CN111724879A

CN111724879A - Rehabilitation training evaluation processing method, device and equipment

Info

Publication number: CN111724879A
Application number: CN202010605473.XA
Authority: CN
Inventors: 马佳鑫
Original assignee: China Gold Yuneng Education Technology Group Co ltd
Current assignee: China Gold Yuneng Education Technology Group Co ltd
Priority date: 2020-06-29
Filing date: 2020-06-29
Publication date: 2020-09-29

Abstract

The embodiment of the invention provides a rehabilitation training evaluation processing method, a device and equipment, wherein the method comprises the steps of obtaining rehabilitation training video data corresponding to a user to be rehabilitated, which are collected by video collection equipment, determining a motion image set according to the rehabilitation training video data, identifying the motion image set by adopting a motion function evaluation model, determining action parameter values corresponding to motion images in the motion image set, wherein the motion function evaluation model is obtained by training according to the motion training image set, analyzing and processing the action parameter values corresponding to the motion images in the motion image set on the basis of a prestored rehabilitation medical knowledge map to obtain a training result, and sending the training result to terminal equipment corresponding to the user to be rehabilitated. The effect of rehabilitation training is improved, and then the rehabilitation experience of the user waiting for rehabilitation is improved.

Description

Rehabilitation training evaluation processing method, device and equipment

Technical Field

The embodiment of the invention relates to the technical field of data processing, in particular to a rehabilitation training evaluation processing method, a rehabilitation training evaluation processing device and rehabilitation training evaluation processing equipment.

Background

Rehabilitation medicine is an emerging subject appearing in the middle of the 20 th century, is called as 'four major medical science', is a medical subject which is used for eliminating and relieving functional disorders of people, making up and reconstructing functional deficiency of people and trying to improve and improve various functions of people so that physical functions of patients are restored to normal living level after treatment such as medicine or operation is completed.

At present, due to the limitation of the medical level, there are still a large number of disabled persons, elderly persons and patients with chronic diseases who have urgent needs for rehabilitation medicine.

However, due to the concept of heavy treatment and light rehabilitation for a long time, only large hospitals are provided with equipment and technicians related to rehabilitation, and general small or community hospitals are not provided with related equipment and technicians, a user to be rehabilitated can only frequently go to the large hospitals to receive rehabilitation training or firstly receive rehabilitation training in the large hospitals, and then the user can train alone at home according to the learned rehabilitation knowledge.

Disclosure of Invention

The embodiment of the invention provides a rehabilitation training evaluation processing method, a device and equipment, which are used for improving the rehabilitation training effect.

In a first aspect, an embodiment of the present invention provides a rehabilitation training evaluation processing method, including: acquiring rehabilitation training video data corresponding to a user to be rehabilitated and acquired by video acquisition equipment, and determining a motion image set according to the rehabilitation training video data; the rehabilitation training video data are video data formed by the action of the user to be rehabilitated according to the pre-evaluated data to be rehabilitated; identifying the moving image set by adopting a moving function evaluation model, and determining an action parameter value corresponding to each moving image in the moving image set, wherein the moving function evaluation model is obtained by training according to a moving training image set; analyzing and processing action parameter values corresponding to all the motion images in the motion image set based on a prestored rehabilitation medical knowledge map to obtain a training result; and sending the training result to the terminal equipment corresponding to the user to be recovered.

Optionally, the graph structure inference algorithm of the rehabilitation medical knowledge graph includes any one or more of a path feature algorithm, a rule learning algorithm, and a knowledge representation learning algorithm, and the analyzing and processing of the action parameter values corresponding to the motion images in the motion image set based on the pre-stored rehabilitation medical knowledge graph to obtain the training result includes: and analyzing and processing action parameter values corresponding to the motion images in the motion image set based on any one or combination of a plurality of algorithms in the path characteristic algorithm, the rule learning algorithm and the knowledge representation learning algorithm in the pre-stored rehabilitation medical knowledge map to obtain a training result.

Optionally, the to-be-rehabilitated training data includes rehabilitation training data of different grades of the corresponding part of the to-be-rehabilitated user, where the rehabilitation training data includes rehabilitation training actions, rehabilitation training duration, and/or rehabilitation training times, the to-be-rehabilitated training video data acquired by the video acquisition device and corresponding to the to-be-rehabilitated user is acquired, and the motion image set is determined according to the rehabilitation training video data, including: acquiring rehabilitation training video data acquired by video acquisition equipment according to rehabilitation training actions, rehabilitation training duration and/or rehabilitation training times in the rehabilitation training data of a user to be rehabilitated; and separating the rehabilitation video data according to frames to obtain a moving image set containing a plurality of frame images.

Optionally, the method further includes: acquiring basic sign parameter data monitored by wearable sensing equipment; the method comprises the following steps of analyzing and processing action parameter values corresponding to all the motion images in the motion image set based on a pre-stored rehabilitation medical knowledge map to obtain a training result, wherein the method comprises the following steps: and analyzing and processing the basic sign parameter data and the action parameter values corresponding to the motion images in the motion image set based on a pre-stored rehabilitation medical knowledge map to obtain a training result.

Optionally, before the acquiring the rehabilitation training video data corresponding to the user to be rehabilitated and acquired by the video acquisition device, the method further includes: determining a guidance action corresponding to the user to be recovered according to the recovery information corresponding to the user to be recovered; acquiring rehabilitation evaluation video data acquired by the video acquisition equipment; the rehabilitation evaluation video data are video data formed by the user to be rehabilitated acting according to the guiding action; determining an evaluation moving image set according to the rehabilitation evaluation video data, identifying the evaluation moving image set by adopting a moving function evaluation model, and determining action parameter values corresponding to each evaluation moving image in the evaluation moving image set; and based on the rehabilitation medical knowledge map, evaluating action parameter values corresponding to the evaluation motion images in the evaluation motion image set and the rehabilitation information to obtain the pre-evaluated rehabilitation training data.

