Human bone rehabilitation training method, device, electronic device and storage medium

Abstract

An embodiment of the present invention provides a human bone rehabilitation training method, device, electronic device, and storage medium, which relate to the field of rehabilitation training. The method collects video data through an electronic device, obtains the coordinates of human bone points based on the video data, calculates the real-time action angles during the user's training process, and then determines whether the user has completed the training action, realizing effective monitoring of the user's actual training situation during the user's training process, helping the user to effectively perform bone rehabilitation training, and thus improving the training effect.

Description

Technical Field

[0001] The present invention relates to the field of rehabilitation training, and more particularly, to a method, device, electronic device, and storage medium for human bone rehabilitation training. Background Art

[0002] With the rapid development of terminal technology, the functions of electronic devices have become increasingly rich, and the ability to access the Internet has been very mature. Therefore, more and more people use terminal devices for bone rehabilitation training.

[0003] Now, when using an electronic device for bone rehabilitation training, different training actions are displayed on the electronic device, and the user selects a training action according to their subjective will. The electronic device plays the training action according to the user's selection, enabling the user to perform corresponding actions following the played training action. However, this method cannot effectively monitor the actual training situation of the user, resulting in poor training effects for the user. Summary of the Invention

[0004] In view of this, an object of the present invention is to provide a method, device, electronic device, and storage medium for human bone rehabilitation training to solve the problem in the prior art that the actual training situation of the user cannot be effectively monitored, resulting in poor training effects for the user.

[0005] To achieve the above object, the technical solutions adopted in the embodiments of the present invention are as follows:

[0006] In a first aspect, the present invention provides a method for human bone rehabilitation training, which is applied to a first terminal. The first terminal includes a camera, and the method includes:

[0007] Based on the acquired video data collected by the camera, identify the coordinates of the human bone points in the video data;

[0008] When it is determined that the first user corresponding to the first terminal meets the training conditions based on the coordinates of the human bone points, determine the coordinates of the target bone points among the human bone points in the video data and the coordinates of the reference bone points adjacent to the target bone points according to the training action currently played by the first terminal;

[0009] Calculate the real-time action angle during the training process of the first user based on the coordinates of the target bone points and the coordinates of the reference bone points;

[0010] Determine whether the first user has completed the training action based on the real-time action angle during the training process of the first user.

[0011] In an alternative embodiment, after the step of identifying the coordinates of the human body skeleton points in the video data acquired by the camera, the method further includes:

[0012] Determine whether the current body direction of the first user matches a preset body direction, whether the body of the first user is located in a specified area on the screen of the first terminal, and whether the current body posture of the first user matches a preset posture according to the coordinates of the human body skeleton points; the preset body direction, the specified area, and the preset posture are all associated with the training action;

[0013] When the current body direction of the first user matches the preset body direction, the body of the first user is located in the specified area, and the current body posture of the first user matches the preset posture, determine that the first user corresponding to the first terminal meets the training conditions.

[0014] In an alternative embodiment, the determining whether the first user completes the training action according to the real-time action angle during the training process of the first user includes:

[0015] Obtain a real-time angle range according to the real-time action angle during the training process of the first user;

[0016] Determine a valid angle range according to the real-time angle range and a preset angle range;

[0017] Obtain a valid angle according to the valid angle range;

[0018] When the number of times that the real-time action angle during the training process of the first user matches the valid angle meets a preset number of times, determine that the first user completes the training action; the preset angle range and the preset number of times are both associated with the training action.

[0019] In an alternative embodiment, the first terminal is communicatively connected to a server, and the server is also communicatively connected to a second terminal. The method further includes:

[0020] Receive a rehabilitation training plan sent by the server; the rehabilitation training plan is generated by the server according to a movement prescription uploaded by the second terminal; the movement prescription is set by a second user corresponding to the second terminal according to a health report of the first user and uploaded to the second terminal; the rehabilitation training plan includes the training action.

[0021] In an alternative embodiment, the rehabilitation training plan further includes a preset number of days. The method further includes:

[0022] When the number of training days of the first user meets the preset number of days and the training actions corresponding to each day in the preset number of days are completed, it is determined that the first user has completed the rehabilitation training plan.

[0023] In an alternative embodiment, the method further includes:

[0024] Obtain the training evaluation data input by the first user after completing the rehabilitation training plan;

[0025] Send the training evaluation data to the server, so that the server generates a training report based on the training evaluation data and sends the training report to the second terminal, thereby facilitating the second user to update the exercise prescription according to the training report and sending the updated exercise prescription to the server, and the server updates the rehabilitation training plan according to the updated exercise prescription.

[0026] In an alternative embodiment, the method further includes:

[0027] When receiving the stop training voice command of the first user, control the camera to stop collecting the video data and stop the currently played training action;

[0028] Broadcast a voice prompt message; the voice prompt message is used to ask the reason for the first user to stop training;

[0029] When receiving the reason voice command issued by the first user based on the voice prompt message, convert the reason voice command into a text command and report the text command to the server communicatively connected to the first terminal.

