Autism evaluation system and method

Abstract

The invention relates to the technical field of rehabilitation medical treatment, in particular to an autism assessment system and method.The system comprises a data acquisition module, a data processing module and a data analysis module, and the method comprises the steps that assessment data of the assessment item execution process of a patient is obtained to obtain feature data values; calculating an evaluation value based on the feature data value; generating a first feature set and a second feature set based on a comparison result of the feature data value and a standard feature data value; determining a data extraction proportion of a feature set based on the evaluation value, and determining a correction coefficient according to the emotion fluctuation frequency of the patient to generate an intervention strategy; and determining whether a single intervention target meets the standard, determining whether the intervention strategy meets the standard based on the number proportion, and determining an adjustment data extraction proportion or a correction coefficient based on the number proportion difference of the intervention targets under the condition that the intervention strategy does not meet the standard. The accuracy of the intervention strategy generated according to the evaluation result is improved.

Description

Technical Field

[0001] The present invention relates to the field of rehabilitation medical technology, and in particular to an autism assessment system and method. Background Art

[0002] Autism assessment technology has made significant progress in recent years, especially in early diagnosis and intervention. As the number of patients with autism spectrum disorders continues to increase worldwide, scientific and effective assessment and intervention have become important issues. The diagnosis of autism no longer relies solely on traditional behavioral observations and parent reports, but incorporates interdisciplinary research results from multiple fields such as genetics, neuroscience, and psychology.

[0003] In this context, a variety of advanced assessment systems and methods have emerged, including automated assessment tools based on big data and artificial intelligence technology, as well as assessment systems for specific disorders such as social disorders. These systems use standardized scales, behavioral observations, and advanced technologies such as genetic testing and biomarkers to achieve comprehensive and personalized assessments of autistic patients.

[0004] At the same time, with the popularization of telemedicine and digital health tools, autism assessment services have become more convenient and efficient, especially for patients in remote areas and resource-poor areas. In addition, with the continuous advancement of technology, the accuracy and efficiency of the assessment system are also continuously improving, providing strong support for the early diagnosis and effective intervention of autism.

[0005] Chinese Patent Publication No.: CN109498038A discloses an autism assessment method and device. The invention provides an autism assessment method and device. By capturing the facial activity characteristics of the autism subject when watching pre-made videos with different cognitive stimulation angles and the autism estimation neural network model, it is estimated whether the autism subject has autism. Compared with the questionnaire survey method, it effectively shortens the estimation time, improves the estimation efficiency, is not easily affected by external interference, and the evaluation method is simple and easy.

[0006] It can be seen that the autism assessment method and device have the following problems: this method assesses autism based on the facial activity characteristics of autistic subjects when they watch pre-made videos with different cognitive stimulation angles and the autism prediction neural network model, but this method only obtains the facial activity characteristics of autistic subjects, the data is single, and the accuracy of the assessment results cannot be guaranteed, and thus the accuracy of the intervention strategy designed based on the assessment results cannot be guaranteed. Summary of the invention

[0007] To this end, the present invention provides an autism assessment system and method to overcome the problem in the prior art that the accuracy of autism assessment results is low, which leads to the low accuracy of intervention strategies designed based on the assessment results.

[0008] To achieve the above objectives, on the one hand, the present invention provides an autism assessment system and method, comprising:

[0009] A data acquisition module is used to obtain the assessment data of the patient during the assessment project execution, wherein the assessment data includes audio data, video data, physiological data and scale data;

[0010] A data processing module connected to the data acquisition module, for performing standardization processing on the evaluation data to obtain each characteristic data value, generating a plurality of charts based on each characteristic data value and calculating the evaluation value according to the plurality of charts;

[0011] A data analysis module connected to the data processing module is used to determine whether the characteristic data value meets the standard based on the comparison result between the characteristic data value and the standard characteristic data value, so as to generate a first feature set based on the characteristic data value that meets the standard, and generate a second feature set based on the characteristic data value that does not meet the standard, and determine the data extraction ratio of the characteristic set based on the evaluation value, and determine the correction coefficient of the data extraction ratio according to the frequency of the patient's emotional fluctuations, generate an intervention strategy based on the extracted data, and determine whether a single intervention target meets the standard based on the patient's execution deviation, and determine whether the intervention strategy meets the standard based on the proportion of the number of intervention targets that do not meet the standard, and determine the adjustment data extraction ratio or the correction coefficient of the adjustment data extraction ratio based on the difference in the proportion of the number of intervention targets under the condition that the intervention strategy does not meet the standard.

