Training data processing method and electronic device

Abstract

The present application relates to the field of information technology, and discloses a method for processing training data. The method for processing training data includes: obtaining the training task type of the training process; obtaining the timing duration corresponding to the training task type; according to the timing duration, asynchronously triggering the stage processing method in the preset method sequence in a preset order; when the stage processing method is a data collection method, the stage processing method is used to collect the training data of the current training stage; when the stage processing method is a data analysis method, the stage processing method is used to analyze the collected training data of the previous training stage, and the stage analysis results are given; when the training process ends, the overall analysis results corresponding to the training task type of the training process are determined according to the stage analysis results of each training stage. The use of the training data processing method can reduce the waiting time of users and improve the user experience. The present application also discloses an electronic device.

Description

Technical Field

[0001] The present application relates to the field of information technology, and in particular to a method for processing training data and an electronic device. Background Art

[0002] With the advent of the big data era, the importance of data has become particularly prominent. Using certain data analysis methods to analyze data can obtain results that reflect the actual situation.

[0003] For example, during rehabilitation training, users are usually more concerned about their own recovery level. Experienced rehabilitation therapists can give more accurate evaluation results based on the user's rehabilitation training situation. During rehabilitation training, in order to reduce the reliance on the rich experience of rehabilitation therapists, rehabilitation robots can be used to assist users in rehabilitation training. During rehabilitation training, rehabilitation robots can collect user's motion data, posture data, and strength data, and then use mature data analysis methods to automatically evaluate the user's recovery level and display the recovery level to the user. This meets the user's need to understand their own recovery level and also reduces the reliance on the rich experience of rehabilitation therapists.

[0004] In the process of implementing the embodiments of the present application, it is found that there are at least the following problems in the related technology:

[0005] In order to obtain more accurate analysis results, it is necessary to collect data from the entire rehabilitation training process and analyze the data from the entire rehabilitation training process to obtain analysis results. Such an analysis process will take a certain amount of time and require users to wait for a certain amount of time, resulting in a poor user experience. In addition, when the amount of data in the rehabilitation training process is relatively large, or the data analysis method is relatively complex, the software (human-computer interaction software of the rehabilitation robot) may easily become stuck, further reducing the user experience. Summary of the invention

[0006] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0007] The embodiments of the present application provide a training data processing method and an electronic device to shorten the time consumption of the training data analysis process, reduce the waiting time of the user for the analysis results, and improve the user's experience.

[0008] In some embodiments, a method for processing training data includes: obtaining a training task type of a training process; the training process includes multiple training stages, the training task type is pre-configured according to known body training rules, the training task type corresponds to a device type, and the multiple training stages divide the training process into multiple continuous time periods, each training stage corresponds to a time period; obtaining a timing duration corresponding to the training task type; according to the timing duration, asynchronously triggering a stage processing method in a preset method sequence in a preset order, the preset method sequence includes multiple stage processing methods, at least one stage processing method is a data collection method, and at least one stage processing method is a data analysis method; when the stage processing method is a data collection method, the stage processing method is used to collect training data of the current training stage; when the stage processing method is a data analysis method, the stage processing method is used to analyze the collected training data of the previous training stage and give a stage analysis result; when the training process ends, the overall analysis result corresponding to the training task type of the training process is determined according to the stage analysis result of each training stage.

[0009] Optionally, the multiple training stages in the training process are divided in the following manner: the training process is divided into multiple training stages according to the training duration; or the training process is divided into multiple training stages according to the training tasks in the training process.

[0010] Optionally, the training data of the training phase is collected using a phase processing method, including: monitoring an external pause operation, and pausing the data collection process if the pause operation is monitored.

[0011] Optionally, the method for processing training data also includes: obtaining a training mode type of the training process, the training mode type is a multiple-selection training mode or a single-selection training mode, the multiple-selection training mode includes a combination of multiple training modes and multiple trainings of a single training mode, and the single-selection training mode is a single training of a single training mode; the training mode is used to represent the relationship between the output force of the robot and the force applied to the robot by the user during the robot's movement; when the training mode type is a multiple-selection training mode, the multiple training modes are split into single-selection training modes, and the training data under each single-selection training mode is collected in sequence and stored in a data structure (Data Structure); after the training process ends, the training data of all single-selection training modes collected during the training process are transferred from the data structure to the data container.

[0012] Optionally, during the data collection process, if the collected data is the training data of the first training stage of the training process, the training data collection will start after the collection start marker; if the collected data is the training data of the last training stage of the training process, the end marker will be collected after the last training data is collected; wherein the start marker and the end marker appear in pairs.

[0013] Optionally, obtaining the training mode type of the training process includes: obtaining the number of data collection requests; when the number of data collection requests is greater than 1, determining that the training mode type of the training process is a multiple-selection training mode; when the number of data collection requests is equal to 1, determining that the training mode type of the training process is a single-selection training mode.

[0014] Optionally, the training data processing method further includes: during the data collection process, if the collected data is training data of the first training stage of the training process, initializing the data structure according to the first collected stage training data.

