Processing method and system for intelligent wearable device to reduce upper limb tremor

Abstract

The present application provides a processing method and system for a smart wearable device for alleviating upper limb tremor. The method includes: the smart wearable device collects the user's tremor characteristics and sends them to a first server. The first server determines the target method for alleviating the user's tremor based on the tremor amplitude and a pre-set amplitude threshold. If the target method is a nerve stimulation method, the first server analyzes and predicts the tremor characteristics based on the tremor characteristics using a pre-trained tremor suppression model, obtains suppression parameters, and sends them to the smart wearable device. Through the above method, upper limb tremor of Parkinson's patients can be suppressed, which not only helps patients recover physically but also provides convenience for their lives.

Description

Technical Field

[0001] The present application relates to the field of health care technology, and in particular to a processing method and system for an intelligent wearable device for alleviating upper limb tremor. Background Art

[0002] Parkinson's disease (PD), also known as Parkinson's paralysis syndrome, is a chronic degenerative disorder of the central nervous system. Patients with PD typically experience varying degrees of movement disorders, clinically characterized by resting tremor, bradykinesia, muscle rigidity, and postural and gait disturbances. These symptoms render patients unable to function independently in daily life, making a cure for PD a major research goal.

[0003] At present, the treatment of Parkinson's disease is divided into drug therapy and physical therapy. Although drug therapy is the current mainstream treatment method, it also has the risk of misdiagnosis and drug side effects. Although physical therapy seems to be a better method, it lacks suitable auxiliary tools to help patients better carry out treatment and be able to persist in it for a long time.

[0004] In summary, how to suppress upper limb tremors in Parkinson's patients is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0005] The present application provides a processing method and system for an intelligent wearable device for alleviating upper limb tremor, which is used to solve the problem of how to suppress upper limb tremor in Parkinson's patients.

[0006] In a first aspect, the present application provides a processing method for a smart wearable device for alleviating upper limb tremor, which is applied to a tremor suppression system, wherein the tremor suppression system includes a smart wearable device, a first server, a second server, a monitoring device, and a user's terminal device; the smart wearable device, the first server, the second server, and the monitoring device are communicatively connected, and the smart wearable device, the monitoring device, the first server, and the terminal device are communicatively connected; the method includes:

[0007] The smart wearable device collects tremor characteristics of the user and sends the collection to the first server, where the tremor characteristics include tremor frequency and tremor amplitude;

[0008] The first server determines a target method for alleviating the user's tremor based on the tremor amplitude and a preset amplitude threshold, the target method including a voice prompt method or a nerve stimulation method;

[0009] If the target method is a neural stimulation method, the first server analyzes and predicts the tremor characteristics based on the tremor characteristics using a pre-trained tremor suppression model to obtain suppression parameters, and sends the obtained suppression parameters to the smart wearable device. The suppression parameters are used to perform neural stimulation on the user to reduce limb tremors. The tremor suppression model is trained based on a random forest model.

[0010] The smart wearable device outputs a nerve stimulation signal according to the inhibition parameter.

[0011] In combination with the first aspect, in some embodiments, the method further includes:

[0012] The monitoring device collects the user's tremor change information in real time and sends it to the first server;

[0013] The first server adjusts the suppression parameter according to the tremor change information using a pre-designed closed-loop control model to obtain the adjusted suppression parameter and sends the adjusted suppression parameter to the smart wearable device;

[0014] Accordingly, the smart wearable device performs nerve stimulation on the user according to the inhibition parameter, including:

[0015] The smart wearable device performs neural stimulation on the user according to the adjusted inhibition parameters.

[0016] In conjunction with the first aspect, in some embodiments, the first server adjusts the suppression parameter using a pre-designed closed-loop control model according to the tremor change information to obtain the adjusted suppression parameter, including:

[0017] The first server performs fuzzification processing on the tremor change information to obtain fuzzy information;

[0018] The first server determines an adjustment variable according to a preset fuzzy rule and the fuzzified information, wherein the adjustment variable is used to adjust the suppression parameter;

[0019] The first server performs defuzzification processing on the adjustment variable to obtain a defuzzified adjustment variable;

[0020] The first server adjusts the suppression parameter according to the defuzzified adjustment variable to obtain the adjusted suppression parameter.

[0021] In combination with the first aspect, in some embodiments, the method further includes:

[0022] The second server acquires a data set, wherein the data set includes tremor data and nerve stimulation data of at least one user;

[0023] The second server pre-trains the data set and divides the data set into a training set and a test set according to a preset ratio;

[0024] The second server trains the forest model according to the training set using a preset optimization algorithm to obtain an initial tremor suppression model.

[0025] In combination with the first aspect, in some embodiments, the method further includes:

[0026] The second server tests and adjusts the initial tremor suppression model according to the test set until a mean square error of an output of the adjusted initial tremor suppression model is less than a preset mean square error threshold, and then determines the adjusted initial tremor suppression model as the tremor suppression model.

[0027] In combination with the first aspect, in some embodiments, the method further includes:

[0028] If the target method is a voice prompt method, the first server generates voice prompt information according to the tremor characteristics and sends it to the smart wearable device, where the voice prompt information is used to prompt the user to adjust posture and correct movement;

[0029] The smart wearable device provides a voice prompt to the user according to the voice prompt information.

[0030] In conjunction with the first aspect, in some embodiments, the first server determines, based on the tremor amplitude and a preset amplitude threshold, a target method for reducing the user's tremor, including:

[0031] If the vibration amplitude is less than the amplitude threshold, the first server determines the voice prompt method as the target method;

[0032] If the tremor amplitude is greater than the amplitude threshold, the first server determines the nerve stimulation method as the target method.

[0033] In combination with the first aspect, in some embodiments, the smart wearable device collects tremor characteristics of the user, including:

[0034] The smart wearable device acquires sensor data in real time, wherein the sensor data is upper limb motion data of the user collected based on a pre-set fusion sensor;

[0035] The smart wearable device preprocesses the sensor data to obtain processed sensor data;

[0036] The smart wearable device performs feature extraction on the processed sensor data using a wavelet transform algorithm to obtain the tremor feature.

