Deep learning-based obsessive-compulsive disorder recognition intervention method and intervention system

Abstract

The invention relates to a deep learning-based obsessive-compulsive disorder recognition intervention method and intervention system, and the method comprises the steps: carrying out the segmentation training of a collected video image of a target object when the target object appears in a visual field, predicting the obsessive-compulsive disorder correlation degree, and carrying out the segmentation training of the collected video image of the target object when the target object is not in the visual field; multiple physiological index data of obsessive-compulsive disorder persons are collected through the bracelet, a fuzzy neural network is adopted for prediction, obsessive-compulsive disorder relevancy detected under two scenes can achieve data fusion, finally, a target control function is judged, a remote control instruction is sent to the bracelet in time when an obsessive-compulsive disorder behavior occurs, and the obsessive-compulsive disorder behavior is controlled. And meanwhile, the bracelet display screen is used for reminding the user of'relaxing ', so that the obsessive-compulsive disorder person is postponed physically and mentally and jumps out of the obsessive-compulsive disorder mode. Therefore, according to the technical scheme, the obsessive-compulsive disorder behavior of the person is accurately and efficiently predicted, and the obsessive-compulsive disorder behavior is timely intervened and guided in an audio-visual mode on the basis of prediction.

Description

Technical Field

[0001] The present invention relates to the field of medical care information, and in particular, to an obsessive-compulsive disorder identification and intervention method and intervention system based on deep learning. Background Art

[0002] Obsessive-compulsive disorder (OCD) is characterized by repeated emphasis on intrusive obsessions in the mind, regardless of personal will, and compulsive actions to eliminate anxiety or prevent threatening consequences, and then continue to perform compulsive behaviors. The clinical manifestations of obsessive-compulsive disorder mainly include obsessions and compulsive behaviors. Obsessions are some unwanted or intrusive thoughts, doubts or impulses that appear repeatedly in the mind. People with obsessive-compulsive disorder know that these are meaningless, but they cannot get rid of them, which causes distress and anxiety. Compulsive behaviors refer to repetitive behaviors or psychological activities, which may lead to loss of social function. For example, people with obsessive-compulsive disorder often worry about "what if the food is not washed clean and the stomach gets upset", and they wash the food repeatedly, worry about "what if I cross the road without paying attention and get hit by a car", and they look dazed when crossing the road, looking left and right to confirm repeatedly. Obsessive-compulsive disorder is not an infectious disease and is not contagious. Obsessive-compulsive disorder is a cognitive disorder that occurs in the process of seeking peace of mind. This cognitive disorder is a mental illness, but it will affect a person's normal life and work. In severe cases, people will fall into extreme pain, anxiety and even self-harm.

[0003] Traditional intervention methods for OCD generally involve consulting a psychologist, and some use machine learning to predict and assess the risk of OCD. For example, Chinese invention patent CN112037914B - a method, system and equipment for constructing an OCD risk assessment model, CN119361124A - an OCD diagnosis and symptom assessment system, and CN109360112B - a mental illness certification method based on data processing and related equipment. However, existing methods are mostly based on image acquisition, existing statistical data or brain wave analysis to predict and judge OCD. However, in many scenarios, people with OCD are not always in the field of vision, and data cannot be uploaded at any time. Therefore, this type of method is not only difficult to accurately identify OCD behavior at the practical level, but also unable to intervene in time and effectively guide. Therefore, existing machine learning methods cannot adapt to different scenarios of such people. Summary of the invention

[0004] In view of the defects and problems in the above-mentioned background technology, the present invention proposes an obsessive-compulsive disorder identification intervention method and intervention system based on deep learning. The specific technical scheme is as follows:

[0005] A deep learning-based obsessive-compulsive disorder identification and intervention method determines whether a target object is within a field of view. If so, the method enters an image acquisition and processing step: an image of the target object is acquired, and a CNN network is used to perform image segmentation, classification, and prediction, and finally an obsessive-compulsive disorder relevance S is output; if not, the method enters a physiological indicator parameter acquisition and processing step: physiological indicator parameters are acquired from the target object, and the physiological indicator parameters are preprocessed, trained, and predicted, and the obsessive-compulsive disorder relevance S is input into a target control function Ψ; based on the obsessive-compulsive disorder relevance S and the target control function Ψ, it is predicted whether the target object has obsessive-compulsive disorder behavior, and if so, intervention is performed on the obsessive-compulsive disorder behavior of the target object.

