CN115813343A - Child behavior abnormity evaluation method and system - Google Patents
Child behavior abnormity evaluation method and system Download PDFInfo
- Publication number
- CN115813343A CN115813343A CN202211543980.0A CN202211543980A CN115813343A CN 115813343 A CN115813343 A CN 115813343A CN 202211543980 A CN202211543980 A CN 202211543980A CN 115813343 A CN115813343 A CN 115813343A
- Authority
- CN
- China
- Prior art keywords
- test
- child
- tested
- behavior
- data
- 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.)
- Pending
Links
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The embodiment of the application provides a child behavior abnormity evaluation method and system, wherein behavior test data of a tested child, which are acquired by data acquisition equipment arranged in a test chamber, are acquired under the condition that the tested child is located in at least one test scene displayed in the test chamber; analyzing and processing the behavior test data of the tested child to determine the behavior characteristics of the tested child; and evaluating the probability of the abnormal behaviors of the tested child according to the behavior characteristics. The test scene corresponds to an abnormal behavior type to be evaluated of the tested child, and the abnormal behavior type comprises at least one performance behavior corresponding to the autism spectrum disorder. The behavior testing data of the tested child under the real scene is collected through the data collecting device, so that the real actions and behaviors of the tested child are comprehensively and accurately recorded. Therefore, the possibility of abnormal behaviors of the tested child can be evaluated by analyzing the behavior test data, the test time is shortened, and the evaluation efficiency of the abnormal behaviors is improved.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a child behavior abnormity assessment method and system.
Background
The abnormal behaviors are also called as behavioral disorders, and refer to the abnormal behaviors and actions of patients caused by the neural developmental disorders in the aspects of cognition, emotion and will. For example, autistic Spectrum Disorder (ASD) includes a group of neurodevelopmental disorders, which is a pervasive developmental Disorder occurring in the growth process of children from birth to infancy, and the behavioral abnormalities of patients are mainly manifested by social interaction Disorder, communication difficulty, narrow range of interest, and repetition of stereotypical behaviors.
In the related art, when evaluating whether behaviors of a tested child are abnormal, a professional is usually required to sequentially test various behavior abilities of the tested child according to test rules corresponding to various psychogenic developmental disorders, so as to determine whether actions and behaviors of the tested child are abnormal according to test results. For example, in assessing whether a child to be tested has an Autism spectrum disorder, a professional physician communicates with the child to be tested on the basis of test items listed in an Autism Diagnosis Observation Scale (ADOS), an Autism Diagnosis Interview Review (ADIR), a Childhood Autism Rating Scale (CARS), and the like, and observes the reaction and action of the child to be tested during the communication, thereby assessing the social interaction, language communication, response behavior, and the like of the child to be tested, and thus determining the risk of the child to be tested for having the Autism spectrum disorder.
However, in the above-mentioned screening method for abnormal behaviors, it is necessary to rely on a professional physician to complete the abnormal behavior evaluation, and it takes several hours to complete the abnormal behavior evaluation corresponding to one example of neurodevelopmental disorder, so that the screening efficiency of various neurodevelopmental disorder diseases is low, and the wide-range popularization is difficult.
Disclosure of Invention
The application provides a method and a system for evaluating the abnormal behavior of the child, which can reduce the professional requirements of an evaluator on the abnormal behavior evaluation process, avoid the requirements on instruction compliance and language ability of the tested child, are also suitable for young children, and shorten the test time required by the abnormal behavior evaluation, thereby improving the screening efficiency of the neurodevelopmental disorder disease related to the abnormal behavior.
In a first aspect, the present application provides a method for evaluating a child behavior abnormality, including:
acquiring behavior test data of the tested child, which is acquired by data acquisition equipment arranged in a test chamber, under the condition that the tested child is positioned in at least one test scene displayed in the test chamber; the test scene corresponds to an abnormal behavior type to be evaluated of the tested child, and the abnormal behavior type comprises at least one performance behavior corresponding to the autism spectrum disorder;
analyzing and processing the behavior test data of the tested child to determine the behavior characteristics of the tested child;
and evaluating the probability of abnormal behaviors of the tested children according to the behavior characteristics.
In a second aspect, the application further provides a child behavior abnormity evaluation system, which comprises a main control room and a test room, wherein the main control room comprises data processing equipment, and data acquisition equipment is arranged in the test room;
the data acquisition equipment is used for acquiring behavior test data of the tested child and sending the behavior test data to the data processing equipment under the condition that the tested child is positioned in the test chamber and shows at least one test scene; the test scene corresponds to an abnormal behavior type to be evaluated of the tested child, and the abnormal behavior type comprises at least one performance behavior corresponding to the autism spectrum disorder;
and the data processing equipment is used for analyzing and processing the behavior test data of the tested child, determining the behavior characteristics of the tested child and evaluating the abnormal probability of the behavior of the tested child according to the behavior characteristics.
In a third aspect, the present application further provides a child behavior abnormality assessment apparatus, including:
the data acquisition module is used for acquiring behavior test data of the tested child, which is acquired by data acquisition equipment arranged in the test chamber, under the condition that the tested child is positioned in at least one test scene displayed in the test chamber; the test scene corresponds to an abnormal behavior type to be evaluated of the tested child, and the abnormal behavior type comprises at least one performance behavior corresponding to the autism spectrum disorder;
the data analysis module is used for analyzing and processing the behavior test data of the tested child and determining the behavior characteristics of the tested child;
and the behavior evaluation module is used for evaluating the probability of the abnormal behavior of the tested child according to the behavior characteristics.
In a fourth aspect, the present application further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.
In a fifth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, which computer program, when executed by a processor, implements the steps of any one of the above-mentioned methods of the first aspect.
In a sixth aspect, the present application further provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of any of the above-mentioned methods of the first aspect.
The technical scheme provided by the application can at least achieve the following beneficial effects:
according to the method and the system for evaluating the abnormal behavior of the child, the behavior test data of the child to be tested, which is acquired by data acquisition equipment arranged in a test chamber, is acquired under the condition that the child to be tested is located in at least one test scene displayed in the test chamber; analyzing and processing the behavior test data of the tested child to determine the behavior characteristics of the tested child; and evaluating the probability of the abnormal behaviors of the tested child according to the behavior characteristics. The test scene corresponds to an abnormal behavior type to be evaluated of the tested child, and the abnormal behavior type comprises at least one performance behavior corresponding to the autism spectrum disorder. Therefore, the behavior test data of the tested child under the real scene is collected through the data collection device, and the real actions and behaviors of the tested child can be comprehensively and accurately recorded through the behavior test data. Therefore, the behavior characteristics of the tested child can be determined by analyzing the behavior test data of the tested child so as to evaluate the possibility of abnormal behavior of the tested child. In addition, in the process of evaluating abnormal behaviors, only a real test scene corresponding to the abnormal behavior type needs to be preset, and data acquisition equipment is deployed in the test scene. In the test process, a professional doctor is not required to guide the tested child to execute a plurality of test items according to the test rule, and the test result is not determined according to medical experience of the professional doctor, so that the test time is shortened, the evaluation efficiency of abnormal behaviors is improved, and the screening efficiency of the neural developmental disorder related to the abnormal behaviors is improved.
