An intelligent auxiliary guidance method for the mental health of children with ADHD

By capturing ADHD test videos and building a matrix with analytical indicators, generating and adjusting guidance plans, the problem of inefficient treatment in the existing technology is solved, and personalized and efficient guidance of the mental health of ADHD children is achieved.

CN118412095BActive Publication Date: 2024-11-26CENT SOUTH UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410610047.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-16
Publication Date
2024-11-26
Estimated Expiration
2044-05-16

AI Technical Summary

Technical Problem

In the existing psychological treatment of ADHD, there is a lack of personalized guidance methods, which leads to inefficient treatment. Relying on doctors’ artificial observation and fixed treatment plans, it cannot vary from person to person.

Method used

By capturing ADHD test videos, building a matrix with analysis indicators, generating an initial guidance plan, and adjusting it based on bias, association, and proportional coefficients, providing personalized auxiliary guidance plan.

Benefits of technology

It improves the pertinence and reliability of psychological health guidance for children with ADHD and improves treatment efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118412095B_ABST
    Figure CN118412095B_ABST
Patent Text Reader

Abstract

The present invention provides an intelligent auxiliary guidance method for the mental health of children with ADHD, which belongs to the field of intelligent guidance technology, including: capturing the test video of the target object based on each ADHD test scheme, respectively obtaining the ADHD analysis index of each ADHD test scheme; analyzing the corresponding test video based on the ADHD analysis index to build a test matrix, and obtaining the test feature vector to generate an initial guidance scheme; obtaining the ADHD proportion coefficient of the target object based on each ADHD analysis index based on the test matrix; adjusting the initial guidance scheme to obtain an auxiliary guidance scheme according to the test bias of each ADHD test scheme, the bias association between different ADHD test schemes and the ADHD proportion coefficient, and sending it to the guidance end to perform psychological health auxiliary guidance on the target object. Effectively ensure the pertinence and reliability of the scheme, and effectively improve the efficiency of psychological health guidance.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent guidance, and in particular to an intelligent auxiliary guidance method for the mental health of children with ADHD. Background Art

[0002] Attention deficit hyperactivity disorder, also known as ADHD, is a common psychological disorder in children. It is characterized by inattention and short attention span, hyperactivity and impulsivity that are not commensurate with age and development level, and is often accompanied by learning difficulties, conduct disorders and maladjustment.

[0003] At present, the solution to the problem of ADHD is generally achieved by combining cognitive behavioral therapy and drug therapy. However, in the process of cognitive behavioral therapy, doctors generally rely on manual observation of children to determine the results. In the subsequent treatment process, conventional fixed treatment methods are used for psychological counseling, which does not vary from person to person, resulting in low guidance efficiency.

[0004] Therefore, the present invention proposes an intelligent auxiliary guidance method for the mental health of children with ADHD. Summary of the invention

[0005] The present invention provides an intelligent auxiliary guidance method for the mental health of children with ADHD, which is used to capture the test video of each test plan and combine it with analysis indicators to ensure that the symptom information of the child is obtained from multiple aspects, provide a complete data analysis basis for subsequent analysis, and subsequently construct a matrix, generate a plan, and adjust the plan based on bias, correlation, and proportional coefficients to effectively ensure the pertinence and reliability of the plan, and effectively improve the efficiency of mental health guidance.

[0006] The present invention provides an intelligent auxiliary guidance method for the mental health of children with ADHD, comprising:

[0007] Step 1: Capture the test videos of the target subject based on each ADHD test scheme respectively, and at the same time, obtain the ADHD analysis indicators of each ADHD test scheme respectively;

[0008] Step 2: Analyze the corresponding test video based on the ADHD analysis indicators to build a test matrix, and obtain the test feature vector to generate an initial bootstrap scheme;

[0009] Step 3: Based on the test matrix, obtain the ADHD ratio coefficient of the target object based on each ADHD analysis indicator;

[0010] Step 4: According to the test bias of each ADHD test scheme, the bias correlation between different ADHD test schemes and the ADHD proportion coefficient, the initial guidance scheme is adjusted to obtain an auxiliary guidance scheme, and sent to the guidance end to provide auxiliary guidance for the target object's mental health.