Optionally, the method further includes: judging whether the training result is within a preset score range; and if the training result is not within the preset score range, re-executing the steps of determining the guiding action corresponding to the user to be recovered and the subsequent steps according to the recovery information corresponding to the user to be recovered, and determining new pre-estimated recovery training data, wherein the part corresponding to the user to be recovered in the new pre-estimated recovery training data is different from the part in the original estimated recovery training data, or the part corresponding to the user to be recovered in the new pre-estimated recovery training data is the same as the part in the original estimated recovery training data, and any one or more parameters of the recovery training action, the recovery training duration and the recovery training times of the part corresponding to the user to be recovered are different from the parameters in the original estimated recovery training data.

Optionally, the method further includes: if any parameter data in the basic sign parameter data monitored by the wearable sensing equipment exceeds a preset threshold, generating an alarm prompt; and sending the alarm prompt to a monitoring terminal.

Optionally, the wearable sensing device includes any one or more of a vital sign sensing wristwatch, a plantar pressure sensor, and a surface myoelectricity wearable sensor.

Optionally, the rehabilitation information corresponding to the user to be rehabilitated includes: the user to be rehabilitated comprises any one or more of sex, age, height, weight, past medical history and physical defect information.

Optionally, the method further includes: acquiring the motion training image set; and inputting the motion training image set into a convolutional neural network for training to obtain the motion function evaluation model.

Optionally, the method further includes: acquiring rehabilitation medical knowledge; determining a rule system corresponding to the rehabilitation medical knowledge according to a pre-stored system construction rule, wherein the rule system corresponding to the rehabilitation medical knowledge comprises a rehabilitation medical knowledge entity, entity attributes and mutual relations; constructing an initial rehabilitation medicine knowledge graph based on the rehabilitation medicine knowledge entities, the entity attributes and the mutual relations; and determining the graph structure of the initial rehabilitation medical knowledge graph based on any one or more algorithms of a path feature algorithm, a rule learning algorithm and a knowledge representation learning algorithm to obtain the rehabilitation medical knowledge graph.

Optionally, the method further includes: and sending the training result to a monitoring terminal for displaying.

In a second aspect, an embodiment of the present invention provides a rehabilitation training evaluation processing apparatus, including: the acquisition module is used for acquiring rehabilitation training video data corresponding to a user to be rehabilitated and acquired by the video acquisition equipment and determining a motion image set according to the rehabilitation training video data; the rehabilitation training video data are video data formed by the action of the user to be rehabilitated according to the pre-evaluated data to be rehabilitated; the processing module is used for identifying the moving image set by adopting a motion function evaluation model and determining action parameter values corresponding to all the moving images in the moving image set, wherein the motion function evaluation model is obtained by training according to a motion training image set; the processing module is further used for analyzing and processing action parameter values corresponding to the motion images in the motion image set based on a prestored rehabilitation medical knowledge map to obtain a training result; the processing module is further configured to send the training result to the terminal device corresponding to the user to be rehabilitated.

In a third aspect, an embodiment of the present invention provides a rehabilitation training evaluation processing apparatus, including: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the rehabilitation training assessment processing method of any of the first aspects.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the rehabilitation training assessment processing method according to any one of the first aspect is implemented.

The embodiment of the invention provides a rehabilitation training evaluation processing method, a device and equipment, after the scheme is adopted, the rehabilitation training video data corresponding to a user to be rehabilitated and collected by a video collecting device can be obtained firstly, a corresponding motion image set is determined according to the rehabilitation training video data, then a motion function evaluation model is adopted to identify the motion image set, the action parameter value corresponding to each motion image in the motion image set is determined, then the action parameter value corresponding to each motion image in the motion image set is analyzed and processed based on a prestored rehabilitation medical knowledge map to obtain a training result, the training result is sent to the terminal equipment corresponding to the user to be rehabilitated, the training condition of the user to be rehabilitated is automatically determined based on the motion function evaluation model and the rehabilitation medical knowledge map, and the phenomenon that the user to be rehabilitated trains independently at home is reduced, the problem that whether the training action is correct or not and whether the training action is standard or not is not known, and the rehabilitation training effect is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

Fig. 1 is a schematic structural diagram of an application system of a rehabilitation training evaluation processing method according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of a rehabilitation training evaluation processing method according to an embodiment of the present invention;

fig. 3 is a schematic application diagram of an action parameter identification process according to an embodiment of the present invention;

fig. 4 is a schematic flow chart illustrating a rehabilitation training evaluation processing method according to another embodiment of the present invention;

fig. 5 is a schematic structural diagram of a rehabilitation training evaluation processing device according to an embodiment of the present invention;

fig. 6 is a schematic diagram of a hardware structure of a rehabilitation training evaluation processing device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of including other sequential examples in addition to those illustrated or described. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

At present, due to the limitation of medical level, there are still a large number of disabled persons, old persons and patients with chronic diseases who have urgent needs for rehabilitation.

However, due to the concept of heavy treatment and light rehabilitation for a long time, only large hospitals are equipped with equipment and technicians related to rehabilitation, and general small or community hospitals are not equipped with related equipment and technicians, so that a user to be rehabilitated can only frequently go to the large hospital to receive rehabilitation training, and the convenience of receiving the rehabilitation training by the user to be rehabilitated is influenced. The user to be rehabilitated can receive rehabilitation training in a large hospital and then train at home according to the learned rehabilitation knowledge, and due to the fact that the user to be rehabilitated has different learning levels and is unsupervised, the user does not know whether the training action is correct or not or whether the training action is standard or not during home independent training, the effect of rehabilitation training is reduced, and rehabilitation experience of the user to be rehabilitated is influenced.

