Special child intervention scheme generation method

Abstract

The invention relates to the technical field of rehabilitation medicine, in particular to a special child intervention scheme generation method which comprises the steps that an analysis module obtains data and generates an intervention strategy; for the intervention strategy of the single special child, obtaining a first target proportion and a second target proportion after the intervention training stage is ended, and determining whether the training effect of the intervention training stage meets the standard or not based on the second target proportion; under the condition that the training effect of the intervention training stage does not conform to the standard, training targets of which the training effects do not conform to the standard are obtained, and the extraction quantity of the corresponding feature data is determined and adjusted based on the target proportion; and determining whether the intervention strategy generated by the analysis module meets the standard based on the third target proportion, and determining to adopt the first adjustment mode or the second adjustment mode to adjust the extraction quantity of the feature data based on the target proportion difference value. The credibility of the intervention strategy generated by the analysis module is improved.

Description

Technical Field

[0001] The present invention relates to the field of rehabilitation medical technology, and in particular to a method for generating a special children intervention program. Background Art

[0002] With the deepening of modern medical and educational research, people have gradually realized that special children, such as those with intellectual disabilities, autism, hearing impairment, and visual impairment, face many challenges in their growth. These challenges not only affect their daily life and learning, but also constitute obstacles to their social integration and future development. Therefore, in order to promote the all-round development of special children and improve their quality of life, all sectors of society have begun to actively explore scientific and effective methods for generating intervention strategies.

[0003] This method aims to develop personalized rehabilitation plans based on the individual differences and rehabilitation needs of special children by comprehensively applying knowledge and techniques from multiple disciplines such as medicine, education, and psychology. In this process, we not only focus on the recovery and training of children's physiological functions, but also emphasize the comprehensive cultivation of their psychological, cognitive, emotional, and social abilities. Through scientific evaluation, design, implementation, and feedback mechanisms, we continuously optimize intervention strategies to ensure that special children can receive the most suitable rehabilitation services for themselves, thereby maximizing their potential and realizing their personal value and social integration.

[0004] Chinese Patent Publication No.: CN116705236A discloses a method, system and device for generating a patient rehabilitation program, the method comprising: obtaining patient data, wherein the patient data at least includes the patient's personal data, medical record data, injury and disease assessment data and training data; processing the patient data to obtain multimodal feature data, wherein the multimodal feature data at least includes first univariate feature data, text feature data, second univariate feature data, sequence feature data and mesh topology structure feature data; inputting the multimodal feature data into a rehabilitation program generation model obtained by training the MMGT neural network to obtain the patient's rehabilitation program. Through this method, the patient's rehabilitation program can be automatically obtained according to the data in the patient's rehabilitation process, and the patient's rehabilitation program can be automatically adjusted according to the patient's rehabilitation progress, avoiding the influence of human factors, and improving the efficiency and accuracy of the patient's rehabilitation program generation.

[0005] It can be seen that the method, system and device for generating patient rehabilitation plans have the following problems: the invention automatically generates a patient rehabilitation plan based on the MMGT neural network, and automatically adjusts the patient's rehabilitation plan according to the patient's rehabilitation progress, but the invention lacks monitoring of the robustness of the neural network and cannot guarantee the credibility of the rehabilitation plan issued by the neural network based on patient information. Summary of the invention

[0006] To this end, the present invention provides a method for generating a special children's rehabilitation program to overcome the problem in the prior art that there is a lack of monitoring of the accuracy of intervention strategies, thereby resulting in low credibility of intervention strategies generated by an analysis module based on historical rehabilitation data of patients.

