CN112450932B - Psychological disorder detection system and method - Google Patents
Psychological disorder detection system and method Download PDFInfo
- Publication number
- CN112450932B CN112450932B CN202011475939.5A CN202011475939A CN112450932B CN 112450932 B CN112450932 B CN 112450932B CN 202011475939 A CN202011475939 A CN 202011475939A CN 112450932 B CN112450932 B CN 112450932B
- Authority
- CN
- China
- Prior art keywords
- mental disorder
- information
- target object
- psychological
- area image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
The invention is suitable for the technical field of computers, and provides a mental disorder detection system and a mental disorder detection method, wherein the mental disorder detection system comprises wearable data acquisition equipment and data processing equipment communicated with the wearable data acquisition equipment; the data processing equipment is used for determining mental disorder information of the target object by combining a preset mental disorder detection model according to the facial expression, the dialogue information and the body language of the target object; generating a psychological barrier dispersion scheme corresponding to the psychological barrier information according to the psychological barrier information of the target object; sending the mental disorder information and the mental disorder grooming scheme to the wearable data acquisition device. The invention has low requirement on the psychological diagnosis skill of the detector, so that the detector can quickly identify the psychological barrier information of the target object and the corresponding psychological barrier leading scheme in real time while seeing the conversation scene area, and the target object can be effectively detected and treated in time, and the applicability is wide.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a mental disorder detection system and a mental disorder detection method.
Background
Psychological disorders refer to abnormal behavioural patterns of various abnormal psychological processes and abnormal personality traits of a person due to physiological, psychological or social reasons, and are conditions in which a person exhibits an inability to behave in a socially accepted appropriate manner, such that the consequences of his behaviour are not adapted to the person and society.
The psychological disorder is almost the emotional disorder caused by the practical problems, such as emotional fluctuation and disorder caused by loss of love, straying, interpersonal relationship conflict, interest reduction caused by bad mood for a period of time, life law disorder, even behavior disorder, character deviation and the like. Most people often adjust by themselves, when self-adjustment has no effect, parents, relatives and friends, teachers, psychological consultants and the like with psychological treatment experience need to be searched for help to adjust, self-help psychological treatment measures which are suitable for practical application cannot be obtained in time, and the mode needs the parents, the relatives and friends, the teachers, the psychological consultants and the like with the psychological treatment experience to have strong observation and measurement force, otherwise, the mode easily generates a treatment effect which is suitable for the contrary because of negligence in detection, and the time is consumed.
Therefore, the existing mental disorder detection means has the problems of high requirements on the skill conditions of detection personnel, long time consumption and certain treatment effect caused by human detection negligence.
Disclosure of Invention
The embodiment of the invention aims to provide a psychological disorder detection system, and aims to solve the problems that the existing psychological disorder detection means has high requirements on the skill conditions of detection personnel, takes long time and has a treatment effect which is suitable for the contrary through human detection negligence.
The embodiment of the invention is realized in such a way that a mental disorder detection system comprises a wearable data acquisition device and a data processing device communicated with the wearable data acquisition device;
the wearable data acquisition device is used for acquiring a conversation scene area image in a user visual range, wherein the conversation scene area image carries a facial expression, conversation information and a body language of a target object; sending the conversation scene area image to the data processing device; receiving mental disorder information and a mental disorder grooming scheme returned by the data processing equipment; displaying the mental disorder information and a mental disorder grooming scheme in the conversation scene area image;
the data processing device is used for receiving the conversation scene area image sent by the wearable data acquisition device; according to the facial expression, the dialogue information and the body language of the target object, combining a preset mental disorder detection model to determine the mental disorder information of the target object; the preset mental disorder detection model is generated by training a plurality of pre-collected mental disorder characteristic samples through a convolutional neural network; generating a psychological barrier dispersion scheme corresponding to the psychological barrier information according to the psychological barrier information of the target object; and sending the mental disorder information and the mental disorder grooming scheme to the wearable data acquisition equipment.
Another objective of an embodiment of the present invention is to provide a mental disorder detection method, including:
receiving a conversation scene area image sent by the wearable data acquisition device, wherein the conversation scene area image carries a facial expression, conversation information and a body language of a target object;
determining mental disorder information of the target object by combining a preset mental disorder detection model according to the facial expression, the dialogue information and the body language of the target object; the preset mental disorder detection model is generated by training a plurality of pre-collected mental disorder characteristic samples through a convolutional neural network;
generating a psychological barrier dispersion scheme corresponding to the psychological barrier information according to the psychological barrier information of the target object;
sending the mental disorder information and the mental disorder dispersion scheme to the wearable data acquisition device, so that the wearable data acquisition device displays the mental disorder information and the mental disorder dispersion scheme in the conversation scene area image.
In the mental disorder detection system provided by the embodiment of the invention, a wearable data acquisition device is used for acquiring a dialogue scene area image carrying facial expressions, dialogue information and body languages of a target object in a user visual range, a data processing device is used for determining mental disorder information of the target object according to the facial expressions, the dialogue information and the body languages of the target object in combination with a preset mental disorder detection model, and a mental disorder dispersion scheme corresponding to the mental disorder information is generated according to the mental disorder information of the target object, so that the wearable data acquisition device displays the mental disorder information and the mental disorder dispersion scheme in the dialogue scene area image; the invention has low requirement on the psychological diagnosis skills of the detection personnel, so that the detection personnel can quickly identify the psychological barrier information of the target object and the corresponding psychological barrier leading scheme in real time while seeing the conversation scene area, so that the target object can be effectively detected and treated in time, and the applicability is wide.
