Method and device for correcting hyperactivity behavior

Abstract

The invention relates to an attention deficit hyperactivity disorder behavior correction method and device, and the method comprises the steps: a sensing module obtains an action sensing signal of a wearer in real time, and transmits the action sensing signal to an AI discrimination module; the AI judgment module judges whether the action sensing signal is a normal action signal or an abnormal action signal; and when the AI judgment module recognizes that the action sensing signal is an abnormal action signal, the AI judgment module controls the vibration module to send a vibration reminding signal. According to the hyperactivity behavior correction method and device, the sensing module, the AI judgment module and the vibration module are integrated together, judgment about whether the action of a wearer is a disease action or not is given in real time, feedback is given in real time through the vibration module, and the attention of the wearer is attracted.

Description

Technical Field

[0001] The present invention relates to the field of wearable devices, and in particular to a method and device for correcting ADHD behavior. Background Art

[0002] At present, behavioral correction of ADHD is mainly through manual intervention, but manual behavior correction is often expensive and cannot be performed during school classes. In the prior art, a timed vibration watch is used to correct ADHD, but the timed vibration watch is often not intelligent and cannot distinguish between normal and abnormal movements, and can only vibrate repeatedly. Summary of the invention

[0003] The present invention provides a method and device for correcting behavior of ADHD, aiming to solve at least one of the technical problems existing in the prior art.

[0004] The technical solution of the present invention is a method for correcting ADHD behavior, which is applied to an ADHD behavior correction device, wherein the ADHD behavior correction device comprises a perception module, an AI discrimination module and a vibration module connected in sequence, and is characterized in that the method for correcting ADHD behavior comprises the following steps:

[0005] S100, the perception module acquires the motion perception signal of the wearer in real time, the perception module is provided with at least one motion sensor, and the perception module sends the motion perception signal to the AI ​​discrimination module;

[0006] S200, the AI ​​identification module determines whether the motion perception signal is a normal motion signal or an abnormal motion signal;

[0007] S300: When the AI ​​identification module identifies that the motion sensing signal is an abnormal motion signal, the AI ​​identification module controls the vibration module to send a vibration reminder signal.

[0008] Further, the step S100 includes:

[0009] S110, based on a preset sampling frequency, the motion sensor acquires a motion perception signal of the wearer;

[0010] S120, based on a preset time interval, the sensing module converts the action sensing signal into a group signal;

[0011] S130: The sensing module sends the group signal to the AI ​​determination module.

[0012] Further, in step S110, the action sensing signal includes a first signal, a second signal, a third signal, a fourth signal, a fifth signal and a sixth signal, the first signal is an upward direction signal, the second signal is a downward direction signal, the third signal is a left direction signal, the fourth signal is a right direction signal, the fifth signal is a front direction signal, and the sixth signal is a rear direction signal;

[0013] In the step S120, the group of signals includes a first signal sorting value, a second signal sorting value, a third signal sorting value, a fourth signal sorting value, a fifth signal sorting value and a sixth signal sorting value.

[0014] Further, the step S200 includes:

[0015] S210, the AI ​​identification module receives the group signal at a preset time interval;

[0016] S220, the AI ​​identification module interprets the group of signals, and sends the first signal sorting value, the second signal sorting value, the third signal sorting value, the fourth signal sorting value, the fifth signal sorting value and the sixth signal sorting value to a preset ADHD behavior recognition model;

[0017] S230: The ADHD behavior recognition model outputs a recognition result, where the recognition result includes a normal action signal or an abnormal action signal.

[0018] Further, in step S220,

[0019] The ADHD behavior recognition model includes an input layer Input, a convolution layer Conv1D, a pooling layer MaxPooling1D, a discard layer Dropout, a flattening layer Flatten, a fully connected layer Dense and an output layer Output which are connected in sequence.

[0020] Furthermore, the input format of the input layer is a two-dimensional array, the number of rows of the two-dimensional array is 100, and the number of columns of the two-dimensional data is 6;

[0021] The convolution layer Conv1D is a one-dimensional convolution, and the convolution kernel size kernel_size of the convolution layer Conv1D is 2 or 3;

[0022] The pooling layer MaxPooling1D is a one-dimensional maximum pooling, and the convolution kernel size of the pooling layer MaxPooling1D is 2;

[0023] The flattening layer Flatten is used to flatten the matrix, flattening a feature map with a shape into a vector vector;

[0024] The fully connected layer Dense changes the number of channels of a feature vector feature vector through the fully connected layer Dense;

[0025] The output layer Output is used to output the normal action signal probability value and the abnormal action signal probability value in the recognition result.

[0026] Furthermore, the present invention also provides a computer-readable storage medium having program instructions stored thereon, and the program instructions, when executed by a processor, implement the ADHD behavior correction method.