[0030] In a second aspect, the present invention provides a human body bone rehabilitation training device, which is applied to a first terminal, the first terminal includes a camera, and the device includes:

[0031] A coordinate acquisition module, configured to identify the coordinates of human body bone points in the video data according to the acquired video data collected by the camera;

[0032] An angle calculation module, configured to determine the coordinates of a target bone point among the human body bone points in the video data and the coordinates of a reference bone point adjacent to the target bone point according to the currently played training action of the first terminal when it is determined that the first user corresponding to the first terminal meets the training conditions according to the coordinates of the human body bone points; calculate the real-time action angle during the training process of the first user according to the coordinates of the target bone point and the coordinates of the reference bone point;

[0033] A determination module, configured to determine whether the first user has completed the training action according to the real-time action angle during the first user's training process.

[0034] In a third aspect, the present invention provides an electronic device, including a processor and a memory. The memory stores a computer program, and when the processor executes the computer program, the method described in any one of the foregoing embodiments is implemented.

[0035] In a fourth aspect, the present invention provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in any one of the foregoing embodiments is implemented.

[0036] The human body bone rehabilitation training method, device, electronic device, and storage medium provided by the embodiments of the present invention identify the coordinates of human body bone points in the video data acquired by the acquired camera. When it is determined that the first user corresponding to the first terminal meets the training conditions according to the coordinates of the human body bone points, the coordinates of the target bone points among the human body bone points in the video data and the coordinates of the reference bone points adjacent to the target bone points are determined according to the training action currently played by the first terminal. And according to the coordinates of the target bone points and the coordinates of the reference bone points, the real-time action angle during the first user's training process is calculated. Furthermore, according to the real-time action angle during the first user's training process, it is determined whether the first user has completed the training action. By collecting video data through an electronic device and obtaining the coordinates of human body bone points according to the video data, the real-time action angle during the user's training process is calculated, and then it is determined whether the user has completed the training action, realizing effective monitoring of the user's actual training situation during the user's training process, which helps the user to effectively perform bone rehabilitation training and thus improves the training effect.

[0037] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given and described in detail in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1 Shows a schematic diagram of an application environment of the human body bone rehabilitation training method provided by the embodiments of the present invention;

[0040] Figure 2 Shows a schematic block diagram of an electronic device provided by the embodiments of the present invention;

[0041] Figure 3 shows a schematic flowchart of a human bone rehabilitation training method provided by an embodiment of the present invention;

[0042] Figure 4 shows a schematic diagram for calculating the real-time motion angle during the training of the first user;

[0043] Figure 5 shows another schematic flowchart of the human bone rehabilitation training method provided by an embodiment of the present invention;

[0044] Figure 6 shows Figure 3 a schematic flowchart of the sub-steps of step S304 in

[0045] Figure 7 shows yet another schematic flowchart of the human bone rehabilitation training method provided by an embodiment of the present invention;

[0046] Figure 8 shows a functional module diagram of a human bone rehabilitation training device provided by an embodiment of the present invention;

[0047] Figure 9 shows another functional module diagram of the human bone rehabilitation training device provided by an embodiment of the present invention.

[0048] Icons: 10 - First terminal; 20 - Server; 30 - Second terminal; 210 - Memory; 220 - Processor; 230 - Communication module; 401 - Coordinate acquisition module; 402 - Angle calculation module; 403 - Determination module; 404 - Condition confirmation module; 405 - Transceiving module; 406 - Voice module. Detailed implementation manners

[0049] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Usually, the components of the embodiments of the present invention described and illustrated herein can be arranged and designed in various different configurations.

[0050] Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0051] It should be noted that relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0052] Please refer to Figure 1 , which is a schematic diagram of an application environment for the human bone rehabilitation training method provided in an embodiment of the present invention. As Figure 1 shown, the first terminal 10 is communicatively connected to the server 20, and the server 20 is communicatively connected to the second terminal 30. Among them, the number of the first terminals 10 is one or more, and the embodiments of the present invention do not limit this.

[0053] In this embodiment, taking a patient and a doctor as an example, a patient APP is installed on the first terminal, and a doctor APP is installed on the second terminal. The patient and the doctor can respectively scan the same two-dimensional code sent by the server 20 through the patient APP on the first terminal 10 and the doctor APP on the second terminal 30 to establish a corresponding connection. The patient can fill in a health report on the patient APP on the first terminal 10 according to his own health condition and upload it to the server 20, so that the doctor can obtain the above-mentioned health report through the doctor APP on the second terminal 30 to give corresponding suggestions. When the server 20 receives the suggestions uploaded by the doctor APP on the second terminal 30, it generates a corresponding training plan and sends it to the patient APP on the corresponding first terminal 10, so that the patient can train according to the training plan.

[0054] Among them, the first terminal 10 and the second terminal 30 may be, but are not limited to: a personal computer (PC), a laptop computer, a tablet computer, a mobile phone, etc., and the embodiments of the present invention do not limit this.

[0055] Please refer to Figure 2 , which is a schematic block diagram of an electronic device that can implement the above-mentioned first terminal 10 provided in an embodiment of the present invention. The electronic device includes a memory 210, a processor 220, and a communication module 230. The elements of the memory 210, the processor 220, and the communication module 230 are directly or indirectly electrically connected to each other to realize data transmission or interaction. For example, these elements can be electrically connected to each other through one or more communication buses or signal lines.

[0056] Among them, the memory 210 is used to store programs or data. The memory 210 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0057] The processor 220 may be an integrated circuit chip with signal processing capabilities. The processor 220 can be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0058] Among them, the processor 220 is used to read and write the data or programs stored in the memory 210 and execute the corresponding functions. For example, when the processor 220 executes the computer program stored in the memory 210, the human bone rehabilitation training method disclosed in the embodiments of the present invention can be implemented.