[0011] Preferably, before capturing the test videos of the target subjects based on each ADHD test protocol, the following steps are included:

[0012] Obtaining the behavioral demands of the target object's surrounding people on the target object, and searching the behavioral demands based on a text search engine to obtain several key texts;

[0013] Perform cluster analysis on all key texts to obtain the cluster concentration density Jm under each cluster i1 , cluster area Sm i1 And the number of texts Nw under the corresponding cluster i1 , construct the first auxiliary function Fy1(Jm i1 ,Sm i1 ,Nw i1 ),in, M1 i1 Indicates the number of remaining key texts outside the text corresponding to the cluster contained in the cluster area that satisfies the set normal distribution probability under the i1th cluster; L1 j1 Represents the distance value from the i1th cluster to the j1th remaining key text in the corresponding cluster area; (L1 j1 ) max Indicates all L1 j1 The maximum value in; ln represents the sign of logarithmic function; ∝1 and ∝2 represent the proportional coefficients respectively; Indicated by (L1 j1 ) max The obtained circular area is constructed for the circular area;

[0014] At the same time, the modifiers based on each cluster are obtained from the behavioral appeal to determine the modifier tone intensity Xs i1 , and construct the second auxiliary function Fy2(Xs i1 ),in, M2 i1 Indicates the number of modifiers involved in the key text in the clustering result corresponding to the i1th cluster; yq j2 Indicates the tone coefficient of the corresponding j2th modifier; L2 j2 Indicates the distance value between the key text directly matched by the corresponding j2th modifier and the i1th cluster; Indicates based on M1 i1 The text weight and; Indicates that it is based on M2 i1 The text weight and;

[0015] Based on the first auxiliary function and the second auxiliary function, and in combination with the constraint determination criteria, the primary behavior and the secondary behavior of the target object are obtained;

[0016]

[0017] Where G1 represents the first auxiliary standard judgment set; G2 represents the second auxiliary standard judgment set; P i1 represents the behavior result based on the i 1th cluster;

[0018] According to the behavior types and behavior weights of the main behaviors and secondary behaviors, several ADHD test schemes are screened from the test database.

[0019] Preferably, constructing a test matrix based on the analysis indicators of ADHD by analyzing the corresponding test videos includes:

[0020] Perform action decoding on each frame of the corresponding test video to obtain a decoding set, and at the same time, obtain the decoding representation of each ADHD analysis indicator;

[0021] Extracting single behavior information corresponding to the ADHD analysis indicator based on each frame action from the decoded set according to the decoded representation;

[0022] A test matrix is ​​constructed based on all single behavior information.

[0023] Preferably, obtaining the test feature vector to generate an initial bootstrap scheme includes:

[0024] Performing vector solving on the test matrix to obtain a test feature vector;

[0025] Assigning a vector weight to a corresponding test feature vector according to a test attribute of each test video, wherein the test attribute includes a behavior type combination of the corresponding test;

[0026]

[0027] Among them, Xq represents the corresponding vector weight; x1 represents the number of types involved in the main behavior in the behavior type combination of the corresponding test video; x2 represents the number of types involved in the secondary behavior in the behavior type combination of the corresponding test video; max represents the maximum value symbol; min represents the minimum value symbol;

[0028] At the same time, according to the correlation cluster coefficient between the main behavior and the secondary behavior of the target object and the behavior weight, the solution weight of each ADHD test solution is obtained respectively;

[0029]

[0030] Among them, Fq represents the program weight corresponding to the ADHD test program; cx averepresents the average value of all correlation cluster coefficients of the main behaviors and secondary behaviors matched by the ADHD test scheme; sum(rq) represents the sum of the behavioral weights of the main behaviors and secondary behaviors matched by the ADHD test scheme; σ1 2 represents the variance of all correlation cluster coefficients of primary and secondary behaviors matched to the ADHD test protocol;

[0031] adjusting the vector weight based on the scheme weight;

[0032] The test feature vector and the adjusted weights are input into the solution generation model to generate an initial bootstrap solution.

[0033] Preferably, adjusting the vector weight based on the scheme weight includes:

[0034]

[0035] Among them, σ2 2 It represents the weight variance of the behavioral weights of the primary behaviors and secondary behaviors that match all corresponding ADHD test schemes; e represents a constant, and its value is 2.7.

[0036] Preferably, obtaining the ADHD proportion coefficient of the target object based on each ADHD analysis indicator based on the test matrix includes:

[0037] Plotting each row vector in the test matrix to obtain a first curve;

[0038] Obtaining a first fitting value of the first curve;

[0039] Determine the first number and position of the peak points above the first fitting value, and lock the leftmost peak point and the rightmost peak point to intercept the curve segment;

[0040] According to the average test value Z1 of the intercepted segment ave and the first number JN, and obtain the corresponding ADHD proportion coefficient Db;

[0041]

[0042] Among them, Z max Indicates the maximum test value among all peak points on the first curve; Z min Indicates the minimum test value among all peak points on the corresponding first curve; represents the length ratio of the intercepted segment, and Dc represents the length of the intercepted segment; Dz represents the length of the first curve; and D1 represents the total number of peak points on the first curve.