[0006] The target subjects are people with obsessive-compulsive disorder, and the intervention uses video reminders and / or music playing.

[0007] The image is collected through a camera, and the physiological index parameters are collected through a bracelet worn by the target object.

[0008] The image acquisition and processing steps include the following steps S11-S14:

[0009] Step S11: The target object is within the field of view, and the camera collects a video frame image D of the target object in the area. n,t , where t is time and n represents a frame;

[0010] Step S12: Convert the video frame image D n,t Import the CNN network and process the video frame image D n,t Perform image segmentation to obtain multiple feature maps D i,j,t , using the weighted bidirectional feature pyramid structure, different weights are assigned to the feature layers to transmit more effective feature information, where the subscripts “i, j” represent the feature map D i,j,t In the original video frame image D n,t The coordinate position in ;

[0011] Step S13: In the output result of the CNN network, set the classification type, which includes face, action, and associated object, and preset the weight W corresponding to each classification type in the softmax layer i,j , through the CNN network combined with the bidirectional feature pyramid and Yolo head, each classification type is output, and the classification type is used as the classification prediction value of the video frame image to determine the event type R at the current moment t ;

[0012] The Yolohead includes but is not limited to the head module units of the Yolo (full name: You Only Look Once) series of algorithms, such as Yolov5 head, Yolov6 head, Yolov7 head, and Yolov8 head.

[0013] Step S14: Traverse the event type R of a preset time before this moment t-1 , R t-2 , R t-3 , R t-n , judge R t-n With R t Are they the same? If they are the same, they are judged to be the same event type, and the obsessive-compulsive disorder relevance S is determined based on the number of times the same event occurs;

[0014] The levels of the obsessive-compulsive disorder relevance S are defined as: no relevance (the same event occurs only once or does not occur); medium relevance (the same event occurs twice); and high relevance (the same event occurs three times or more).

[0015] The physiological index parameter collection and processing step includes the following steps S21-S25:

[0016] Step S21: When the target object is in the blind spot or out of sight, multiple physiological index data of the obsessive-compulsive person are collected in real time through the wristband worn by the obsessive-compulsive person. The physiological index data include the current geographical location Dxy, heart rate TH, respiratory rate ζ1, pulse rate ζ2, blood pressure P, movement posture M m and the obsessive-compulsive disorder correlation S, where the S value is obtained by the step S14;

[0017] Step S22: Data preprocessing: normalize multiple physiological index data to obtain a data set {X i，t}, specifically, the normalization parameter X i for:

[0018] (1)

[0019] In the formula, Y represents the value of a physiological index before normalization, X represents the physiological index after normalization, the subscript "t" represents a time point, and the subscript "i" represents the i-th item;

[0020] Step S23: The preprocessed data set {X i，t} as input parameters, set the number of neurons and the number of training times, and import them into the fuzzy neural network for training;

[0021] The TS prediction model is used for prediction, and the fuzzy function of nonlinear prediction is as follows:

[0022] (2)

[0023] In the above formula, f( ) and g( ) are both smooth nonlinear functions, S t represents the relevance of the person's obsessive-compulsive disorder at time t, u is the actual output value of the fuzzy prediction, and the format of g( ) is:

[0024] (3)

[0025] Step S24: Normalize the parameters X in the data set i And the obsessive-compulsive disorder correlation S at the current moment is trained and learned, and the parameters in the fuzzy network are updated;

[0026] Step S25: Based on step S24, the target control function Ψ is calculated, and it is determined whether the obsessive-compulsive disorder correlation S is medium correlation or above. If so, it is further determined whether it reaches the preset threshold Ψ set ,If so, the MCU control unit sends remote control instructions to the ,bracelet to intervene in the obsessive-compulsive behavior of the target ,object through audio-visual prompts.

[0027] (4)

[0028] Wherein, coefficients a1~a6 are obtained by repeated iterative solution of the above fuzzy neural network when the initial parameters are given, and Ψ(t) is used as the control parameter in the neural network training process.

[0029] Based on the obsessive-compulsive disorder intervention method based on image recognition, an obsessive-compulsive disorder identification intervention system based on deep learning is further proposed. The intervention system includes a camera, a bracelet and a controller. The camera is provided with an image acquisition unit, and the bracelet is provided with an indicator acquisition unit. The indicator acquisition unit includes a geographic location sensor, a heart rate sensor, a respiratory rate sensor, a pulse sensor, a blood pressure sensor and a motion posture sensor. The camera and the bracelet are both communicatively connected to the controller.

