CN116665892A

CN116665892A - Autism evaluation system, method and device

Info

Publication number: CN116665892A
Application number: CN202310300588.1A
Authority: CN
Inventors: 刘靖; 李雪; 郭延庆; 程建宏; 马增慧; 金衍
Original assignee: Beijing Azuaba Technology Co ltd; PEKING UNIVERSITY SIXTH HOSPITAL
Current assignee: Beijing Azuaba Technology Co ltd; PEKING UNIVERSITY SIXTH HOSPITAL
Priority date: 2023-03-24
Filing date: 2023-03-24
Publication date: 2023-08-29
Anticipated expiration: 2043-03-24
Also published as: CN116665892B

Abstract

An autism spectrum disorder assessment system, method and apparatus are disclosed. The system comprises: the scene module is used for setting corresponding scenes for the paradigm of evaluating the evaluated person and comprises a prompting device; the model switching module is used for acquiring specific voice and specific limb actions of the evaluator so as to determine the start, the end and the interruption of the model evaluation; the behavior data acquisition module is used for acquiring behavior data of the evaluated person in the scene set by the scene module; the system comprises a data processing module, a prompt device and a data processing module, wherein the data processing module is used for generating multi-mode behavior data aiming at an estimated person based on the behavior data and the questionnaire information and generating an autism spectrum disorder estimation result based on the multi-mode behavior data, and the prompt device comprises a display device based on polarization and a receiving device worn by the estimated person.

Description

Autism evaluation system, method and device

Technical Field

The present disclosure relates to the technical field of evaluation and calculation processing of autism spectrum disorders in children, and more particularly, to an autism spectrum disorder evaluation system, method and apparatus.

Background

Autism spectrum disorder (Autism Spectrum Disorder, ASD) is a neurological disorder that contributes to mental disorders, a neurological disorder that arises in infancy. The disorder men are seen in many cases, and mainly show social interaction disorder, speech development disorder, behavior inscription and interest stenosis at different degrees. About 50% of children with autism spectrum disorder are associated with a more pronounced mental retardation. Some infants have abnormal ability to express in some way in the background of general mental retardation. Generally, around 3 years of age is the prime time to find autism spectrum disorders. According to existing research results, the age 7 years ago is the best time to effectively treat children with autism spectrum disorders. Thus, finding and confirming autism spectrum disorder children as early as possible would be very beneficial for rehabilitation interventions. It is advantageous to perform rehabilitation interventions on children with autism spectrum disorders as early as possible. With age, rehabilitation interventions will not only be effective, but also miss the optimal treatment time. This also greatly increases the economic burden of children and families with autism spectrum disorders.

One current general assessment method for autism spectrum disorder subjects is the autism judgment and observation scale (ADOS). ADOS is the initiative of the evaluateee by the playing assessment of the semi-structure. The assessed content may include social initiation, play, gestures, requests, eye contact, common attention, etc. applied for viewing and encoded by the inspector. With ADOS, inspectors elicit target behavior by utilizing specific toys, activities, interview questions, and the like, and observe and encode lettering behavior, sensory sensitivity, abnormal behavior, and the like. ADOS typically takes about 30-60 minutes to observe, followed by scoring taking about 15 minutes. ADOS typically uses 29 questions (12-14 of which are used to score). The overall assessment process of ADOS takes about 60-90 minutes. ADOS must be done by a professional. Another common method of assessment of autism spectrum disorder is the autism diagnostic interview scale-revision (Autism Diagnostic Interview Revised, ADI-R). ADI-R has a high confidence level between reviewers. Researchers interview the person with the person being evaluated with 93 major questions and multiple sub-elements (in total over 150) that are semi-structured. It takes 2.5-3 hours to perform ADI-R. ADI-R is also a must-be done by a professional.

One problem with currently known autism spectrum disorder assessment tools is that they are relatively time consuming and must be done by very specialized personnel. The experience of the practitioner plays a very critical role in the accuracy of the determination. At present, professionals who diagnose autism spectrum disorders in China are very deficient. These professionals focus mainly on first line cities such as Beijing, shanghai, guangzhou, shenzhen, and the like. This results in a significant waiting time for the person to be evaluated to take, and diagnosis is often significantly delayed.

Another problem with currently known tools for risk assessment of autism spectrum disorders is that the known tools typically require an evaluator and a person with support to reach a diagnostically-capable facility long distance. It is difficult to reserve to professionals. The burden of the transportation and the food-destination expenses for people with the food is very heavy. As a result, this limits the ability of average raters to obtain suitable resources for risk assessment of autism spectrum disorders, especially those assessed in remote areas and raters. Furthermore, in unfamiliar circumstances, the subject often cannot exhibit natural behavioral characteristics. This results in limited acquisition and knowledge of the information of the subject by the professional. In the actual evaluation process, the time spent by the professional on each subject to be evaluated is limited. This further increases the difficulty of accurate evaluation, resulting in a higher probability of judgment error.

Currently, there have been some researchers attempting to improve autism spectrum disorder assessment tools by technical means.

For example, the document "autism evaluation system combining questionnaire and multimodal behavior data analysis" with patent No. ZL201910606484.7 proposes an autism evaluation system combining questionnaire and multimodal behavior data analysis.