Based on the problems, the application provides a pre-trained motion function evaluation model based on the convolutional neural network technology, and a constructed rehabilitation medical knowledge graph identifies a motion image set determined by a user to be rehabilitated in the rehabilitation process, automatically determines the accuracy of the training action of the person to be rehabilitated, plays a role in automatically supervising the rehabilitation process of the person to be rehabilitated, improves the rehabilitation training effect, does not need to frequently go to a large hospital to realize rehabilitation training, improves the convenience for the user to be rehabilitated to receive rehabilitation training, and achieves the technical effect of improving the rehabilitation experience of the user to be rehabilitated.

Fig. 1 is a schematic structural diagram of an application system of a rehabilitation training evaluation processing method according to an embodiment of the present invention, as shown in fig. 1, including: the rehabilitation training system comprises a video acquisition device 101, a terminal device 102 and a server 103, wherein the video acquisition device 101 is used for acquiring a motion video of a user to be rehabilitated in the rehabilitation training process, obtaining a motion image set according to the motion video, and then transmitting the motion image set to the server 103 through the terminal device 102. The video capture device 101 may be a separate device or may be a component integrated in the terminal device 102. In addition, an exercise function evaluation model and a rehabilitation medicine knowledge map, which may be, for example, an exercise function evaluation model 104 and a rehabilitation medicine knowledge map 105, are deployed in the server 103. The analysis processing of the moving image set is realized through the moving function evaluation model 104 and the rehabilitation medical knowledge map 105 deployed in the server 103, the accuracy of the rehabilitation action of the user to be rehabilitated is determined, and the training result is finally obtained and pushed to the terminal device corresponding to the relevant user, for example, the training result may be the terminal device corresponding to the user to be rehabilitated, the training result may also be the terminal device corresponding to professional medical staff, and the training result may also be the monitoring terminal at the far end.

The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.

Fig. 2 is a flowchart illustrating a rehabilitation training evaluation processing method according to an embodiment of the present invention, where the method of this embodiment may be executed by the server 103. As shown in fig. 2, the method of this embodiment may include:

s201: acquiring rehabilitation training video data corresponding to a user to be rehabilitated and acquired by video acquisition equipment, and determining a motion image set according to the rehabilitation training video data; the rehabilitation training video data are video data formed by the action of the user to be rehabilitated according to the pre-evaluated data to be rehabilitated.

In this embodiment, before the rehabilitation training of the user to be rehabilitated, the current situation of the user to be rehabilitated can be determined according to the professional evaluation, and then the corresponding pre-evaluated data to be rehabilitated is determined according to the current situation of the user to be rehabilitated, so that the user to be rehabilitated can perform rehabilitation training at home or in a community hospital according to the corresponding pre-evaluated data to be rehabilitated.

Specifically, the pre-evaluated training data to be rehabilitated may be pre-stored determined video data, or may be evaluated and determined according to the actual situation of the user to be rehabilitated. The data to be rehabilitated may include rehabilitation training data of different grades of the corresponding part of the user to be rehabilitated. The rehabilitation training data may include rehabilitation training movements, rehabilitation training durations, and/or rehabilitation training times.

Furthermore, the corresponding parts of the user to be rehabilitated may include the shoulder, elbow joint, knee joint, etc. parts of the user to be rehabilitated, and different parts may also correspond to different levels of rehabilitation training data, and the different levels of rehabilitation training data may represent different training strengths. For example, different levels of rehabilitation training data of the same part can be divided into a first level, a second level and a third level, wherein the first level is the level with the best rehabilitation degree and the level closest to the normal living standard, the second level is the level with the better rehabilitation degree and the level closer to the normal living standard, and the third level is the level with the ordinary rehabilitation degree and needs more training from the normal living standard. The first-level corresponding rehabilitation training data can be corresponding actions for training shoulders, the training is carried out for one hour every day, and each group of actions is trained for 5 times; the second-level corresponding rehabilitation training data can be corresponding actions for training shoulders, the training is carried out for two hours every day, and each group of actions are trained for 10 times; the rehabilitation training data corresponding to the three levels can be corresponding actions for training shoulders, three hours of training are carried out every day, and each group of actions are trained for 15 times. The specific evaluation rule of the rehabilitation grade can be classified and evaluated according to different parts according to the existing standard, and is not discussed in detail here.

In a specific example, a specific implementation manner of determining the corresponding pre-evaluated training data to be rehabilitated may be:

before step S201, a guidance action corresponding to the user to be rehabilitated may be determined according to the rehabilitation information corresponding to the user to be rehabilitated. And acquiring the rehabilitation evaluation video data acquired by the video acquisition equipment. And the rehabilitation evaluation video data is formed by the user to be rehabilitated performing actions according to the guiding action. And determining an evaluation moving image set according to the rehabilitation evaluation video data, identifying the evaluation moving image set by adopting a moving function evaluation model, and determining action parameter values corresponding to each evaluation moving image in the evaluation moving image set. And based on the rehabilitation medical knowledge map, evaluating action parameter values and rehabilitation information corresponding to the evaluation moving images in the evaluation moving image set to obtain pre-evaluated rehabilitation training data.

Specifically, when the rehabilitation training video data corresponding to the user to be rehabilitated is determined, the guidance action corresponding to the user to be rehabilitated can be determined according to the rehabilitation information corresponding to the user to be rehabilitated, and then the user to be rehabilitated can perform the corresponding action according to the guidance action, so that the rehabilitation evaluation video data can be obtained. The rehabilitation information corresponding to the user to be rehabilitated may include: the sex, age, height, weight, past medical history and physical defect information of the user to be rehabilitated. After the rehabilitation evaluation video data is obtained, a corresponding evaluation motion image set can be determined according to the rehabilitation evaluation video data. And inputting the evaluation motion image set into the motion function evaluation model for identification, determining action parameter values corresponding to the evaluation motion images in the evaluation motion image set, and after obtaining the action parameter values, evaluating the action parameter values corresponding to the evaluation motion images in the evaluation motion image set based on a rehabilitation medical knowledge map to obtain pre-evaluated rehabilitation training data.