[0037] In a second aspect, the present application provides a processing device for a smart wearable device for alleviating upper limb tremor, comprising:

[0038] A first acquisition module is configured to use the smart wearable device to acquire tremor characteristics of the user and send the collected tremor characteristics to the first server, where the tremor characteristics include tremor frequency and tremor amplitude;

[0039] a determination module, configured for the first server to determine a target method for alleviating the user's tremor based on the tremor amplitude and a preset amplitude threshold, the target method including a voice prompt method or a nerve stimulation method;

[0040] a prediction module configured to, if the target method is a neural stimulation method, cause the first server to analyze and predict the tremor characteristics based on the tremor characteristics using a pre-trained tremor suppression model to obtain suppression parameters, and send the obtained suppression parameters to the smart wearable device, wherein the suppression parameters are used to perform neural stimulation on the user to reduce limb tremor, and the tremor suppression model is trained based on a random forest model;

[0041] An output module is used for the smart wearable device to output a neural stimulation signal according to the inhibition parameter.

[0042] In conjunction with the second aspect, in some embodiments, the apparatus further includes:

[0043] a second collection module, configured to collect tremor change information of the user in real time using a monitoring device, and send the information to the first server;

[0044] an adjustment module, configured for the first server to adjust the suppression parameter according to the tremor change information through a pre-designed closed-loop control model, obtain the adjusted suppression parameter, and send the adjusted suppression parameter to the smart wearable device;

[0045] Accordingly, the output module includes:

[0046] An output unit is used for the smart wearable device to output a nerve stimulation signal according to the adjusted inhibition parameter.

[0047] In conjunction with the second aspect, in some embodiments, the adjustment module includes:

[0048] a fuzzification unit configured to perform fuzzy processing on the tremor change information by the first server to obtain fuzzy information;

[0049] a determining unit, configured for the first server to determine an adjustment variable according to a preset fuzzy rule and the fuzzified information, wherein the adjustment variable is used to adjust the suppression parameter;

[0050] A defuzzification unit, configured for the first server to perform defuzzification processing on the adjustment variable to obtain a defuzzified adjustment variable;

[0051] An adjusting unit is configured to enable the first server to adjust the suppression parameter according to the defuzzified adjustment variable to obtain the adjusted suppression parameter.

[0052] In conjunction with the second aspect, in some embodiments, the apparatus further includes:

[0053] An acquisition module, configured to acquire, by a second server, a data set including tremor data and nerve stimulation data of at least one user;

[0054] a processing module, configured for the second server to preprocess the data set and divide it into a training set and a test set according to a preset ratio;

[0055] A training module is used for the second server to train the forest model according to the training set through a preset optimization algorithm to obtain an initial tremor suppression model.

[0056] In conjunction with the second aspect, in some embodiments, the apparatus further includes:

[0057] and a test adjustment module configured to cause the second server to test and adjust the initial tremor suppression model according to the test set until a mean square error (MSE) of an output of the adjusted initial tremor suppression model is less than a preset MSE threshold, and then determine the adjusted initial tremor suppression model as the tremor suppression model.

[0058] In conjunction with the second aspect, in some embodiments, the apparatus further includes:

[0059] a generating module configured to, if the target method is a voice prompt method, cause the first server to generate voice prompt information based on the tremor characteristics and send the generated voice prompt information to the smart wearable device, wherein the voice prompt information is used to prompt the user to adjust posture and correct movement;

[0060] A voice prompt module is used for the smart wearable device to provide voice prompts to the user according to the voice prompt information.

[0061] In conjunction with the second aspect, in some embodiments, the determining module includes:

[0062] a first determining unit, configured to, if the tremor amplitude is less than the amplitude threshold, determine, by the first server, the voice prompt method as the target method;

[0063] The second determining unit is configured to, if the tremor amplitude is greater than the amplitude threshold, enable the first server to determine the nerve stimulation method as the target method.

[0064] In conjunction with the second aspect, in some embodiments, the first acquisition module includes:

[0065] an acquisition unit, configured to acquire sensor data in real time from the smart wearable device, wherein the sensor data is upper limb motion data of the user collected based on a pre-set fusion sensor;

[0066] a preprocessing unit, configured for the smart wearable device to preprocess the sensor data to obtain processed sensor data;

[0067] A feature extraction unit is used for the smart wearable device to extract features from the processed sensor data using a wavelet transform algorithm to obtain the tremor feature.

[0068] In a third aspect, the present application provides an intelligent wearable device, comprising: a processor, a memory communicatively connected to the processor, and a fusion sensor;

[0069] The memory stores computer-executable instructions;

[0070] The processor executes the computer-executable instructions stored in the memory to implement the processing method of the smart wearable device for reducing upper limb tremor described in any one of the first aspects.

[0071] In a fourth aspect, the present application provides a tremor control system, comprising: a smart wearable device, a first server, a second server, a monitoring device, and a user's terminal device; the smart wearable device, the first server, the second server, and the monitoring device are communicatively connected, and the smart wearable device, the monitoring device, the first server, and the terminal device are communicatively connected; and is used to execute the processing method for alleviating upper limb tremor of the smart wearable device described in any one of the first aspects.

[0072] In a fifth aspect, the present application provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement the processing method of the smart wearable device for reducing upper limb tremor described in any one of the first aspects.

[0073] In a sixth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the processing method for reducing upper limb tremor in an intelligent wearable device described in any one of the first aspects.