[0007] To achieve the above object, the present invention provides a method for generating intervention strategies for special children, comprising:

[0008] Acquire some data of special children, extract physiological characteristic data set based on physiological data, and extract psychological characteristic data set based on psychological data;

[0009] Performing data processing on historical rehabilitation data to extract key features and generate a key feature dataset;

[0010] Inputting the physiological characteristic data set, the psychological characteristic data set and the key characteristic data set into an analysis module to generate an intervention strategy, wherein the intervention strategy includes a plurality of intervention training stages;

[0011] For each intervention training stage, a first training target set, a second training target set, and a third training target set with corresponding proportions are set based on the data proportion of each feature data set;

[0012] A preset number of tests are set for the intervention training target, and the test results are obtained to determine whether the training effect of a single intervention training target meets the standard, and the first target ratio of the training effect meeting the standard is calculated, and a second target ratio is generated based on the text summary of the test process of the single test target by the behavior assessor to determine whether the training effect of the intervention training stage meets the standard, wherein the single test results include pass, auxiliary pass and fail, and the semantic sentiment analysis results include positive, negative and neutral;

[0013] Under the condition that the training effect in the intervention training stage does not meet the standard, obtaining the training targets of each training effect that does not meet the standard, determining the training target set to which each training target belongs, and determining the number of training effects that do not meet the standard in each training target set, and adjusting the number of extracted feature data corresponding to the adjustment based on the target ratio, wherein the target ratio is the ratio of the number of training targets of each training target set whose training effect does not meet the standard to the number of training targets in each training target set during the intervention training stage;

[0014] The training effects of several special children in the intervention training stage are obtained, and whether the accuracy of the intervention strategy meets the standard is determined based on the third target proportion of the training effects meeting the standard; and under the condition that the accuracy of the intervention strategy does not meet the standard, based on the target proportion difference, determine whether to adopt the first adjustment mode or the second adjustment mode to adjust the number of extracted feature data, wherein the third target proportion is the ratio of the number of special children whose training effects in the intervention training stage meet the standard to the number of all special children in the intervention training stage.

[0015] Furthermore, a training target of a corresponding proportion is set in each intervention training stage based on the data proportion of the physiological characteristic data set, the psychological characteristic data set and the key characteristic data set.

[0016] Furthermore, the process of determining whether the training effect of a single intervention training target meets the standard based on the test results includes:

[0017] Obtaining the test results of the preset number of times;

[0018] If the number of passes is greater than or equal to the preset number of passes, it is determined that the training effect of the single intervention training target meets the standard;

[0019] If the number of passes is less than the preset number of passes, it is determined that the training effect of the single intervention training target does not meet the standard.

[0020] Furthermore, the process of generating the second target proportion based on the semantic sentiment analysis result includes:

[0021] If the semantic sentiment analysis result is positive, determining to use a first correction coefficient to correct the first target proportion to generate the second target proportion;

[0022] If the semantic sentiment analysis result is negative, determining to use a second correction coefficient to correct the first target proportion to generate the second target proportion;

[0023] If the semantic sentiment analysis result is neutral, the first target proportion is not corrected.

[0024] Furthermore, the process of determining whether the training effect of the intervention training phase meets the standard based on the second target proportion includes:

[0025] If the second target proportion is greater than or equal to the first preset target proportion, it is determined that the training effect of the intervention training phase meets the standard;

[0026] If the second target proportion is less than the first preset target proportion, it is determined that the training effect of the intervention training phase does not meet the standard.

[0027] Further, under the condition that the training effect in the intervention training stage does not meet the standard, the process of determining the extraction quantity of the corresponding feature data based on the target proportion includes:

[0028] Calculating the proportion of each target for the first training target set, the second training target set, and the third training target set;

[0029] Based on the comparison result that each target proportion is greater than the second preset target proportion, it is determined to adjust the corresponding extraction quantity of the first feature data, and / or the extraction quantity of the second feature data, and / or the extraction quantity of the third feature data.

[0030] Furthermore, several adjustment methods are set for the extraction quantity of each of the characteristic data, and each adjustment method has a different adjustment range for the extraction quantity of each of the characteristic data.

[0031] Further, the process of determining whether the accuracy of the intervention strategy meets the standard based on the third target proportion of the training effect meeting the standard includes:

[0032] If the third target proportion is greater than or equal to the third preset target proportion, it is determined that the accuracy of the intervention strategy meets the standard;

[0033] If the third target proportion is less than the third preset target proportion, it is determined that the accuracy of the intervention strategy does not meet the standard.

