Performance Testing Method, Device and Computer Readable Storage Medium for Wearable Devices

Abstract

The present disclosure discloses a performance testing method, device and computer-readable storage medium for a wearable device. Among them, the method includes: detecting a target action performed by a target object when wearing the wearable device; obtaining a first electromyogram signal detected when the target object wears the wearable device and performs the target action; performing signal processing on the first electromyogram signal based on a processing method corresponding to the target action to obtain a processing result; determining a performance test result of the wearable device according to the processing result and a second electromyogram signal, where the second electromyogram signal is the electromyogram signal detected when the target object who does not wear the wearable device performs the target action. The present disclosure solves the technical problem of low evaluation efficiency in the prior art when evaluating the device performance of a wearable device.

Description

Technical Field

[0001] The present disclosure relates to the field of device testing, and more particularly, to a method and apparatus for testing the performance of a wearable device, and a computer-readable storage medium. Background Art

[0002] In recent years, with the development of technology, exoskeletons can be applied in various fields. For example, exoskeletons can be applied to assistive exoskeleton robots and medical rehabilitation exoskeleton robots. Among them, assistive exoskeleton robots are mainly used to assist in carrying heavy objects, and medical rehabilitation exoskeleton robots are mainly used to replace physicians to complete physical rehabilitation training.

[0003] For assistive exoskeletons, there is currently no standard and unified evaluation method to measure their assistive effects. Subjective evaluation methods and energy testing methods are usually used to evaluate the assistive effects of exoskeletons.

[0004] However, the subjective evaluation method evaluates the assistive effect of the exoskeleton by scoring the assistive effect of the exoskeleton based on the usage feelings of different wearers. This method has a large subjective component and cannot objectively evaluate the assistive effect of the exoskeleton. Moreover, for wearers, the wearing experience is related not only to the assistive effect but also to the design of the wearable parts, etc. Therefore, this method cannot directly make an objective evaluation of the assistive effect of the exoskeleton.

[0005] The energy testing method indirectly evaluates the assistive effect of the exoskeleton by analyzing the oxygen consumption of the wearer when performing the same task before and after wearing the exoskeleton. However, in this method, a long time is required for testing in one experiment, and the equipment for accurately testing oxygen consumption is expensive and complex.

[0006] In view of the above problems, no effective solution has been proposed yet. Summary of the Invention

[0007] Embodiments of the present disclosure provide a method and apparatus for testing the performance of a wearable device, and a computer-readable storage medium, so as to at least solve the technical problem of low evaluation efficiency in evaluating the device performance of wearable devices in the prior art.

[0008] According to one aspect of the embodiments of the present disclosure, a method for testing the performance of a wearable device is provided, including: detecting a target action performed by a target object when wearing the wearable device; obtaining a first electromyogram signal detected when the target object performs the target action while wearing the wearable device; performing signal processing on the first electromyogram signal based on a processing method corresponding to the target action to obtain a processing result; and determining a performance test result of the wearable device according to the processing result and a second electromyogram signal, where the second electromyogram signal is an electromyogram signal detected when the target object performs the target action without wearing the wearable device.

[0009] Furthermore, the performance testing method for the wearable device further includes: determining the action type corresponding to the target action; determining the processing method according to the action type; and processing the first myoelectric signal based on the processing method to obtain a processing result.

[0010] Furthermore, the performance testing method for the wearable device further includes: when the action type is the first action type, preprocessing the first myoelectric signal to obtain the preprocessed first myoelectric signal, where the first action type represents the action when the target object is in a relatively static state; performing windowing processing on the preprocessed first myoelectric signal to obtain the windowed first myoelectric signal; and solving the eigenvalue of the windowed first myoelectric signal to obtain the processing result.

[0011] Furthermore, the performance testing method for the wearable device further includes: when the action type is the second action type, preprocessing the first myoelectric signal to obtain the preprocessed first myoelectric signal, where the second action type represents a periodic action; determining the target time according to the signal intensity of the preprocessed first myoelectric signal; performing windowing processing on the preprocessed first myoelectric signal based on the target time to obtain the windowed first myoelectric signal; and solving the eigenvalue of the windowed first myoelectric signal to obtain the processing result.

[0012] Furthermore, the performance testing method for the wearable device further includes: detecting the signal intensity of the preprocessed first myoelectric signal; and determining the time with the maximum signal intensity as the target time, where the target time is the windowing reference point.

[0013] Furthermore, the performance testing method for the wearable device further includes: determining a time window based on the target time; adjusting the time window to obtain an adjusted time window when a time window adjustment instruction is received; and performing windowing processing on the preprocessed first myoelectric signal based on the adjusted time window to obtain the windowed first myoelectric signal.