[0030] The controller includes an image processing unit, a fuzzy prediction unit and an MCU control unit, wherein the video frame image data collected by the image acquisition unit is transmitted to the image processing unit for image segmentation, denoising and classification prediction, and the multiple physiological index data collected by the index acquisition unit are transmitted to the fuzzy prediction unit for preprocessing, fuzzy training and output of the target control function. When the target control function Ψ reaches a preset threshold Ψ set , and when the obsessive-compulsive disorder relevance S is medium or above, the MCU control unit sends a remote control command to the bracelet.

[0031] In summary, the obsessive-compulsive disorder identification intervention method and intervention system based on deep learning have the following beneficial effects compared with the prior art:

[0032] When the target object appears in the field of vision, the obsessive-compulsive disorder relevance is predicted by segmenting the collected video images of the target object. When the target object is not in the field of vision, multiple physiological indicator data of the obsessive-compulsive disorder personnel are collected through the bracelet, and the fuzzy neural network is used for prediction. The obsessive-compulsive disorder relevance detected in the two scenarios can achieve data fusion. Finally, by judging the target control function, when obsessive-compulsive disorder behavior occurs, remote control instructions are sent to the bracelet in time to play soothing music. At the same time, the user is prompted to "relax the mentality" through the bracelet display screen, so that the obsessive-compulsive disorder personnel can temporarily relax physically and mentally and jump out of the obsessive-compulsive disorder mode. Therefore, this technical solution accurately and efficiently predicts the obsessive-compulsive disorder behavior of personnel, and on the basis of the prediction, timely intervenes and guides the obsessive-compulsive disorder behavior through audio-visual methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a flow chart of an obsessive-compulsive disorder identification and intervention method based on deep learning of the present invention;

[0034] Figure 2 It is a schematic diagram of the SAME unit of the present invention;

[0035] Figure 3 This is a structural diagram of an obsessive-compulsive disorder identification and intervention system based on deep learning of the present invention. DETAILED DESCRIPTION

[0036] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention.

[0037] Please inspect Figure 1 , a deep learning-based obsessive-compulsive disorder identification and intervention method, including two basic steps S11-S14 (image acquisition and processing steps) and steps S21-S25 (physiological index parameter acquisition and processing steps):

[0038] Step S11: The target object is within the field of view, and the camera collects a video frame image D of the target object in the area. n,t , where t is time, n represents a certain frame, and the target object is a person with obsessive-compulsive disorder;

[0039] Step S12: Convert the video frame image D n,tImport the CNN network (convolutional neural network) to the video frame image D n,t Perform image segmentation to obtain multiple feature maps D i,j,t , using the weighted bidirectional feature pyramid (BiFPN) structure, different weights are given to the feature layers to transmit more effective feature information; adding a detection layer scale improves the network's detection accuracy for small targets, solves the problem of many targets in the field of view and inaccurate recognition of small targets, and is also conducive to the rapid convergence of results;

[0040] In the above formula, the subscript "i, j" represents the feature map D i,j,t In the original video frame image D n,t The coordinate position in ;

[0041] Step S13: In the output result of the CNN network, the classification type is set, and the classification types include face, action, and related objects. The weights corresponding to each classification type are preset in the softmax layer, and then the CNN network is combined with the bidirectional feature pyramid and Yolo head to output each classification type. The output classification type is used as the classification prediction value of the video frame image to determine the event type R at the current moment. t ;

[0042] Step S14: Traverse the event type R of a preset time before this moment t-1 , R t-2 , R t-3 , R t-n , judge R t-n With R t For example, if the event type identified in the image at time t is that the target object cleans the living room, if the event type identified at time t-2 is that the target object cleans the living room, and the action has been completed at time t-1, then R t With R t-2 For the same event type, the OCD relevance S is determined based on the number of occurrences of the same event;

[0043] The level of OCD relevance S is defined as: no relevance (the same event occurs only once or not at all); medium relevance (the same event occurs twice); and high relevance (the same event occurs three times or more).