In addition, the pre-evaluated rehabilitation training data may be a result determined when the user to be rehabilitated evaluates for the first time, that is, a result obtained by evaluating the user to be rehabilitated before the user to be rehabilitated receives rehabilitation training. If the pre-evaluated rehabilitation training data is pre-stored determined training data, the stored pre-evaluated rehabilitation training data can be directly obtained from the database without executing the relevant steps for obtaining the pre-evaluated rehabilitation training data.

The data to be rehabilitated may include rehabilitation training data of different grades of corresponding parts of the user to be rehabilitated, and the rehabilitation training data may include rehabilitation training actions, rehabilitation training duration, and/or rehabilitation training times.

If the to-be-rehabilitated training data includes rehabilitation training data of different grades of corresponding parts of the to-be-rehabilitated user, and the rehabilitation training data includes rehabilitation training actions, rehabilitation training duration and/or rehabilitation training times, acquiring rehabilitation training video data corresponding to the to-be-rehabilitated user acquired by the video acquisition device, and determining a specific implementation mode of the motion image set according to the rehabilitation training video data may include: and acquiring rehabilitation training video data acquired by the video acquisition equipment according to rehabilitation training actions, rehabilitation training duration and/or rehabilitation training times in the rehabilitation training data of the user to be rehabilitated. And separating the rehabilitation video data according to frames to obtain a moving image set containing a plurality of frame images. For example, when the rehabilitation video data is subjected to the separation processing on a frame basis, the rehabilitation video data may be subjected to the separation processing on a 24-frame-per-second basis.

S202: and identifying the motion image set by adopting a motion function evaluation model, and determining the action parameter value corresponding to each motion image in the motion image set, wherein the motion function evaluation model is obtained by training according to the motion training image set.

In this embodiment, there may be one or more moving images in the motion set. The motion image may include a rehabilitation training action executed by the user to be rehabilitated according to pre-estimated data to be rehabilitated, and after receiving the motion image set, the motion function evaluation model may determine an action parameter value corresponding to the rehabilitation training action executed by the user to be rehabilitated according to the rehabilitation training action included in each motion image in the motion image set. The motion parameter values corresponding to the rehabilitation training motion can comprise joint activity, posture and proprioception measurement; measuring muscle strength and muscle tension; gait measurement and analysis; analyzing a balance function; lower limb joint stability; upper limb joint stability, and skin temperature measurement.

For example, fig. 3 is an application schematic diagram of an action parameter identification process provided in an embodiment of the present invention, in this example, the rehabilitation training video data guides a person to be rehabilitated to use a fibula small head as a shaft head, a fixed arm is parallel to a femur, a moving arm is parallel to a fibula, and a flexion range of the knee joint is 0 to 135 degrees. As shown in a in fig. 3, the action parameter values corresponding to the rehabilitation training action executed by the user to be rehabilitated and identified by the motor function evaluation model are specifically: the joint is knee joint, the type of motion is flexion and extension, and the angle is 36.5 degrees. As shown in b in fig. 3, the action parameter values corresponding to the rehabilitation training action executed by the user to be rehabilitated and identified by the motor function evaluation model are specifically: the joint is knee joint, the type of motion is flexion and extension, and the angle is 127.4 degrees.

In addition, in the rehabilitation training process of the user to be rehabilitated, in order to better remind whether the rehabilitation action of the user to be rehabilitated is trained in place, specific parameter values corresponding to the training action of the user to be rehabilitated can be broadcasted in a voice mode when the user to be rehabilitated carries out rehabilitation training, and specific parameter values corresponding to the training action of the user to be rehabilitated can be displayed on the terminal device in real time, so that the user can adjust nonstandard actions in the rehabilitation training process in real time, and the rehabilitation training effect is further improved.

In addition, the exercise function evaluation model can be obtained by training according to an exercise training image set, and the specific implementation mode can be as follows: a set of athletic training images is acquired. And inputting the motion training image set into a convolutional neural network for training to obtain a motion function evaluation model.

Specifically, the exercise training image set is each exercise training image carrying a label, a test environment comprising a camera, a constant-speed/equal-length muscle strength test device, a balance test device and a plantar pressure test device is built in a relevant hospital, a rehabilitation evaluation video and rehabilitation evaluation measurement parameters of a user to be rehabilitated in the rehabilitation process are recorded and marked, and an effective exercise training image set is formed.

S203: and analyzing and processing the action parameter values corresponding to the motion images in the motion image set based on the pre-stored rehabilitation medical knowledge map to obtain a training result.

In this embodiment, after determining the motion parameter value corresponding to each motion image in the motion image set, the motion parameter value corresponding to each motion image in the motion image set may be analyzed based on the pre-stored rehabilitation medical knowledge map, so as to obtain the training result. The training result can be a standard degree score of the training action of the user to be rehabilitated in the rehabilitation process. The rehabilitation medical knowledge graph can realize standard degree scoring of the motion image set determined according to rehabilitation training data of different grades of the corresponding part.

In a specific example, taking the rehabilitation training of a scapulohumeral periarthritis patient as an example, in the rehabilitation training process, a person to be rehabilitated trains shoulders of the person to be rehabilitated according to rehabilitation training data corresponding to the shoulders to obtain a corresponding motion image set, then inputs the motion image set into a motion function evaluation model for identification, determines motion parameter values corresponding to each action in the scapulohumeral periarthritis rehabilitation training process, such as arm lifting angle, rotation angle and the like, and then analyzes the motion parameter values corresponding to each action in the scapulohumeral periarthritis rehabilitation training process based on a rehabilitation medicine knowledge graph, such as arm lifting angle, rotation angle and the like, so as to obtain standard degree scores of rehabilitation actions performed by the user to be rehabilitated.

