AI evaluation system based on comprehensive ability of children developed slowly

Abstract

The invention relates to the field of comprehensive ability evaluation, in particular to an AI evaluation system based on comprehensive ability of children with development retardation, which comprises the following steps: determining a data acquisition strategy according to a comparison result of a dynamic image evaluation value and a preset dynamic image evaluation value; based on a first data acquisition strategy, determining the qualification of intervention according to the coincidence degree evaluation value; determining the eligibility of the expanded dynamic image according to the expanded dynamic image coincidence degree evaluation value based on a second data acquisition strategy; determining the qualification of the expanded dynamic image selection standard according to the comprehensive evaluation value of the expanded dynamic image; determining the eligibility of the expanded dynamic image according to the accuracy evaluation value of the expanded dynamic image based on the standard qualification of the expanded dynamic image; and determining the eligibility of the expanded dynamic image according to the ratio of the accuracy evaluation value of the expanded dynamic image to a preset accuracy evaluation value based on the unqualified expanded dynamic image, and determining an adjustment mode. According to the invention, the accuracy and efficiency of comprehensive ability evaluation of children with delayed development are improved.

Description

Technical Field

[0001] The present invention relates to the field of comprehensive ability assessment, and in particular to an AI assessment system based on the comprehensive ability of children with developmental delays. Background Art

[0002] The assessment of children with developmental delay is a complex and serious task, requiring diagnosticians to have proficient professional skills and a scientific attitude. The assessment focuses not only on the child's intelligence level, but also on the development of their adaptive behavior, social interaction skills and other aspects. Through comprehensive assessment, appropriate and effective individualized teaching plans can be provided for children with developmental delay to promote their all-round development.

[0003] Chinese patent application publication number: CN114842958A discloses a system and method for evaluating and analyzing children's comprehensive abilities. The system includes: a self-test module for obtaining basic information of the evaluated child, providing self-test questions to the parents of the evaluated child based on the basic information based on a preset self-test question bank, and automatically generating a personalized evaluation package based on the self-test results; an evaluation module for obtaining evaluation questions suitable for the ability of the evaluated child from a preset evaluation question bank based on the personalized evaluation package, and determining corresponding teaching aids based on the self-test evaluation report and the evaluation questions, obtaining the answers of the evaluated child to the evaluation questions based on the teaching aids, scoring each evaluation question based on the answers, and obtaining the scores of all evaluation questions; an analysis module for generating child speech behavior evaluation analysis results based on the scores of all evaluation questions based on preset analysis rules. However, the prior art has the following problems:

[0004] This method has low accuracy in assessing the comprehensive abilities of children with developmental delays, which leads to low accuracy and efficiency in assessing the comprehensive abilities of children with developmental delays. Summary of the invention

[0005] To this end, the present invention provides an AI evaluation system based on the comprehensive abilities of children with developmental delays, so as to overcome the problems of low accuracy and low efficiency in the evaluation of the comprehensive abilities of children with developmental delays in the prior art.

[0006] To achieve the above objectives, the present invention provides an AI evaluation system based on the comprehensive ability of children with developmental delays, comprising:

[0007] An acquisition strategy determination module, which is used to determine a data acquisition strategy according to a comparison result between a dynamic image evaluation value and a preset dynamic image evaluation value;

[0008] An intervention determination module, connected to the acquisition strategy determination module, for determining the eligibility of the intervention according to the overlap evaluation value based on the first data acquisition strategy;

[0009] An image eligibility determination module, connected to the acquisition strategy determination module, for determining the eligibility of the expanded dynamic image according to the overlap evaluation value of the expanded dynamic image based on the second data acquisition strategy;

[0010] A selection standard determination module, which is connected to the intervention determination module and the image eligibility determination module respectively, and is used to determine the eligibility of the extended dynamic image selection standard according to the comprehensive evaluation value of the extended dynamic image;

[0011] an accuracy determination module connected to the selection standard determination module, for determining the eligibility of the extended dynamic image based on the eligibility of the extended dynamic image selection standard and according to the accuracy evaluation value of the extended dynamic image;

[0012] The process adjustment module is connected to the accuracy determination module, and is used to determine the eligibility of the expanded dynamic image based on the ratio of the accuracy evaluation value of the expanded dynamic image to the preset accuracy evaluation value, and determine the adjustment method.