[0044] The above steps S11-S14 are to perform segmentation training on the video image of the target object when the target object is in the field of view, and predict the obsessive-compulsive disorder relevance. When the target object is not in the field of view, in order to predict and intervene in the obsessive-compulsive disorder behavior of the target object in time, the following steps S21-S25 are also included:

[0045] Step S21: The target object is in the blind spot or out of view, data collection and information entry: through the wristband worn by the obsessive-compulsive person, real-time data collection of multiple physiological indicators of the obsessive-compulsive person is performed, including the current geographical location Dxy, heart rate TH, respiratory rate ζ1, pulse rate ζ2, blood pressure P, movement posture M m and the obsessive-compulsive disorder correlation S, where the S value is obtained by the step S14;

[0046] Based on a large number of obsessive-compulsive disorder intervention and treatment cases, the physiological indicator parameters selected in this embodiment can determine the degree of repetitiveness of a person's actions in daily life through geographic location and movement posture. When the obsessive-compulsive disorder is strong, due to neurological factors, endocrine disorders, etc., it is easy to cause significant changes in physiological parameters such as heart rate, respiratory rate, pulse frequency, and blood pressure. The changes in these physiological parameters can reflect the psychological state of the obsessive-compulsive disorder patient to a certain extent. For example, the detection of a person's accelerated respiratory rate, arrhythmia, sudden changes in pulse frequency, and increased blood pressure reflects the anxious psychological state of the obsessive-compulsive disorder patient who knows that it is a compulsive behavior but cannot control it autonomously. On this basis, combined with the degree of repetition of the person's actions, the obsessive-compulsive disorder relevance S of the person in the blind spot / non-video state can be inferred.

[0047] Step S22: Data preprocessing: normalize multiple physiological index data to obtain a data set {X i，t}, specifically, the normalization parameter X i for:

[0048] (1)

[0049] Where Y represents a physiological index value before normalization (including geographic location Dxy, heart rate TH, respiratory rate ζ1, pulse rate ζ2, blood pressure P, exercise posture M m ), X represents the normalized physiological index, the subscript "t" represents a certain time point, and the subscript "i" represents the i-th item;

[0050] Step S23: The preprocessed data set {X i，t} as input parameters, set the number of neurons and the number of training times, and import them into the fuzzy neural network for training;

[0051] Since the change of obsessive-compulsive disorder over time is nonlinear, in the above step S23, in order to achieve a more accurate prediction, the present invention adopts the TS prediction model, and the fuzzy function of the nonlinear prediction is as follows:

[0052] (2)

[0053] In the above formula, f( ) and g( ) are both smooth nonlinear functions, u is the actual output value of fuzzy prediction, S t represents the obsessive-compulsive disorder relevance of a person at time t, where g( ) is in the format of:

[0054] (3)

[0055] Step S24: Normalize the parameters X in the data set i And the obsessive-compulsive disorder correlation S at the current moment is trained and learned, and the parameters in the fuzzy network are updated;

[0056] Step S25: Based on step S24, calculate the target control function Ψ and determine whether it reaches the preset threshold Ψ set If so, the obsessive-compulsive disorder relevance S is further determined based on the result. If the obsessive-compulsive disorder relevance S is medium or above, the MCU control unit sends a remote control command to the bracelet to start music playback. The music played is soothing music, and the user is prompted to "relax" through the bracelet display.

[0057] (4)

[0058] Wherein, coefficients a1~a6 are obtained by repeated iterative solution of the above fuzzy neural network when the initial parameters are given, and Ψ(t) is used as the control parameter in the neural network training process.

[0059] In the above step S23, the basic steps of the fuzzy prediction algorithm are as follows:

[0060] 1) Define the input eX of the system state i,t , eS t and the domain, membership function and fuzzy prediction rule of the actual output value u of the fuzzy prediction, where the input eX i,t , eS t Corresponding to the data set {X i，t}、Obsessive-compulsive disorder correlation S t ;

[0061] 2) The real input (eX i,t , eS t ) and the actual output value u of the fuzzy prediction is mapped to the input (eX i,t *, eS t *) and output u*;

[0062] 3) Determine (eX i,t *, eS t *)'s fuzzy subset A i and B j and its effect fuzzy prediction rule Rk ;

[0063] 4) Calculate the membership value μ of each action rule k , μ k Used to describe an element eX i,t or eS t Belongs to a fuzzy subset A i and B j The calculation is shown in formula (5):

[0064] (5)

[0065] 5) Based on formula (5), the centroid method is used to perform defuzzification to obtain the fuzzy output u*, as shown in formula (6):

[0066] (6)