[0043] Preferably, adjusting the initial guidance scheme to obtain an auxiliary guidance scheme includes:

[0044] Obtain the test bias of each ADHD test protocol from the protocol-bias mapping table;

[0045] Establishing a bias correlation coefficient between any two ADHD test schemes according to the test bias, and at the same time, determining a scheme correlation coefficient between any two ADHD test schemes;

[0046] Determine the association description of any two ADHD test schemes according to the bias correlation coefficient, scheme correlation coefficient and all ADHD proportion coefficients involved in the any two ADHD test schemes;

[0047] The initial guidance scheme is adjusted based on all associated descriptions to obtain an auxiliary guidance scheme.

[0048] Preferably, obtaining the association description of any two ADHD test schemes comprises:

[0049] Performing an indicator comparison analysis on the ADHD analysis indicator of the first ADHD test scheme of any two ADHD test schemes and the ADHD analysis indicator of the second ADHD test scheme, and determining a set weight array and a scheme description array for the same indicator;

[0050] The set weight array and the scheme description array are analyzed according to the bias correlation coefficient, the scheme correlation coefficient and the two ADHD ratio coefficients under the same indicator, so as to obtain the first key description of the same indicator by performing description screening from the scheme description array;

[0051] Obtain the set weights and scheme descriptions of individual indicators, and combine the ADHD ratio coefficients of the corresponding indicators to obtain the second key description by screening the descriptions from the corresponding scheme descriptions;

[0052] The associated descriptions are all the first key descriptions and the second key descriptions.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] By capturing the test video of each test plan and combining it with analysis indicators, we can ensure that children's symptom information is obtained from multiple aspects, providing a complete data analysis basis for subsequent analysis. Subsequently, by constructing matrices, generating plans, and adjusting plans based on bias, correlation, and proportional coefficients, we can effectively ensure the targetedness and reliability of the plans and effectively improve the efficiency of mental health guidance.

[0055] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0056] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0058] Figure 1 It is a flow chart of an intelligent auxiliary guidance method for the mental health of children with ADHD in an embodiment of the present invention;

[0059] Figure 2 It is a structural diagram of the first curve in an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0061] The present invention provides an intelligent auxiliary guidance method for the mental health of children with ADHD, such as Figure 1 As shown, including:

[0062] Step 1: Capture the test videos of the target subject based on each ADHD test scheme respectively, and at the same time, obtain the ADHD analysis indicators of each ADHD test scheme respectively;

[0063] Step 2: Analyze the corresponding test video based on the ADHD analysis indicators to build a test matrix, and obtain the test feature vector to generate an initial bootstrap scheme;

[0064] Step 3: Based on the test matrix, obtain the ADHD ratio coefficient of the target object based on each ADHD analysis indicator;

[0065] Step 4: According to the test bias of each ADHD test scheme, the bias correlation between different ADHD test schemes and the ADHD proportion coefficient, the initial guidance scheme is adjusted to obtain an auxiliary guidance scheme, and sent to the guidance end to provide auxiliary guidance for the target object's mental health.

[0066] In this embodiment, the target object refers to a child who needs to be judged whether he or she has symptoms of ADHD.

[0067] In this embodiment, the ADHD test program refers to testing of children, such as psychological assessment scales, routine examinations, electroencephalograms, brain evoked potentials, neuroimaging examinations, etc., presented in the form of videos to capture whether children have problems such as inattention, short attention span, excessive activity, impulsivity, conduct disorders, etc. under different programs. That is, through corresponding programs, it is ensured that the behavioral feedback information of children can be accurately captured, which is convenient for subsequent reasonable analysis and effective auxiliary guidance.

[0068] In this embodiment, the test video refers to the process of collecting feedback results of children based on the test scheme during the test of children using the test scheme, and the purpose of the feedback results is to construct a test matrix.

[0069] In this embodiment, the ADHD analysis index is pre-set, and each ADHD test scheme has its corresponding ADHD analysis index.

[0070] In this embodiment, the test matrix is ​​constructed by using the video analysis results of each ADHD analysis indicator as a row vector.

[0071] In this embodiment, the initial bootstrap solution is generated based on a combination of a test feature vector and a solution generation model.

[0072] In this embodiment, the ADHD ratio coefficient refers to the coefficient obtained by analyzing the row vectors under the corresponding indicators in the corresponding test matrix.

[0073] In this embodiment, the test bias refers to the test direction of the corresponding scheme, for example, the emphasis on attention, or the measurement of the number of activities, etc.

[0074] In this embodiment, the biased correlation refers to the correlation between the emphasis test directions between schemes. For example, there is a certain correlation between attention and the number of activities. The less focused the attention, the greater the number of corresponding activities.