Drawings
FIG. 1 is a schematic diagram of a child behavior anomaly assessment system according to an exemplary embodiment of the present application;
FIG. 2 is a flow chart illustrating a method for assessing abnormal behavior of a child according to an exemplary embodiment of the present application;
FIG. 3 is a schematic diagram illustrating a preference test scenario in accordance with an exemplary embodiment of the present application;
FIG. 4 is a schematic diagram illustrating a common focus test scenario according to an exemplary embodiment of the present application;
FIG. 5 is a schematic diagram of an acoustic response test scenario illustrated in an exemplary embodiment of the present application;
fig. 6 is a schematic structural diagram of a behavior abnormality assessment apparatus according to an exemplary embodiment of the present application;
fig. 7 is a schematic structural diagram of a computer device according to an exemplary embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application 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 present application and are not intended to limit the present application.
Currently, in screening early-stage neurological developmental disorder of children, subjective assessment is mainly used, professional doctors communicate with the children to be tested, behaviors of the children to be tested are observed, description of daily behaviors of the children to be tested by guardians is combined to assess whether the children to be tested have abnormal behaviors, and then the possibility that the children to be tested have the neurological developmental disorder is analyzed.
In the child behavior abnormity evaluation process, due to lack of objective and quantitative behavior indexes, the risk of misdiagnosis of the neurodevelopmental disorder is increased; and the behavioral abnormality evaluation result depends on the medical experience of the doctor, and the requirement on the professional degree of the doctor is high.
Based on the above, the application provides a method and a system for evaluating the abnormal behavior of the child, which do not need to carry out invasive examination on the tested child, have no requirements on the intelligence and high-level cognitive ability of the tested child, and do not need the tested child to have certain language ability. By acquiring real behavior test data of the tested child and a tester in a simple interaction process in a test scene, behavior characteristics of the tested child can be analyzed, and the probability of behavior abnormality of the tested child is evaluated. In addition, for a tester, the tester can finish the behavior abnormity evaluation work only by mastering the related operation of the children behavior abnormity evaluation system, so that the behavior abnormity evaluation efficiency is greatly improved. Therefore, by evaluating the abnormal behaviors of the children to be tested, auxiliary information is provided for diagnosing/screening the neurodevelopmental disorder related to the abnormal behaviors, and the diagnosis efficiency and the accuracy of the diagnosis result of the neurodevelopmental disorder are improved. Therefore, early discovery, early intervention and treatment can be realized, and the adverse effect of the neurodevelopmental disorder on children is reduced.
In an exemplary embodiment, as shown in fig. 1, the present application provides a child behavior abnormality assessment system, which includes a main control room including a data processing device 110 and a test room in which a data acquisition device 120 is disposed.
Specifically, under the condition that the tested child is located in the test room to display at least one test scene, the data acquisition device 120 is configured to acquire behavior test data of the tested child and send the behavior test data to the data processing device 110; and the data processing device 110 is configured to analyze and process the behavior test data of the tested child, determine a behavior characteristic of the tested child, and evaluate the probability that the tested child has the behavior abnormality according to the behavior characteristic.
The test scene corresponds to an abnormal behavior type to be evaluated of the tested child, and the abnormal behavior type comprises at least one performance behavior corresponding to the autism spectrum disorder.
Optionally, in order to reduce other interference factors in the testing room, so that the tested child can freely move in the testing room and show the real behavior and action of the tested child, the main control room and the testing room can be independently arranged and separated from each other to form an independent space area. Therefore, when the children to be tested are evaluated in abnormal behaviors, the evaluator controls the testing process in the main control room, the children to be tested and the tester carry out interactive testing in the testing room, and the situation that the actual testing behaviors of the children to be tested are influenced by the existence of the evaluator is avoided.
The number of the test chambers is not limited in the embodiment of the present application. When the method is implemented specifically, a plurality of test chambers can be arranged, and each test chamber is internally provided with a test scene corresponding to an abnormal behavior type; a test room can also be arranged, and test scenes corresponding to various abnormal behavior types are sequentially arranged in the test room according to test requirements; it is also possible to arrange different test scenarios in different areas of one test chamber, in case the test chamber space is large enough.
The evaluator in the main control room may be a physician or other staff capable of operating the data processing device. According to the test requirement, one tester or a plurality of testers can enter the test room to interact with the tested children to complete the test process.
When data acquisition equipment is deployed in a test room, the data acquisition equipment can be deployed in a fixed position area in advance, or the deployment position of the equipment can be adjusted in real time according to test requirements, so that all behavior test data of a tested child in the test room can be comprehensively recorded as a reference.
In some embodiments, the data acquisition device in the present application includes an image acquisition device and a sound acquisition device. The image capture device may be, but is not limited to, an RGB camera, an RGB-D camera, a depth camera, a dual mode camera (e.g., infrared camera + visible light camera), an eye tracker, etc., and the sound capture device may include an array of microphones disposed in the test room, and/or wearable microphones worn on the child and test person under test.
In some embodiments, a data processing apparatus includes a controller, a processor, and a display. The controller is used for controlling the opening, the operation and the closing of the data acquisition equipment in the test chamber and the state of the test prop in the test chamber; the processor is used for receiving the behavior test data sent by the data acquisition equipment, analyzing and processing the behavior test data, determining the behavior characteristics of the tested child, evaluating the probability of behavior abnormality of the tested child and evaluating the risk of the tested child suffering from the neural developmental disorder related to the behavior abnormality; the display is used for displaying information such as behavior test data and evaluation results.
As one example, the data processing device may be any computer device. Such as a terminal or server. The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, portable wearable devices and the like; the server may be, but is not limited to, at least one standalone server, distributed server, cloud server, server cluster, and the like.
In the method for evaluating children behavior abnormality provided in the embodiment of the present application, an execution subject may be any computer device, or may also be a behavior abnormality evaluation apparatus, and the apparatus may be implemented as part or all of a processor in a computer device in a manner of software, hardware, or a combination of software and hardware.
Based on the child behavior abnormity assessment system, the behavior abnormity of the autism spectrum disorder patient is mainly manifested in social communication disorder, communication difficulty, narrow interest range and repetition of stereotypical behaviors, so that when the tested child is screened in an auxiliary manner through behavior abnormity assessment to determine whether the tested child has the autism spectrum disorder, at least one test scene can be arranged in the test room according to the abnormal behavior type corresponding to the autism spectrum disorder, so as to analyze the behavior characteristics of the tested child in the test scene.
In some embodiments, to facilitate screening for autism spectrum disorders, the test scenario disposed in the test room may include at least one of: a preference test scenario, a co-focus test scenario, and a sound response test scenario.
The preference scene comprises a testing person and at least one first testing prop for attracting the vision of the tested child; the common attention test scene comprises a tester and a plurality of second test props which are arranged in front of the tester and used for leading the tested children to watch the tested children together; the sound response test scenario includes at least one controllable sound producing object.
It should be noted that, the first test prop and the second test prop may be arranged according to the actual preference of the tested child, and the type of the test prop is not limited in the embodiment of the present application.