[0014] Furthermore, the performance testing method for the wearable device further includes: filtering the first myoelectric signal to obtain the filtered first myoelectric signal; and smoothing the filtered first myoelectric signal to obtain the preprocessed first myoelectric signal.

[0015] According to another aspect of the embodiments of the present disclosure, there is also provided a performance testing device for a wearable device, including: a detection module configured to detect a target action performed by a target object when wearing the wearable device; an acquisition module configured to acquire a first electromyogram signal detected when the target object wears the wearable device and performs the target action; a processing module configured to perform signal processing on the first electromyogram signal based on a processing method corresponding to the target action to obtain a processing result; and a determination module configured to determine a performance test result of the wearable device according to the processing result and a second electromyogram signal, where the second electromyogram signal is an electromyogram signal detected when the target object who does not wear the wearable device performs the target action.

[0016] According to another aspect of the embodiments of the present disclosure, there is also provided a computer-readable storage medium storing a computer program, where the computer program is configured to execute the above-mentioned performance testing method for a wearable device when running.

[0017] According to another aspect of the embodiments of the present disclosure, there is also provided an electronic device including one or more processors; and a storage device configured to store one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement a program for running, where the program is configured to execute the above-mentioned performance testing method for a wearable device when running.

[0018] In the embodiments of the present disclosure, a method of using electromyogram signals to evaluate the performance of a wearable device is adopted. By detecting the target action performed by the target object when wearing the wearable device, acquiring the first electromyogram signal detected when the target object wears the wearable device and performs the target action, then performing signal processing on the first electromyogram signal based on the processing method corresponding to the target action to obtain a processing result, and finally determining the performance test result of the wearable device according to the processing result and the second electromyogram signal detected when the target object who does not wear the wearable device performs the target action.

[0019] In the above process, the performance of the wearable device is tested through electromyogram signals. This process does not take the wearer's usage experience as a performance evaluation parameter for the wearable device, making the performance test result of the wearable device more objective. In addition, compared with the energy test method in the prior art, the test time for testing the performance of the wearable device through electromyogram signals is short, and the wearer is not easily fatigued, thus improving the evaluation efficiency of the device performance of the wearable device. Moreover, in the present application, different processing methods are adopted for different types of actions of the target object wearing the wearable device to process the electromyogram signals, so that the evaluation result of the device performance of the wearable device is more accurate.

[0020] As can be seen, the solution provided by this application achieves the purpose of accurately evaluating the device performance of the wearable device, thus realizing the technical effect of improving the evaluation efficiency of the wearable device, and further solving the technical problem of low evaluation efficiency existing in the prior art when evaluating the device performance of the wearable device. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present disclosure and form a part of this application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation to the present disclosure. In the drawings:

[0022] Figure 1 is a flowchart of a method for testing the performance of a wearable device according to an embodiment of the present disclosure;

[0023] Figure 2 is a schematic structural diagram of an optional performance testing system for a wearable device according to an embodiment of the present disclosure;

[0024] Figure 3 is a flowchart of a method for processing an electromyogram signal according to an embodiment of the present disclosure;

[0025] Figure 4 is a flowchart of a method for processing an electromyogram signal according to an embodiment of the present disclosure;

[0026] Figure 5 is a schematic diagram of a device for testing the performance of a wearable device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] In order to enable those skilled in the art to better understand the solution of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present disclosure.

[0028] It should be noted that the terms "first", "second", etc. in the specification, claims and above-mentioned drawings of the present disclosure are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily limit to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] According to an embodiment of the present disclosure, there is provided an embodiment of a performance testing method for a wearable device. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0031] Figure 1 is a flowchart of a performance testing method for a wearable device according to an embodiment of the present disclosure, as Figure 1 shown, the method includes the following steps:

[0032] Step S102, detecting a target action performed by a target object when wearing a wearable device.

[0033] In step S102, the target object is a tester wearing the wearable device, and the wearable device can be, but is not limited to, an exoskeleton. In addition, the above-mentioned target action can determine the action type according to the signal strength of the signal generated when the target object performs the action. Among them, the target action can include, but is not limited to, static actions and periodic actions. Optionally, the signal strength generated by static actions is weak, for example, a stretching action; while the signal strength generated by periodic actions is strong, for example, a running action, a walking action.

[0034] It should be noted that when the target object performs different actions, the intensity of the myoelectric signals generated by them is different. In this application, when testing the device performance of the wearable device, considering the influence of the actions performed by the target object on the test results, different processing methods are adopted for the myoelectric signals generated by different types of target actions performed by the target object, which improves the accuracy of the performance evaluation of the wearable device.