[0075] In this embodiment, the initial guidance scheme is adjusted to optimize and improve the scheme to ensure the reliability of guidance.

[0076] The beneficial effects of the above technical scheme are: by capturing the test video of each test scheme and combining it with analysis indicators, it is ensured that the child's symptom information is obtained from multiple aspects, providing a complete data analysis basis for subsequent analysis, and subsequently by constructing a matrix, generating schemes, and adjusting the schemes based on bias, correlation, and proportional coefficients, it is effectively guaranteed that the schemes are targeted and reliable, and the efficiency of mental health guidance is effectively improved.

[0077] The present invention provides an intelligent auxiliary guidance method for the mental health of children with ADHD, which comprises: before capturing test videos of target objects based on each ADHD test scheme respectively.

[0078] Obtaining the behavioral demands of the target object's surrounding people on the target object, and searching the behavioral demands based on a text search engine to obtain several key texts;

[0079] Perform cluster analysis on all key texts to obtain the cluster concentration density Jm under each cluster i1 , cluster area Sm i1 And the number of texts Nw under the corresponding cluster i1 , construct the first auxiliary function Fy1(Jm i1 ,Sm i1 ,Nw i1 ),in, M1 i1 Indicates the number of remaining key texts outside the text corresponding to the cluster contained in the cluster area that satisfies the set normal distribution probability under the i1th cluster; L1 j1 Represents the distance value from the i1th cluster to the j1th remaining key text in the corresponding cluster area; (L1 j1 ) max Indicates all L1 j1 The maximum value in; ln represents the sign of logarithmic function; ∝1 and ∝2 represent the proportional coefficients respectively; Indicated by (L1 j1 ) max The obtained circular area is constructed for the circular area;

[0080] At the same time, the modifiers based on each cluster are obtained from the behavioral appeal to determine the modifier tone intensity Xs i1 , and construct the second auxiliary function Fy2(Xs i1 ),in, M2 i1 Indicates the number of modifiers involved in the key text in the clustering result corresponding to the i1th cluster; yq j2 Indicates the tone coefficient of the corresponding j2th modifier; L2 j2 Indicates the distance value between the key text directly matched by the corresponding j2th modifier and the i1th cluster; Indicates based on M1 i1 The text weight and; Indicates that it is based on M2 i1 The text weight and;

[0081] Based on the first auxiliary function and the second auxiliary function, and in combination with the constraint determination criteria, the primary behavior and the secondary behavior of the target object are obtained;

[0082]

[0083] Where G1 represents the first auxiliary standard judgment set; G2 represents the second auxiliary standard judgment set; P i1 represents the behavior result based on the i 1th cluster;

[0084] According to the behavior types and behavior weights of the main behaviors and secondary behaviors, several ADHD test schemes are screened from the test database.

[0085] In this embodiment, the surrounding people refer to the children's parents and other people who have a close relationship with the children, so as to ensure the authenticity and reliability of the behavioral demands obtained, and the behavioral demands refer to the feedback of the surrounding people on the children's daily behavior and habits, which are reflected in the form of text, and are used as a basis to preliminarily determine which plans are more suitable for testing children.

[0086] In this embodiment, the text search engine is pre-constructed, mainly for searching the text related to the behavioral appeal to obtain key text, that is, keywords, and the key text refers to the corresponding symptoms of children under the appeal behavior.

[0087] In this embodiment, cluster analysis is performed to classify similar key texts to determine the classification of children's appeal behaviors, and then to construct a first auxiliary function. The normal distribution probability is set to refer to the clustered texts existing in the normal distribution area that meets the 70% probability.

[0088] In this embodiment, the clustering area is the area of ​​the corresponding region after the clustering result is determined.

[0089] In this embodiment, the distance value refers to the distance length between two texts.

[0090] In this embodiment, ∝1+∝2=1.

[0091] In this embodiment, the modifier refers to a modified description of the corresponding key text. For example, the key text is attention, and the modifier may be severely inattentive, not very focused, etc., thereby determining the intensity of the modified tone.

[0092] In this embodiment, the tone coefficient is obtained after matching the modifier word with the word-coefficient mapping table, providing a basis for calculation.

[0093] In this embodiment, after clustering analysis of key texts, a corresponding set weight will be set for each key text, so the weight based on M1 can be directly and effectively determined. i1 、M2 i1 The text weight and .

[0094] In this embodiment, the constraint determination criteria refer to G1 and G2.

[0095] In this embodiment, G1 and G2 are pre-set to provide a basic judgment standard with the first auxiliary function and the second auxiliary function, and G1 includes the first auxiliary function in different combinations, and G2 includes different second auxiliary functions.