In the technical solution of the document with patent number ZL201910606484.7, when using a questionnaire, the questionnaire content is too much, which is still relatively long. This is very a trial of the patience and understanding of the person taking care, severely affecting the quality of the questionnaire data. There is some irrational nature of this solution. In the technical scheme of ZL201910606484.7, the audio and video acquisition equipment and the scene are too complex, the cost is high, and the popularization is not facilitated. For some behavioral patterns, such as a notch action or improper behavior, the evaluators have difficulty in presenting in short videos. Only in the environment familiar to the person to be evaluated, it is possible to capture the behavior prescribed in such a system by long-term observation. Thus, such systems have certain limitations.

Therefore, an evaluation system is needed to collect the fully natural characteristic behavior information of the evaluated person, assist the professional to comprehensively understand the evaluated person, shorten the time for evaluating the autism spectrum disorder, and improve the accuracy of the autism spectrum disorder evaluation.

Disclosure of Invention

It is an object of the present disclosure to provide a new solution for the evaluation of autism spectrum disorders.

According to a first aspect of the present disclosure there is provided an autism spectrum disorder assessment system, comprising: the questionnaire data collection module is used for collecting and recording the assessed person and the relevant questionnaire information thereof; the scene module is used for carrying out corresponding scenes of the paradigm setting of the evaluated person and comprises a prompting device; the model switching module is used for acquiring specific voice and specific limb actions of the evaluator so as to determine the start, the end and the interruption of the model evaluation; the behavior data acquisition module is used for acquiring behavior data of the evaluated person in the scene set by the scene module; the data processing module is used for generating multi-mode behavior data aiming at the evaluated person based on the questionnaire information and the behavior data and generating an autism spectrum disorder evaluation result based on the multi-mode behavior data. The prompting device comprises a display device arranged at a visible position of the evaluator and a receiving device worn by the evaluator. The display device generates an output image, the output image comprises a first sub-image with a first polarization state and a second sub-image with a second polarization state, the first polarization state and the second polarization state are orthogonal, the first sub-image comprises prompt information, and the first sub-image and the second sub-image in the output image are overlapped so that the prompt information cannot be distinguished by human eyes. The receiving device comprises a light filtering device which filters the second sub-image with the second polarization state so as to output the first sub-image for the evaluator to view the prompt information.

According to a second aspect of the present disclosure there is provided a method of assessing autism spectrum disorder comprising: collecting and recording the assessed person and the related questionnaire information; setting corresponding scenes based on a paradigm of evaluating an evaluated person, wherein a prompting device is arranged in the scenes; for obtaining a specific voice and a specific limb movement of the evaluator, thereby determining the start, end and interruption of the paradigm evaluation; collecting behavior data of an evaluated person in a scene set by a scene module; generating multi-modal behavioral data for the subject based on the questionnaire information and the behavioral data; and generating an autism spectrum disorder assessment result based on the multimodal behavioral data, wherein the prompting device comprises a display device arranged at a visible position of the evaluator and a receiving device worn by the evaluator, wherein the display device generates an output image comprising a first sub-image of a first polarization state and a second sub-image of a second polarization state, the first polarization state and the second polarization state being orthogonal, the first sub-image comprising prompting information, the first sub-image and the second sub-image in the output image being superimposed such that the prompting information is not distinguishable by a human eye, and wherein the receiving device comprises a light filtering device that filters the second sub-image of the second polarization state, thereby outputting the first sub-image for viewing by the evaluator.

According to a third aspect of the present disclosure, there is provided an autism spectrum disorder assessment device, comprising: means for collecting and recording questionnaire information of an evaluative subject related to autism spectrum disorder; a unit that sets a corresponding scene based on a paradigm in which an evaluators are evaluated, wherein a prompting device is set in the scene; means for acquiring a specific voice and a specific limb movement of the evaluator, thereby determining a start, an end and an interruption of the paradigm evaluation; a unit for collecting behavior data of the evaluators in the scene set by the scene module; a unit for generating multimodal behavioral data for the subject based on the questionnaire information and the behavioral data; and means for generating an autism spectrum disorder assessment result based on the multimodal behavioral data, wherein the prompting means comprises a display means disposed in a visible position of the evaluator and a receiving means worn by the evaluator, wherein the display means generates an output image comprising a first sub-image of a first polarization state and a second sub-image of a second polarization state, the first polarization state and the second polarization state being orthogonal, the first sub-image comprising a prompting message, the first sub-image and the second sub-image in the output image being superimposed such that the prompting message is not resolved by a human eye, and wherein the receiving means comprises a light filtering means that filters the second sub-image of the second polarization state so as to output the first sub-image for the evaluator to view the prompting message.

According to embodiments of the present disclosure, the impact on the evaluator is reduced while providing a prompt to the evaluator.

Other features of the present disclosure and its advantages will become apparent from the following detailed description of exemplary embodiments of the disclosure, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure.

Fig. 1 shows a schematic block diagram of an autism spectrum disorder assessment system according to one embodiment.

Fig. 2 shows a schematic flow chart of a method of autism spectrum disorder assessment according to one embodiment.

FIG. 3 shows a schematic diagram of a reminder device according to one embodiment.

Fig. 4 shows a schematic view of a reminder device according to another embodiment.

FIG. 5 illustrates a schematic diagram of a scene module according to one embodiment.

Fig. 6 illustrates an exemplary computing device that may be used to implement an autism spectrum disorder assessment system according to one embodiment.

Fig. 7 shows a schematic network in which an autism spectrum disorder assessment system may be arranged according to one embodiment.