[0012] Furthermore, the data analysis module determines, for a single feature data, that the feature data value does not meet the standard based on a comparison result that the feature data value is greater than a first standard feature data value or is less than a second standard feature data value.

[0013] Further, the data analysis module determines the data extraction ratio of the feature set based on the evaluation value, including determining to extract the data of the feature set using a first extraction ratio based on a comparison result that the evaluation value is greater than or equal to a preset evaluation value;

[0014] Based on the comparison result that the evaluation value is less than the preset evaluation value, it is determined to use a second extraction ratio to extract the data of the feature set.

[0015] Furthermore, the data analysis module determines a correction coefficient of the data extraction ratio based on the emotion fluctuation frequency.

[0016] If the emotion fluctuation frequency is greater than a first preset fluctuation frequency, the data analysis module determines to use a first correction coefficient to correct the data extraction ratio;

[0017] If the emotion fluctuation frequency is less than or equal to the first preset fluctuation frequency and greater than the second preset fluctuation frequency, the data analysis module determines to use a second correction coefficient to correct the data extraction ratio;

[0018] If the emotion fluctuation frequency is less than the second preset fluctuation frequency, the data analysis module determines to use a third correction coefficient to correct the data extraction ratio.

[0019] Further, the data analysis module determines whether a single intervention target meets the standard based on the execution deviation, including determining that the intervention target does not meet the standard based on a comparison result that the execution deviation is less than a preset deviation.

[0020] Furthermore, the data analysis module counts the number of intervention targets that do not meet the standards and calculates the number ratio, and determines that the intervention strategy does not meet the standards based on a comparison result that the number ratio is less than a preset number ratio.

[0021] Further, the data analysis module determines to adjust the data extraction ratio based on the comparison result that the quantity ratio difference is greater than a preset quantity ratio difference under the condition that the intervention strategy does not meet the standard;

[0022] The adjustment of the correction coefficient is determined based on a comparison result that the quantity ratio difference is less than or equal to a preset quantity ratio difference.

[0023] Furthermore, the data analysis module sets several adjustment methods based on the data extraction ratio, and the adjustment range of the data extraction ratio in each adjustment method is positively correlated with the difference in the quantity proportion.

[0024] Furthermore, the data analysis module sets several adjustment methods based on the correction coefficient, and the adjustment range of the correction coefficient in each adjustment method is positively correlated with the difference in the quantity proportion.

[0025] In another aspect, the present invention further provides an autism assessment method, comprising:

[0026] Acquire the assessment data of the patient during the assessment project execution, and perform standardization on the assessment data to obtain the values ​​of each characteristic data;

[0027] generating a plurality of graphs based on each of the characteristic data values ​​and calculating evaluation values ​​according to the plurality of graphs;

[0028] Determine whether the feature data value meets the standard based on the comparison result between the feature data value and the standard feature data value, and generate a first feature set and a second feature set according to the comparison result;

[0029] Determining a data extraction ratio of a feature set based on the evaluation value, and determining a correction coefficient of the data extraction ratio according to the patient's mood fluctuation frequency to generate an intervention strategy;

[0030] For a single intervention target in the intervention strategy, whether the single intervention target meets the standard is determined based on the patient's execution deviation, and whether the intervention strategy meets the standard is determined based on the proportion of the number of intervention targets that do not meet the standard; if the intervention strategy does not meet the standard, the data extraction ratio or the correction coefficient of the data extraction ratio is determined based on the difference in the proportion of the number of intervention targets.

[0031] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention extracts characteristic data values ​​based on the evaluation data of potential patients in the evaluation items and generates a first feature set and a second feature set, and generates a chart based on the evaluation data, so that various aspects of the evaluation data of the potential patients can be intuitively presented, the evaluation values ​​are calculated according to the charts, and the data extraction ratio in the first feature set and the second feature set is determined based on the evaluation values, and the correction coefficient of the ratio is determined according to the frequency of the patient's emotional fluctuations to generate an intervention strategy, and a certain proportion of data can be extracted according to the evaluation value of the potential patient, thereby improving the generation benchmark of the intervention strategy; for a single intervention target in the generated intervention strategy, the execution deviation of the patient is detected, and the larger the deviation, the less satisfactory the setting of the single intervention target, the percentage of the number of intervention targets that do not meet the standards is calculated to determine whether the intervention strategy meets the standards, and the adjustment of the extraction ratio or the adjustment correction coefficient is determined for the intervention strategy that does not meet the standards, thereby improving the accuracy of the intervention strategy generated according to the evaluation results.