[0096] The beneficial effect of the above technical solution is: by obtaining behavioral demands and searching for the demands, it is easy to obtain several key texts, and then construct the first auxiliary function and the second auxiliary function through cluster analysis and modifier determination, and make comprehensive standard judgments from two aspects to effectively determine the main behavior and the secondary behavior, providing an effective basis for subsequent screening of ADHD test programs, indirectly improving the accuracy of analysis of children's ADHD, and improving the efficiency of subsequent guidance.

[0097] The present invention provides an intelligent auxiliary guidance method for the mental health of children with ADHD, which analyzes corresponding test videos based on the ADHD analysis index to construct a test matrix, including:

[0098] Perform action decoding on each frame of the corresponding test video to obtain a decoding set, and at the same time, obtain the decoding representation of each ADHD analysis indicator;

[0099] Extracting single behavior information corresponding to the ADHD analysis indicator based on each frame action from the decoded set according to the decoded representation;

[0100] A test matrix is ​​constructed based on all single behavior information.

[0101] In this embodiment, the action decoding is obtained based on the decoding of the corresponding video decoder, and the decoding set includes the action information involved in each frame. The decoding representation is to match the decoding set to obtain a single behavior information for each indicator, wherein the single behavior information refers to the action situation under the corresponding indicator.

[0102] In this embodiment,

[0103] The beneficial effect of the above technical solution is: by decoding the action of the video and the decoded representation of the obtained indicators, single behavior information for the indicators can be obtained, thereby facilitating the construction of a test matrix and providing a basis for subsequent analysis.

[0104] The present invention provides an intelligent auxiliary guidance method for the mental health of children with ADHD, which obtains a test feature vector to generate an initial guidance scheme, including:

[0105] Performing vector solving on the test matrix to obtain a test feature vector;

[0106] Assigning a vector weight to a corresponding test feature vector according to a test attribute of each test video, wherein the test attribute includes a behavior type combination of the corresponding test;

[0107]

[0108] Among them, Xq represents the corresponding vector weight; x1 represents the number of types involved in the main behavior in the behavior type combination of the corresponding test video; x2 represents the number of types involved in the secondary behavior in the behavior type combination of the corresponding test video; max represents the maximum value symbol; min represents the minimum value symbol;

[0109] At the same time, according to the correlation cluster coefficient between the main behavior and the secondary behavior of the target object and the behavior weight, the solution weight of each ADHD test solution is obtained respectively;

[0110]

[0111] Among them, Fq represents the program weight corresponding to the ADHD test program; cx ave represents the average value of all correlation cluster coefficients of the main behaviors and secondary behaviors matched by the ADHD test scheme; sum(rq) represents the sum of the behavioral weights of the main behaviors and secondary behaviors matched by the ADHD test scheme; σ1 2 represents the variance of all correlation cluster coefficients of primary and secondary behaviors matched to the ADHD test protocol;

[0112] adjusting the vector weight based on the scheme weight;

[0113] The test feature vector and the adjusted weights are input into the solution generation model to generate an initial bootstrap solution.

[0114] Preferably, adjusting the vector weight based on the scheme weight includes:

[0115]

[0116] Among them, σ2 2 It represents the weight variance of the behavioral weights of the primary behaviors and secondary behaviors that match all corresponding ADHD test schemes; e represents a constant, and its value is 2.7.

[0117] In this embodiment, the vector solution of the matrix is ​​implemented based on |A-λE|=0, thereby obtaining the test eigenvector.

[0118] In this embodiment, the behavior types include: attention behavior type, action behavior type, emotion behavior type, etc.

[0119] In this embodiment, the correlation cluster coefficient = the distance between two specified behaviors / the sum of the distances between all arbitrary two behaviors.

[0120] In this embodiment, the solution generation model is based on the combination of different test feature vectors and the matched weights, and is obtained by training the neural network model with the solution set by experts under the combination as a sample. Therefore, the initial guidance solution can be directly obtained.

[0121] The beneficial effect of the above technical solution is: the test feature vector is obtained by vectorizing the matrix, and the vector is assigned in combination with the attributes, and then the vector weight is adjusted by the scheme weight to make important adjustments to the test feature vector, thereby ensuring the pertinence and reliability of the subsequent initial guidance scheme generation.