Detailed Description

Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless it is specifically stated otherwise.

The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.

Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.

In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of exemplary embodiments may have different values.

It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.

The autism spectrum disorder assessment system shown in fig. 1 includes: the system comprises a questionnaire data collection module 1, a scene module 2, a paradigm switching module 3, a behavior data acquisition module 4 and a data processing module 5.

The questionnaire data collection module 1 is used for collecting and recording the assessed person and the questionnaire information related to the assessed person. For example, a guardian of the subject may use the questionnaire data collection module 1 to collect information about the subject into the evaluation system. Alternatively, the evaluator may collect the information of the evaluator using the questionnaire data collection module 1. The questionnaire data collection module 1 may include a microphone, speaker, keyboard, etc. input or output devices to facilitate the collection of questionnaire data. The questionnaire data collection module 1 may include questionnaires in a predetermined format or the like to aid in the collection of relevant data. The questionnaire collecting module 1 may collect questionnaire data about the behavior, interests, or activities of the subject's restricted repetitive patterns. For example, the questionnaire data contains 10 entries filled in by parents for five aspects, assessing a child's inscribed or repetitive physical movements, object use, or language; adherence to identity or lack of elasticity adherence to conventional or ritualized language or non-language behavioral patterns; a highly constrained, fixed interest; overreaction or under reaction to sensory input; an unusual interest in the sensory aspect of the environment; and (3) self-injury behavior.

The scene module 2 is configured to set a corresponding scene based on a paradigm of evaluating an evaluated person. Such as a scene when eating things, a scene when playing games, various free-moving scenes, etc.

In one embodiment, the scene module 2 comprises a prompting device 21. The evaluator may be assisted in the evaluation by the prompting device 21. On the one hand, the prompt device can provide prompt information related to evaluation for an evaluator, and help the evaluator to complete an evaluation task. On the other hand, the evaluation progress can be prompted to the evaluator by the prompting apparatus. By means of the prompting device, consistency in evaluation can be improved. Compared with other schemes, even if the evaluation is carried out by different evaluators, or even if the evaluation is carried out by different evaluators or the evaluation is carried out by the same evaluators at different times, the speed and the process of the evaluation can be ensured to be more consistent to a certain extent by using the prompting device. In this case, the evaluation system can obtain more accurate results when the evaluation is finally performed. In addition, the data thus obtained may help the evaluation system to improve. Furthermore, by means of the prompting device, the evaluation system can also judge the various phases of the evaluation process, such as the start, stop, end, etc. of the evaluation paradigm more accurately.

The paradigm shift module 3 is used to acquire a particular voice and a particular limb movement of an evaluator, thereby determining the start, end, and interruption of the paradigm evaluation. In the actual evaluation process, the evaluated person is often very sensitive to any external changes.

Autism spectrum disorder assessment paradigm refers to a series of patterns or specifications designed for a certain assessment purpose when assessing autism spectrum disorders.

In assessing patients with autism spectrum disorder, it is necessary to constantly switch the paradigm of assessment. If, when switching the evaluation paradigm, the evaluator instructs the paradigm switch using a language that is not in communication with the evaluator, or uses an additional alert device (e.g., an indicator light) or the like to perform the paradigm switch, both of these approaches may draw the attention of the evaluator. These factors often cause the state of the person being evaluated to change, which makes the collected evaluation data inaccurate, resulting in an increase in the error rate of the evaluation result. In this embodiment, the influence of the paradigm switch on the subject can be reduced by using the specific voice and specific limb motion of the subject to perform the switch, so that the evaluation result is more accurate. Specific voices and specific limb actions are, for example, specific voices and specific limb actions that may be used by the evaluator when communicating with the evaluator. Specific speech and specific limb movements are speech and limb movements that do not draw particular attention to the person being evaluated. In addition, the pattern switching is judged by combining specific voice and specific limb actions, and misrecognition of the pattern switching can be further avoided.

The behavior data acquisition module 4 is used for acquiring behavior data of the evaluated person in the scene set by the scene module. The behavior data acquisition module 4 may include, for example, a microphone, a camera, a handwriting input device, and the like. The behavior data acquisition module 4 can be used for recording the performance of the evaluated person in the evaluation process so as to facilitate the subsequent evaluation.

Patients with autism spectrum disorder have a greater response to external disturbances. If during the assessment, the evaluator generates an action or voice outside of the task interaction with the evaluator in a specific scenario, this may affect the emotion of the evaluator and thus the assessment result. In view of this specificity of the autism spectrum disorder patient, in this embodiment, specific actions or instructions of the evaluator and the evaluator in the interaction process may be adopted as identification features for intercepting behavior data, so that the influence on the evaluator in the evaluation process may be reduced while the data volume is reduced and the pertinence of the data is increased.

For example, specific actions by which an evaluator communicates with an evaluator include: the evaluator communicates with the particular limb movements of the evaluator, e.g., gestures, rotations of the head, etc.; eye movements that the evaluator communicates with the subject, etc. The specific voices that the evaluator communicates with the evaluator include: the evaluator calls the speech of the evaluator; the evaluator asks the speech of the evaluated person, etc. The motion of the subject includes, for example, micro-motion of the subject's limb, eye motion, and the like. The speech of the evaluators includes abnormal sounds of the evaluators, speech of the evaluators answering questions, and the like.