[0015] Optionally, the method for processing training data further includes: obtaining user data analysis requirements;

[0016] On this basis, according to the timing duration, the stage processing method in the preset method sequence is asynchronously triggered in a preset order, including: obtaining a preset demand method sequence corresponding to the user data analysis demand, the data analysis method in the preset demand method sequence corresponds to the user data analysis demand; according to the timing duration, the stage demand processing method in the preset demand method sequence is asynchronously triggered in a preset order, the preset demand method sequence includes multiple stage demand processing methods, at least one stage demand processing method is a data collection method, and at least one stage demand processing method is a demand data analysis method;

[0017] When the stage processing method is a data analysis method, the stage processing method is used to analyze the training data collected in the previous training stage, and a stage analysis result is given, including: when the stage processing method is the demand data analysis method, the demand data analysis method is used to analyze the demand data in the training data collected in the previous training stage, and a stage analysis result is given.

[0018] Optionally, the training data processing method further includes: classifying and storing all the training data collected in the training stage and the demand data in the training data collected in the training stage.

[0019] In some embodiments, the electronic device includes a processor and a memory storing program instructions, and the processor is configured to execute the training data processing method provided in the above embodiments when executing the program instructions.

[0020] The training data processing method and electronic device provided in the embodiments of the present application can achieve the following technical effects:

[0021] A plurality of stage processing methods are pre-stored in the preset method sequence, and the stage processing method is a data collection method or a data analysis method. In this way, by asynchronously triggering the stage processing method in the preset method sequence in a preset order, the data collection method and the data analysis method can be asynchronously executed in a preset order. As the training process continues, the data collection method can continuously collect training data in the training process. At the same time, the training data of each training stage and the stage analysis results of the training data of each stage can be obtained. After the training process is completed, the analysis results of multiple stages are processed to obtain the overall analysis results of the training process, thereby reducing the workload of data analysis after the end of the training process and the time from the end of the training process to obtaining the overall analysis results. The overall analysis results can be fed back to the user in a more timely manner, thereby reducing the user's waiting time and improving the user's experience.

[0022] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] One or more embodiments are exemplarily described by corresponding drawings, and these exemplary descriptions and drawings do not limit the embodiments. Elements with the same reference numerals in the drawings are regarded as similar elements, and wherein:

[0024] Figure 1 It is a flowchart of a method for processing training data provided in an embodiment of the present application;

[0025] Figure 2 It is a flowchart of a method for processing training data provided in an embodiment of the present application;

[0026] Figure 3 It is a flowchart of a method for processing training data provided in an embodiment of the present application;

[0027] Figure 4 It is a flowchart of a method for processing training data provided in an embodiment of the present application;

[0028] Figure 5 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to be able to understand the features and technical contents of the embodiments of the present application in more detail, the implementation of the embodiments of the present application is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present application. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, in the absence of these details, one or more embodiments can still be implemented. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0030] The terms "first", "second", etc. in the specification and claims of the embodiments of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present application described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0031] Unless otherwise stated, the term "plurality" means more than two.

[0032] In the embodiment of the present application, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0033] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0034] In some application scenarios, the user completes the training process with the assistance of the training device. After the training process is completed, the training device will promptly give the analysis results of the training process so that the user can obtain timely result feedback. The training device usually has a display screen. After the user completes the training process, the training device needs to analyze the training data in the training process to obtain the analysis results. During this analysis process, the display screen of the training device shows that the training has been completed, but does not display the analysis results. This process will give the user a sense of lag, and the duration of this process is the user's waiting time.

[0035] In an embodiment of the present application, an asynchronous data collection method and a data analysis method are adopted to distribute the data analysis process throughout the entire data collection process, that is, to distribute the data analysis process throughout the entire training process, so as to shorten the time required to obtain the overall analysis results of the training process after the training process is completed, shorten the duration that the display screen of the training device shows that the training has been completed but does not display the analysis results, reduce the sense of lag, shorten the user's waiting time, and improve the user experience.

[0036] Figure 1It is a flowchart of a method for processing training data provided in an embodiment of the present application.

[0037] Combination Figure 1 As shown, the method for processing training data includes:

[0038] S101. Obtain a training task type in a training process.

[0039] The training process in the embodiment of the present application refers to physical training, and the method for processing training data in the embodiment of the present application can be applied to known physical training scenarios such as physical rehabilitation training scenarios and physical relaxation training scenarios.

[0040] The following only takes the scenario where the training data processing method is applied to physical rehabilitation training as an example to exemplify the training data processing method.

[0041] The training task type is pre-configured according to known body training rules, and the training task type corresponds to the equipment type. For example, the training task type may represent the rehabilitation training process of different parts of the body, and the rehabilitation training process of different parts of the body can be completed on the corresponding rehabilitation training equipment.

[0042] Specifically, the training task type may be upper limb rehabilitation training, which can be completed on the upper limb rehabilitation training device; or, the training task type may be lower limb rehabilitation training, which can be completed on the lower limb rehabilitation training device; or, the training task type may be spinal rehabilitation training, which can be completed on the spinal rehabilitation training device; or, the training task type may be wrist rehabilitation training, which can be completed on the wrist rehabilitation training device; or, the training task type may be elbow rehabilitation training, which can be completed on the elbow rehabilitation training device; or, the training task type may be shoulder rehabilitation training, which can be completed on the shoulder rehabilitation training device; or, the training task type may be ankle rehabilitation training, which can be completed on the ankle rehabilitation training device; or, the training task type may be knee rehabilitation training, which can be completed on the knee rehabilitation training device; or, the rehabilitation training task type may be hip rehabilitation training, which can be completed on the hip rehabilitation training device.

