Test data enhancement processing method for children's motor cognitive logic test

Abstract

The present application provides a test data enhancement processing method for a children's motor cognitive logic test, which relates to the field of data enhancement technology, including: obtaining test data collected in a children's motor cognitive logic test; supplementing multiple motion data sequences with motion data respectively, obtaining multiple supplementary motion data sequences and supplementary motion moment sequences; dividing the supplementary motion data of the same supplementary motion moment in multiple supplementary motion data sequences, and performing consistency analysis respectively; screening to obtain multiple enhanced motion data sets, and obtaining multiple enhanced motion data sequences as test data enhancement processing results. The present application can solve the technical problem in the prior art that the comprehensive evaluation of motor cognitive ability is limited due to the lack or inaccuracy of traditional collected data, realize the technical goal of the supplementary mechanism of enhanced data, and achieve the technical effect of comprehensively evaluating children's motor cognitive ability and improving the reliability and consistency of test results.

Description

Technical Field

[0001] The present application relates to the technical field of data enhancement, and in particular to a test data enhancement processing method for children's motor cognitive logic test. Background Art

[0002] Children's motor cognitive tests, as an important means of evaluating children's motor ability and cognitive level, have been widely used in fields such as education, psychology and sports science.

[0003] At present, the data collection method of children's motor cognition test mainly relies on traditional video image acquisition technology. Although this method can provide intuitive motion data, it has certain deficiencies in data integrity and diversity. Motion image data is usually affected by external conditions such as shooting angle, resulting in missing or inaccurate data. Traditional motion data collection methods mainly focus on static or simple dynamic states, and the analysis of continuity and transitional data during the movement process is relatively weak, which makes it impossible to fully display some key details in the motor cognitive logic test. In addition, existing motion data processing technologies often rely on existing data sets and lack sufficient supplementary mechanisms. When children's motor behaviors are more complex and change rapidly, resulting in the missing of certain moments in the motion data or the sparseness of motion image data, the existing technology acquisition methods often find it difficult to obtain enough continuous image data and cannot effectively fill these gaps, resulting in the consistency and accuracy of the test results being affected, limiting the comprehensive evaluation of motor cognitive ability.

[0004] In summary, there are technical problems in the prior art that the traditional video image acquisition method is affected by external conditions such as the shooting angle, resulting in missing or inaccurate data, further affecting the integrity and diversity of motion data, and thus limiting the comprehensive assessment of motion cognitive ability. Summary of the invention

[0005] The purpose of this application is to provide a test data enhancement processing method for children's motor cognitive logic test, so as to solve the technical problem in the prior art that the traditional video image acquisition method is affected by external conditions such as the shooting angle, resulting in missing or inaccurate data, further affecting the integrity and diversity of the motion data, and thus limiting the comprehensive assessment of motor cognitive ability.

[0006] In view of the above problems, the present application provides a test data enhancement processing method for a children's movement cognitive logic test, comprising: obtaining test data collected in a children's movement cognitive logic test, wherein the test data includes multiple motion data sequences collected at multiple angles, and the multiple motion data sequences all correspond to motion moment sequences; performing motion data supplementation on the multiple motion data sequences respectively to obtain multiple supplementary motion data sequences and supplementary motion moment sequences, wherein the motion data of the two preceding and succeeding motion moments are used to supplement the motion data of the intermediate supplementary motion moment; according to the multiple supplementary motion moments in the supplementary motion moment sequence, the supplementary motion data of the same supplementary motion moment in the multiple supplementary motion data sequences are divided to obtain multiple supplementary moment motion data sets, and consistency analysis is performed respectively to obtain multiple supplementary consistency parameters; according to the multiple supplementary consistency parameters, multiple enhanced motion data sets are screened to obtain, and the data are added to the multiple motion data sequences to obtain multiple enhanced motion data sequences as test data enhancement processing results.