[0035] Step S104, acquiring a first myoelectric signal detected when the target object wears the wearable device and performs the target action.

[0036] Optionally, before performing a performance test on the wearable device, the tester first needs to evaluate the muscles of the target object. Specifically, the tester can select one or more muscles that are highly relevant to the task according to different tasks. Since the amplitudes of the electromyographic signals generated by different muscles are different when the target object performs the same action, selecting the muscles with larger signal amplitudes of the electromyographic signals (for example, the muscles with signal amplitudes of the electromyographic signals greater than a preset amplitude) to perform the performance test on the wearable device can reduce the influence of noise on the evaluation result, thereby improving the evaluation accuracy of the wearable device.

[0037] Furthermore, after determining the muscles to be tested of the target object, the tester can install the electromyographic signal acquisition sensor on the above-mentioned muscles to be tested. Generally, before installing the electromyographic signal acquisition sensor on the muscles to be tested, surface treatment work such as wiping the skin with an alcohol swab needs to be carried out to remove the sweat on the muscles to be tested of the target object and reduce the impedance between the electromyographic signal acquisition sensor and the skin. When installing the electromyographic signal acquisition sensor, the tester needs to fix the electromyographic signal acquisition sensor with medical tape to prevent the electromyographic signal acquisition sensor from loosening during the movement of the target object and introducing noise. Moreover, the test scenario needs to be far away from places with large electromagnetic interference to prevent interference with the electromyographic signal.

[0038] It should be noted that using the first electromyographic signal obtained in step S104 to test the device performance of the wearable device not only ensures the accuracy of the evaluation result, but also has a short test time, the target object is not easily fatigued, and the comfort of the target object during the test is improved. In addition, in this embodiment, an electromyographic signal acquisition sensor is used to collect the first electromyographic signal, and the electromyographic signal acquisition sensor is lightweight, can use a wireless transmission method, the device installation is simple, the cost is low, and it is not easy to affect the target action performed by the target object, thereby improving the evaluation accuracy of the wearable device.

[0039] Step S106, perform signal processing on the first electromyographic signal based on the processing method corresponding to the target action to obtain a processing result.

[0040] In step S106, for different types of actions, the processing methods of their corresponding electromyographic signals are different. For example, the processing method of the electromyographic signal generated when the target object performs a static action is different from the processing method of the electromyographic signal generated when the target object performs a periodic action.

[0041] It should be noted that for the EMG signals generated by different types of actions, different processing methods are used for signal processing, so as to process the corresponding EMG signals in the optimal processing method, and then accurate performance test results for evaluating the performance of the wearable device can be obtained.

[0042] Step S108: Determine the performance test result of the wearable device according to the processing result and the second EMG signal, where the second EMG signal is the EMG signal detected when the target object without wearing the wearable device performs the target action.

[0043] In step S108, the processing result is the EMG signal after processing the first EMG signal generated when the target object wears the wearable device, and the second EMG signal is the EMG signal generated when the target object does not wear the wearable device. The performance test result of the wearable device can be obtained by analyzing the processing result and the second EMG signal. Among them, the above performance test result at least includes the assistance effect of the wearable device.

[0044] Optionally, the performance test result of the wearable device can be obtained by calculating the cumulative sum of the difference between the above processing result and the first EMG signal. For example, when the above cumulative sum is greater than the preset cumulative sum, it is determined that the performance test of the wearable device is poor; when the above cumulative sum is less than or equal to the preset cumulative sum, it is determined that the performance test of the wearable device is good.

[0045] Based on the solution defined in the above steps S102 to S108, it can be known that in the embodiment of the present disclosure, the method of using EMG signals to evaluate the performance of the wearable device detects the target action performed by the target object when wearing the wearable device, obtains the first EMG signal detected when the target object wears the wearable device and performs the target action, then performs signal processing on the first EMG signal based on the processing method corresponding to the target action to obtain the processing result, and finally determines the performance test result of the wearable device according to the processing result and the second EMG signal detected when the target object without wearing the wearable device performs the target action.

[0046] It is easy to notice that in the above process, the performance of the wearable device is tested through EMG signals, and the user experience of the wearer is not used as a performance evaluation parameter for the wearable device, making the performance test result of the wearable device more objective. In addition, compared with the energy test method in the prior art, the test time for testing the performance of the wearable device through EMG signals is short, and the wearer is not easily fatigued, thus improving the evaluation efficiency of the device performance of the wearable device. Moreover, in this application, for different types of actions of the target object wearing the wearable device, different processing methods are used to process the EMG signals, so that the evaluation result of the device performance of the wearable device is more accurate.