[0043] Moreover, there is a corresponding relationship between the training task type and the data analysis requirement. For example, the data analysis requirement corresponding to upper limb rehabilitation training may be the rehabilitation degree of the upper limbs, the data analysis requirement corresponding to lower limb rehabilitation training may be the rehabilitation degree of the lower limbs, the data analysis requirement corresponding to spinal rehabilitation training may be the rehabilitation degree of the spine, and so on.

[0044] The training process includes multiple training phases. The multiple training phases divide the overall training process into multiple consecutive time periods, and each training phase corresponds to a time period.

[0045] There is a correspondence between the multiple training stages of the training process and the training task type of the training process. After obtaining the training task type, the multiple training stages corresponding to the training task type can be determined according to the correspondence between the multiple training stages of the training process and the training task type of the training process.

[0046] Specifically, the multiple training stages of the training process can be divided in the following way: obtain the training duration from the start time to the current time; according to the training duration, divide the training process into multiple training stages. Each training stage corresponds to a time range. For example, the time for a rehabilitation training is 45 minutes, 0 to 15 minutes is the first time range, corresponding to the first training stage; 15 minutes to 30 minutes is the second time range, corresponding to the second training stage; 30 minutes to 45 minutes is the third time range, corresponding to the third training stage. The correspondence between the time range training stages listed here is only an illustrative description and does not constitute a substantial limitation on the technical solution. Those skilled in the art can determine the time range that conforms to the actual training task type according to actual conditions.

[0047] Alternatively, the multiple training stages of the training process can be divided as follows: obtain the training movements of the training process; divide the training process into multiple training stages according to the training movements. One or more training tasks can be determined as a training stage. For example, the training tasks of the training process are: elbow extension movement and elbow swing movement, respectively. The process of performing elbow extension movement can be determined as one training stage, and the process of performing elbow swing movement can be determined as another training stage; or, the training tasks of the training process include elbow extension movement and elbow swing movement. One or more elbow extension movements, and one or more elbow swing movements connected, can be determined as a group of movements, and the process of performing each group of movements can be determined as a training stage. The training tasks listed here and the division method of the training stages are only exemplary and do not constitute a substantial limitation on the present technical solution. Those skilled in the art can determine the training stage that conforms to the actual training task type according to actual conditions.

[0048] S102: Obtain a timing duration corresponding to the training task type.

[0049] The timing duration is used to trigger the stage processing method in the preset method sequence. For example, a stage processing method in the preset method sequence is triggered at one moment, and after the timing duration, another stage processing method after the stage processing method in the preset method sequence is asynchronously triggered.

[0050] Furthermore, one training task type corresponds to a timing duration, so that the stage processing methods in the preset method sequence can be traversed and triggered according to the timing duration.

[0051] Alternatively, in multiple training stages in a training task type, each training stage corresponds to a timing duration; for example, the training process includes two consecutive training stages: a first training stage and a second training stage, and the first training stage corresponds to a first timing duration, and the second training stage corresponds to a second timing duration. In the first training stage, according to the first timing duration, the stage processing method in the preset method sequence is asynchronously triggered in a preset order, and in the second training stage, according to the second timing duration, the stage processing method in the preset method sequence is asynchronously triggered in a preset order.

[0052] The correspondence between the training task type and the timing duration may be pre-stored in a database. After obtaining the training task type, the timing duration corresponding to the training task type may be obtained by querying the database.

[0053] In actual applications, technicians in this field can set the timing duration based on experience. For example, the denser the amount of data corresponding to the training task type, the shorter the timing duration; the sparser the amount of data corresponding to the training task type, the shorter the timing duration. The above is only an example of how to obtain the timing duration, and does not limit the specific method of obtaining the timing duration. Those skilled in the art can set the timing duration that conforms to the actual situation according to the actual training situation.

[0054] Of course, the timing duration can also correspond to the data analysis requirements corresponding to the training task type. For example, the timing duration can be obtained in the following way: obtain the data analysis requirements corresponding to the training task type, and then obtain the data analysis method corresponding to the data analysis requirements. According to the inverse correlation between time complexity and duration, determine the timing duration corresponding to the time complexity of the data analysis method. The greater the time complexity of the data analysis method, the shorter the timing duration, and the less data collected within the timing duration using the data collection method. The time required for the data analysis method with greater time complexity to complete the analysis of a small amount of data is exponentially reduced, so that for each training data collected in a training stage, the data analysis method can synchronously analyze and obtain the stage analysis results, thereby improving the real-time performance of obtaining the stage analysis results during the training process, so that after the training process is completed, the overall analysis results can be obtained faster, reducing the user's waiting time and improving the user's experience.

[0055] For example, the time complexity of the data analysis method is O(N 2 ) or O(2 N), the amount of training data collected in the first time length t1 is N1, and the amount of training data collected in the second time length t2 is N2, t2=2t1, N2=2N1, then the data analysis method needs to calculate N1 to analyze the training data of N1 2 times or 2 N1 Second, the data analysis method analyzes N2 training data and needs to calculate N2 2 times or 2 N2 times, assuming that the data analysis method completes N1 2 times or 2 N1 The time required for the calculation is t1, so the data analysis method completes N2 2 times or 2 N2 The time required for the calculation is basically greater than t2. It can be seen that based on the above conditions, when the timing duration is t2, the data analysis method cannot obtain the stage analysis results within t2; when the time complexity of the data analysis method remains unchanged, after shortening the timing duration to t1, the data analysis method can obtain the stage analysis results within t1.