[0013] Furthermore, under the condition of collecting dynamic images of children with developmental delays, the acquisition strategy determination module determines a first data acquisition strategy based on a comparison result in which the dynamic image evaluation value is less than or equal to a preset dynamic image evaluation value, and determines a second data acquisition strategy based on a comparison result in which the dynamic image evaluation value is greater than the preset dynamic image evaluation value.

[0014] Furthermore, under the condition of the first data collection strategy, the intervention determination module determines that the intervention is qualified according to a comparison result that the dynamic image coincidence evaluation value is greater than a first preset coincidence evaluation value.

[0015] Furthermore, the image qualification determination module determines that the expanded dynamic image is qualified according to a comparison result that the expanded dynamic image coincidence evaluation value is greater than a second preset coincidence evaluation value under the condition of the second data acquisition strategy.

[0016] Furthermore, the selection standard determination module determines that the extended dynamic image selection standard is qualified based on a comparison result that the comprehensive evaluation value of the extended dynamic image is less than or equal to a preset comprehensive evaluation value under the condition that the supplemented dynamic image is qualified.

[0017] Furthermore, the accuracy determination module determines that the expanded dynamic image is unqualified based on a comparison result that the accuracy evaluation value of the expanded dynamic image is less than or equal to a preset accuracy evaluation value, under the condition that the expanded dynamic image selection standard is qualified.

[0018] Furthermore, the process adjustment module determines to increase the preset comprehensive evaluation value according to a comparison result that the ratio of the accuracy evaluation value to the preset accuracy evaluation value is less than or equal to the preset ratio under the condition that the expanded dynamic image is unqualified.

[0019] Furthermore, under the condition that the expanded dynamic image is unqualified, the process adjustment module determines to increase the second preset coincidence evaluation value according to the comparison result that the ratio of the accuracy evaluation value to the preset accuracy evaluation value is greater than the preset ratio.

[0020] Furthermore, the process adjustment module determines, under the condition of increasing the preset comprehensive evaluation value, to increase the preset comprehensive evaluation value by a preset comprehensive adjustment coefficient based on a comparison result of a preset ratio and a difference between the ratio and a first preset difference, wherein the ratio is a ratio of an accuracy evaluation value to a preset accuracy evaluation value.

[0021] Furthermore, the process adjustment module determines, under the condition of increasing the second preset coincidence evaluation value, to increase the second preset coincidence evaluation value by a preset coincidence adjustment coefficient based on a comparison result of a difference between the ratio and the preset ratio and the second preset difference, wherein the ratio is a ratio of the accuracy evaluation value to the preset accuracy evaluation value.

[0022] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention determines the data collection strategy through the comparison result of the dynamic image evaluation value with the preset dynamic image evaluation value, and under the condition of determining the first data collection strategy, determines the eligibility of the intervention according to the comparison result of the dynamic image coincidence evaluation value with the first preset coincidence evaluation value, thereby achieving accurate assessment of children with developmental delay, improving intervention efficiency, and thus improving the accuracy and efficiency of comprehensive ability assessment of children with developmental delay. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of an AI evaluation system based on the comprehensive ability of children with developmental delays according to an embodiment of the present invention;

[0024] Figure 2 A flow chart for determining a data collection strategy for an embodiment of the present invention;

[0025] Figure 3 A flow chart for determining intervention eligibility for an embodiment of the present invention;

[0026] Figure 4 A flow chart of determining eligibility of extended dynamic image selection criteria according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] See also Figure 1-Figure 4 As shown, Figure 1 This is a flow chart of an AI evaluation system based on the comprehensive ability of children with developmental delays according to an embodiment of the present invention; Figure 2 A flow chart for determining a data collection strategy for an embodiment of the present invention; Figure 3 A flow chart for determining intervention eligibility for an embodiment of the present invention; Figure 4 A flow chart of determining eligibility of extended dynamic image selection criteria according to an embodiment of the present invention.