The data processing module 5 generates multimodal behavior data for the subject based on the questionnaire information and the behavior data, and generates an autism spectrum disorder assessment result based on the multimodal behavior data. Here, the data to be evaluated is multimodal behavior data, which incorporates questionnaire information of the subject to be evaluated, performance data of the subject to be evaluated under various paradigms.

The data processing module 5 may extract voice information, time information, spatial information, behavior hierarchy information, and behavior association information for performing interactive paradigm task activities between the evaluators to construct a key feature behavior dataset. The paradigm task activities include, for example, interactive paradigm task activities such as snack food activities, shout names and car play activities, co-attention activities, and free play activities. The characteristic behavior in the key characteristic behavior dataset comprises at least one of the following behaviors: eye-sight behavior, finger movements with coordinated gaze, facial expressions, vocalization, limb language, giving movements, asking, showcase movements, functional play, imaginative play, initiating common attention, responding to common attention, calling reactions, social offers and conversations.

The data processing module 5 may comprise an artificial intelligence AI module. The artificial intelligence AI module is used for training an autism spectrum disorder classifier based on the questionnaire data and the key characteristic behavior data by using a machine learning algorithm, and establishing an autism spectrum disorder risk assessment model. The data processing module 5 can also perform intelligent evaluation prediction on the autism spectrum disorder risk condition of the evaluators according to the collected evaluators questionnaire data, the extracted key feature data and the trained autism spectrum disorder risk evaluation model, and generate an autism spectrum disorder evaluation result.

In yet another embodiment, the behavioral data acquisition module 4 acquires continuous behavioral data of an autism spectrum disorder evaluateee, determines a first identification feature in the continuous behavioral data, and intercepts a portion of the behavioral data from the continuous behavioral data as first behavioral data based on the first identification feature. The data processing module 2 processes the first behavior data to generate second behavior data. The data processing module 5 generates an evaluation conclusion based on the second behavior data. The data processing module 5 also sends an assessment report to the user comprising the assessment conclusion.

For example, the first row of data includes a timestamp. The data processing module 5 obtains at least one of the following intervals based on the time stamp: a first interval between consecutive two behaviors of the subject; and a second interval between the behavior of the evaluator and the behavior of the evaluated person. The data processing module 5 may determine the state of the evaluative person based on at least one of the first interval and the second interval.

At present, characteristic behaviors are usually identified and evaluated manually. This approach is greatly affected by human subjective factors. In this embodiment, an automated evaluation may be employed. Where the behavior of the subject is converted into a canonical activity. And describing the autism spectrum disorder risk by determining whether the characteristic behaviors appear, the reaction time of the occurrence, the scene of the occurrence (whether an operator prompts or not and the degree of the operator prompts), the frequency of the occurrence and the association of different characteristic behaviors, and establishing a training model. With the time stamp, the time interval can be determined more accurately even if the processed behavior data is intercepted data.

The data processing module 5 may evaluate the state of the evaluative person based on the first interval and the second interval. For example, the greater the frequency of characteristic behavior (e.g., fear, anger, disgust), the shorter the first interval; the longer the second interval, the more severe the symptoms.

In addition, the behavioural data acquisition module 4 can display a presentation video for guiding the data acquisition operator through the display device 23. Here, at least one of the data acquisition module 1 or the data processing module 2 detects a first behavior feature of the subject based on the first behavior data, and determines a next presentation video based on the first behavior feature. In this way, guidance can be provided to the operator adaptively. For example, the first behavioral characteristics include at least one of a first sound characteristic, a first motion characteristic, and a first expression characteristic.

Patients with autism spectrum disorder (i.e., the subject) are very sensitive to external influences. Any change or thing in the evaluation scene may have an influence on the evaluator and lead to inaccuracy of the evaluation result. During the evaluation, if the evaluated person can see the content of the prompting device, the prompting device influences the emotion of the evaluated person, so that the evaluation process is fluctuated. In this way, the collected evaluation data may be inaccurate and result in deviations in the evaluation results.

The inventors of the present disclosure found this contradiction in the actual evaluation process: on one hand, the prompting device can improve the evaluation efficiency of the autism spectrum disorder, and bring a plurality of benefits to the evaluation of the autism spectrum disorder; on the other hand, when the evaluators see the content in the presentation device, this may also make the evaluation result inaccurate.

For example, the presentation device 21 includes a display device 211 provided at a visible position of the evaluator and a receiving device 212 worn by the evaluator. The display device 211 generates an output image comprising a first sub-image of a first polarization state and a second sub-image of a second polarization state. The first polarization state and the second polarization state are orthogonal. The first sub-image contains a hint. In this way, the first sub-image and the second sub-image in the output image may be superimposed such that the cue information is not resolved by the human eye. The receiving device 212 includes a light filtering device 2121, and the light filtering device 2121 filters the second sub-image with the second polarization state, so as to output the first sub-image for the evaluator to view the prompt.

In this way, the prompting contents of the prompting device are invisible to the evaluators. This may minimize the impact of the prompting device. Meanwhile, the evaluator can utilize the receiving device to see the content of the prompting device, so as to evaluate. In this way, the prompting device can still be used for assisting the evaluator in evaluating under the condition that the influence of the prompting device on the evaluated person is reduced, so that the benefit brought by the prompting device is retained.

The receiving means are for example spectacles coated with a polarizing filter membrane. Such glasses may be similar to ordinary glasses. The subject will not pay additional attention to such glasses and will not have a significant impact on the collection of evaluation data.

