Training program generation method based on manipulator and related device

Abstract

The present application provides a method and related device for generating a training program based on a manipulator, the method comprising: obtaining the historical training records and injured parts of a target user, the historical training records including the trained actions of the target user and the training scores corresponding to the trained actions; predicting the rehabilitation degree of the target user according to the trained actions and the training scores corresponding to the trained actions; determining at least one training action according to the rehabilitation degree and the injured part; determining the maximum joint angle of the manipulator corresponding to each training action in at least one training action according to the rehabilitation degree and the historical training records; generating a target training program according to at least one training action, the maximum joint angle and the historical training records; sending the target training program to an electronic device, the target training program is used to indicate a motor control instruction, and the motor control instruction is used to control the movement of the hand joints of the manipulator. The intelligence and user experience of generating a training program for rehabilitation training can be improved.

Description

Technical Field

[0001] The present application belongs to the field of new generation information technology, and specifically relates to a training program generation method based on a robot and related devices. Background Art

[0002] Currently, when arranging rehabilitation training for users, the number of training times for each training action is fixed, and each training action cannot be appropriately adjusted based on the user's injury during training. This makes it impossible to conduct targeted rehabilitation training based on the user's actual injury and rehabilitation situation. Moreover, each training session simply repeats the last training action, which makes the user's rehabilitation training process boring, causing the user to have a negative attitude towards training, resulting in poor training results. Summary of the invention

[0003] The embodiments of the present application provide a method and related devices for generating a training program based on a robot, so as to improve the intelligence and rationality of generating a training program for rehabilitation training, and to improve the rehabilitation training effect and user experience of the user.

[0004] In a first aspect, an embodiment of the present application provides a method for generating a training program based on a manipulator, which is applied to a server of a rehabilitation training system, wherein the rehabilitation training system includes the server, an electronic device, and a manipulator, wherein the server is communicatively connected to the electronic device, and the electronic device is communicatively connected to the manipulator, and the method includes:

[0005] Acquire historical training records and injured parts of the target user, wherein the historical training records include trained movements of the target user and training scores corresponding to the trained movements;

[0006] predicting the degree of recovery of the target user according to the trained actions and the training scores corresponding to the trained actions;

[0007] determining at least one training action according to the rehabilitation degree and the injured part;

[0008] Determine, according to the rehabilitation degree and the historical training record, the maximum angle of the joint of the manipulator corresponding to each training action in the at least one training action;

[0009] Generate a target training program according to the at least one training action, the maximum joint angle and the historical training record;

[0010] The target training scheme is sent to the electronic device, where the target training scheme is used to indicate a motor control instruction, and the motor control instruction is used to control the movement of the hand joints of the manipulator.

[0011] In a second aspect, an embodiment of the present application provides a training program generation device based on a manipulator, which is applied to a server of a rehabilitation training system, wherein the rehabilitation training system includes the server, an electronic device, and a manipulator, wherein the server is communicatively connected to the electronic device, and the electronic device is communicatively connected to the manipulator, and the device includes:

[0012] An acquisition unit, configured to acquire a historical training record and an injured part of a target user, wherein the historical training record includes a trained action of the target user and a training score corresponding to the trained action;

[0013] a prediction unit, configured to predict the degree of recovery of the target user according to the trained actions and the training scores corresponding to the trained actions;

[0014] A first determining unit, configured to determine at least one training action according to the rehabilitation degree and the injured part;

[0015] A second determination unit, configured to determine a maximum joint angle of the manipulator corresponding to each training action in the at least one training action according to the rehabilitation degree and the historical training record;

[0016] a generating unit, configured to generate a target training program according to the at least one training action, the maximum joint angle and the historical training record;

[0017] A sending unit is used to send the target training scheme to the electronic device, where the target training scheme is used to indicate motor control instructions, and the motor control instructions are used to control the movement of the hand joints of the manipulator.

[0018] In a third aspect, an embodiment of the present application provides a server, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program or instructions stored thereon, wherein the computer program or instructions are executed by a processor to implement the steps in the first aspect of the embodiment of the present application.

[0020] It can be seen that in this embodiment, the server first obtains the historical training records and injured parts of the target user, the historical training records including the trained actions of the target user and the training scores corresponding to the trained actions, and then predicts the recovery degree of the target user based on the trained actions and the training scores corresponding to the trained actions, and then determines at least one training action based on the recovery degree and the injured part, and then determines the maximum joint angle of the manipulator corresponding to each training action in the at least one training action based on the recovery degree and the historical training records, and then generates a target training plan based on the at least one training action, the maximum joint angle and the historical training records, and finally sends the target training plan to the electronic device, and the target training plan is used to indicate motor control instructions, and the motor control instructions are used to control the movement of the hand joints of the manipulator.