[0074] This application provides a processing method and system for a smart wearable device for reducing upper limb tremor. The smart wearable device collects a user's tremor characteristics and sends them to a first server. The first server determines a target method for reducing the user's tremor based on the tremor amplitude and a pre-set amplitude threshold. If the target method is a neural stimulation method, the first server analyzes and predicts the tremor characteristics using a pre-trained tremor suppression model, obtains suppression parameters, and sends them to the smart wearable device. This method suppresses upper limb tremor in Parkinson's patients, helping them recover while also providing convenience. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0076] Figure 1 This is a diagram of an application scenario of a processing method for a smart wearable device for alleviating upper limb tremor provided in an embodiment of the present application;

[0077] Figure 2 A flowchart of a first embodiment of a processing method for a smart wearable device for alleviating upper limb tremor provided in an embodiment of the present application;

[0078] Figure 3 A flowchart of a second embodiment of a processing method for a smart wearable device for alleviating upper limb tremor provided in an embodiment of the present application;

[0079] Figure 4 A flowchart of a third embodiment of a processing method for a smart wearable device for alleviating upper limb tremor provided in an embodiment of the present application;

[0080] Figure 5 A flowchart of a fourth embodiment of a processing method for a smart wearable device for alleviating upper limb tremor provided in an embodiment of the present application;

[0081] Figure 6 A flowchart of a fifth embodiment of a processing method for a smart wearable device for alleviating upper limb tremor provided in an embodiment of the present application;

[0082] Figure 7 This is a structural diagram of a first embodiment of a processing device for an intelligent wearable device for alleviating upper limb tremor provided in an embodiment of the present application;

[0083] Figure 8 This is a structural diagram of a second embodiment of a processing device for an intelligent wearable device for alleviating upper limb tremor provided in an embodiment of the present application;

[0084] Figure 9 This is a schematic structural diagram of a third embodiment of a processing device for an intelligent wearable device for alleviating upper limb tremor provided in an embodiment of the present application;

[0085] Figure 10 This is a structural diagram of a fourth embodiment of a processing device for an intelligent wearable device for alleviating upper limb tremor provided in an embodiment of the present application;

[0086] Figure 11 This is a structural diagram of a fifth embodiment of a processing device for an intelligent wearable device for alleviating upper limb tremor provided in an embodiment of the present application;

[0087] Figure 12 This is a structural diagram of a sixth embodiment of a processing device for an intelligent wearable device for alleviating upper limb tremor provided in an embodiment of the present application;

[0088] Figure 13 A schematic diagram of the structure of the smart wearable device provided in an embodiment of the present application;

[0089] Figure 14 A schematic diagram of the architecture of a vibration control system provided in an embodiment of the present application.

[0090] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0091] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0092] Parkinson's disease (PD), also known as Parkinson's syndrome. Parkinson's syndrome is a chronic degenerative disorder of the central nervous system. Parkinson's patients usually have varying degrees of movement disorder symptoms, clinically characterized by resting tremor, bradykinesia, muscle rigidity and posture and gait disorders. The above characteristics make it impossible for patients to take care of themselves normally in daily life, so the cure for Parkinson's disease has become a major research goal. At present, the treatment of Parkinson's disease is divided into drug therapy and physical therapy. Although drug therapy is the mainstream treatment method, it also has the risk of misdiagnosis and drug side effects. Although physical therapy seems to be a better method, it lacks suitable auxiliary tools to help patients better carry out treatment and be able to persist in it for a long time. Therefore, how to suppress the tremor of the upper limbs of Parkinson's patients is a technical problem that urgently needs to be solved in this field.

[0093] To address the above-mentioned issues, the present application provides a processing method and system for a smart wearable device for alleviating upper limb tremor, thereby suppressing upper limb tremor in Parkinson's disease patients. Specifically, Parkinson's disease has become a serious threat to the health of middle-aged and elderly people. Parkinson's disease patients typically experience varying degrees of movement disorders, which not only affect their body posture but also have significant negative effects on their daily living abilities and quality of life, such as decreased upper limb movement initiative, physical discomfort, limited daily activities, emotional communication, and cognitive impairment. Treatment for Parkinson's disease is divided into medication and physical therapy. Although medication is currently the mainstream treatment method, it also carries the risk of misdiagnosis and drug side effects. While physical therapy appears to be a better method, it lacks appropriate auxiliary tools to help patients better carry out treatment and maintain long-term adherence. Considering these issues, the inventors investigated whether a tremor suppression system could analyze and predict the patient's tremor characteristics collected in real time, thereby generating suppression parameters that can suppress the patient's upper limb tremor. They then designed a smart wearable device that stimulates the patient's nerves based on the suppression parameters to achieve tremor suppression, thereby facilitating the patient's daily life.

[0094] Figure 1 This is an application scenario diagram of the processing method for alleviating upper limb tremor in an intelligent wearable device provided in an embodiment of the present application, such as Figure 1As shown, the scenario includes at least one Parkinson's patient and a tremor suppression system, wherein the tremor suppression system includes at least a smart wearable device, a first server, a monitoring device and a terminal device. The Parkinson's patient can wear the smart wearable device, which can be a smart glove, a smart bracelet, a smart ring, etc. The Parkinson's patient also holds a terminal device, which can communicate data with the smart wearable device and the monitoring device. The terminal device can be an electronic device such as a smart phone. The smart wearable device is equipped with a fusion sensor, such as a gyroscope, an accelerometer, etc., which can collect tremor data of the Parkinson's patient's upper limb in real time and then send it to the first server. The first server can analyze and predict the tremor data according to a pre-configured tremor suppression model, thereby obtaining suppression parameters and sending them to the smart wearable device. The smart wearable device outputs a neural stimulation signal according to the suppression parameters, and then the neural stimulation signal can stimulate the Parkinson's patient, thereby achieving tremor suppression.

[0095] In one possible implementation, while the neural stimulation signal suppresses the tremor of the Parkinson's patient, the monitoring device monitors the tremor changes of the Parkinson's patient in real time, and then sends the patient's tremor changes to the first server. The first server can adjust the suppression parameters according to the patient's tremor changes, thereby preventing insufficient or excessive tremor suppression, facilitating the patient's daily life, and also providing rehabilitation assistance to the patient.

[0096] It should be noted that the terminal device can obtain the tremor data of Parkinson's patients and related records of tremor suppression in real time, so that patients can view their own health information, and patients can also adjust the configuration information of smart wearable devices through the terminal device.