[0027] Furthermore, the present invention also provides an ADHD behavior correction device, which is used to perform the ADHD behavior correction method, and the ADHD behavior correction device comprises:

[0028] A perception module, wherein at least one motion sensor is provided on the perception module, and the motion sensor is used to collect motion perception signals of the wearer, and the motion perception signals are group signals;

[0029] An AI discrimination module, the AI ​​discrimination module is electrically connected to the perception module, and the AI ​​discrimination module is used to determine whether the action perception signal is a normal action signal or an abnormal action signal;

[0030] A vibration module, wherein the vibration module is electrically connected to the AI ​​identification module, and wherein the vibration module is used to send a vibration reminder signal when the AI ​​identification module identifies that the motion sensing signal is an abnormal motion signal.

[0031] Furthermore, the present invention also provides a watch, which at least includes the ADHD behavior correction device.

[0032] The beneficial effects of the present invention are:

[0033] The ADHD behavior correction method and device integrate the perception module, AI discrimination module and vibration module, and give a real-time judgment on whether the wearer's action is an onset action, and give feedback through the vibration module in real time to attract the wearer's attention. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Flowchart of behavior modification methods for ADHD.

[0035] Figure 2 The present invention is a flowchart of a sensing module in an ADHD behavior correction method for acquiring the wearer's motion sensing signal in real time.

[0036] Figure 3The present invention is a flow chart of an AI discrimination module in an ADHD behavior correction method for determining whether the motion perception signal is a normal motion signal or an abnormal motion signal.

[0037] Figure 4 This is a schematic diagram of the ADHD behavior identification model in the ADHD behavior correction method.

[0038] Figure 5 The present invention is a schematic diagram of an ADHD behavior correction device in an ADHD behavior correction method.

[0039] Attached figure numbers, 100, perception module; 110, motion sensor; 200, AI discrimination module; 210, ADHD behavior recognition model; 300, vibration module. DETAILED DESCRIPTION

[0040] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0041] It should be noted that, unless otherwise specified, when a feature is referred to as being "fixed" or "connected" to another feature, it may be directly fixed or connected to the other feature, or it may be indirectly fixed or connected to the other feature. In addition, the descriptions of up, down, left, right, top, bottom, etc. used in the present invention are only relative to the relative positional relationship of the components of the present invention in the drawings.

[0042] In addition, unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art. The terms used in this specification are only for describing specific embodiments, not for limiting the present invention. The term "and / or" used herein includes any combination of one or more related listed items.

[0043] It should be understood that, although the terms first, second, third, etc. may be used to describe various elements in the present disclosure, these elements should not be limited to these terms. These terms are only used to distinguish elements of the same type from each other. For example, without departing from the scope of the present disclosure, the first element may also be referred to as the second element, and similarly, the second element may also be referred to as the first element.

[0044] Reference Figures 1 to 5 In some embodiments, the technical solution of the present invention is a method and device for correcting ADHD behavior, referring to Figure 1The ADHD behavior correction method is applied to an ADHD behavior correction device, wherein the ADHD behavior correction device comprises a sensing module 100, an AI discrimination module 200 and a vibration module 300 connected in sequence, and is characterized in that the ADHD behavior correction method comprises the following steps:

[0045] S100, the perception module 100 acquires the motion perception signal of the wearer in real time, the perception module 100 is provided with at least one motion sensor 110, and the perception module 100 sends the motion perception signal to the AI ​​discrimination module 200;

[0046] S200, the AI ​​identification module 200 determines whether the motion perception signal is a normal motion signal or an abnormal motion signal;

[0047] S300: When the AI ​​identification module 200 identifies that the motion sensing signal is an abnormal motion signal, the AI ​​identification module 200 controls the vibration module 300 to send a vibration reminder signal.

[0048] The beneficial effects of the present invention are:

[0049] The ADHD behavior correction method and device integrate the perception module 100, the AI ​​discrimination module 200 and the vibration module 300, and give a real-time judgment on whether the wearer's action is an action of disease, and give feedback in real time through the vibration module 300 to attract the wearer's attention.

[0050] Further, refer to Figure 2 , the step S100 comprises:

[0051] S110, based on a preset sampling frequency, the motion sensor 110 acquires a motion perception signal of the wearer;

[0052] S120, based on a preset time interval, the sensing module 100 converts the action sensing signal into a group signal;

[0053] S130 , the sensing module sends the group signal to the AI ​​determination module 200 .