[0047] As can be seen, the solution provided by this application achieves the purpose of accurately evaluating the device performance of the wearable device, thereby achieving the technical effect of improving the evaluation efficiency of the wearable device, and further solving the technical problem of low evaluation efficiency existing in the prior art when evaluating the device performance of the wearable device.

[0048] In an alternative embodiment, Figure 2 FIG. shows a schematic structural diagram of a performance test system for a wearable device. The performance test system includes an acquisition unit and a processing unit. Among them, the acquisition unit at least includes the above-mentioned electromyogram signal acquisition sensor and a data sending unit. The data sending unit can be, but is not limited to, a wireless transmission unit or a wired transmission unit. Preferably, in this embodiment, the data sending unit is a wireless transmission unit, such as a Bluetooth module. In addition, the processing unit at least includes a data receiving unit and a processor. The data receiving unit is connected to the processor through a USB (Universal Serial Bus) serial port. Similarly, the data receiving unit can be, but is not limited to, a wireless transmission unit or a wired transmission unit. Preferably, in this embodiment, the data receiving unit is a wireless transmission unit, such as a Bluetooth module. The processor is composed of a user information management module, a parameter self-tuning module, an effect evaluation module, a display module, an evaluation action selection module, and a storage module.

[0049] Optionally, the user information management module is mainly used to manage information of different subjects. When using the system for the first time, it is necessary to input the object information of the subject (i.e., the above-mentioned target object), such as basic information such as name, gender, age, height, and weight. Among them, these object information is associated with subsequent test data, and the above object information can be stored in a database.

[0050] Optionally, for different muscles, or the same muscle when performing different actions, the output characteristics of electromyogram signals are different. Therefore, when the subject uses the system for the first time, it is necessary to use the parameter self-tuning module to perform online tuning on some parameters that are greatly affected by individual differences. Specifically, after installing the electromyogram signal acquisition box (i.e., the electromyogram signal acquisition sensor) on the surface of the muscle to be tested of the subject, the subject performs the corresponding operation task, that is, the subject performs the corresponding action. The processor can determine some evaluation parameters required in the effect evaluation module through the parameter self-tuning algorithm in the parameter self-tuning module, such as data such as zero-point offset and signal variance. Among them, the above-mentioned evaluation parameters will be stored in the database corresponding to the specified subject for direct use when the subject is tested again next time, and can also be used by the algorithm in the effect evaluation module.

[0051] Optionally, the effect evaluation module can obtain the myoelectric signals collected by the myoelectric signal acquisition sensor through the wireless receiving unit, preprocess the myoelectric signals, and then process the preprocessed myoelectric signals through the assistance effect evaluation algorithm to determine the assistance effect of the wearable device.

[0052] Optionally, in order to evaluate the assistance effect of the wearable device, the subject needs to perform the same actions with and without wearing the wearable device. Specifically, first, the subject is required to wear the wearable device and perform specific static actions or cyclic actions according to the instructions of the command issuer. After the specified test process ends, click the system end button in the display module to end the test system. Then, click the result save button to save the test results of this time to the storage module. Then, after the subject rests for a period of time, perform the same actions in the same process as above when the subject is not wearing the wearable device until the results are finally saved.

[0053] It should be noted that the above command issuer can select the target action performed by the subject through the evaluation action selection module. In addition, the above display module can also display in real time the myoelectric signals collected by the myoelectric signal acquisition sensor, and can also display the performance test results for evaluating the performance of the wearable device.

[0054] In an optional embodiment, after obtaining the first myoelectric signal detected when the target object wears the wearable device and performs the target action, the above processor determines the action type corresponding to the target action, then determines the processing method according to the action type, and processes the first myoelectric signal based on the processing method to obtain a processing result.

[0055] Optionally, the tester (i.e., the above command issuer) can select the action to be performed by the target object through the evaluation action selection module. For example, there is an action selection control in the display module corresponding to the processor. The tester can select the action to be performed by the target object from multiple actions by clicking the action selection control, such as stretching, extending, walking, running and other actions. After the processor detects that the tester has selected the target action to be performed by the target object, it determines the action type according to the target action, that is, determines whether the target action is a cyclic action or a static action. Then the processor selects different processing methods for the myoelectric signals according to different action types.

[0056] Further, when the action type is the first action type, the processor preprocesses the first EMG signal to obtain the preprocessed first EMG signal, performs windowing on the preprocessed first EMG signal to obtain the windowed first EMG signal, and then solves for the eigenvalue of the windowed first EMG signal to obtain the processing result. Among them, the first action type represents the action when the target object is in a relatively static state.