[0097] Optionally, the tremor suppression system may further include a second server, which may configure a tremor suppression model for the first server and may pre-train the tremor suppression model.

[0098] This embodiment does not specifically limit the specific forms of the specific physical devices mentioned above, and each device in the tremor suppression system can be an independent device, or the tremor suppression system can be configured in a smart wearable device or terminal device, and the other devices are modules therein.

[0099] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0100] Figure 2This is a flow chart of a first embodiment of a processing method for a smart wearable device for alleviating upper limb tremor provided in an embodiment of the present application. The method is applied to a tremor suppression system, which includes a smart wearable device, a first server, a second server, a monitoring device, and a user's terminal device. The smart wearable device, the first server, the second server, and the monitoring device are communicatively connected, and the smart wearable device, the monitoring device, the first server, and the terminal device are communicatively connected. The method specifically includes:

[0101] S201: The smart wearable device collects tremor characteristics of the user and sends the data to a first server.

[0102] In this step, in order to help Parkinson's patients get rid of the inconvenience in life caused by upper limb tremors, some methods can be used to suppress the user's tremors. It is necessary to analyze the user's tremors. The user's tremors can be collected in real time through the smart wearable device worn by the user, and then sent to the first server. The tremor characteristics include tremor frequency and tremor amplitude.

[0103] Specifically, the smart wearable device acquires sensor data in real time, then preprocesses the sensor data to obtain processed sensor data, and finally extracts features from the processed sensor data using a wavelet transform algorithm to obtain tremor features.

[0104] S202: The first server determines a target method for reducing user tremor according to the tremor amplitude and a preset amplitude threshold.

[0105] In this step, after the first server receives the tremor characteristics sent by the smart wearable device, in order to suppress the user's tremor, it determines a target method for reducing the user's tremor based on the tremor amplitude and a pre-set amplitude threshold, where the target method includes a voice prompt method or a neural stimulation method.

[0106] Specifically, the tremor amplitude represents the degree of the user's tremor. If the user's tremor is mild, that is, the tremor amplitude is less than the amplitude threshold, it means that the user's symptoms are mild. The user can suppress the tremor by adjusting his or her own movement form or posture. Therefore, the voice prompt method is determined as the target method.

[0107] If the user's tremor is severe, that is, the tremor amplitude is greater than the amplitude threshold, it means that the user's symptoms are severe and the user cannot suppress the tremor by adjusting his or her own movement form or posture. In this case, the neural stimulation method is determined as the target method.

[0108] S203: If the target method is a nerve stimulation method, the first server analyzes and predicts the tremor characteristics according to the tremor characteristics using a pre-trained tremor suppression model, obtains suppression parameters, and sends them to the smart wearable device.

[0109] In this step, if the user is unable to suppress tremor by adjusting their movement or posture, meaning the target method is neural stimulation, the first server analyzes and predicts the tremor characteristics using a pre-trained tremor suppression model, obtains suppression parameters, and sends them to the smart wearable device. These suppression parameters are used to stimulate the user's nerves to reduce limb tremor. The tremor suppression model is trained using a random forest model.

[0110] S204: The smart wearable device outputs a nerve stimulation signal according to the inhibition parameter.

[0111] In this step, after obtaining the inhibition parameters, the smart wearable device receives the inhibition parameters sent by the first server, and generates a nerve stimulation signal that can stimulate the user's nerves by analyzing the inhibition parameters.

[0112] Optionally, the smart wearable device can stimulate the user's nerves according to the nerve stimulation signal, thereby suppressing tremors.

[0113] Optionally, the method further includes:

[0114] S205: If the target method is a voice prompt method, the first server generates voice prompt information according to the tremor characteristics and sends it to the smart wearable device.

[0115] In this step, if the user's tremor amplitude is small, the tremor can be suppressed by adjusting one's own movement form or posture. That is, the target method is a voice prompt method. Therefore, the first server generates a voice prompt message based on the tremor characteristics and sends it to the smart wearable device. The voice prompt message is used to prompt the user to adjust the posture and correct the movement.

[0116] S206: The smart wearable device provides a voice prompt to the user according to the voice prompt information.

[0117] In this step, after receiving the voice prompt information, the smart wearable device can provide voice prompts to the user according to the voice prompt information, thereby suppressing tremors.

[0118] For example, smart wearable devices can emit vibration or sound prompts to remind patients to adjust their posture or perform specific exercises. These prompts can help patients reduce the discomfort caused by tremors and help them better manage their symptoms.

[0119] This embodiment provides a processing method for a smart wearable device for reducing upper limb tremor. The smart wearable device collects a user's tremor characteristics and sends them to a first server. The first server then determines a target method for reducing the user's tremor based on the tremor amplitude and a pre-set amplitude threshold. If the target method is neural stimulation, the first server analyzes and predicts the tremor characteristics using a pre-trained tremor suppression model, obtains suppression parameters, and sends them to the smart wearable device. This method suppresses upper limb tremor in Parkinson's patients, helping them recover while also providing convenience.

[0120] Figure 3 This is a flow chart of a second embodiment of a processing method for a smart wearable device for alleviating upper limb tremor provided in an embodiment of the present application, as shown in FIG. Figure 3 As shown, based on the above embodiment, it specifically includes:

[0121] S301: The monitoring device collects the user's tremor change information in real time and sends it to the first server.

[0122] In this step, based on the above embodiment, after the smart wearable device generates a neural stimulation signal, the upper limb tremor of the patient user is suppressed by the neural stimulation signal, so that the tremor information of the patient user will change. The monitoring device monitors the tremor changes of the patient user in real time, and collects the user's tremor change information in real time and sends it to the first server.

[0123] Specifically, the monitoring device is equipped with a sensor, which collects tremor change information through the sensor. In order to accurately monitor the tremor changes of the patient user, a sensor with higher sensitivity needs to be configured. This embodiment does not specifically limit the specific model of the sensor, as long as it can meet the requirements of accurately collecting the tremor change information of the patient user.

[0124] S302: The first server adjusts the suppression parameters according to the tremor change information through a pre-designed closed-loop control model, obtains the adjusted suppression parameters, and sends them to the smart wearable device.

[0125] In this step, after obtaining the tremor change information of the patient user, in order to accurately suppress the patient user's upper limb tremor and avoid insufficient or excessive suppression, the generated suppression parameters are adjusted through a pre-designed closed-loop control model, and then the adjusted suppression parameters are generated and sent to the smart wearable device.

[0126] Specifically, the tremor change information is first fuzzified to obtain fuzzy information, and then the adjustment variable is determined according to the pre-set fuzzy rules and fuzzy information. The adjustment variable is then defuzzified to obtain the defuzzified adjustment variable. Finally, the suppression parameter is adjusted according to the defuzzified adjustment variable to obtain the adjusted suppression parameter.

[0127] Correspondingly, after the smart wearable device receives the adjusted suppression parameter sent by the first server, based on the above embodiment, step S204 includes:

[0128] S303: The smart wearable device outputs a nerve stimulation signal according to the adjusted inhibition parameter.

[0129] In this step, by adjusting the suppression parameters through the closed-loop control model, the patient's upper limb tremor can be better suppressed and over-suppression can be avoided. The smart wearable device then outputs a neural stimulation signal based on the adjusted suppression parameters.

[0130] This embodiment provides a processing method for a smart wearable device for alleviating upper limb tremor. A monitoring device collects real-time tremor change information from a user and transmits it to a first server. Based on this tremor change information, the first server adjusts a suppression parameter using a pre-designed closed-loop control model. The server then transmits the adjusted suppression parameter to the smart wearable device, which then outputs a neural stimulation signal based on the adjusted suppression parameter. This method dynamically adjusts the suppression parameter, thereby better suppressing a patient's upper limb tremor and providing convenience for the patient's daily life.

[0131] Figure 4 This is a flow chart of a third embodiment of a processing method for a smart wearable device for alleviating upper limb tremor provided in an embodiment of the present application, as shown in FIG. Figure 4 As shown, based on the above embodiments, step S302 specifically includes:

[0132] S401: The first server performs fuzzy processing on the vibration change information to obtain fuzzy information.

[0133] In this step, after the monitoring device sends the tremor change information to the first server, in order to avoid excessive or insufficient suppression of the user's tremor, the suppression parameters need to be adaptively adjusted, which can be optimized and adjusted through a pre-designed closed-loop control model. First, the tremor change information needs to be fuzzy processed to obtain fuzzy information.

[0134] Specifically, the tremor change information is fuzzified, that is, specific numerical values ​​are converted into fuzzy concepts, such as "low", "medium", "high", etc.

[0135] S402: The first server determines an adjustment variable according to pre-set fuzzy rules and fuzzified information.

[0136] In this step, after the fuzzy information is obtained, the suppression parameter can be adjusted according to the fuzzy information to obtain the adjustment variable.

[0137] Specifically, fuzzy rules are predefined to describe the relationship between input and output variables. For example, the input variables could be the frequency and amplitude of a tremor, and the output variable could be the adjustment of a suppression parameter. Based on the defined fuzzy rules, fuzzy reasoning is performed to infer the fuzzy value of the output variable, or adjustment variable, from the fuzzified information. This is typically achieved using fuzzy logic operations such as fuzzy AND and fuzzy OR.

[0138] S403: The first server performs defuzzification processing on the adjustment variable to obtain a defuzzified adjustment variable.

[0139] S404: The first server adjusts the suppression parameter according to the defuzzified adjustment variable to obtain an adjusted suppression parameter.

[0140] After obtaining the adjustment variable, in order to adjust the suppression parameter according to the adjustment variable, the adjustment parameter needs to be defuzzified, and the suppression parameter is adjusted through the defuzzified adjustment variable to obtain the adjusted suppression parameter.

[0141] Optionally, specific implementation methods of converting the adjustment variable obtained by fuzzy reasoning into a specific parameter adjustment amount include:

[0142] The first method is to convert the membership function of the adjustment variable into a standard digital form. The membership function describes the distribution of the fuzzy output values ​​within the range of the adjustment variable, usually expressed in the form of a triangle, trapezoid, or Gaussian curve.

[0143] The second method: First, you need to calculate the product of the fuzzy output value under each membership function and the corresponding value point, and then perform weighted average on these product values ​​to obtain a weighted average as the final output.

[0144] It should be noted that the specific method of defuzzification is not specifically limited in this embodiment.

[0145] This embodiment provides a method for reducing upper limb tremor in a smart wearable device. A first server fuzzifies tremor change information to obtain fuzzified information. Then, based on pre-defined fuzzy rules and the fuzzified information, it determines an adjustment variable. The adjustment variable is then defuzzified to obtain a defuzzified adjustment variable. Finally, a suppression parameter is adjusted based on the defuzzified adjustment variable to obtain an adjusted suppression parameter. By designing a closed-loop control model and implementing fuzzy control to adjust the suppression parameter, the suppression parameter can be used to more accurately suppress a patient's upper limb tremor.

[0146] Figure 5 This is a flow chart of a fourth embodiment of a processing method for a smart wearable device for alleviating upper limb tremor provided in an embodiment of the present application, as shown in FIG. Figure 5 As shown, based on the above embodiments, the method includes:

[0147] S501: The second server obtains a data set.

[0148] In this step, in order to obtain a model that can accurately predict the inhibition parameters, it is necessary to select an adaptive basic model for training. It is necessary to train based on the user's relevant data.

[0149] Specifically, the second server is used to train the model, and the second server obtains a data set through the user's terminal device, wherein the data set includes tremor data and nerve stimulation data of at least one user.

[0150] Optionally, the tremor data may include tremor data of Parkinson's patients and related physiological signal data, such as electromyography, accelerometer data, etc.

[0151] S502: The second server preprocesses the data set and divides it into a training set and a test set according to a preset ratio.

[0152] In this step, after obtaining the data set, the second server needs to pre-process the data in the data set and divide it into proportions to obtain a training set and a test set.

[0153] Specifically, preprocessing includes operations such as data cleaning, denoising, and feature extraction, and the data is divided according to a pre-set ratio, for example, 50% as a training set and 50% as a test set.

[0154] S503: The second server trains the forest model according to the training set using a preset optimization algorithm to obtain an initial tremor suppression model.

[0155] In this step, since the random forest model has the characteristics of high accuracy, resistance to overfitting, and multi-feature processing, and thus has good predictive ability for suppressing tremors in Parkinson's patients, the random forest model is trained using a training set. During the training process, the model parameters can be optimized using a pre-set optimization algorithm, such as a particle swarm algorithm, a genetic algorithm, an ant colony algorithm, a simulated annealing algorithm, and the like.

[0156] Specifically, the training data is labeled with the corresponding suppression parameters based on their settings and actual effects. For example, the data can be divided into different categories or labels based on the strength or frequency of the suppression parameters. The labeled training set is then used to train the random forest model. During training, the random forest learns the complex relationship between tremor data and physiological signal data and the suppression parameters based on the input features, thereby establishing an initial tremor suppression model that predicts the suppression parameters.

[0157] S504: The second server tests and adjusts the initial tremor suppression model according to the test set until the mean square error of the output of the adjusted initial tremor suppression model is less than a preset mean square error threshold, and then determines the adjusted initial tremor suppression model as the tremor suppression model.

[0158] In this step, after the initial tremor suppression model is obtained, in order to make the model prediction ability more accurate, the initial tremor model is verified and adjusted through the test set, thereby obtaining the tremor suppression model.

[0159] Specifically, the test set is input into the initial tremor suppression model for analysis and prediction to obtain the output suppression parameters, and the mean square error (MSE) between the output suppression parameters and the actual parameters is calculated. If the MSE is greater than the preset MSE threshold, it means that the prediction ability of the model cannot meet user needs. In this case, the initial tremor suppression model needs to be adjusted until the MSE is less than the MSE threshold, and finally the tremor suppression model is obtained.

[0160] In the processing method for reducing upper limb tremor provided by this embodiment, a second server obtains a dataset, preprocesses the dataset, and divides it into a training set and a test set according to a preset ratio. Then, a forest model is trained based on the training set using a preset optimization algorithm to obtain an initial tremor suppression model. Finally, the initial tremor suppression model is tested and adjusted based on the test set until the mean square error (MSE) of the output of the adjusted initial tremor suppression model is less than a preset MSE threshold. The adjusted initial tremor suppression model is then determined as the tremor suppression model. By training the random forest model, suppression parameters that can accurately predict a patient user are obtained, and upper limb tremor suppression can be achieved using the suppression parameters.

[0161] Figure 6This is a flow chart of a fifth embodiment of a processing method for a smart wearable device for alleviating upper limb tremor provided in an embodiment of the present application, as shown in FIG. Figure 6 As shown, based on the above embodiments, step S201 specifically includes:

[0162] S601: The smart wearable device obtains sensor data in real time.

[0163] In this step, in order to accurately suppress the patient's upper limb tremor, thereby ensuring that the patient can live a normal life and assist the patient in rehabilitation treatment, it is necessary to collect the user's tremor information in real time.

[0164] Specifically, the smart wearable device is equipped with a sensor, which collects sensor data in real time. The sensor data is upper limb motion data of the user collected based on a pre-set fusion sensor, and the upper limb motion data includes tremor information of the user.

[0165] It should be noted that the fusion sensors configured in smart wearable devices may include accelerometers, gyroscopes, etc.

[0166] S602: The smart wearable device preprocesses the sensor data to obtain processed sensor data.

[0167] S603: The smart wearable device performs feature extraction on the processed sensor data using a wavelet transform algorithm to obtain tremor features.

[0168] After acquiring the sensor data, in order to ensure the accuracy of the data, the sensor data is preprocessed, such as removing duplicate data, missing data, and abnormal data, and then normalized to obtain processed sensor data. In order to obtain accurate tremor data, the processed sensor data is subjected to feature extraction through wavelet transform to obtain tremor features, which include tremor frequency and tremor amplitude.

[0169] Specifically, for the feature extraction process, it is necessary to first select a wavelet basis function, such as Haar wavelet, Daubechies wavelet, Morlet wavelet, etc., and then use the selected wavelet basis function to decompose the processed sensor data to obtain wavelet coefficients at different scales, and then extract the tremor features from the wavelet coefficients.

[0170] It should be noted that this embodiment does not impose any specific restrictions on the specific type of wavelet basis function, and it can be selected according to actual scenarios.

[0171] This embodiment provides a processing method for a smart wearable device for alleviating upper limb tremor. The smart wearable device acquires sensor data in real time, preprocesses the sensor data to obtain processed sensor data, and finally extracts features from the processed sensor data using a wavelet transform algorithm to obtain tremor signatures. By processing and extracting features from the sensor data collected from the patient, the patient's tremor condition is accurately determined, providing an accurate and robust data foundation for subsequent tremor suppression.

[0172] Optionally, a neuron model can be incorporated into the closed-loop control model design. Simulation experiments can then be conducted using the neuron model to evaluate the effects of different suppression parameters on the user's neuronal activity. This can then be used to predict the effect of the suppression parameters on the user's tremor. Based on the results from the neuron model, the closed-loop control model can be used to adjust the suppression parameters. By simulating changes in neuronal activity under different parameters, the closed-loop control model's parameter adjustment strategy can be optimized, thereby improving the suppression effect.