Drawings
Fig. 1 is a schematic structural diagram of a mental disorder detection system according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a wearable data acquisition device according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating steps of generating a predetermined mental disorder detection model according to an embodiment of the present invention
Fig. 5 is a flowchart illustrating an implementation of a mental disorder detection method according to an embodiment of the present invention;
fig. 6 is a flowchart illustrating another implementation of a mental disorder detection method according to an embodiment of the present invention;
fig. 7 is a flowchart illustrating an implementation of another mental disorder detection method according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In order to solve the problems that the existing mental disorder detection means has high requirements on the skill conditions of detection personnel, takes long time and has an adverse treatment effect due to neglect of artificial detection, the embodiment of the invention provides a mental disorder detection system, wherein a wearable data acquisition device is used for acquiring a conversation scene area image carrying facial expressions, conversation information and body languages of a target object in a user visual range, a data processing device is used for determining the mental disorder information of the target object according to the facial expressions, the conversation information and the body languages of the target object by combining a preset mental disorder detection model, and a mental disorder dispersion scheme corresponding to the mental disorder information is generated according to the mental disorder information of the target object, so that the wearable data acquisition device displays the mental disorder information and the mental disorder dispersion scheme in the conversation scene area image; the invention has low requirement on the psychological diagnosis skills of the detection personnel, so that the detection personnel can quickly identify the psychological barrier information of the target object and the corresponding psychological barrier leading scheme in real time while seeing the conversation scene area, so that the target object can be effectively detected and treated in time, and the applicability is wide.
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the embodiments, structures, features and effects according to the present invention will be given with reference to the accompanying drawings and preferred embodiments.
Fig. 1 is a schematic structural diagram of a mental disorder detection system according to an embodiment of the present invention, and for convenience of description, only parts related to the embodiment of the present invention are shown.
In the embodiment of the present invention, the mental disorder detection system includes a wearable data acquisition device 110 and a data processing device 120 communicating with the wearable data acquisition device 110.
The wearable data acquisition device 110 is configured to acquire a dialog scene area image in a visual range of a user, where the dialog scene area image carries a facial expression, dialog information, and a body language of a target object; sending the dialog scene region image to the data processing device 120; receiving mental disorder information and a mental disorder grooming scheme returned by the data processing device 120; and displaying the mental disorder information and a mental disorder grooming scheme in the conversation scene area image.
In the embodiment of the present invention, the wearable data acquisition device 110 is generally in the form of glasses, helmet, eye mask, etc., which can be worn on the head of the user and has a transparent display screen in front of the eyes of the user.
In the embodiment of the present invention, in order to more conveniently acquire a dialog scene area image carrying a facial expression, dialog information, and a body language of a target object in a user visual range, a plurality of image information acquisition devices may be disposed at positions in each direction of an eye frame member of the wearable data acquisition device 110, and a speech data acquisition device may be disposed in the wearable data acquisition device 110, so that according to the position information of the plurality of image information acquisition devices, the dialog scene area image acquired by each image information acquisition device is fused and de-duplicated, and speech data acquired by the speech data acquisition device is processed by a text and then presented in a dialog scene area image in a corresponding time period, so as to acquire a dialog scene area image carrying a facial expression, dialog information, and a body language of a target object in a user visual range.
In the embodiment of the present invention, the mental disorder information includes but is not limited to mental activity disorders such as feelings, consciousness, memory, thinking, emotion, attention, will, intelligence, personality, consciousness, etc., and features such as anxiety, horror, hallucination, delusion, excitation, depression, mental retardation, conduct disorder, inability to adapt to social environment, etc., and reasons caused by the features of the mental disorder; the analysis of the psychological disorder characteristics and the generation reasons can be obtained by observing the facial expressions, dialogue information and body language of the target object during the communication process.
In the embodiment of the invention, the psychological obstacles are different due to different moods and different psychological obstacles because of different ages, identities, occupations, things, environments, interpersonal and social-cultural relationships and the like which people face everyday. The mental disorder grooming scheme is a mental disorder treatment scheme generated by comprehensively considering the age, identity, occupation, and the like of the target object in combination with mental disorder information thereof, and may be presented in the form of operation instructions, for example, when the cause of the mental disorder of the target object cannot be still determined according to facial expressions, dialog information, and body languages presented by the current target object during communication, the mental disorder treatment scheme first includes a dialog text for guiding the target object to explain the cause of the mental disorder, so that the user can further communicate with the target object according to the dialog text until the cause of the mental disorder of the target object is determined, and then further generates a mental disorder treatment scheme, for example, when the target object is determined to be depressed due to a large mental stress, so as to introduce the corresponding mental disorder treatment scheme to the target object in a manner effective for relieving the mental stress, such as travelling, playing music, guiding a crime, or guiding a humming, or guiding reading of a humorous.
Generally, when some patients suspect psychological disorders through observation of their emotional fluctuation, they can help them to dredge their psychological activities, guide their front view to reality, watch everything in peaceful and optimistic mind, throw away negative thoughts, and continuously mine their own value, etc. by having their body trust to wear the wearable data acquisition device 110. In addition, the mental disorder information and the mental disorder dispersion scheme are displayed on the display screen of the wearable data acquisition device 110, and since the display screen is transparent, the user can simultaneously see the mental disorder information and the mental disorder dispersion scheme while visually observing the target object for communication, so as to adjust the communication direction or the dispersion strategy in time.