[0032] Furthermore, the present invention compares the patient's characteristic data values ​​with the corresponding standard characteristic data values ​​of normal people, respectively determines the characteristic data values ​​of the patient that meet the standards and do not meet the standards, and generates a first feature set and a second feature set, and determines the data extraction ratio in the feature set according to the evaluation value, and determines the patient's emotional fluctuation frequency, and corrects the data extraction ratio for patients with a high frequency of emotional fluctuations to generate personalized intervention strategies in a targeted manner, thereby improving the accuracy of the intervention strategy generated according to the evaluation results.

[0033] Furthermore, the present invention obtains the execution deviation of a single intervention target to determine whether the setting of the single intervention target meets the standard during the patient's execution of the intervention strategy, makes an accuracy judgment on the single intervention target, counts the proportion of intervention targets that do not meet the standard to determine the accuracy of the intervention strategy, and makes targeted adjustments to the generation process of the intervention strategy whose accuracy does not meet the standard, thereby improving the accuracy of the intervention strategy generated according to the evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 is a structural block diagram of an autism assessment system according to an embodiment of the present invention;

[0035] Figure 2 is a flow chart of an autism assessment method according to an embodiment of the present invention;

[0036] Figure 3 A flowchart for determining whether a characteristic data value meets a standard according to an embodiment of the present invention;

[0037] Figure 4 The present invention is a flowchart of determining a data extraction ratio according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0039] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0040] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0041] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0042] See also Figure 1 , which is a structural block diagram of an autism assessment system according to an embodiment of the present invention.

[0043] An embodiment of the present invention provides an autism assessment system, comprising:

[0044] A data acquisition module is used to obtain the assessment data of the patient during the assessment project execution, wherein the assessment data includes audio data, video data, physiological data and scale data;

[0045] A data processing module connected to the data acquisition module, for performing standardization processing on the evaluation data to obtain each characteristic data value, generating a plurality of charts based on each characteristic data value and calculating the evaluation value according to the plurality of charts;

[0046] A data analysis module connected to the data processing module is used to determine whether the characteristic data value meets the standard based on the comparison result between the characteristic data value and the standard characteristic data value, so as to generate a first feature set based on the characteristic data value that meets the standard, and generate a second feature set based on the characteristic data value that does not meet the standard, and determine the data extraction ratio of the characteristic set based on the evaluation value, and determine the correction coefficient of the data extraction ratio according to the frequency of the patient's emotional fluctuations, generate an intervention strategy based on the extracted data, and determine whether a single intervention target meets the standard based on the patient's execution deviation, and determine whether the intervention strategy meets the standard based on the proportion of the number of intervention targets that do not meet the standard, and determine the adjustment data extraction ratio or the correction coefficient of the adjustment data extraction ratio based on the difference in the proportion of the number of intervention targets under the condition that the intervention strategy does not meet the standard.

[0047] Specifically, the audio data includes but is not limited to the audio data of the patient's word recognition, the video data includes but is not limited to the video of the patient's actions on the assessment items, and the physiological data includes but is not limited to blood pressure and heart rate.

[0048] Specifically, the data analysis module may adopt an AI model such as a decision tree model or a traditional algorithm such as feature matching, which may be replaced according to actual conditions and is not specifically limited.

[0049] Specifically, the graphs include but are not limited to one-dimensional scatter graphs, two-dimensional scatter graphs and bar graphs.

[0050] Specifically, the process of acquiring characteristic data values ​​is as follows: organize and quantify each evaluation data, remove outliers, missing values ​​and other data that do not meet the requirements, convert data of different dimensions into data of the same dimension, and use machine learning algorithms to screen out and extract features that have a significant impact on the evaluation target.

[0051] Specifically, in the embodiment of the present invention, if the data analysis module still does not meet the standards after adjusting the intervention strategy that does not meet the standards, the user is asked to manually define the scope and regenerate the intervention strategy.