As one example, the first test prop may be a balloon, the second test prop may be a doll, and the controllable sound object may be a bell. It should be understood that the controllable sound object in the test prop and sound response test may be other objects as well.
Furthermore, different test scenes are used for testing different abnormal behavior types of the tested child, so that behavior test data of the tested child, which need to be acquired in different test scenes, are also different. For the three test scenarios, the corresponding data acquisition equipment and behavior test data are as follows:
(1) The test scene is a preference test scene;
in the test scene, the data acquisition device comprises a first image acquisition device, a second image acquisition device and a first sound acquisition device which are arranged in the test scene.
Specifically, being surveyed children and being located the in-process that communicates face to face with the tester to the tester carries out face-to-face with being surveyed children, first image acquisition equipment is used for gathering the first front video of being surveyed children, and second image acquisition equipment is used for gathering the first mutual video of tester and being surveyed children, and first sound collection equipment is used for gathering the first mutual audio frequency of tester and being surveyed children.
Correspondingly, the behavioral test data includes a first front-facing video, a first interactive video, and a first interactive audio.
(2) The test scene is a common attention test scene;
in the test scenario, the data acquisition device includes a third image acquisition device, a fourth image acquisition device, and a second sound acquisition device disposed in the test scenario.
Specifically, being surveyed children and being located opposite with the tester to the tester guides the in-process of being surveyed children to watch on the test stage property, and third image acquisition equipment is used for gathering the second of being surveyed children and openly videos, and fourth image acquisition equipment is used for gathering tester's third, and second sound acquisition equipment is used for gathering tester and surveyed children's second mutual audio frequency.
Correspondingly, the behavioral test data includes a second front-facing video, a third front-facing video, and a second interactive audio.
(3) The test scene is a sound response test scene;
in the test scenario, the data acquisition device includes a fifth image acquisition device and a third sound acquisition device disposed in the test scenario.
Specifically, when the tested child is located in the preset range of the controllable sounding object and the controllable sounding object makes a sound, the fifth image acquisition device is used for acquiring a reaction video of the tested child, and the third sound acquisition device is used for acquiring a reaction audio of the tested child.
Correspondingly, the behavioral test data includes reaction video and reaction audio.
It should be understood that the above-mentioned "first" and "second" etc. are only used for distinguishing the data acquisition devices under different test scenarios, and are not used for limiting the type, position, sequence, etc. of the data acquisition devices.
In the embodiment of the application, the children behavior abnormity evaluation system comprises a main control room and a test room, wherein the main control room and the test room are independent from each other, so that the interference of other personnel to a tested child in the test process can be reduced. Secondly, aiming at screening different neurogenic dysgenesis, at least one test scene for evaluating the abnormal behaviors of the tested child can be set in the test room according to the corresponding abnormal behavior type. Therefore, by arranging the real test scene, the behavior of the tested child in the test scene can be expressed more freely; moreover, the test scene can be adjusted in real time according to the abnormal behavior type to be tested, so that more abnormal behaviors can be evaluated. In addition, when the children to be tested are subjected to behavior abnormity evaluation in a test scene, behavior test data of the children to be tested can be acquired through the data acquisition equipment arranged in the test chamber, the data is more complete and effective, the accuracy is higher, and the behavior characteristics of the children to be tested can be analyzed.
Based on the above-mentioned children behavior abnormity evaluation system, in an exemplary embodiment, as shown in fig. 2, the present application further provides a children behavior abnormity evaluation method, which is applied to the data processing device 110 shown in fig. 1, and includes the following steps:
step 210: and acquiring behavior test data of the tested child, which is acquired by data acquisition equipment arranged in the test chamber, under the condition that the tested child is positioned in at least one test scene displayed in the test chamber.
The test scene corresponds to an abnormal behavior type to be evaluated of the tested child, and the abnormal behavior type comprises at least one performance behavior corresponding to the autism spectrum disorder.
In some embodiments, the behavioral test data of the tested child includes all the behavioral data of the tested child in the test scenario. For example, the voice expression information, the facial feature information, the generalized eye movement information, the limb deflection information, the walking position information, and the like of the child to be tested are recorded in the form of video, audio, images, and the like.
As one example, the test scenario for the assessment of the behavioral abnormality of the child corresponding to the autism spectrum disorder may include at least one of a preference test scenario, a common focus test scenario, and a voice response test scenario.
It should be noted that, for specific contents of the test scenarios, the data acquisition devices arranged in each test scenario, and the behavior test data of the child to be tested that needs to be acquired in each test scenario, reference may be made to the description in the foregoing system embodiment, and details are not repeated here.
It should be understood that, according to the test requirements, test scenes corresponding to the types of abnormal behaviors exhibited in other neurodevelopmental disorders may also be arranged in the test chamber, and the number of the test scenes and the specific arrangement area of the test scenes in the test chamber are not limited in the embodiment of the present application, and may be adjusted according to the actual test requirements.
Step 220: and analyzing and processing the behavior test data of the tested child to determine the behavior characteristics of the tested child.
With the increasingly wide application of machine learning technology in system disease diagnosis and risk prediction, when the behavior characteristics of the tested children are analyzed, a machine learning algorithm can be adopted to analyze and process a large amount of behavior test data of the tested children, so that the machine has a certain induction and summarization capability to assist in behavior abnormity evaluation, the screening time of the neural developmental disorder related to the behavior abnormity is shortened, and the misdiagnosis rate is reduced.
Specifically, the trained neural network model is used for carrying out feature extraction, data fusion, action prediction and other processing on the behavior test data of the tested child, and determining the behavior features of the tested child.
For autism spectrum disorders, the behavioral characteristics to be assessed may include attention preference characteristics, co-concern characteristics, and voice response characteristics. And the different behavior characteristics are determined based on the behavior test data under different test scenes.
Next, the process of analyzing the behavior characteristics of the tested child under different test scenarios will be explained.
(1) If the test scene is a preference test scene, the behavior characteristic is an attention preference characteristic;
in one possible implementation manner, the implementation procedure of step 220 may be: performing frame analysis on the first interactive audio and/or the first interactive video; detecting a first test starting instruction in the first interactive audio, and/or acquiring first human body key point data of a tested child contained in each frame of image in the first front video after detecting a first test starting action of a tester in the first interactive video; analyzing the limb deviation action of the detected child and the action duration corresponding to the limb deviation action according to the first human body key point data corresponding to each frame of image; and evaluating the attention preference characteristics of the tested child according to the limb deviation action and the action duration.
The first test starting instruction may be a first sentence of active voice communication between the tester and the tested child, or may be another fixed starting sentence. The first test starting action may be any action of raising, waving, turning, etc. of the tester, which is not limited in the embodiment of the present application.
In some embodiments, after the first interactive audio is acquired, frame-by-frame detection is performed on the first interactive audio to identify a speech text corresponding to each frame of audio, and further, according to a sampling time stamp of an audio frame corresponding to the first test start instruction as a starting point, a starting frame image corresponding to the sampling time stamp is determined in the first front-side video, and then first human body key point data of the child to be tested is extracted from each frame image of the first front-side video after the starting frame image, so as to analyze attention preference characteristics of the child to be tested.