The data processing device 120 is configured to receive a dialog scene area image sent by the wearable data acquisition device 110; determining mental disorder information of the target object by combining a preset mental disorder detection model according to the facial expression, the dialogue information and the body language of the target object; generating a psychological barrier dispersion scheme corresponding to the psychological barrier information according to the psychological barrier information of the target object; sending the mental disorder information and the mental disorder grooming scheme to the wearable data acquisition device 110.
In the embodiment of the present invention, the data processing device is a terminal device, such as a tablet computer, a notebook computer, a desktop computer, or a display adapter with data analysis processing capability, such as a video card, in which a preset mental disorder detection model, a mental disorder feature database, and a corresponding mental disorder grooming scheme database are stored, but is not limited thereto.
In the embodiment of the present invention, the facial expression and the body language of the target object may be identified and acquired from the images of the dialog scene area continuously shot at a certain time interval, for example, 1s, and the specific identification method may refer to the prior art and will not be described herein again.
In the embodiment of the present invention, the preset mental disorder detection model is generated by training a plurality of pre-collected mental disorder feature samples through a convolutional neural network, and the generation steps are specifically shown in fig. 4.
Generally speaking, if any psychological problem occurs, a user needs to consult a psychologist, inconvenience is caused in life, and a plurality of psychological barrier users know that the psychological barrier users cannot be integrated with the society, and cannot easily seek the psychologist to help overcome the psychological barrier, so that the psychological barrier degree is more and more serious, and the psychological barrier can be dredged by the psychological barrier users at any time in a mode, so that the degree is not deepened.
In the mental disorder detection system provided by the embodiment of the invention, a wearable data acquisition device is used for acquiring a dialogue scene area image carrying facial expressions, dialogue information and body languages of a target object in a user visual range, a data processing device is used for determining mental disorder information of the target object according to the facial expressions, the dialogue information and the body languages of the target object in combination with a preset mental disorder detection model, and a mental disorder dispersion scheme corresponding to the mental disorder information is generated according to the mental disorder information of the target object, so that the wearable data acquisition device displays the mental disorder information and the mental disorder dispersion scheme in the dialogue scene area image; the invention has low requirement on the psychological diagnosis skills of the detection personnel, so that the detection personnel can quickly identify the psychological barrier information of the target object and the corresponding psychological barrier leading scheme in real time while seeing the conversation scene area, so that the target object can be effectively detected and treated in time, and the applicability is wide.
Fig. 2 is a schematic structural diagram of the wearable data acquisition device according to the embodiment of the present invention, and for convenience of description, only parts related to the embodiment of the present invention are shown.
In this embodiment of the present invention, the wearable data acquisition device 110 includes:
a conversation scene area image acquiring unit 111, configured to acquire a conversation scene area image in a visual range of a user, where the conversation scene area image carries a facial expression, conversation information, and a body language of a target object.
In the embodiment of the present invention, in order to more conveniently acquire a dialog scene area image carrying a facial expression, dialog information, and a body language of a target object in a user visual range, a plurality of image information acquisition devices may be disposed at positions in each direction of an eye-box component of the dialog scene area image acquisition unit 111, and a speech data acquisition device may be disposed in the dialog scene area image acquisition unit 111, so that according to position information of the plurality of image information acquisition devices, the dialog scene area images acquired by the image information acquisition devices are fused and deduplicated, and speech data acquired by the speech data acquisition device is processed by a text and then presented in a dialog scene area image in a corresponding time period, so as to acquire the dialog scene area image carrying the facial expression, the dialog information, and the body language of the target object in the user visual range.
A dialogue scene area image transmission unit 112, configured to transmit the dialogue scene area image to the data processing apparatus.
A mental disorder information and grooming scheme receiving unit 113, configured to receive the mental disorder information and the mental disorder grooming scheme returned by the data processing device.
In the embodiment of the present invention, the mental disorder information includes but is not limited to mental activity disorders such as feeling, perception, memory, thinking, emotion, attention, will, intelligence, personality, and consciousness, which are commonly characterized by anxiety, horror, hallucination, delusion, excitement, depression, mental retardation, conduct disorder, and inability to adapt to social environment, and causes of the above-mentioned mental disorder features; the analysis of the psychological disorder characteristics and the generation reasons can be obtained by observing the facial expressions, dialogue information and body language of the target object during the communication process.
In the embodiment of the invention, the psychological obstacles are different due to different moods and different psychological obstacles because of different ages, identities, occupations, things, environments, interpersonal and social-cultural relationships and the like which people face everyday. The mental disorder grooming scheme is a mental disorder treatment scheme generated by comprehensively considering the age, identity, occupation, and the like of the target object in combination with mental disorder information thereof, and may be presented in the form of operation instructions, for example, when the cause of the mental disorder of the target object cannot be still determined according to facial expressions, dialog information, and body languages presented by the current target object during communication, the mental disorder treatment scheme first includes a dialog text for guiding the target object to explain the cause of the mental disorder, so that the user can further communicate with the target object according to the dialog text until the cause of the mental disorder of the target object is determined, and then further generates a mental disorder treatment scheme, for example, when the target object is determined to be depressed due to a large mental stress, so as to introduce the corresponding mental disorder treatment scheme to the target object in a manner effective for relieving the mental stress, such as travelling, playing music, guiding a crime, or guiding a humming, or guiding reading of a humorous.
A mental disorder information and dispersion scheme display unit 114, configured to display the mental disorder information and the mental disorder dispersion scheme in the conversation scene area image.