Fig. 3 shows an implementation of the prompting device.

As shown in fig. 3, the display device is a liquid crystal display. The liquid crystal display comprises a backlight light source a1, a first polaroid a2 and liquid crystal panels a3, a4 and a5. The liquid crystal panels a3, a4, a5 include, for example, a lower glass substrate and a transparent electrode a3, a liquid crystal a4 and an upper glass substrate and a color filter and an electrode a5. The liquid crystal panel generates a first sub-image based on the modulated liquid crystal state.

In fig. 3, the receiving means is glasses, and lenses of the glasses include a second polarizer a7.

In this embodiment, since the liquid crystal display panel does not include the second polarizer located above the liquid crystal panel, but the second polarizer is disposed on the glasses worn by the evaluator, the light a6 emitted from the liquid crystal display panel includes the light of the first sub-image and the light of the second sub-image orthogonal to the light of the first sub-image. The light of the second sub-image is, for example, light emitted from the backlight source that is not modulated by the liquid crystal panel.

Since the human eye is only sensitive to the intensity of light and cannot distinguish the polarization state of the light, the human eye sees the color of the backlight source a1 from the prompting device and cannot distinguish the first sub-image. In other words, the human eye cannot see the prompt information from the prompt device without the help of the receiving device.

The second polarizer a7 filters the second sub-image and transmits the first sub-image. Thus, the evaluator wearing the receiving device can see the prompt. The second polarizer a7 is, for example, a polarizing film applied on a glass lens of eyeglasses.

In this way, the prompt information can be provided to the evaluator without the evaluator noticing.

Fig. 4 shows another implementation of the prompting device.

As shown in fig. 4, the 4 display device includes an LED display panel b1, a first polarizing device b2, a second image light source b3, and light combiners b4, b5.

The first polarizing device b2 converts the output image of the LED display panel into a first sub-image of a third polarization state. The second image light source b3 generates a second sub-image of a fourth polarization state. The third polarization state and the fourth polarization state are orthogonal. The third polarization state is one of the first polarization state and the second polarization state. The fourth polarization state is one of the second polarization state and the first polarization state.

The light combiner b4, b5 receives the first sub-image and the second sub-image and combines the first sub-image and the second sub-image to output the output image.

The optical combiner includes a first optical waveguide b4 and a first composite grating b5 disposed in front of the first polarizing device. The second sub-image output by the second image light source is guided to the first synthetic grating b5 through the first optical waveguide b4 and superimposed with the first sub-image passing through the first polarizing device.

Here, with an additional light source, an LED display may be used as a prompting device, and the above technical effects may be achieved.

As shown in fig. 5, the scene module includes a modular scene platform C1. The scene platform C1 includes, for example, a table. A multimedia device C11 for the evaluators to view, a computing device C12 for the evaluators to use are provided on the table. In addition, the scene module can also comprise a prompting device. The presentation means comprise display means C14 and receiving means C13.

In designing the evaluation system, it is ensured that the light filtering means of the receiving means C13 are compatible with the multimedia device C11 and the computing device C12 displays. In other words, if polarized light is emitted by the multimedia device C11 and the computing device C12, the polarization state of the transmitted light of the light filtering means is identical to the polarization state of the polarized light emitted by the multimedia device C11 and the computing device C12.

In this embodiment, the scene platform adjusts at least one setting of the scene platform based on the paradigm switch determined by the paradigm switch module. The paradigm includes the following task activities: snack taking activities, shout names, and car playing activities, co-attention activities, and free play activities. For example, the display interface of the multimedia device C11 or background music or the like may be changed based on the paradigm shift.

As shown in fig. 1, the behavioral data acquisition module 4 includes an interactive paradigm task activity loyalty assessment module 41 and a feature extraction module 42. The interactive paradigm task activity loyalty assessment module 41 is configured to assess compliance of audio data and video data of the interactive paradigm task activity with rules requirements. The feature extraction module 42 is configured to extract voice information, time information, spatial information, behavior hierarchy information, and behavior association information for performing interaction paradigm task activities between the subject and the data collection operator to construct a key feature behavior data set. The characteristic behavior in the key characteristic behavior dataset comprises at least one of the following behaviors: eye-sight behavior, finger movements with coordinated gaze, facial expressions, vocalization, limb language, giving movements, asking, showcase movements, functional play, imaginative play, initiating common attention, responding to common attention, calling reactions, social offers and conversations.

As shown in fig. 1, the autism spectrum disorder assessment system further includes a familiarity module 6. The affinity module 6 may be used to assist the evaluator in establishing an affinity with the evaluator through the game, at least by playing sound and multimedia interactions. Through the affinity module 6, the children with autism spectrum disorder can still show natural characteristic behaviors in a strange environment, so that the real characteristic behavior data of the evaluated person can be obtained.

For example, the affinity module 6 may automatically adjust the volume of the background sound based on the movement position of the subject.

In one embodiment, the affinity module 6 may include an affinity sound collection module 61 and an acoustic varying device 62. The affinity sound collecting module 61 collects the affinity sound of a person who is in close proximity to the subject. The sound varying device 62 adjusts the instruction sound of the autism spectrum disorder assessment system and/or the sound of the evaluator to approach the approach sound based on the approach sound collected by the approach sound collection module. Often, autism spectrum disorder patients will produce a resistant mood for strange sounds. By using the affinity module, the evaluators can be integrated into the evaluation process as soon as possible, and the influence of the evaluation process on the evaluators is reduced. In this case, the collected subject data is more accurate. This will make the evaluation system more stable and the evaluation result more accurate.