[0059] The communication module 230 is used to establish a communication connection between the electronic device and other terminal devices (for example, the server 20) through the network and is used to transmit and receive data through the network.

[0060] It should be understood that Figure 2 The structure shown is only a schematic diagram of the structure of the electronic device, and the electronic device may also include more or fewer components than those shown in Figure 2 or have a different configuration from that shown in Figure 2 . Figure 2 The components shown in can be implemented by hardware, software or a combination thereof.

[0061] An embodiment of the present invention further provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, it can implement the multi-functional system operation optimization method disclosed in each embodiment of the present invention.

[0062] In the prior art, when a user uses an electronic device for bone rehabilitation training, different training actions are displayed on the electronic device. The user selects a training action according to his / her subjective will, and the electronic device plays the training action according to the user's selection, enabling the user to perform corresponding actions following the played training action. However, this method cannot effectively monitor the actual training situation of the user, thus resulting in poor training effects for the user.

[0063] Based on the above problems, in order to effectively monitor the actual training situation of the user, an embodiment of the present invention provides a human bone rehabilitation training method. Please refer to Figure 3 , Figure 3 which is a schematic flowchart of a human bone rehabilitation training method provided by an embodiment of the present invention. The method includes:

[0064] Step S301: According to the video data collected by the acquired camera, identify the coordinates of the human bone points in the video data.

[0065] Optionally, when the first user is performing rehabilitation training, the camera of the first terminal needs to be turned on first. The first terminal can then collect video data through the camera. Based on human recognition technology, the first terminal identifies the coordinates of the human bone points in the video data. Among them, the method of identifying the coordinates of the human bone points in the video data is not limited and can be set according to actual application requirements. Taking the first terminal as a mobile phone as an example, the upper left corner of the mobile phone screen can be defined as the coordinate origin, the right direction can be defined as the horizontal coordinate axis, and the downward direction can be defined as the vertical coordinate axis, so as to identify the coordinates of the human bone points in the video data.

[0066] Among them, the human bone points include but are not limited to: head, left shoulder, right shoulder, left elbow, right elbow, left wrist, right wrist, left hip, right hip, left knee, right knee, left ankle, right ankle, left heel, right heel, left toe, right toe. The human bone points for which coordinates need to be identified can be set according to actual needs and are not limited in the embodiments of the present invention.

[0067] In the embodiments of the present invention, the human recognition technology can be the human bone point SDK (Software Development Kit) technology. This technology can collect video data through the camera, detect the human body in the video in real time, accurately locate the core human bone points of the main parts of the human body, and accurately identify the coordinates of the human bone points in the video data.

[0068] It should be noted that in practical applications, the above-mentioned human body recognition technology can also be OpenCV human body recognition technology, AI (Artificial Intelligence) human body recognition technology, etc. The choice of human body recognition technology can be set according to actual needs and is not limited in the embodiments of the present invention.

[0069] Step S302, when it is determined that the first user corresponding to the first terminal meets the training conditions according to the coordinates of the human body bone points, determine the coordinates of the target bone points among the human body bone points in the video data and the coordinates of the reference bone points adjacent to the target bone points according to the training action currently played by the first terminal.

[0070] Optionally, the first terminal obtains the human body part to be trained according to the currently played training action. In order to achieve the purpose of training this human body part, determine the human body bone points that need to move. These human body bone points that need to move are the target bone points, and the adjacent human body bone points that support the movement of the target bone points are the reference bone points. The adjacent human body bone points that are on the same straight line as the reference bone points are also reference bone points. Among them, the adjacent human body bone points that are on the same straight line as the reference bone points can be one or more, and are not limited in the embodiments of the present invention.

[0071] For example, taking the training of the left elbow as an example, the first terminal obtains the human body part to be trained as the left elbow according to the currently played training action. In order to achieve the purpose of training the left elbow, determine that the human body bone point that needs to move is the left wrist. The left wrist is the target bone point, and the left elbow that supports the movement of the left wrist is the reference bone point. The left shoulder that is on the same straight line as the left elbow is also the reference bone point.

[0072] It should be noted that the human body part to be trained can be a human body bone point, or the human body part between the human body bone points that need to move and the control of the human body bone points that need to move. The first user fills in the health report according to the actual situation of himself / herself so that the second user can set it, and it is not limited in the embodiments of the present invention.

[0073] Step S303, calculate the real-time action angle of the first user during the training according to the coordinates of the target bone points and the coordinates of the reference bone points.

[0074] Optionally, use the coordinates of the reference bone points that support the movement of the target bone points as vertices, use the connection line between the coordinates of the reference bone points as vertices and the target bone points as the side lines, and use the connection line between the coordinates of the reference bone points as vertices and the coordinates of the remaining other reference bone points as the side lines to calculate the real-time action angle during the training process of the first user. It can be understood that the first user needs to continuously move according to the training actions currently played by the first terminal during the training process, and the action angle during the training process of the first user changes in real time.