S204: and sending the training result to the terminal equipment corresponding to the user to be recovered.

In this embodiment, after the training result is obtained, the training result may be sent to the terminal device corresponding to the user to be rehabilitated, so that the user to be rehabilitated can check the training result, and the rehabilitation training action can be adjusted in time according to the training result. In addition, the basic information, the historical case, the training result and the like of the user to be recovered can be integrated to obtain the training report sheet of the user to be recovered, and the training report sheet is sent to the terminal equipment corresponding to the user to be recovered to be displayed so as to remind the user to be recovered to check the generated training report sheet in time.

In addition, the training result can be sent to the monitoring terminal to be displayed, so that the medical staff can check the training condition of the user to be recovered in real time, and guide the user to be recovered to train according to the training condition of the user to be recovered, and the training effect of the user to be recovered is improved.

In addition, when the training result is the standard degree score of the rehabilitation action performed by the user to be rehabilitated, different training reports can be correspondingly generated according to the score result, for example, if the standard degree score is in the range of 100-80, a training report with excellent training action can be correspondingly generated. If the standard degree score is in the range of 80-70, a training report sheet with good training action can be correspondingly generated. If the standard degree score is in the range of 70-60, a training report sheet with qualified training actions can be correspondingly generated. If the standard degree score is in the range of 60-0, a training report sheet with unqualified training actions can be correspondingly generated.

By adopting the scheme, the training condition of the user to be recovered is automatically determined based on the motion function evaluation model and the rehabilitation medicine knowledge map, the problems that whether the training action is correct or not and whether the training action is standard or not are not known when the user to be recovered is trained at home alone are solved, and the effect of the rehabilitation training is improved.

Based on the method of fig. 2, the present specification also provides some specific embodiments of the method, which are described below.

In another embodiment, the graph structure inference algorithm of the rehabilitation medicine knowledge graph includes any one or a combination of a path feature algorithm, a rule learning algorithm and a knowledge representation learning algorithm, and the specific implementation manner of step S203 may be:

and analyzing and processing the action parameter values corresponding to the motion images in the motion image set based on any one or combination of a plurality of algorithms in a path characteristic algorithm, a rule learning algorithm and a knowledge representation learning algorithm in a prestored rehabilitation medical knowledge map to obtain a training result.

In the present embodiment, the path feature algorithm, the rule learning algorithm, and the knowledge representation learning algorithm may employ existing algorithms. Before analyzing and processing the action parameter values corresponding to the motion images in the motion image set through the rehabilitation medical knowledge map, a map structure of the rehabilitation medical knowledge map can be constructed based on one or more algorithms of a path characteristic algorithm, a rule learning algorithm and a knowledge representation learning algorithm. Wherein, the construction mode can be as follows:

and acquiring rehabilitation medical knowledge. And determining a rule system corresponding to the rehabilitation medical knowledge according to a pre-stored system construction rule, wherein the rule system corresponding to the rehabilitation medical knowledge comprises a rehabilitation medical knowledge entity, entity attributes and mutual relations. An initial rehabilitation medicine knowledge map is constructed based on the rehabilitation medicine knowledge entities, the entity attributes and the mutual relations. And determining the graph structure of the initial rehabilitation medical knowledge graph based on any one or more algorithms of a path feature algorithm, a rule learning algorithm and a knowledge representation learning algorithm to obtain the rehabilitation medical knowledge graph.

Specifically, under the guidance of a professional person in rehabilitation medicine, a rehabilitation medicine knowledge representation method and a unified rule system such as entities, attributes and relations are designed, then a graph database is selected for storage, and data acquisition, knowledge extraction, knowledge representation, knowledge fusion and knowledge reasoning workflow are determined. And then, a mode combining top-down and bottom-up is adopted, firstly, a rehabilitation medicine knowledge body and a data mode are defined, and then, the entity is led into a graph database to form a basic knowledge graph. And then, crawling professional website data by adopting a web crawler method, updating the high-quality rehabilitation medical literature to a basic knowledge map, forming continuous knowledge transformation capability from bottom to top, realizing knowledge updating, extracting entities and relations, and constructing the rehabilitation medical knowledge map through knowledge fusion and knowledge reasoning.

In addition, when the rehabilitation medical knowledge is extracted, the entities can be named according to the dictionary and the rules based on the rehabilitation medical knowledge core content imported in batches and the data crawled by the web crawler, and the rehabilitation medical knowledge entities, the entity attributes and the mutual relations can be extracted. When the knowledge representation and storage are realized, the knowledge can be stored by using the graph database, and updating, inquiring and analyzing are realized. Among them, the graph database may be Neo4 j. When the knowledge fusion is realized, the initial rehabilitation medical knowledge map can be formed after the multi-source heterogeneous knowledge is integrated, disambiguated, processed and updated under the unified rule. And finally, establishing a reasoning and entity relationship quantification algorithm through any one or more algorithms of a path characteristic algorithm, a rule learning algorithm and a knowledge representation learning algorithm based on the initial rehabilitation medical knowledge map to obtain a complete rehabilitation medical knowledge map, and further realizing the function of analyzing whether the training action is accurate.

Fig. 4 is a schematic flow chart of a rehabilitation training evaluation processing method according to another embodiment of the present invention, and as shown in fig. 4, the method may further include:

s401: and acquiring basic sign parameter data monitored by the wearable sensing equipment.

S402: and analyzing and processing the basic sign parameter data and the action parameter values corresponding to the motion images in the motion image set based on the pre-stored rehabilitation medical knowledge map to obtain a training result.