[0034] Further, under the condition that the accuracy of the intervention strategy does not meet the standard, the process of determining to use the first adjustment mode to adjust the extraction quantity of feature data based on the target proportion difference includes:

[0035] If the target proportion difference is greater than or equal to the preset difference, determining to use the first adjustment mode to adjust the extraction quantity of the feature data;

[0036] The first adjustment mode sets several adjustment methods for the extraction quantity of the characteristic data, and each adjustment method has a different adjustment range for the extraction quantity of the characteristic data.

[0037] Further, the process of determining to use the second adjustment mode to adjust the extraction quantity of feature data based on the target proportion difference includes:

[0038] If the target proportion difference is less than the preset difference, determining to use the second adjustment mode to adjust the extraction quantity of the feature data;

[0039] The second adjustment mode sets several adjustment methods for the extraction quantity of the characteristic data, and each adjustment method has a different adjustment range for the extraction quantity of the characteristic data.

[0040] Compared with the prior art, the beneficial effects of the present invention are: the present invention extracts each feature data set based on the data of special children, inputs each feature data set into the analysis module to generate an intervention strategy, and provides effective intervention strategies for children of different age groups, different conditions and different rehabilitation goals; after completing a stage of rehabilitation training, a preset number of tests are set based on the goals of the rehabilitation training in this stage to determine whether the special children have achieved the goals of the rehabilitation training, and based on the proportion of special children who have achieved the intervention training goals, it is determined whether the intervention strategy generated by the analysis module is appropriate, thereby evaluating whether the accuracy of the intervention strategy meets the standards, and if it does not meet the standards, the data volume of the feature data set is corrected in a targeted manner, thereby improving the credibility of the intervention strategy generated by the analysis module.

[0041] Furthermore, the present invention sets the ratio of training targets based on the data ratio of each feature data set. The more data volume of the feature data set, the more problems the special children have in the data corresponding to the feature data. The training targets for rehabilitation training need to be divided more finely to ensure that the rehabilitation effect of special children reaches the expected level, thereby improving the credibility of the intervention strategy generated by the analysis module.

[0042] Furthermore, the present invention sets a preset number of tests for a single intervention training target in each intervention training stage, determines the proportion of the first target based on the test results, and corrects the proportion of the first target based on the text summary of the behavioral assessor to generate a second target proportion, and based on the second target proportion, comprehensively and objectively determines whether the training effect of the intervention training stage meets the standard, thereby improving the credibility of the intervention strategy generated by the analysis module.

[0043] Furthermore, for the intervention training stage where the rehabilitation training effect does not meet the standards, the present invention is based on the characteristic data belonging to the training targets that do not meet the standards, and statistics the percentage of training targets set according to each characteristic data that do not meet the standards. According to each percentage, the extracted number of characteristic data corresponding to the percentage is corrected, thereby improving the credibility of the intervention strategy generated by the analysis module.

[0044] Furthermore, the present invention determines whether the accuracy of the intervention strategy meets the standard based on the proportion of the third target whose training effects meet the standard for several special children, and determines the adjustment mode based on the proportion of the target difference for situations that do not meet the standard, and sets several adjustment methods in each adjustment mode, thereby improving the credibility of the intervention strategy generated by the analysis module. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flowchart of a method for generating intervention strategies for special children according to an embodiment of the present invention;

[0046] Figure 2 A flowchart for determining whether a training effect of a single intervention training target meets a standard according to an embodiment of the present invention;

[0047] Figure 3 A flowchart for generating the second target proportion for an embodiment of the present invention;

[0048] Figure 4 The present invention is a flowchart for determining whether the training effect of the intervention training phase meets the standard. DETAILED DESCRIPTION

[0049] 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.

[0050] 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.

[0051] 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.

[0052] 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.

[0053] See also Figure 1 As shown, it is a flow chart of a method for generating intervention strategies for special children according to an embodiment of the present invention.