[0054] Further, refer to Figure 2 In step S110, the action sensing signal includes a first signal, a second signal, a third signal, a fourth signal, a fifth signal and a sixth signal, the first signal is an upward direction signal, the second signal is a downward direction signal, the third signal is a left direction signal, the fourth signal is a right direction signal, the fifth signal is a front direction signal, and the sixth signal is a rear direction signal;

[0055] In the step S120, the group of signals includes a first signal sorting value, a second signal sorting value, a third signal sorting value, a fourth signal sorting value, a fifth signal sorting value and a sixth signal sorting value;

[0056] Among them, for the first signal, first calculate the first signal mean and the first signal variance of all the first signals collected within a preset time interval, and then divide the difference between the first signal and the first signal mean by the first signal by the first signal variance to obtain the first signal sorting value; for the second signal, first calculate the second signal mean and the second signal variance of all the second signals collected within a preset time interval, and then divide the difference between the second signal and the second signal mean by the second signal by the second signal variance to obtain the second signal sorting value; for the third signal, first calculate the third signal mean and the third signal variance of all the third signals collected within the preset time interval, and then divide the difference between the third signal and the third signal mean by the third signal by the third signal variance to obtain the third signal sorting value value; for the fourth signal, first calculate the fourth signal mean and the fourth signal variance of all fourth signals collected within the preset time interval, and then divide the difference of the fourth signal minus the fourth signal mean by the fourth signal variance to obtain the fourth signal sorted value; for the fifth signal, first calculate the fifth signal mean and the fifth signal variance of all fifth signals collected within the preset time interval, and then divide the difference of the fifth signal minus the fifth signal mean by the fifth signal variance to obtain the fifth signal sorted value; for the sixth signal, first calculate the sixth signal mean and the sixth signal variance of all sixth signals collected within the preset time interval, and then divide the difference of the sixth signal minus the sixth signal mean by the sixth signal variance to obtain the sixth signal sorted value.

[0057] Further, refer to Figure 3 , the step S200 comprises:

[0058] S210, the AI ​​identification module 200 receives the group signal at a preset time interval;

[0059] S220, the AI ​​identification module 200 interprets the group of signals, and sends the first signal sorting value, the second signal sorting value, the third signal sorting value, the fourth signal sorting value, the fifth signal sorting value and the sixth signal sorting value to the preset ADHD behavior recognition model 210;

[0060] S230: The ADHD behavior recognition model 210 outputs a recognition result, where the recognition result includes a normal action signal or an abnormal action signal.

[0061] Specifically, in a specific embodiment, the preset sampling frequency is 100 samples per second. Referring to Table 1, it is an example of 100 group signals composed of the first signal, the second signal, the third signal, the fourth signal, the fifth signal and the sixth signal within 1 second.

[0062]

[0063]

[0064]

[0065] Further, refer to Figure 3 and Figure 4 In the step S220,

[0066] The ADHD behavior recognition model 210 includes an input layer Input, a convolution layer Conv1D, a pooling layer MaxPooling1D, a discard layer Dropout, a flattening layer Flatten, a fully connected layer Dense and an output layer Output which are connected in sequence.

[0067] Further, refer to Figure 4 , the input format of the input layer is a two-dimensional array, the number of rows of the two-dimensional array is 100, and the number of columns of the two-dimensional data is 6;

[0068] The convolution layer Conv1D is a one-dimensional convolution, the convolution kernel size kernel_size of the convolution layer Conv1D is 2 or 3, and the number of output channels filters is 100;

[0069] The pooling layer MaxPooling1D is a one-dimensional maximum pooling, and the convolution kernel size of the pooling layer MaxPooling1D is 2;

[0070] The flattening layer Flatten is used to flatten the matrix, flattening a feature map with a shape into a vector vector;

[0071] The fully connected layer Dense changes the number of channels of a feature vector feature vector through the fully connected layer Dense;

[0072] The output layer Output is used to output the normal action signal probability value and the abnormal action signal probability value in the recognition result.

[0073] Furthermore, the present invention also provides a computer-readable storage medium having program instructions stored thereon, and the program instructions, when executed by a processor, implement the ADHD behavior correction method.

[0074] Further, refer to Figure 5 The present invention also provides an ADHD behavior correction device, which is used to perform the ADHD behavior correction method, and the ADHD behavior correction device includes:

[0075] A sensing module 100, wherein at least one motion sensor 110 is provided on the sensing module 100, and the motion sensor 110 is used to collect motion sensing signals of the wearer, and the motion sensing signals are group signals;

[0076] An AI identification module 200, the AI ​​identification module 200 is electrically connected to the perception module 100, and the AI ​​identification module 200 is used to determine whether the action perception signal is a normal action signal or an abnormal action signal;

[0077] The vibration module 300 is electrically connected to the AI ​​identification module 200 , and is used to send a vibration reminder signal when the AI ​​identification module 200 identifies that the motion sensing signal is an abnormal motion signal.