[0067] 6) The output u* obtained by fuzzy prediction is mapped to the actual output value u, and the actual output value u is used as the adjustment value of the difference ΔS of the obsessive-compulsive disorder correlation S. At time t+1, the difference ΔS t+1 According to the difference ΔS at time t t The inference calculation is performed with the actual output value of the fuzzy prediction. The calculation method is specifically listed in formula (7) and formula (8):

[0068] (7)

[0069] (8)

[0070] Among them, select the variable values ​​of ΔS, (S*dS / dt) and u, PB for positive and large, PM for positive and medium, PS for positive and small, NS for negative and small, NM for negative and large, NB for negative, ΔS and (S*dS / dt) correspond to six fuzzy rules of PB, PM, PS, NS, NM and NB, fill in the six fuzzy rules of ΔS and (S*dS / dt) in rows and columns, and query the value of u according to any fuzzy rule of ΔS and (S*dS / dt). The value of u is shown in Table 1:

[0071] Table 1 Fuzzy rule table

[0072] u PB PM PS NS NM NB PB 1 2 1 2 1 -1 PM 2 0 1 1 1 -1 PS 2 1 0 1 0 1 NS 1 1 -1 -1 0 -1 NM 1 0 -1 0 0 -1 NB 2 1 0 -1 -2 -2

[0073] In order to improve the recognition effect of the image and reduce the recognition loss, a soft attention mask is embedded between step S13 and step S14, the mask image is sent to the Transformer encoder for encoding, and the soft attention weights of the high-level features are embedded in the mask, thereby supplementing the mask area that is not segmented due to the limited local receptive field. In order to enhance the recognition effect of multi-scale text sequences, the mask features and text features of different scales are hierarchically embedded to obtain a soft attention weight map to assist text recognition. The recognition loss can be back-propagated to the Transformer multi-head encoder, and the detection can be guided by optimizing the attention weight map. Specifically, the soft attention mask embedding module includes 1 Transformer encoder and 4 upsampling structures. The input of SAME is the mask map Mask (Mask becomes Mask after encoding, adding weights and activation) 1 、Mask 2 、Mask 3 ) and 3 levels of soft attention feature maps (including , , , the soft attention feature map is a feature map in text format, and the text type is determined by the event type R t Determine), after the above mask image Mask is encoded by the Transformer encoder, the soft attention weight d of the high-level features is 1 d 2 The above mask map is embedded, and the mask map is activated by the commonly used Sigmoid function. On this basis, the original mask map Mask is transformed into Mask 1 、Mask 2 、Mask 3 , and 3 levels of soft attention feature map , , Perform fusion and / or cross multiplication operations in sequence to form soft attention mask fusion maps SM 1 , SM 2 , SM 3 , in SM 1 Based on the feature upsampling U up Get SM 2 , in SM 2 Based on the feature upsampling U up Get SM 3 , and finally the original image and Mask 3 After the cross product is performed, input the recognizer and Mask 3 Input recognizer, the two are compared in the recognizer, and then a soft attention weight map is obtained to assist in the recognition of classified text, and the recognition loss L rog (L rogThe gradient descent method is used for calculation. Gradient descent is used to find the corresponding value of the independent variable when a function is minimized. It can be back-propagated (i.e., identifying the gradient reflux) to the Transformer multi-head encoder, and by optimizing the attention weight d 1 d 2 Adjust the recognition accuracy. The above method improves the recognition effect of the face or human action image in the area, accurately identifies the event type, and reduces the recognition loss. The specific structure of the SAME unit is shown in the attached figure. Figure 2 as shown in .

[0074] In the above embodiment, when the target object appears in the field of view, the relevance of obsessive-compulsive disorder is predicted by segmenting the collected video image of the target object. When the target object is not in the field of view, in order to predict and timely intervene in the obsessive-compulsive behavior of the target object, multiple physiological indicator data of the obsessive-compulsive person are collected through the bracelet, and the nonlinear fuzzy prediction function is used for prediction. The obsessive-compulsive relevance detected in the two scenarios can achieve data fusion. Finally, by judging the target control function, when the obsessive-compulsive behavior appears, a remote control instruction is sent to the bracelet in time to play soothing music. At the same time, the user is prompted to "relax the mind" through the bracelet display screen, so that the obsessive-compulsive person can temporarily relax physically and mentally and jump out of the obsessive-compulsive mode. Therefore, this technical solution actually combines image segmentation and nonlinear fuzzy prediction functions to accurately and efficiently predict the obsessive-compulsive behavior of the personnel, and on the basis of the prediction, timely intervene and guide the obsessive-compulsive behavior through audio-visual methods.

