patient motion data sets belonging to the same aerobic motion type are data-integrated according to the aerobic motion type to which each of the first candidate heart failure patient motion data sets respectively belongs, there is a problem of irregular data integration, so that it is difficult to accurately obtain the first heart failure patient motion data sets including the aerobic motion identifier, and in order to improve the above technical problem, the step of performing data integration on the first candidate heart failure patient motion data sets belonging to the same aerobic motion type according to the aerobic motion type to which each of the first candidate heart failure patient motion data sets respectively belongs to obtain the first heart failure patient motion data sets including the aerobic motion identifier described in step S224 may specifically include the following steps h1 and h 2.

Step h1, determining the aerobic exercise type of each first candidate heart failure patient exercise data set.

And h2, when more than one first candidate heart failure patient motion data sets adjacent in time sequence all belong to the same aerobic motion type, merging the more than one first candidate heart failure patient motion data sets to obtain a first heart failure patient motion data set corresponding to the same aerobic motion type.

It can be understood that, when performing the above-mentioned descriptions in step h1 and step h2, when performing data integration on the first candidate heart failure patient motion data sets belonging to the same aerobic motion type according to the aerobic motion type to which each of the first candidate heart failure patient motion data sets respectively belongs, the problem of irregular data integration is avoided, so that the first heart failure patient motion data set including the aerobic motion identifier can be accurately obtained.

Further, it can be understood that, when the content described in the above steps S221 to S224 is executed, when the first heart rate data recognition processing is performed on the aerobic exercise recognition result set through the first preset heart rate data recognition strategy, the problem of heart rate data recognition disorder is avoided, so that the first heart failure patient exercise data set including the aerobic exercise identifier can be accurately obtained.

Step S23, performing global analysis processing based on the first heart failure patient motion data set and the second heart failure patient motion data set to obtain a reference motion data set matching the target motion in the target heart failure patient motion data; the target motion comprises at least one of an aerobic motion and an anaerobic motion, and the reference motion data set is used for correcting the motion data of the target heart failure patient.

In this embodiment, the reference motion data set matched with the target motion in the motion data of the target heart failure patient is used to represent the coefficient for judging the motion type, so that the accuracy of judging the oxygen-based motion and the oxygen-free motion types can be improved as much as possible.

It can be understood that, when the above-mentioned steps S21-S23 are performed, the motion data of the target heart failure patient to be corrected is obtained, and aerobic type motion recognition and anaerobic type motion recognition are respectively performed on a plurality of motion data segments in the motion data of the target heart failure patient, so as to ensure the integrity and the differentiation of the aerobic type motion recognition result set and the anaerobic type motion recognition result set as much as possible, thereby effectively expanding the types of the data sets and providing sufficient analysis basis for subsequent data correction. In addition, the first heart rate data and the second heart rate data can be identified to obtain a first heart failure patient motion data set and a second heart failure patient motion data set, and then global analysis processing is performed on the basis of the first heart failure patient motion data set and the second heart failure patient motion data set to obtain a reference motion data set matched with the target motion. Wherein the reference motion data set is used for correcting the motion data of the target heart failure patient.

Based on the above basis, when the traversed current group corresponds to the real-time recognition result and the oxygen-type motion recognition results corresponding to the second intra-index motion data segment starting from the current group are all real-time recognition results, before the current group is used as the second heart rate graph data of the current group, the method further includes the following contents described in step r1 and step r 2.

And r1, when the change index of the motion data set of the heart failure patient determined by the traversed current group and the first heart rate curve chart data of the current group is less than a third preset index, determining whether the aerobic motion recognition result corresponding to the current group is a real-time recognition result.

Illustratively, the preset index is used for characterizing the index, or called statistical index, and is an important statistical method for analyzing the change of the social and economic phenomena.

In order to improve the above technical problem, the step r1 may specifically include the following steps k 1-k 3, where the step r1 is to set the motion data segment corresponding to the first delayed recognition result in the current loop as the first heart rate graph data of the current group.

And step k1, determining the target motion data segment corresponding to the first delay identification result in the current cycle in the updated aerobic motion identification result set.

And k2, when the aerobic exercise identification result corresponding to the next group of the target exercise data segment is the real-time identification result, setting the aerobic exercise identification result corresponding to the target exercise data segment as the real-time identification result.

