Special children's sports intervention information interaction method and system based on cloud platform

Abstract

The present application relates to the field of information interaction processing technology, and discloses a method and system for information interaction in sports intervention for special children based on a cloud platform. The method includes: this solution collects facial expressions, sounds, physiology and behavior data of special children through multi-source sensing equipment, performs feature extraction and time synchronization processing; performs hierarchical analysis and fusion of the data to form an interaction intensity data set; based on this, adaptively screens and dynamically configures the training content to achieve personalized training; achieves real-time interactive matching through multimodal analysis; uses distributed encrypted storage to ensure data security; and finally performs multi-dimensional correlation analysis to achieve intervention effect evaluation. The present application realizes the real-time collection, secure storage and personalized analysis of multi-dimensional data, thereby supporting the precise adjustment and effect evaluation of training programs.

Description

Technical Field

[0001] The present application relates to the field of information interaction processing, and in particular to a cloud platform-based special children's sports intervention information interaction method and system. Background Art

[0002] With the growing demand for rehabilitation for children with special needs, exercise intervention has become widely used as an important rehabilitation tool. Existing exercise intervention methods primarily rely on manual observation and assessment, using wearable devices, smart sensors, and other technologies to collect performance data on children with special needs during exercise. Furthermore, the development of cloud computing technology has provided technical support for remote rehabilitation guidance and data analysis, making data collection, storage, and analysis during exercise intervention more convenient and efficient. Significant progress has been made in multi-source data fusion, real-time monitoring, and the development of personalized training programs.

[0003] However, existing technologies still have obvious shortcomings in the interaction of sports intervention information. First, traditional data collection methods often only focus on single-dimensional data and cannot effectively integrate multi-dimensional information such as sports performance, emotional state, and interactive feedback. Second, the data analysis process lacks in-depth consideration of the individual characteristics of special children, making it difficult to achieve precise adjustment of training programs. Third, data security and privacy protection mechanisms are relatively weak and cannot meet the special requirements of rehabilitation data management for special children. In addition, most existing systems use fixed evaluation criteria, which are difficult to adapt to the developmental characteristics and rehabilitation needs of different special children. Summary of the Invention

[0004] This application provides a cloud platform-based method and system for interactive information on sports intervention for special children, which enables real-time collection, secure storage, and personalized analysis of multi-dimensional data, thereby supporting precise adjustment of training programs and effect evaluation.

[0005] In the first aspect, the present application provides a method for interactive information on sports intervention for special children based on a cloud platform, and the method comprises: performing time-series acquisition and processing on the expression data stream, sound data, physiological data and behavioral data of the special children's sports process through multi-source sensing equipment, performing feature extraction and time synchronization processing on the multi-source data to obtain a multi-dimensional training data stream; performing hierarchical analysis and processing on the interaction parameters according to the multi-dimensional training data stream, fusing the millisecond-level response data, minute-level adjustment data and day-level optimization data to obtain an interaction intensity data set; based on the multi-dimensional training data stream and the interaction intensity data set, adaptively screening the training content in the sports project library, and integrating the training difficulty parameters, training rhythm parameters and so on. The parameters and training duration parameters are dynamically configured to obtain a personalized training data packet; based on the interaction intensity data set and the personalized training data packet, the real-time motion data of special children are subjected to multimodal analysis and processing, and the movement standardization data, emotional change data and interaction feedback data are matched in real time to obtain a collaborative interaction data stream; the multidimensional training data stream, the collaborative interaction data stream and the personalized training data packet are encrypted and stored through distributed nodes, and the data access rights are hierarchically configured to obtain a security management database; based on the collaborative interaction data stream and the security management database, a multi-dimensional correlation analysis is performed on the motor ability data, emotional state data and interaction effect data, and the analysis results are quantitatively evaluated to obtain an intervention effect data set.

[0006] In a second aspect, the present application provides a cloud platform-based special children's sports intervention information interaction system, the cloud platform-based special children's sports intervention information interaction system comprising:

[0007] The acquisition module is used to collect and process the expression data stream, sound data, physiological data and behavioral data of special children during their movements through multi-source sensing equipment, extract features and perform time synchronization processing on the multi-source data to obtain a multi-dimensional training data stream;

[0008] An analysis module is used to perform hierarchical analysis on interaction parameters according to the multi-dimensional training data stream, and to fuse millisecond-level response data, minute-level adjustment data, and day-level optimization data to obtain an interaction intensity data set;

[0009] a screening module for adaptively screening the training content in the sports project library based on the multidimensional training data stream and the interaction intensity data set, dynamically configuring the training difficulty parameter, the training rhythm parameter, and the training duration parameter to obtain a personalized training data packet;

[0010] a processing module for performing multimodal analysis on the real-time motion data of special children based on the interaction intensity data set and the personalized training data set, matching the movement standardization data, the emotion change data, and the interaction feedback data in real time to obtain a collaborative interaction data stream;

[0011] An encryption module is used to encrypt and store the multidimensional training data stream, the collaborative interaction data stream, and the personalized training data packet through distributed nodes, and to configure data access permissions in a hierarchical manner to obtain a security management database;

[0012] The association module is used to perform multi-dimensional association analysis on the athletic ability data, emotional state data and interaction effect data based on the collaborative interaction data stream and the security management database, and quantitatively evaluate the analysis results to obtain an intervention effect data set.

[0013] In the technical solution provided by this application, multi-source sensing equipment is used to conduct all-round time-series collection and feature extraction of the facial expressions, sounds, physiological and behavioral data of special children during exercise, achieving accurate perception and quantitative characterization of the movement status of special children, providing a rich data foundation for subsequent personalized intervention. Based on the multi-dimensional training data stream, hierarchical analysis and processing are carried out, and millisecond-level response data, minute-level adjustment data and day-level optimization data are integrated to build a hierarchical interaction intensity assessment system, which can accurately grasp the immediate needs and long-term development trends of special children from different time scales. On this basis, the solution uses an adaptive screening algorithm to intelligently screen the sports project library, dynamically optimize and configure parameters such as training difficulty, rhythm and duration, achieve accurate matching and personalized adjustment of training content, and effectively improve the pertinence and adaptability of exercise intervention. At the same time, the solution also establishes a real-time interaction mechanism based on multimodal analysis, which matches and collaboratively analyzes the movement standardization, emotional changes and interactive feedback data in real time. It can not only promptly detect and respond to the abnormal state of special children during training, but also dynamically adjust the training strategy to ensure the continuous optimization of training effects. In terms of data security, the solution uses distributed nodes for encrypted storage and implements fine-grained access control, effectively ensuring the security and privacy of data related to special children. Finally, the solution has built a complete intervention effect evaluation system. Through multi-dimensional correlation analysis and quantitative evaluation, it can objectively reflect the actual effect of exercise intervention, providing a scientific basis for the continuous improvement of training programs. Overall, this solution innovatively applies artificial intelligence algorithms in the field of exercise intervention for special children, including adaptive screening algorithms, multimodal analysis algorithms, and collaborative interaction algorithms. The organic combination of these algorithms not only improves the intelligence level and personalization of exercise intervention, but also significantly enhances the real-time and accuracy of the intervention process, providing more scientific and efficient technical support for the rehabilitation training of special children. Through the deep integration and optimized application of algorithmic features, the solution successfully solves the problems of insufficient personalization, poor real-time performance, and weak security in traditional exercise intervention methods, greatly improving the overall effect of exercise intervention for special children. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 This is a schematic diagram of an embodiment of a method for interacting with special children's sports intervention information based on a cloud platform in an embodiment of the present application;

[0016] Figure 2 This is a timing diagram of performing hierarchical analysis and processing on interaction parameters according to a multi-dimensional training data stream in an embodiment of the present application;

[0017] Figure 3 This is a schematic diagram of an embodiment of a special children's sports intervention information interaction system based on a cloud platform in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The embodiments of the present application provide a special children's sports intervention information interaction method and system based on a cloud platform. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0019] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In one embodiment of the present application, a method for interacting with special children's sports intervention information based on a cloud platform includes:

[0020] Step S101: Using multi-source sensing equipment, the expression data stream, sound data, physiological data, and behavioral data of the special child's movement process are collected and processed in time series, and the multi-source data are subjected to feature extraction and time synchronization processing to obtain a multi-dimensional training data stream;

[0021] Step S102: performing hierarchical analysis on the interaction parameters based on the multi-dimensional training data stream, fusing the millisecond-level response data, minute-level adjustment data, and day-level optimization data to obtain an interaction intensity dataset;

[0022] Step S103: Based on the multidimensional training data stream and the interactive intensity data set, adaptively screening the training content in the sports project library, dynamically configuring the training difficulty parameter, training rhythm parameter, and training duration parameter to obtain a personalized training data packet;

[0023] Step S104: Based on the interaction intensity data set and the personalized training data set, multimodal analysis and processing are performed on the real-time motion data of the special children, and the movement standardization data, emotion change data, and interaction feedback data are matched in real time to obtain a collaborative interaction data stream;

[0024] Step S105: encrypt and store the multidimensional training data stream, the collaborative interaction data stream, and the personalized training data packet through distributed nodes, and configure the data access rights in a hierarchical manner to obtain a security management database;

[0025] Step S106: Based on the collaborative interaction data stream and the security management database, a multi-dimensional correlation analysis is performed on the athletic ability data, the emotional state data, and the interaction effect data, and the analysis results are quantitatively evaluated to obtain an intervention effect data set.

[0026] It is understandable that the execution subject of this application can be a special children's sports intervention information interaction system based on a cloud platform, or a terminal or a server, which is not limited here. The embodiment of this application is described by taking the server as the execution subject as an example.

[0027] Specifically, multi-source sensing equipment is used to collect multidimensional data from children with special needs during exercise. The facial expression data stream is captured using a high-speed camera at a sampling rate of 60 fps. Feature points are annotated on the captured facial image sequence to extract the characteristics of facial expression changes. Frequency domain analysis is then performed using a discrete Fourier transform to obtain temporal data on the variation of facial and micro-expression features. Simultaneously, audio data is collected using an 8-channel circular microphone array. After noise reduction and signal enhancement, acoustic feature parameters such as pitch, speech rate, and volume are extracted. Physiological data, such as heart rate variability and galvanic skin response, are collected using a smart wristband. Data segmentation and feature extraction are performed according to fixed time windows. Behavioral data is collected using a depth camera to capture three-dimensional spatial coordinate information during exercise. Spatial mapping and trajectory analysis of joint positions are performed. These multi-source data are then time-synchronized and feature-fused to form a multidimensional training data stream.

[0028] Based on the acquired multidimensional training data stream, interaction parameters are analyzed and processed hierarchically. First, real-time response analysis is performed at the millisecond level. A sliding window is used to detect unexpected states such as emotional fluctuations and abnormal movements, generating millisecond-level response data. At the minute level, data is accumulated and trends in training engagement, emotional stability, and movement standardization are analyzed to generate minute-level adjustment data. At the daily level, long-term performance indicators such as training effectiveness, emotional patterns, and physical condition are summarized and analyzed to generate daily optimization data. These three levels of data are integrated into an interaction intensity dataset using a weighted fusion approach. Subsequently, the multidimensional training data stream and the interaction intensity dataset are used to select and configure training content. First, the performance data in the training data stream is evaluated and matched with training items in the sports library to identify suitable candidate training items. A secondary screening process is then performed based on the emotional parameters in the interaction intensity dataset to ensure that the training items are aligned with the emotional state. The difficulty coefficients and difficulty levels of the selected training items are calculated and quantified to generate training difficulty parameters. The movement tempo is adjusted based on the reaction speed metric to generate training tempo parameters. The training duration is divided based on the persistence metric to generate training duration parameters. These parameters are then integrated to form a personalized training data package.

[0029] During training, real-time analysis is performed based on the interaction intensity dataset and personalized training data package. Spatial deviations between real-time motion data and standard motions are calculated, and the standardization of motions is assessed using training difficulty parameters. Real-time emotion indicators are compared with training rhythm parameters to analyze emotional trends. The standardization of motions is scored in real time and paired with emotion change data to generate interaction status data. This data undergoes time alignment and correlation analysis to form a collaborative interaction data stream. To ensure data security, a distributed storage architecture is used for data management. The multidimensional training data stream, collaborative interaction data stream, and personalized training data package are encrypted separately to generate corresponding data fingerprints, which are then stored across distributed nodes. Network topology and redundant backup are configured for the storage nodes. A role-based access control mechanism is established to fine-tune data access rights for different users, ultimately creating a security management database.

[0030] Finally, an effectiveness evaluation was conducted based on data from the collaborative interaction data stream and the security management database. Action standardization data, emotional change data, and interaction feedback data were extracted from the collaborative interaction data stream and subjected to time series analysis and feature extraction, respectively. Capability change trends and emotional feature sequences were time-aligned and correlated, and then integrated with interaction quality scores to generate comprehensive evaluation data. Through comparative analysis with historical data, the degree of improvement was calculated and quantified according to evaluation dimensions, ultimately generating an intervention effectiveness dataset.

[0031] Taking the exercise intervention process of a six-year-old child with autism as an example, multi-source sensing equipment collected data on facial expression changes, emotional characteristics of voice, heart rate variability, and joint movement trajectory during exercise. After time alignment, this data was used to detect emotional fluctuations and movement incoordination during training at the millisecond level. Changes in the child's training engagement and movement standardization were analyzed at the minute level, and long-term improvement trends in specific training programs were identified at the daily level. Based on these analysis results, training content tailored to the child's ability level was selected from a library of exercise programs, and the difficulty and pace of training were dynamically adjusted based on the child's emotional characteristics. During training, the child's movement standardization, emotional state, and interaction quality were analyzed in real time, and training parameters were adjusted promptly when fatigue or distraction occurred. All collected and analyzed data was encrypted and stored in distributed nodes, with access permissions configured for different roles, such as therapists, teachers, and parents. Through long-term tracking and analysis, a quantitative assessment of the child's improvement in motor skills, emotional stability, and social interaction skills was conducted, providing a basis for optimizing subsequent intervention plans.

[0032] In the embodiment of the present application, multi-source sensing equipment is used to collect and extract features of the facial expressions, sounds, physiological and behavioral data of special children during exercise, achieving accurate perception and quantitative characterization of the movement state of special children, providing a rich data foundation for subsequent personalized intervention. Based on the multidimensional training data stream, hierarchical analysis and processing are carried out, and millisecond-level response data, minute-level adjustment data and day-level optimization data are integrated to build a hierarchical interaction intensity assessment system, which can accurately grasp the immediate needs and long-term development trends of special children from different time scales. On this basis, the solution uses an adaptive screening algorithm to intelligently screen the sports project library, dynamically optimize and configure parameters such as training difficulty, rhythm and duration, achieve accurate matching and personalized adjustment of training content, and effectively improve the pertinence and adaptability of exercise intervention. At the same time, the solution also establishes a real-time interaction mechanism based on multimodal analysis, which matches and collaboratively analyzes the action standardization, emotional changes and interactive feedback data in real time, which can not only timely detect and respond to the abnormal state of special children during training, but also dynamically adjust the training strategy to ensure the continuous optimization of training effects. In terms of data security, the solution uses distributed nodes for encrypted storage and implements fine-grained access control, effectively ensuring the security and privacy of data related to special children. Finally, the solution has built a complete intervention effect evaluation system. Through multi-dimensional correlation analysis and quantitative evaluation, it can objectively reflect the actual effect of exercise intervention, providing a scientific basis for the continuous improvement of training programs. Overall, this solution innovatively applies artificial intelligence algorithms in the field of exercise intervention for special children, including adaptive screening algorithms, multimodal analysis algorithms, and collaborative interaction algorithms. The organic combination of these algorithms not only improves the intelligence level and personalization of exercise intervention, but also significantly enhances the real-time and accuracy of the intervention process, providing more scientific and efficient technical support for the rehabilitation training of special children. Through the deep integration and optimized application of algorithmic features, the solution successfully solves the problems of insufficient personalization, poor real-time performance, and weak security in traditional exercise intervention methods, greatly improving the overall effect of exercise intervention for special children.