[0052] Specifically, the present invention extracts characteristic data values ​​based on the evaluation data of potential patients in the evaluation items and generates a first feature set and a second feature set, and generates charts based on the evaluation data, so that various aspects of the evaluation data of the potential patients can be intuitively presented, the evaluation values ​​are calculated according to the charts, and the data extraction ratio in the first feature set and the second feature set is determined based on the evaluation values, and the correction coefficient of the ratio is determined according to the frequency of the patient's emotional fluctuations to generate an intervention strategy, and a certain proportion of data can be extracted specifically according to the evaluation value of the potential patient, thereby improving the generation benchmark of the intervention strategy; for a single intervention target in the generated intervention strategy, the patient's execution deviation is detected, and the larger the deviation, the non-standard setting of the single intervention target is. The proportion of the number of intervention targets that do not meet the standards is counted to determine whether the intervention strategy meets the standards, and the adjustment of the extraction ratio or the adjustment correction coefficient is determined for the intervention strategy that does not meet the standards, thereby improving the accuracy of the intervention strategy generated according to the evaluation results.

[0053] See also Figure 3 As shown, it is a flow chart of determining whether a characteristic data value meets the standard according to an embodiment of the present invention.

[0054] Specifically, the data analysis module determines, for a single characteristic data value, that the characteristic data value does not meet the standard based on a comparison result that the characteristic data value is greater than a first standard characteristic data value or is less than a second standard characteristic data value.

[0055] Specifically, the first standard feature data value and the second standard feature data value are the maximum value and the minimum value corresponding to the feature data values ​​of normal persons.

[0056] See also Figure 4 As shown, it is a flow chart of determining the data extraction ratio according to an embodiment of the present invention.

[0057] Specifically, the data analysis module determines the data extraction ratio of the feature set based on the evaluation value, including determining to extract the data of the feature set using a first extraction ratio based on a comparison result that the evaluation value is greater than or equal to a preset evaluation value;

[0058] Based on the comparison result that the evaluation value is less than the preset evaluation value, it is determined to use a second extraction ratio to extract the data of the feature set.

[0059] Specifically, the calculation process of the evaluation value includes: calculating the characteristic data value of each chart, such as the standard deviation, which is not specifically limited, subtracting the characteristic data value from the standard characteristic data value to obtain the difference, and the sum of the weight coefficient corresponding to the difference and the product of the difference is the evaluation value, wherein the weight coefficient is determined according to the scale data; the preset evaluation value is determined according to the historical evaluation process.

[0060] Specifically, the data analysis module determines a correction coefficient of the data extraction ratio based on the emotion fluctuation frequency.

[0061] If the emotion fluctuation frequency is greater than a first preset fluctuation frequency, the data analysis module determines to use a first correction coefficient to correct the data extraction ratio;

[0062] If the emotion fluctuation frequency is less than or equal to the first preset fluctuation frequency and greater than the second preset fluctuation frequency, the data analysis module determines to use a second correction coefficient to correct the data extraction ratio;

[0063] If the emotion fluctuation frequency is less than the second preset fluctuation frequency, the data analysis module determines to use a third correction coefficient to correct the data extraction ratio.

[0064] Specifically, the emotion fluctuation frequency is extracted by a time-frequency analysis method.

[0065] Specifically, an alternative way for the data analysis module to determine the correction coefficient of the data extraction ratio based on the emotion fluctuation frequency is:

[0066] The data analysis module determines a correction coefficient for the data extraction ratio based on the active communication frequency.

[0067] If the active communication frequency is greater than the first preset communication frequency, the data analysis module determines to use a fourth correction coefficient to correct the data extraction ratio;

[0068] If the active communication frequency is less than or equal to the first preset communication frequency and greater than the second preset communication frequency, the data analysis module determines to use a fifth correction coefficient to correct the data extraction ratio;

[0069] If the active communication frequency is less than the second preset communication frequency, the data analysis module determines to use a sixth correction coefficient to correct the data extraction ratio.

[0070] Specifically, the values ​​of the first preset fluctuation frequency and the second preset fluctuation frequency are determined by the historical data of the emotion fluctuation impact assessment results, and the values ​​corresponding to the confidence level of 95% are taken; the values ​​of the first preset communication frequency and the second preset communication frequency are determined by the historical data of the active communication assessment results, and the values ​​corresponding to the confidence level of 95% are taken.

[0071] Specifically, the extraction ratio is the ratio of the amount of data extracted from the first feature set to the amount of data extracted from the second feature set.