Generally, when some patients suspect psychological disorders through observation of their emotional fluctuation, they can help them to dredge their psychological activities, guide their front view to reality, watch everything in peaceful and optimistic mind, throw away negative thoughts, and continuously mine their own value, etc. by having their body trust to wear the wearable data acquisition device 110. In addition, the mental disorder information and the mental disorder dispersion scheme are displayed on the display screen of the wearable data acquisition device 110, and since the display screen is transparent, the user can simultaneously see the mental disorder information and the mental disorder dispersion scheme while visually observing the target object for communication, so as to adjust the communication direction or the dispersion strategy in time.
Fig. 3 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention, and for convenience of description, only a part related to the embodiment of the present invention is shown.
In this embodiment of the present invention, the data processing apparatus 120 includes:
a dialog scene region image receiving unit 121, configured to receive a dialog scene region image sent by the wearable data acquisition device.
A mental disorder information determining unit 122, configured to determine mental disorder information of the target object according to a facial expression, dialog information, and a body language of the target object in combination with a preset mental disorder detection model.
In the embodiment of the present invention, the facial expression and the body language of the target object are obtained by recognizing the images of the dialog scene area continuously shot at a certain time interval, for example, 1s, and the specific recognition mode may refer to the prior art and will not be described herein again.
The preset mental disorder detection model is generated by training a plurality of pre-collected mental disorder feature samples through a convolutional neural network, and the generation steps are specifically shown in fig. 4.
A mental disorder grooming scheme generating unit 123, configured to generate a mental disorder grooming scheme corresponding to the mental disorder information according to the mental disorder information of the target object.
A mental disorder information and grooming scheme sending unit 124, configured to send the mental disorder information and the mental disorder grooming scheme to the wearable data acquisition device.
The following is a schematic structural diagram of another mental disorder detection system provided in an embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown.
The mental disorder grooming scheme generating unit 123 is further configured to send the dialog scene area image to a third-party diagnosis mechanism; receiving a psychological barrier evaluation result generated by the third-party diagnosis mechanism according to the dialogue scene area image; and generating a psychological disorder dispersion scheme according to the psychological disorder information and the psychological disorder evaluation result.
In the embodiment of the invention, the third-party diagnosis mechanism refers to a conventional psychotherapy mechanism, and a professional psychologist can analyze and judge the conversation scene area image carrying the facial expression, the conversation information and the body language of the target object to form a psychological disorder evaluation result. The mental disorder assessment result not only relates to the mental disorder feature information obtained by assessment, but also relates to a mental treatment proposal corresponding to the mental disorder feature information, so that the mental disorder grooming scheme generating unit 330 integrates the mental disorder information and the mental disorder assessment result to generate a better mental disorder grooming scheme.
In a preferred embodiment of the present invention, since the third-party diagnosis institution is determined by the expert manually, the analysis efficiency is low, when the third-party diagnosis institution does not generate the mental disorder assessment result, the third-party diagnosis institution generates the mental disorder dispersion scheme based on the mental disorder information with priority, until the mental disorder assessment result sent by the third-party diagnosis institution is received, the mental disorder dispersion scheme generating unit 330 synthesizes the mental disorder information and the mental disorder assessment result to generate a better mental disorder dispersion scheme, and updates the mental disorder dispersion scheme, so that the communication continuity and naturalness between the user and the target object can be maintained, the target object can be presented more truly, and the detection and treatment effects are better.
According to the psychological disorder detection system provided by the embodiment of the invention, the psychological disorder dispersion scheme is formed by integrating the psychological disorder evaluation result generated by the third-party diagnosis mechanism according to the dialogue scene area image and the psychological disorder information generated by the preset psychological disorder detection model, the detection result is more accurate, the formed psychological disorder dispersion scheme is further matched with the psychological disorder characteristics of the target user, and the treatment effect is improved.
The following is a schematic structural diagram of another mental disorder detection system provided in an embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown.
In this embodiment of the present invention, the data processing device 120 is further configured to generate a mental disorder training scene according to the dialog scene region image; and sending the mental disorder training scene to the wearable data acquisition equipment.
The wearable data acquisition device 110 is further configured to receive a mental disorder training scene sent by the data processing device; and displaying the mental disorder training scene to a user so as to enable the user to carry out corresponding training.
In the embodiment of the invention, generally speaking, when the behavior of a person is not coordinated with the environment to a certain extent, and poor social adaptation occurs, the psychological activities of the person may be abnormal. However, although the psychological disorder caused by the fear of social contact can be eliminated by contacting the society and conducting a social training, the psychological adjustment ability of the individual psychological disorder is limited because the psychological disorder is caused by a long-term living environment, and not all people are willing to conduct a social training to overcome the psychological disorder. Therefore, a mental disorder person wears the wearable data acquisition device 110 to acquire specific scene information, namely a conversation scene area image, in a social environment closely related to the mental disorder person, so that the data processing device 120 generates a mental disorder training scene according to the conversation scene area image carrying facial expressions, conversation information and body languages of a target object, if the mental disorder person fears to make contact with a neighboring elder of the mental disorder person, the data processing device 120 further generates a corresponding mental disorder training scene by acquiring the conversation scene area image of the mental disorder person when communicating with the neighboring elder, and the wearable data acquisition device 110 displays the corresponding mental disorder training scene to a user, so that the mental disorder person performs corresponding targeted mental training to gradually overcome a mental disorder phenomenon when making contact with the neighboring elder of the mental disorder person.