[0007] The technical solution provided in the present application has at least the following technical effects or advantages: by acquiring test data collected in a children's motor cognitive logic test, wherein the test data includes multiple motion data sequences collected at multiple angles, and the multiple motion data sequences all correspond to motion moment sequences; the multiple motion data sequences are respectively supplemented with motion data to obtain multiple supplementary motion data sequences and supplementary motion moment sequences, wherein the motion data of the two preceding and succeeding motion moments are used to supplement the motion data of the intermediate supplementary motion moment; according to the multiple supplementary motion moments in the supplementary motion moment sequence, the supplementary motion data of the same supplementary motion moment in the multiple supplementary motion data sequences are divided to obtain multiple supplementary moment motion data sets, and consistency analysis is performed to obtain multiple supplementary consistency parameters; according to the multiple supplementary consistency parameters, multiple enhanced motion data sets are screened to obtain, and added to the multiple motion data sequences to obtain multiple enhanced motion data sequences as test data enhancement processing results, that is, by achieving the technical goal of improving the accuracy and continuity of motion data collection, enhancing the data supplementation mechanism, and overcoming the data sparsity problem, a more comprehensive and accurate assessment of children's motor cognitive ability and the technical effect of improving the reliability and consistency of test results are achieved.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0010] Figure 1 This is a flow chart of a test data enhancement processing method for a children's motor cognitive logic test in this application;

[0011] Figure 2 This is a flow chart of obtaining test data collected in a children's motor cognitive logic test in the test data enhancement processing method for the children's motor cognitive logic test in this application. DETAILED DESCRIPTION

[0012] This application solves the technical problem in the prior art that the traditional video image acquisition method is affected by external conditions such as shooting angle, resulting in missing or inaccurate data, further affecting the integrity and diversity of motion data, and thus limiting the comprehensive evaluation of motor cognitive ability by providing a test data enhancement processing method for children's motor cognitive logic test. It achieves the technical goals of improving the accuracy and continuity of motion data acquisition, enhancing the data supplement mechanism, and overcoming the data sparsity problem, achieving a more comprehensive and accurate evaluation of children's motor cognitive ability and improving the reliability and consistency of test results.

[0013] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0014] Please see attached Figure 1, the present application provides a test data enhancement processing method for children's motor cognitive logic test, which specifically includes the following steps:

[0015] Step 1: Acquire test data collected in a children's movement cognitive logic test, wherein the test data includes multiple movement data sequences collected at multiple angles, and the multiple movement data sequences all correspond to movement moment sequences.

[0016] Specifically, in the children's movement cognitive logic test, multiple movement data sequences of children in the process of movement in continuous time are obtained by recording from different angles. Each movement data sequence contains multiple movement data collected from one angle on the movement moment sequence, and multiple movement data sequences at multiple angles correspond to the movement moment sequence. Among them, one movement moment corresponds to multiple movement data from multiple angles. Further, the movement moment sequence refers to the order of continuous collection time. Multiple angles represent the angles collected from the child, such as the front, side and back. Multiple movement data sequences ensure that the movement performance at each moment is recorded comprehensively and accurately.

[0017] Step 2: Supplement the motion data of the multiple motion data sequences respectively to obtain multiple supplemented motion data sequences and supplemented motion moment sequences, wherein the motion data of the two preceding and succeeding motion moments are used to supplement the motion data of the intermediate supplemented motion moment.

[0018] Specifically, the motion data of the two previous and next motion moments are extracted from each motion data sequence, and then the known motion data is used to infer and fill in the data of the intermediate moment, that is, the interpolation of the motion image is generated, so that the enhanced motion data sequence has a higher frame number and the motion cognitive ability is more accurate. Among them, the motion state of the intermediate moment is generated according to the data of the two previous and next motion moments. For example, in a motion data sequence, the first moment is when the child stands, and the second moment is when the child starts running. Between the two moments, the motion data of the child from standing to running is inferred by generating an adversarial network. According to the order of the motion moments, the multiple supplementary motion data corresponding to each angle are combined to obtain the supplementary motion data sequence corresponding to each angle, and then multiple supplementary motion data sequences corresponding to multiple angles are obtained. Among them, the motion moment corresponding to each supplementary motion data sequence is used as a supplementary motion moment sequence. The supplementary motion data sequence makes the original motion data more complete and coherent, which helps to better reflect every detail and transition in the motion process.

