TWI828462B - Intelligent pressure-relief equipment and controlling method thereof - Google Patents

Abstract

An intelligent pressure-relief equipment and a controlling method thereof are provided. The intelligent pressure-relief equipment includes a pressure-relief device, a sensing device and a processing device. The pressure-relief device is used for performing a pressure relief function on a user. The sensing device is used for sensing at least one physiological signal of the user. The processing device includes a prediction unit, a parameter analysis unit and a control unit. The prediction unit is used for predicting an emotional state and a muscle state of the user in the future according to the physiological signal. The parameter analysis unit is used for analyzing at least one control parameter according to the user's emotional state and muscle state. The control unit is used for controlling the pressure-relief device to perform the pressure relief function according to the control parameters.

Description

Intelligent stress relief equipment and control method

The present disclosure relates to an electronic device and a control method thereof, and in particular, to an intelligent stress relief device and a control method thereof.

Modern people's lives are stressful, and more and more people need various massage and stress relief devices to relax their body and mind. However, these massage and stress-relieving equipment simply perform the stress-relieving function according to the set parameters without taking into account the user's feelings. Each user may experience the same level of compression differently. In order for massage and stress relief equipment to provide the most comfortable experience, researchers are working hard to develop an intelligent stress relief device to achieve more effective relaxation and stress relief effects.

The present disclosure relates to an intelligent stress relief device and a control method thereof. When the user uses the stress relief device, the sensing device can sense the user's current physiological signals. The processing device can obtain muscle status and emotional status based on physiological signals. The analysis of control parameters takes into account not only muscle status, but also emotional status, making Stress relief devices not only allow users to relax their muscles, but also relax mentally. In addition, the machine learning model is trained using the different manual control signals of each user to provide personalized control parameters for different users.

According to one aspect of the present disclosure, an intelligent stress relief device is provided. The intelligent stress relief device includes a stress relief device, a sensing device and a processing device. The stress relief device is used to perform a stress relief function on a user. The sensing device is used to sense at least one physiological signal from the user. The processing device includes a prediction unit, a parameter analysis unit and a control unit. The prediction unit is used to predict the user's future emotional state and muscle state based on physiological signals. The parameter analysis unit is used to analyze at least one control parameter based on the user's future emotional state and muscle state. The control unit is used to control the stress relief device to perform the stress relief function according to the control parameters.

According to another aspect of the present disclosure, a control method of a stress relief device is provided. The control method of stress relief equipment includes the following steps. A stress relief device is used to perform a stress relief function on a user. Sensing at least one physiological signal to the user. Based on physiological signals, predict the user's future emotional state and muscle state. At least one control parameter is analyzed based on the user's future emotional state and the muscle state. The stress relief device is controlled to perform the stress relief function according to the control parameters.

In order to have a better understanding of the above and other aspects of the present disclosure, embodiments are given below and described in detail with reference to the accompanying drawings:

100,100’: Intelligent stress relief equipment

110: Stress relief device

120,120’: sensing device

130,130’: processing device

131: Prediction unit

132: Parameter analysis unit

133:Control unit

134:Storage unit

CM: automatic control signal

CMk: Manual control signal

ES: emotional state

PMj: control parameter

MD1, MD2, MD2k: machine learning models

MS:muscle status

S110, S120, S130, S140, S150, S160, S170: steps

Si: physiological signal

T0, T1, T2: time points

Figure 1 is a schematic diagram of a smart stress relief device according to an embodiment.

Figure 2 is a schematic diagram of a smart stress relief device according to another embodiment.

Figure 3 illustrates a block diagram of a smart stress relief device according to an embodiment.

Figure 4 illustrates a flow chart of a control method of a stress relief device according to an embodiment.

Figure 5 illustrates physiological signals, emotional states and muscle states.

Figure 6 illustrates a machine learning model and a machine learning model according to an embodiment.

Figure 7 illustrates a flow chart of a personalized training method for a machine learning model according to an embodiment.

Figure 8 shows a schematic diagram of training a machine learning model.

Please refer to FIG. 1 , which illustrates a schematic diagram of a smart stress relief device 100 according to an embodiment. The intelligent stress relief device 100 includes a stress relief device 110, a sensing device 120 and a processing device 130. The stress relief device 110 is used to perform a stress relief function on a user, such as a massage chair, an electrotherapy patch or a massage gun.

The sensing device 120 is used to sense at least one physiological signal Si to the user, such as a heart rhythm measuring device, a blood pressure monitor, an electromyography measuring device, a brain wave measuring device, a thermometer, and a respiration volume. detector, or a radio device.

The processing device 130 is used to perform various analysis and processing procedures, such as a chip, a circuit, a circuit board, a computer program product, program code, or a storage device that stores program code. In the embodiment of FIG. 1 , the sensing device 120 and the processing device 130 are both disposed on the stress relief device 110 .