[0054] The embodiment of the present invention provides a method for generating a special children intervention strategy, comprising:

[0055] Step S1, obtaining some data of special children, extracting a physiological characteristic data set based on the physiological data, and extracting a psychological characteristic data set based on the psychological data;

[0056] Step S2, performing data processing on the historical rehabilitation data to extract key features and generate a key feature data set;

[0057] Step S3, inputting the physiological characteristic data set, the psychological characteristic data set and the key characteristic data set into an analysis module to generate an intervention strategy, wherein the intervention strategy includes a plurality of intervention training stages;

[0058] Step S4, for each intervention training stage, a first training target set, a second training target set, and a third training target set with corresponding proportions are set based on the data proportions of each feature data set;

[0059] Step S5, setting a preset number of tests for the intervention training target, obtaining the test results to determine whether the training effect of a single intervention training target meets the standard, calculating the first target ratio of the training effect meeting the standard, and generating a second target ratio based on the text summary of the test process of the single test target by the behavior assessor to determine whether the training effect of the intervention training stage meets the standard, wherein the single test results include pass, auxiliary pass and fail, and the semantic sentiment analysis results include positive, negative and neutral;

[0060] Step S6, under the condition that the training effect in the intervention training stage does not meet the standard, obtaining the training targets of each training effect not meeting the standard, determining the training target set to which each training target belongs, and determining the number of training effects not meeting the standard in each training target set, and adjusting the extraction quantity of the corresponding feature data based on the target proportion, wherein the target proportion is the ratio of the number of training targets of each training target set whose training effect does not meet the standard to the number of training targets in each training target set during the intervention training stage;

[0061] Step S7, obtaining the training effects of several special children in the intervention training stage, determining whether the accuracy of the intervention strategy meets the standard based on the third target proportion of training effects that meet the standard, and under the condition that the accuracy of the intervention strategy does not meet the standard, determining whether to use the first adjustment mode or the second adjustment mode to adjust the number of feature data extracted based on the target proportion difference, wherein the third target proportion is the ratio of the number of special children whose training effects in the intervention training stage meet the standard to the number of all special children in the intervention training stage.

[0062] Specifically, the historical rehabilitation data includes but is not limited to intervention plans and implementation status.

[0063] Specifically, the steps for processing the historical rehabilitation data are: 1. cleaning; 2. denoising; 3. summarizing into a number of data points using a digital method.

[0064] Specifically, the key feature data set generation process includes: generating a one-dimensional scatter plot based on data points, for example, without specific limitation, analyzing curve fluctuation data based on the graph, extracting key features including but not limited to the standard deviation and average value of the data points to generate a key feature data set.

[0065] Specifically, the analysis module uses an AI model such as a decision tree model or a traditional algorithm such as feature matching, which can be replaced according to actual needs and is not specifically limited.

[0066] Specifically, the physiological data includes but is not limited to age, height, weight, and physiological function data; the psychological data includes but is not limited to intelligence assessment data, social skills assessment data, the relationship between emotions and behaviors, and cognitive development.

[0067] Specifically, the feature data extraction process 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.

[0068] Specifically, in the embodiment of the present invention, the intervention strategy automatically output by the analysis module is determined by the user whether to use it. If the user chooses not to use it, the intervention strategy can be manually selected. If the repetition rate between the manually selected intervention strategy and the automatically generated intervention strategy is less than 50%, the user is prompted for a second confirmation.

[0069] Specifically, the present invention extracts each feature data set based on the data of special children, inputs each feature data set into the analysis module to generate an intervention strategy, and provides effective intervention strategies for children of different age groups, different conditions and different rehabilitation goals; after completing a stage of rehabilitation training, a preset number of tests are set based on the goals of the rehabilitation training in this stage to determine whether the special children have achieved the goals of the rehabilitation training, and based on the proportion of special children who have achieved the intervention training goals, determine whether the intervention strategy generated by the analysis module is appropriate, so as to evaluate whether the accuracy of the intervention strategy meets the standards, and if it does not meet the standards, the data volume of the feature data set is corrected in a targeted manner.

[0070] Specifically, a training target of a corresponding proportion is set in each intervention training stage based on the data proportion of the physiological characteristic data set, the psychological characteristic data set and the key characteristic data set.

[0071] Specifically, the present invention sets the ratio of training targets based on the data ratio of each feature data set. The more data volume of the feature data set, the more problems the special children have in the data corresponding to the feature data. The training targets for rehabilitation training need to be divided more finely to ensure that the rehabilitation effect of special children reaches the expected level, thereby improving the accuracy of the intervention strategy generated by the analysis module.