[0056] S103: According to the timing duration, asynchronously trigger the stage processing methods in the preset method sequence in a preset order.

[0057] Among them, the preset method sequence includes multiple stage processing methods, at least one stage processing method is a data collection method, and at least one stage processing method is a data analysis method.

[0058] The data collection method is used to collect the training data generated during the training process, and the data analysis method is used to analyze the collected data.

[0059] The above data collection method may include the setting of the data source, for example, obtaining training data through a sensor at a specific location; or, the data collection method may include the setting of the communication protocol, such as the communication protocol with the sensor at a specific location; or, the data collection method may also include the setting of the sampling frequency, such as driving the sensor to sample at the sampling frequency. The above content is only an exemplary description of the data collection method and does not constitute a substantial limitation on the data collection method. Different data types, different sensors, and different training task types, etc., can correspond to different data collection methods. Those skilled in the art can set a data collection method that conforms to the actual situation based on experience.

[0060] In terms of hardware configuration, in addition to directly collecting training data through sensors, an interface can also be set up, and other devices are connected to the interface for communication, and the training data is collected through the interface. In this case, the data collection method may include setting a communication protocol, and making the communication protocol correspond to the data type. After the training data is collected through the interface, if the communication protocol and the data type of the collected training data are in a corresponding relationship, the training data are stored and analyzed; if the communication protocol and the data type of the collected training data are not in a corresponding relationship, the training data whose communication protocol and the data type are not in a corresponding relationship are discarded.

[0061] The above-mentioned data analysis methods include but are not limited to statistical analysis methods and artificial intelligence (AI) analysis methods.

[0062] In the preset method sequence, the data acquisition method and the data analysis method can be arranged alternately. For example, the method after one or more data acquisition methods is the data analysis method, and the method after one or more data analysis methods is the data acquisition method.

[0063] In the specific application process, an array can be constructed to represent the preset method sequence; each element in the array is a function pointer of a data acquisition method or a data analysis method. Each time an element in the array is selected, the data acquisition method or data analysis method corresponding to the element is called. Each element in the array can be polled and traversed according to the timing duration, and the data acquisition method or data analysis method corresponding to each element can be called.

[0064] Specifically, a timer can be set to realize the timing of the timing duration, or the timing of the timing duration can be realized by sampling times according to the sampling frequency. The timing process of the timing duration is carried out synchronously with the training process: if the training process continues, the timing process of the timing duration continues; if the training process is paused, the timing of the timing duration is paused, and the timing duration during the pause is recorded; if the pause process is resumed, the timing continues based on the aforementioned timing duration. In specific applications, the above timing can be positive timing or countdown, and the embodiments of the present application do not specifically limit the specific timing process.

[0065] The stage processing methods in the aforementioned preset method sequence are executed asynchronously, which can realize simultaneous collection and analysis.

[0066] In addition, since asynchrony is not affected by the frame rate, the sampling frequency can also be increased by asynchronously executing the stage processing methods in the preset method sequence.

[0067] Asynchronous triggering of the stage processing method in the preset method sequence can be implemented in the following ways: the stage processing method in the preset method sequence can be called in an asynchronous manner, or the stage processing method in the preset method sequence can be called in a multi-threaded manner, or the stage processing method in the preset method sequence can be called using multiple computing cores.

[0068] The data collection method and the data analysis method in the embodiments of the present application both have a corresponding relationship with the data analysis requirements: to meet the data analysis requirements, it is necessary to adopt a data analysis method corresponding to the data analysis requirements; to meet the data requirements of the data analysis method, it is necessary to adopt a data collection method corresponding to the data analysis requirements.

[0069] S104: When the stage processing method is a data collection method, the training data of the current training stage is collected using the stage processing method.

[0070] Each training phase corresponds to one or more data collection methods.

[0071] S105. When the stage processing method is a data analysis method, the stage processing method is used to analyze the training data collected in the previous training stage, and a stage analysis result is given.

[0072] Each training phase corresponds to one or more data analysis methods.

[0073] The above-mentioned data collection method and data analysis method can be executed asynchronously. The asynchronously executed data collection method ensures that the data collection method can continuously collect the training data generated during the training process and will not miss any data. On the other hand, after each training stage is completed, the asynchronously executed data analysis method can analyze the collected training data of the completed training stage and give a stage analysis result, so that after the training process is completed, the stage analysis results of each training stage can be further analyzed to obtain the overall analysis result of the training process.

[0074] The training process includes multiple training stages, and the above-mentioned data collection method and data analysis method are executed in each training stage.

[0075] S106. At the end of the training process, determine the overall analysis result corresponding to the training task type of the training process according to the stage analysis results of multiple training stages.

[0076] In the last training stage of the training process, after the data analysis method is executed, the stage analysis results of each training stage in the training process can be obtained. The training process includes multiple training stages, and the number of stage analysis results is also multiple.

[0077] Among them, the process of determining the overall analysis results corresponding to the training task type of the training process based on the stage analysis results of multiple training stages includes, but is not limited to, statistical analysis methods and AI analysis methods.