[0032] The embodiment of the present invention is based on an AI evaluation system for comprehensive abilities of children with developmental delays, including:

[0033] Step S1, determining a data acquisition strategy according to a comparison result between a dynamic image evaluation value and a preset dynamic image evaluation value;

[0034] Step S2, determining the eligibility of the intervention according to the overlap evaluation value based on the first data collection strategy;

[0035] Step S3, determining the eligibility of the expanded dynamic image according to the overlap evaluation value of the expanded dynamic image based on the second data acquisition strategy;

[0036] Step S4, determining the eligibility of the extended dynamic image selection criteria according to the comprehensive evaluation value of the extended dynamic image;

[0037] Step S5, determining the eligibility of the expanded dynamic image based on the extended dynamic image selection criteria being qualified according to the accuracy evaluation value of the expanded dynamic image;

[0038] Step S6, based on the fact that the expanded dynamic image is unqualified, the eligibility of the expanded dynamic image is determined according to the difference between the accuracy evaluation value of the expanded dynamic image and the preset accuracy evaluation value, and an adjustment method is determined.

[0039] Specifically, the embodiment of the present invention determines a data collection strategy based on a comparison result of a dynamic image evaluation value obtained from a dynamic image collected from a child with developmental delay and a preset dynamic image evaluation value;

[0040] When the dynamic image evaluation value is less than or equal to the preset dynamic image evaluation value, determining a first data acquisition strategy;

[0041] When the dynamic image evaluation value is greater than the preset dynamic image evaluation value, a second data acquisition strategy is determined.

[0042] In the embodiment of the present invention, the preset dynamic image evaluation value is 0.85, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0043] Specifically, the embodiment of the present invention calculates the dynamic image evaluation value according to the following formula, setting:

[0044]

[0045] Among them, P represents the dynamic image evaluation value, γ represents the grayscale standard deviation, ω represents the grayscale mean, and η represents the edge density.

[0046] Among them, the grayscale mean represents the average value of the grayscale values ​​of all pixels in the dynamic image, and the edge density represents the number of edge pixels in the dynamic image.

[0047] Specifically, the embodiment of the present invention determines the first data collection strategy as using only the collected dynamic image data before and after the intervention; and determines the second data collection strategy as using the expanded dynamic image data, wherein the expanded dynamic image data includes but is not limited to the dynamic image data before and after the intervention of different individuals.

[0048] Specifically, under the condition of determining the first data acquisition strategy, the embodiment of the present invention determines the eligibility of the intervention according to the comparison result between the dynamic image coincidence evaluation value and the first preset coincidence evaluation value of 0.84;

[0049] When the dynamic image coincidence evaluation value is less than or equal to the first preset coincidence evaluation value, determining that the intervention is unqualified;

[0050] When the dynamic image coincidence evaluation value is greater than the first preset coincidence evaluation value, it is determined that the intervention is qualified.

[0051] In an embodiment of the present invention, the first preset coincidence evaluation value is 0.84. The first preset coincidence evaluation value is obtained by taking the average of the coincidence evaluation values ​​of several historical dynamic images that have qualified intervention. However, the above value is not limited to this. Technical personnel in this field can also adjust the value according to actual needs.

[0052] Specifically, the embodiment of the present invention calculates the dynamic image coincidence evaluation value according to the following formula, setting:

[0053]

[0054] Where R represents the dynamic image coincidence evaluation value, i represents the ith dynamic image, j represents the jth dynamic image, μi represents the mean of the ith dynamic image, μj represents the mean of the jth dynamic image, σi 2 represents the variance of the ith dynamic image, σj 2 represents the variance of the j-th dynamic image, and σij represents the covariance between the ith dynamic image and the j-th dynamic image.