In this embodiment, when the training result is determined by the rehabilitation medical knowledge graph evaluation, the action parameter values corresponding to the motion images in the motion image set can be evaluated, and the action parameter values and the basic sign parameter data monitored by the wearable sensing device can be analyzed simultaneously, so that the accuracy of judging whether the rehabilitation training action of the user to be rehabilitated is standard or not is improved.

In addition, in this embodiment, the wearable sensing device may include any one or more of a vital sign sensing wristwatch, a plantar pressure sensor, and a surface myoelectricity wearable sensor, and then may realize real-time acquisition, transmission, integration, storage, and calculation processing of data such as heart rate, blood pressure, blood oxygen, electrocardiogram, body surface tissue fluid composition, surface myoelectricity, pressure distribution, and movement speed, so as to obtain basic sign parameter data.

In addition, in this embodiment, the method may further include: and if any parameter data in the basic sign parameter data monitored by the wearable sensing equipment exceeds a preset threshold, generating an alarm prompt. And sending the alarm prompt to the monitoring terminal.

Specifically, treat that the recovered user carries out the rehabilitation training in-process, wearable sensing equipment can real-time supervision sign data change and early warning, will treat the exercise intensity control of recovered user at reasonable within range, avoid because of the proruption discomfort of health that the rehabilitation training caused, guarantee the rehabilitation training safety under the recovered scene of community and family. The preset threshold value of the exercise intensity can be set in a user-defined mode on the basis of the cardiopulmonary function of the user to be recovered and other suffered chronic diseases. In addition, if any parameter data in the basic sign parameter data monitored by the wearable sensing equipment exceeds a preset threshold value, an alarm prompt can be generated and sent to the monitoring terminal, wherein the monitoring terminal is a terminal device corresponding to a professional technician, risks encountered by the person to be rehabilitated in the rehabilitation process can be found in real time, and the safety of the rehabilitation training process is improved.

Furthermore, in another embodiment, the method may further include:

and judging whether the training result is within a preset score range.

And if the training result is not within the preset score range, determining the guidance action corresponding to the user to be recovered and the subsequent steps according to the recovery information corresponding to the user to be recovered again, and determining new pre-estimated recovery training data. The new pre-evaluated rehabilitation training data may be the same as or different from the original pre-evaluated rehabilitation training data. When the new pre-evaluated rehabilitation training data is different from the original pre-evaluated rehabilitation training data, the part corresponding to the user to be rehabilitated in the new pre-evaluated rehabilitation training data may be different from the part in the original pre-evaluated rehabilitation training data, or the part corresponding to the user to be rehabilitated in the new pre-evaluated rehabilitation training data may be the same as the part in the original pre-evaluated rehabilitation training data, and any one or more parameters of the rehabilitation training action, the rehabilitation training duration, and the rehabilitation training frequency of the part corresponding to the user to be rehabilitated may be different from the parameters in the original pre-evaluated rehabilitation training data.

Specifically, after the training result is obtained, it may be determined whether the training result is within a preset score range, for example, the preset score may be set to a range of 100-60. If the training result is not within the preset score range, it is indicated that the rehabilitation action performed by the user to be rehabilitated is not standard, it is indicated that the rehabilitation training data adopted by the current rehabilitation training may not be suitable for the user to be rehabilitated, namely, the current body state of the user to be rehabilitated is not suitable for the rehabilitation training data of the current pre-evaluation, the user to be rehabilitated needs to be evaluated again, and new rehabilitation training data of the pre-evaluation is determined, so that the user to be rehabilitated performs rehabilitation training according to the new rehabilitation training data of the pre-evaluation, and the rehabilitation training effect of the user to be rehabilitated is improved.

If the training result is within the preset score range, the pre-evaluated rehabilitation training data adopted by the current rehabilitation training is suitable for the user to be rehabilitated, a training action standard can be generated, the prompt of the training is continuously tried and pushed to the related user, and the user to be rehabilitated can continuously perform rehabilitation training according to the pre-evaluated rehabilitation training data adopted by the current rehabilitation training.

In addition, in another embodiment, the method can also be applied to the field of epidemic prevention, and in the face of a major public health accident, the community is one of the main battlefields for epidemic prevention and epidemic prevention. The embodiment can realize home body building and rehabilitation guidance. The body temperature detection alarm can be realized through wearable sensing equipment, the body temperature of a specific crowd is monitored in real time, early warning is timely carried out, and the occurrence of the infectious diseases is avoided. Meanwhile, real-time positioning and track playback can be realized, and the system can be connected with an epidemic situation resistant big data platform, so that data support is provided for accurate epidemic prevention and control and long-acting mechanism establishment.

Based on the same idea, an embodiment of the present specification further provides a device corresponding to the method, and fig. 5 is a schematic structural diagram of a rehabilitation training evaluation processing device provided in an embodiment of the present invention, as shown in fig. 5, the method may include:

the acquiring module 501 is configured to acquire rehabilitation training video data corresponding to a user to be rehabilitated, which is acquired by a video acquisition device, and determine a moving image set according to the rehabilitation training video data; the rehabilitation training video data are video data formed by the action of the user to be rehabilitated according to the pre-evaluated data to be rehabilitated.

In this embodiment, the pre-evaluated training data to be rehabilitated may be pre-stored determined video data, or may be evaluated and determined according to the actual situation of the user to be rehabilitated. The data to be rehabilitated may include rehabilitation training data of different grades of the corresponding part of the user to be rehabilitated. The rehabilitation training data may include rehabilitation training movements, rehabilitation training durations, and/or rehabilitation training times.