[0078] A plurality of stage processing methods are pre-stored in the preset method sequence, and the stage processing method is a data collection method or a data analysis method. In this way, by asynchronously triggering the stage processing method in the preset method sequence in a preset order, the data collection method and the data analysis method can be asynchronously executed in a preset order. As the training process continues, the data collection method can continuously collect training data in the training process. At the same time, the training data of each training stage and the stage analysis results of the training data of each stage can be obtained. After the training process is completed, the analysis results of multiple stages are processed to obtain the overall analysis results of the training process, thereby reducing the workload of data analysis after the end of the training process and the time from the end of the training process to obtaining the overall analysis results. The overall analysis results can be fed back to the user in a more timely manner, thereby reducing the user's waiting time and improving the user's experience.

[0079] Figure 2 It is a flowchart of a method for processing training data provided in an embodiment of the present application.

[0080] Combination Figure 2 As shown, the method for processing training data includes:

[0081] S201. Obtain a training task type of a training process.

[0082] The training process includes multiple training stages, the training task type is pre-configured according to known physical training rules, and the multiple training stages divide the training process into multiple continuous time periods, and each training stage corresponds to a time period.

[0083] S202: Obtain a timing duration corresponding to the training task type.

[0084] S203: According to the timing duration, asynchronously trigger the stage processing methods in the preset method sequence in a preset order.

[0085] Among them, the preset method sequence includes multiple stage processing methods, at least one stage processing method is a data collection method, and at least one stage processing method is a data analysis method.

[0086] S204: When the stage processing method is a data collection method, the training data of the current training stage is collected using the stage processing method, and an external pause operation is monitored.

[0087] The above-mentioned “external” may refer to the outside of the program that executes the processing solution for the training data. For example, an external pause operation signal may be received through an interface, and the information of the interface may be monitored to realize monitoring of the external pause operation.

[0088] The above-mentioned pause operation can be an operation of the user on the training device, for example, the user presses the pause button / emergency stop button on the training device, or it can be a pause operation actively performed by the training device, such as a pause operation performed after the training device detects an abnormality in the device.

[0089] S205: If a pause operation has been detected, the data collection process is paused.

[0090] The data collection process depends on the operation of the data collection method. The data collection process can be suspended by pausing the data collection method.

[0091] After pausing the data collection process, the external pause operation is continuously monitored. If the external pause operation is eliminated, the data collection method is continued to run and the data collection process is continued.

[0092] Alternatively, after pausing the data collection process, the training data processing method currently running is terminated at the same time, and the training data processing method is re-run after the external pause operation is eliminated.

[0093] This can improve the accuracy of the collected training data.

[0094] In addition, it is mentioned in the aforementioned embodiment that the timing process of the timing duration is carried out synchronously with the training process. After monitoring the external pause operation, the timing process of the timing duration is paused while the data collection process is paused; if the external pause operation is eliminated and the data collection method continues to run, the timing process of the timing duration is also continued at the same time.

[0095] In this way, after stopping the data collection process, the method called in the preset method sequence will not be switched due to the expiration of the timing duration. The method called in the preset method sequence can continue to be maintained, maintaining the correspondence between the training stage and the stage processing method, thereby improving the accuracy of the collected training data and the accuracy of the stage analysis results of each training stage.

[0096] S206: If no pause operation is detected, the training data of the training phase is continuously collected using the phase processing method.

[0097] S207: When the stage processing method is a data analysis method, the stage processing method is used to analyze the collected training data of the training stage, and a stage analysis result is given.

[0098] S208. At the end of the training process, determine the overall analysis result corresponding to the training task type of the training process according to the stage analysis results of multiple training stages.

[0099] In the above embodiment, when the stage processing method is a data analysis method, even if there is an external operation, the data analysis method can continue to run, and the data analysis process can still be sustainable. In the embodiment of the present application, the data acquisition method and the data analysis method run asynchronously. In the presence of an external pause operation, the data acquisition method pauses and the data acquisition process is paused. The data analysis method can still continue to run and the data analysis process can still continue. In this way, under the premise of improving the accuracy of the collected training data, the time for giving the stage analysis results will not be extended. After the pause operation is eliminated, the data acquisition process continues. This method of suspending the data acquisition process without suspending the data analysis process can reduce the time from the end of the training process to obtaining the overall analysis result, and more timely feedback of the overall analysis result to the user, reducing the user's waiting time and improving the user's experience.

[0100] The following is a detailed description of the data collection process:

[0101] Figure 3 It is a flowchart of a method for processing training data provided in an embodiment of the present application.

[0102] Combination Figure 3 As shown, the method for processing training data includes:

[0103] S301: Obtain a training mode type of a training process.

[0104] The above-mentioned training mode types are multiple-selection training mode or single-selection training mode. The multiple-selection training mode includes a combination of multiple training modes and multiple trainings of a single training mode. The single-selection training mode is a single training of a single training mode. The training mode is used to indicate the relationship between the output force of the robot and the force applied to the robot by the user during the robot's movement.

[0105] During the robot's movement, if the robot's output force is in the same direction as the force applied to the robot by the user, the robot is in a power-assisting state; if the robot's output force is in the opposite direction to the force applied to the robot by the user, the robot is in a resistance state.

[0106] As examples, the training mode may be an active training mode, a passive compliance mode, an on-demand assistance mode, or a resistance training mode.