In some embodiments, after the first interactive video is acquired, frame-by-frame detection is performed on the first interactive video to identify behavior actions of a tester in each frame of interactive image, and then according to a sampling time stamp of the interactive image corresponding to the first test starting action as a starting point, a starting frame image corresponding to the sampling time stamp is determined in the first front video, and then first human body key point data of the tested child is extracted from each frame image of the first front video after the starting frame image, so as to analyze attention preference characteristics of the tested child.
Specifically, frame analysis is carried out on the first front video, human body sub-images of the detected child are determined in each frame of image, then a bone point detection model trained in advance is adopted, human body bone point identification is carried out on the multiple human body sub-images of the detected child, and first human body key point data of the detected child corresponding to each human body sub-image is obtained.
The first human body key point data comprises coordinate information of a plurality of limb key points and face key points of the tested child. Wherein, the key points of the face include, but are not limited to, the left and right canthus of the eyes, the nose tip, the mouth corner, etc.; limb endpoints include, but are not limited to, shoulder, elbow, wrist, chest, abdomen, crotch, knee, ankle, and the like.
In some embodiments, the face orientation of the detected child is analyzed through algorithms such as face detection/face alignment and the like based on the coordinate information of the face key points, and the distribution situation of the attention points of the detected child is determined through spatial transformation.
In some embodiments, the limb deviation action of the detected child can be analyzed according to the key point coordinates of the key points of the human body and the association relationship among the key points. For example, the arm swing posture of the tested child can be analyzed according to the key point coordinates of the shoulder joint, the elbow joint and the wrist joint.
Since the first front video comprises a plurality of frames of continuous images, for a limb deviation action, the action duration of the limb deviation action can be calculated according to the number of image frames and the frame interval duration of the limb deviation action in the first front video.
Further, according to the limb deviation action, determining a focus distribution map of the tested child, wherein the focus distribution map is used for recording the position of at least one first region of interest watched by the tested child; according to the action duration, determining the concentration duration of the tested child watching each first region of interest; and evaluating attention preference characteristics of the tested children according to the attention point distribution diagram and the duration of attention.
It should be understood that the first region of interest may be a region where a tester is located in a preference test scenario, may also be a region where the first test prop is located, and may also be another region in the preference test scenario.
Specifically, according to the attention point distribution diagram, the change condition of the area of the first interest area concerned by the preference of the tested child can be analyzed, and then the behavior of the tested child is determined to be attracted by the first test prop, or attracted by the tested person, or immersed in the world of the tested child, and the action behavior of the tested child is not influenced by the tested person and the first test prop.
Aiming at the duration of concentration, the duration of each action of the tested child can be analyzed, so that the duration of the tested child watching the first test prop or the duration and concentration degree of interaction between the tested child and the tester can be determined.
Wherein the attention preference feature may comprise preference information, i.e. whether the tested child prefers to communicate/co-locate with a person or prefers to co-locate with an object.
As one example, as shown in fig. 3, the first test prop is a balloon. Then, when the preference test is carried out, the tested child is brought into a preference test scene arranged in the test room by the guardian/staff, or the tested child enters the test room by itself. Starting when the tested child enters the spatial edge of the preference test scene, the tester starts to call and make an exaggerated positive expression.
During the test, the tester faces the tested child, the vision of the tested child is attracted through a series of actions and expression changes, and a balloon is placed beside the tester and used for attracting the attention of the tested child. The first image acquisition equipment is arranged behind the body of a tester and is used for clearly shooting the front image of the tested child; the second image acquisition equipment records the interaction condition of the tester and the tested child, and the first sound acquisition equipment records the sound data in the testing process.
After the test is finished, the reaction of the tested child when watching the tester and the first test prop is determined through the first front video collected by the first image collecting device. Specifically, the first image acquisition device records head data and limb data of the detected child, determines the face orientation of the detected child according to the head data, and analyzes the change situation of the attention point of the detected child based on the face orientation; and determining information such as limb orientation, walking condition, playing and concentration duration and the like of the tested child in a preference test scene according to the limb data so as to evaluate the attention preference characteristics of the tested child.
(2) If the test scene is a common attention test scene, the behavior characteristic is a common attention characteristic;
in one possible implementation manner, the implementation procedure of step 220 may be: performing frame analysis on the second interactive audio and/or the third front-side video; detecting a second test starting instruction in the second interactive audio, and/or acquiring a common attention area which is focused by the tested child and guided by the tested person from the third front-facing video after a second test starting action of the tested person is detected in the third front-facing video; after a second test starting instruction and/or a second test starting action are/is detected, acquiring a face image contained in each frame image in a second front video; acquiring head characteristic data of the detected child according to the face image; determining a second region of interest and a region attention duration watched by the gaze of the child to be detected according to the head characteristic data of the child to be detected; and evaluating the common attention characteristics of the tested children according to the common attention area, the second interest area and the area attention duration.
Wherein the common concern area is an area where any one of the second test props is located; the head feature data comprises head orientation, deflection angle and sight direction of the tested child.
Similarly, the second test start command may be the first sentence of active voice communication between the tester and the tested child, or may be another fixed start sentence. The second test starting action may be any action of the tester lifting a hand, waving a hand, second testing props with fingers, and the like, and the embodiment of the application is not limited thereto.
In some embodiments, after the second interactive audio is obtained, frame-by-frame detection is performed on the second interactive audio to identify a speech text corresponding to each frame of audio, and further, according to a sampling time stamp of the audio corresponding to the second test start instruction as a starting point, a starting frame image corresponding to the sampling time stamp is determined in the third front video, and then multi-frame images located behind the starting frame image in the third front video are analyzed to determine a common attention area where a tester guides a tested child to pay attention to.
In some embodiments, after the third front video is acquired, frame-by-frame detection is performed on the third front video to identify behavior actions of a tester in each frame of image, and then according to a sampling time stamp of an image corresponding to the second test starting action as a starting point, a starting frame image corresponding to the sampling time stamp is determined in the third front video, and then a plurality of frames of images located behind the starting frame image in the third front video are analyzed to determine a common attention area where the tester guides a tested child to pay attention.
Specifically, frame analysis is carried out on the third front video, human body sub-images of the testers are determined in each frame of image, then human body bone point recognition is carried out on the multiple human body sub-images of the testers by adopting a pre-trained bone point detection model, and human body key point data of the testers in each human body sub-image is obtained. And finally, determining a common attention area for the tester to guide the tested child to pay attention to according to the human body key point data of the tester.
The human body key point data of the tester comprises key point coordinates of a plurality of human body key points of the tester. For example, according to the coordinates of the key points of the elbow joint, the coordinates of the key points of the wrist joint and the coordinates of other key points of the hand, the direction indicated by the fingers of the tester can be analyzed, and the common attention area can be determined based on the direction.
In addition, while determining the common attention area where the test person guides attention, it is necessary to determine whether the child under test understands the guide of the test person and whether the child under test can follow the guide of the test person to watch the common attention area.