[0075] In the embodiment of the present invention, taking the training of the left elbow as an example, according to the training actions currently played by the first terminal, the human body part to be trained is the left elbow. To achieve the purpose of training the left elbow, the human bone point that needs to move is determined to be the left wrist, and the left wrist is the target bone point, while the left elbow that supports the movement of the left wrist is the reference bone point, and the left shoulder on the same straight line as the left elbow is another reference bone point. Taking the coordinates of the left elbow as the vertex, and taking the connection line between the coordinates of the left elbow and the left wrist, and the connection line between the coordinates of the left elbow and the left shoulder as the side lines, calculate the real-time action angle of the first user during the training of the left elbow.

[0076] For ease of understanding, for the processes of steps S302 and S303 above, continue to take the training of the left elbow as an example, please refer to Figure 4 , Figure 4 which is a schematic diagram provided by the embodiment of the present invention for calculating the real-time action angle of the first user during the training process.

[0077] Among them, the coordinate X(a, b) represents the coordinates of the left wrist; the coordinate Y(c, d) represents the coordinates of the left elbow, and the coordinate Z(e, f) represents the coordinates of the left shoulder; A represents the real-time action angle of the first user during the training of the left elbow.

[0078] Determine the straight line XY according to the coordinate X(a, b) and the coordinate Y(a, b), and calculate the first included angle α between the straight line XY and the X-axis; determine the coordinate YZ according to the coordinate Y(c, d) and the coordinate Z(e, f), and the second included angle β between the straight line YZ and the X-axis; the real-time action angle of the first user during the training of the left elbow can be calculated according to the cosine formula. It can be expressed by the following formula:

[0079] tanA = (tanα - tanβ) / (1 + tanα * tanβ);

[0080] A = α - β;

[0081] Among them, α represents the first included angle, that is, the first included angle between the straight line XY and the X-axis; β represents the second included angle, that is, the second included angle β between the straight line YZ and the X-axis; A represents the real-time action angle of the first user during the training of the left elbow.

[0082] It should be noted that the above calculation process is only for illustrative purposes, and the specific calculation method can be set according to actual needs, which is not limited in the embodiments of the present invention.

[0083] Step S304: Determine whether the first user has completed the training action according to the real-time action angle during the first user's training process.

[0084] Optionally, the first terminal determines whether the first user has completed the training action according to whether the real-time action angle during the first user's training process meets the condition for completing the training action. When the real-time action angle meets the condition for completing the training action, it is determined that the first user has completed the training action; when the real-time action angle does not meet the condition for completing the training action, it is determined that the first user has not completed the training action, and the first user is prompted to continue to complete the training action.

[0085] The human body bone rehabilitation training method provided by the embodiments of the present invention acquires video data collected by a camera, identifies the coordinates of human body bone points in the video data, and when it is determined that the first user corresponding to the first terminal meets the training conditions according to the coordinates of the human body bone points, determines the coordinates of the target bone points and the coordinates of the reference bone points adjacent to the target bone points among the human body bone points in the video data according to the training action currently played by the first terminal, and calculates the real-time action angle during the first user's training process according to the coordinates of the target bone points and the coordinates of the reference bone points, and then determines whether the first user has completed the training action according to the real-time action angle during the first user's training process. By collecting video data through an electronic device and obtaining the coordinates of human body bone points according to the video data, calculating the real-time action angle during the user's training process, and then determining whether the user has completed the training action, it realizes effective monitoring of the user's actual training situation during the user's training process, helps the user effectively perform bone rehabilitation training, and thus improves the training effect.

[0086] To accurately calculate the real-time action angle during the first user's training process, please refer to Figure 5 , Figure 5 is another flowchart of the human body bone rehabilitation training method provided by the embodiments of the present invention. The method further includes:

[0087] Step S305: Determine whether the current body direction of the first user matches the preset body direction, whether the body of the first user is located in the specified area on the screen of the first terminal, and whether the current body posture of the first user matches the preset posture; the preset body direction, the specified area, and the preset posture are all associated with the training action.

[0088] Optionally, when the first user determines the training action to be played but the first terminal has not played the training action yet, the first terminal sets a preset body direction, a specified area, and a preset posture corresponding to the training action to be played. It can be understood that the first terminal sets the corresponding preset body direction, specified area, and preset posture according to different training actions to be played, that is to say, the preset body direction, the specified area, and the preset posture are all associated with the training action.

[0089] Optionally, before the first user starts training, the first terminal instructs the first user to face a certain direction with the body so as to match the preset body direction, and the preset body direction is consistent with the body direction in the training action. It can be understood that the current body direction of the first user is calculated through the coordinates of the human body bone points, and by comparing the current body direction of the first user with the preset body direction, it is determined whether the current body direction of the first user matches the preset body direction. For example, when the first user is required to face the screen, the abscissa of the left shoulder in the human body bone points is smaller than the abscissa of the right shoulder, indicating that the first user is facing the screen and matches the preset body direction; otherwise, the first user is facing away from the screen and does not match the preset body direction.

[0090] It should be noted that in actual applications, when the body direction does not match the preset body direction before training, the first terminal can also prompt the first user to adjust the current body direction by means of voice prompts.

[0091] Optionally, before the first user starts training, the first terminal instructs the first user that when the camera collects video data, the body of the first user in the video data should be in the specified area on the screen of the first terminal. For example, taking Figure 4 as an example, when the training action requires the first user to face the left side to train the left elbow, in order to collect the video data of the first user, the right area on the screen of the first terminal is specified as the specified area. It can be understood that the specified area can include a coordinate range, and according to whether the coordinates of the human body bone points are within the coordinate range of the specified area, it can be determined whether the body of the first user is located in the specified area on the screen of the first terminal.