[0122] The present invention provides an intelligent auxiliary guidance method for the mental health of children with ADHD, which obtains the ADHD proportion coefficient of the target object based on each ADHD analysis index based on the test matrix, including:

[0123] Plotting each row vector in the test matrix to obtain a first curve;

[0124] Obtaining a first fitting value of the first curve;

[0125] Determine the first number and position of the peak points above the first fitting value, and lock the leftmost peak point and the rightmost peak point to intercept the curve segment;

[0126] According to the average test value Z1 of the intercepted segment ave and the first number JN, and obtain the corresponding ADHD proportion coefficient Db;

[0127]

[0128] Among them, Z max Indicates the maximum test value among all peak points on the first curve; Z min Indicates the minimum test value among all peak points on the corresponding first curve; represents the length ratio of the intercepted segment, and Dc represents the length of the intercepted segment; Dz represents the length of the first curve; and D1 represents the total number of peak points on the first curve.

[0129] In this embodiment, the horizontal axis of the first curve is the time frame, and the vertical axis is the test value under the corresponding indicator.

[0130] In this embodiment, the first fitting value can be obtained by fitting the first curve using the fitting processing function.

[0131] In this embodiment, if Figure 2As shown, the first curve is a1, the horizontal fitting line corresponding to the fitting value is a2, and the points b1, b2 and b3 above the horizontal fitting line a2 in the curve a1 are the peak points. The first number is 3, the leftmost peak point is b1, the rightmost peak point is b3, and the curve segment between b1 and b3 is the intercepted segment.

[0132] In this embodiment, the average test value refers to the average processing after the accumulation of all points in the intercepted segment.

[0133] The beneficial effect of the above technical solution is: by drawing a curve for each row of vectors and performing fitting analysis and interception analysis on the first curve, the ADHD proportion coefficient can be effectively determined, providing a basis for subsequent adjustments to the initial guidance plan and ensuring the rationality of the obtained auxiliary guidance plan.

[0134] The present invention provides an intelligent auxiliary guidance method for the mental health of children with ADHD, wherein the initial guidance scheme is adjusted to obtain an auxiliary guidance scheme, comprising:

[0135] Obtain the test bias of each ADHD test protocol from the protocol-bias mapping table;

[0136] Establishing a bias correlation coefficient between any two ADHD test schemes according to the test bias, and at the same time, determining a scheme correlation coefficient between any two ADHD test schemes;

[0137] Determine the association description of any two ADHD test schemes according to the bias correlation coefficient, scheme correlation coefficient and all ADHD proportion coefficients involved in the any two ADHD test schemes;

[0138] The initial guidance scheme is adjusted based on all associated descriptions to obtain an auxiliary guidance scheme.

[0139] In this embodiment, the scheme-bias mapping table includes different ADHD test schemes and the test biases matched with the schemes, mainly to determine the pertinence of the test of the scheme.

[0140] In this embodiment, the bias correlation coefficient = s im{any two test biases}.

[0141] In this embodiment, the scheme correlation coefficient = {any two test schemes}.

[0142] In this embodiment, the associated description refers to a description that requires adjustment to the initial bootstrap solution.

[0143] In this embodiment, the initial boot scheme includes step 1, step 2, and step 3. At this time, step 21 is added under the associated description. At this time, the obtained auxiliary boot scheme includes: step 1, step 2, step 21 and step 3.

[0144] The beneficial effect of the above technical solution is: by obtaining the test bias from the mapping table to establish the bias correlation coefficient, and combining the scheme correlation coefficient and the ADHD proportion coefficient, the correlation description is effectively determined, the initial guidance scheme is reasonably adjusted, and the efficiency of subsequent guidance is guaranteed.

[0145] The present invention provides an intelligent auxiliary guidance method for the mental health of children with ADHD, which obtains a correlation description of any two ADHD test schemes, including:

[0146] Performing an indicator comparison analysis on the ADHD analysis indicator of the first ADHD test scheme of any two ADHD test schemes and the ADHD analysis indicator of the second ADHD test scheme, and determining a set weight array and a scheme description array for the same indicator;

[0147] The set weight array and the scheme description array are analyzed according to the bias correlation coefficient, the scheme correlation coefficient and the two ADHD ratio coefficients under the same indicator, so as to obtain the first key description of the same indicator by performing description screening from the scheme description array;

[0148] Obtain the set weights and scheme descriptions of individual indicators, and combine the ADHD ratio coefficients of the corresponding indicators to obtain the second key description by screening the descriptions from the corresponding scheme descriptions;

[0149] The associated descriptions are all the first key descriptions and the second key descriptions.

[0150] In this embodiment, for example: the first ADHD test solution includes indicator 1, indicator 2, indicator 3 and indicator 4, and the second ADHD test solution includes indicator 1, indicator 2, indicator 5 and indicator 6. At this time, the same indicator refers to indicator 1 and indicator 2. Since the weights of the indicators involved in each ADHD test solution are pre-set, the arrays for indicator 1 and indicator 2 can be directly obtained, that is: the set weight array of indicator 1 = {the weight of indicator 1 based on the first ADHD test solution is based on the weight of indicator 1 based on the second ADHD test solution}.