[0075] Please inspect Figure 3 In the above-mentioned embodiment, an obsessive-compulsive disorder intervention method based on image recognition is further proposed. An obsessive-compulsive disorder identification intervention system based on deep learning is proposed. The system includes a camera, a bracelet and a controller. The camera has an image acquisition unit. The bracelet is provided with an index acquisition unit. The index acquisition unit includes a geographic location sensor, a heart rate sensor, a respiratory rate sensor, a pulse sensor, a blood pressure sensor and a motion posture sensor. The geographic location sensor is used to detect the current geographic location Dxy, the heart rate sensor is used to detect the current heart rate TH, the respiratory rate sensor is used to detect the current respiratory rate ζ1, the pulse sensor is used to detect the current pulse frequency ζ2, the blood pressure sensor is used to detect the current blood pressure P, and the motion posture sensor is used to detect the current motion posture M of the person. m , the camera and the bracelet are both connected to the controller for communication.

[0076] The controller includes an image processing unit, a fuzzy prediction unit and an MCU control unit. The video frame image data collected by the image acquisition unit is transmitted to the image processing unit for image segmentation, denoising and classification prediction. The multiple physiological index data collected by the index acquisition unit are transmitted to the fuzzy prediction unit for preprocessing, fuzzy training and output of the target control function. When the target control function Ψ reaches the preset threshold Ψ set , and when the obsessive-compulsive disorder relevance S is medium or above, the MCU control unit sends a remote control command to the bracelet to start music playback. The music played is soothing music, and the user is prompted to "relax" through the bracelet display.

[0077] This embodiment also relates to a computer-readable storage medium, which is arranged in an MCU control unit, and the readable storage medium includes a stored computer program; when the computer program is processed by a processor, the device where the computer-readable storage medium is located is controlled to execute the above embodiment.

[0078] Those skilled in the art should understand that the above embodiments only describe the optimal implementation method of the present invention and are not limited to the above technical solutions. Without departing from the basic concept of the above invention, other technical solutions are formed by any combination of the above technical features or their equivalent features, such as the technical solutions formed by replacing the above technical features with the technical features with similar functions invented in the present invention. The protection scope of the present invention is determined by the technical solutions covered by the claims.

Claims

1. A deep learning-based obsessive-compulsive disorder identification and intervention method, characterized by: Determine whether the target object is within the field of view. If so, enter the image acquisition and processing step: acquire an image of the target object, use the CNN network to perform image segmentation, classification, and prediction, and finally output the obsessive-compulsive disorder relevance S; if not, enter the physiological indicator parameter acquisition and processing step: acquire physiological indicator parameters of the target object, pre-process, train, and predict the physiological indicator parameters, and input the obsessive-compulsive disorder relevance S into the target control function Ψ; predict whether the target object has obsessive-compulsive disorder behavior based on the obsessive-compulsive disorder relevance S and the target control function Ψ, and if so, intervene in the obsessive-compulsive disorder behavior of the target object.

2. The deep learning-based obsessive-compulsive disorder identification and intervention method according to claim 1, characterized in that: The target subjects are people with obsessive-compulsive disorder, and the intervention uses video reminders and / or music playing.

3. The deep learning-based obsessive-compulsive disorder identification and intervention method according to claim 1, characterized in that: The image is collected through a camera, and the physiological index parameters are collected through a bracelet worn by the target object.

4. The deep learning-based obsessive-compulsive disorder identification and intervention method according to claim 2, characterized in that: The intervention uses video reminders and / or music playback, specifically: the music playback is soothing music, and the user is prompted to "relax" through the bracelet display screen.

5. The deep learning-based obsessive-compulsive disorder identification and intervention method according to claim 1, characterized in that: The level of the obsessive-compulsive disorder correlation S is defined as: if the same event occurs only once or does not occur, it is irrelevant; if the same event occurs twice, it is moderately correlated; if the same event occurs three times or more, it is highly correlated.