[0092] It should be noted that in actual applications, when the body of the first user is not located in the specified area on the screen of the first terminal before training, the first terminal can also prompt the first user to adjust the body by means of voice prompts.

[0093] Optionally, a preparation posture corresponds to the training action, and this preparation posture is the preset posture. Among them, the conditions for determining whether the current body posture of the first user matches the preset posture are not restricted and can be set according to actual needs. For example, the first relative position relationship can be determined according to the coordinates of the human body bone points corresponding to the preset posture, and the second relative position relationship can be determined according to the coordinates of the human body bone points corresponding to the current body posture of the first user. When the first relative position relationship and the second relative position relationship are corresponding or similar, it can be determined that the current body posture of the first user matches the preset posture. The first relative position relationship and the second relative position relationship represent the distance between the coordinates of the human body bone points.

[0094] It should be noted that in practical applications, before training, when the current body posture of the first user does not match the preset posture, the first terminal can also prompt the first user to adjust the current body posture by means of voice prompts.

[0095] Step S306, when the current body direction of the first user matches the preset body direction, the body of the first user is located in the specified area, and the current body posture of the first user matches the preset posture, it is determined that the first user corresponding to the first terminal meets the training conditions.

[0096] Optionally, when it is determined that the first user corresponding to the first terminal meets the training conditions, the first terminal can play the training action, so that the first user can perform rehabilitation training according to the training action currently played by the first terminal.

[0097] In order to determine that the first user has completed the training action, on the basis of Figure 3 a possible implementation manner is given to determine that the first user has completed the training action, such as Figure 6 , Figure 6 This is Figure 3 a schematic flowchart of a sub-step of step S304 provided by the embodiment of the present invention. The above step S304 includes:

[0098] Step S3041, obtain the real-time angle interval according to the real-time action angle during the training of the first user.

[0099] Optionally, the first user needs to continuously move according to the training action currently played by the first terminal during the training process. The action angle during the training process of the first user changes in real time. There will be corresponding maximum and minimum values for the real-time action angle during the training process of the first user. The real-time angle interval is determined according to the maximum and minimum values. Since the maximum and minimum values of the real-time action angle that the first user can reach may change in real time during the training process, the obtained real-time angle interval will also be updated accordingly.

[0100] Step S3042: Determine the effective angle range based on the real-time angle range and the preset angle range.

[0101] Optionally, the training action specifies the specified range that the real-time action angle during the training of the first user needs to reach. Different training actions correspond to different preset angle ranges. For example, the real-time angle range during the training of the first user is (80° - 110°), and the preset angle range is (90° - 120°). At this time, the effective angle range is (90° - 110°).

[0102] It should be noted that since the real-time angle range is updated in real time, the effective angle range will also be updated accordingly.

[0103] Step S3043: Obtain the effective angle based on the effective angle range.

[0104] In the embodiment of the present invention, the selection of the effective angle is not restricted and can be set according to actual application requirements. Optionally, continuing with the example in step S3042 above, the effective angle range is (90° - 110°), and the middle number 100° of this effective angle range can be selected as the effective angle.

[0105] It should be noted that since the effective angle range is updated in real time, the effective angle will also be updated accordingly.

[0106] Step S3044: When the number of times the real-time action angle during the training of the first user matches the effective angle meets the preset number of times, it is determined that the first user has completed the training action; the preset angle range and the preset number of times are both associated with the training action.

[0107] Optionally, when the first user determines the training action to be played, but the first terminal has not played the training action yet, the first terminal obtains the preset angle range and the preset number of times corresponding to the training action to be played according to the training action to be played. It can be understood that the first terminal will obtain the corresponding preset angle range and the preset number of times according to different training actions to be played, that is to say, the preset angle range and the preset number of times are both associated with the training action.

[0108] Optionally, during the training process, the first user needs to repeat and complete the training action multiple times, and the training action corresponds to a preset number of times. Among them, the preset number of times is not restricted, and the first terminal can obtain it according to the training action. For example, it can be 10 times. When the first user completes 10 training actions, it is determined that the first user has completed the training action. It can be understood that different training actions correspond to different preset numbers of times, that is, the preset number of times is associated with the training action.

[0109] Optionally, when the first terminal determines that the real-time action angle during the first user's training process is equal to the effective angle, it determines that the first user has completed a training action. Alternatively, when the first terminal determines that the real-time action angle during the first user's training process is within the preset range of the effective angle, it determines that the first user has completed a training action. Here, the selection of the preset range of the effective angle is not restricted and can be set according to actual application requirements. For example, the preset range can be plus or minus 5° of the effective angle. Alternatively, the movement trajectory during the first user's training process is calculated based on the coordinates of the target bone point and the coordinates of the reference bone point. The first straight line is determined based on the coordinates of the reference bone point and the effective angle. Through the movement trajectory, the second straight line is determined based on the coordinates of the target bone point and the coordinates of the reference bone point. When the second straight line passes through the first straight line back and forth once through the movement trajectory, it is further determined that the first user has completed a training action. The movement trajectory can also be displayed on the screen of the first terminal so that the first user can intuitively obtain the situation of the training process.