[0055] Specifically, the present invention determines the data collection strategy by comparing the dynamic image evaluation value with the preset dynamic image evaluation value. Under the condition of determining the first data collection strategy, the eligibility of the intervention is determined according to the comparison result between the dynamic image coincidence evaluation value and the first preset coincidence evaluation value, thereby achieving accurate assessment of children with developmental delays and improving intervention efficiency, thereby improving the accuracy and efficiency of comprehensive ability assessment of children with developmental delays.

[0056] Specifically, under the condition of determining the second data acquisition strategy, the embodiment of the present invention determines the eligibility of the expanded dynamic image according to the comparison result between the expanded dynamic image coincidence evaluation value and the second preset coincidence evaluation value 0.8;

[0057] When the expanded dynamic image coincidence evaluation value is less than or equal to the second preset coincidence evaluation value, determining that the expanded dynamic image is unqualified;

[0058] When the expanded dynamic image coincidence evaluation value is greater than the second preset coincidence evaluation value, it is determined that the expanded dynamic image is qualified.

[0059] In the embodiment of the present invention, the second preset overlap evaluation value is 0.8, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0060] Specifically, the embodiment of the present invention calculates the evaluation value of the overlap degree of the extended dynamic image according to the following formula, and sets:

[0061]

[0062] Where L represents the overlap evaluation value of the extended dynamic image, m represents the mth extended dynamic image, n represents the nth extended dynamic image, μm represents the mean of the mth extended dynamic image, μn represents the mean of the nth extended dynamic image, σm 2 represents the variance of the mth extended dynamic image, σn 2 represents the variance of the nth extended dynamic image, and σmn represents the covariance between the mth extended dynamic image and the nth extended dynamic image.

[0063] Specifically, the embodiment of the present invention determines the eligibility of the extended dynamic image selection standard according to the comparison result of the comprehensive evaluation value of the extended dynamic image and the preset comprehensive evaluation value of 0.87 under the condition that the extended dynamic image is determined to be qualified;

[0064] When the comprehensive evaluation value of the extended dynamic image is less than or equal to the preset comprehensive evaluation value, it is determined that the extended dynamic image selection standard is qualified;

[0065] When the comprehensive evaluation value of the expanded dynamic image is greater than the preset comprehensive evaluation value, it is determined that the expanded dynamic image selection standard is unqualified.

[0066] In the embodiment of the invention, the preset comprehensive evaluation value is 0.87. The preset comprehensive evaluation value is obtained by taking the average value of several historical comprehensive evaluation values ​​that meet the expanded dynamic image selection criteria. However, the above value is not limited to this. Those skilled in the art can also adjust the value according to actual needs.

[0067] Specifically, the embodiment of the present invention calculates the comprehensive evaluation value of the extended dynamic image according to the following formula, setting:

[0068]

[0069] Where H represents the comprehensive evaluation value of the expanded dynamic image, gi represents the brightness value of the RGB color space of the i-th pixel in the expanded dynamic image, represents the average brightness value, N represents the total number of pixels of the expanded dynamic image, Wi represents the saturation value of the i-th pixel in the expanded dynamic image in the HSV color space, and Vi represents the brightness value of the i-th pixel in the expanded dynamic image in the HSV color space.

[0070] Specifically, the embodiment of the present invention determines the eligibility of the expanded dynamic image based on the comparison result of the accuracy evaluation value of the expanded dynamic image and the preset accuracy evaluation value of 0.83 under the condition that the expanded dynamic image selection standard is determined to be qualified;

[0071] When the accuracy evaluation value of the expanded dynamic image is less than or equal to the preset accuracy evaluation value, the expanded dynamic image is determined to be unqualified;

[0072] When the accuracy evaluation value of the expanded dynamic image is greater than the preset accuracy evaluation value, the expanded dynamic image is determined to be qualified.

[0073] In the embodiment of the invention, the preset accuracy evaluation value is 0.83. The preset accuracy evaluation value is obtained by taking the average value of several historical accuracy evaluation values ​​of the expanded dynamic image. However, the above value is not limited to this. Those skilled in the art can also adjust the value according to actual needs.