[0107] Among them, the active training mode means that the robot moves at a preset speed and preset trajectory to drive the user to complete the action; the passive compliance mode means that the user moves according to his own will, and the robot passively follows the user's actions; the on-demand assistance mode means that in the process of completing the action, if the force applied by the user is sufficient, the robot will not provide assistance, if the force applied by the user is not enough to complete the action, the robot will provide assistance to the user; the resistance training mode means that the robot provides resistance to the user in the process of completing the action.

[0108] Of course, the training mode is only exemplified here for applying the training data processing method to the rehabilitation training scenario. In other application scenarios, the training mode is determined according to the known training process in other scenarios.

[0109] The training mode is pre-configured and stored. For example, when the user is ready for training, the training mode for the user to select can be displayed on the human-computer interaction interface. After it is determined that the user has selected the training mode, the robot movement is controlled according to the training mode selected by the user.

[0110] Alternatively, the training mode type of the training process can be obtained in the following manner: obtain the number of data collection requests; when the number of data collection requests is greater than 1, determine that the training mode type of the training process is a multiple-selection training mode; when the number of data collection requests is equal to 1, determine that the training mode type of the training process is a single-selection training mode.

[0111] S302: When the training mode type is a multiple-selection training mode, split the multiple-selection training mode into single-selection training modes, and collect training data in each single-selection training mode in sequence and store them in a data structure.

[0112] The above order refers to the order of each training in the multiple-choice training mode.

[0113] In actual training scenarios, the device can only execute one training mode at the same time. Regardless of whether it is a combination of multiple training modes or multiple trainings of a single training mode, each training is performed in sequence.

[0114] S303: After the training process is finished, the training data of all single-choice training modes collected during the training process are transferred from the data structure to the data container.

[0115] By adopting the above technical solution, the collection of training data generated during the training process of the multiple-selection training mode is realized. In addition, when the training mode type is the multiple-selection training mode, the data structure can store the training data of each training in the multiple-selection training mode, and after the training process is completed, all the collected data is transferred to the data container, so that the training process and the training data can be stored in the data container in a one-to-one correspondence.

[0116] When the training mode type is a single-choice training mode, the training data generated during the training process is collected and stored in a data structure. After the training process is completed, the training data of the single-choice training mode collected during the training process is transferred from the data structure to the data container.

[0117] By identifying the training mode type at the collection entrance and executing the data collection plan corresponding to the training mode type, it is possible to achieve that one collection entrance can collect training data under the single-select training mode and the multiple-select training mode, thereby improving the diversity and comparability of the training data.

[0118] Furthermore, during the data collection process, if the collected data is the training data of the first training stage of the training process, the training data collection will start after the collection start marker; if the collected data is the training data of the last training stage of the training process, the end marker will be collected after the last training data is collected; wherein the start marker and the end marker appear in pairs.

[0119] The training data between the start identifier and the end identifier is the training data generated by a training process. The start identifier and the end identifier appearing in pairs can improve the integrity of the training data and improve the one-to-one correspondence between the training data and the training process. In particular, when the training mode type of the training process is a multiple-selection training mode, one training process corresponds to multiple trainings, which can better reflect that the start identifier and the end identifier appearing in pairs can improve the integrity of the training data and improve the one-to-one correspondence between the training data and the training process.

[0120] The above-mentioned start identifier and end identifier can be custom identifiers; usually, after receiving the instruction to start collecting data, the collection is started, and after receiving the instruction to end collecting data, the collection is received again. The instruction to start collecting data can also be used as the start identifier, and the instruction to end collecting data can be used as the end identifier.

[0121] In the above embodiment, the process from starting to collect training data to transferring the training data to the data container is exemplified. In this process, if the training mode type is a multiple-selection training mode, the multiple-selection training mode is split into single-selection training modes, and the training data in each single-selection training mode is collected in sequence and stored in the data structure.

[0122] Data structure is the way computers store and organize data, including but not limited to array, stack, queue, linked list, tree, graph, heap, and hash table.

[0123] In the aforementioned data collection process, if the collected data is the training data of the first training stage of the training process, the data structure is initialized according to the first collected stage training data.

[0124] The collected data is the training data of the first training stage of the training process, which means that the data structure is used for the first time to store the training data generated by the training process. The data structure is initialized according to the first collected stage training data to ensure that the training data of each training process stored is restarted, avoiding the mutual influence of training data generated by different training processes, thereby ensuring the accuracy of the stage analysis results obtained by the data analysis method.

[0125] Specifically, the data structure may be initialized in the following manner: obtaining the data type of the stage training data collected for the first time, and initializing the data type of the data structure according to the data type of the stage training data.

[0126] The data storage process is further illustrated below.

[0127] The collected training data can be stored in Json format. In order to cope with a large number of data display functions, more data fields are required. When using Json format to store these more data fields, only one field is stored in the database, which is convenient for storage; and Json's internal components are flexible and convenient, and it is easy to expand complex data relationship chains. When data storage requirements change, directly adjusting Json's internal structure can meet the changed data storage requirements. By storing training data in Json format, the complexity of the data structure is reduced, readability is improved, and changes in the database structure are reduced at the time of changing requirements; using Json format storage can also reduce storage memory.

[0128] The collection time of the training data can also be marked and stored. This is conducive to the retrieval of the training data, and can improve the uniqueness and accuracy of the training data. The training data actually collected can be marked and kept valid.

[0129] The type of training data can also be marked and stored. For example, the data collection method includes the setting of the communication protocol. Different communication protocols correspond to different data types. The type of training data can be marked and stored according to the communication protocol used when collecting data. This is conducive to the retrieval of training data. At the same time, the training data marked with the collection time and type can meet the changing needs relatively quickly.

[0130] The following is an exemplary description of the method for processing the training data in the overall solution.

[0131] In the aforementioned embodiment, it is mentioned that there is a corresponding relationship between the training task type and the data analysis requirement. For example, the data analysis requirement corresponding to the upper limb rehabilitation training may be the degree of rehabilitation of the upper limb.

[0132] Furthermore, the degree of rehabilitation of the upper limbs includes multiple dimensions, that is, the degree of rehabilitation of the upper limbs can be evaluated in multiple dimensions, for example, the degree of rehabilitation of the upper limbs can be evaluated in the dimension of muscle strength, or the degree of rehabilitation of the upper limbs can be evaluated in the dimension of range of motion of the shoulder joint, elbow joint or wrist joint.

[0133] Different users have different requirements for specific data analysis dimensions. To meet user needs, the user data analysis requirements can be obtained before the stage processing method (i.e., S103) in the preset method sequence is asynchronously triggered in a preset order according to the timing duration, and the corresponding preset requirement method sequence is determined based on the user data analysis requirements, and then data analysis is performed to obtain the overall analysis results of the training results. Figure 4 It is a flowchart of a method for processing training data provided in an embodiment of the present application, to exemplify the above process.

[0134] Combination Figure 4 As shown, the method for processing training data includes:

[0135] S401: Obtain a training task type in a training process.

[0136] S402: Obtain user data analysis requirements.

[0137] The user data analysis requirement may be one or more of the multiple dimensions of the data analysis requirements corresponding to the training task type. As described above, when the training task type is upper limb rehabilitation training, the data analysis requirement corresponding to the upper limb rehabilitation training is the degree of rehabilitation of the upper limbs, and the degree of rehabilitation of the upper limbs at least includes the analysis of the muscle strength dimension and the analysis of the joint range of motion dimension. In such a scenario, the user data analysis requirement may be the analysis of the muscle strength dimension or the analysis of the joint range of motion dimension.

[0138] Alternatively, the user data analysis requirements are basic analysis requirements during the training process. The basic analysis requirements are data analysis requirements common to various types of training tasks during the rehabilitation training process. For example, statistics on the training duration of this training process, statistics on the number of training sessions in this training process, etc.

[0139] S403: Obtain a timing duration corresponding to the training task type.

[0140] Furthermore, the timing duration can be obtained by: obtaining a demand data analysis method corresponding to the user data analysis demand, and determining the timing duration corresponding to the time complexity of the demand data analysis method according to the inverse correlation between time complexity and duration.

[0141] S404: Obtain a preset requirement method sequence corresponding to the user data analysis requirement.

[0142] The data analysis methods in the preset requirement method sequence correspond to the user's data analysis requirements.

[0143] S405. According to the timing duration, asynchronously trigger the stage demand processing method in the preset demand method sequence in a preset order.

[0144] The preset demand method sequence includes multiple stage demand processing methods, at least one stage demand processing method is a data collection method, and at least one stage demand processing method is a demand data analysis method.

[0145] S406: When the stage processing method is a demand data analysis method, the demand data in the training data collected in the previous training stage is analyzed using the demand data analysis method, and a stage analysis result is given.

[0146] S407: At the end of the training process, determine the overall analysis result corresponding to the training task type of the training process according to the stage analysis results of multiple training stages.

[0147] By adopting the above technical solution, the training data processing method can be adapted to the changing user data analysis needs, thereby improving the user experience; and, since the data analysis method is reduced, the calculation time between the end of the training process and the acquisition of the overall analysis results can be further reduced, shortening the user's waiting time and improving the user experience.

[0148] In the training data processing method, the data analysis method and the data collection method are executed asynchronously. On the basis of the above technical solution combining the user data analysis requirements, the data collection method in the preset requirement method sequence can also correspond to the user data analysis requirements. In this case, at least one stage requirement processing method is a requirement data collection method. When the requirement stage processing method is a requirement data collection method, the training data of the current training stage is collected using the requirement stage processing method.

[0149] Alternatively, based on the above technical solution combined with the user data analysis requirements, the data collection method in the preset demand method sequence still corresponds to the training task type, and the data collection method is not adjusted based on the user data analysis requirements. In this way, the training data collected by the data collection method is more comprehensive than the demand data of the demand data analysis method.

[0150] On this basis, all the training data collected in the training phase and the demand data in the training data collected in the training phase can also be classified and stored.

[0151] In this way, after the training process is completed, a relatively comprehensive analysis result can still be obtained based on the stored training data.

[0152] Figure 5 is a schematic diagram of an electronic device provided in an embodiment of the present application. Figure 5 As shown, the electronic equipment includes:

[0153] The processor 51 and the memory 52 may also include a communication interface 53 and a bus 54. The processor 51, the communication interface 53, and the memory 52 may communicate with each other through the bus 54. The communication interface 53 may be used for information transmission. The processor 51 may call the logic instructions in the memory 52 to execute the training data processing method provided in the above-mentioned embodiment.