[0057] Optionally, Figure 3 shows an optional method for processing EMG signals. It can be seen that Figure 3 after the first EMG signal is obtained, the processor first preprocesses the first EMG signal, that is, performs band-pass filtering, full-wave rectification, and smoothing processing on the first EMG signal to obtain the preprocessed first EMG signal. Then, the processor performs windowing on the preprocessed first EMG signal. Among them, the time window added by the processor to the preprocessed first EMG signal is an adjacent window with equal width. Finally, the processor calculates the average value or the maximum value of the preprocessed first EMG signal within the above time window, and determines the average value or the maximum value as the eigenvalue of the windowed first EMG signal above, that is, the above processing result.

[0058] It should be noted that the method for solving the eigenvalue of the windowed first EMG signal is not limited to the above method of calculating the average value or the maximum value, and other calculations such as integration can also be performed on the windowed first EMG signal to obtain the above processing result.

[0059] In an optional embodiment, when the action type is the second action type, the processor preprocesses the first EMG signal to obtain the preprocessed first EMG signal, determines the target time according to the signal intensity of the preprocessed first EMG signal, then performs windowing on the preprocessed first EMG signal based on the target time to obtain the windowed first EMG signal, and finally solves for the eigenvalue of the windowed first EMG signal to obtain the processing result. Among them, the second action type represents a periodic action.

[0060] Optionally, Figure 4 shows an optional method for processing EMG signals. It can be seen from Figure 4It can be seen that after obtaining the first EMG signal, the processor first preprocesses the first EMG signal, that is, performs band-pass filtering, full-wave rectification, and smoothing processing on the first EMG signal to obtain the preprocessed first EMG signal. Then, the processor performs windowing processing on the preprocessed first EMG signal, where the time window added by the processor to the preprocessed first EMG signal is a time window with adjustable width. Finally, the processor calculates the average value or the maximum value of the preprocessed first EMG signal within the above-mentioned time window, and determines the average value or the maximum value as the eigenvalue of the first EMG signal after windowing, that is, the above-mentioned processing result.

[0061] It should be noted that the method for solving the eigenvalue of the first EMG signal after windowing is not limited to the above method of calculating the average value or the maximum value, and it is also possible to perform calculations such as integration on the first EMG signal after windowing to obtain the above-mentioned processing result.

[0062] In an alternative embodiment, after obtaining the preprocessed first EMG signal, the processor detects the signal strength of the preprocessed first EMG signal, and determines the time with the maximum signal strength as the target time, where the target time is the windowing reference point.

[0063] Optionally, in Figure 4 , the processor first detects whether the signal strength of the preprocessed first EMG signal is greater than a preset strength. If the signal strength of the preprocessed first EMG signal is greater than the preset strength, it indicates that the first EMG signal is an EMG signal corresponding to a periodic action. Otherwise, it indicates that the first EMG signal is an EMG signal corresponding to a static action. When the signal strength of the preprocessed first EMG signal is greater than the preset strength, the time point with the maximum signal strength is used as the windowing reference point to perform windowing processing on the preprocessed first EMG signal.

[0064] Optionally, the processor can determine the time window based on the target time, and then, in the case of receiving a time window adjustment instruction, adjust the time window to obtain an adjusted time window, and perform windowing processing on the preprocessed first EMG signal based on the adjusted time window to obtain the first EMG signal after windowing.

[0065] It should be noted that in this embodiment, the front and rear widths of the time window are adjustable, so as to avoid the problem of inaccurate eigenvalue solution caused by the time point with the maximum signal strength not being at the midpoint of the periodic action, thereby ensuring the evaluation accuracy of the performance of the wearable device.

[0066] In an alternative embodiment, by Figure 3 and Figure 4It can be known that when the target actions are static actions and periodic actions, the preprocessing process of the first electromyogram signal is the same, that is, during the preprocessing of the first electromyogram signal, both filtering processing and smoothing processing are performed on the first electromyogram signal.

[0067] Specifically, the processor first performs filtering processing on the first electromyogram signal to obtain the filtered first electromyogram signal, and then performs smoothing processing on the filtered first electromyogram signal to obtain the preprocessed first electromyogram signal.

[0068] It should be noted that the above first electromyogram signal is the original electromyogram signal, which is a weak signal collected through the contact point between the silver electrode and the muscle. In order to improve the accuracy of signal processing, in this embodiment, the original electromyogram signal (i.e., the first electromyogram signal) is preprocessed such as differential amplification and filtering through a hardware circuit, and the preprocessed first electromyogram signal is transmitted to the processor of the central host by wireless transmission to perform signal processing and analysis on the first electromyogram signal.