As shown in fig. 1, the autism spectrum disorder assessment system may further include: a camera array 7, a microphone 8 and a loudspeaker 9. The camera array 7, microphone 8 and speaker 9 may comprise corresponding devices in other modules, such as the questionnaire data collection module 1 and the affinity module 6, as well as additional devices.

In one embodiment, the camera array 7 is used to detect a first position of the subject and a second position of the subject. The camera array 7 can determine an evaluator and an evaluated person by face/body recognition, for example. The camera array 7 may determine the first position and the second position by triangulation. The microphone 8 is used to detect a first volume of sound emitted by the evaluator. The speaker 9 outputs a second volume based on the first position, the second position and the first volume so that the second volume received by the evaluator is comparable to the first volume received by him. The speaker 9 includes a speaker array that generates sound directed to the subject to be evaluated by beamforming. The speaker 9 may be used to play background music or to play evaluation instructions.

The studies herein found that evaluating the initial volume change affects the mood of patients with autism spectrum disorder. In some cases, excessive volume changes may have a sustained effect on patients with autism spectrum disorders. This effect is likely to extend through the whole evaluation process. Thus, reducing the abrupt volume change may make the evaluation process smoother and the data collected by the evaluation system more accurate.

It is common practice to adjust the volume of the speaker based on the background sound. However, this approach does not meet the need for evaluation of autism spectrum disorders. Current electronics are difficult to adjust specifically for patients with autism spectrum disorders. On the one hand, the needs of autism spectrum disorder patients and others may be different and susceptible to external changes. Thus, improper volume more easily affects autism spectrum disorder patients. Moreover, the operation of adjusting the volume by the evaluator may also affect the emotion of the evaluator. On the other hand, patients with autism spectrum disorder may not be able to respond immediately to inappropriate volume. Thus, the played sound may already have a large and impact on the autism spectrum disorder patient before adjustment.

The evaluator is directly faced with the evaluator, who will make a judgment about the situation in the field. His volume is closer to the most appropriate volume. Here, therefore, we propose to set the volume of the speaker based on the volume of the evaluator to avoid affecting the evaluator. Further, since the sound of the speaker is identical to the sound of the evaluator, the interference of the two sounds to the evaluator can be reduced.

In addition, the influence of the occurrence distance on the volume is considered here. This can further reduce the influence of the volume factor on the subject.

On the other hand, the direction of sound may affect the subject. In this embodiment, the directional factor of the sound is also considered. The sound is directed to the subject to be evaluated by means of a loudspeaker array. This can enhance the feeling that the subject is concerned with, thereby enhancing the evaluation quality.

In one embodiment, the behavioral data collection module 4 collects continuous audio and video of the subject, detects speech and/or motion of the subject in the continuous audio and video, and intercepts portions of the audio and video based on the detected speech and/or motion. The data processing module 5 synchronizes the partial audio and video, generates multi-modal behavioral data using the questionnaire information, and generates an autism spectrum disorder assessment result using the multi-modal autism spectrum disorder assessment model. The data processing module 5 also trains the multimodal autism spectrum disorder assessment model using the multimodal behavioral data.

Patients with autism spectrum disorders are often very sensitive. External disturbances can have a significant impact. If the recording device is controlled during the recording of the behaviour of the patient suffering from autism spectrum disorder, this will affect the behaviour of the patient suffering from autism spectrum disorder, resulting in a final evaluation deviation. The behavior of patients with autism spectrum disorders is often abrupt and sometimes difficult to predict. As the current techniques for the evaluation of autism spectrum disorders are still immature, no skilled person has recognized this problem. In this embodiment, the behavioural data acquisition module 4 continuously acquires continuous behavioural data of the person under evaluation. In this way, the acquisition process need not be interrupted during data acquisition, and the record control operation of the evaluator is not required. In this way, on the one hand, missing of key behaviors of the evaluated person can be avoided; on the other hand, adverse effects of the operation during data acquisition on autism spectrum disorder children can be avoided as much as possible. In this way, the continuity of data acquisition can be maintained.

In addition, by intercepting the collected behavior data, the data amount of the behavior data can be reduced. The behavior data thus obtained is more targeted, and in the subsequent processing, the paradigm of the behavior data can be easily determined. In addition, this can also reduce the traffic during data transmission and reduce the data processing amount handled by the subsequent processing device.

As shown in fig. 2, in step S1, questionnaire information related to the person whose autism spectrum disorder is evaluated is collected and recorded.

In step S2, a corresponding scene is set on the basis of the paradigm of evaluating the subject, wherein a presentation device is set in the scene.

In step S3, specific voices and specific limb movements of the evaluator are acquired to determine the start, end and interruption of the paradigm evaluation.

In step S4, behavioral data of the autism spectrum disorder evaluators are collected in the scene set by the scene module.

In step S5, multimodal behavioral data for the subject is generated based on the questionnaire information and the behavioral data.

In step S6, autism spectrum disorder assessment results are generated based on the multimodal behavioral data.