[0151] Scheme description array = {based on the test information related to indicator 1 in the first ADHD test scheme, based on the test information related to indicator 1 in the second ADHD test scheme}.

[0152] In this embodiment, the first key description refers to partial information extracted from the test information in the scheme description array, and the bias correlation coefficient, scheme correlation coefficient, and two ADHD proportion coefficients of indicator 1 between the first ADHD test scheme and the second ADHD test scheme are comprehensively calculated to determine the extraction ratios for the two test information respectively.

[0153] The details are as follows: (bias correlation coefficient + scheme correlation coefficient + two ADHD proportion coefficients) / 4 = the initial proportion coefficient of information extraction, and then the current proportion coefficient is calculated again according to each set weight in the corresponding set weight array and the initial proportion coefficient.

[0154] When the set weight is greater than 0.3, the current proportional coefficient = initial proportional coefficient + set weight / (set weight + 0.3). If the current proportional coefficient is greater than 1, the corresponding test information is fully extracted. If the current test proportional coefficient is not greater than 1, the test information is proportionally extracted according to the corresponding proportion.

[0155] When the weight is set to be no greater than 0.3, the current proportional coefficient = the initial proportional coefficient, and the test information is proportionally extracted according to the corresponding initial proportional coefficient, and the final result is the first key description.

[0156] In this embodiment, the second key description is obtained by extracting information from the solution description based on the calculation ratio of ADHD ratio coefficient+set weight / (set weight+0.3).

[0157] The beneficial effect of the above technical solution is: by extracting the same indicators from two ADHD test schemes to determine overlapping indicators and separate indicators, and then adopting different description extraction methods to achieve the extraction of key descriptions, it facilitates the adjustment of the subsequent initial guidance plan and ensures the efficiency of guidance.

[0158] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent auxiliary guidance method for the mental health of children with ADHD, characterized in that: include: Step 1: Capture the test videos of the target subject based on each ADHD test scheme respectively, and at the same time, obtain the ADHD analysis indicators of each ADHD test scheme respectively; Step 2: Analyze the corresponding test video based on the ADHD analysis indicators to build a test matrix, and obtain the test feature vector to generate an initial bootstrap scheme; Step 3: Based on the test matrix, obtain the ADHD ratio coefficient of the target object based on each ADHD analysis indicator; Step 4: According to the test bias of each ADHD test scheme, the bias correlation between different ADHD test schemes and the ADHD ratio coefficient, the initial guidance scheme is adjusted to obtain an auxiliary guidance scheme, and sent to the guidance end to provide psychological health auxiliary guidance to the target object; Before capturing the test videos of the target subjects based on each ADHD test protocol, the following steps are included: Obtaining the behavioral demands of the target object's surrounding people on the target object, and searching the behavioral demands based on a text search engine to obtain several key texts; Perform cluster analysis on all key texts to obtain the cluster concentration density Jm under each cluster i1 , cluster area Sm i1 And the number of texts Nw under the corresponding cluster i1 , construct the first auxiliary function Fy1(Jm i1 ,Sm i1 ,Nw i1 ),in, M1 i1 Indicates the number of remaining key texts outside the text corresponding to the cluster contained in the cluster area that satisfies the set normal distribution probability under the i1th cluster; L1 j1 Represents the distance value from the i1th cluster to the j1th remaining key text in the corresponding cluster area; (L1 j1 ) max Indicates all L1 j1 The maximum value in; ln represents the sign of logarithmic function; ∝1 and ∝2 represent the proportional coefficients respectively; Indicated by (L1 j1 ) max The obtained circular area is constructed for the circular area; At the same time, the modifiers based on each cluster are obtained from the behavioral appeal to determine the modifier tone intensity Xs i1 , and construct the second auxiliary function Fy2(Xs i1 ),in, M2 i1 Indicates the number of modifiers involved in the key text in the clustering result corresponding to the i1th cluster; yq j2 Indicates the tone coefficient of the corresponding j2th modifier; L2 j2 Indicates the distance value between the key text directly matched by the corresponding j2th modifier and the i1th cluster; Indicates based on M1 i1 The text weight and; Indicates that it is based on M2 i1 The text weight and; Based on the first auxiliary function and the second auxiliary function, and in combination with the constraint determination criteria, the primary behavior and the secondary behavior of the target object are obtained; Where G1 represents the first auxiliary standard judgment set; G2 represents the second auxiliary standard judgment set; P i1 Represents the behavior result based on the i1th cluster; According to the behavior types and behavior weights of the main behaviors and secondary behaviors, several ADHD test schemes are screened from the test database.