And k3, when the oxygen type motion recognition result corresponding to the next group of the target motion data segment is the delay recognition result, taking the target motion data segment as the first heart rate curve chart data of the current group.

It can be understood that, when the above-mentioned steps k 1-k 3 are performed, the problem of update error is avoided when the updated aerobic exercise identification result is collected, so that the exercise data segment corresponding to the first delayed identification result in the current loop can be used as the first heart rate graph data of the current group.

Step r2, when the current group corresponds to the time-delay identification result, using the current group as one of the motion data sets of the heart failure patients corresponding to the current group; and when the current group corresponds to a real-time identification result and an aerobic exercise identification result in a second preset index from the current group comprises a delay identification result, taking an exercise data segment corresponding to a first delay identification result in the second preset index from the current group as a next current group for traversing, and returning to the step of determining whether the aerobic exercise identification result corresponding to the current group is the real-time identification result when a change index of an exercise data set of the heart failure patient determined by the traversed current group and the first heart rate curve diagram data of the current group is less than a third preset index.

It can be understood that when the contents described in the above steps r1 and r2 are executed, the analysis is performed by three indexes, so that the accuracy of the quality inspection data in multiple directions is performed by the three indexes, and therefore, the accuracy of the data can be effectively improved.

Based on the above basis, the step of performing second heart rate data recognition processing on the non-oxygen type exercise recognition result set through a second preset heart rate data recognition strategy to obtain a second heart failure patient exercise data set including a non-oxygen type exercise identifier may further include the following contents described in steps G1 and G2.

And G1, performing iterative update processing on the anaerobic motion recognition result set to obtain a plurality of second candidate heart failure patient motion data sets including the anaerobic motion identifications.

Illustratively, the anaerobic type motion recognition result set is continuously updated in an iterative manner, so that the range of data can be effectively improved, more data can be extracted, more samples can be found in the recognition data, the extracted data is more accurate, and the subsequent determination of the anaerobic type is more accurate. (for example, the cloud database continuously receives and stores new and effective data, so that the sample data type is improved, more matched data can be found when the data are extracted, and the problem of data mismatch is effectively reduced.)

And G2, performing data integration on the second candidate heart failure patient motion data sets belonging to the same anaerobic type according to the anaerobic type corresponding to each second candidate heart failure patient motion data set to obtain a second heart failure patient motion data set comprising an anaerobic type motion identifier.

It can be understood that, when the content described in the above steps G1 and G2 is executed, when the second heart rate data recognition processing is performed on the non-oxygen type exercise recognition result set through the second preset heart rate data recognition strategy, the problem of unreliable data recognition is avoided, so that the second heart failure patient exercise data set including the non-oxygen type exercise identifier can be reliably obtained.

In another alternative embodiment, the step of performing global analysis processing based on the first heart failure patient motion data set and the second heart failure patient motion data set to obtain a reference motion data set matching the target motion in the target heart failure patient motion data may further include the following steps M1-M3.

And step M1, when the second heart failure patient motion data set is completely in the first heart failure patient motion data set, or the first heart failure patient motion data set is completely in the second heart failure patient motion data set, filtering the second heart failure patient motion data set and reserving the first heart failure patient motion data set to obtain a reference motion data set matched with aerobic motion.

Illustratively, when the second heart failure patient motion data set is completely in the first heart failure patient motion data set, or the first heart failure patient motion data set is completely in the second heart failure patient motion data set, the data set with a large range is deleted, so that the range of data processing can be effectively reduced, the workload of the processor is reduced, and the work efficiency is effectively improved.

And step M2, when the posterior motion data segment in the first heart failure patient motion data set overlaps with the anterior motion data segment in the second heart failure patient motion data set, keeping the first heart failure patient motion data set as a reference motion data set matched with aerobic motion, taking the second heart rate graph data in the first heart failure patient motion data set as the first heart rate graph data in the second heart failure patient motion data set, obtaining an updated second heart failure patient motion data set, and taking the updated second heart failure patient motion data set as the reference motion data set matched with anaerobic motion.