[0072] See also Figure 2 As shown, it is a flow chart of an embodiment of the present invention for determining whether the training effect of a single intervention training target meets the standard.

[0073] Specifically, the process of determining whether the training effect of a single intervention training target meets the standard based on the test results includes:

[0074] Obtain the test results of the preset number of 10 times;

[0075] If the number of passes is greater than or equal to the preset number of passes of 7 times, it is determined that the training effect of the single intervention training target meets the standard;

[0076] If the number of passes is less than the preset number of passes of 7 times, it is determined that the training effect of the single intervention training target does not meet the standard.

[0077] See also Figure 3 As shown, it is a flow chart of generating the second target proportion in an embodiment of the present invention.

[0078] Specifically, the process of generating the second target proportion based on the semantic sentiment analysis result includes:

[0079] If the semantic sentiment analysis result is positive, determining to use a first correction coefficient of 1.1 to correct the first target proportion to generate the second target proportion;

[0080] If the semantic sentiment analysis result is negative, determining to use a second correction coefficient of 0.9 to correct the first target proportion to generate the second target proportion;

[0081] If the semantic sentiment analysis result is neutral, the first target proportion is not corrected.

[0082] Specifically, if the semantic sentiment analysis result is neutral, the first target proportion is the second target proportion.

[0083] Specifically, the results of semantic analysis are directly output by the analysis module, which uses natural language processing technology to deeply understand and analyze the text content to determine the emotional tendency expressed by the text.

[0084] See also Figure 4As shown, it is a flow chart of an embodiment of the present invention for determining whether the training effect of the intervention training stage meets the standard.

[0085] Specifically, the process of determining whether the training effect of the intervention training phase meets the standard based on the second target proportion includes:

[0086] If the second target proportion is greater than or equal to 85% of the first preset target proportion, it is determined that the training effect of the intervention training phase meets the standard;

[0087] If the second target proportion is less than 85% of the first preset target proportion, it is determined that the training effect of the intervention training stage does not meet the standard.

[0088] Specifically, the present invention sets a preset number of tests for a single intervention training target in each intervention training stage, determines the proportion of the first target based on the test results, and corrects the proportion of the first target based on the text summary of the behavioral assessor to generate a second target proportion, and based on the second target proportion, comprehensively and objectively determines whether the training effect of the intervention training stage meets the standard.

[0089] Specifically, under the condition that the training effect of the intervention training stage does not meet the standard, the process of determining the extraction quantity of feature data corresponding to the adjustment based on the target proportion includes:

[0090] Calculating the proportion of each target for the first training target set, the second training target set, and the third training target set;

[0091] Based on the comparison result that each target proportion is greater than 60% of the second preset target proportion, it is determined to adjust the corresponding extraction quantity of the first feature data, and / or the extraction quantity of the second feature data, and / or the extraction quantity of the third feature data.

[0092] Specifically, several adjustment methods are set for the extraction quantity of each feature data, and each adjustment method has a different adjustment range for the extraction quantity of each feature data.

[0093] Specifically, the difference between the target proportion and the second preset target proportion is recorded as the first difference.

[0094] If the first difference is greater than or equal to a first preset difference of 10%, it is determined to use a first quantity adjustment coefficient of 1.5 to adjust the extraction quantity of the corresponding feature data;

[0095] If the first difference is less than 10% of the first preset difference, it is determined to use the second quantity adjustment coefficient of 1.2 to adjust the extraction quantity of the corresponding feature data.

[0096] Specifically, the present invention targets the intervention training stage in which the rehabilitation training effect does not meet the standards. Based on the characteristic data of the training targets that do not meet the standards, and statistically analyzing the percentage of training targets set according to each characteristic data that do not meet the standards, the extracted number of characteristic data corresponding to the percentage is corrected according to each percentage.