The prompting device comprises a display device arranged at a visible position of the evaluator and a receiving device worn by the evaluator. The display device generates an output image, the output image comprises a first sub-image with a first polarization state and a second sub-image with a second polarization state, the first polarization state and the second polarization state are orthogonal, the first sub-image comprises prompt information, and the first sub-image and the second sub-image in the output image are overlapped so that the prompt information cannot be distinguished by human eyes. The receiving device comprises a light filtering device which filters the second sub-image with the second polarization state so as to output the first sub-image for the evaluator to view the prompt information.

The steps performed in this method embodiment are similar to those performed in the autism spectrum disorder assessment system described above, and thus, the same description is not repeated here.

According to another embodiment, an autism spectrum disorder assessment device may be provided. The autism spectrum disorder assessment device comprises means for performing the processing in the corresponding steps of the autism spectrum disorder assessment method described above. The autism spectrum disorder assessment device implements steps in the method shown in fig. 2 and/or implements processing steps in the system shown in fig. 1. The same description is not repeated here.

Fig. 6 illustrates an exemplary computing device that may be used to implement an autism spectrum disorder assessment system according to one embodiment. In an autism spectrum disorder assessment system, one or more computing devices as shown in fig. 6 may be arranged.

As shown in fig. 6, computing device 300 includes a processor 302, a readable storage medium 304.

Computing device 300 may also include a display screen 310, a user interface 312, a camera 314, an audio/video interface 316, sensors 318, and communications component 320, among others. The computing device 300 may also include a power management chip 306, a battery 308, and the like. Computing device 300 may be a variety of smart devices, etc.

The processor 302 may be a variety of processors. The readable storage medium 304 may store underlying software, system software, application software, data, and the like, required for operation of the computing device 300. The readable storage medium 304 may include various forms of memory, such as ROM, RAM, flash, etc.

The display screen 310 may be a liquid crystal display screen, an OLED display screen, or the like. In one example, display screen 310 may be a touch screen. The user may perform an input operation through the display screen 310. In addition, the user can also conduct fingerprint identification and the like through the touch screen.

The user interface 312 may include a USB interface, a lightning interface, a keyboard, etc.

The camera 314 may be a single camera or multiple cameras. In addition, the camera 314 may be used for face recognition of the user.

The audio/video interface 316 may include, for example, a speaker interface, a microphone interface, a video transmission interface such as HDMI, and the like.

The sensor 318 may include, for example, a gyroscope, an accelerometer, a temperature sensor, a humidity sensor, a pressure sensor, and the like. For example, the environment surrounding the computing device may be determined by sensors, and the like.

The communication component 320 may include, for example, a WiFi communication component, a bluetooth communication component, a 3G, 4G, and 5G communication component, and the like. The computing device 300 may be arranged in a network through the communication component 320.

The power management chip 306 may be used to manage the power of the power input to the computing device 300 and may also manage the battery 308 to ensure greater efficiency of utilization. The battery 308 is, for example, a lithium ion battery or the like.

The computing device shown in fig. 6 is merely illustrative and is in no way intended to limit the embodiments herein, their applications or uses.

Fig. 7 shows a schematic network in which an autism spectrum disorder assessment system may be arranged according to one embodiment. The autism spectrum disorder assessment system may be arranged in a network as shown in fig. 7.

Fig. 7 shows a plurality of terminal devices 31, 32, 33 and a communication network 40. A plurality of servers 41, 42 may be provided in the network 40. Each of the terminal devices 31, 32, 33 and the servers 41, 42 may be, for example, a computing device shown in fig. 6. An autism spectrum disorder assessment system according to one embodiment includes at least one processor and at least one readable storage medium. The at least one processor and the at least one readable storage medium may be distributed among the terminal devices 31, 32, 33 and the servers 41, 42. The readable storage medium stores executable instructions. The executable instructions, when executed by the processor, cause the processor to implement the processing in the autism spectrum disorder assessment system or the steps in the autism spectrum disorder assessment method according to embodiments.

The present disclosure may also include a computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions, i.e., executable instructions, embodied thereon for causing a processor to implement aspects of the present disclosure.

The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.

The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.

Computer program instructions for performing the operations of the present disclosure can be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present disclosure are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information of computer readable program instructions, which can execute the computer readable program instructions.

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, computing devices, and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of computing devices, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based computing devices which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.

The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvement of the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present disclosure is defined by the appended claims.

Claims

1. An autism spectrum disorder assessment system, comprising:

a questionnaire data collection module for collecting and recording questionnaire information related to the autism spectrum disorder evaluators;

the scene module is used for setting corresponding scenes for the paradigm of the evaluated person and comprises a prompting device;

the model switching module is used for acquiring specific voice and specific limb actions of the evaluator so as to determine the start, the end and the interruption of the model evaluation;

the behavior data acquisition module is used for acquiring behavior data of the evaluated person in the scene set by the scene module;

A data processing module for generating multi-modal behavior data for the subject based on the questionnaire information and the behavior data, and generating an autism spectrum disorder assessment result based on the multi-modal behavior data,

wherein the prompting device comprises a display device arranged at a visible position of the evaluator and a receiving device worn by the evaluator,

wherein the display device generates an output image comprising a first sub-image of a first polarization state and a second sub-image of a second polarization state, the first polarization state and the second polarization state being orthogonal, the first sub-image comprising a hint information, the first sub-image and the second sub-image in the output image being superimposed such that the hint information is indistinguishable to the human eye, and

the receiving device comprises a light filtering device which filters the second sub-image with the second polarization state, so that the first sub-image is output for an evaluator to view the prompt information.