[0110] To obtain the training action, please refer to Figure 7 , Figure 7 is another flowchart of the human bone rehabilitation training method provided by the embodiments of the present invention. The method further includes:

[0111] Step S307, receiving the rehabilitation training plan sent by the server; the rehabilitation training plan is generated by the server according to the exercise prescription uploaded by the second terminal; the exercise prescription is set by the second user corresponding to the second terminal according to the health report of the first user and uploaded to the second terminal; the rehabilitation training plan includes training actions.

[0112] Optionally, when the first user performs rehabilitation training for the first time, the first terminal will prompt the first user to set a health report according to their own situation. The first terminal uploads the health report to the server, and the second terminal obtains the health report through the server, enabling the second user to give a corresponding exercise prescription according to the health report, such as the training cycle, training actions, the number of times to complete the training actions, etc. The second terminal uploads the exercise prescription to the server, and the server generates a corresponding rehabilitation training plan according to the exercise prescription. The first user can receive the rehabilitation training plan through the first terminal and perform rehabilitation training through the first terminal. Here, the rehabilitation training plan includes the training actions that the first terminal needs to play, the preset number of times, etc.

[0113] Optionally, to determine whether the first user has completed the rehabilitation training plan and update the rehabilitation training plan, the method further includes:

[0114] Step S308, when the number of training days of the first user meets the preset number of days and the training actions corresponding to each day in the preset number of days are completed, it is determined that the first user has completed the rehabilitation training plan.

[0115] Optionally, the rehabilitation training plan further includes a preset number of days. The first user completes the training actions that need to be completed every day according to the rehabilitation training plan, and the number of training days needs to meet the preset number of days. Then, the first user completes the rehabilitation training plan. Herein, the preset number of days is not restricted and can be set by the second user according to the health report of the first user. For example, the preset number of days can be set to 7 days. When the number of training days of the first user meets 7 days and the training actions corresponding to each day in the preset number of days are completed, the first terminal determines that the first user has completed the rehabilitation training plan. It can be understood that the training actions corresponding to the same day can be one or multiple, and the training actions corresponding to different days can be the same or different, which are not limited in the embodiments of the present invention.

[0116] Step S309: Obtain the training evaluation data input by the first user after completing the rehabilitation training plan.

[0117] Optionally, after the first user completes the rehabilitation training plan, the first terminal will prompt the first user to complete the evaluation report, and the first user inputs the training evaluation data according to the evaluation report.

[0118] Step S310: Send the training evaluation data to the server so that the server generates a training report according to the training evaluation data, and sends the training report to the second terminal. Furthermore, it is convenient for the second user to update the exercise prescription according to the training report, and send the updated exercise prescription to the server. Then, the server updates the rehabilitation training plan according to the updated exercise prescription.

[0119] Optionally, after receiving the training evaluation data sent by the first terminal, the server generates a training report. The second user obtains the training report through the second terminal, updates the exercise prescription according to the training report and the above-mentioned health report of the first user, and sends the updated exercise prescription to the server through the second terminal, so that the server updates the rehabilitation training plan according to the updated exercise prescription and pushes the updated rehabilitation training plan to the first terminal.

[0120] It can be understood that the updated rehabilitation training plan received by the first terminal will be used as the rehabilitation training plan for the next stage of the first user. That is, the first user can continue to train according to the updated rehabilitation training plan. When the first terminal does not receive the updated rehabilitation training plan, that is, when the server does not update the rehabilitation training plan, it indicates that the first user has completed the rehabilitation training, that is, the first user has recovered and no longer needs training.

[0121] Optionally, during the process of the first user performing rehabilitation training, according to his own situation, the first user can stop the rehabilitation training at any time. To avoid the trouble caused by the first user's manual operation and improve the user experience during the training process, the method further includes:

[0122] Step S311, when receiving the stop training voice command of the first user, control the camera to stop collecting video data and stop the currently played training action.

[0123] Optionally, during the rehabilitation training of the first user, the first terminal will detect the voice command of the first user in real time. When the first user needs to stop training and says a voice like "stop training", the first terminal can receive the stop training voice command of the first user, control the camera to stop collecting video data, and stop the currently played training action.

[0124] Step S312, broadcast a voice prompt message; the voice prompt message is used to ask the first user about the reason for stopping training.

[0125] Optionally, the first terminal will ask the first user about the reason for stopping training by broadcasting a voice.

[0126] Step S313, when receiving the reason voice command issued by the first user based on the voice prompt message, convert the reason voice command into a text command and report the text command to the server communicatively connected to the first terminal.

[0127] Optionally, after the first terminal reports the text command to the server communicatively connected to the first terminal, the second user can obtain the text command through the second terminal and judge whether to update the exercise prescription according to the text command.

[0128] Among them, the first terminal can also prompt the first user about the training action to be completed in real time during the training of the first user.

[0129] It should be noted that in practical applications, the first terminal will, according to the methods in steps S305 and S306, judge in real time whether the body of the first user is in the specified area on the screen of the first terminal during the training of the first user. When the body of the first user is not in the specified area on the screen of the first terminal during the training of the first user, the first terminal can also prompt the first user to adjust the body by means of voice prompts.

[0130] It should be noted that in practical applications, the real-time action angle, number of training times, etc. of the first user during the training can also be obtained through sensors, where the sensors include: angular velocity sensors, acceleration sensors, angular acceleration sensors, etc.