[0154] In addition, the logic instructions in the memory 52 described above can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0155] The memory 52 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present application. The processor 51 executes functional applications and data processing by running the software programs, instructions, and modules stored in the memory 52, that is, implementing the methods in the above method embodiments.

[0156] The memory 52 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 52 may include a high-speed random access memory and may also include a non-volatile memory.

[0157] An embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the training data processing method provided in the aforementioned embodiment.

[0158] An embodiment of the present application provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the training data processing method provided by the aforementioned embodiment.

[0159] The computer-readable storage medium mentioned above may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0160] The technical solution of the embodiment of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for enabling 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 method in the embodiment of the present application. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes, or a transient storage medium.

[0161] The above description and the accompanying drawings fully illustrate the embodiments of the present application so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates otherwise, the singular forms of "a", "an" and "the" are intended to include plural forms as well. In addition, when used in this application, the term "comprise" and its variants "comprises" and / or including (comprising) refer to the existence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the existence or addition of one or more other features, wholes, steps, operations, elements, components and / or these groups. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same or similar parts between the embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0162] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. Technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiments of the present application. Technicians can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0163] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units can be only a logical function division, and there can 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. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0164] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present application. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or code, and a part of a module, program segment or code includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can also be executed in the opposite order sometimes, which can depend on the functions involved. Each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a dedicated hardware-based system that performs the function or action of the specification, or can be realized by a combination of special-purpose hardware and computer instructions.

Claims

1. A method for processing training data, characterized in that: include: Get the training task type of the training process; The training process includes a plurality of training phases, the training task type is preconfigured according to known physical training rules, and the training task type corresponds to the equipment type; Multiple training phases divide the training process into multiple consecutive time periods, with each training phase corresponding to a time period; Obtaining a timing duration corresponding to the training task type; According to the timing duration, asynchronously triggering the stage processing methods in the preset method sequence in a preset order; The preset method sequence includes multiple stage processing methods, at least one stage processing method is a data acquisition method, and at least one stage processing method is a data analysis method; When the stage processing method is a data collection method, the training data of the current training stage is collected using the stage processing method; When the stage processing method is a data analysis method, the training data of the previous training stage that has been collected is analyzed using the stage processing method, and a stage analysis result is given; When the training process is finished and the data analysis method is executed in the last training stage of the training process, the overall analysis result corresponding to the training task type of the training process is determined according to the stage analysis result of each training stage.

2. The processing method according to claim 1, characterized in that: The multiple training stages in the training process are divided as follows: The training process is divided into multiple training stages according to the training duration; or, the training process is divided into multiple training stages according to the training tasks in the training process.

3. The processing method according to claim 1, characterized in that: The training data of the training phase is collected using the stage processing method, including: Monitor external pause operations. If a pause operation is detected, the data collection process will be paused.

4. The processing method according to any one of claims 1 to 3, characterized in that: Also includes: Get the training mode type of the training process; The training mode type is a multiple-selection training mode or a single-selection training mode. The multiple-selection training mode includes a combination of multiple training modes and multiple trainings of a single training mode. The single-selection training mode is a single training of a single training mode. The training mode is used to represent the relationship between the robot’s output force and the force applied to the robot by the user during the robot’s motion; In the case where the training mode type is a multiple-selection training mode, the multiple training modes are divided into single-selection training modes, and the training data under each single-selection training mode is collected in sequence and stored in a data structure; After the training process is completed, the training data of all single-choice training modes collected during the training process are transferred from the data structure to the data container.

5. The processing method according to claim 4, characterized in that: During the data collection process, if the collected data is the training data of the first training stage of the training process, the training data collection will start after the collection start mark; If the collected data is the training data of the last training stage of the training process, the end mark is collected after the last training data is collected; The start mark and the end mark appear in pairs.

6. The processing method according to claim 4, characterized in that: Get the training mode type of the training process, including: Get the number of data collection requests; When the number of the data collection requests is greater than 1, determining that the training mode type of the training process is a multiple selection training mode; When the number of the data collection requests is equal to 1, it is determined that the training mode type of the training process is a single-selection training mode.

7. The processing method according to claim 4, characterized in that: Also includes: During the data collection process, if the collected data is the training data of the first training stage of the training process, the data structure is initialized according to the first collected stage training data.

8. The processing method according to any one of claims 1 to 3, characterized in that: It also includes: obtaining user data analysis needs; According to the timing duration, the stage processing method in the preset method sequence is asynchronously triggered in a preset order, including: obtaining a preset requirement method sequence corresponding to the user data analysis requirement, the data analysis method in the preset requirement method sequence corresponds to the user data analysis requirement; according to the timing duration, the stage requirement processing method in the preset requirement method sequence is asynchronously triggered in a preset order, the preset requirement method sequence includes multiple stage requirement processing methods, at least one stage requirement processing method is a data collection method, and at least one stage requirement processing method is a requirement data analysis method; When the stage processing method is a data analysis method, the stage processing method is used to analyze the training data collected in the previous training stage, and a stage analysis result is given, including: when the stage processing method is the demand data analysis method, the demand data analysis method is used to analyze the demand data in the training data collected in the previous training stage, and a stage analysis result is given.

9. The processing method according to claim 8, characterized in that: Also includes: All the training data collected in the training phase and the demand data in the training data collected in the training phase are classified and stored.

10. An electronic device comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to perform the training data processing method according to any one of claims 1 to 9 when executing the program instructions.

Images