[0173] Specifically, a neuron model is first established. Commonly used models include biologically plausible neuron models such as the Hodgkin-Huxley model or simplified neuron models such as the Izhikevich model. Based on the user's clinical data and neurological characteristics, the model parameters are adjusted to ensure that it accurately reflects the patient's neuronal activity. A neuron network is constructed using the selected neuron model to simulate neuronal activity in the brains of Parkinson's patients. The neuron network simulation is run, and the simulation results, including neuronal firing patterns and synaptic transmission, are observed. Based on the simulation results of the neuron model, the parameters of the closed-loop control model are adjusted and optimized.

[0174] Figure 7 This is a structural diagram of a first embodiment of a processing device for a smart wearable device for alleviating upper limb tremor provided in an embodiment of the present application, as shown in FIG. Figure 7 As shown, a processing device 700 for a smart wearable device for alleviating upper limb tremor includes:

[0175] The first collection module 701 is configured to collect tremor characteristics of the user using the smart wearable device and send the collected tremor characteristics to the first server. The tremor characteristics include tremor frequency and tremor amplitude.

[0176] The determination module 702 is configured for the first server to determine a target method for alleviating the user's tremor based on the tremor amplitude and a preset amplitude threshold, where the target method includes a voice prompt method or a nerve stimulation method.

[0177] Prediction module 703 is used to, if the target method is a neural stimulation method, cause the first server to analyze and predict the tremor characteristics based on the tremor characteristics using a pre-trained tremor suppression model, obtain suppression parameters, and send them to the smart wearable device. The suppression parameters are used to perform neural stimulation on the user to reduce limb tremors. The tremor suppression model is trained based on a random forest model.

[0178] The output module 704 is used for the smart wearable device to output a nerve stimulation signal according to the inhibition parameter.

[0179] Optionally, the processing device 700 for the smart wearable device for alleviating upper limb tremor further includes:

[0180] The generating module 705 is used to generate voice prompt information according to the tremor characteristics and send it to the smart wearable device if the target method is the voice prompt method. The voice prompt information is used to prompt the user to adjust the posture and correct the movement.

[0181] The voice prompt module 706 is used for the smart wearable device to provide voice prompts to the user according to the voice prompt information.

[0182] Figure 8 This is a structural diagram of a second embodiment of a processing device for an intelligent wearable device for alleviating upper limb tremor provided in an embodiment of the present application, as shown in FIG. Figure 8 As shown, the processing device 700 of the smart wearable device for alleviating upper limb tremor further includes:

[0183] The second collection module 801 is used for the monitoring device to collect the user's tremor change information in real time and send it to the first server.

[0184] The adjustment module 802 is used for the first server to adjust the suppression parameters according to the tremor change information through a pre-designed closed-loop control model, obtain the adjusted suppression parameters, and send them to the smart wearable device.

[0185] Accordingly, the output module 704 includes:

[0186] The output unit is used for the smart wearable device to output a nerve stimulation signal according to the adjusted inhibition parameters.

[0187] Figure 9 This is a structural diagram of a third embodiment of a processing device for an intelligent wearable device for alleviating upper limb tremor provided in an embodiment of the present application, as shown in FIG. Figure 9 As shown, the adjustment module 802 includes:

[0188] The fuzzification unit 901 is configured to enable the first server to perform fuzzy processing on the tremor change information to obtain fuzzy information.

[0189] The determining unit 902 is configured to enable the first server to determine an adjustment variable according to a preset fuzzy rule and fuzzification information, where the adjustment variable is used to adjust the suppression parameter.

[0190] The defuzzification unit 903 is configured to perform defuzzification processing on the adjustment variable by the first server to obtain a defuzzified adjustment variable.

[0191] The adjusting unit 904 is configured to enable the first server to adjust the suppression parameter according to the defuzzified adjustment variable to obtain the adjusted suppression parameter.

[0192] Figure 10 This is a structural diagram of a fourth embodiment of a processing device for an intelligent wearable device for alleviating upper limb tremor provided in an embodiment of the present application, as shown in FIG. Figure 10 As shown, the processing device 700 of the smart wearable device for alleviating upper limb tremor further includes:

[0193] The acquisition module 1001 is configured to enable the second server to acquire a data set, where the data set includes tremor data and nerve stimulation data of at least one user.

[0194] The processing module 1002 is used for the second server to pre-process the data set and divide it into a training set and a test set according to a preset ratio.

[0195] The training module 1003 is used for the second server to train the forest model according to the training set using a preset optimization algorithm to obtain an initial tremor suppression model.

[0196] The test adjustment module 1004 is configured to enable the second server to test and adjust the initial tremor suppression model according to the test set until the mean square error of the output of the adjusted initial tremor suppression model is less than a preset mean square error threshold, and then determine the adjusted initial tremor suppression model as the tremor suppression model.

[0197] Figure 11 This is a structural diagram of a fifth embodiment of a processing device for an intelligent wearable device for alleviating upper limb tremor provided in an embodiment of the present application, as shown in FIG. Figure 11 As shown, the determination module 702 includes:

[0198] The first determining unit 1101 is configured to, if the tremor amplitude is less than an amplitude threshold, enable the first server to determine the voice prompt method as a target method.

[0199] The second determining unit 1102 is configured to, if the tremor amplitude is greater than the amplitude threshold, determine, by the first server, the neural stimulation method as the target method.

[0200] Figure 12This is a structural diagram of a sixth embodiment of a processing device for a smart wearable device for alleviating upper limb tremor provided in an embodiment of the present application, as shown in FIG. Figure 12 As shown, the first acquisition module 701 includes:

[0201] The acquisition unit 1201 is used for the smart wearable device to acquire sensor data in real time. The sensor data is the user's upper limb movement data collected based on a pre-set fusion sensor.

[0202] The preprocessing unit 1202 is used for the smart wearable device to preprocess the sensor data to obtain processed sensor data.

[0203] The feature extraction unit 1203 is used for the smart wearable device to extract features from the processed sensor data using a wavelet transform algorithm to obtain tremor features.

[0204] The processing devices for the smart wearable device for alleviating upper limb tremor provided in the above-mentioned embodiments are used to execute the processing methods for the smart wearable device for alleviating upper limb tremor in any of the above-mentioned method embodiments. The implementation principles and technical effects are similar and will not be repeated here.