[0033] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0034] (1) The facial expression data stream is sampled at 60fps for data collection, and the collected facial expression data is marked with feature points to obtain facial feature data; the facial feature data is analyzed in the frequency domain by discrete Fourier transform to extract the facial micro-expression feature sequence to obtain facial feature data;

[0035] (2) The sound data is collected in all directions through an 8-channel microphone array, and the collected sound data is subjected to noise reduction and signal enhancement processing to obtain pure speech data; the pure speech data is analyzed in the time and frequency domain to extract the acoustic characteristic parameters of pitch, speaking speed, and volume to obtain sound feature data;

[0036] (3) Physiological data are collected in real time through wearable sensors, and the heart rate variability and galvanic skin response physiological signals are filtered to obtain steady-state physiological data; the steady-state physiological data are divided into time windows, and the characteristics of physiological state changes are extracted to obtain physiological characteristic data;

[0037] (4) The behavioral data is collected in three dimensions through a depth camera, and the joint position data is mapped to spatial coordinates to obtain motion trajectory data; the motion trajectory data is analyzed in time series to extract the motion amplitude, speed, and acceleration motion characteristics to obtain behavioral feature data;

[0038] (5) Time alignment is performed on the facial expression feature data, sound feature data, physiological feature data, and behavioral feature data, and the aligned feature data is subjected to feature fusion to obtain a feature vector sequence; the feature vector sequence is sorted according to the sampling timestamp to obtain a multi-dimensional training data stream.

[0039] Specifically, a high-speed camera collects facial expressions of special children at a sampling rate of 60 frames per second, ensuring that the facial area is completely captured during the collection process. Feature points are annotated for each frame of the image collected. The annotated feature points include the positioning points of key areas such as eyebrows, eyes, nose, and mouth. Facial feature data is constructed through the spatial distribution of these feature points. The facial feature data is then converted to the frequency domain space through discrete Fourier transform, and the changing characteristics of facial micro-expressions are extracted in the frequency domain space. Discrete Fourier transform decomposes the time domain signal into a superposition of sine waves of different frequencies, thereby identifying the main frequency components of facial expression changes. These frequency components reflect the speed and amplitude characteristics of expression changes, forming expression feature data.

[0040] Sound data is collected using an 8-channel circular microphone array, evenly distributed in a circular pattern, to achieve omnidirectional sound collection. The collected raw sound signals first undergo noise reduction processing, using an adaptive filter to remove ambient noise and interfering signals. Signal enhancement then selectively amplifies the effective components of the speech signal to produce pure speech data. Time-frequency domain analysis is performed on the pure speech data to extract pitch characteristics (fundamental frequency variation), speech rate characteristics (phoneme duration), and volume characteristics (energy envelope). These acoustic characteristic parameters together constitute the sound feature data. Physiological data collection relies on wearable sensors such as smart bracelets, which record heart rate variability and galvanic skin response signals in real time. Heart rate variability data reflects the changes in the time intervals between consecutive heartbeats, while galvanic skin response data records changes in skin conductivity. These raw signals are processed through a bandpass filter to remove high-frequency noise and baseline drift, producing steady-state physiological data. The steady-state physiological data are divided into fixed time windows (e.g., 30 seconds). Within each time window, statistical features (such as mean, variance, and peak value) and variation characteristics (such as rate of rise and rate of fall) are extracted to form the physiological feature data.

[0041] Behavioral data collection uses a depth camera, which uses infrared structured light to obtain three-dimensional depth information during movement. The depth camera captures the spatial position information of human skeletal joints and maps this position data into a standard three-dimensional space through spatial coordinate transformation, generating motion trajectory data. Time series analysis of the motion trajectory data is performed to calculate the joint motion amplitude (displacement), instantaneous velocity (the first-order derivative of displacement with respect to time), and acceleration (the first-order derivative of velocity with respect to time). These kinematic parameters constitute the behavioral signature data.

[0042] Time alignment is performed on facial, vocal, physiological, and behavioral feature data, associating data from different sources with the same time point based on the timestamps of data acquisition. The aligned feature data is then fused at the feature level, concatenating the feature vectors from each data source into a unified feature vector. These feature vectors are arranged in timestamp order, forming a multidimensional training data stream that represents the movement status of a specific child.

[0043] For example, during a movement intervention training session, data acquisition equipment simultaneously recorded multimodal data from children with special needs as they completed simple movement tasks. A high-speed camera captured subtle changes in facial expression, identifying facial expressions such as raised eyebrows and raised corners of the mouth through feature point annotation. Frequency domain analysis revealed that these changes in expression exhibited regular frequency characteristics. Simultaneously, the speech signal collected by the microphone array was subjected to noise reduction and enhancement, revealing the acoustic characteristics of slow speech but rich intonation. Heart rate variability data recorded by the wearable device showed regular fluctuation patterns, while galvanic skin response (GSR) varied with task difficulty. A depth camera tracked and recorded joint motion during exercise, analyzing the patterns of movement amplitude, velocity, and acceleration. These data from different sensors were time-aligned and feature-fused to form a multidimensional feature sequence that comprehensively reflects the movement and emotional state of the child with special needs.

[0044] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0045] (1) Segment the multi-dimensional training data stream according to the time dimension, divide the sampled data into millisecond time windows, and obtain millisecond data segments; perform mutation detection on the millisecond data segments, extract the emotional fluctuations and abnormal movement state data, and obtain millisecond response data;

[0046] (2) Accumulate multi-dimensional training data streams at the minute level, perform sliding window analysis on the accumulated data, and obtain training process data; perform trend analysis on the training process data, extract the state change data of training participation, emotional stability, and action norms, and obtain minute-level adjustment data;

[0047] (3) Summarize the multi-dimensional training data stream at the daily level, perform periodic analysis on the summarized data, and obtain training regularity data; perform statistical analysis on the training regularity data, extract the long-term performance data of training effects, emotional changes, and physical condition, and obtain daily optimization data;

[0048] (4) Weights are assigned to millisecond-level response data, and the impact of the sudden state is quantified as an interactive adjustment parameter to obtain rapid response weight data; minute-level adjustment data is normalized, and the impact of state changes is quantified as an interactive correction parameter to obtain medium-term adjustment weight data; daily optimization data is normalized, and the impact of long-term performance is quantified as an interactive optimization parameter to obtain long-term adjustment weight data;

[0049] (5) The quick response weight data, the medium-term adjustment weight data and the long-term adjustment weight data are weighted and combined, and the combined data are normalized to obtain the interaction intensity data set.

[0050] Specifically, if Figure 2 As shown, this is a timing diagram of the hierarchical analysis and processing of interaction parameters according to the multidimensional training data stream in an embodiment of the present application, which shows the complete processing flow from raw data to the final interaction intensity dataset. The figure includes four main participants: multidimensional training data stream (MDS), millisecond processing (MS), minute processing (MIN) and day processing (DAY), as well as the final interaction intensity dataset (INT). In the millisecond processing link, the system performs segmented processing on the data in 10 millisecond time windows, identifies emotional fluctuations and abnormal movements through the mutation detection formula D(t), and generates rapid response weight data. In the minute processing link, the system uses a 60-second sliding window for analysis, and uses the trend analysis formula T(w) to evaluate training participation, emotional stability and movement standardization to form medium-term adjustment weight data. In the day processing link, the system summarizes the data, uses the statistical analysis formula P(d) to analyze the training effect, emotional changes and physical condition, and generates long-term adjustment weight data. The weight data of these three time scales are integrated through the normalization processing formula W(t) to form a unified interaction intensity dataset. The annotations in the figure clearly show the mathematical formulas and main analysis contents used in each processing stage, intuitively reflecting the hierarchical and systematic nature of the entire data processing.