And similarly, performing frame analysis on the second front video of the detected child, determining the human body subimages of the detected child in each frame of image, and then performing human body bone point identification on a plurality of human body subimages of the detected child by adopting a pre-trained bone point detection model to obtain the human body key point data of the detected child in each human body subimage. The human body key point data comprises coordinate information of a face key point and a limb key point, so that the head orientation, the deflection angle and the sight line direction (namely the eyeball watching direction) of the detected child can be determined according to the coordinate information of the face key point of the detected child, and head characteristic data can be obtained; and determining a second region of interest watched by the tested child in the test scene according to the head characteristic data.
The second front video comprises a plurality of frames of continuous images, so that for the same head characteristic data, the number of image frames corresponding to the head characteristic data in the second front video can be determined according to the head orientation and the same sight line direction, and the region attention duration of the second interest region concerned by the tested child is calculated according to the number of the image frames and the frame interval duration.
Further, calculating the area deviation between the common attention area and the second attention area, and determining the attention deviation information of the tested child; determining the action response time length of the detected child according to the second region of interest and the region attention time length; and evaluating the common attention characteristics of the tested children according to the attention deviation information and the action response duration.
The second region of interest may be a region where a tester is located in the common attention test scenario, a region where the second test prop is located, or other regions in the common attention test scenario.
It should be understood that if the common region of interest and the second region of interest are the same, the second region of interest, which indicates that the child under test is looking at, is the region that the test person is guiding and is expected to be interested in by the child under test. Therefore, when the second region of interest watched by the tested child is the common attention region, the fact that the tested child can understand the interaction intention of the testing personnel is shown, and accurate response actions can be given.
The action response time length is the time length for the tested child to understand the meaning and generate response according to the attention guiding action of the tester in the attention guiding process, so that whether the tested child can correctly understand the interactive meaning in the communication process is judged, and a correct response action is given to evaluate the comprehension ability and the reaction ability of the tested child.
The common concern features can include information understanding ability, reaction ability and interaction ability to reflect whether the tested child can normally communicate with the testing personnel and generate correct response to external interaction actions.
As one example, as shown in FIG. 4, the second test object is a doll on a doll stand. When the common attention test is carried out, the tested child is brought into a common attention test scene arranged in the test room by the guardian/staff, or the tested child enters the common attention test scene in the test room by self. The tester sits/stands behind a child table, the tested child sits/stands in front of the child table, and the tested person and the tested child communicate face to face. After the tester starts to signal the start of the hand-lifting, the tester points to any doll on the doll rack on the same plane as the table with the hand and simultaneously issues a voice command (for example, "look at this!") to wait for the tested child to react for 3-5s. A plurality of dolls of a doll stand are sequentially indicated to guide a tested child to pay attention to the indicated dolls.
The third image acquisition device and the fourth image acquisition device can be placed on a desktop and used for shooting a second front video of the tested child and a third front video of the tester.
After the test is finished, extracting skeleton data of the tester according to the third front video of the tester, and calculating a common attention area for the tester to guide attention according to the hand skeleton data and the head steering. Meanwhile, frame removing is carried out on a second front video of the detected child, face detection is carried out in each frame of video image, then a face image in the video is determined through face alignment, the face image is input into a pre-trained neural network model, irrelevant personnel in the video are filtered, and sub-images of the detected child are extracted to calculate head characteristic data and limb characteristic data of the detected child. And then solving the PnP problem by using direct linear transformation based on the head characteristic data to obtain the deflection angle and the pose of the head of the child relative to the camera, and determining a second interested area concerned by the detected child.
And finally, comparing the common attention area guided by the tester to the second attention area concerned by the tested child, and calculating the common attention degree between the tested child and the tester to evaluate the common attention capacity of the tested child.
(3) If the test scene is a sound response test scene, the behavior characteristic is a sound response characteristic;
in one possible implementation manner, the implementation procedure of step 220 may be: performing frame analysis on the reaction video to obtain second human body key point data of the detected child contained in each frame of image in the reaction video; determining pose change information and reaction duration of the detected child according to second human body key point data corresponding to each frame of image; and evaluating the sound response characteristics of the detected child according to the pose change information and the reaction duration.
The extraction of key point data of the human body, the pose calculation and the like can be realized through a pre-trained neural network model, and the feature extraction efficiency and the accuracy of a calculation result are improved.
In some embodiments, the audio response characteristics may include the reaction action and the reaction duration of the audio stimulus, which is used to describe the responsiveness of the tested child to the application of the audio stimulus.
As an example, as shown in FIG. 5, the controllable sound-producing object is a bell. When the sound response test is performed, the tested child is brought into the sound response test scene arranged in the test room by the guardian/staff, or the tested child enters the sound response test scene in the test room by itself. When the tested child walks under the guidance of the tester or passes through the bell hung on the wall, the evaluator in the main control room controls the bell to make a sound through the data processing equipment to wait for the reaction of the tested child.
The fifth image acquisition device can be placed behind the detected child to shoot a reaction video of the detected child after hearing the sound of the bell.
After the test is finished, extracting skeleton data of the tested child from the reaction video, positioning the head position of the tested child, extracting a head image, and/or positioning the limb position of the tested child and extracting a whole body image; the head image and/or the whole body image are input into a pre-trained motion detection model, the deflection motion amplitude, the deflection motion angle and the deflection motion speed of the head/body of the child are calculated according to an optical flow method, and the head rotation condition and the reaction time length of the detected child after the child hears the bell sound are determined, so that the sound response capability of the child is evaluated.
Step 230: and evaluating the probability of abnormal behaviors of the tested children according to the behavior characteristics.
It should be noted that, when the probability of behavior abnormality of the tested child is evaluated, the evaluation may be performed based on the behavior characteristics in one test scenario, or may be performed by combining multiple behavior characteristics obtained in multiple test scenarios, which is not limited in the embodiment of the present application.
If the test scenes comprise a preference test scene, a common attention test scene and a sound response test scene, after the test is performed in sequence, the attention preference characteristic, the common attention characteristic and the sound response characteristic of the tested child can be obtained through analysis. In one possible implementation manner, the implementation procedure of step 230 is: and acquiring the influence weight of each behavior characteristic, and evaluating the probability of the abnormal behavior of the tested child by combining each behavior characteristic and the corresponding influence weight.
Optionally, deep learning may be performed through mass data to obtain a behavior anomaly detection model through training, and after behavior test data of the tested child is obtained, feature extraction is performed through the behavior anomaly detection model, and a probability of behavior anomaly is output.
Further, after the presence of abnormal behaviors in the children to be tested is evaluated, the children to be tested can also be evaluated to have neurodevelopmental disorder related to the abnormal behaviors based on the abnormal behaviors in the children to be tested.
For example, according to the attention preference feature, the common attention feature and the sound response feature of the tested child, whether the tested child has abnormal behaviors such as social communication disorder, communication difficulty, narrow interest range, repetition of stereotyped behaviors and the like is determined. If such abnormal behavior is present in the test child, the test child may be further assessed for risk of having autism spectrum disorder.