[0205] Figure 13 A schematic diagram of the structure of a smart wearable device provided in an embodiment of the present application is shown, wherein the smart wearable device 1300 includes: a processor 1302, a memory 1301 communicatively connected to the processor 1302, and a fusion sensor 1303;

[0206] The memory 1301 stores computer-executable instructions.

[0207] The processor 1302 executes the computer-executable instructions stored in the memory 1301 to implement the processing method of the smart wearable device for reducing upper limb tremor in any of the aforementioned method embodiments.

[0208] The fusion sensor 1303 is used to collect the user's tremor characteristics and tremor change information in real time.

[0209] Figure 14 This is a schematic diagram of the architecture of a tremor control system provided in an embodiment of the present application. The tremor control system 1400 includes:

[0210] Smart wearable device 1300, first server 1401, second server 1402, monitoring device 1403 and user's terminal device 1404, wherein the smart wearable device 1300, first server 1401, second server 1402 and monitoring device 1403 are communicatively connected, and the smart wearable device 1300, monitoring device 1403, first server 1401 and terminal device 1404 are communicatively connected. The system is used to execute the processing method for alleviating upper limb tremor of the smart wearable device in any of the aforementioned method embodiments. The technical principles and technical effects implemented are similar and will not be repeated here.

[0211] An embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement the processing method of the smart wearable device for reducing upper limb tremor in any embodiment.

[0212] The computer-readable storage medium may be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic storage, flash memory, magnetic disk, or optical disk. The computer-readable storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0213] Optionally, a readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0214] An embodiment of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when at least one processor executes the computer program, it can implement the technical solution provided by any of the above method embodiments.

[0215] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0216] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A tremor suppression system, characterized in that: The system comprises a smart wearable device, a first server, a second server, a monitoring device, and a user's terminal device; the smart wearable device, the first server, the second server, and the monitoring device are communicatively connected, the smart wearable device, the monitoring device, the first server, and the terminal device are communicatively connected, and the wearable device is worn on the upper limb of the patient user; The smart wearable device collects tremor characteristics of the user and sends the tremor characteristics to the first server, where the tremor characteristics include tremor frequency and tremor amplitude, and the tremor characteristics are determined based on upper limb motion data collected from the upper limb; The first server determines a target method for alleviating the user's tremor based on the tremor amplitude and a preset amplitude threshold, including: If the vibration amplitude is less than the amplitude threshold, the first server determines the voice prompt method as the target method; If the tremor amplitude is greater than the amplitude threshold, the first server determines the neural stimulation method as the target method; If the target method is a neural stimulation method, the first server analyzes and predicts the tremor characteristics based on the tremor characteristics using a pre-trained tremor suppression model to obtain suppression parameters, and sends the obtained suppression parameters to the smart wearable device. The suppression parameters are used to perform neural stimulation on the user to reduce limb tremors. The tremor suppression model is trained based on a random forest model, and the tremor suppression model is trained in the second server and deployed in the first server. The smart wearable device outputs a nerve stimulation signal according to the inhibition parameter; The monitoring device collects the user's tremor change information in real time and sends it to the first server; The first server adjusts the suppression parameter according to the tremor change information by using a pre-designed closed-loop control model combined with a pre-set neuron model, obtains the adjusted suppression parameter, and sends the adjusted suppression parameter to the smart wearable device; The neuron model is obtained by adjusting parameters based on clinical data and neurological characteristics, and is used to simulate the user's neuron activity state; Accordingly, the inhibition parameter is adjusted by combining the pre-designed closed-loop control model with the pre-set neuron model to obtain the adjusted inhibition parameter, including: simulating the user's neuron activity based on the neuron model to obtain a simulation result; Adjusting and optimizing the parameters of the closed-loop control model based on the simulation results to obtain an adjusted closed-loop control model; Adjusting the suppression parameter based on the adjusted closed-loop control model to obtain the adjusted suppression parameter; Accordingly, the smart wearable device outputs a nerve stimulation signal according to the inhibition parameter, including: The smart wearable device outputs a neural stimulation signal according to the adjusted inhibition parameter; The smart wearable device collects tremor characteristics of the user, including: The smart wearable device acquires sensor data in real time, wherein the sensor data is upper limb motion data of the user collected based on a pre-set fusion sensor; The smart wearable device preprocesses the sensor data to obtain processed sensor data; The smart wearable device performs feature extraction on the processed sensor data using a wavelet transform algorithm to obtain the tremor feature.

2. The system according to claim 1, wherein: The first server adjusts the suppression parameter according to the tremor change information using a pre-designed closed-loop control model to obtain the adjusted suppression parameter, including: The first server performs fuzzification processing on the tremor change information to obtain fuzzy information; The first server determines an adjustment variable according to a preset fuzzy rule and the fuzzified information, wherein the adjustment variable is used to adjust the suppression parameter; The first server performs defuzzification processing on the adjustment variable to obtain a defuzzified adjustment variable; The first server adjusts the suppression parameter according to the defuzzified adjustment variable to obtain the adjusted suppression parameter.

3. The system according to claim 1, wherein: The second server acquires a data set, wherein the data set includes tremor data and nerve stimulation data of at least one user; The second server preprocesses the data set and divides it into a training set and a test set according to a preset ratio; The second server trains the forest model according to the training set using a preset optimization algorithm to obtain an initial tremor suppression model.

4. The system according to claim 3, characterized in that The second server tests and adjusts the initial tremor suppression model according to the test set until a mean square error of an output of the adjusted initial tremor suppression model is less than a preset mean square error threshold, and then determines the adjusted initial tremor suppression model as the tremor suppression model.

5. The system according to claim 1, wherein: If the target method is a voice prompt method, the first server generates voice prompt information according to the tremor characteristics and sends it to the smart wearable device, where the voice prompt information is used to prompt the user to adjust posture and correct movement; The smart wearable device provides a voice prompt to the user according to the voice prompt information.

Images