[0051] In millisecond-level processing, the multidimensional training data stream is segmented into 10-millisecond time windows, and mutation detection is performed on the data in each time window. The detection formula is:

[0052]

[0053] in, represents the value of the i-th emotional feature (such as facial expression changes, voice emotion changes) at time t, represents the value of the j-th action feature (such as joint angle, movement speed) at time t, D(t): represents the mutation detection value at time t is the weight coefficient of the i-th emotional feature; is the weight coefficient of the j-th action feature; It is the overall balancing factor for emotional mutations; is the overall balance factor of action mutation; n is the total number of emotion features; m is the total number of action features.

[0054] The sudden state is identified by calculating the difference between these feature values ​​and the previous moment or the standard reference value. For example, when a special child is detected doing a pitching action, the facial expression suddenly changes from calm to nervous ( The value suddenly changes), and the arm trajectory appears unstable and jittery ( Values ​​deviate from the standard value ), these changes will lead to The value increases, thus being identified as an emergency state that requires an immediate response.

[0055] In minute-level data processing, a 60-second sliding window is used, updated every 10 seconds, and trend analysis is performed on the accumulated data within the window. The analysis formula is:

[0056]

[0057] In this formula, Represents the change gradient of the state parameters (such as attention concentration and action completion quality) within the window w, Indicates the stability index of the feature (such as emotional stability, action coherence). T(w) is the trend analysis value within the window w; is the gradient of the state parameter; is the standard deviation of the kth state parameter in window w; is the stability index value of the lth feature;

[0058] is the maximum reference value of the lth feature; is the weight coefficient of the kth state parameter; is the weight coefficient of the lth stability index; p is the total number of state parameters; q is the total number of stability indicators.

[0059] By calculating the trend and stability of these parameters, the system can identify medium-term change patterns during training. For example, if a child's attention level is found to be gradually decreasing within a one-minute window ( is negative), and the action accuracy also begins to decrease ( These changes will be reflected by changes in the T(w) value.

[0060] Daily data processing focuses on the analysis of long-term training performance and uses the following statistical analysis formula:

[0061]

[0062] In this formula, Represents the training effect indicators on day d (such as movement accuracy, completion time), Represents an indicator of mood change (such as the duration of positive mood), represents an indicator of physical condition (e.g., fatigue, concentration level). P(d) is the overall performance score on day d; is the weight of the rth training effect indicator; is the weight of the e-th sentiment change indicator; is the weight of the vth individual physical condition indicator; is the overall weight of the training effect dimension; is the overall weight of the emotion change dimension; is the overall weight of the physical condition dimension; s is the total number of training effect indicators; t is the total number of mood change indicators; u is the total number of physical condition indicators.

[0063] By weighting these indicators, the system can find the long-term changes in the training effect. For example, through the analysis of data for several consecutive days, it may be found that the training effect of children in the morning is better (higher values) and emotional states (more stable values) are better than other periods.

[0064] In order to integrate the data of these three time scales into a unified interaction intensity indicator, the following normalization formula is used:

[0065]

[0066] Among them, M(t), N(t), and L(t) represent the weight values ​​of millisecond-level, minute-level, and day-level data at time t, respectively. 、 、 These weight coefficients are used to balance the importance of data at different time scales. This normalization process ensures that data at different time scales can be compared and integrated within the same numerical range. W(t) is the normalized interaction strength value at time t.

[0067] For example, suppose a child with special needs is undergoing pitching training. The system detects sudden changes in facial expression and abnormal arm trajectory at the millisecond scale and immediately calculates the mutation detection value using the D(t) formula. Simultaneously, at the minute scale, the T(w) formula analyzes trends in attention and movement accuracy. At the day scale, the P(d) formula reveals that the child's training effect is better during specific periods. These analysis results at different time scales are ultimately integrated into a unified interaction intensity dataset using the W(t) formula, providing a quantitative basis for training adjustments. Through weight allocation and normalization, this interaction intensity dataset is formed to guide training adjustments.

[0068] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0069] (1) Decomposing the sports performance data in the multidimensional training data stream, and conducting ability assessment analysis on the decomposed data to obtain sports ability benchmark data; matching and screening the sports ability benchmark data with the training items in the sports item library to obtain a set of alternative training items;

[0070] (2) Perform correlation analysis on the emotion parameters in the interaction intensity dataset and the candidate training item set, filter the correlation data by emotion threshold, and obtain emotion-compatible training data; perform secondary screening on the candidate training item set based on the emotion-compatible training data to obtain training item data;

[0071] (3) Calculate the difficulty coefficient of the training movements in the training project data, compare the calculation results with the sports ability benchmark data, and obtain the training difficulty parameter; quantify the training difficulty parameter by level and obtain dynamic difficulty data;

[0072] (4) According to the reaction speed index in the interaction intensity data set, the action rhythm in the training project data is adjusted to obtain the training rhythm parameter; the training rhythm parameter is divided into intervals to obtain the rhythm control data;

[0073] (5) Based on the persistence index in the interaction intensity dataset, the training time in the training project data is segmented to obtain the training duration parameters; the training duration parameters are configured into time periods to obtain the duration control data;

[0074] (6) Integrate the dynamic difficulty data, rhythm control data, and duration control data, arrange the integrated data into a training sequence, and obtain a personalized training data package.

[0075] Specifically, principal component analysis and feature extraction are performed on the athletic performance data, including quantitative indicators of dimensions such as motor stability, coordination, and reaction speed. These decomposed features are combined using an ability assessment matrix to form baseline data reflecting the current athletic ability level of children with special needs. This athletic ability baseline data is then feature-matched with a sports program library. By calculating the similarity between feature vectors, a set of candidate training programs that meet the current ability level is selected.

[0076] Emotional parameters from the interaction intensity dataset were correlated with the candidate training item set. Emotional parameters included facial expression frequency, vocal emotional eigenvalues, and physiological signal fluctuations. These parameters were compared with the emotional activation threshold for each candidate training item. Using the emotional threshold, training items with high emotional compatibility were retained to form emotional compatibility training data. The candidate training item set was then subjected to a secondary screening based on the emotional compatibility training data to obtain the training item data.

[0077] For the calculation and adjustment of training difficulty, the following formula is used:

[0078]

[0079] Parameter meaning: is the difficulty coefficient of training action d; is the i-th complexity index of action d; is the benchmark value of the i-th complexity index; is the j-th accuracy requirement of action d; is the standard value of the jth accuracy requirement; is the mth motion parameter of action d; is the reference value of the mth motion parameter; is the complexity index weight; Weight is required for accuracy; is the motion parameter deviation weight; is the number of complexity indicators; Require quantity for accuracy; is the number of motion parameters.

[0080] In practical applications, complexity indicators Including specific parameters such as throwing distance (2 meters), target area (circle with a diameter of 30 cm), throwing angle requirement (vertical 45 degrees), etc., the accuracy requirement Q_j(d) is quantified into indicators such as hit rate requirement and force control, and the motion parameters It includes real-time monitoring data such as wrist angular velocity, elbow flexion, and torso stability.

[0081] For the adjustment of action rhythm, the following formula is used:

[0082]

[0083] Parameter meaning: is the rhythm parameter at time t; is the pth reaction speed index; is the rth action continuity index; is the u-th rhythm stability index; is the weight of the reaction speed indicator; is the weight of action continuity index; is the weight of the rhythm stability index; , , is the overall weight of the three types of indicators; is the maximum value of the reaction speed index; is the average value of the coherence index; It is the reference value of rhythm stability.

[0084] In the specific implementation, the reaction speed index Indicates the time interval from receiving the instruction to starting the action (average 1.5 seconds), action continuity index The fluency score of the complete throwing action is reflected, while the rhythm stability index This reflects the stability of the time interval between two consecutive throws (the target is set at 3 seconds). Based on the persistence indicators in the interaction intensity dataset, the training time is segmented. Sustainability indicators include attention span, physical endurance, and emotional stability periods. Based on the distribution characteristics of these indicators, the training time is divided into multiple segments, and each segment is assigned a corresponding training duration parameter. These duration parameters are configured over time periods to form detailed duration control data.

