Real-time motion posture monitoring and correction system for augmented reality

Abstract

This invention discloses a real-time motion posture monitoring and correction system for augmented reality. The system includes: a data acquisition module that acquires the user's limb spatial trajectory in standard mode from a motion capture device; a posture analysis module including: a deviation calculation unit that calculates the deviation between the limb spatial trajectory and a preset standard trajectory; a proficiency mapping unit that determines the user's proficiency level based on the trajectory deviation; a first mode switching unit that switches to a matching training mode according to the proficiency level, dividing the limb spatial trajectory into multiple regions based on body parts; an error analysis unit that calculates the regional error value between the limb spatial trajectory of each region and its corresponding standard trajectory; a key body part decision unit that analyzes the importance of the corresponding body parts and, together with the regional error value, determines the key body parts to be corrected first; and an augmented reality display module that displays correction prompts through an augmented reality device. This invention combines error intensity and motion contribution analysis, which helps improve user focus.

Description

Technical Field

[0001] This invention relates to the field of augmented reality and human motion posture monitoring technology, specifically to a real-time motion posture monitoring and correction system for augmented reality. Background Technology

[0002] Traditional vision-based posture monitoring systems are mostly limited to two-dimensional planar analysis, which is insufficient in the reproduction of three-dimensional human posture and has a weak ability to acquire depth information. Furthermore, users cannot receive posture feedback and correction guidance in an intuitive and immersive way, which affects the efficiency of sports training and rehabilitation.

[0003] With the development of motion capture technology, it has been widely used in various fields such as sports training, rehabilitation medicine, and virtual reality. Especially in the fields of sports training and posture correction, by collecting users' three-dimensional posture data, it can help evaluate training effects, thereby improving athletic performance or rehabilitation efficiency.

[0004] However, in actual monitoring and correction, users often have multiple parts that are inconsistent with the standard posture. If they are reminded at the same time, most users cannot absorb all of them, which will also cause them to lose focus. In fact, the original standard posture may become more inaccurate due to the overall adjustment, thus delaying the correction time. Summary of the Invention

[0005] To address the problem that existing systems cannot promptly correct all overall user errors, this invention provides a real-time motion posture monitoring and correction system for augmented reality.

[0006] To achieve the above objectives, the technical solution of the present invention is as follows:

[0007] In a first aspect, this application discloses a real-time motion posture monitoring and correction system for augmented reality, including a data acquisition module, a posture analysis module, and an augmented reality display module.

[0008] The data acquisition module acquires the user's limb spatial trajectory in standard mode from the motion capture device;

[0009] The attitude analysis module includes:

[0010] The deviation calculation unit calculates the deviation between the limb spatial trajectory and the preset standard trajectory;

[0011] The proficiency mapping unit determines the user's proficiency level based on the mapping relationship between trajectory deviation and proficiency.

[0012] The first mode switching unit switches to the matching training mode according to the proficiency level, and then divides the user's limb spatial trajectory in the training mode into multiple areas according to the body parts.

[0013] The error analysis unit calculates the regional error value between the limb spatial trajectory of each region and its corresponding standard trajectory, and sorts them in descending order;

[0014] The key part decision unit analyzes the importance of each part in the corresponding area in the entire limb space trajectory based on the ranking results, and determines the key parts to be corrected first by combining the regional error values.

[0015] The augmented reality display module uses an augmented reality device to display a posture comparison between key parts and a standard trajectory, and displays correction prompts.

[0016] Secondly, this application discloses a method for real-time monitoring and correction of motion posture for augmented reality, including the following steps:

[0017] Acquire the user's limb spatial trajectory in standard mode from motion capture devices;

[0018] Calculate the deviation between the limb spatial trajectory and the preset standard trajectory;

[0019] Determine the user's proficiency level based on the mapping relationship between trajectory deviation and proficiency.

[0020] The system switches to the matching training mode based on the user's proficiency level, and then divides the user's limb spatial trajectory in the training mode into multiple areas based on body parts.

[0021] Calculate the regional error value between the limb spatial trajectory of each region and its corresponding standard trajectory, and sort them in descending order;

[0022] Based on the ranking results, the importance of each part of the corresponding region in the entire limb spatial trajectory is analyzed one by one, and the key parts to be corrected first are determined by combining the regional error values.