[0021] In this way, the training action of the current training and the maximum angle of the manipulator joint corresponding to each training action can be determined based on the user's actual rehabilitation situation, so as to generate a training plan for the user's actual situation and improve the intelligence of the server in generating plans for rehabilitation training. At the same time, using the manipulator to move the hand joints based on the training plan to drive the user to perform passive training can also improve the training effect and convenience of the user's rehabilitation training. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 It is a schematic diagram of the composition of a rehabilitation training system provided in an embodiment of the present application;

[0024] Figure 2 It is a structural diagram of a server provided in an embodiment of the present application;

[0025] Figure 3 It is a structural schematic diagram of a manipulator provided in an embodiment of the present application;

[0026] Figure 4 It is a flowchart of a method for generating a training program based on a manipulator provided in an embodiment of the present application;

[0027] Figure 5 is a schematic diagram of a first training interface provided in an embodiment of the present application;

[0028] Figure 6is a schematic diagram of a second training interface provided in an embodiment of the present application;

[0029] Figure 7 is a schematic diagram of a third training interface provided in an embodiment of the present application;

[0030] Figure 8 It is a block diagram of the functional units of a training program generation device based on a manipulator provided in an embodiment of the present application;

[0031] Fig. 9 This is a block diagram of the functional units of another robot-based training program generation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0033] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0034] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0035] Currently, when specifying a rehabilitation training plan for a user, only a fixed training plan is formulated, and a targeted training plan cannot be generated based on the user's actual rehabilitation situation. Moreover, when the user is training, each training movement cannot be appropriately adjusted based on the user's injury situation.

[0036] In view of the above problems, an embodiment of the present application provides a method for generating a training program based on a robot and a related device. The embodiment of the present application is described in detail below in conjunction with the accompanying drawings.

[0037] See also Figure 1 , Figure 1 Schematic diagram of a rehabilitation training system provided in an embodiment of the present application. Figure 1 As shown, the rehabilitation training system 10 includes a server 101, an electronic device 102 and a manipulator 103. The server 101 is connected to the electronic device 102 in communication, and the electronic device 102 is connected to the manipulator 103 in communication. In particular, the electronic device 102 can be connected to the manipulator 103 in communication via Bluetooth or Wi-Fi, or the electronic device 102 can also be connected to the manipulator by wire. The server 101 is used to formulate a training plan for the target user's current training, and send the training plan to the electronic device 102. The electronic device 102 generates a motor control instruction based on the training plan, and then sends the motor control instruction to the manipulator 103, so that the manipulator 103 moves based on the motor control instruction and drives the user's hand to perform passive training.

[0038] See also Figure 2 , Figure 2 It is a structural diagram of a server provided in an embodiment of the present application. The server 101 includes a processor 120, a memory 130, a communication interface 140 and one or more programs 131, wherein the one or more programs 131 are stored in the above-mentioned memory 130 and are configured to be executed by the above-mentioned processor 120, and the one or more programs 131 include instructions for executing any step in the following method embodiment. In a specific implementation, the processor 120 is used to execute any step executed by the server in the following method embodiment, and when performing data transmission such as sending, the communication interface 140 can be selectively called to complete the corresponding operation. It should be noted that the electronic device 102 has the same structure as the server 101, and may also include a processor 120, a memory 130, a communication interface 140 and one or more programs 131, which will not be repeated here.

[0039] See also Figure 3 , Figure 3 It is a structural schematic diagram of a manipulator provided in an embodiment of the present application. Figure 3The manipulator 103 shown includes a plurality of joint drivers 1031, a palm fixing belt 1032 and a finger fixing belt 1033. Each finger of the manipulator 103 corresponds to at least one joint driver 1031. The joint driver 1031 outputs driving information based on the motor control instruction of the electronic device 102, so that the corresponding finger on the manipulator moves, so that the manipulator can perform training movements. When the user uses the manipulator for rehabilitation training, the injured hand is bound to the manipulator through the palm fixing belt 1032 and the finger fixing belt 1033, and then the manipulator performs training movements based on the motor control instruction, and drives the user's hand to perform corresponding training movements, thereby realizing the user's passive training.

[0040] See also Figure 4 , Figure 4 The figure is a flow chart of a method for generating a training program based on a manipulator provided in an embodiment of the present application. The method for generating a training program based on a manipulator is applied to the above server and specifically includes the following steps.

[0041] S201, obtaining historical training records and injured parts of a target user.

[0042] The historical training record includes the trained actions of the target user and the training scores corresponding to the trained actions. The historical training record may also include the number of training times for each trained action. The training score corresponding to each trained action may refer to the average score of the trained action during the last training of the trained action. It may also refer to the average score of the trained action during the most recent preset number of trainings. The injured part may indicate whether the user is injured in a finger or a palm, if the injured part is a finger.