According to the mental disorder detection system provided by the embodiment of the invention, a mental disorder training scene is generated according to the dialogue scene area image, so that the wearable data acquisition device displays the mental disorder training scene to a user, and the user can perform corresponding training. The invention can carry out social environment training closely related to the psychopath, and truly presents the targeted social environment, thereby being beneficial to the psychopath to gradually overcome the psychopath in multiple times of social environment training, and having more pertinence, higher training efficiency and better effect compared with the common training scene.
A schematic structural diagram of another mental disorder detection system according to an embodiment of the present invention is provided below, and for convenience of description, only the relevant portions related to the embodiment of the present invention are shown.
In this embodiment of the present invention, the data processing device 120 is further configured to obtain identity information of the target object; generating a diversified scene model according to the identity information, the facial expression, the dialogue information and the body language of the target object; and responding to the selection operation of the user on at least one diversified scene model, and sending the diversified scene model to the wearable data acquisition device.
The wearable data acquisition device 110 is further configured to receive the diversified scene models sent by the data processing device; and displaying the virtual scene corresponding to the diversified scene model to a user so that the user can carry out corresponding training.
In the embodiment of the invention, on the basis of the above embodiment, the identity information, the facial expression, the dialogue information and the body language of the fear object are acquired according to the social environment closely related to the psychopath, so as to generate the diversified scene model, avoid the user from being boring due to the single scene model, and enhance the training effect.
The mental disorder detection system provided by the embodiment of the invention acquires the identity information of a target object; generating diversified scene models according to the identity information, the facial expressions, the dialogue information and the body language of the target object, responding to the selection operation of a user on at least one diversified scene model, and enabling the wearable data acquisition equipment to display virtual scenes corresponding to the diversified scene models for the user so that the user can carry out corresponding training. The invention can avoid the single scene model from causing the user to be boring, improve the training interest of the mental handicapped and strengthen the training effect.
Fig. 4 is a flowchart illustrating steps of generating a predetermined mental disorder detection model according to an embodiment of the present invention, which is described in detail below.
In step S401, a plurality of samples of psychological barrier characteristics are obtained.
In an embodiment of the present invention, the mental disorder feature sample includes facial expressions, dialogue information, and body language of the mental disorder person, and may be acquired by a mental detection center.
Step S402, obtaining target mental disorder information of the mental disorder feature samples.
Step S403, determining first mental disorder information of the first mental disorder feature sample according to the first mental disorder feature sample and a convolutional neural network model containing variable parameters.
In an embodiment of the present invention, the convolutional neural network model comprises an input layer, a plurality of convolutional layers, a plurality of pooling layers, at least one fully-connected layer, and an output layer, wherein variable parameters exist in the plurality of convolutional layers and the plurality of fully-connected layers.
In the embodiment of the present invention, when the variable parameters in the plurality of convolutional layers and the plurality of fully-connected layers are changed, the response probability heatmaps output for the same input psychological barrier characteristics sample are different.
Step S404, calculating a first loss difference between the first mental disorder information and the first mental disorder information corresponding to the first mental disorder feature sample.
Step S405, determining whether the loss difference of the plurality of mental disorder feature samples satisfies a preset condition.
In the embodiment of the present invention, it may be determined whether the established mental disorder detection model meets requirements by determining whether the loss difference of the plurality of mental disorder feature samples meets a preset condition, for example, when the loss difference of the plurality of mental disorder feature samples is smaller than a certain threshold, it indicates that the facial expression, the dialog information, and the body language of the target object are input according to the trained mental disorder detection model, so as to obtain more accurate mental disorder information.
In the embodiment of the present invention, when it is determined that the loss difference of the plurality of mental disorder feature samples does not satisfy the preset condition, it indicates that the trained mental disorder detection model has a large error, and step S406 is executed; when it is determined that the loss difference of the plurality of mental disorder feature samples satisfies the preset condition, it indicates that the trained mental disorder detection model is relatively stable, and step S407 is executed.
Step S406, adjusting variable parameters in the convolutional neural network model.
In the embodiment of the present invention, the variable parameters in the convolutional neural network model may be adjusted according to a back propagation algorithm or a gradient descent algorithm, and after the variable parameters are adjusted, the process returns to step S403 to recalculate the loss difference.
Step S407, determining the current convolutional neural network model with variable parameters as a preset mental disorder detection model.
Fig. 5 is a flowchart of an implementation of a mental disorder detection method according to an embodiment of the present invention, which is described in detail as follows.
Step S501, receiving a dialog scene area image sent by the wearable data acquisition device, where the dialog scene area image carries a facial expression, dialog information, and a body language of a target object.
In the embodiment of the invention, in order to more conveniently acquire the dialogue scene area images carrying the facial expression, the dialogue information and the body language of the target object in the visual range of the user, a plurality of image information acquisition devices can be arranged at positions in all directions of an eye frame part of the wearable data acquisition equipment, and a speech data acquisition device is arranged in the wearable data acquisition equipment, so that the dialogue scene area images acquired by the image information acquisition devices are fused and deduplicated according to the position information of the image information acquisition devices, and speech data acquired by the speech data acquisition devices are displayed in the dialogue scene area images in corresponding time periods after text processing, so that the dialogue scene area images carrying the facial expression, the dialogue information and the body language of the target object in the visual range of the user can be acquired.