[0097] Specifically, the process of determining whether the accuracy of the intervention strategy meets the standard based on the third target proportion of the training effect meeting the standard includes:

[0098] If the third target proportion is greater than or equal to 90% of the third preset target proportion, it is determined that the accuracy of the intervention strategy meets the standard;

[0099] If the third target proportion is less than 90% of the third preset target proportion, it is determined that the accuracy of the intervention strategy does not meet the standard.

[0100] Specifically, under the condition that the accuracy of the intervention strategy does not meet the standard, the process of determining to use the first adjustment mode to adjust the number of extracted feature data based on the target proportion difference includes:

[0101] If the target proportion difference is greater than or equal to a preset difference of 5%, determining to use the first adjustment mode to adjust the extraction quantity of the feature data;

[0102] The first adjustment mode sets several adjustment methods for the extraction quantity of the characteristic data, and each adjustment method has a different adjustment range for the extraction quantity of the characteristic data.

[0103] Specifically, the difference percentage between the target proportion difference and the preset difference is recorded as the first percentage;

[0104] If the first percentage is greater than or equal to a first preset percentage of 20%, it is determined to use a third quantity adjustment coefficient of 1.7 to adjust the quantity of the extracted feature data;

[0105] If the first percentage is less than the first preset percentage of 20%, it is determined to use a fourth quantity adjustment coefficient of 1.5 to adjust the quantity of feature data to be extracted.

[0106] Specifically, the process of determining to use the second adjustment mode to adjust the amount of feature data to be extracted based on the target proportion difference includes:

[0107] If the target proportion difference is less than the preset difference of 5%, determining to use the second adjustment mode to adjust the extraction quantity of the feature data;

[0108] The second adjustment mode sets several adjustment methods for the extraction quantity of the characteristic data, and each adjustment method has a different adjustment range for the extraction quantity of the characteristic data.

[0109] Specifically, the difference percentage between the target proportion difference and the preset difference is recorded as the second percentage;

[0110] If the second percentage is greater than or equal to the second preset percentage of 10%, it is determined to use a fifth quantity adjustment coefficient of 1.4 to adjust the quantity of the extracted feature data;

[0111] If the second percentage is less than the second preset percentage of 10%, it is determined to use the fifth quantity adjustment coefficient of 1.2 to adjust the extraction quantity of the feature data.

[0112] Specifically, the number of extracted feature data adjusted by different adjustment modes refers to the total number of extracted feature data determined by physiological data, historical rehabilitation data and psychological data.

[0113] Specifically, the present invention determines whether the accuracy of the intervention strategy meets the standard based on the proportion of the third target whose training effects meet the standard for several special children, and for situations that do not meet the standard, determines the adjustment mode based on the proportion of the target difference, and sets several adjustment methods under each adjustment mode.

[0114] 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. A method for generating a special child intervention program, characterized in that: include: Acquire some data of special children, extract physiological characteristic data set based on physiological data, and extract psychological characteristic data set based on psychological data; Performing data processing on historical rehabilitation data to extract key features and generate a key feature dataset; Inputting the physiological characteristic data set, the psychological characteristic data set and the key characteristic data set into an analysis module to generate an intervention strategy, wherein the intervention strategy includes a plurality of intervention training stages; For each intervention training stage, a first training target set, a second training target set, and a third training target set with corresponding proportions are set based on the data proportion of each feature data set; A preset number of tests are set for the intervention training target, and the test results are obtained to determine whether the training effect of a single intervention training target meets the standard, and the first target ratio of the training effect meeting the standard is calculated, and a second target ratio is generated based on the text summary of the test process of the single test target by the behavior assessor to determine whether the training effect of the intervention training stage meets the standard, wherein the single test results include pass, auxiliary pass and fail, and the semantic sentiment analysis results include positive, negative and neutral; Under the condition that the training effect in the intervention training stage does not meet the standard, obtaining the training targets of each training effect that does not meet the standard, determining the training target set to which each training target belongs, and determining the number of training effects that do not meet the standard in each training target set, and adjusting the number of extracted feature data corresponding to the adjustment based on the target ratio, wherein the target ratio is the ratio of the number of training targets of each training target set whose training effect does not meet the standard to the number of training targets in each training target set during the intervention training stage; The training effects of several special children in the intervention training stage are obtained, and whether the accuracy of the intervention strategy meets the standard is determined based on the third target proportion of the training effects meeting the standard; and under the condition that the accuracy of the intervention strategy does not meet the standard, based on the target proportion difference, determine whether to adopt the first adjustment mode or the second adjustment mode to adjust the number of extracted feature data, wherein the third target proportion is the ratio of the number of special children whose training effects in the intervention training stage meet the standard to the number of all special children in the intervention training stage.