[0069] Optionally, during the filtering process of the first electromyogram signal by the processor, band-pass filtering and full-wave rectification can be performed on the first electromyogram signal. It should be noted that although filtering is achieved through a hardware circuit in the front-end signal acquisition circuit, considering that noise may also be introduced during the signal transmission process, in this application, the processor also performs band-pass filtering on the received first electromyogram signal. Among them, the range of the band-pass filter can be determined according to the effective electromyogram signal range. Optionally, in this embodiment, the low-pass frequency range of the band-pass filter is 450 - 500 Hz, and the high-pass frequency range is 10 - 20 Hz.

[0070] Optionally, during the rectification process, the processor mainly processes the electromyogram signal with a negative sign. Among them, rectification includes half-wave rectification and full-wave rectification. In the embodiment, the rectification method for the electromyogram signal is the full-wave rectification method.

[0071] Optionally, in this embodiment, the smoothing process of the electromyogram signal can be achieved by the method of windowed moving average or low-pass filtering. Among them, in this application, the low-pass filtering method is used to achieve the smoothing process of the electromyogram signal, and the low-pass frequency of this low-pass filter is 6 Hz.

[0072] It should be noted that the above filtering and smoothing processes can be performed in the central host or the client, and will not be specifically explained here.

[0073] The following takes the evaluation of the assistance effect of the exoskeleton when walking with a 20-kilogram load on the back (i.e., a periodic action) as an example for introduction. Since there are many lower limb muscles involved in walking, in this embodiment, the activity intensity ratio of the rectus femoris is selected to evaluate the assistance effect of the exoskeleton. The specific steps are as follows:

[0074] Step S1: Enter the selected subject information into the system through the user information management module.

[0075] Step S2: Wipe the muscle surface of the subject with an alcohol swab, then arrange the electromyogram (EMG) signal acquisition sensor along the direction of the rectus femoris muscle fibers, and fix the EMG signal acquisition sensor with medical tape. The tester starts the system, enters the parameter self-tuning module, and performs the walking task separately when the subject is not wearing the exoskeleton and when wearing the exoskeleton, walking for 10 cycles. The parameter self-tuning module calculates the recorded data to obtain the maximum value Vmaxi of the signal in the gait cycle (where i = 1 represents the maximum value when the subject is not wearing the exoskeleton; i = 2 represents the maximum value when the subject is wearing the exoskeleton), and stores the calculated value in the database.

[0076] Step S3: Enter the effect evaluation module. After switching the evaluation action type switch to periodic action evaluation, set the band-pass filtering range of the EMG signal to 10 - 500 Hz, set the action threshold (i.e., the preset intensity) to 50% of Vmaxi, and set the time window to 1 / 2 of the gait cycle.

[0077] After completing the above settings, when the tester clicks the start button, the subject starts gait walking with a load from the upright state without wearing the exoskeleton. After walking 10 complete gait cycles, the system ends and saves the results. After the same subject rests for 30 minutes, then walks with a load while wearing the exoskeleton. After walking 10 cycles at the same walking frequency, the system ends and saves the results. Finally, use the end output function to output the quantitative evaluation results of the two times.

[0078] In addition, through the result display function of the system, the results of the two times can be plotted on the display interface of the system at the same time, and the cumulative sum of the difference between the two can be calculated, so that the assisting effect of the exoskeleton can be evaluated numerically in an intuitive and quantitative manner. It should be noted that when evaluating different exoskeletons, the quantitative assisting effect of each exoskeleton can be given quantitatively.

[0079] As can be seen from the above, the present application provides an online real-time quantitative evaluation method for the assistance effect of an exoskeleton based on myoelectric signals. This method reflects the activation intensity of muscles through myoelectric signals and uses the activation activity intensity before and after wearing the exoskeleton to quantitatively evaluate the assistance effect of the exoskeleton. Compared with the existing energy test method, the test time is short, the subjects are not easily fatigued, and it is also convenient for women to conduct the test. In addition, this method can dynamically view the muscle condition online in real time and quantitatively output the assistance effect, which is more persuasive compared with the existing subjective evaluation method. Moreover, in the real-time assistance effect evaluation algorithm for cyclic movements, the maximum value of the signal is used as the reference point for windowing, and then the muscle strength eigenvalue is obtained; the test results are output online in real time. Compared with offline data processing after testing various data, the labor intensity is greatly reduced, the processing efficiency is improved, and the influence of the inconsistency of the windowing position and width on the results in manual processing is reduced. Finally, in the present application, the myoelectric signal acquisition sensor is light and wireless, the device is simple to install, and the cost is low, and it will not affect the movement to be tested.