[0074] Specifically, the embodiment of the present invention calculates the accuracy evaluation value of the extended dynamic image according to the following formula, setting:

[0075]

[0076] Among them, X represents the accuracy evaluation value of the expanded dynamic image, N represents the total number of pixels of the expanded dynamic image, ri represents the pixel size of the i-th pixel in the expanded dynamic image, rmax represents the maximum pixel size in the expanded dynamic image, and rmin represents the minimum pixel size in the expanded dynamic image.

[0077] Specifically, under the condition that the expanded dynamic image is determined to be unqualified, the embodiment of the present invention determines to adjust the preset comprehensive evaluation value or the second preset coincidence evaluation value according to the comparison result of the ratio of the accuracy evaluation value to the preset accuracy evaluation value and the preset ratio 0.7;

[0078] When the ratio is less than or equal to the preset ratio, it is determined to increase the preset comprehensive evaluation value;

[0079] When the ratio is greater than the preset ratio, it is determined to increase the second preset coincidence evaluation value;

[0080] The ratio is the ratio of the accuracy evaluation value to the preset accuracy evaluation value.

[0081] In the embodiment of the invention, the preset ratio is 0.7, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0082] Specifically, the embodiment of the present invention determines to increase the preset comprehensive evaluation value according to the comparison result between the difference between the preset ratio and the ratio and the first preset difference of 0.15 under the condition of determining to increase the preset comprehensive evaluation value;

[0083] When the difference is less than or equal to the first preset difference, it is determined to increase the preset comprehensive evaluation value to a corresponding value by the first preset comprehensive adjustment coefficient;

[0084] When the difference is greater than the first preset difference, it is determined to increase the preset comprehensive evaluation value to a corresponding value using the second preset comprehensive adjustment coefficient;

[0085] The difference is a difference between a preset ratio and the ratio.

[0086] In the embodiment of the invention, the first preset difference value is 0.15, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0087] In an embodiment of the present invention, the increased preset comprehensive evaluation value is set to Dz, and Dz=D×Ki is set, wherein D represents the preset comprehensive evaluation value, Ki represents the i-th preset comprehensive adjustment coefficient, i takes a value of 1 or 2, K1 is the first preset comprehensive adjustment coefficient, and K2 is the second preset comprehensive adjustment coefficient.

[0088] Specifically, under the condition that the second preset overlap evaluation value is determined to be adjusted, the embodiment of the present invention determines to increase the second preset overlap evaluation value according to the comparison result of the difference between the ratio and the preset ratio and the second preset difference value of 0.08;

[0089] When the difference is less than or equal to the second preset difference, it is determined to increase the preset coincidence evaluation value to a corresponding value by using the first preset coincidence adjustment coefficient;

[0090] When the difference is greater than a second preset difference, it is determined to increase the preset coincidence evaluation value to a corresponding value using a second preset coincidence adjustment coefficient;

[0091] The difference value is a ratio of the difference value to a preset difference value.

[0092] In the embodiment of the invention, the preset ratio is 0.08, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0093] In an embodiment of the present invention, the increased second preset coincidence evaluation value is set to Uz, and Uz=U×Ki is set, wherein U represents the second preset coincidence evaluation value, Ki represents the i-th preset coincidence adjustment coefficient, i takes a value of 1 or 2, K1 is the first preset coincidence adjustment coefficient, and K2 is the second preset coincidence adjustment coefficient.

[0094] 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.