2. The intelligent auxiliary guidance method for the mental health of children with ADHD according to claim 1, characterized in that: Based on the ADHD analysis indicators, the corresponding test videos are analyzed to build a test matrix, including: Perform action decoding on each frame of the corresponding test video to obtain a decoding set, and at the same time, obtain the decoding representation of each ADHD analysis indicator; Extracting single behavior information corresponding to the ADHD analysis indicator based on each frame action from the decoded set according to the decoded representation; A test matrix is ​​constructed based on all single behavior information.

3. The intelligent auxiliary guidance method for the mental health of children with ADHD according to claim 1, characterized in that: Get the test feature vector to generate the initial bootstrap solution, including: Performing vector solving on the test matrix to obtain a test feature vector; Assigning a vector weight to a corresponding test feature vector according to a test attribute of each test video, wherein the test attribute includes a behavior type combination of the corresponding test; Among them, Xq represents the corresponding vector weight; x1 represents the number of types involved in the main behavior in the behavior type combination of the corresponding test video; x2 represents the number of types involved in the secondary behavior in the behavior type combination of the corresponding test video; max represents the maximum value symbol; min represents the minimum value symbol; At the same time, according to the correlation cluster coefficient between the main behavior and the secondary behavior of the target object and the behavior weight, the solution weight of each ADHD test solution is obtained respectively; Among them, Fq represents the program weight corresponding to the ADHD test program; cx ave represents the average value of all correlation cluster coefficients of the main behaviors and secondary behaviors matched by the ADHD test scheme; sum(rq) represents the sum of the behavioral weights of the main behaviors and secondary behaviors matched by the ADHD test scheme; σ1 2 represents the variance of all correlation cluster coefficients of primary and secondary behaviors matched to the ADHD test protocol; adjusting the vector weight based on the scheme weight; The test feature vector and the adjusted weights are input into the solution generation model to generate an initial bootstrap solution.

4. The intelligent auxiliary guidance method for the mental health of children with ADHD according to claim 3 is characterized in that: Adjusting the vector weight based on the scheme weight includes: Among them, σ2 2 It represents the weight variance of the behavioral weights of the primary behaviors and secondary behaviors that match all corresponding ADHD test schemes; e represents a constant, and its value is 2.

7.

5. The intelligent auxiliary guidance method for the mental health of children with ADHD according to claim 1, characterized in that: Based on the test matrix, the ADHD ratio coefficient of the target object based on each ADHD analysis indicator is obtained respectively, including: Plotting each row vector in the test matrix to obtain a first curve; Obtaining a first fitting value of the first curve; Determine the first number and position of the peak points above the first fitting value, and lock the leftmost peak point and the rightmost peak point to intercept the curve segment; According to the average test value Z1 of the intercepted segment ave and the first number JN, and obtain the corresponding ADHD proportion coefficient Db; Among them, Z max Indicates the maximum test value among all peak points on the first curve; Z min Indicates the minimum test value among all peak points on the corresponding first curve; represents the length ratio of the intercepted segment, and Dc represents the length of the intercepted segment; Dz represents the length of the first curve; and D1 represents the total number of peak points on the first curve.

6. The intelligent auxiliary guidance method for the mental health of children with ADHD according to claim 1, characterized in that: The initial guidance scheme is adjusted to obtain an auxiliary guidance scheme, including: Obtain the test bias of each ADHD test protocol from the protocol-bias mapping table; Establishing a bias correlation coefficient between any two ADHD test schemes according to the test bias, and at the same time, determining a scheme correlation coefficient between any two ADHD test schemes; Determine the association description of any two ADHD test schemes according to the bias correlation coefficient, scheme correlation coefficient and all ADHD proportion coefficients involved in the any two ADHD test schemes; The initial guidance scheme is adjusted based on all associated descriptions to obtain an auxiliary guidance scheme.

7. The intelligent auxiliary guidance method for the mental health of children with ADHD according to claim 6, characterized in that: Get the associated description of any two ADHD test schemes, including: Performing an indicator comparison analysis on the ADHD analysis indicator of the first ADHD test scheme of any two ADHD test schemes and the ADHD analysis indicator of the second ADHD test scheme, and determining a set weight array and a scheme description array for the same indicator; The set weight array and the scheme description array are analyzed according to the bias correlation coefficient, the scheme correlation coefficient and the two ADHD ratio coefficients under the same indicator, so as to obtain the first key description of the same indicator by performing description screening from the scheme description array; Obtain the set weights and scheme descriptions of individual indicators, and combine the ADHD ratio coefficients of the corresponding indicators to obtain the second key description by screening the descriptions from the corresponding scheme descriptions; The associated descriptions are all the first key descriptions and the second key descriptions.