And step M3, when the posterior motion data segment in the second heart failure patient motion data set overlaps with the anterior motion data segment in the first heart failure patient motion data set, keeping the first heart failure patient motion data set as a reference motion data set matched with aerobic motion, taking the first heart rate graph data in the first heart failure patient motion data set as the second heart rate graph data in the second heart failure patient motion data set, obtaining an updated second heart failure patient motion data set, and taking the updated second heart failure patient motion data set as the reference motion data set matched with anaerobic motion.

It can be understood that, when the above-mentioned steps M1-M3 are performed, when the global analysis processing is performed based on the first heart failure patient motion data set and the second heart failure patient motion data set, the problem of inaccurate data analysis is avoided, and by means of the continuous update processing of the data sets, the data can be accurately analyzed, so that the reference motion data set matching the target motion in the target heart failure patient motion data can be accurately obtained.

In another alternative embodiment, the method further comprises the following steps S41-S44.

In step S41, wave pits and wave bumps are determined.

Illustratively, the undulation pits are used to characterize the lowest point of the curve in one amplitude, and the undulation peaks are used to characterize the highest point of the curve in one amplitude. The fluctuation concave point and the fluctuation convex point are calculated by obtaining the vibration amplitudes of two adjacent concave points and convex points from front-end fluctuation equipment.

And step S42, controlling the wave concave point as a wave data starting point to obtain a vibration amplitude period from the front-end wave equipment.

And step S42, controlling the fluctuation salient point as a fluctuation data terminal to acquire the latest vibration amplitude period in interval time from the front-end fluctuation device, and storing the latest vibration amplitude period in the interval time in a cache list of the fluctuation salient point, wherein the interval time is the time for detecting the occurrence position of the fluctuation concave point and jumping the fluctuation task of the fluctuation concave point to the fluctuation salient point.

Illustratively, an amplitude period is randomly selected as reference data, and the time of the amplitude period is determined, so that the curve can be decomposed section by section, and the condition that the curve is disordered can be avoided, thereby causing data distraction to be unclear.

Step S44, if the position of the fluctuation pit is detected, controlling the fluctuation bump to continue the fluctuation task of the fluctuation pit, where the fluctuation task includes a unit fluctuation range of a vibration amplitude cycle obtained from the front-end fluctuation device and a sample fluctuation list for storing a vibration amplitude cycle in a cache list of the fluctuation bump in cloud storage.

It can be understood that, when the contents included in the above steps S41-S44 are executed, the concave value and the adjacent peak value of the curve are used as the basis for analyzing the data, so that the complex data is effectively simplified, and the workload of the server is reduced, thereby effectively improving the fluency of the server and making the server operation faster.

Based on the same inventive concept, a data processing system based on heart failure exercise rehabilitation is also provided, the system comprises an exercise data acquisition end and a data processing server, the exercise data acquisition end is in communication connection with the data processing server, and the data processing server is specifically used for:

Further, the data processing server is specifically configured to:

respectively carrying out free weight training recognition on a plurality of motion data segments in the target motion data segment to obtain free weight training recognition results corresponding to the motion data segments;

correlating the free weight training recognition result and the fixed instrument training recognition result corresponding to the same heart failure patient;

Further, the data processing server is specifically configured to:

for each motion data segment in the aerobic motion identification result set, when the number of the initial motion types of the motion data segment is at least two, obtaining the motion type heat of each initial motion type;

Further, the data processing server is specifically configured to:

when more than one first candidate heart failure patient motion data sets adjacent in time sequence all belong to the same aerobic motion type, merging the more than one first candidate heart failure patient motion data sets to obtain a first heart failure patient motion data set corresponding to the same aerobic motion type.

Further, the data processing server is specifically configured to:

traversing a segment of motion data subsequent to the current set of first heart rate graph data; when the traversed current group corresponds to a real-time identification result and the aerobic exercise identification results corresponding to the second preset exponential exercise data segment starting from the current group are all real-time identification results, taking the current group as second heart rate curve diagram data of the current group; and taking the motion data segment corresponding to the first delay identification result after the second heart rate curve graph data of the current group as the first heart rate curve graph data of the current group of the next circulation, and returning to the step of traversing the motion data segment after the first heart rate curve graph data of the current group to continue executing until obtaining multiple groups of the first heart rate curve graph data and the second heart rate curve graph data.