[0019] Step three: according to the multiple supplementary motion moments in the supplementary motion moment sequence, the supplementary motion data of the same supplementary motion moment in the multiple supplementary motion data sequences are divided to obtain multiple supplementary moment motion data sets, and consistency analysis is performed on each of them to obtain multiple supplementary consistency parameters.

[0020] Specifically, according to the multiple supplementary movement moments in the supplementary movement moment sequence, the data of the same supplementary movement moment in the supplementary movement data sequence is divided to form multiple supplementary moment movement data sets. Each supplementary moment represents a specific transition moment in the movement data, and the gap in the movement data sequence is filled by supplementary generation. For example, the supplementary movement moment sequence contains the transition moment from standing to running, and the data of the supplementary movement moment sequence are separated for analysis. Among them, the data of the same supplementary movement moment comes from multiple movement data from different angles. Next, a consistency analysis is performed on each supplementary moment movement data set to determine the consistency of the children's movement movements and positions in the supplementary movement data. Finally, based on the results of the consistency analysis, multiple supplementary consistency parameters are obtained to indicate the degree of compliance of each supplementary moment data.

[0021] Step 4: According to the multiple supplementary consistency parameters, multiple enhanced motion data sets are screened and obtained, and added to the multiple motion data sequences to obtain multiple enhanced motion data sequences as test data enhancement processing results.

[0022] Specifically, based on multiple supplementary consistency parameters, multiple enhanced motion data sets that meet the consistency standards are screened out, and the supplementary consistency parameters that meet the consistency requirements are determined to ensure that only high-quality supplementary data that conforms to the laws of motion are included in the enhanced data set. Next, the screened enhanced motion data sets are added to the original multiple motion data sequences. By combining the supplementary data with the original motion data sequence, the motion data is further enriched, making the entire data sequence more complete and coherent. Finally, the enhanced motion data sequence forms multiple enhanced motion data sequences, which, as the result of the test data enhancement processing, provide higher quality data support for subsequent test analysis.

[0023] The test data enhancement processing method for children's motor cognitive logic test can achieve the technical goals of improving the accuracy and continuity of motor data collection, enhancing the data supplement mechanism, and overcoming the data sparsity problem, thereby achieving a more comprehensive and accurate assessment of children's motor cognitive ability and improving the reliability and consistency of test results.

[0024] Further, if Figure 2 As shown, the present application also includes: in a children's movement cognitive logic test, the children's movement data are continuously collected at multiple angles according to a continuous movement moment sequence to obtain multiple movement data sets; the multiple movement data sets are arranged according to the movement moment sequence to obtain multiple movement data sequences.

[0025] Specifically, in the children's movement cognitive logic test, the children's movement data is collected from multiple angles in a continuous time according to a continuous movement moment sequence. The movement moment sequence refers to the time sequence of recording movement. Multiple angles are different perspectives, such as capturing children's movements from the front, side or back. By observing at multiple time points, various data of children during the movement process, such as moving images, can be continuously collected. The movement data collected in the continuous movement moment sequence are combined to form multiple movement data sets. Among them, one movement moment corresponds to multiple movement data from multiple angles.

[0026] Next, according to the motion moment sequence, the corresponding multiple motion data sets are arranged to form multiple motion data sequences. Each motion moment sequence includes the motion data collected in the motion moment sequence at the same angle.

[0027] By collecting data sequences from multiple angles, a complete motion image is obtained, providing more dimensional support for subsequent cognitive analysis.