2. The method for generating a special children intervention program according to claim 1, characterized in that: A training target of a corresponding proportion is set in each intervention training stage based on the data proportion of the physiological characteristic data set, the psychological characteristic data set and the key characteristic data set.

3. The method for generating a special children intervention program according to claim 2, characterized in that: The process of determining whether the training effect of a single intervention training goal meets the standard based on the test results includes: Obtaining the test results of the preset number of times; If the number of passes is greater than or equal to the preset number of passes, it is determined that the training effect of the single intervention training target meets the standard; If the number of passes is less than the preset number of passes, it is determined that the training effect of the single intervention training target does not meet the standard.

4. The method for generating a special children intervention program according to claim 3, characterized in that: The process of generating the second target proportion based on the semantic sentiment analysis result includes: If the semantic sentiment analysis result is positive, determining to use a first correction coefficient to correct the first target proportion to generate the second target proportion; If the semantic sentiment analysis result is negative, determining to use a second correction coefficient to correct the first target proportion to generate the second target proportion; If the semantic sentiment analysis result is neutral, the first target proportion is not corrected.

5. The method for generating a special children intervention program according to claim 4, characterized in that: The process of determining whether the training effect of the intervention training phase meets the standard based on the second target proportion includes: If the second target proportion is greater than or equal to the first preset target proportion, it is determined that the training effect of the intervention training phase meets the standard; If the second target proportion is less than the first preset target proportion, it is determined that the training effect of the intervention training phase does not meet the standard.

6. The method for generating a special child intervention program according to claim 5, characterized in that: Under the condition that the training effect of the intervention training stage does not meet the standard, the process of determining the extraction quantity of feature data corresponding to the adjustment based on the target proportion includes: Calculating the proportion of each target for the first training target set, the second training target set, and the third training target set; Based on the comparison result that each target proportion is greater than the second preset target proportion, it is determined to adjust the corresponding extraction quantity of the first feature data, and / or the extraction quantity of the second feature data, and / or the extraction quantity of the third feature data.

7. The method for generating a special child intervention program according to claim 6, characterized in that: Several adjustment methods are set for the extraction quantity of each feature data, and each adjustment method has a different adjustment range for the extraction quantity of each feature data.

8. The method for generating a special child intervention program according to claim 5, characterized in that: The process of determining whether the accuracy of the intervention strategy meets the standard based on the third target proportion of the training effect meeting the standard includes: If the third target proportion is greater than or equal to the third preset target proportion, it is determined that the accuracy of the intervention strategy meets the standard; If the third target proportion is less than the third preset target proportion, it is determined that the accuracy of the intervention strategy does not meet the standard.

9. The method for generating a special child intervention program according to claim 6, characterized in that: Under the condition that the accuracy of the intervention strategy does not meet the standard, the process of determining to use the first adjustment mode to adjust the extraction quantity of feature data based on the target proportion difference includes: If the target proportion difference is greater than or equal to the preset difference, determining to use the first adjustment mode to adjust the extraction quantity of the feature data; The first adjustment mode sets several adjustment methods for the extraction quantity of the characteristic data, and each adjustment method has a different adjustment range for the extraction quantity of the characteristic data.

10. The method for generating a special child intervention program according to claim 9, characterized in that: The process of determining to use the second adjustment mode to adjust the extraction quantity of feature data based on the target proportion difference includes: If the target proportion difference is less than the preset difference, determining to use the second adjustment mode to adjust the extraction quantity of the feature data; The second adjustment mode sets several adjustment methods for the extraction quantity of the characteristic data, and each adjustment method has a different adjustment range for the extraction quantity of the characteristic data.

Images