In the embodiment of the present invention, the facial expression and the body language of the target object may be identified and acquired from the images of the dialog scene area continuously shot at a certain time interval, for example, 1s, and the specific identification method may refer to the prior art and will not be described herein again.
Step S502, according to the facial expression, the dialogue information and the body language of the target object, and in combination with a preset mental disorder detection model, determining the mental disorder information of the target object.
In the embodiment of the present invention, the mental disorder information includes but is not limited to mental activity disorders such as feeling, perception, memory, thinking, emotion, attention, will, intelligence, personality, and consciousness, which are commonly characterized by anxiety, horror, hallucination, delusion, excitement, depression, mental retardation, conduct disorder, and inability to adapt to social environment, and causes of the above-mentioned mental disorder features; the analysis of the psychological disorder characteristics and the generation reasons can be obtained by observing the facial expressions, dialogue information and body language of the target object during the communication process.
In the embodiment of the present invention, the preset mental disorder detection model is generated by training a plurality of pre-collected mental disorder feature samples through a convolutional neural network, and the generation steps are specifically shown in fig. 4.
Step S503, generating a mental disorder grooming plan corresponding to the mental disorder information according to the mental disorder information of the target object.
In the embodiment of the invention, due to the difference of things, environments, interpersonal and social-cultural relationships and the like which people of different ages, identities and professions face everyday, the mood is different, and the existing psychological obstacles are also different. The mental disorder grooming plan is a mental disorder treatment plan generated by comprehensively considering the age, identity, occupation, and the like of the target object and combining mental disorder information of the target object, and the mental disorder grooming plan can be presented in the form of operation instructions, for example, when the reason for generating the mental disorder of the target object cannot be determined according to facial expressions, conversation information, and body language expressed by the current target object in the communication process, the mental disorder treatment plan firstly includes a conversation text for guiding the target object to explain the reason for generating the mental disorder, so that the user can further communicate with the target object according to the conversation text until the reason for generating the mental disorder of the target object is determined, and then a mental disorder treatment plan is further generated, for example, when the target object is determined to generate depression due to large mental stress, the corresponding mental disorder treatment plan can be used for introducing travel to the target object and a way for relieving the mental stress, such as playing music, guiding a pouring, crying, or guiding reading of humorous.
Step S504 is to send the mental disorder information and the mental disorder grooming scheme to the wearable data acquisition device, so that the wearable data acquisition device displays the mental disorder information and the mental disorder grooming scheme in the dialog scene area image.
Generally speaking, when some patients suspect psychological disorders through observation of emotional fluctuation, the wearable data acquisition device can be worn by the people to help the patients to dredge psychological activities, guide the patients to see the reality, watch everything in the world in a calm and optimistic mood, throw away negative thoughts, continuously mine own values and the like. In addition, the mental disorder information and the mental disorder dispersion scheme are displayed on the display screen of the wearable data acquisition device, and the display screen is transparent, so that the user can synchronously see the mental disorder information and the mental disorder dispersion scheme while visually observing the communication of the target object, and adjust the communication direction or the dispersion strategy in time.
Generally speaking, if any psychological problem occurs, a user needs to consult a psychologist, inconvenience is caused in life, and a plurality of psychological barrier users know that the psychological barrier users cannot be integrated with the society, and cannot easily seek the psychologist to help overcome the psychological barrier, so that the psychological barrier degree is more and more serious, and the psychological barrier can be dredged by the psychological barrier users at any time in a mode, so that the degree is not deepened.
In the mental disorder detection method provided by the embodiment of the present invention, a dialogue scene area image which is sent by the wearable data acquisition device and carries a facial expression, dialogue information and a body language of a target object is received, according to the facial expression, the dialogue information and the body language of the target object, a preset mental disorder detection model is combined to determine mental disorder information of the target object, and according to the mental disorder information of the target object, a mental disorder grooming scheme corresponding to the mental disorder information is generated, so that the wearable data acquisition device displays the mental disorder information and the mental disorder grooming scheme in the dialogue scene area image; the invention has low requirement on the psychological diagnosis skill of the detector, so that the detector can quickly identify the psychological barrier information of the target object and the corresponding psychological barrier leading scheme in real time while seeing the conversation scene area, and the target object can be effectively detected and treated in time, and the applicability is wide.
Fig. 6 is a flowchart of another implementation of a mental disorder detection method according to an embodiment of the present invention, which is different from the foregoing embodiment in that the mental disorder detection method further includes:
step S601, generating a mental disorder training scene according to the dialogue scene area image.
In the embodiment of the invention, generally speaking, when the behavior of a person is not coordinated with the environment to a certain extent and the social adaptation is poor, the psychological activities of the person are reflected to be abnormal. However, although the psychological disorder caused by the fear of social contact can be eliminated by contacting the society and conducting a social training, the psychological adjustment ability of the individual psychological disorder is limited because the psychological disorder is caused by a long-term living environment, and not all people are willing to conduct a social training to overcome the psychological disorder. Therefore, the mental disorder training scene is generated by wearing the wearable data acquisition device by the mental disorder person to acquire specific scene information, namely the dialogue scene area image, in the social environment closely related to the mental disorder person, and further generating the mental disorder training scene according to the dialogue scene area image carrying the facial expression, the dialogue information and the body language of the target object, if the mental disorder person fears to make contact with the neighboring elders, the corresponding mental disorder training scene is further generated by the data processing device 120 by acquiring the dialogue scene area image when the mental disorder person communicates with the neighboring elders,
step S602, sending the mental disorder training scene to the wearable data acquisition device, so that the wearable data acquisition device displays the mental disorder training scene to a user, so that the user performs corresponding training.