[0028] Furthermore, the present application also includes: performing motion data supplementation on a first motion data sequence at a first angle within the multiple motion data sequences to obtain a first supplemented motion data sequence, wherein the motion data of two preceding and succeeding motion moments are used to supplement the motion data of an intermediate supplementary motion moment to obtain a supplemented motion moment sequence, and the supplemented motion moment sequence corresponds to the first supplemented motion data sequence; and continuing to perform motion data supplementation on the other multiple motion data sequences respectively to obtain multiple supplemented motion data sequences.

[0029] Specifically, the first angle is an angle randomly extracted from multiple angles. The motion data sequence at the first angle is used as the first motion data sequence. The first motion data sequence at the first angle in the multiple motion data sequences is supplemented with motion data to obtain motion data of each motion moment between adjacent motion moments, and all supplemented motion data are combined in the time sequence of the motion moments to obtain a first supplemented motion data sequence.

[0030] Next, the motion data of multiple motion data sequences corresponding to other angles are supplemented respectively to obtain the motion data of each motion moment between adjacent motion moments, and to obtain multiple supplemented motion data sequences corresponding to multiple angles.

[0031] By supplementing multiple motion data sequences, a more complete motion data sequence is gradually generated. By analyzing the motion data of the previous and next motion moments, the generative adversarial network can predict and supplement the data of the intermediate moments, ensuring the coherence and authenticity of the supplemented data, and providing a richer reference for subsequent motion analysis and cognitive research.

[0032] Furthermore, the present application also includes: extracting the first motion data and the second motion data at the first motion moment and the second motion moment in the first motion data sequence; based on the generative adversarial network, according to the first motion data and the second motion data, performing motion data supplementation generation for the first supplementary motion moment between the first motion moment and the second motion moment, to obtain the first supplementary motion data, wherein the first supplementary motion moment has the same time interval as the first motion moment and the second motion moment; continuing to extract the second motion data and the third motion data at the second motion moment and the third motion moment in the first motion data sequence, to supplement and generate the second supplementary motion data for the second supplementary motion moment; continuing to supplement and generate the first supplementary motion data sequence according to the first motion data sequence, and arranging multiple supplementary motion moments to obtain a supplementary motion moment sequence.

[0033] Specifically, the motion data at the first motion moment and the second motion moment are randomly extracted from the first motion data sequence. The first motion moment and the second motion moment respectively represent two different time points recorded, and the first motion data and the second motion data are the motion states of the child recorded at these two moments. For example, during the test, the first motion moment may be the moment when the child starts to jump, and the second motion moment is the highest point of the child's jump.

[0034] Next, according to the generative adversarial network (GAN) technology, the first motion data and the second motion data are used to perform supplementary generation between the first motion moment and the second motion moment, that is, based on the existing first motion data and the second motion data, the generative adversarial network will infer the motion state between the first motion moment and the second motion moment, thereby filling the gap in the corresponding time period and generating data for the first supplementary motion moment. Among them, the first supplementary motion moment has the same time interval as the first motion moment and the second motion moment. For example, if the time interval between the first motion moment and the second motion moment is four seconds, then the generative adversarial network will generate supplementary motion data two seconds after the first motion moment, which is called the first supplementary motion data.

[0035] Continue to randomly extract the second motion data and the third motion data at the second motion moment and the third motion moment from the first motion data sequence, use the generative adversarial network to supplement the motion data of the second supplementary motion moment between the second motion data and the third motion data, fill the gap between the second motion moment and the third motion moment, and serve as the second supplementary motion data.

[0036] Finally, all the supplementary motion data will be combined together according to the chronological order to form a complete supplementary motion data sequence. According to the supplementary motion data sequence, a corresponding supplementary motion moment sequence is formed to ensure the motion data in all time periods, thereby providing more complete data support for subsequent analysis.

[0037] By extracting data at specific moments from the motion data sequence and using generative adversarial network technology to supplement the data at intermediate moments, the entire motion data sequence is gradually generated and improved, providing richer information for further analysis.