[0043] In a specific implementation, when obtaining the training score, the degree of deformation of the corresponding action of the manipulator and the pressure value obtained by the manipulator during each training can be determined. During the training process, if the training action is not suitable for the user, the user may unnaturally produce action resistance or spasm, etc., causing the action of the manipulator to become. At the same time, if the user can complete the training action independently, since the user controls the movement of the hand independently, the pressure obtained from the user's hand when the manipulator performs the training action will become smaller. Therefore, the score of the corresponding training action during each training can be determined based on the degree of deformation of the action and the pressure value.

[0044] S202: predicting the target user's rehabilitation degree according to the trained movements and the training scores corresponding to the trained movements.

[0045] Among them, each training action of the user can be determined based on the user's rehabilitation level, that is, if the user is just undergoing rehabilitation training, the corresponding training action may be the most basic training action. When the user's rehabilitation level increases, the training action of the user during rehabilitation training may be a more difficult or more complex action. Therefore, the user's current rehabilitation level can be determined based on the user's trained actions. At the same time, even at the same rehabilitation level, the actual rehabilitation effect of each user is different, so the actual rehabilitation degree of the user at the rehabilitation level can also be determined based on the user's training score under each trained action. When determining the degree of rehabilitation based on the training score, the trained actions can be divided according to the rehabilitation level corresponding to each trained action, and then the average training score of the trained action with the highest rehabilitation level is calculated, and the degree of rehabilitation is determined based on the average training score. The higher the average training score, the higher the degree of rehabilitation.

[0046] For example Figure 5 As shown, Figure 5 is a schematic diagram of a first training interface provided by an embodiment of the present application. When a user is performing rehabilitation training, the display interface of the electronic device can display example actions corresponding to the current training action and the number of times the user has trained, for example Figure 5 For the current action "ball grasp", the user needs to practice 20 times, and has currently practiced 20 times. At the same time, the current training score will be displayed every time the user completes an action, for example Figure 5 The training score of the user performing the training action for the 20th time is 75 points. When the user completes the training action, the average training score of the training action during the 20 trainings will be displayed again, which is 73 points. At this time, 73 points is the training score corresponding to the trained action "ball grip".

[0047] S203: Determine at least one training action according to the rehabilitation degree and the injured part.

[0048] Among them, each injured part corresponds to a training action set, and the training action set includes multiple training action subsets, and the actions in each training action subset correspond to a rehabilitation level. When determining at least one training action for this rehabilitation training, the initial training action set can be determined based on the rehabilitation level corresponding to the rehabilitation degree, and then at least one training action is obtained from other training action subsets based on the average training score. The lower the average training score, the more other training action subsets there are, and the more training actions are obtained from other training action subsets. The rehabilitation level corresponding to the other training action subsets is lower than the rehabilitation level corresponding to the user's current rehabilitation degree. That is, if the user's average training score is low, when conducting rehabilitation training, not only should the rehabilitation actions corresponding to the current rehabilitation degree be trained, but more basic rehabilitation actions should also be trained. So that the generated training plan can be more in line with the user's actual rehabilitation situation and improve the user's rehabilitation training effect.

[0049] S204: Determine the maximum joint angle of the manipulator corresponding to each training action in the at least one training action according to the rehabilitation degree and the historical training record.

[0050] The robot moves based on the motor control instructions of the electronic device, and the motor control instructions indicate the movement angle of the fingers of the robot. Therefore, the maximum angle of the joints of the robot indicates the amplitude of the training action of the user during rehabilitation training.

[0051] In a possible embodiment, determining the maximum joint angle of the manipulator corresponding to each training action in the at least one training action according to the rehabilitation degree and the historical training records includes: determining the basic joint angle of the manipulator corresponding to each training action according to the rehabilitation degree; determining the average joint angle in the trained action according to the historical training records; determining the historical maximum joint angle corresponding to the training action whose training score is greater than or equal to a preset value according to the training score corresponding to the trained action; determining an angle adjustment coefficient according to the average joint angle and the historical maximum joint angle; adjusting the basic joint angle according to the angle adjustment coefficient to obtain the maximum joint angle of the manipulator corresponding to each training action.

[0052] Among them, the higher the user's rehabilitation degree, the larger the corresponding maximum joint angle of the training action will be, that is, when the user is trained based on the same training action, the greater the range of motion of the hand will be. In actual training, the user can adjust the maximum joint angle of the corresponding training action according to the training situation, so the range of motion of most training actions in the user's actual training process can be determined based on the user's training situation. The training score is greater than or equal to the preset value, which means that the trained action corresponding to the training score is well mastered by the user, so the maximum joint angle of this part of the training action can indicate the upper limit of the joint angle adapted by the current user. The historical maximum joint angle may refer to the average value or maximum value of the maximum joint angle of the training action whose training score is greater than or equal to the preset value. In a specific implementation, when determining the adjustment coefficient, the target difference between the historical maximum joint angle and the average joint angle can be obtained, and the quotient of the target difference and the average joint angle is determined as the angle adjustment coefficient. In particular, the basic joint angle may refer to the minimum joint angle corresponding to the rehabilitation degree.

[0053] It can be seen that in this embodiment, the maximum joint angle of each training action in the current training is comprehensively determined based on the user's rehabilitation level and the maximum joint angle in historical training, which can improve the intelligence of the generation of training plans, and at the same time make the training plans closer to the user's actual situation, making rehabilitation training more reasonable, and improving the rehabilitation training effect and user experience.

[0054] S205: Generate a target training plan according to the at least one training action, the maximum joint angle and the historical training records.

[0055] In a possible embodiment, generating a target training plan based on the at least one training action, the maximum joint angle and the historical training record includes: dividing the at least one training action into a first reference training action and a second reference training action, the first reference training action being the trained action, and the second reference training action being the training action other than the first reference training action in the at least one training action; obtaining a training score for each first reference training action in the first reference training action; obtaining a first target reference training action and a second target reference training action, the first target reference training action being the first reference training action whose training score is greater than or equal to a preset value, and the second target reference training action being the first reference training action whose training score is less than the preset value; generating an initial training action sequence based on the second reference training action and the second target reference training action, the second reference training action being arranged after the second target reference training action in the initial training action sequence; randomly inserting the first reference training action into the initial training action sequence to obtain a target training action sequence; obtaining the basic training times for each training action; generating the target training plan based on the basic training times for each training action, the maximum joint angle of the manipulator corresponding to each training action and the target training action sequence.

[0056] Among them, the target training action sequence is used to indicate the training order of each training action when the user is training. When sorting at least one training action, the training actions that the user has trained but have low training scores are prioritized in the front row, and then the actions that the user has not trained are arranged in sequence, so that the user can first consolidate the training actions during training, so that the rehabilitation training can be carried out step by step, and the rehabilitation training effect is improved. At the same time, the trained actions with high training scores are randomly interspersed in the training action sequence, so that the user can enhance the training confidence based on these training actions during the training process.

[0057] In a possible embodiment, obtaining the basic training times for each training action includes: performing the following operations for each training action: determining the action category to which the current training action belongs, the action category being used to indicate that the current training action belongs to the second reference training action or the first target reference training action or the second target reference training action; when the current training action belongs to the second reference training action, determining the basic training times as the minimum training times corresponding to the second reference training action; when the current training action belongs to the first target reference training action, determining the number of times the current training action has been trained according to the historical training record; determining the basic training times according to the number of times the training has been trained, the more the number of times the basic training has been trained, the more the number of times the basic training has been trained; when the current training action belongs to the second target reference training action, determining the training level of the current training action according to the training score of the current training action in the historical training record; and determining the basic training times according to the training level.

[0058] Among them, when determining at least one training action corresponding to this training, it is also necessary to determine the number of training times for each training action in this training process. The number of training times corresponding to different training actions may be different. That is, if the current training action is one that the user has already trained and the score is high, the number of times the user has trained for the current training action in history can be determined. If the number of training times is lower, it means that the user has mastered the training action based on fewer training times, and the number of training times for the current training action can be less. On the contrary, if the user has trained many times to master the training action, more training based on the training action can be performed during this training, so that the user can consolidate the training action.

[0059] If the current training action is one that the user has trained before but the training score is not high, the user's training level for the current training action can be determined based on the user's actual training score, and then the number of training sessions can be determined based on the training level. Different training levels correspond to different numbers of training sessions.

[0060] It can be seen that in this embodiment, the number of training times for each training action is determined based on the action category to which the training action belongs, so that the training plan is more in line with the actual situation of the user, the intelligence of determining the training plan is enhanced, and the user experience is improved.

[0061] In a possible embodiment, after sending the target training plan to the electronic device, the method further includes: performing the following operations for each training action: obtaining a current training score of the current training action from the electronic device after one training; when the current training score is less than the preset value for a consecutive preset number of times, updating the target training plan so that the target user ends the training for the current training action; when the current training score is greater than or equal to the preset value for a consecutive preset number of times, adjusting the maximum joint angle and training times of the manipulator corresponding to the current training action according to the current training score, and updating the target training plan according to the adjusted maximum joint angle and training times.

[0062] Among them, during the rehabilitation training, the user can update the training plan in real time based on the training results of the user's current action. When training, the user will repeat the training based on the number of training times corresponding to the current training action. In this repeated training process, the training score of each training based on the current training action can be obtained. If the user's multiple training scores are less than the preset value, it is considered that the user is not suitable for training the action at present, and the training action does not need to be trained again in this training, that is, the current training action is deleted from the target training plan. Even if the user's training times for the current training action do not reach the number of training times corresponding to the current training action in the original target training plan, no more training will be performed, but the next training action will be performed. If the user's multiple training scores are greater than or equal to the preset value, it is considered that the user has a certain degree of mastery of the current training action. At this time, the maximum angle of the joint corresponding to the current training action can be appropriately increased so that the current training action matches the user's actual rehabilitation situation. At the same time, the number of training times of the user for the training action can also be appropriately reduced.

[0063] When determining the adjustment value of the number of training times, it can be determined whether the adjusted maximum joint angle matches the current rehabilitation degree of the user. Each rehabilitation degree corresponds to a maximum joint angle fluctuation range. In actual training, the user can increase the maximum joint angle corresponding to the rehabilitation degree, but cannot exceed the fluctuation range. This can protect the user and prevent the user from taking too large a span in the training of a certain action, causing injury. That is, if the adjusted maximum joint angle value is already within the fluctuation range, the maximum joint angle will no longer be adjusted, but the number of training times will be reduced based on the user's fluctuation value. The larger the fluctuation value, the fewer the number of training times. The fluctuation value is the difference between the adjusted maximum joint angle and the maximum joint angle corresponding to the rehabilitation degree. In particular, if the difference, that is, the fluctuation value, reaches the upper limit of the fluctuation range, the training of the current training action is terminated.

[0064] It can be seen that in this embodiment, the training plan is updated in real time based on the user's training situation, so that the training plan is more in line with the user's actual situation, the intelligence of determining the training plan is enhanced, and the user experience is improved.

[0065] In a possible embodiment, adjusting the maximum joint angle of the manipulator corresponding to the current training action according to the current training score includes: determining a current standard score of the current training action according to the current training score, wherein the current standard score is the mode among the current training scores of the current training action; determining a training level of the current training action corresponding to the current standard score; and adjusting the maximum joint angle of the manipulator corresponding to the current training action according to the training level.

[0066] Among them, when the user trains the current training action multiple times, the training score obtained by the user during each training can be obtained, and the mode in the training score can represent the user's actual training situation for the current training action. Each training action corresponds to multiple training levels, and the maximum angles of the manipulator joints of the current action corresponding to different training levels are different. The maximum angle of the joints suitable for the user's current training can be determined based on the training level. That is, the maximum angle of the joints corresponding to all the training actions of the user during this training can be determined based on the user's rehabilitation level and other content, and then based on the user's actual training situation, it is determined to make differentiated adjustments to the maximum angle of the joints corresponding to each training action.

[0067] It can be seen that in this embodiment, based on the user's score for the current training action, the maximum joint angle of the current training action is differentiated and adjusted, so that the training plan is more in line with the user's actual situation, the intelligence of the determination of the training plan is enhanced, and the user experience is improved.

[0068] In a possible embodiment, after sending the target training plan to the electronic device, the method also includes: obtaining an adjustment request from the electronic device, the adjustment request being used to request adjustment of the at least one training action, adjustment of the training order of the at least one training action, and / or adjustment of the number of training times of the at least one training action; obtaining the training goal set by the target user; determining whether the adjustment request matches the training goal based on the historical training record; if so, adjusting the target training plan based on the adjustment request; if not, outputting a prompt message, the prompt message being used to prompt that the adjustment has failed.

[0069] Among them, when the user wears the manipulator for training, the display interface of the electronic device can also synchronously display the current training action, the number of trainings corresponding to the current training action, the maximum angle of the joint, and the maximum example action of the current training action. The user can adjust the training plan on the display interface. If the training plan adjusted by the user matches the user's training goal, the training plan is adjusted based on the user's choice. If it does not match, the user is prompted that the adjustment failed. Before conducting rehabilitation training, the user can first determine whether to set a training goal. The training goal can be used to indicate the user's expected number of rehabilitation days or expected degree of rehabilitation. At this time, when determining the training plan, the server can also generate a training plan based on at least one training action, maximum joint angle, historical training records and training goals.

[0070] When determining whether the adjustment request matches the training target, the adjustment content corresponding to the adjustment request can be determined, and the action category to which the training action belongs can be obtained at the same time. Based on the action category, the adjustable range of the current training action is determined, and the adjustable range includes whether the training action can be deleted and the minimum number of training times of the training action. It is determined whether the adjustment content corresponding to the training action is within the adjustable range. If so, the number of training actions corresponding to the adjustment content is determined. If the number is greater than a preset value, it is considered that all training actions corresponding to the adjustment content do not match. If it is less than the preset value, it is considered that they match. At the same time, if there is an adjustment content that is not within the adjustable range, the training action does not match.

[0071] For example Figure 6 As shown, Figure 6 This is a schematic diagram of a second training interface provided by an embodiment of the present application. For example, if the current training action is a ball grip, the example action corresponding to the current training action will be displayed on the display interface. At the same time, the user can click on the sidebar and display the training plan on the display interface, that is, display the number of training times and the maximum joint angle corresponding to the ball grip, for example Figure 6 The number of training times shown in the figure is 10 times, and the maximum joint angle is 30°. At the same time, the user can also directly switch the current training action on the display interface, as well as change the number of training times and the maximum joint angle, thereby generating an adjustment request. Alternatively, the user can also choose to view, adjust, or delete the training plan. For example Figure 7 As shown, Figure 7 is a schematic diagram of a third training interface provided in an embodiment of the present application. Figure 7 In the example, the corresponding operation interface can be displayed based on the view, adjust or delete control clicked by the user. For example, when the user selects the delete operation, the entire target training sequence can be called out on the interface, and then the user can determine the training action to be deleted in the training sequence, and then an adjustment request is generated based on the user's selection.

[0072] It can be seen that in this embodiment, the user can adjust the training plan based on the needs, and the server will determine whether to adjust the training plan based on the user's training goals. This can not only meet the user's training needs, but also ensure the user's training effect, improve the intelligence of the determination of the training plan, and improve the user experience.

[0073] S206: Send the target training plan to the electronic device.

[0074] Wherein, the target training scheme is used to indicate motor control instructions, and the motor control instructions are used to control the movement of the hand joints of the manipulator.

[0075] It can be seen that this embodiment can determine the training action of the current training and the maximum angle of the joint of the manipulator corresponding to each training action based on the actual rehabilitation situation of the user, so as to generate a training plan for the actual situation of the user, and improve the intelligence of the server in generating plans for rehabilitation training. At the same time, using the manipulator to move the hand joints based on the training plan to drive the user to perform passive training can also improve the training effect and convenience of the user's rehabilitation training.

[0076] For the above embodiments, please refer to Figure 8 , Figure 8 1 is a functional unit block diagram of a training program generation device based on a manipulator provided in an embodiment of the present application. Figure 8 As shown, a training program generating device 30 based on a manipulator is applied to a server of a rehabilitation training system, wherein the rehabilitation training system includes the server, an electronic device and a manipulator, wherein the server is communicatively connected to the electronic device, and the electronic device is communicatively connected to the manipulator, and the training program generating device 30 based on the manipulator includes: an acquisition unit 301, which is used to acquire a historical training record and an injured part of a target user, wherein the historical training record includes a trained action of the target user and a training score corresponding to the trained action; and a prediction unit 302, which is used to predict the rehabilitation of the target user according to the trained action and the training score corresponding to the trained action. degree; a first determining unit 303, used to determine at least one training action according to the rehabilitation degree and the injured part; a second determining unit 304, used to determine the maximum joint angle of the manipulator corresponding to each training action in the at least one training action according to the rehabilitation degree and the historical training record; a generating unit 305, used to generate a target training plan according to the at least one training action, the maximum joint angle and the historical training record; a sending unit 306, used to send the target training plan to the electronic device, the target training plan is used to indicate the motor control instruction, and the motor control instruction is used to control the movement of the hand joints of the manipulator.

[0077] In a possible embodiment, in terms of generating a target training scheme based on the at least one training action, the maximum joint angle and the historical training record, the generating unit 305 is specifically used to: divide the at least one training action into a first reference training action and a second reference training action, the first reference training action being the trained action, and the second reference training action being the training action other than the first reference training action in the at least one training action; obtaining a training score for each first reference training action in the first reference training action; obtaining a first target reference training action and a second target reference training action, the first target reference training action being the first reference training action whose training score is greater than or equal to a preset value, and the second target reference training action being the first reference training action whose training score is less than the preset value; generating an initial training action sequence based on the second reference training action and the second target reference training action, the second reference training action being arranged after the second target reference training action in the initial training action sequence; randomly inserting the first reference training action into the initial training action sequence to obtain a target training action sequence; obtaining the basic training times for each training action; generating the target training scheme based on the basic training times for each training action, the maximum joint angle of the manipulator corresponding to each training action and the target training action sequence.

[0078] In a possible embodiment, after sending the target training plan to the electronic device, the generation unit 305 is further used to: perform the following operations for each training action: obtain the current training score of the current training action from the electronic device after one training; when the current training score is less than the preset value for a consecutive preset number of times, update the target training plan so that the target user ends the training for the current training action; when the current training score is greater than or equal to the preset value for a consecutive preset number of times, adjust the maximum joint angle and training number of the manipulator corresponding to the current training action according to the current training score, and update the target training plan according to the adjusted maximum joint angle and training number.

[0079] In a possible embodiment, in terms of adjusting the maximum joint angle of the manipulator corresponding to the current training action according to the current training score, the generation unit 305 is specifically used to: determine the current standard score of the current training action according to the current training score, the current standard score being the mode among the current training scores of the current training action; determine the training level of the current training action corresponding to the current standard score; and adjust the maximum joint angle of the manipulator corresponding to the current training action according to the training level.

[0080] In a possible embodiment, in terms of obtaining the basic training times for each training action, the generating unit 305 is specifically used to: perform the following operations for each training action: determine the action category to which the current training action belongs, the action category being used to indicate that the current training action belongs to the second reference training action or the first target reference training action or the second target reference training action; when the current training action belongs to the second reference training action, determine the basic training times as the minimum training times corresponding to the second reference training action; when the current training action belongs to the first target reference training action, determine the number of times the current training action has been trained according to the historical training record; determine the basic training times according to the number of times the training has been trained, the more the number of times the basic training has been trained, the more the number of times the basic training has been trained; when the current training action belongs to the second target reference training action, determine the training level of the current training action according to the training score of the current training action in the historical training record; and determine the basic training times according to the training level.

[0081] In a possible embodiment, in terms of determining the maximum joint angle of the manipulator corresponding to each training action in the at least one training action according to the rehabilitation degree and the historical training records, the second determination unit 304 is specifically used to: determine the basic joint angle of the manipulator corresponding to each training action according to the rehabilitation degree; determine the average joint angle in the trained action according to the historical training records; determine the historical maximum joint angle corresponding to the training action whose training score is greater than or equal to a preset value according to the training score corresponding to the trained action; determine an angle adjustment coefficient according to the average joint angle and the historical maximum joint angle; adjust the basic joint angle according to the angle adjustment coefficient to obtain the maximum joint angle of the manipulator corresponding to each training action.

[0082] In a possible embodiment, after sending the target training plan to the electronic device, the manipulator-based training plan generating device 30 is further used to: obtain an adjustment request from the electronic device, the adjustment request is used to request adjustment of the at least one training action, adjustment of the training order of the at least one training action, and / or adjustment of the number of training times of the at least one training action; obtain the training goal set by the target user; determine whether the adjustment request matches the training goal based on the historical training records; if so, adjust the target training plan according to the adjustment request; if not, output a prompt message, and the prompt message is used to prompt that the adjustment fails.

[0083] It can be understood that since the method embodiment and the device embodiment are different presentation forms of the same technical concept, the content of the method embodiment part in this application should be synchronously adapted to the device embodiment part and will not be repeated here.

[0084] In the case of integrated units, see Fig. 9 , Fig. 9 1 is a functional unit block diagram of another training program generation device based on a manipulator provided in an embodiment of the present application. Fig. 9 In the embodiment, the training scheme generating device 30 based on the robot comprises: a processing module 312 and a communication module 311. The processing module 312 is used to control and manage the actions of the training scheme generating device 30 based on the robot, for example, to execute the steps of the acquisition unit 301, the prediction unit 302, the first determination unit 303, the second determination unit 304, the generation unit 305 and the sending unit 306, and / or to execute other processes of the technology described herein. The communication module 311 is used for the interaction between the training scheme generating device 30 based on the robot and other devices. Fig. 9 As shown, the training scheme generating device 30 based on the robot may further include a storage module 313, and the storage module 313 is used to store the program code and data of the training scheme generating device 30 based on the robot.

[0085] Among them, the processing module 312 can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 311 can be a transceiver, an RF circuit or a communication interface, and the like. The storage module 313 can be a memory.

[0086] Among them, all relevant contents of each scenario involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here. The above-mentioned training program generation device 30 based on the robot can execute the above-mentioned Figure 4 The manipulator-based training solution generation method shown.

[0087] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0088] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.

[0089] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0090] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0091] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0092] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0093] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0094] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the above-mentioned methods in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0095] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0096] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A training program generation method based on a robot, characterized in that: A server applied to a rehabilitation training system, the rehabilitation training system comprising the server, an electronic device and a manipulator, the server being communicatively connected to the electronic device, the electronic device being communicatively connected to the manipulator, the method comprising: Acquire historical training records and injured parts of the target user, wherein the historical training records include trained movements of the target user and training scores corresponding to the trained movements; predicting the degree of recovery of the target user according to the trained actions and the training scores corresponding to the trained actions; determining at least one training action according to the rehabilitation degree and the injured part; Determine, according to the rehabilitation degree and the historical training record, the maximum angle of the joint of the manipulator corresponding to each training action in the at least one training action; Dividing the at least one training action into a first reference training action and a second reference training action, wherein the first reference training action is the trained action, and the second reference training action is a training action in the at least one training action other than the first reference training action; Obtaining a training score for each first reference training action in the first reference training actions; Acquire a first target reference training action and a second target reference training action, wherein the first target reference training action is a first reference training action with a training score greater than or equal to a preset value, and the second target reference training action is a first reference training action with a training score less than the preset value; generating an initial training action sequence according to the second reference training action and the second target reference training action, wherein the second reference training action is arranged after the second target reference training action in the initial training action sequence; randomly inserting the first reference training action into the initial training action sequence to obtain a target training action sequence; Obtaining the basic training times for each training action; Generate a target training plan according to the basic training times of each training action, the maximum angle of the joint of the manipulator corresponding to each training action, and the target training action sequence; The target training scheme is sent to the electronic device, where the target training scheme is used to indicate a motor control instruction, and the motor control instruction is used to control the movement of the hand joints of the manipulator.