In the embodiment of the invention, the wearable data acquisition equipment displays the mental disorder training scene to the user, so that the mental disorder person can perform corresponding targeted training to gradually overcome the mental disorder phenomenon of making an intersection with a neighboring elder around the mental disorder person.
According to the mental disorder detection method provided by the embodiment of the invention, a mental disorder training scene is generated according to the dialogue scene area image, so that the wearable data acquisition device displays the mental disorder training scene to a user, and the user can perform corresponding training. The invention can carry out social environment training closely related to the psychopath, and truly presents the targeted social environment, thereby being beneficial to the psychopath to gradually overcome the psychopath in multiple times of social environment training, and having more pertinence, higher training efficiency and better effect compared with the common training scene.
Fig. 7 is a flowchart of another implementation of a mental disorder detection method according to an embodiment of the present invention, which is different from the foregoing embodiment in that the mental disorder detection method further includes:
step S701, obtaining identity information of the target object.
Step S702, generating a diversified scene model according to the identity information, the facial expression, the dialogue information and the body language of the target object.
Step S703, in response to a selection operation of the user on at least one diversified scene model, sending the diversified scene model to the wearable data acquisition device, so that the wearable data acquisition device displays a virtual scene corresponding to the diversified scene model to the user, so that the user performs corresponding training.
In the embodiment of the invention, on the basis of the above embodiment, the identity information, the facial expression, the dialogue information and the body language of the fear object are obtained according to the social environment closely related to the psychopath, so as to generate the diversified scene model, avoid the user from being boring due to the single scene model, and enhance the training effect.
The mental disorder detection method provided by the embodiment of the invention comprises the steps of acquiring identity information of a target object, generating diversified scene models according to the identity information, facial expressions, dialogue information and body languages of the target object, and responding to selection operation of a user on at least one diversified scene model to enable wearable data acquisition equipment to display virtual scenes corresponding to the diversified scene models for the user so as to enable the user to carry out corresponding training. The invention can avoid the boring of the user due to the single scene model, improve the training interest of the people with mental disorder and strengthen the training effect.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (5)
1. A psychological disorder detection system, characterized in that the psychological disorder detection system comprises a wearable data acquisition device and a data processing device in communication with the wearable data acquisition device;
the wearable data acquisition equipment is used for acquiring a conversation scene area image in a visual range of a user, wherein the conversation scene area image carries a facial expression, conversation information and a body language of a target object; sending the conversation scene area image to the data processing device; receiving mental disorder information and a mental disorder grooming scheme returned by the data processing equipment; displaying the mental disorder information and a mental disorder grooming scheme in the conversation scene area image;
the data processing device is configured to receive a dialog scene area image sent by the wearable data acquisition device; according to the facial expression, the dialogue information and the body language of the target object, combining a preset mental disorder detection model to determine the mental disorder information of the target object; the preset mental disorder detection model is generated by training a plurality of pre-collected mental disorder characteristic samples through a convolutional neural network; generating a psychological barrier dispersion scheme corresponding to the psychological barrier information according to the psychological barrier information of the target object; sending the mental disorder information and the mental disorder grooming scheme to the wearable data acquisition device;
the data processing equipment is further used for generating a mental disorder training scene according to the dialogue scene area image; sending the mental disorder training scene to the wearable data acquisition device;
the wearable data acquisition device is further configured to receive a mental disorder training scene sent by the data processing device; displaying the mental disorder training scene to a user so that the user can carry out corresponding training;
the data processing equipment is also used for acquiring the identity information of the target object; generating a diversified scene model according to the identity information, the facial expression, the dialogue information and the body language of the target object; responding to a selection operation of a user on at least one diversified scene model, and sending the diversified scene model to the wearable data acquisition device;
the wearable data acquisition device is further configured to receive the diversified scene models sent by the data processing device; and displaying the virtual scene corresponding to the diversified scene model to a user so that the user can carry out corresponding training.
2. The mental disorder detection system of claim 1 wherein the wearable data acquisition device comprises:
the system comprises a conversation scene area image acquisition unit, a judgment unit and a display unit, wherein the conversation scene area image acquisition unit is used for acquiring a conversation scene area image in a visual range of a user, and the conversation scene area image carries the facial expression, the conversation information and the body language of a target object;
a dialogue scene area image transmission unit for transmitting the dialogue scene area image to the data processing device;
a mental disorder information and dispersion scheme receiving unit, configured to receive the mental disorder information and the mental disorder dispersion scheme returned by the data processing device; and
and the mental disorder information and dispersion scheme display unit is used for displaying the mental disorder information and the mental disorder dispersion scheme in the conversation scene area image.
3. A mental disorder detection system as claimed in claim 1, wherein said data processing apparatus comprises:
a conversation scene area image receiving unit, configured to receive a conversation scene area image sent by the wearable data acquisition device;
the mental disorder information determining unit is used for determining the mental disorder information of the target object according to the facial expression, the dialogue information and the body language of the target object and by combining a preset mental disorder detection model; the preset mental disorder detection model is generated by training a plurality of pre-collected mental disorder characteristic samples through a convolutional neural network;
a psychological barrier dispersion scheme generation unit, configured to generate a psychological barrier dispersion scheme corresponding to the psychological barrier information according to the psychological barrier information of the target object; and
and the mental disorder information and dispersion scheme sending unit is used for sending the mental disorder information and the mental disorder dispersion scheme to the wearable data acquisition equipment.