Please refer to Figure 2, which illustrates smart stress relief according to another embodiment. Schematic diagram of device 100’. The sensing device 120' of the smart stress relief device 100' is, for example, a smart bracelet or a smart watch. The processing device 130' is, for example, a smartphone. In the embodiment of FIG. 2 , neither the sensing device 120 nor the processing device 130 is disposed on the stress relief device 110 . The following description takes the intelligent stress relief device 100 in Figure 1 as an example.

Please refer to FIG. 3 , which illustrates a block diagram of a smart stress relief device 100 according to an embodiment. The processing device 130 includes a prediction unit 131, a parameter analysis unit 132, a control unit 133 and a storage unit 134. When the user uses the stress relief device 110, the sensing device 120 can sense the current physiological signal Si to the user. The processing device 130 can control the stress relief device 110 to perform the stress relief function according to the physiological signal Si. The following is a flow chart that details the operation of each component.

Please refer to FIG. 4 , which illustrates a flow chart of a control method of the stress relief device 110 according to an embodiment. In step S110, the stress relief device 110 performs a stress relief function on the user. When the stress relief device 110 is activated, the user can log in basic information. According to the user's basic information, the control unit 133 can obtain a set of appropriate control parameters PMj from the storage unit 134 . For example, when the user is a child or an elderly person, a lighter control parameter PMj is provided; when the user is a young person, a heavier control parameter PMj is provided.

Then, in step S120, the sensing device 120 senses at least one physiological signal Si for the user. The physiological signal Si is, for example, a heartbeat, a blood pressure, a muscle activity potential, a breathing rate, a body surface temperature, a skin conductivity, a sound, a brain wave or a combination thereof. The sensing device 120 may be composed of multiple components with different measurement functions. The physiological signal Si is, for example, measurement information for a period of time (for example, 5 minutes), such as heart rhythm change curve, temperature change curve, brain wave curve, etc. Or, physiological The signal Si can also be a change at a single point in time, such as a change in temperature, a change in breathing rate, etc.

Next, in step S130, as shown in FIG. 5, the prediction unit 131 of the processing device 130 predicts an emotional state ES and a muscle state MS of the user in the future based on the physiological signal Si. Figure 5 illustrates the physiological signal Si, the emotional state ES and the muscle state MS. After the sensing device 120 measures the physiological signal Si from time point T0 to time point T1, the prediction unit 131 can predict the emotional state ES and muscle state MS from time point T1 to time point T2 in the future at time point T1. The time point T1 to the time point T2 are, for example, 5 seconds. The emotional state ES is, for example, tension, pressure, excitement or calmness. The muscle state MS is, for example, tight or relaxed.

Please refer to FIG. 6 , which illustrates machine learning model MD1 and machine learning model MD2 according to an embodiment. In this embodiment, the prediction unit 131 can predict the user's future emotional state ES and muscle state MS through the machine learning model MD1. As shown in Figure 5, after multiple physiological signals Si are input to the machine learning model MD1, the emotional state ES and muscle state MS can be output.

Next, in step S140, as shown in FIG. 6, the parameter analysis unit 132 of the processing device 130 analyzes at least one control parameter PMj based on the user's future emotional state ES and muscle state MS. In this embodiment, the parameter analysis unit 132 can analyze the control parameter PMj through the machine learning model MD2. As shown in Figure 6, after the emotional state ES and muscle state MS are input to the machine learning model MD2, the control parameter PMj can be output. The control parameter PMj is, for example, the size of the skin surface electric wave, visual presentation, music, white noise, pressing wheel position, vibration mode or a combination thereof.

Then, in step S150, the control unit 133 controls the stress relief device 110 to perform the stress relief function according to the control parameter PMj. The control unit 133 controls The parameter PMj generates an automatic control signal CM, and transmits the automatic control signal CM to the pressure relief device 110 to control the pressure relief device 110 . In this embodiment, the analysis of the control parameter PMj not only considers the muscle state MS, but also considers the emotional state ES, so that the stress relief device 110 can not only allow the user to obtain muscle relaxation, but also obtain psychological relaxation.

In addition, in addition to the control unit 133 automatically controlling the stress relief device 110 to perform the stress relief function, the user can also control it by himself through a smartphone application or buttons on the stress relief device 110 . In this case, the model training mechanism can be activated to train a personalized machine learning model MD2. Please refer to FIG. 7 , which illustrates a flow chart of a personalized training method of the machine learning model MD2 according to an embodiment. In step S160, the control unit 133 further receives a manual control signal CMk from the user. Although the control unit 133 automatically generates the automatic control signal CM, everyone has different feelings about pressing or music. When the user is dissatisfied with the current pressure or music, the user can manually control the stress relief device 110 through a smartphone application or a button on the stress relief device 110 to generate a manual control signal CMk.