[0072] Specifically, the value of the first correction coefficient is set to [1.2, 1.3], and 1.23 is preferably selected in the embodiment of the present invention; the value of the second correction coefficient is set to [1.01, 1.19], and 1.1 is preferably selected in the embodiment of the present invention; the third correction coefficient is set to 1; the value of the fourth correction coefficient is set to [0.8, 0.9], and 0.85 is preferably selected in the embodiment of the present invention; the value of the fifth correction coefficient is set to [0.91, 0.99], and 0.95 is preferably selected in the embodiment of the present invention; the sixth correction coefficient is set to 1.

[0073] Specifically, the data analysis module determines whether a single intervention target meets the standard based on the execution deviation, including determining that the intervention target does not meet the standard based on a comparison result that the execution deviation is less than a preset deviation.

[0074] Specifically, the execution deviation is determined based on the degree of overlap between the patient's movement trajectory during the intervention target training and the preset movement trajectory. The smaller the overlap, the greater the execution deviation. The preset deviation is the average execution deviation of the training effect that meets the standard during the historical training process.

[0075] Specifically, the data analysis module counts the number of intervention targets that do not meet the standards and calculates the number ratio, and determines that the intervention strategy does not meet the standards based on a comparison result that the number ratio is less than a preset number ratio.

[0076] Specifically, the value range of the preset quantity ratio is set to [40%, 100%], and 40% is preferred in the embodiment of the present invention.

[0077] Specifically, the data analysis module determines to adjust the data extraction ratio based on the comparison result that the quantity ratio difference is greater than a preset quantity ratio difference under the condition that the intervention strategy does not meet the standard;

[0078] The adjustment of the correction coefficient is determined based on a comparison result that the quantity ratio difference is less than or equal to a preset quantity ratio difference.

[0079] Specifically, the value range of the preset quantity proportion difference is set to [3%, 20%], and 5% is preferred in the embodiment of the present invention.

[0080] Specifically, the data analysis module sets several adjustment methods based on the data extraction ratio, and the adjustment range of the data extraction ratio in each adjustment method is positively correlated with the difference in the quantity proportion.

[0081] Specifically, the larger the difference in the quantity ratio is, the greater the adjustment range of the data extraction ratio is.

[0082] Specifically, the data analysis module sets several adjustment methods based on the correction coefficient, and the adjustment range of the correction coefficient in each adjustment method is positively correlated with the difference in the quantity proportion.

[0083] Specifically, the larger the difference in the quantity proportion is, the greater the adjustment range of the correction coefficient is.

[0084] See also Figure 2 As shown, it is a flow chart of the autism assessment method according to an embodiment of the present invention.

[0085] The present invention also provides an autism assessment method, comprising:

[0086] Step S1, obtaining the assessment data of the patient during the assessment project execution, and performing standardization processing on the assessment data to obtain each characteristic data value;

[0087] Step S2, generating a plurality of charts based on each of the characteristic data values ​​and calculating evaluation values ​​according to the plurality of charts;

[0088] Step S3, determining whether the feature data value meets the standard based on the comparison result between the feature data value and the standard feature data value, and generating a first feature set and a second feature set according to the comparison result;

[0089] Step S4, determining a data extraction ratio of the feature set based on the evaluation value, and determining a correction coefficient of the data extraction ratio according to the patient's mood fluctuation frequency to generate an intervention strategy;

[0090] Step S5, for a single intervention target in the intervention strategy, determining whether the single intervention target meets the standard based on the patient's execution deviation, and determining whether the intervention strategy meets the standard based on the proportion of the number of intervention targets that do not meet the standard; if the intervention strategy does not meet the standard, determining the adjustment data extraction ratio or the correction coefficient of the adjustment data extraction ratio based on the difference in the proportion of the number of intervention targets.