[0080] Embodiment 2

[0081] According to an embodiment of the present disclosure, there is also provided an embodiment of a performance test device for a wearable device, wherein, Figure 5 is a schematic diagram of a performance test device for a wearable device according to an embodiment of the present disclosure, as Figure 5 shown, the device includes: a detection module 501, an acquisition module 503, a processing module 505, and a determination module 507.

[0082] Among them, the detection module 501 is used to detect a target action executed by a target object when wearing the wearable device; the acquisition module 503 is used to acquire a first myoelectric signal detected when the target object wears the wearable device and executes the target action; the processing module 505 is used to perform signal processing on the first myoelectric signal based on a processing method corresponding to the target action to obtain a processing result; the determination module 507 is used to determine a performance test result of the wearable device according to the processing result and a second myoelectric signal, where the second myoelectric signal is a myoelectric signal detected when the target object who does not wear the wearable device executes the target action.

[0083] It should be noted that the above first response module 801, second response module 803, and third response module 805 correspond to steps S102 to S108 in the above embodiment. The examples and application scenarios implemented by the four modules and the corresponding steps are the same, but are not limited to the content disclosed in the above embodiment 1.

[0084] Optionally, the processing module includes: a first determination module, a second determination module, and a first processing module. Among them, the first determination module is configured to determine the action type corresponding to the target action; the second determination module is configured to determine the processing method according to the action type; the first processing module is configured to process the first electromyogram signal based on the processing method to obtain a processing result.

[0085] Optionally, the first processing module includes: a first preprocessing module, a first windowing module, and a second processing module. Among them, the first preprocessing module is configured to preprocess the first electromyogram signal to obtain a preprocessed first electromyogram signal when the action type is the first action type, where the first action type represents the action when the target object is in a relatively static state; the first windowing module is configured to perform windowing processing on the preprocessed first electromyogram signal to obtain a windowed first electromyogram signal; the second processing module is configured to solve the eigenvalue of the windowed first electromyogram signal to obtain a processing result.

[0086] Optionally, the first processing module includes: a second preprocessing module, a third determination module, a second windowing module, and a third processing module. Among them, the second preprocessing module is configured to preprocess the first electromyogram signal to obtain a preprocessed first electromyogram signal when the action type is the second action type, where the second action type represents a periodic action; the third determination module is configured to determine the target time according to the signal intensity of the preprocessed first electromyogram signal; the second windowing module is configured to perform windowing processing on the preprocessed first electromyogram signal based on the target time to obtain a windowed first electromyogram signal; the third processing module is configured to solve the eigenvalue of the windowed first electromyogram signal to obtain a processing result.

[0087] Optionally, the third determination module includes: a first detection module and a fourth determination module. Among them, the first detection module is configured to detect the signal intensity of the preprocessed first electromyogram signal; the fourth determination module is configured to determine the time with the maximum signal intensity as the target time, where the target time is the windowing reference point.

[0088] Optionally, the second windowing module includes: a fifth determination module, an adjustment module, and a third windowing module. Among them, the fifth determination module is configured to determine the time window based on the target time; the adjustment module is configured to adjust the time window to obtain an adjusted time window when receiving a time window adjustment instruction; the third windowing module is configured to perform windowing processing on the preprocessed first electromyogram signal based on the adjusted time window to obtain a windowed first electromyogram signal.

[0089] Optionally, the performance testing apparatus for the wearable device further includes: a filtering module and a fourth processing module. Among them, the filtering module is configured to perform filtering processing on the first electromyogram signal to obtain a filtered first electromyogram signal; the fourth processing module is configured to perform smoothing processing on the filtered first electromyogram signal to obtain a preprocessed first electromyogram signal.

[0090] Embodiment 3

[0091] According to another aspect of the embodiments of the present disclosure, there is also provided a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the performance testing method for the wearable device in Embodiment 1 when running.

[0092] Embodiment 4

[0093] According to another aspect of the embodiments of the present disclosure, there is also provided an electronic device including one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement a program for running, wherein the program is configured to execute the performance testing method for the wearable device in Embodiment 1 when running.

[0094] The serial numbers of the above embodiments of the present disclosure are only for description and do not represent the advantages or disadvantages of the embodiments.

[0095] In the above embodiments of the present disclosure, the descriptions of the respective embodiments have their own focuses. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0096] In the several embodiments provided by the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units can be a logical function division, and in actual implementation, there can be other division methods. For example, 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 displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the units or modules can be in an electrical or other form.