[0085] The dynamic difficulty data, rhythm control data, and duration control data are integrated. The integration process considers the mutual constraints between the three types of data and generates a training sequence arrangement plan through a multi-objective optimization algorithm to form a personalized training data package.

[0086] For example, in a pitching training program for a 7-year-old child with autism, motor characteristics such as hand-eye coordination and spatial perception were first extracted from the multidimensional training data stream. Decomposition and evaluation of these characteristics revealed a basic level of hand-eye coordination, but relatively strong spatial perception. Based on this baseline motor ability data, candidate training programs, including spot pitching and moving pitching, were selected from a sports program library. Analysis of emotional parameters from the interaction intensity dataset revealed that the child was emotionally stable when throwing at a fixed target, while moving target training was prone to anxiety. Therefore, fixed-target training programs were retained through emotional threshold filtering. The difficulty coefficient was calculated by factoring in parameters such as pitching distance, target size, and accuracy requirements into the formula, taking into account the child's characteristics. Regarding movement rhythm, rhythm parameters such as pitching preparation time and pitching interval were quantitatively adjusted based on the child's reaction speed. Training duration was divided into multiple 15-20 minute training sessions based on the child's attention span and physical condition. Ultimately, these parameters are integrated into a personalized training data package with progressive difficulty, controllable rhythm, and reasonable duration.

[0087] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0088] (1) Map the standard motion data in the personalized training data package to the real-time collected motion data, calculate the spatial deviation of the mapped data, and obtain the motion error data; compare and analyze the motion error data with the training difficulty parameter to obtain the motion standardization data;

[0089] (2) Synchronously compare the real-time emotion indicators in the interaction intensity dataset with the training rhythm parameters, perform fluctuation detection on the comparison results, and obtain emotion difference data; perform temporal correlation between the emotion difference data and the training duration parameters to obtain emotion change data;

[0090] (3) Score the normative indicators in the action normativeness data in real time, match the scoring results with the emotion change data in a time window to obtain the interaction state data; perform segmented statistics on the interaction state data to obtain the interaction feedback data;

[0091] (4) Time-align the action norm data with the emotion change data, perform correlation analysis on the aligned data to obtain action-emotion correlation data; fuse the action-emotion correlation data with the interaction feedback data to obtain multimodal feature data;

[0092] (5) Segmentally mark the training process based on the multimodal feature data, match the marking results with the training parameters in the personalized training data package to obtain training matching data; arrange the training matching data in time sequence to obtain training sequence data;

[0093] (6) Cross-validate the training sequence data with the interactive feedback data, integrate the validation results, and obtain the collaborative interactive data stream.

[0094] Specifically, standard movement data is extracted from the personalized training data package. This data contains the three-dimensional coordinate sequence of the joint points of the standard movement. A depth camera is used to collect the movement data of the special child in real time. Key joint points (such as the shoulder, elbow, and wrist) in this data are spatially mapped to the standard movement data. Euclidean distances are calculated for the mapped data to obtain the spatial deviation value for each joint point, thereby forming movement error data. This error data is then compared with the training difficulty parameter. Based on the allowable error range for different difficulty levels, a movement standardization score is calculated to generate movement standardization data.

[0095] During the emotion analysis phase, real-time emotion indicators are extracted from the interaction intensity dataset, including data such as the frequency of facial expression changes, vocal emotional characteristics, and physiological signal fluctuations. These emotion indicators are then synchronously compared with training rhythm parameters to determine whether the emotional state matches the current training rhythm. Emotional difference data is generated by calculating the amplitude and frequency of fluctuations in the emotion indicators. This difference data is then temporally correlated with the training duration parameters to analyze the relationship between emotional change trends and training duration, generating emotion change data. The normative indicators in the movement normativeness data are scored in real time based on dimensions such as movement accuracy, stability, and coherence. The scoring results are paired with the emotion change data within the same time window to generate interaction state data reflecting the current training state. This state data is then divided into time periods and statistically analyzed to generate interaction feedback data that represents training quality.

[0096] To deeply analyze the correlation between movement performance and emotional state, the movement standardization data and the emotion change data need to be temporally aligned. Correlation analysis is then performed on the aligned data to calculate the correlation between movement performance and emotion change, generating movement-emotion correlation data. This correlation data is then fused with the interactive feedback data at the feature level to generate multimodal feature data containing multidimensional information. Based on this multimodal feature data, the entire training process is time-labeled, with the markers selected based on significant changes in the feature data. These labeled results are then matched with the training parameters in the personalized training data package to evaluate the parameter fit for each training stage and generate training matching data. This matching data is arranged in chronological order to form training sequence data.

[0097] The training sequence data is cross-validated with the interactive feedback data. The validation process mainly examines whether the rationality of the training sequence is supported by the interactive feedback. The validated data is integrated to ultimately generate a collaborative interactive data stream reflecting the entire training process.

[0098] For example, a child with special needs undergoing pitching training. As the child begins pitching, a depth camera captures real-time coordinate data of joints such as the wrist, elbow, and shoulder. This data is mapped and compared with the joint data of a standard pitching motion to calculate spatial position deviations. Simultaneously, a facial expression recognition system captures the child's emotional changes, such as tension (furrowed brows) during pitching preparation and relaxation (smile) after pitching. These emotional indicators are compared with a preset training rhythm (e.g., 3-second intervals between pitches), revealing that emotional fluctuations increase with increasing rhythm. The system time-aligns the motion error data with the emotional change data and finds that when emotions stabilize, motion accuracy improves. This correlation is recorded in the motion-emotion correlation data and matched with training parameters, ultimately forming a collaborative interactive data stream to guide subsequent training parameter adjustments.

[0099] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0100] (1) Classify and organize the multi-dimensional training data stream according to the data type, encrypt and mark the organized data to obtain the training encrypted data; generate a data summary of the training encrypted data through a hash function to obtain the training data fingerprint;

[0101] (2) Divide the collaborative interaction data stream into blocks according to the time series, encrypt and package the block data to obtain interactive encrypted data; digitally sign the interactive encrypted data to obtain the interactive data fingerprint;

[0102] (3) Classify the personalized training data package according to the training project, encrypt and encapsulate the classified data to obtain the encrypted data of the training package; store the encrypted data of the training package on the blockchain to obtain the data fingerprint of the training package;

[0103] (4) Distribute and store the training data fingerprint, interaction data fingerprint, and training package data fingerprint, configure the network topology of the storage nodes, and obtain node distribution data; perform redundant backup of the node distribution data and obtain storage node mapping;

[0104] (5) Divide the access levels of training encrypted data, interactive encrypted data, and training package encrypted data, configure the access rights of different roles in a matrix, and obtain permission allocation data; associate and bind the permission allocation data with the storage node mapping to obtain access control data;

[0105] (6) Integrate the access control data and node distribution data, construct an index for the integrated data, and obtain a security management database.

[0106] Specifically, the multidimensional training data stream is classified by data type, with expression data, voice data, physiological data, and behavioral data categorized separately. A unique identifier and timestamp are added to each data type and encrypted using the AES-256 encryption algorithm to generate encrypted training data. The SHA-256 hash algorithm is then used to calculate a data digest of the encrypted training data, generating a fixed-length training data fingerprint. This fingerprint uniquely identifies the integrity of the data content. The collaborative interaction data stream is processed using a time series block-based approach, dividing the continuous data stream into multiple data blocks of fixed time length (e.g., 10 minutes). Each data block contains action standardization data, emotion change data, and interaction feedback data within that time period. These block-based data are encrypted using the RSA asymmetric encryption algorithm to generate encrypted interaction data. The encrypted data is digitally signed with a private key to generate an interaction data fingerprint for subsequent data verification.