[0078] Furthermore, the present invention also provides a watch, which at least includes the ADHD behavior correction device.

[0079] The above is only a preferred embodiment of the present invention. The present invention is not limited to the above implementation. As long as the technical effect of the present invention is achieved by the same means, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the scope of protection of the present disclosure. All should belong to the protection scope of the present invention. Within the protection scope of the present invention, its technical scheme and / or implementation method can have various modifications and changes.

Claims

1. A method for correcting behavior of ADHD, applied to an ADHD behavior correction device, wherein the ADHD behavior correction device comprises a perception module (100), an AI discrimination module (200) and a vibration module (300) connected in sequence, characterized in that: The ADHD behavior correction method comprises the following steps: S100, the perception module (100) acquires a motion perception signal of the wearer in real time, the perception module (100) is provided with at least one motion sensor (110), and the perception module (100) sends the motion perception signal to the AI ​​discrimination module (200); S200, the AI ​​identification module (200) determines whether the motion perception signal is a normal motion signal or an abnormal motion signal; S300: When the AI ​​identification module (200) identifies that the motion sensing signal is an abnormal motion signal, the AI ​​identification module (200) controls the vibration module (300) to send out a vibration reminder signal.

2. The method for correcting ADHD behavior according to claim 1, characterized in that: The step S100 includes: S110, based on a preset sampling frequency, the motion sensor (110) acquires a motion perception signal of the wearer; S120, based on a preset time interval, the sensing module (100) converts the action sensing signal into a group signal; S130, the sensing module sends the group signal to the AI ​​determination module (200).

3. The method for correcting ADHD behavior according to claim 2, characterized in that: In step S110, the action sensing signal includes a first signal, a second signal, a third signal, a fourth signal, a fifth signal and a sixth signal, the first signal is an upward direction signal, the second signal is a downward direction signal, the third signal is a left direction signal, the fourth signal is a right direction signal, the fifth signal is a front direction signal, and the sixth signal is a rear direction signal.

4. The method for correcting ADHD behavior according to claim 1, characterized in that: The step S200 includes: S210, the AI ​​identification module (200) receives the group signal at a preset time interval; S220, the AI ​​identification module (200) interprets the group of signals, and sends the first signal sorting value, the second signal sorting value, the third signal sorting value, the fourth signal sorting value, the fifth signal sorting value and the sixth signal sorting value to a preset ADHD behavior recognition model (210); S230: The ADHD behavior recognition model (210) outputs a recognition result, wherein the recognition result includes a normal action signal or an abnormal action signal.

5. The method for correcting ADHD behavior according to claim 4, characterized in that: In the step S220, The ADHD behavior recognition model (210) comprises an input layer Input, a convolution layer Conv1D, a pooling layer MaxPooling1D, a dropout layer Dropout, a flattening layer Flatten, a fully connected layer Dense and an output layer Output which are connected in sequence.

6. The method for correcting ADHD behavior according to claim 5, characterized in that: The input format of the input layer is a two-dimensional array, the number of rows of the two-dimensional array is 100, and the number of columns of the two-dimensional data is 6; The convolution layer Conv1D is a one-dimensional convolution, and the convolution kernel size kernel_size of the convolution layer Conv1D is 2 or 3; The pooling layer MaxPooling1D is a one-dimensional maximum pooling, and the convolution kernel size of the pooling layer MaxPooling1D is 2; The flattening layer Flatten is used to flatten the matrix, flattening a feature map with a shape into a vector vector; The fully connected layer Dense changes the number of channels of a feature vector feature vector through the fully connected layer Dense; The output layer Output is used to output the normal action signal probability value and the abnormal action signal probability value in the recognition result. 7 . A computer-readable storage medium having program instructions stored thereon, wherein the program instructions, when executed by a processor, implement the method according to any one of claims 1 to 6 .

8. A device for correcting behavior of ADHD, wherein the device is used to perform the method for correcting behavior of ADHD as claimed in any one of claims 1 to 6, characterized in that: The ADHD behavior correction device comprises: A perception module (100), wherein at least one motion sensor (110) is provided on the perception module (100), and the motion sensor (110) is used to collect motion perception signals of a wearer, wherein the motion perception signals are group signals; An AI discrimination module (200), the AI ​​discrimination module (200) being electrically connected to the perception module (100), the AI ​​discrimination module (200) being used to judge whether the action perception signal is a normal action signal or an abnormal action signal; A vibration module (300), the vibration module (300) being electrically connected to the AI ​​identification module (200), the vibration module (300) being used to send a vibration reminder signal when the AI ​​identification module (200) identifies that the motion sensing signal is an abnormal motion signal.

9. A watch, characterized in that: The watch at least includes the ADHD behavior correction device as claimed in claim 8.

Images