2. The autism spectrum disorder assessment system according to claim 1, wherein the display device is a liquid crystal display screen including a backlight source, a first polarizer, and a liquid crystal panel that generates a first sub-image based on the modulated liquid crystal state, and

Wherein the receiving means is a pair of spectacles and the lenses of the spectacles comprise a second polarizer for filtering the second sub-image and transmitting the first sub-image, and the second polarizer is a polarizing film applied on the glass lenses of the spectacles.

3. The autism spectrum disorder assessment system according to claim 1, wherein the display device includes an LED display panel, a first polarizing device, a second image light source, and a light combiner,

wherein the first polarizing device converts the output image of the LED display panel into a first sub-image of a third polarization state, the second image light source generates a second sub-image of a fourth polarization state, the third polarization state is orthogonal to the fourth polarization state, the third polarization state is one of the first polarization state and the second polarization state, the fourth polarization state is one of the second polarization state and the first polarization state,

wherein the light combiner receives the first sub-image and the second sub-image and combines the first sub-image and the second sub-image to output the output image,

wherein the optical combiner comprises a first optical waveguide and a first composite grating arranged in front of a first polarizing device, and

wherein the second sub-image output by the second image light source is guided to the first composite grating by the first optical waveguide and superimposed with the first sub-image passing through the first polarizing device.

4. The autism spectrum disorder assessment system according to claim 1, wherein the scenario module includes a modular scenario platform,

wherein the scene platform adjusts at least one setting of the scene platform based on the paradigm switch determined by the paradigm switch module,

wherein the paradigm includes the following task activities: snack taking activities, shout names, and car playing activities, co-attention activities, and free play activities.

5. The autism spectrum disorder assessment system according to claim 4, wherein the behavioral data collection module includes an interactive paradigm task activity loyalty assessment module and a feature extraction module,

wherein the interactive paradigm task activity loyalty evaluation module is used for evaluating the conformity degree of the audio data and the video data of the interactive paradigm task activity with the rule requirement,

wherein the feature extraction module is used for extracting voice information, time information, space information, behavior hierarchy information and behavior association information of interaction paradigm task activities between an evaluated person and a data acquisition operator to construct a key feature behavior data set,

wherein the characteristic behavior in the key characteristic behavior dataset comprises at least one of the following behaviors: eye-sight behavior, finger movements with coordinated gaze, facial expressions, vocalization, limb language, giving movements, asking, showcase movements, functional play, imaginative play, initiating common attention, responding to common attention, calling reactions, social offers and conversations.

6. The autism spectrum disorder assessment system according to claim 1, further comprising:

a relatedness module for automatically adjusting the volume of the background sound based on the mobile position of the evaluated person,

wherein the affinity module comprises an affinity sound collecting module and a sound changing device,

wherein the affinity sound collecting module collects the affinity sound of the person who is close to the person to be evaluated,

wherein the sound varying device adjusts the instruction sound of the autism spectrum disorder assessment system and/or the sound of the evaluator to approach the proximity sound based on the proximity sound collected by the affinity sound collecting module.

7. The autism spectrum disorder assessment system according to claim 1, further comprising: a camera array, a microphone and a loudspeaker,

wherein the camera array is used for detecting a first position of an estimated person and a second position of the estimated person,

wherein the microphone is used for detecting the first volume of the sound of the evaluator,

wherein the speaker outputs a second volume based on the first location, the second location and the first volume such that the second volume received by the evaluator is comparable to the first volume received by the evaluator,

wherein the speaker comprises a speaker array that produces sound directed to the subject by beamforming.

8. The autism spectrum disorder assessment system according to claim 1, wherein the behavioral data collection module collects continuous audio and video of the subject, detects speech and/or motion of the subject in the continuous audio and video, and intercepts portions of the audio and video based on the detected speech and/or motion;

the data processing module synchronizes the partial audio and video, generates multi-modal behavior data by utilizing questionnaire information, and generates an autism spectrum disorder assessment result by utilizing a multi-modal autism spectrum disorder assessment model; and

the data processing module also trains the multimodal autism spectrum disorder assessment model using the multimodal behavioral data.

9. A method of assessing autism spectrum disorder comprising:

collecting and recording questionnaire information related to the evaluated person;

setting corresponding scenes based on a paradigm of evaluating an evaluated person, wherein a prompting device is arranged in the scenes;

for obtaining a specific voice and a specific limb movement of the evaluator, thereby determining the start, end and interruption of the paradigm evaluation;

collecting behavior data of an evaluated person in a scene set by a scene module;

Generating multi-modal behavioral data for the subject based on the questionnaire information and the behavioral data; and

generating autism spectrum disorder assessment results based on the multimodal behavioral data,

10. An autism spectrum disorder assessment device, comprising:

a unit for collecting and recording questionnaire information related to the subject;

a unit for setting corresponding scenes for a paradigm of evaluating an evaluated person, wherein a prompting device is arranged in the scenes;

Means for acquiring a specific voice and a specific limb movement of the evaluator, thereby determining a start, an end and an interruption of the paradigm evaluation;

a unit for collecting behavior data of the evaluators in the scene set by the scene module;

a unit for generating multimodal behavioral data for the subject based on the questionnaire information and the behavioral data; and

a unit for generating autism spectrum disorder assessment results based on the multimodal behavioral data,