[0107] Personalized training data packages are first categorized by training program type, such as basic movement training, coordination training, and sensory integration training. Each training data type is grouped and encrypted using a hybrid encryption method: the data content is first encrypted with a symmetric key, and then the symmetric key is encrypted with an asymmetric public key to form the encrypted training package data. This encrypted data is stored on the blockchain network, with each data package written as a transaction record, generating an unalterable training package data fingerprint. The three types of data fingerprints (training data fingerprint, interaction data fingerprint, and training package data fingerprint) are stored using a distributed architecture, with data distributed across multiple service nodes. The network topology between nodes adopts a peer-to-peer (P2P) structure, with each node maintaining a complete routing table. Data is sharded and distributed using a consistent hashing algorithm to generate node-distributed data. A multi-copy backup strategy is implemented for this distributed data, with copies stored on geographically distributed nodes to form a storage node mapping.

[0108] Data access control is based on the RBAC (role-based access control) model, which categorizes users into different roles (such as administrator, therapist, teacher, and parent). Different access levels are set for three types of encrypted data (training encrypted data, interaction encrypted data, and training package encrypted data). The access control matrix defines the operational permissions for each role on different data, generating permission allocation data. This permission data is then associated with storage node mappings to ensure that users can only access data on authorized nodes, forming access control data.

[0109] Access control data and node distribution data are integrated to construct a distributed index structure. The index uses a B+ tree structure, with data identifiers as index keys and storage location and access permission information as index values, forming a complete security management database. The database supports multi-dimensional queries, such as searches by time, type, and user role.

[0110] For example, during a sports intervention training session for a child with special needs, when training data containing a pitching motion is collected, the motion, facial, and physiological data within this data are first encrypted using AES, and corresponding hash values ​​are generated. This encrypted data is then divided into multiple time blocks, each of which is digitally signed. Simultaneously, the relevant training plan data is encapsulated, encrypted, and recorded on the blockchain. The storage location of all this data is recorded in distributed nodes, with corresponding access permissions set. For example, a therapist can view the complete training data, while parents can only access summary training reports. When the therapist needs to adjust the training plan, they verify their identity through the access control system, retrieve the required encrypted data from the distributed storage, and decrypt it using the authorized key. This multi-layered security mechanism effectively protects the privacy of the child's data while ensuring convenient access to the required information.

[0111] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0112] (1) Extracting movement standardization data from the collaborative interaction data stream, calculating the scores of movement completion quality, and obtaining movement ability data; processing the movement ability data into time series, performing trend analysis on movement performance, and obtaining the ability change curve;

[0113] (2) Extract emotion change data from the collaborative interaction data stream, perform numerical statistics on the amplitude of emotion fluctuations, and obtain emotion state data; perform periodic analysis on the emotion state data, extract features of emotion changes, and obtain emotion feature sequences;

[0114] (3) Extract interaction feedback data from the collaborative interaction data stream, perform data analysis on the interaction response degree, and obtain interaction effect data; segment the interaction effect data, perform statistical scoring on the interaction quality, and obtain an interaction score sequence;

[0115] (4) Time-align the ability change curve with the emotion feature sequence, calculate the correlation of the aligned data, and obtain the ability-emotion correlation data; fuse the ability-emotion correlation data with the interaction score sequence to obtain the comprehensive evaluation data;

[0116] (5) Search the historical data in the safety management database, compare and analyze the search results with the comprehensive assessment data to obtain the progress data; perform dimensional statistics on the progress data to obtain intervention analysis data;

[0117] (6) The intervention analysis data are quantified according to the evaluation dimensions, and an indicator system is constructed for the processing results to obtain an intervention effect data set.

[0118] Specifically, movement standardization data includes quantitative indicators such as angular deviation, force control, and speed stability when performing movements for children with special needs. By weighting these quantitative indicators, motor ability data reflecting the quality of movement completion is generated. This motor ability data is arranged chronologically to form a time series. Trend analysis of this time series is performed to calculate the rate of change in movement accuracy and the degree of improvement in stability, thereby generating a performance curve.

[0119] The emotion analysis component extracts emotion change data from the collaborative interaction data stream. This data includes information such as facial expression changes, vocal emotional characteristics, and physiological signal fluctuations. Statistical analysis is performed on the amplitude of emotion fluctuations, calculating the frequency, duration, and transition patterns of positive and negative emotions to generate emotion state data. Periodic analysis of this emotion state data identifies regular patterns of emotion change, such as emotional stability during specific training phases and emotional response patterns to different training content, thereby forming an emotion feature sequence. The processing of interaction feedback data focuses on analyzing the quality of interaction among children with special needs during training. Interaction feedback data extracted from the collaborative interaction data stream includes metrics such as instruction response speed, action correction effectiveness, and attention span. These metrics are quantitatively analyzed to assess the timeliness and effectiveness of interactions, generating interaction effect data. The interaction effect data is segmented by training phase, and the interaction quality of each phase is scored to form an interaction score sequence.

[0120] The correlation analysis between the ability change curve and the emotional signature sequence first requires time alignment to ensure temporal correspondence between the two data sets. Correlation coefficients are calculated for the aligned data, analyzing the correlation patterns between improved athletic ability and emotional changes to generate ability-emotion correlation data. This correlation data is then integrated with the interaction score sequence at the feature level. By combining multi-dimensional features, comprehensive evaluation data is generated that fully reflects the training effect. Historical training data is retrieved from the safety management database and compared with the current comprehensive evaluation data. This comparison includes the degree of improvement in movement accuracy, the degree of improvement in emotional stability, and the changing trends in interaction quality. This longitudinal comparison generates progress data. This progress data is then categorized and statistically analyzed according to different dimensions (such as athletic ability, emotional regulation, and social interaction) to form intervention analysis data.

[0121] Transform intervention analysis data into standardized evaluation metrics. Dimensions include basic motor skills, coordination, attention, emotional regulation, and social interaction. Quantify the data for each dimension, establish a multi-level indicator evaluation system, and ultimately generate an intervention effectiveness dataset.

[0122] Taking the hand-eye coordination training of a six-year-old child with special needs as an example, data on hand movement trajectory deviation and force control stability when grasping and placing objects were extracted from the movement standardization data. Analysis of this data showed that the accuracy of hand movements gradually improved with continued training, with particularly significant progress in force control. Furthermore, emotional change data revealed that after completing the correct movement, both facial expressions and vocal characteristics displayed positive emotional reactions, and this positive emotional state was positively correlated with the accuracy of subsequent movements. Regarding interactive feedback, records showed that the child's response speed to instructions gradually improved with the progress of training, and particularly when using a gamified training approach, his activeness in interaction was significantly enhanced. Comparison with historical training data revealed that over the three-month training period, the child's hand-eye coordination accuracy improved significantly, as did his emotional regulation ability. These improvements were quantified using standardized assessment indicators.

[0123] The above describes the special children's sports intervention information interaction method based on the cloud platform in the embodiment of the present application. The following describes the special children's sports intervention information interaction system based on the cloud platform in the embodiment of the present application. Figure 3 In one embodiment of the present application, a cloud platform-based special children's sports intervention information interaction system includes:

[0124] The acquisition module 201 is used to collect and process the expression data stream, sound data, physiological data and behavioral data of the special children's movement process in a time series through multi-source sensing equipment, extract features and perform time synchronization processing on the multi-source data to obtain a multi-dimensional training data stream;

[0125] Analysis module 202, configured to perform hierarchical analysis on interaction parameters based on the multi-dimensional training data stream, and fuse millisecond-level response data, minute-level adjustment data, and daily-level optimization data to obtain an interaction intensity dataset;

[0126] A screening module 203 is configured to adaptively screen the training content in the sports program library based on the multidimensional training data stream and the interaction intensity data set, dynamically configure the training difficulty parameter, the training rhythm parameter, and the training duration parameter, and obtain a personalized training data packet;

[0127] The processing module 204 is configured to perform multimodal analysis on the real-time motion data of the special child based on the interaction intensity data set and the personalized training data set, and to match the movement standardization data, the emotion change data, and the interaction feedback data in real time to obtain a collaborative interaction data stream;

[0128] An encryption module 205 is configured to encrypt and store the multidimensional training data stream, the collaborative interaction data stream, and the personalized training data packet through distributed nodes, and to perform hierarchical configuration of data access rights to obtain a security management database;

[0129] The correlation module 206 is used to perform multi-dimensional correlation analysis on the athletic ability data, emotional state data and interaction effect data based on the collaborative interaction data stream and the security management database, and quantitatively evaluate the analysis results to obtain an intervention effect data set.