Next, in step S170, as shown in FIG. 8, the parameter analysis unit 132 further trains the machine learning model MD2 based on the manual control signal CMk. Figure 8 shows a schematic diagram of training the machine learning model MD2. The machine learning model MD2 can be trained into a machine learning model MD2k by utilizing each user's different manual control signals CMk. Different machine learning models MD2k can provide personalized control parameters PMj for different users.

According to the above embodiment, when the user uses the stress relief device 110, The sensing device 120 can sense the current physiological signal Si of the user. The processing device 130 can obtain the muscle state MS and the emotional state ES based on the physiological signal Si. The analysis of the control parameter PMj not only considers the muscle state MS, but also considers the emotional state ES, so that the stress relief device 110 can not only allow the user to obtain muscle relaxation, but also obtain psychological relaxation. In addition, the machine learning model MD2 can be trained into the machine learning model MD2k by utilizing the different manual control signals CMk of each user. Different machine learning models MD2k can provide personalized control parameters PMj for different users.

In summary, although the present disclosure has been disclosed in the above embodiments, they are not used to limit the present disclosure. Those with ordinary knowledge in the technical field to which this disclosure belongs can make various modifications and modifications without departing from the spirit and scope of this disclosure. Therefore, the protection scope of the present disclosure shall be subject to the scope of the appended patent application.

100: Intelligent stress relief equipment

110: Stress relief device

120: Sensing device

130: Processing device

131: Prediction unit

132: Parameter analysis unit

133:Control unit

134:Storage unit

CM: automatic control signal

CMk: Manual control signal

ES: emotional state

PMj: control parameters

MS:muscle status

Si: physiological signal

Claims (14)

An intelligent stress relief device, including: a stress relief device for performing a stress relief function on a user; a sensing device for sensing at least one physiological signal on the user; and a processing device, including: A prediction unit is used to predict a future emotional state and a muscle state of the user based on the physiological signal; a parameter analysis unit is used to analyze at least one parameter based on the user's future emotional state and muscle state. Control parameters; and a control unit for controlling the stress relief device to perform the stress relief function according to the control parameters, wherein the sensing device measures the physiological signal from a first time point to a second time point. , the prediction unit predicts the emotional state and the muscle state from the second time point to a third time point in the future at the second time point. The intelligent stress relief device as described in claim 1, wherein the physiological signal is a heartbeat, a blood pressure, a muscle activity potential, a breathing rate, a body surface temperature, a skin conductivity, a sound, a brain wave or other combination. The intelligent stress relief device as described in claim 1, wherein the emotional state and the muscle state in the future are the emotional state and the muscle state in the next 5 seconds. The intelligent stress relief device as described in claim 1, wherein the emotional state is tension, stress, excitement or calmness, and the muscle state is contraction or relaxation. The intelligent stress relief device of claim 1, wherein the prediction unit predicts the user's future emotional state and muscle state through a machine learning model. The intelligent stress relief device of claim 1, wherein the parameter analysis unit analyzes the control parameter through a machine learning model. The intelligent stress relief device of claim 6, wherein the control unit further receives a manual control signal from the user, and the parameter analysis unit further trains the machine learning model based on the manual control signal. The intelligent stress relief device as described in claim 1, wherein the control parameter is the size of the skin surface electric wave, visual presentation, music, white noise, pressing wheel position, vibration mode or a combination thereof. A control method for a stress relief device, including: using a stress relief device to perform a stress relief function on a user; sensing at least one physiological signal to the user; and predicting the user's future emotional state based on the physiological signal. and a muscle state; Analyzing at least one control parameter based on the user's future emotional state and the muscle state; and controlling the stress relief device to perform the stress relief function based on the control parameter, wherein from a first time point to a second time After sensing the physiological signal at the second time point, the emotional state and the muscle state from the second time point to a third time point in the future are predicted. The control method of a stress relief device as described in claim 9, wherein the emotional state and the muscle state in the future are the emotional state and the muscle state in the next 5 seconds. The control method of a stress relief device as described in claim 9, wherein the emotional state is tension, stress, excitement or calmness, and the muscle state is contraction or relaxation. The control method of a stress relief device as described in claim 9, wherein in the step of predicting the user's future emotional state and the muscle state, a machine learning model is used to predict the user's future emotional state and the muscle state. Muscle status. The control method of a stress relief device as described in claim 9, wherein in the step of analyzing the control parameter, the control parameter is analyzed through a machine learning model. The method of controlling a stress relief device as described in claim 13 further includes: receiving a manual control signal from the user; and training the machine learning model based on the manual control signal.

Images