[0097] The units described 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 can be located in one place or distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0098] In addition, in each embodiment of the present disclosure, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0099] 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 storage medium. Based on such an understanding, the technical solution of the present disclosure, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs.

[0100] The above are only the preferred embodiments of the present disclosure. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present disclosure, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present disclosure.

Claims

1. A performance testing method for a wearable device, characterized in that, Including: Detecting a target action performed when a target object wears a wearable device; Obtaining a first electromyogram signal detected when the target object wears the wearable device and performs the target action; Performing signal processing on the first electromyogram signal based on a processing method corresponding to the target action to obtain a processing result; Determining a performance test result of the wearable device according to the processing result and a second electromyogram signal, where the second electromyogram signal is an electromyogram signal detected when the target object who does not wear the wearable device performs the target action; Wherein, performing signal processing on the first electromyogram signal based on a processing method corresponding to the target action to obtain a processing result includes: Determining an action type corresponding to the target action; Determining the processing method according to the action type; Performing processing on the first electromyogram signal based on the processing method to obtain the processing result; Wherein, performing processing on the first electromyogram signal based on the processing method to obtain the processing result includes: When the action type is a second action type, preprocessing the first electromyogram signal to obtain a preprocessed first electromyogram signal, where the second action type represents a periodic action; Determining a target time according to the signal intensity of the preprocessed first electromyogram signal; Performing windowing processing on the preprocessed first electromyogram signal based on the target time to obtain a windowed first electromyogram signal; Solving for eigenvalue of the windowed first electromyogram signal to obtain the processing result.

2. The method according to claim 1, wherein Performing processing on the first electromyogram signal based on the processing method to obtain the processing result, including: When the action type is a first action type, preprocessing the first electromyogram signal to obtain a preprocessed first electromyogram signal, where the first action type represents an action when the target object is in a relatively static state; Performing windowing processing on the preprocessed first electromyogram signal to obtain a windowed first electromyogram signal; Solving for eigenvalue of the windowed first electromyogram signal to obtain the processing result.

3. The method according to claim 2, wherein Determining a target time according to the signal intensity of the preprocessed first electromyogram signal includes: Detecting the signal intensity of the preprocessed first electromyogram signal; Determining the time with the maximum signal intensity as the target time, where the target time is a windowing reference point.

4. The method according to claim 3, characterized in that, Performing windowing processing on the preprocessed first electromyogram signal based on the target time to obtain a windowed first electromyogram signal, including: Determining a time window based on the target time; Adjusting the time window when a time window adjustment instruction is received to obtain an adjusted time window; Performing windowing processing on the preprocessed first electromyogram signal based on the adjusted time window to obtain the windowed first electromyogram signal.

5. The method according to claim 1 or 2, characterized in that, Preprocessing the first electromyogram signal to obtain a preprocessed first electromyogram signal, including: Performing filtering processing on the first electromyogram signal to obtain a filtered first electromyogram signal; Performing smoothing processing on the filtered first electromyogram signal to obtain the preprocessed first electromyogram signal.

6. A performance testing device for a wearable device, characterized in that Including: A detection module, configured to detect a target action performed when a target object wears a wearable device; An acquisition module, configured to acquire a first electromyogram signal detected when the target object wears the wearable device and performs the target action; A processing module, configured to perform signal processing on the first electromyogram signal based on a processing method corresponding to the target action to obtain a processing result; A determination module, configured to determine a performance test result of the wearable device according to the processing result and a second electromyogram signal, where the second electromyogram signal is an electromyogram signal detected when the target object performs the target action without wearing the wearable device; Wherein, the processing module is further configured to determine an action type corresponding to the target action; determine the processing method according to the action type; perform processing on the first electromyogram signal based on the processing method to obtain the processing result; Wherein, the device is further configured to, when the action type is a second action type, perform preprocessing on the first electromyogram signal to obtain a preprocessed first electromyogram signal, where the second action type represents a periodic action; determine a target time according to the signal intensity of the preprocessed first electromyogram signal; perform windowing processing on the preprocessed first electromyogram signal based on the target time to obtain a windowed first electromyogram signal; solve eigenvalues of the windowed first electromyogram signal to obtain the processing result.

7. A computer-readable storage medium, characterized in that, A computer program is stored in the computer-readable storage medium, wherein the computer program is configured to execute the performance test method of the wearable device described in any one of claims 1 to 5 when running.

8. An electronic device, characterized in that, The electronic device includes one or more processors; a storage device, configured to store one or more programs, when the one or more programs are executed by the one or more processors, enabling the one or more processors to implement a program for running, wherein the program is configured to execute the performance test method of the wearable device described in any one of claims 1 to 5 when running.

Images