In a specific example, the processing module 502 may be further configured to: and determining the guiding action corresponding to the user to be recovered according to the recovery information corresponding to the user to be recovered. And acquiring the rehabilitation evaluation video data acquired by the video acquisition equipment. And the rehabilitation evaluation video data is formed by the user to be rehabilitated performing actions according to the guiding action. And determining an evaluation moving image set according to the rehabilitation evaluation video data, identifying the evaluation moving image set by adopting a moving function evaluation model, and determining action parameter values corresponding to each evaluation moving image in the evaluation moving image set. And based on the rehabilitation medical knowledge map, evaluating action parameter values and rehabilitation information corresponding to the evaluation moving images in the evaluation moving image set to obtain pre-evaluated rehabilitation training data.

If the data to be rehabilitated includes the data to be rehabilitated of different levels of the corresponding part of the user to be rehabilitated, and the data to be rehabilitated includes the rehabilitation training action, the duration of the rehabilitation training, and/or the number of times of the rehabilitation training, the processing module 502 may further be configured to: and acquiring rehabilitation training video data acquired by the video acquisition equipment according to rehabilitation training actions, rehabilitation training duration and/or rehabilitation training times in the rehabilitation training data of the user to be rehabilitated. And separating the rehabilitation video data according to frames to obtain a moving image set containing a plurality of frame images.

The processing module 502 may be further configured to: and identifying the motion image set by adopting a motion function evaluation model, and determining the action parameter value corresponding to each motion image in the motion image set, wherein the motion function evaluation model is obtained by training according to the motion training image set.

In addition, the processing module 502 may further be configured to: a set of athletic training images is acquired. And inputting the motion training image set into a convolutional neural network for training to obtain a motion function evaluation model.

The processing module 502 may be further configured to: and analyzing and processing the action parameter values corresponding to the motion images in the motion image set based on the pre-stored rehabilitation medical knowledge map to obtain a training result.

The processing module 502 may be further configured to: and sending the training result to the terminal equipment corresponding to the user to be recovered.

In addition, the processing module 502 may further be configured to: and sending the training result to a monitoring terminal for displaying.

In addition, in another embodiment, the graph structure inference algorithm of the rehabilitation medicine knowledge graph comprises any one or more of a combination of a path feature algorithm, a rule learning algorithm and a knowledge representation learning algorithm.

The processing module 502 may be further configured to: and analyzing and processing action parameter values corresponding to the motion images in the motion image set based on any one or combination of a plurality of algorithms in the path characteristic algorithm, the rule learning algorithm and the knowledge representation learning algorithm in the pre-stored rehabilitation medical knowledge map to obtain a training result.

The processing module 502 may be further configured to: and acquiring rehabilitation medical knowledge. And determining a rule system corresponding to the rehabilitation medical knowledge according to a pre-stored system construction rule, wherein the rule system corresponding to the rehabilitation medical knowledge comprises a rehabilitation medical knowledge entity, entity attributes and mutual relations. An initial rehabilitation medicine knowledge map is constructed based on the rehabilitation medicine knowledge entities, the entity attributes and the mutual relations. And determining the graph structure of the initial rehabilitation medical knowledge graph based on any one or more algorithms of a path feature algorithm, a rule learning algorithm and a knowledge representation learning algorithm to obtain the rehabilitation medical knowledge graph.

In another embodiment of the present invention, the processing module 502 may further be configured to:

and acquiring basic sign parameter data monitored by the wearable sensing equipment.

And analyzing and processing the basic sign parameter data and the action parameter values corresponding to the motion images in the motion image set based on the pre-stored rehabilitation medical knowledge map to obtain a training result.

In this embodiment, the processing module is further configured to: and if any parameter data in the basic sign parameter data monitored by the wearable sensing equipment exceeds a preset threshold, generating an alarm prompt. And sending the alarm prompt to a monitoring terminal.

In this embodiment, the wearable sensing device may include any one or more of a vital signs sensing wristwatch, a plantar pressure sensor, and a surface myoelectricity wearable sensor.

In addition, in another embodiment, the processing module 502 may further be configured to:

and judging whether the training result is in a preset score range.

The apparatus provided in the embodiment of the present invention may implement the method in the embodiment shown in fig. 2, and the implementation principle and the technical effect are similar, which are not described herein again.

Fig. 6 is a schematic diagram of a hardware structure of a rehabilitation training evaluation processing device according to an embodiment of the present invention. As shown in fig. 6, the present embodiment provides an apparatus 600 including: at least one processor 601 and memory 602. The processor 601 and the memory 602 are connected by a bus 603.

In a specific implementation, at least one processor 601 executes computer-executable instructions stored by the memory 602 to cause the at least one processor 601 to perform the methods of the above-described method embodiments.

For a specific implementation process of the processor 601, reference may be made to the above method embodiments, which implement the principle and the technical effect similarly, and details of this embodiment are not described herein again.

In the embodiment shown in fig. 6, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.

The memory may comprise high speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.

The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.

The embodiment of the invention also provides a computer-readable storage medium, wherein a computer execution instruction is stored in the computer-readable storage medium, and when a processor executes the computer execution instruction, the rehabilitation training evaluation processing method of the embodiment of the method is realized.

The computer-readable storage medium may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.

An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium may also reside as discrete components in the apparatus.

Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A rehabilitation training assessment processing method, comprising:

acquiring rehabilitation training video data corresponding to a user to be rehabilitated and acquired by video acquisition equipment, and determining a motion image set according to the rehabilitation training video data; the rehabilitation training video data are video data formed by the action of the user to be rehabilitated according to the pre-evaluated data to be rehabilitated;

identifying the moving image set by adopting a moving function evaluation model, and determining an action parameter value corresponding to each moving image in the moving image set, wherein the moving function evaluation model is obtained by training according to a moving training image set;

analyzing and processing action parameter values corresponding to all the motion images in the motion image set based on a prestored rehabilitation medical knowledge map to obtain a training result;

and sending the training result to the terminal equipment corresponding to the user to be recovered.