[0131] Please refer to Figure 8 , which is a functional module diagram of a human bone rehabilitation training device provided by an embodiment of the present invention. The human bone rehabilitation training device includes: a coordinate acquisition module 401, an angle calculation module 402, and a determination module 403.

[0132] Optionally, the above modules can be stored in the form of software or firmware. Figure 2 The memory 210 shown in the figure may be fixed in the operating system (OS) of the electronic device and may be Figure 2 Meanwhile, the data and program codes required for executing the above modules may be stored in the memory 210.

[0133] The coordinate acquisition module 401 is used to identify the coordinates of human skeleton points in the video data according to the video data collected by the camera.

[0134] It can be understood that the coordinate acquisition module 401 can execute the above step S301.

[0135] The angle calculation module 402 is used to determine the coordinates of the target bone point in the human bone points in the video data and the coordinates of the reference bone points adjacent to the target bone point according to the training action currently played by the first terminal, when it is determined that the first user corresponding to the first terminal meets the training conditions according to the coordinates of the human bone points; and calculate the real-time action angle of the first user during the training process according to the coordinates of the target bone point and the coordinates of the reference bone point.

[0136] It can be understood that the angle calculation module 402 can execute the above steps S302 and S303.

[0137] The determination module 403 is used to determine whether the first user has completed the training action according to the real-time action angle of the first user during the training process.

[0138] It can be understood that the determination module 403 can execute the above step S304.

[0139] Optional, see Figure 9 , is another functional module diagram of the human skeleton rehabilitation training device provided by the embodiment of the present invention. The human skeleton rehabilitation training device also includes: a condition confirmation module 404, a transceiver module 405 and a voice module 406.

[0140] The condition confirmation module 404 is used to determine whether the current body direction of the first user matches the preset body direction, whether the body of the first user is located in a designated area on the screen of the first terminal, and whether the current body posture of the first user matches the preset posture based on the coordinates of the human skeleton points; the preset body direction, the designated area, and the preset posture are all associated with training actions; when the current body direction of the first user matches the preset body direction, the body of the first user is located in the designated area, and the current body posture of the first user matches the preset posture, it is determined that the first user corresponding to the first terminal meets the training conditions.

[0141] It can be understood that the condition confirmation module 404 can execute the above steps S305 and S306.

[0142] Optionally, the determination module 403 is configured to obtain a real-time angle range according to the real-time action angle during the first user's training process; determine a valid angle range according to the real-time angle range and a preset angle range; obtain a valid angle according to the valid angle range; and determine that the first user has completed the training action when the number of times the real-time action angle during the first user's training process matches the valid angle meets a preset number of times; the preset angle range and the preset number of times are both associated with the training action.

[0143] It can be understood that the determination module 403 can also execute the above steps S3041, S3042, S3043, and S3044.

[0144] The transceiver module 405 is configured to receive a rehabilitation training plan sent by the server; the rehabilitation training plan is generated by the server according to the exercise prescription uploaded by the second terminal; the exercise prescription is set by the second user corresponding to the second terminal according to the health report of the first user and uploaded to the second terminal; the rehabilitation training plan includes training actions; it is determined that the first user has completed the rehabilitation training plan when the number of training days of the first user meets the preset number of days and the training actions corresponding to each day in the preset number of days are completed; obtain the training evaluation data input by the first user after completing the rehabilitation training plan; and send the training evaluation data to the server so that the server can generate a training report according to the training evaluation data and send the training report to the second terminal, thereby facilitating the second user to update the exercise prescription according to the training report and send the updated exercise prescription to the server, and the server updates the rehabilitation training plan according to the updated exercise prescription.

[0145] It can be understood that the transceiver module 405 can execute the above steps S307, S308, S309, and S310.

[0146] The voice module 406 is configured to, when receiving a stop training voice command from the first user, control the camera to stop collecting video data and stop the currently played training action; broadcast a voice prompt message; the voice prompt message is used to ask the first user about the reason for stopping training; and when receiving a reason voice command from the first user based on the voice prompt message, convert the reason voice command into a text command and report the text command to the server communicatively connected to the first terminal.

[0147] It can be understood that the voice module 406 can execute the above steps S311, S312, and S313.

[0148] The human bone rehabilitation training device provided by the embodiments of the present invention obtains the video data collected by a camera through a coordinate acquisition module, identifies the coordinates of human bone points in the video data, and when the angle calculation module determines that the first user corresponding to the first terminal meets the training conditions according to the coordinates of the human bone points, determines the coordinates of the target bone points among the human bone points in the video data and the coordinates of the reference bone points adjacent to the target bone points according to the training actions currently played on the first terminal, and calculates the real-time action angle during the training process of the first user according to the coordinates of the target bone points and the coordinates of the reference bone points. Then, the determination module determines whether the first user has completed the training action according to the real-time action angle during the training process of the first user. By collecting video data through an electronic device and obtaining the coordinates of human bone points according to the video data, the real-time action angle during the user's training process is calculated, and then whether the user has completed the training action is determined, effectively monitoring the actual training situation of the user during the user's training process, which helps the user to effectively perform bone rehabilitation training, thereby improving the training effect.