6. The deep learning-based obsessive-compulsive disorder identification and intervention method according to claim 1, characterized in that: The image acquisition and processing steps include the following steps S11-S14: Step S11: The target object is within the field of view, and the camera collects a video frame image D of the target object in the area. n,t , where t is time and n represents a frame; Step S12: Convert the video frame image D n,t Import the CNN network and process the video frame image D n,t Perform image segmentation to obtain multiple feature maps D i,j,t , using the weighted bidirectional feature pyramid structure, different weights are assigned to the feature layers, where the subscript "i,j" represents the feature map D i,j,t In the original video frame image D n,t The coordinate position in ; Step S13: In the output result of the CNN network, set the classification type, which includes face, action, and associated object, and preset the weight W corresponding to each classification type in the softmax layer i,j , through the CNN network combined with the bidirectional feature pyramid and Yolo head, each classification type is output, and the output classification type is used as the classification prediction value of the video frame image to determine the event type R at the current moment t ; Step S14: Traverse the event type R of a preset time before this moment t-1 , R t-2 , R t-3 , R t-n , judge R t-n With R t Are they the same? If they are the same, they are judged to be the same event type, and the obsessive-compulsive disorder relevance S is determined based on the number of times the same event occurs.

7. The deep learning-based obsessive-compulsive disorder identification and intervention method according to claim 6, characterized in that: The physiological index parameter collection and processing step includes the following steps S21-S25: Step S21: when the target object is in the blind spot or out of sight, multiple physiological index data of the obsessive-compulsive disorder person are collected in real time through the wristband worn by the obsessive-compulsive disorder person; Step S22: Data preprocessing: normalize multiple physiological index data to obtain a data set {X i，t }, specifically, the normalization parameter X i for: （1） In the formula, Y represents the value of a physiological index before normalization, X represents the physiological index after normalization, the subscript "t" represents a time point, and the subscript "i" represents the i-th item; Step S23: The preprocessed data set {X i，t } as input parameters, set the number of neurons and the number of training times, and import them into the fuzzy neural network for training; The TS prediction model is used for prediction, and the fuzzy function of nonlinear prediction is as follows: （2） In the above formula, f( ) and g( ) are both smooth nonlinear functions, S t represents the relevance of the person's obsessive-compulsive disorder at time t, u is the actual output value of the fuzzy prediction, and the format of g( ) is: （3） Step S24: Normalize the parameters X in the data set i And the obsessive-compulsive disorder correlation S at the current moment is trained and learned, and the parameters in the fuzzy network are updated; Step S25: Based on step S24, the target control function Ψ is calculated, and it is determined whether the obsessive-compulsive disorder correlation S is medium correlation or above. If so, it is further determined whether it reaches the preset threshold Ψ set ,If so, the MCU control unit sends remote control instructions to the bracelet to intervene in the obsessive-compulsive ,behavior of the target object through audio-visual prompts; （4） Wherein, coefficients a1~a6 are obtained by repeated iterative solution of the above fuzzy neural network when the initial parameters are given, and Ψ(t) is used as the control parameter in the neural network training process.

8. The deep learning-based obsessive-compulsive disorder identification and intervention method according to claim 7, characterized in that: The physiological index data includes the current geographical location Dxy, heart rate TH, respiratory rate ζ1, pulse frequency ζ2, blood pressure P, movement posture M m And the obsessive-compulsive disorder correlation S, the S value is obtained by the step S14.

9. An obsessive-compulsive disorder identification and intervention system based on deep learning, using an obsessive-compulsive disorder identification and intervention method based on deep learning as claimed in claim 1, characterized in that: The intervention system includes a camera, a bracelet and a controller. The camera is provided with an image acquisition unit, and the bracelet is provided with an index acquisition unit. The index acquisition unit includes a geographic location sensor, a heart rate sensor, a respiratory rate sensor, a pulse sensor, a blood pressure sensor and a motion posture sensor. The camera and the bracelet are both communicatively connected with the controller.

10. The deep learning-based obsessive-compulsive disorder identification and intervention system according to claim 9, characterized in that: The controller includes an image processing unit, a fuzzy prediction unit and an MCU control unit, wherein the video frame image data collected by the image acquisition unit is transmitted to the image processing unit for image segmentation, denoising and classification prediction, and the multiple physiological index data collected by the index acquisition unit are transmitted to the fuzzy prediction unit for preprocessing, fuzzy training and output of the target control function. When the target control function Ψ reaches a preset threshold Ψ set , and when the obsessive-compulsive disorder relevance S is medium or above, the MCU control unit sends a remote control command to the bracelet.

Images