2. The method of claim 1, wherein the graph structure inference algorithm of the rehabilitation medicine knowledge-graph comprises any one or more of a path feature algorithm, a rule learning algorithm, and a knowledge representation learning algorithm,

the method comprises the following steps of analyzing and processing action parameter values corresponding to all the motion images in the motion image set based on a pre-stored rehabilitation medical knowledge map to obtain a training result, wherein the method comprises the following steps:

and analyzing and processing action parameter values corresponding to the motion images in the motion image set based on any one or combination of a plurality of algorithms in the path characteristic algorithm, the rule learning algorithm and the knowledge representation learning algorithm in the pre-stored rehabilitation medical knowledge map to obtain a training result.

3. The method according to claim 1, wherein the rehabilitation training data comprises rehabilitation training data of different grades of corresponding parts of the user to be rehabilitated, the rehabilitation training data comprises rehabilitation training actions, rehabilitation training duration and/or rehabilitation training times,

the acquiring of the rehabilitation training video data corresponding to the user to be rehabilitated, acquired by the video acquisition device, and determining the moving image set according to the rehabilitation training video data includes:

acquiring rehabilitation training video data acquired by video acquisition equipment according to rehabilitation training actions, rehabilitation training duration and/or rehabilitation training times in the rehabilitation training data of a user to be rehabilitated;

and separating the rehabilitation video data according to frames to obtain a moving image set containing a plurality of frame images.

4. The method according to any one of claims 1-3, further comprising:

acquiring basic sign parameter data monitored by wearable sensing equipment;

and analyzing and processing the basic sign parameter data and the action parameter values corresponding to the motion images in the motion image set based on a pre-stored rehabilitation medical knowledge map to obtain a training result.

5. The method according to any one of claims 1 to 3, wherein before the acquiring the rehabilitation training video data corresponding to the user to be rehabilitated and collected by the video collecting device, the method further comprises:

determining a guidance action corresponding to the user to be recovered according to the recovery information corresponding to the user to be recovered;

acquiring rehabilitation evaluation video data acquired by the video acquisition equipment; the rehabilitation evaluation video data are video data formed by the user to be rehabilitated acting according to the guiding action;

determining an evaluation moving image set according to the rehabilitation evaluation video data, identifying the evaluation moving image set by adopting a moving function evaluation model, and determining action parameter values corresponding to each evaluation moving image in the evaluation moving image set;

and based on the rehabilitation medical knowledge map, evaluating action parameter values corresponding to the evaluation motion images in the evaluation motion image set and the rehabilitation information to obtain the pre-evaluated rehabilitation training data.

6. The method of claim 5, further comprising:

judging whether the training result is within a preset score range;

and if the training result is not within the preset score range, re-executing the steps of determining the guiding action corresponding to the user to be recovered and the subsequent steps according to the recovery information corresponding to the user to be recovered, and determining new pre-estimated recovery training data, wherein the part corresponding to the user to be recovered in the new pre-estimated recovery training data is different from the part in the original estimated recovery training data, or the part corresponding to the user to be recovered in the new pre-estimated recovery training data is the same as the part in the original estimated recovery training data, and any one or more parameters of the recovery training action, the recovery training duration and the recovery training times of the part corresponding to the user to be recovered are different from the parameters in the original estimated recovery training data.

7. The method of claim 4, further comprising:

if any parameter data in the basic sign parameter data monitored by the wearable sensing equipment exceeds a preset threshold, generating an alarm prompt;

and sending the alarm prompt to a monitoring terminal.

8. The method of claim 4, wherein the wearable sensing device comprises any one or more of a vital signs sensing wristwatch, a plantar pressure sensor, and a surface myoelectric wearable sensor.

9. The method of claim 5, wherein the rehabilitation information corresponding to the user to be rehabilitated comprises: the user to be rehabilitated comprises any one or more of sex, age, height, weight, past medical history and physical defect information.

10. The method according to any one of claims 1-3, further comprising:

acquiring the motion training image set;

and inputting the motion training image set into a convolutional neural network for training to obtain the motion function evaluation model.

11. The method according to any one of claims 1-3, further comprising:

acquiring rehabilitation medical knowledge;

determining a rule system corresponding to the rehabilitation medical knowledge according to a pre-stored system construction rule, wherein the rule system corresponding to the rehabilitation medical knowledge comprises a rehabilitation medical knowledge entity, entity attributes and mutual relations;

constructing an initial rehabilitation medicine knowledge graph based on the rehabilitation medicine knowledge entities, the entity attributes and the mutual relations;

and determining the graph structure of the initial rehabilitation medical knowledge graph based on any one or more algorithms of a path feature algorithm, a rule learning algorithm and a knowledge representation learning algorithm to obtain the rehabilitation medical knowledge graph.

12. The method according to any one of claims 1-3, further comprising:

and sending the training result to a monitoring terminal for displaying.

13. A rehabilitation training evaluation processing device, comprising:

the acquisition module is used for acquiring rehabilitation training video data corresponding to a user to be rehabilitated and acquired by the video acquisition equipment and determining a motion image set according to the rehabilitation training video data; the rehabilitation training video data are video data formed by the action of the user to be rehabilitated according to the pre-evaluated data to be rehabilitated;

the processing module is used for identifying the moving image set by adopting a motion function evaluation model and determining action parameter values corresponding to all the moving images in the moving image set, wherein the motion function evaluation model is obtained by training according to a motion training image set;

the processing module is further used for analyzing and processing action parameter values corresponding to the motion images in the motion image set based on a prestored rehabilitation medical knowledge map to obtain a training result;

the processing module is further configured to send the training result to the terminal device corresponding to the user to be rehabilitated.

14. A rehabilitation training evaluation processing device, comprising: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the rehabilitation training assessment processing method of any of claims 1-12.

15. A computer-readable storage medium having stored thereon computer-executable instructions which, when executed by a processor, implement the rehabilitation training assessment processing method of any of claims 1-12.