Further, the data processing server is specifically configured to:

when the current group corresponds to a delay identification result, taking the current group as one of the motion data sets of the heart failure patients corresponding to the current group; when the current group corresponds to a real-time recognition result and an aerobic exercise recognition result in a second preset index from the current group comprises a delay recognition result, taking an exercise data segment corresponding to a first delay recognition result in the second preset index from the current group as a next current group for traversing, and returning to the step of determining whether the aerobic exercise recognition result corresponding to the current group is the real-time recognition result when a change index of an exercise data set of the heart failure patient determined by the traversed current group and the first heart rate curve diagram data of the current group is less than a third preset index;

Based on the same inventive concept as above, please refer to fig. 3, a block diagram of functional blocks of the data processing apparatus 500 based on heart failure exercise rehabilitation is also provided, and the detailed description about the data processing apparatus 500 based on heart failure exercise rehabilitation is as follows.

The data processing device 500 based on heart failure motor rehabilitation is applied to a data processing server, and the device 500 comprises:

a data identification module 510, configured to obtain motion data of a target heart failure patient to be corrected; respectively carrying out aerobic type motion recognition and anaerobic type motion recognition on a plurality of motion data segments in the motion data of the target heart failure patient to obtain an aerobic type motion recognition result set and an anaerobic type motion recognition result set;

the recognition result processing module 520 is configured to perform first heart rate data recognition processing on the aerobic exercise recognition result set through a first preset heart rate data recognition strategy to obtain a first heart failure patient exercise data set including an aerobic exercise identifier; performing second heart rate data identification processing on the oxygen-free exercise identification result set through a second preset heart rate data identification strategy to obtain a second heart failure patient exercise data set comprising oxygen-free exercise identification;

a data correction module 530, configured to perform global analysis processing based on the first heart failure patient motion data set and the second heart failure patient motion data set, to obtain a reference motion data set that matches a target motion in the target heart failure patient motion data; the target motion comprises at least one of an aerobic motion and an anaerobic motion, and the reference motion data set is used for correcting the motion data of the target heart failure patient.

The application provides a data processing server, which comprises a processor and a memory which are communicated with each other, wherein the processor is used for retrieving a computer program from the memory and realizing the method by running the computer program.

In summary, when the above scheme is applied, the motion data of the target heart failure patient to be corrected is acquired, and aerobic motion recognition and anaerobic motion recognition are respectively performed on a plurality of motion data segments in the motion data of the target heart failure patient, so that the integrity and the differentiation of the aerobic motion recognition result set and the anaerobic motion recognition result set are ensured as much as possible, the types of the data sets are effectively expanded, and sufficient analysis basis is provided for subsequent data correction. In addition, the first heart rate data and the second heart rate data can be identified to obtain a first heart failure patient motion data set and a second heart failure patient motion data set, and then global analysis processing is performed on the basis of the first heart failure patient motion data set and the second heart failure patient motion data set to obtain a reference motion data set matched with the target motion. Wherein the reference motion data set is used for correcting the motion data of the target heart failure patient.

It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A data processing system based on heart failure exercise rehabilitation is characterized by comprising a data processing server and an exercise data acquisition end which are in communication connection with each other;

the data processing server is configured to:

performing first heart rate data identification processing on the aerobic exercise identification result set through a first preset heart rate data identification strategy to obtain a first heart failure patient exercise data set comprising an aerobic exercise identifier; performing second heart rate data identification processing on the oxygen-free exercise identification result set through a second preset heart rate data identification strategy to obtain a second heart failure patient exercise data set comprising oxygen-free exercise identification;

performing global analysis processing based on the first heart failure patient motion data set and the second heart failure patient motion data set to obtain a reference motion data set matched with target motion in the target heart failure patient motion data; the target motion comprises at least one of an aerobic motion and an anaerobic motion, and the reference motion data set is used for correcting the motion data of the target heart failure patient;

wherein the global analysis processing is performed based on the first heart failure patient motion data set and the second heart failure patient motion data set to obtain a reference motion data set matched with a target motion in the target heart failure patient motion data, and the data processing server is configured to:

when the second heart failure patient motion data set is completely in the first heart failure patient motion data set, or the first heart failure patient motion data set is completely in the second heart failure patient motion data set, filtering the second heart failure patient motion data set and reserving the first heart failure patient motion data set to obtain a reference motion data set matched with aerobic motion;