2. The method according to claim 1, characterized in that After sending the target training program to the electronic device, the method further includes: For each of the exercises described, do the following: Obtaining a current training score of a current training action from the electronic device after one training; When the current training score is less than the preset value for a consecutive preset number of times, updating the target training plan so that the target user ends the training for the current training action; When the current training score is greater than or equal to the preset value for a preset number of consecutive times, the maximum joint angle and the number of training times of the manipulator corresponding to the current training action are adjusted according to the current training score, and the target training plan is updated according to the adjusted maximum joint angle and the number of training times.

3. The method according to claim 2, characterized in that The step of adjusting the maximum joint angle of the manipulator corresponding to the current training action according to the current training score includes: Determine a current standard score of the current training action according to the current training score, wherein the current standard score is the mode of the current training scores of the current training action; Determining a training level of the current training action corresponding to the current standard score; The maximum joint angle of the manipulator corresponding to the current training action is adjusted according to the training level.

4. The method according to claim 1, characterized in that: The obtaining of the basic training times of each training action comprises: For each of the exercises described, do the following: Determine an action category to which a current training action belongs, where the action category is used to indicate that the current training action belongs to the second reference training action or the first target reference training action or the second target reference training action; In a case where the current training action belongs to the second reference training action, determining the basic training times to be the minimum training times corresponding to the second reference training action; In the case where the current training action belongs to the first target reference training action, determining the number of times the current training action has been trained according to the historical training record; determining the basic training number according to the number of times trained, the more the number of times trained, the more the basic training number; In the case that the current training action belongs to the second target reference training action, the training level of the current training action is determined according to the training score of the current training action in the historical training record; and the basic training times are determined according to the training level.

5. The method according to claim 1, characterized in that The determining, according to the rehabilitation degree and the historical training record, the maximum joint angle of the manipulator corresponding to each training action in the at least one training action comprises: Determining a basic joint angle of the manipulator corresponding to each training action according to the rehabilitation degree; Determine the average angle of the joint in the trained action according to the historical training record; Determine, according to the training score corresponding to the trained action, the historical maximum joint angle corresponding to the training action whose training score is greater than or equal to the preset value; Determine an angle adjustment coefficient according to the average joint angle and the historical maximum joint angle; The basic joint angle is adjusted according to the angle adjustment coefficient to obtain the maximum joint angle of the manipulator corresponding to each training action.

6. The method according to claim 1, characterized in that After sending the target training program to the electronic device, the method further includes: Acquire an adjustment request from the electronic device, the adjustment request being used to request adjustment of the at least one training action, adjustment of a training order of the at least one training action, and / or adjustment of a training number of the at least one training action; Acquire a training target set by the target user; Determining whether the adjustment request matches the training target according to the historical training record; If they match, adjusting the target training program according to the adjustment request; If they do not match, a prompt message is output, where the prompt message is used to indicate that the adjustment has failed.

7. A training program generating device based on a robot, characterized in that: A server applied to a rehabilitation training system, the rehabilitation training system comprising the server, an electronic device and a manipulator, the server being communicatively connected to the electronic device, the electronic device being communicatively connected to the manipulator, and the device comprising: An acquisition unit, configured to acquire a historical training record and an injured part of a target user, wherein the historical training record includes a trained action of the target user and a training score corresponding to the trained action; a prediction unit, configured to predict the degree of recovery of the target user according to the trained actions and the training scores corresponding to the trained actions; A first determining unit, configured to determine at least one training action according to the rehabilitation degree and the injured part; A second determination unit, configured to determine a maximum joint angle of the manipulator corresponding to each training action in the at least one training action according to the rehabilitation degree and the historical training record; A generating unit, for dividing the at least one training action into a first reference training action and a second reference training action, the first reference training action being the trained action, and the second reference training action being the training action other than the first reference training action in the at least one training action; and for obtaining a training score for each first reference training action in the first reference training action; and for obtaining a first target reference training action and a second target reference training action, the first target reference training action being the first reference training action whose training score is greater than or equal to a preset value, and the second target reference training action being the first reference training action whose training score is less than the preset value; and for generating an initial training action sequence according to the second reference training action and the second target reference training action, the second reference training action being arranged after the second target reference training action in the initial training action sequence; and for randomly inserting the first reference training action into the initial training action sequence to obtain a target training action sequence; and for obtaining a basic training number of each training action; and for generating a target training plan according to the basic training number of each training action, the maximum joint angle of the manipulator corresponding to each training action, and the target training action sequence; A sending unit is used to send the target training scheme to the electronic device, where the target training scheme is used to indicate motor control instructions, and the motor control instructions are used to control the movement of the hand joints of the manipulator.

8. A server, characterized in that: The method comprises a processor, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: The computer program or instructions are executed by a processor to implement the steps of the method according to any one of claims 1 to 6.

Images