[0038] Furthermore, the present application also includes: according to the motion cognition logic test data in the historical time, collecting the pre-sample motion data set and the post-sample motion data set under the first angle, and according to each group of pre-sample motion data and each group of post-sample motion data, processing to obtain the sample supplementary motion data, and obtaining the sample supplementary motion data set; using a generative adversarial network to construct a motion data generation path, wherein the motion data generation path includes a generator and a discriminator; using the pre-sample motion data set and the post-sample motion data set as generated training data, using the sample supplementary motion data set as discriminant supervision data, and training the motion data generation path until convergence; using the first motion data and the second motion data as the pre-motion data and the post-motion data respectively, inputting the motion data generation path to generate the first supplementary motion data.

[0039] Specifically, the first angle is an angle randomly extracted from multiple angles. According to the movement cognitive logic test data of the children's movement cognitive logic test in the historical time, the pre-sample movement data set and the post-sample movement data set under the first angle are collected. The pre-sample movement data and the post-sample movement data refer to the sample movement data collected at two adjacent movement moments. Combine the pre-sample movement data and the post-sample movement data collected at multiple adjacent movement moments to obtain the pre-sample movement data set and the post-sample movement data set. According to each group of pre-sample movement data and post-sample movement data, the corresponding adjacent sample movement moments are obtained, and the intermediate movement moments between the adjacent sample movement moments are extracted as the sample intermediate supplementary movement moments. The movement data corresponding to the sample intermediate supplementary movement moment is extracted to generate the sample supplementary movement data, so that the multiple groups of sample supplementary movement data generated according to the multiple groups of pre-sample movement data and each group of post-sample movement data are combined to obtain the sample supplementary movement data set.

[0040] Next, a generative adversarial network is used to construct a generation path for motion data. The generative adversarial network consists of two generators and a discriminator. The generator generates new motion data based on the input data, while the discriminator determines whether the generated data is real and whether it conforms to the laws of actual motion. The generator and the discriminator compete with each other and continuously optimize, thereby gradually improving the quality of the generated data. Through the confrontation process between the generator and the discriminator, the motion data generation path can continuously improve the way motion data is generated, so that the final generated motion data is closer to the real data.

[0041] Then, the pre-sample motion data set and the post-sample motion data set are combined as the training data of the generator, and the sample supplementary motion data set is combined as the supervision data of the discriminator to train the motion data generation path. During the training process, the generator will generate new motion data based on the input pre-sample motion data set and post-sample motion data set, while the discriminator determines whether the generated data is true and gives feedback until the data generated by the generator can pass the verification of the discriminator. After multiple iterations and optimizations, the generation path will eventually converge, and the generated motion data generation path will tend to be accurate and true.

[0042] Finally, the first motion data and the second motion data are respectively used as the front motion data and the back motion data, and are input into the trained motion data generation path to generate the corresponding first supplementary motion data. For example, the first motion data represents the child's starting state, and the second motion data represents the child's running state. By generating the path, transition motion data between starting and running can be generated, so that the entire motion process becomes more coherent and complete.

[0043] By collecting motion data before and after the sample from historical data, the generative adversarial network is used to train the data generation path, and finally the supplementary generation of motion data is achieved. Through the interaction between the generator and the discriminator, the generated data is continuously optimized to ensure that the supplementary motion data can truly and reasonably reflect the motion process, which not only improves the integrity of the motion data, but also makes the motion data sequence more coherent and accurate by generating data at intermediate moments.

[0044] Furthermore, the present application also includes: obtaining multiple supplementary motion moments in the supplementary motion moment sequence; dividing the supplementary motion data of the same supplementary motion moment in the multiple supplementary motion data sequences according to the multiple supplementary motion moments to obtain multiple supplementary moment motion data sets; training a consistency recognition path for analyzing the consistency of motion data based on motion cognition logic test data within historical time; inputting the multiple supplementary moment motion data in each supplementary moment motion data set into the consistency recognition path, performing consistency analysis, and outputting multiple supplementary consistency parameters.

[0045] Specifically, multiple supplementary motion moments in multiple supplementary motion moment sequences corresponding to multiple angles are obtained. The supplementary motion moments are intermediate moments generated by supplementation, filling the gaps in the motion data sequence, and representing transition time points in the motion process.