[0095] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An AI assessment system based on the comprehensive ability of children with developmental delays, characterized in that: include: An acquisition strategy determination module, which is used to determine a data acquisition strategy according to a comparison result between a dynamic image evaluation value and a preset dynamic image evaluation value; An intervention determination module, connected to the acquisition strategy determination module, for determining the eligibility of the intervention according to the overlap evaluation value based on the first data acquisition strategy; An image eligibility determination module, connected to the acquisition strategy determination module, for determining the eligibility of the expanded dynamic image according to the overlap evaluation value of the expanded dynamic image based on the second data acquisition strategy; A selection standard determination module, which is connected to the intervention determination module and the image eligibility determination module respectively, and is used to determine the eligibility of the extended dynamic image selection standard according to the comprehensive evaluation value of the extended dynamic image; an accuracy determination module connected to the selection standard determination module, for determining the eligibility of the extended dynamic image based on the eligibility of the extended dynamic image selection standard and according to the accuracy evaluation value of the extended dynamic image; The process adjustment module is connected to the accuracy determination module, and is used to determine the eligibility of the expanded dynamic image based on the ratio of the accuracy evaluation value of the expanded dynamic image to the preset accuracy evaluation value, and determine the adjustment method.

2. The AI ​​evaluation system based on the comprehensive ability of children with developmental delay according to claim 1 is characterized in that: Under the condition of collecting dynamic images of children with developmental delay, the acquisition strategy determination module determines the first data acquisition strategy according to the comparison result that the dynamic image evaluation value is less than or equal to the preset dynamic image evaluation value, and determines the second data acquisition strategy according to the comparison result that the dynamic image evaluation value is greater than the preset dynamic image evaluation value.

3. The AI ​​evaluation system based on the comprehensive ability of children with developmental delay according to claim 2 is characterized in that: The intervention determination module determines that the intervention is qualified according to a comparison result that the dynamic image coincidence evaluation value is greater than a first preset coincidence evaluation value under the condition of the first data collection strategy.

4. The AI ​​evaluation system based on comprehensive ability of children with developmental delay according to claim 2 is characterized in that: The image qualification determination module determines that the expanded dynamic image is qualified according to a comparison result that the expanded dynamic image coincidence evaluation value is greater than a second preset coincidence evaluation value under the condition of the second data acquisition strategy.

5. The AI ​​evaluation system based on comprehensive ability of children with developmental delay according to claim 4 is characterized in that: The selection standard determination module determines that the extended dynamic image selection standard is qualified according to a comparison result that the comprehensive evaluation value of the extended dynamic image is less than or equal to a preset comprehensive evaluation value under the condition that the supplemented dynamic image is qualified.

6. The AI ​​evaluation system based on comprehensive ability of children with developmental delay according to claim 5, characterized in that: The accuracy determination module determines that the expanded dynamic image is unqualified based on a comparison result that the accuracy evaluation value of the expanded dynamic image is less than or equal to a preset accuracy evaluation value, under the condition that the expanded dynamic image selection standard is qualified.

7. The AI ​​evaluation system based on comprehensive ability of children with developmental delay according to claim 6 is characterized in that: The process adjustment module determines to increase the preset comprehensive evaluation value according to a comparison result that the ratio of the accuracy evaluation value to the preset accuracy evaluation value is less than or equal to the preset ratio under the condition that the expanded dynamic image is unqualified.

8. The AI ​​evaluation system based on comprehensive ability of children with developmental delay according to claim 6, characterized in that: The process adjustment module determines to increase the second preset coincidence evaluation value according to a comparison result that the ratio of the accuracy evaluation value to the preset accuracy evaluation value is greater than the preset ratio under the condition that the expanded dynamic image is unqualified.

9. The AI ​​evaluation system based on comprehensive ability of children with developmental delay according to claim 7, characterized in that: The process adjustment module determines, under the condition of increasing the preset comprehensive evaluation value, to increase the preset comprehensive evaluation value by a preset comprehensive adjustment coefficient based on a comparison result between a preset ratio and a difference between the ratio and a first preset difference, wherein the ratio is a ratio of an accuracy evaluation value to a preset accuracy evaluation value.

10. The AI ​​evaluation system based on comprehensive ability of children with developmental delay according to claim 8, characterized in that: The process adjustment module determines, under the condition of increasing the second preset coincidence evaluation value, to increase the second preset coincidence evaluation value by a preset coincidence adjustment coefficient based on a comparison result of a difference between the ratio and the preset ratio and the second preset difference, wherein the ratio is a ratio of the accuracy evaluation value to the preset accuracy evaluation value.

Images