4. Mental disorder detection system according to claim 3,
the mental disorder dispersion scheme generation unit is also used for sending the dialogue scene area image to a third-party diagnosis mechanism; receiving a psychological barrier evaluation result generated by the third-party diagnosis mechanism according to the dialogue scene area image; and generating a psychological disorder dispersion scheme according to the psychological disorder information and the psychological disorder evaluation result.
5. A mental disorder detection system according to claim 1, wherein said preset mental disorder detection model is generated by the steps of:
obtaining a plurality of mental disorder feature samples;
acquiring target mental disorder information of the plurality of mental disorder feature samples;
determining first mental disorder information of the first mental disorder feature sample according to the first mental disorder feature sample and a convolutional neural network model containing variable parameters;
calculating a first loss difference between the first mental disorder information and first mental disorder information corresponding to the first mental disorder feature sample;
judging whether the loss difference of the multiple mental disorder characteristic samples meets a preset condition or not;
when the loss difference of the plurality of mental disorder feature samples is judged not to meet the preset condition, adjusting variable parameters in the convolutional neural network model, and returning to the step of determining first mental disorder information of the first mental disorder feature sample according to the first mental disorder feature sample and the convolutional neural network model containing the variable parameters;
and when the loss difference of the plurality of mental disorder characteristic samples is judged to meet a preset condition, determining the current convolutional neural network model containing the variable parameters as a preset mental disorder detection model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011475939.5A CN112450932B (en) | 2020-12-14 | 2020-12-14 | Psychological disorder detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011475939.5A CN112450932B (en) | 2020-12-14 | 2020-12-14 | Psychological disorder detection system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112450932A CN112450932A (en) | 2021-03-09 |
| CN112450932B true CN112450932B (en) | 2022-10-21 |
Family
ID=74804409
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011475939.5A Active CN112450932B (en) | 2020-12-14 | 2020-12-14 | Psychological disorder detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112450932B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106236115A (en) * | 2016-08-12 | 2016-12-21 | 渤海大学 | A kind of psychological test system |
| WO2019075522A1 (en) * | 2017-10-19 | 2019-04-25 | Medibio Limited | Risk indicator |
| CN109272259A (en) * | 2018-11-08 | 2019-01-25 | 梁月竹 | A kind of autism-spectrum disorder with children mood ability interfering system and method |
| US20200367798A1 (en) * | 2019-05-20 | 2020-11-26 | Anthony Frolov | Wearable device for determining psycho-emotional state of user during evaluation or testing |
| CN110507335B (en) * | 2019-08-23 | 2021-01-01 | 山东大学 | Multi-mode information based criminal psychological health state assessment method and system |
| CN112007255B (en) * | 2020-09-02 | 2021-04-13 | 龙马智芯（珠海横琴）科技有限公司 | Psychological treatment method, device and system based on mixed reality and server |
-
2020
- 2020-12-14 CN CN202011475939.5A patent/CN112450932B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112450932A (en) | 2021-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ahmed et al. | A systematic survey on multimodal emotion recognition using learning algorithms | |
| Dey et al. | Exploration of an EEG-based cognitively adaptive training system in virtual reality | |
| Sharma et al. | Objective measures, sensors and computational techniques for stress recognition and classification: A survey | |
| JP2019519053A (en) | Method and system for acquiring, analyzing and generating visual function data and modifying media based on the data | |
| Derrick et al. | Design principles for special purpose, embodied, conversational intelligence with environmental sensors (SPECIES) agents | |
| KR102277820B1 (en) | The psychological counseling system and the method thereof using the feeling information and response information | |
| KR102045569B1 (en) | Appratus for controlling integrated supervisory of pilots status and method for guiding task performance ability of pilots using the same | |
| US20130266925A1 (en) | Embedded Conversational Agent-Based Kiosk for Automated Interviewing | |
| CN109155837A (en) | A kind of wearable TeleConference Bridge of mood sensing | |
| JP2009508553A (en) | System and method for determining human emotion by analyzing eyeball properties | |
| KR20150076167A (en) | Systems and methods for sensory and cognitive profiling | |
| CN105022929A (en) | Cognition accuracy analysis method for personality trait value test | |
| US11417045B2 (en) | Dialog-based testing using avatar virtual assistant | |
| US10772527B2 (en) | Brain matching | |
| Harrison | The Emotiv mind: Investigating the accuracy of the Emotiv EPOC in identifying emotions and its use in an Intelligent Tutoring System | |
| Wu et al. | Emotion classification on eye-tracking and electroencephalograph fused signals employing deep gradient neural networks | |
| Butt et al. | Multimodal personality trait recognition using wearable sensors in response to public speaking | |
| Hossain et al. | Using temporal features of observers’ physiological measures to distinguish between genuine and fake smiles | |
| CN113974589B (en) | Multi-modal behavior paradigm evaluation optimization system and cognitive ability evaluation method | |
| CN112450932B (en) | Psychological disorder detection system and method | |
| Kokini et al. | Quantification of trainee affective and cognitive state in real-time | |
| Azman et al. | Non-intrusive physiological measurement for driver cognitive distraction detection: Eye and mouth movements | |
| Maskeliunas et al. | Are you ashamed? Can a gaze tracker tell? | |
| Bhattacharyya et al. | Collaborative brain-computer interfaces to enhance group decisions in an outpost surveillance task | |
| Rafique et al. | Towards estimation of emotions from eye pupillometry with low-cost devices |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |