Action sports scoring method and device based on big data analysis

By using a big data manifold distribution deviation quantification mechanism based on Wasserstein distance and an improved AGCN network model, the computational challenges and misjudgments of traditional scoring systems in the evaluation of high-dimensional motion data are solved, and accurate global evaluation and in-depth quantification of complex sports movements are achieved.

CN121963050APending Publication Date: 2026-05-01YANGTZE UNIVERSITY
0 Cites 2 Cited by

Patent Information

Application Number
CN202610092036.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-01-23
Publication Date
2026-05-01

AI Technical Summary

Technical Problem

Existing sports scoring systems face computational challenges in feature extraction and accurate quantitative evaluation of high-dimensional motion data. They struggle to fully utilize prior knowledge of statistical distributions in large-scale standard motion sample libraries, leading to increased risk of misjudgment. Furthermore, traditional methods ignore the dynamic topological structure of motion sequences in high-dimensional manifold space, limiting their ability to accurately evaluate complex and challenging sports movements globally.

Method used

A big data manifold distribution deviation quantification mechanism based on Wasserstein distance is adopted. By improving the AGCN network model, the manifold features of the athlete's current movement and the distribution parameters of the standard deep manifold are extracted, the optimal transport plan is calculated, the global distribution deviation features are generated, and the scoring results are generated based on this mapping. The comprehensive scoring is carried out using the manifold topological constraint matrix and the self-attention mechanism.

Benefits of technology

It significantly improves the accuracy of motion feature extraction and the ability to express topological structure, accurately reflects the degree of global deviation of athletes' movements from standard norms in manifold space, realizes in-depth quantitative evaluation of motion quality, reduces the risk of misjudgment, and provides an efficient intelligent scoring solution.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses an action sports scoring method and device based on big data analysis, and relates to the technical field of computer vision, and the method comprises the following steps: S1, constructing a human body posture tensor manifold; s2, generating aligned action track characteristics; s3, generating symmetrical positive definite manifold features; s4, generating deep manifold distribution parameters; s5, quantifying global distribution deviation characteristics; s6, calculating a residual vector based on the deep manifold distribution parameters and the standard action distribution parameters, inputting the residual vector into the improved AGCN model for processing, constructing an adaptive topology based on the residual vector, and performing aggregation analysis to obtain a joint-level physical angle error after multi-scale space-time convolution and manifold enhancement; and S7, outputting a comprehensive score vector. According to the method, the limitation that a traditional method only depends on local geometric features and ignores global topological structure constraints and statistical distribution priori is overcome, and an efficient solution is provided for intelligent scoring of sports actions.
Need to check novelty before this filing date? Find Prior Art