In the embodiment of the application, behavior test data of a tested child, which is acquired by data acquisition equipment arranged in a test chamber, is acquired under the condition that the tested child is located in at least one test scene displayed in the test chamber; analyzing and processing the behavior test data of the tested child to determine the behavior characteristics of the tested child; and evaluating the probability of the abnormal behaviors of the tested child according to the behavior characteristics. The test scene corresponds to an abnormal behavior type to be evaluated of the tested child, and the abnormal behavior type comprises at least one performance behavior corresponding to the autism spectrum disorder. Therefore, the behavior test data of the tested child under the real scene is collected through the data collection device, and the real actions and behaviors of the tested child can be comprehensively and accurately recorded through the behavior test data. Therefore, the behavior characteristics of the tested child can be determined by analyzing the behavior test data of the tested child so as to evaluate the possibility of abnormal behavior of the tested child. In addition, in the process of evaluating abnormal behaviors, only a real test scene corresponding to the abnormal behavior type needs to be preset, and data acquisition equipment is deployed in the test scene. In the test process, a professional doctor is not required to guide the tested child to execute a plurality of test items according to the test rule, and the test result is not determined according to medical experience of the professional doctor, so that the test time is shortened, the evaluation efficiency of abnormal behaviors is improved, and the screening efficiency of the neural developmental disorder related to the abnormal behaviors is improved.
Based on the same technical concept, the embodiment of the application also provides a child behavior abnormity evaluation device corresponding to the child behavior abnormity evaluation method. The implementation scheme provided by the device in solving the technical problem is similar to the implementation scheme described in the above method embodiments, so that the specific function limitations in one or more of the embodiments of the behavior abnormality assessment device provided below can be referred to the limitations of the related steps in the above method for assessing the behavior abnormality of the child, and are not described herein again.
In an exemplary embodiment, as shown in fig. 6, an embodiment of the present application further provides a behavior abnormality assessment apparatus, where the apparatus 600 includes:
the data acquisition module 610 is configured to acquire behavior test data of the child to be tested, which is acquired by data acquisition equipment arranged in the test chamber, when the child to be tested is located in at least one test scene displayed in the test chamber; the test scene corresponds to an abnormal behavior type to be evaluated of the tested child, and the abnormal behavior type comprises at least one performance behavior corresponding to the autism spectrum disorder;
the data analysis module 620 is used for analyzing and processing the behavior test data of the tested child to determine the behavior characteristics of the tested child;
and the behavior evaluation module 630 is used for evaluating the probability of the detected child having the abnormal behavior according to the behavior characteristics.
In a possible implementation manner, the test scene comprises a preference test scene, wherein the preference scene comprises a test person and at least one first test prop for attracting the vision of the tested child;
the data acquisition equipment comprises first image acquisition equipment, second image acquisition equipment and first sound acquisition equipment which are arranged in a test scene; in the process that the tested child is located opposite to the testing person and the tested child communicate face to face, the first image acquisition device is used for acquiring a first front video of the tested child, the second image acquisition device is used for acquiring a first interactive video of the testing person and the tested child, and the first sound acquisition device is used for acquiring a first interactive audio of the testing person and the tested child;
correspondingly, the behavioral test data includes a first front video, a first interactive video, and a first interactive audio.
In one possible implementation, the behavioral characteristics include attention preference characteristics; a data analysis module 620 comprising:
the first audio and video analysis unit is used for carrying out frame analysis on the first interactive audio and/or the first interactive video;
the first key point detection unit is used for detecting a first test starting instruction in the first interactive audio and/or acquiring first human body key point data of the detected child contained in each frame of image in the first front video after detecting a first test starting action of a tester in the first interactive video;
the first action analysis unit is used for analyzing the limb deviation action of the detected child and the action duration corresponding to the limb deviation action according to the first human body key point data corresponding to each frame of image;
and the first characteristic evaluation unit is used for evaluating attention preference characteristics of the tested child according to the limb deviation action and the action duration.
In a possible implementation manner, the feature evaluation unit is specifically configured to:
determining a focus distribution map of the tested child according to the limb deviation action; the attention point distribution diagram is used for recording the position of at least one first region of interest watched by the vision of the tested child;
according to the action duration, determining the concentration duration of the tested child watching each first region of interest;
and evaluating attention preference characteristics of the tested children according to the attention point distribution diagram and the concentration duration.
In a possible implementation manner, the test scene comprises a common attention test scene, the common attention test scene comprises a tester and a plurality of second test props which are arranged in front of the tester and used for leading the tested children to watch at the same time;
the data acquisition equipment comprises third image acquisition equipment, fourth image acquisition equipment and second sound acquisition equipment which are arranged in a test scene; when the tested child is located opposite to the testing personnel and the testing personnel guides the tested child to watch the test prop, the third image acquisition device is used for acquiring a second front video of the tested child, the fourth image acquisition device is used for acquiring a third front video of the testing personnel, and the second sound acquisition device is used for acquiring a second interactive audio of the testing personnel and the tested child;
correspondingly, the behavioral test data includes a second front-facing video, a third front-facing video, and a second interactive audio.
In one possible implementation, the behavioral characteristics include common attention characteristics; a data analysis module 620 comprising:
the second audio and video analysis unit is used for carrying out frame analysis on the second interactive audio and/or the third front video;
the area determining unit is used for detecting a second test starting instruction in the second interactive audio and/or acquiring a common attention area which is used for guiding the tested child to pay attention to by the testing personnel from the third front-view video after a second test starting action of the testing personnel is detected in the third front-view video; the common attention area is an area where any second test prop is located;
the face detection unit is used for acquiring a face image contained in each frame image in the second front video after a second test starting instruction and/or a second test starting action are/is detected;
the characteristic extraction unit is used for acquiring head characteristic data of the detected child according to the face image; the head characteristic data comprises the head orientation, the deflection angle and the sight line direction of the tested child;
the second action analysis unit is used for determining a second region of interest and a region attention duration watched by the gaze of the detected child according to the head characteristic data of the detected child;
and the second characteristic evaluation unit is used for evaluating the common attention characteristics of the tested children according to the common attention area, the second interested area and the area attention duration.
In a possible implementation manner, the second feature evaluation unit is specifically configured to:
calculating the area deviation between the common attention area and the second attention area, and determining the attention deviation information of the tested child;
determining the action response time of the detected child according to the second region of interest and the region attention time;
and evaluating the common attention characteristics of the tested children according to the attention deviation information and the action response duration.
In one possible implementation, the test scenario includes a sound response test scenario, and the sound response test scenario includes at least one controllable sound object;
the data acquisition equipment comprises fifth image acquisition equipment and third sound acquisition equipment which are arranged in a test scene; when the tested child is located in the preset range of the controllable sound-producing object and the controllable sound-producing object produces sound, the fifth image acquisition device is used for acquiring the reaction video of the tested child, and the third sound acquisition device is used for acquiring the reaction audio of the tested child;
correspondingly, the behavioral test data includes reaction video and reaction audio.