[0130] Through the collaborative efforts of these components, multi-source sensing devices capture and extract features from the facial expressions, vocalizations, physiological data, and behavioral data of children with disabilities during exercise. This enables precise perception and quantitative characterization of these children's motor states, providing a rich data foundation for subsequent personalized interventions. Based on a multi-dimensional training data stream, the system performs hierarchical analysis and processing, integrating millisecond-level response data, minute-level adjustment data, and daily-level optimization data to construct a hierarchical interaction intensity assessment system. This system accurately captures both the immediate needs and long-term development trends of children with disabilities across different timescales. Furthermore, the solution intelligently selects exercise programs using an adaptive screening algorithm, dynamically optimizing parameters such as training difficulty, pace, and duration. This allows for precise matching and personalized adjustment of training content, effectively enhancing the targeted and adaptable nature of exercise interventions. Furthermore, the solution establishes a real-time interaction mechanism based on multimodal analysis, matching and collaboratively analyzing movement standardization, emotional changes, and interactive feedback data in real time. This not only enables timely detection and response to abnormalities in children's training, but also dynamically adjusts training strategies to ensure continuous optimization of training results. In terms of data security, the solution uses distributed nodes for encrypted storage and implements fine-grained access control, effectively ensuring the security and privacy of data related to special children. Finally, the solution has built a complete intervention effect evaluation system. Through multi-dimensional correlation analysis and quantitative evaluation, it can objectively reflect the actual effect of exercise intervention, providing a scientific basis for the continuous improvement of training programs. Overall, this solution innovatively applies artificial intelligence algorithms in the field of exercise intervention for special children, including adaptive screening algorithms, multimodal analysis algorithms, and collaborative interaction algorithms. The organic combination of these algorithms not only improves the intelligence level and personalization of exercise intervention, but also significantly enhances the real-time and accuracy of the intervention process, providing more scientific and efficient technical support for the rehabilitation training of special children. Through the deep integration and optimized application of algorithmic features, the solution successfully solves the problems of insufficient personalization, poor real-time performance, and weak security in traditional exercise intervention methods, greatly improving the overall effect of exercise intervention for special children.

[0131] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0132] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A special children's sports intervention information interaction method based on a cloud platform, characterized by: The cloud platform-based special children's sports intervention information interaction method includes: Through multi-source sensing equipment, the expression data stream, sound data, physiological data and behavioral data of special children during movement are collected and processed in time series, and the multi-source data are subjected to feature extraction and time synchronization processing to obtain a multi-dimensional training data stream; Performing hierarchical analysis on interaction parameters according to the multidimensional training data stream, fusing millisecond-level response data, minute-level adjustment data, and day-level optimization data to obtain an interaction intensity data set; Based on the multidimensional training data stream and the interaction intensity data set, adaptively screening the training content in the sports project library, dynamically configuring the training difficulty parameter, training rhythm parameter and training duration parameter to obtain a personalized training data packet; Based on the interaction intensity data set and the personalized training data packet, multimodal analysis and processing are performed on the real-time motion data of special children, and the action normative data, emotional change data and interactive feedback data are matched in real time to obtain a collaborative interactive data stream, including: mapping the standard action data in the personalized training data packet with the real-time collected action data through joint points, performing spatial deviation calculation on the mapping data to obtain action error data; comparing and analyzing the action error data with the training difficulty parameter to obtain the action normative data; synchronously comparing the real-time emotional index in the interaction intensity data set with the training rhythm parameter, performing fluctuation detection on the comparison result to obtain emotional difference data; performing time series association on the emotional difference data and the training duration parameter to obtain the emotional change data; and performing correlation analysis on the normative index in the action normative data. Perform real-time scoring, pair the scoring results with the emotion change data in a time window to obtain interaction state data; perform segmented statistics on the interaction state data to obtain the interaction feedback data; perform time alignment on the action standardization data and the emotion change data, perform correlation analysis on the aligned data to obtain action emotion association data; perform data fusion on the action emotion association data and the interaction feedback data to obtain multimodal feature data; perform segmented labeling on the training process based on the multimodal feature data, match the labeling results with the training parameters in the personalized training data package to obtain training matching data; perform time sequence arrangement on the training matching data to obtain training sequence data; perform cross-validation on the training sequence data and the interaction feedback data, perform data integration on the validation results to obtain the collaborative interaction data stream; The multidimensional training data stream, the collaborative interaction data stream and the personalized training data packet are encrypted and stored through distributed nodes, and data access rights are hierarchically configured to obtain a security management database; Based on the collaborative interaction data stream and the security management database, a multi-dimensional correlation analysis is performed on the athletic ability data, emotional state data and interaction effect data, and the analysis results are quantitatively evaluated to obtain an intervention effect data set.

2. The method for interactive information on sports intervention for special children based on a cloud platform according to claim 1, characterized in that: The multi-source sensing device is used to collect and process the expression data stream, sound data, physiological data and behavioral data of the special children's movement process in time series, and the multi-source data is subjected to feature extraction and time synchronization processing to obtain a multi-dimensional training data stream, including: The facial expression data stream is sampled at 60fps for data collection, and the collected facial expression data is marked with feature points to obtain facial feature data; the facial feature data is analyzed in the frequency domain by discrete Fourier transform to extract the facial micro-expression feature sequence to obtain facial feature data; The sound data is collected in all directions through an 8-channel microphone array, and the collected sound data is subjected to noise reduction and signal enhancement processing to obtain pure speech data; the pure speech data is analyzed in the time and frequency domain to extract the acoustic characteristic parameters of pitch, speaking rate, and volume to obtain sound feature data; The physiological data is collected in real time through wearable sensors, and the heart rate variability and galvanic skin response physiological signals are filtered to obtain steady-state physiological data; the steady-state physiological data is divided into time windows, and the characteristics of physiological state changes are extracted to obtain physiological characteristic data; The behavioral data is collected in three dimensions through a depth camera, and the joint position data is mapped to spatial coordinates to obtain motion trajectory data; the motion trajectory data is subjected to time series analysis to extract motion amplitude, speed, and acceleration motion features to obtain behavioral feature data; The expression feature data, the sound feature data, the physiological feature data and the behavioral feature data are time-aligned, and the aligned feature data are feature-fused to obtain a feature vector sequence; the feature vector sequence is sorted according to sampling timestamps to obtain the multidimensional training data stream.

3. The method for interactive information on sports intervention for special children based on a cloud platform according to claim 1, characterized in that: The interaction parameters are subjected to hierarchical analysis and processing according to the multi-dimensional training data stream, and the millisecond-level response data, minute-level adjustment data, and day-level optimization data are fused to obtain an interaction intensity data set, including: The multi-dimensional training data stream is segmented and sampled according to the time dimension, and the sampled data is divided into millisecond-level time windows to obtain millisecond-level data segments; mutation detection is performed on the millisecond-level data segments, and the emotional fluctuation and abnormal movement state data are extracted to obtain the millisecond-level response data; Accumulate the multidimensional training data stream at the minute level, perform sliding window analysis on the accumulated data to obtain training process data; perform trend analysis on the training process data, extract data on changes in training participation, emotional stability, and movement norms, and obtain the minute-level adjustment data; Summarizing the multidimensional training data stream at the daily level, performing periodic analysis on the summarized data to obtain training regularity data; performing statistical analysis on the training regularity data, extracting the long-term performance data of training effects, emotional changes, and physical condition, and obtaining the daily optimization data; The millisecond-level response data is weighted, and the impact of the sudden state is quantified as an interactive adjustment parameter to obtain rapid response weight data; the minute-level adjustment data is normalized, and the impact of the state change is quantified as an interactive correction parameter to obtain medium-term adjustment weight data; the daily optimization data is standardized, and the impact of long-term performance is quantified as an interactive optimization parameter to obtain long-term adjustment weight data; The quick response weight data, the mid-term adjustment weight data and the long-term adjustment weight data are weighted and combined, and the combined data are normalized to obtain the interaction intensity data set.