[0091] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. An autism assessment system, characterized in that: include: A data acquisition module is used to obtain the assessment data of the patient during the process of performing the assessment project, wherein the assessment data includes audio data, video data, physiological data and scale data; A data processing module connected to the data acquisition module, for performing standardization processing on the evaluation data to obtain each characteristic data value, generating a plurality of charts based on each characteristic data value and calculating the evaluation value according to the plurality of charts; A data analysis module connected to the data processing module is used to determine whether the characteristic data value meets the standard based on the comparison result between the characteristic data value and the standard characteristic data value, so as to generate a first feature set based on the characteristic data value that meets the standard, and generate a second feature set based on the characteristic data value that does not meet the standard, and determine the data extraction ratio of the characteristic set based on the evaluation value, and determine the correction coefficient of the data extraction ratio according to the frequency of the patient's emotional fluctuations, generate an intervention strategy based on the extracted data, and determine whether a single intervention target meets the standard based on the patient's execution deviation, and determine whether the intervention strategy meets the standard based on the proportion of the number of intervention targets that do not meet the standard, and determine the adjustment data extraction ratio or the correction coefficient of the adjustment data extraction ratio based on the difference in the proportion of the number of intervention targets under the condition that the intervention strategy does not meet the standard.

2. The autism assessment system according to claim 1, characterized in that: The data analysis module determines, for a single feature data, that the feature data value does not meet the standard based on a comparison result that the feature data value is greater than a first standard feature data value or is less than a second standard feature data value.

3. The autism assessment system according to claim 2, characterized in that: The data analysis module determines the data extraction ratio of the feature set based on the evaluation value, including determining to extract the data of the feature set using a first extraction ratio based on a comparison result that the evaluation value is greater than or equal to a preset evaluation value; Based on the comparison result that the evaluation value is less than the preset evaluation value, it is determined to use a second extraction ratio to extract the data of the feature set.

4. The autism assessment system according to claim 3, characterized in that: The data analysis module determines a correction coefficient of the data extraction ratio based on the emotion fluctuation frequency, If the emotion fluctuation frequency is greater than a first preset fluctuation frequency, the data analysis module determines to use a first correction coefficient to correct the data extraction ratio; If the emotion fluctuation frequency is less than or equal to the first preset fluctuation frequency and greater than the second preset fluctuation frequency, the data analysis module determines to use a second correction coefficient to correct the data extraction ratio; If the emotion fluctuation frequency is less than the second preset fluctuation frequency, the data analysis module determines to use a third correction coefficient to correct the data extraction ratio.

5. The autism assessment system according to claim 4, characterized in that: The data analysis module determines whether a single intervention target meets the standard based on the execution deviation, including determining that the intervention target does not meet the standard based on a comparison result that the execution deviation is less than a preset deviation.

6. The autism assessment system according to claim 5, characterized in that: The data analysis module counts the number of intervention targets that do not meet the standards and calculates the number ratio, and determines that the intervention strategy does not meet the standards based on a comparison result that the number ratio is less than a preset number ratio.

7. The autism assessment system according to claim 6, characterized in that: The data analysis module determines to adjust the data extraction ratio based on a comparison result that the quantity ratio difference is greater than a preset quantity ratio difference under the condition that the intervention strategy does not meet the standard; The adjustment of the correction coefficient is determined based on a comparison result that the quantity ratio difference is less than or equal to a preset quantity ratio difference.

8. The autism assessment system according to claim 7, characterized in that: The data analysis module sets several adjustment methods based on the data extraction ratio, and the adjustment range of the data extraction ratio in each adjustment method is positively correlated with the difference in the quantity proportion.

9. The autism assessment system according to claim 7, characterized in that: The data analysis module sets several adjustment methods based on the correction coefficient, and the adjustment range of the correction coefficient in each adjustment method is positively correlated with the difference in the quantity proportion.

10. A method for applying the autism assessment system according to any one of claims 1 to 9, characterized in that: include: Acquire the assessment data of the patient during the assessment project execution, and perform standardization on the assessment data to obtain the values ​​of each characteristic data; generating a plurality of graphs based on each of the characteristic data values ​​and calculating evaluation values ​​according to the plurality of graphs; Determine whether the feature data value meets the standard based on the comparison result between the feature data value and the standard feature data value, and generate a first feature set and a second feature set according to the comparison result; Determining a data extraction ratio of a feature set based on the evaluation value, and determining a correction coefficient of the data extraction ratio according to the patient's mood fluctuation frequency to generate an intervention strategy; For a single intervention target in the intervention strategy, whether the single intervention target meets the standard is determined based on the patient's execution deviation, and whether the intervention strategy meets the standard is determined based on the proportion of the number of intervention targets that do not meet the standard; if the intervention strategy does not meet the standard, the data extraction ratio or the correction coefficient of the data extraction ratio is determined based on the difference in the proportion of the number of intervention targets.

Images