when a posterior motion data segment in the first heart failure patient motion data set overlaps with an anterior motion data segment in the second heart failure patient motion data set, keeping the first heart failure patient motion data set as a reference motion data set matched with aerobic motion, taking second heart rate graph data in the first heart failure patient motion data set as first heart rate graph data of the second heart failure patient motion data set to obtain an updated second heart failure patient motion data set, and taking the updated second heart failure patient motion data set as a reference motion data set matched with anaerobic motion;

when the posterior motion data segment in the second heart failure patient motion data set is overlapped with the anterior motion data segment in the first heart failure patient motion data set, the first heart failure patient motion data set is reserved as a reference motion data set matched with aerobic motion, the first heart rate graph data in the first heart failure patient motion data set is used as the second heart rate graph data in the second heart failure patient motion data set, an updated second heart failure patient motion data set is obtained, and the updated second heart failure patient motion data set is used as the reference motion data set matched with the anaerobic motion.

2. The system according to claim 1, wherein the aerobic type motion recognition and the anaerobic type motion recognition are respectively performed on a plurality of motion data segments in the motion data of the target heart failure patient, so as to obtain an aerobic type motion recognition result set and an anaerobic type motion recognition result set, and the data processing server is configured to:

3. The system according to claim 2, wherein the anaerobic motion recognition is performed on a plurality of motion data segments in the motion data of the target heart failure patient, so as to obtain an anaerobic motion recognition result set, and the data processing server is configured to:

4. The system according to claim 1, wherein the aerobic exercise recognition result set is subjected to a first heart rate data recognition processing by a first preset heart rate data recognition strategy to obtain a first heart failure patient exercise data set including an aerobic exercise identifier, and the data processing server is configured to:

5. The system according to claim 4, wherein the step of performing exercise type screening on each exercise data segment in the aerobic exercise identification result set to obtain a unique exercise type corresponding to each exercise data segment comprises the data processing server configured to:

6. The system according to claim 4, wherein the identification status updating process is performed based on the motion status description information of the aerobic exercise identification status corresponding to the corresponding unique exercise type in each exercise data segment, so as to obtain an updated aerobic exercise identification result set, and the data processing server is configured to:

7. The system according to claim 4, wherein the updated aerobic exercise identification result set is iteratively updated to obtain a plurality of first candidate heart failure patient exercise data sets including aerobic exercise identifiers, and the data processing server is configured to:

for each first candidate heart failure patient motion data set, determining a target aerobic motion type with the largest occurrence number according to the updated unique motion type corresponding to each motion data segment in the first candidate heart failure patient motion data set;

8. The system according to claim 7, wherein the aerobic exercise identification result in the aerobic exercise identification result set includes a real-time identification result and a delayed identification result, the updated aerobic exercise identification result set is iteratively updated to obtain a plurality of sets of first and second heart rate graph data, and the data processing server is configured to:

traversing a segment of motion data subsequent to the current set of first heart rate graph data; when the traversed current group corresponds to a real-time identification result and the aerobic exercise identification results corresponding to the second preset exponential exercise data segment starting from the current group are all real-time identification results, taking the current group as second heart rate curve diagram data of the current group; taking the motion data segment corresponding to the first delay identification result after the second heart rate curve graph data of the current group as the first heart rate curve graph data of the current group of the next circulation, and returning to the step of traversing the motion data segment after the first heart rate curve graph data of the current group to continue to execute until a plurality of groups of first heart rate curve graph data and second heart rate curve graph data are obtained;

wherein, when the traversed current group corresponds to the real-time identification result and the aerobic motion identification result corresponding to the motion data segment in the second preset index starting from the current group is the real-time identification result, before the current group is used as the second heart rate graph data of the current group, the data processing server is further configured to:

when the aerobic motion identification result corresponding to the next group of the target motion data segment is a real-time identification result, setting the aerobic motion identification result corresponding to the target motion data segment as a real-time identification result;

9. A data processing method based on heart failure motor rehabilitation, the method comprising:

wherein the step of performing global analysis processing based on the first heart failure patient motion data set and the second heart failure patient motion data set to obtain a reference motion data set matched with a target motion in the target heart failure patient motion data includes:

10. A data processing server, comprising a processor and a memory in communication with each other, the processor being configured to retrieve a computer program from the memory and to implement the method of claim 9 by executing the computer program.