4. The method for interactive information on sports intervention for special children based on a cloud platform according to claim 1, characterized in that: Based on the multidimensional training data stream and the interaction intensity data set, adaptively screening the training content in the sports project library, dynamically configuring the training difficulty parameter, training rhythm parameter, and training duration parameter to obtain a personalized training data packet, including: Decomposing the athletic performance data in the multidimensional training data stream by features, and performing ability assessment analysis on the decomposed data to obtain athletic ability benchmark data; matching and screening the athletic ability benchmark data with training items in a sports item library to obtain a set of candidate training items; Performing correlation analysis on the emotion parameters in the interaction intensity data set and the candidate training item set, performing emotion threshold filtering on the correlation data to obtain emotion compatibility training data; performing secondary screening on the candidate training item set based on the emotion compatibility training data to obtain training item data; Calculating the difficulty coefficient of the training movements in the training project data, comparing the calculation result with the athletic ability benchmark data to obtain the training difficulty parameter; grading and quantifying the training difficulty parameter to obtain dynamic difficulty data; Adjusting the action rhythm in the training item data according to the reaction speed index in the interaction intensity data set to obtain the training rhythm parameter; dividing the training rhythm parameter into intervals to obtain rhythm control data; Based on the persistence index in the interaction intensity data set, the training time in the training project data is segmented to obtain the training duration parameter; the training duration parameter is configured into time periods to obtain duration control data; The dynamic difficulty data, the rhythm control data and the duration control data are integrated, and a training sequence is arranged for the integrated data to obtain the personalized training data packet.

5. The method for interactive information on sports intervention for special children based on a cloud platform according to claim 1, characterized in that: The multi-dimensional training data stream, the collaborative interaction data stream, and the personalized training data packet are encrypted and stored through distributed nodes, and data access rights are hierarchically configured to obtain a security management database, including: Classifying and arranging the multidimensional training data stream according to data type, encrypting and marking the arranged data to obtain training encrypted data; generating a data summary of the training encrypted data through a hash function to obtain a training data fingerprint; Divide the collaborative interaction data stream into blocks according to the time series, encrypt and package the block data to obtain interactive encrypted data; digitally sign the interactive encrypted data to obtain an interactive data fingerprint; Classifying the personalized training data package according to the training project, encrypting and encapsulating the classified data to obtain training package encrypted data; storing the training package encrypted data on the blockchain to obtain a training package data fingerprint; Distributed storage is performed on the training data fingerprint, the interaction data fingerprint, and the training package data fingerprint, and network topology configuration is performed on the storage nodes to obtain node distribution data; redundant backup is performed on the node distribution data to obtain a storage node mapping; Access levels are divided for the training encrypted data, the interactive encrypted data, and the training package encrypted data, and access rights of different roles are configured in a matrix to obtain permission allocation data; the permission allocation data is associated and bound with the storage node mapping to obtain access control data; The access control data and the node distribution data are integrated, and the integrated data is indexed to obtain the security management database.

6. The method for interactive information on sports intervention for special children based on a cloud platform according to claim 1, characterized in that: Based on the collaborative interaction data stream and the security management database, a multi-dimensional correlation analysis is performed on the athletic ability data, the emotional state data, and the interaction effect data, and the analysis results are quantitatively evaluated to obtain an intervention effect data set, including: Extracting movement standardization data from the collaborative interaction data stream, calculating a score for the movement completion quality, and obtaining the movement ability data; performing time series processing on the movement ability data, performing trend analysis on the movement performance, and obtaining a movement ability change curve; Extracting emotion change data from the collaborative interaction data stream, performing numerical statistics on the amplitude of emotion fluctuations, and obtaining the emotion state data; performing periodic analysis on the emotion state data, performing feature extraction on emotion changes, and obtaining an emotion feature sequence; Extracting interaction feedback data from the collaborative interaction data stream, performing data analysis on the interaction response degree to obtain the interaction effect data; segmenting the interaction effect data, performing score statistics on the interaction quality, and obtaining an interaction score sequence; Time-aligning the capability change curve with the emotion feature sequence, performing correlation calculation on the aligned data to obtain capability-emotion correlation data; fusing the capability-emotion correlation data with the interaction score sequence to obtain comprehensive evaluation data; Searching historical data in the safety management database, comparing and analyzing the search results with the comprehensive assessment data to obtain progress data; performing dimensional statistics on the progress data to obtain intervention analysis data; The intervention analysis data is quantified according to the evaluation dimensions, and an indicator system is constructed for the processing results to obtain the intervention effect data set.

7. A cloud platform-based special children's sports intervention information interaction system, used to implement the cloud platform-based special children's sports intervention information interaction method according to any one of claims 1 to 6, characterized in that: The cloud platform-based special children's sports intervention information interaction system includes: The acquisition module is used to collect and process the expression data stream, sound data, physiological data and behavioral data of special children during their movements through multi-source sensing equipment, extract features and perform time synchronization processing on the multi-source data to obtain a multi-dimensional training data stream; An analysis module is used to perform hierarchical analysis on interaction parameters according to the multi-dimensional training data stream, and to fuse millisecond-level response data, minute-level adjustment data, and day-level optimization data to obtain an interaction intensity data set; a screening module for adaptively screening the training content in the sports project library based on the multidimensional training data stream and the interaction intensity data set, dynamically configuring the training difficulty parameter, the training rhythm parameter, and the training duration parameter to obtain a personalized training data packet; The processing module is used to perform multimodal analysis and processing on the real-time motion data of special children based on the interaction intensity data set and the personalized training data set, and to match the action standardization data, emotion change data and interaction feedback data in real time to obtain a collaborative interaction data stream, including: mapping the standard action data in the personalized training data set with the real-time collected action data, and performing spatial deviation calculation on the mapping data to obtain action error data; comparing and analyzing the action error data with the training difficulty parameter to obtain the action standardization data; synchronously comparing the real-time emotion index in the interaction intensity data set with the training rhythm parameter, and performing fluctuation detection on the comparison result to obtain emotion difference data; performing time series association on the emotion difference data and the training duration parameter to obtain the emotion change data; comparing the standard in the action standardization data with the training rhythm parameter to obtain the emotion change data; comparing the standard in the action standardization data with the training duration parameter to obtain the emotion change data; comparing the standard in the action standardization data with the training rhythm parameter to obtain the emotion difference data; comparing the standard in the action standardization data with the training duration parameter to obtain the emotion change ... The method comprises the following steps: performing real-time scoring of the action norm index and pairing the scoring result with the emotion change data in a time window to obtain the interaction state data; performing segmented statistics on the interaction state data to obtain the interaction feedback data; performing time alignment on the action norm data and the emotion change data, performing correlation analysis on the aligned data to obtain action emotion association data; performing data fusion on the action emotion association data and the interaction feedback data to obtain multimodal feature data; performing segmented labeling on the training process based on the multimodal feature data, matching the labeling result with the training parameters in the personalized training data packet to obtain training matching data; performing time sequence arrangement on the training matching data to obtain training sequence data; cross-validating the training sequence data with the interaction feedback data, and performing data integration on the validation results to obtain the collaborative interaction data stream; An encryption module is used to encrypt and store the multidimensional training data stream, the collaborative interaction data stream, and the personalized training data packet through distributed nodes, and to configure data access permissions in a hierarchical manner to obtain a security management database; The association module is used to perform multi-dimensional association analysis on the athletic ability data, emotional state data and interaction effect data based on the collaborative interaction data stream and the security management database, and quantitatively evaluate the analysis results to obtain an intervention effect data set.

Images