[0046] Next, according to multiple supplementary motion moments, the supplementary motion data of the same supplementary motion moment in multiple supplementary motion data sequences are divided to obtain multiple supplementary motion data of multiple angles corresponding to each supplementary motion moment as each supplementary moment motion data set, thereby obtaining multiple supplementary moment motion data sets corresponding to multiple supplementary motion moments.

[0047] Next, based on the movement cognition logic test data in historical time, the consistency recognition path for analyzing the consistency of movement data is trained to identify whether multiple movement data at multiple angles at the same supplementary movement moment in multiple movement data sequences are consistent. By learning a large amount of historical data, the consistency recognition path can determine whether the children's movement actions and positions in the supplementary movement data are consistent.

[0048] Finally, multiple supplementary moment motion data in each supplementary moment motion data set are input into the consistency identification path to determine whether the child's motion actions and positions in the supplementary motion data are consistent, and a coefficient representing the degree of consistency is obtained as a supplementary consistency parameter. The supplementary consistency parameter represents the degree of consistency of multiple supplementary motion data at the same supplementary motion moment.

[0049] By collecting and marking the consistency of sample motion data and using the consistency recognition path training model, it can automatically judge and identify the consistency of motion data, help analyze whether the supplementary data from multiple angles at the same motion moment are consistent, thereby providing a more accurate and reliable basis for motion data analysis.

[0050] Furthermore, the present application also includes: collecting multiple sample motion data sets based on motion cognition logic test data within historical time, and performing consistency identification on multiple sample motion data in each sample motion data set to obtain a sample consistency parameter set; using the multiple sample motion data sets and the sample consistency parameter set to train a consistency recognition path; respectively inputting the multiple supplementary moment motion data sets into the trained consistency recognition path, and identifying and outputting multiple supplementary consistency parameters.

[0051] Specifically, according to the motion cognition logic test data in the historical time, multiple sample motion data sets are collected. Each sample motion data set is a plurality of supplementary motion data from multiple angles at the same motion moment in history. Next, the consistency of the multiple sample motion data in each sample motion data set is marked, that is, the consistency of the child's motion action and position is judged. If they are consistent, consistency marking is performed to obtain a sample consistency parameter set.

[0052] Then, multiple sample motion data sets and sample consistency parameter sets are used to train the consistency recognition path, that is, by learning the sample data and its consistency identifier, a consistency recognition path is established, which enables it to automatically judge the rationality and consistency of the motion data and discover potential inconsistencies. After sufficient training, the consistency recognition path can effectively perform consistency analysis on new motion data.

[0053] Finally, multiple supplementary moment motion data sets are input into the trained consistency recognition path, and multiple supplementary consistency parameters are obtained by recognition output, and the consistency of the children's motion actions and positions in the supplementary motion data is judged, and the supplementary consistency parameters of each motion moment are output. For example, the percentage coefficient of the supplementary consistency parameter, the higher the consistency degree, the higher the value of the supplementary consistency parameter, and vice versa.

[0054] Furthermore, the present application also includes: obtaining a consistency parameter threshold; screening supplementary moment motion data sets whose supplementary consistency parameters are greater than or equal to the consistency parameter threshold as multiple enhanced motion data sets; and inserting the multiple enhanced motion data sets into the multiple motion data sequences according to the supplementary motion moments corresponding to the multiple enhanced motion data sets to obtain multiple enhanced motion data sequences as test data enhancement processing results.

[0055] Specifically, a consistency parameter threshold is obtained to determine whether the supplemented motion data meets the consistency requirement. The consistency parameter threshold is obtained by analyzing historical motion data to ensure that only motion data that meets the consistency parameter threshold is retained during data analysis.

[0056] Next, the supplementary moment motion data sets whose supplementary consistency parameters are greater than or equal to the consistency parameter threshold are screened out and used as multiple enhanced motion data sets, that is, data sets whose only supplementary consistency parameters are higher than the set threshold are obtained.

[0057] Finally, according to the supplementary motion moments corresponding to multiple enhanced motion data sets, the enhanced motion data are inserted into the original multiple motion data sequences to obtain multiple enhanced motion data sequences as the test data enhancement processing results. Then, by inserting enhanced data that meets the consistency standards, the original data sequence is enriched to make the final motion data sequence more complete and coherent.

[0058] By obtaining the consistency parameter threshold, the data that meets the consistency standard is screened out, and finally the enhanced motion data is inserted into the original motion data sequence to form a more complete and high-quality motion data set, which helps to improve the integrity and accuracy of the data, thereby providing a more reliable data foundation for further motion cognitive analysis and testing.

[0059] In summary, the test data enhancement processing method for children's motor cognitive logic test provided by the present application has the following technical effects: by obtaining test data collected in the children's motor cognitive logic test, wherein the test data includes multiple motion data sequences collected at multiple angles, and the multiple motion data sequences all correspond to motion moment sequences; the multiple motion data sequences are respectively supplemented with motion data to obtain multiple supplementary motion data sequences and supplementary motion moment sequences, wherein the motion data of the two previous and next motion moments are used to supplement the motion data of the intermediate supplementary motion moment; according to the multiple supplementary motion moments in the supplementary motion moment sequence, the supplementary motion data of the same supplementary motion moment in the multiple supplementary motion data sequences are divided to obtain multiple supplementary moment motion data sets, and consistency analysis is performed respectively to obtain multiple supplementary consistency parameters; according to the multiple supplementary consistency parameters, multiple enhanced motion data sets are screened and obtained, and added to the multiple motion data sequences to obtain multiple enhanced motion data sequences as test data enhancement processing results, that is, by achieving the technical goal of improving the accuracy and continuity of motion data collection, enhancing the data supplementation mechanism, and overcoming the data sparsity problem, a more comprehensive and accurate assessment of children's motor cognitive ability and improving the reliability and consistency of test results are achieved.

[0060] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0061] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A test data enhancement processing method for children's motor cognitive logic test, characterized in that: Methods include: Acquire test data collected in a children's movement cognitive logic test, wherein the test data includes multiple movement data sequences collected at multiple angles, and the multiple movement data sequences all correspond to movement moment sequences; Supplementing the motion data of the plurality of motion data sequences respectively to obtain a plurality of supplemented motion data sequences and supplemented motion moment sequences, wherein the motion data of the two preceding and following motion moments are used to supplement the motion data of the intermediate supplemented motion moment; According to the multiple supplementary movement moments in the supplementary movement moment sequence, the supplementary movement data of the same supplementary movement moment in the multiple supplementary movement data sequences are divided to obtain multiple supplementary moment movement data sets, and consistency analysis is performed on each of them to obtain multiple supplementary consistency parameters; According to the multiple supplementary consistency parameters, multiple enhanced motion data sets are screened and obtained, and added to the multiple motion data sequences to obtain multiple enhanced motion data sequences as test data enhancement processing results; Supplementing the motion data of the plurality of motion data sequences respectively to obtain a plurality of supplemented motion data sequences and supplemented motion time sequences, including: Supplementing the motion data of a first motion data sequence at a first angle among the multiple motion data sequences to obtain a first supplemented motion data sequence, wherein the motion data of two preceding and succeeding motion moments are used to supplement the motion data of an intermediate supplemented motion moment to obtain a supplemented motion moment sequence, and the supplemented motion moment sequence corresponds to the first supplemented motion data sequence; Continue to supplement the motion data of other multiple motion data sequences respectively to obtain multiple supplemented motion data sequences; Supplementing motion data of a first motion data sequence at a first angle among the multiple motion data sequences to obtain a first supplemented motion data sequence includes: Extracting first motion data and second motion data at a first motion moment and a second motion moment in the first motion data sequence; Based on the generative adversarial network, motion data of a first supplementary motion moment between the first motion moment and the second motion moment are supplemented and generated according to the first motion data and the second motion data to obtain first supplementary motion data, wherein the first supplementary motion moment has the same time interval as the first motion moment and the second motion moment; Continue to extract the second motion data and the third motion data at the second motion moment and the third motion moment in the first motion data sequence, and supplementarily generate second supplementary motion data at the second supplementary motion moment; Continue to supplement and generate a first supplementary motion data sequence according to the first motion data sequence, and arrange a plurality of supplementary motion moments to obtain a supplementary motion moment sequence; Based on the generative adversarial network, according to the first motion data and the second motion data, motion data of a first supplementary motion moment between the first motion moment and the second motion moment is supplemented and generated to obtain the first supplementary motion data, including: According to the motion cognition logic test data in the historical time, a pre-sample motion data set and a post-sample motion data set under the first angle are collected, and according to each set of pre-sample motion data and each set of post-sample motion data, sample supplementary motion data are processed to obtain a sample supplementary motion data set; Using a generative adversarial network to construct a motion data generation path, wherein the motion data generation path includes a generator and a discriminator; Using the pre-sample motion data set and the post-sample motion data set as generated training data, using the sample supplementary motion data set as discriminant supervision data, and training the motion data generation path until convergence; The first motion data and the second motion data are respectively used as the front motion data and the rear motion data, and are input into the motion data generation path to generate the first supplementary motion data.

2. The test data enhancement processing method for children's motor cognitive logic test according to claim 1 is characterized in that: Get the test data collected from the children's motor cognitive logic test, including: In the children's movement cognitive logic test, the children's movement data are continuously collected from multiple angles according to the continuous movement moment sequence to obtain multiple movement data sets; The multiple motion data sets are arranged according to the motion moment sequence to obtain multiple motion data sequences.

3. The test data enhancement processing method for children's motor cognitive logic test according to claim 1 is characterized in that: According to the multiple supplementary motion moments in the supplementary motion moment sequence, the supplementary motion data of the same supplementary motion moment in the multiple supplementary motion data sequences are divided to obtain multiple supplementary moment motion data sets, and consistency analysis is performed on each of them to obtain multiple supplementary consistency parameters, including: Acquire a plurality of supplementary movement moments in the supplementary movement moment sequence; According to the multiple supplementary motion moments, the supplementary motion data of the same supplementary motion moment in the multiple supplementary motion data sequences are divided to obtain multiple supplementary moment motion data sets; Based on the movement cognition logic test data in historical time, the consistency recognition path for analyzing the consistency of movement data is trained; The multiple supplementary moment motion data in each supplementary moment motion data set are input into the consistency identification path, and consistency analysis is performed to output a plurality of supplementary consistency parameters.

4. The test data enhancement processing method for children's motor cognitive logic test according to claim 3 is characterized in that: Based on the motion cognition logic test data in historical time, the consistency recognition path used to analyze the consistency of motion data is trained, including: According to the motion cognition logic test data in the historical time, multiple sample motion data sets are collected, and the consistency of multiple sample motion data in each sample motion data set is marked to obtain a sample consistency parameter set; Using the plurality of sample motion data sets and sample consistency parameter sets, training a consistency recognition path; The multiple supplementary moment motion data sets are respectively input into the trained consistency recognition path, and the recognition output is used to obtain multiple supplementary consistency parameters.

5. The test data enhancement processing method for children's motor cognitive logic test according to claim 1 is characterized in that: According to the multiple supplementary consistency parameters, multiple enhanced motion data sets are screened and obtained, and added to the multiple motion data sequences to obtain multiple enhanced motion data sequences as test data enhancement processing results, including: Get the consistency parameter threshold; Screening the supplementary moment motion data sets whose supplementary consistency parameters are greater than or equal to the consistency parameter threshold as a plurality of enhanced motion data sets; According to the supplementary motion moments corresponding to the multiple enhanced motion data sets, the multiple enhanced motion data sets are inserted into the multiple motion data sequences to obtain multiple enhanced motion data sequences as test data enhancement processing results.

Images