[0149] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0150] In addition, the functional modules in each embodiment of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0151] When the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of the technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0152] The foregoing are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for rehabilitation training of human bones, characterized in that, Applied to a first terminal, the first terminal including a camera, the method comprising: Identifying coordinates of human body bone points in the video data according to the acquired video data collected by the camera; Determining whether a current body direction of a first user matches a preset body direction, whether the body of the first user is located in a specified area on the screen of the first terminal, and whether a current body posture of the first user matches a preset posture according to the coordinates of the human body bone points; the preset body direction, the specified area, and the preset posture are all associated with a currently played training action; Determining that the first user corresponding to the first terminal meets the training conditions when the current body direction of the first user matches the preset body direction, the body of the first user is located in the specified area, and the current body posture of the first user matches the preset posture; When it is determined according to the coordinates of the human body bone points that the first user corresponding to the first terminal meets the training conditions, determining coordinates of target bone points among the human body bone points in the video data and coordinates of reference bone points adjacent to the target bone points according to the training action currently played by the first terminal; the target bone points represent human body bone points that need to move corresponding to the currently played training action, and the reference bone points include a first adjacent human body bone point that supports the operation of the target bone point and a second adjacent human body bone point that is on the same straight line as the first adjacent human body bone point; Calculating a real-time action angle during the training process of the first user according to the coordinates of the target bone points and the coordinates of the reference bone points; the real-time action angle represents an included angle between a line connecting the target bone point and the first adjacent human body bone point and a line connecting the first adjacent human body bone point and the second adjacent human body bone point; Determining whether the first user completes the training action according to the real-time action angle during the training process of the first user.

2. The method according to claim 1, characterized in that, The determining whether the first user completes the training action according to the real-time action angle during the training process of the first user includes: Obtaining a real-time angle interval according to the real-time action angle during the training process of the first user; Determining an effective angle interval according to the real-time angle interval and a preset angle interval; Obtaining an effective angle according to the effective angle interval; Determining that the first user completes the training action when the number of times the real-time action angle during the training process of the first user matches the effective angle meets a preset number of times; the preset angle interval and the preset number of times are both associated with the training action.

3. The method according to claim 1, wherein The first terminal is communicatively connected to a server, and the server is also communicatively connected to a second terminal. The method further includes: Receiving a rehabilitation training plan sent by the server; the rehabilitation training plan is generated by the server according to a motion prescription uploaded by the second terminal; the motion prescription is set by a second user corresponding to the second terminal according to a health report of the first user and uploaded to the second terminal; the rehabilitation training plan includes the training action.

4. The method according to claim 3, characterized in that, The rehabilitation training plan further includes a preset number of days, and the method further includes: When the number of training days of the first user meets the preset number of days and the training actions corresponding to each day in the preset number of days are completed, it is determined that the first user has completed the rehabilitation training plan.

5. The method according to claim 3, characterized in that The method further includes: Obtaining the training evaluation data input by the first user after completing the rehabilitation training plan; Sending the training evaluation data to the server, so that the server generates a training report based on the training evaluation data and sends the training report to the second terminal, thereby facilitating the second user to update the exercise prescription according to the training report and sending the updated exercise prescription to the server, and the server updates the rehabilitation training plan according to the updated exercise prescription.

6. The method according to claim 1, characterized in that The method further includes: When receiving the stop training voice command of the first user, controlling the camera to stop collecting the video data and stopping the currently played training action; Playing a voice prompt message; the voice prompt message is used to ask the reason for the first user to stop training; When receiving the reason voice command issued by the first user based on the voice prompt message, converting the reason voice command into a text command and reporting the text command to the server communicatively connected to the first terminal.

7. A human bone rehabilitation training device, characterized in that, Applied to a first terminal, the first terminal includes a camera, and the device includes: A coordinate acquisition module, configured to identify the coordinates of the human body skeleton points in the video data according to the acquired video data collected by the camera; A condition confirmation module, configured to determine whether the current body direction of the first user matches the preset body direction, whether the body of the first user is located in a specified area on the screen of the first terminal, and whether the current body posture of the first user matches the preset posture according to the coordinates of the human body skeleton points; the preset body direction, the specified area, and the preset posture are all associated with the currently played training action; when the current body direction of the first user matches the preset body direction, the body of the first user is located in the specified area, and the current body posture of the first user matches the preset posture, it is determined that the first user corresponding to the first terminal meets the training conditions; An angle calculation module, configured to, when it is determined that the first user corresponding to the first terminal meets the training conditions according to the coordinates of the human body bone points, determine the coordinates of the target bone points among the human body bone points in the video data and the coordinates of the reference bone points adjacent to the target bone points according to the training action currently played by the first terminal; calculate the real-time action angle during the training process of the first user according to the coordinates of the target bone points and the coordinates of the reference bone points; the target bone points represent the human body bone points that need to move corresponding to the currently played training action, and the reference bone points include the first adjacent human body bone points that support the operation of the target bone points and the second adjacent human body bone points that are on the same straight line as the first adjacent human body bone points; the real-time action angle represents the included angle between the line connecting the target bone points and the first adjacent human body bone points and the line connecting the first adjacent human body bone points and the second adjacent human body bone points. A determination module, configured to determine whether the first user has completed the training action according to the real-time action angle during the training process of the first user.

8. An electronic device, characterized in that, It includes a processor and a memory, the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1-6 is implemented.

9. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the method according to any one of claims 1-6 is implemented.

Images