In one possible implementation, the behavioral characteristic includes a voice response characteristic; a data analysis module 620 comprising:
the second key point detection unit is used for carrying out frame analysis on the reaction video and acquiring second human body key point data of the detected child contained in each frame of image in the reaction video;
the third action analysis unit is used for determining pose change information and reaction duration of the detected child according to second human body key point data corresponding to each frame of image;
and the third characteristic evaluation unit is used for evaluating the sound response characteristics of the detected child according to the pose change information and the reaction duration.
It should be noted that all or part of the modules in the above behavior abnormality evaluation apparatus may be implemented by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In an exemplary embodiment, the embodiment of the present application further provides a computer device. The computer device can be used as a data processing device for implementing the child behavior abnormality assessment method in the foregoing embodiments. As shown in fig. 7, the computer device includes one or more processors 710, a memory 720, a system bus 730, and a communication interface 740, and the processors 710, the memory 720, and the communication interface 740 are connected by the system bus 730.
The processor may be, among other things, a Central Processing Unit (CPU) or other form of Processing unit having data Processing capabilities and/or instruction execution capabilities, and may control other components in the computer device to perform desired functions.
Optionally, the processor is provided with application software related to data processing and the like.
The memory may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile Memory may include, for example, a Random Access Memory (RAM), a cache Memory (cache), and/or the like. As one example, the non-volatile Memory may include a Read-Only Memory (ROM), a hard disk, a flash Memory, and the like. One or more computer program instructions may be stored on the computer-readable storage medium and executed by the processor to implement the child behavior abnormality assessment methods in the embodiments illustrated above and/or other desired functions.
The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies.
In some embodiments, the computer device may further comprise: input devices and output devices (not shown), which are interconnected by a bus system and/or other form of connection mechanism (not shown). The input device can be a touch layer covered on a display screen, a key, a track ball or a touch pad arranged on a computer equipment shell, an external keyboard, a touch pad or a mouse and the like. The output device can output various information to the outside. Such as a display/screen, speakers, and a communication network and its connected remote output devices.
Of course, for simplicity, only some of the components of the computer device relevant to the embodiments of the present application are shown in fig. 7, and besides, the computer device may also include any other suitable components according to specific application situations.
In an exemplary embodiment, the present application further provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor in a computer device, can implement the child behavior abnormality assessment method provided by the foregoing embodiment.
In an exemplary embodiment, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor in a computer device, the computer program can implement the child behavior abnormality assessment method provided by the foregoing embodiment.
The above embodiments are only intended to be specific embodiments of the present application, and are not intended to limit the scope of the embodiments of the present application, and any modifications, equivalent substitutions, improvements, and the like made on the basis of the technical solutions of the embodiments of the present application should be included in the scope of the embodiments of the present application.
Claims (14)
1. A method for evaluating a child behavior abnormality, comprising:
the method comprises the steps that under the condition that a tested child is located in at least one test scene displayed in a test room, behavior test data of the tested child, which are collected by data collection equipment arranged in the test room, are obtained; the test scene corresponds to an abnormal behavior type to be evaluated of the tested child, and the abnormal behavior type comprises at least one performance behavior corresponding to the autism spectrum disorder;
analyzing and processing the behavior test data of the tested child to determine the behavior characteristics of the tested child;
and evaluating the probability of the abnormal behavior of the tested child according to the behavior characteristics.
2. The method of claim 1, wherein the test scenario comprises a preference test scenario, the preference scenario comprising a test person and at least one first test prop for attracting the eye of the tested child;
the data acquisition equipment comprises first image acquisition equipment, second image acquisition equipment and first sound acquisition equipment which are arranged in the test scene; during the process that the tested child is located opposite to the tested person and the tested child are in face-to-face communication, the first image acquisition device is used for acquiring a first front video of the tested child, the second image acquisition device is used for acquiring a first interactive video of the tested person and the tested child, and the first sound acquisition device is used for acquiring a first interactive audio of the tested person and the tested child;
correspondingly, the behavioral test data includes the first front-facing video, the first interactive video, and the first interactive audio.
3. The method of claim 2, wherein the behavioral characteristics include attention preference characteristics;
the analyzing and processing the behavior test data of the tested child to determine the behavior characteristics of the tested child includes:
performing frame parsing on the first interactive audio and/or the first interactive video;
detecting a first test starting instruction in the first interactive audio, and/or acquiring first human body key point data of the tested child contained in each frame of image in the first front video after detecting a first test starting action of the testing person in the first interactive video;
analyzing the limb deviation action of the detected child and the action duration corresponding to the limb deviation action according to first human body key point data corresponding to each frame of image;
and evaluating attention preference characteristics of the tested child according to the limb deviation action and the action duration.
4. The method of claim 3, wherein said evaluating attention preference characteristics of said subject child based on said limb deviation action and said action duration comprises:
determining a focus distribution map of the detected child according to the limb deviation action; the attention point distribution map is used for recording the position of at least one first region of interest watched by the measured child;
according to the action duration, determining the concentration duration of the tested child watching each first region of interest;
and evaluating attention preference characteristics of the tested child according to the attention point distribution diagram and the concentration duration.
5. The method according to any one of claims 1 to 4, wherein the test scenario comprises a common attention test scenario, the common attention test scenario comprises a test person and a plurality of second test props arranged in front of the test person for guiding the test person to focus on the tested children together;
the data acquisition device comprises a third image acquisition device, a fourth image acquisition device and a second sound acquisition device which are arranged in the test scene; in the process that the tested child is located opposite to the tested person and the tested person guides the tested child to watch the test prop, the third image acquisition device is used for acquiring a second front video of the tested child, the fourth image acquisition device is used for acquiring a third front video of the tested person, and the second sound acquisition device is used for acquiring a second interactive audio of the tested person and the tested child;
correspondingly, the behavioral test data includes the second front-facing video, the third front-facing video, and the second interactive audio.
6. The method of claim 5, wherein the behavioral features comprise common concern features;
the analyzing and processing the behavior test data of the tested child to determine the behavior characteristics of the tested child includes:
performing frame parsing on the second interactive audio and/or the third front-side video;
detecting a second test starting instruction in the second interactive audio, and/or acquiring a common attention area which is focused by the tested child and guided by the tested person from the third front-view video after a second test starting action of the tested person is detected in the third front-view video; the common concern area is an area where any one of the second test props is located;
after the second test starting instruction and/or the second test starting action are/is detected, acquiring a face image contained in each frame image in the second front video;
acquiring head feature data of the detected child according to the face image; the head feature data comprises head orientation, deflection angle and sight line direction of the tested child;
according to the head feature data of the detected child, determining a second region of interest and a region attention duration watched by the gaze of the detected child;
and evaluating the common attention characteristics of the tested children according to the common attention area, the second interest area and the area attention duration.
7. The method of claim 6, wherein said evaluating the common interest characteristics of the children under test based on the common interest region, the second interest region and the region interest duration comprises:
calculating the regional deviation between the common attention region and the second attention region, and determining attention deviation information of the tested child;
determining the action response time length of the detected child according to the second region of interest and the region attention time length;
and evaluating the common attention characteristics of the tested children according to the attention deviation information and the action response duration.
8. The method of any one of claims 1 to 4, wherein the test scenario comprises a sound response test scenario including at least one controllable sound emitting object therein;
the data acquisition device comprises a fifth image acquisition device and a third sound acquisition device which are arranged in the test scene; when the tested child is located within the preset range of the controllable sound-producing object and the controllable sound-producing object produces sound, the fifth image acquisition device is used for acquiring a reaction video of the tested child, and the third sound acquisition device is used for acquiring a reaction audio of the tested child;
correspondingly, the behavior test data comprises the reaction video and the reaction audio.
9. The method of claim 8, wherein the behavioral characteristics include an audible response characteristic;
the analyzing and processing the behavior test data of the tested child to determine the behavior characteristics of the tested child includes:
performing frame analysis on the reaction video to obtain second human body key point data of the detected child contained in each frame of image in the reaction video;
determining pose change information and reaction duration of the detected child according to second human body key point data corresponding to each frame of image;
and evaluating the sound response characteristics of the detected child according to the pose change information and the reaction duration.
10. The children behavior abnormity evaluation system is characterized by comprising a main control room and a test room, wherein the main control room comprises data processing equipment, and data acquisition equipment is arranged in the test room;
the data acquisition equipment is used for acquiring behavior test data of the tested child and sending the behavior test data to the data processing equipment under the condition that the tested child is positioned in the test chamber and shows at least one test scene; the test scene corresponds to an abnormal behavior type to be evaluated of the tested child, and the abnormal behavior type comprises at least one performance behavior corresponding to the autism spectrum disorder;
the data processing device is used for analyzing and processing the behavior test data of the tested child, determining the behavior characteristics of the tested child, and evaluating the probability of the abnormal behavior of the tested child according to the behavior characteristics.
11. The system of claim 10, wherein the test scenario comprises at least one of: a preference test scenario, a common attention test scenario and a sound response test scenario;
wherein, the preference scene comprises a testing person and at least one first testing prop used for attracting the vision of the tested child; the common attention test scene comprises a tester and a plurality of second test props which are arranged in front of the tester and used for leading the tested children to watch the test props together; the sound response test scenario includes at least one controllable sound object.
12. The system of claim 11, wherein if the test scenario is a preference test scenario, the data acquisition device comprises a first image acquisition device, a second image acquisition device and a first sound acquisition device disposed in the test scenario; during the process that the tested child is located opposite to the tested person and the tested child are in face-to-face communication, the first image acquisition device is used for acquiring a first front video of the tested child, the second image acquisition device is used for acquiring a first interactive video of the tested person and the tested child, and the first sound acquisition device is used for acquiring a first interactive audio of the tested person and the tested child;
correspondingly, the behavioral test data includes the first front-facing video, the first interactive video, and the first interactive audio.
13. The system of claim 11, wherein if the test scenario is a common attention test scenario, the data acquisition device comprises a third image acquisition device, a fourth image acquisition device and a second sound acquisition device disposed in the test scenario; in the process that the tested child is located opposite to the tested person and the tested person guides the tested child to watch the test prop, the third image acquisition device is used for acquiring a second front video of the tested child, the fourth image acquisition device is used for acquiring a third front video of the tested person, and the second sound acquisition device is used for acquiring a second interactive audio of the tested person and the tested child;
correspondingly, the behavioral test data includes the second front-facing video, the third front-facing video, and the second interactive audio.
14. The system of claim 11, wherein if the test scenario is a sound response test scenario, the data acquisition device comprises a fifth image acquisition device and a third sound acquisition device disposed in the test scenario; when the tested child is located within the preset range of the controllable sound-producing object and the controllable sound-producing object produces sound, the fifth image acquisition device is used for acquiring a reaction video of the tested child, and the third sound acquisition device is used for acquiring a reaction audio of the tested child;
correspondingly, the behavior test data comprises the reaction video and the reaction audio.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211543980.0A CN115813343A (en) | 2022-12-01 | 2022-12-01 | Child behavior abnormity evaluation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211543980.0A CN115813343A (en) | 2022-12-01 | 2022-12-01 | Child behavior abnormity evaluation method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115813343A true CN115813343A (en) | 2023-03-21 |
Family
ID=85543939
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211543980.0A Pending CN115813343A (en) | 2022-12-01 | 2022-12-01 | Child behavior abnormity evaluation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115813343A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116884096A (en) * | 2023-09-08 | 2023-10-13 | 首都医科大学附属北京友谊医院 | Method, system and equipment for evaluating intelligent development degree of infants |
-
2022
- 2022-12-01 CN CN202211543980.0A patent/CN115813343A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116884096A (en) * | 2023-09-08 | 2023-10-13 | 首都医科大学附属北京友谊医院 | Method, system and equipment for evaluating intelligent development degree of infants |
CN116884096B (en) * | 2023-09-08 | 2023-12-01 | 首都医科大学附属北京友谊医院 | Method, system and equipment for evaluating intelligent development degree of infants |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11989340B2 (en) | Systems, methods, apparatuses and devices for detecting facial expression and for tracking movement and location in at least one of a virtual and augmented reality system | |
CN110313923B (en) | Autism early-stage screening system based on joint attention ability test and audio-video behavior analysis | |
CN110890140B (en) | Virtual reality-based autism rehabilitation training and capability assessment system and method | |
US20190110754A1 (en) | Machine learning based system for identifying and monitoring neurological disorders | |
KR102155309B1 (en) | Method for predicting cognitive impairment, server, user device and application implementing the method | |
US11699529B2 (en) | Systems and methods for diagnosing a stroke condition | |
US11301775B2 (en) | Data annotation method and apparatus for enhanced machine learning | |
CN110363129B (en) | Early autism screening system based on smiling paradigm and audio-video behavior analysis | |
CN109285602B (en) | Master module, system and method for self-checking a user's eyes | |
WO2014150684A1 (en) | Artifact as a feature in neuro diagnostics | |
JP2007289656A (en) | Image recording apparatus, image recording method and image recording program | |
JP2007289659A (en) | Image recording apparatus, image recording method, and image recording program | |
CN112890815A (en) | Autism auxiliary evaluation system and method based on deep learning | |
CN108882853A (en) | Measurement physiological parameter is triggered in time using visual context | |
JP2024512045A (en) | Visual system for diagnosing and monitoring mental health | |
CN111222464B (en) | Emotion analysis method and system | |
CN115813343A (en) | Child behavior abnormity evaluation method and system | |
CN113974589B (en) | Multi-modal behavior paradigm evaluation optimization system and cognitive ability evaluation method | |
Cheng et al. | Computer-aided autism spectrum disorder diagnosis with behavior signal processing | |
CN110364260A (en) | Autism earlier evaluations apparatus and system based on indicative language paradigm | |
Rescio et al. | Ambient and wearable system for workers’ stress evaluation | |
Jo et al. | Rosbag-based multimodal affective dataset for emotional and cognitive states | |
EP4325517A1 (en) | Methods and devices in performing a vision testing procedure on a person | |
CN115553779A (en) | Emotion recognition method and device, electronic equipment and storage medium | |
Shahid et al. | Data-driven automated detection of autism spectrum disorder using activity analysis: A review |
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 |