[0023] Augmented reality devices are used to display a pose comparison between key parts and standard trajectories, and correction prompts are shown.

[0024] Thirdly, this application discloses a method for real-time monitoring and correction of motion posture for augmented reality, including the following steps:

[0025] The system responds to the correction prompts, obtains the user's key body parts from the system, and then obtains the limb spatial trajectory of the key body parts from the motion capture device;

[0026] Retrieve the standard trajectory corresponding to the key parts from the system and calculate the deviation between the limb spatial trajectory and the standard trajectory;

[0027] The deviation is fed back to the system until a stop correction command is received from the system.

[0028] Fourthly, this application discloses a device for real-time monitoring and correction of motion postures for augmented reality, comprising:

[0029] Motion capture devices are installed on various parts of the user's body to collect the user's spatial trajectories;

[0030] The processor receives the limb spatial trajectory captured by the motion capture device and generates a comparison of the user's posture with the standard trajectory, as well as correction prompts.

[0031] An interactive device, embedded in a motion capture device, is used to receive instructions from the processor and provide vibration feedback to the user, while also receiving feedback information from the user.

[0032] Augmented reality devices, worn on the user's head, are used to display gesture comparisons and correction prompts generated by a processor;

[0033] Edge computing devices are used to receive correction prompts from the processor and calculate the deviation of the user's limb spatial trajectory from the standard trajectory for key parts of the body.

[0034] When the processor is working, it executes the steps of the real-time motion posture monitoring and correction method for augmented reality as described in the second aspect; when the edge computing device is working, it executes the steps of the real-time motion posture monitoring and correction method for augmented reality as described in the third aspect.

[0035] Fifthly, this application discloses a computer device including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the real-time motion posture monitoring and correction method for augmented reality as described in the second aspect.

[0036] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0037] 1. This invention not only determines "key parts" based on the magnitude of the error, but also on the importance of the part in the whole set of movements. Combining the analysis of error intensity and movement contribution in two dimensions helps to improve the user's focus and make them prioritize the high-yield parts.

[0038] 2. This invention automatically judges the user's level by combining the degree of deviation and assigns an appropriate training mode to improve the user experience and training effect. It is especially suitable for the gradual training needs of users at different stages and, combined with the correction of key parts, realizes a targeted correction strategy. Attached Figure Description

[0039] The disclosure of this invention is illustrated with reference to the accompanying drawings. It should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. In the drawings, the same reference numerals are used to refer to the same parts. Wherein:

[0040] Figure 1 This is a structural block diagram of the real-time motion posture monitoring and correction system for augmented reality described in this invention;

[0041] Figure 2 Based on Figure 1 A system block diagram with a feedback interaction module;

[0042] Figure 3 Based on Figure 2 A system block diagram with a verification unit;

[0043] Figure 4 Based on Figure 3 The structural block diagram of the verification unit;

[0044] Figure 5 Based on Figure 2 A system block diagram with a second mode switching unit;

[0045] Figure 6 Based on Figure 5 The structural block diagram of the second mode switching unit;

[0046] Figure 7 Based on Figure 2 A system block diagram with a feedback adjustment module;

[0047] Figure 8 Based on Figure 7 The structural block diagram of the feedback adjustment module;

[0048] Figure 9 The image shown is a simulation diagram of a 3D skeleton model divided into different regions.

[0049] Figure 10 Simulation diagram for correction prompts;

[0050] Figure 11 This is a flowchart illustrating the real-time motion posture monitoring and correction method for augmented reality as described in Example 2;

[0051] Figure 12 This is a flowchart of a real-time motion posture monitoring and correction method for augmented reality, as described in Example 3;

[0052] Figure 13 Based on Figure 13 The simulation results of the spatial trajectory of a single camera and the motion acquisition device used in this embodiment;

[0053] Figure 14 Based on Figure 13 The logic diagram of augmented reality. Detailed Implementation

[0054] It is readily understood that, based on the technical solution of this invention, those skilled in the art can propose various interchangeable structural methods and implementations without altering the essential spirit of the invention. Therefore, the following detailed embodiments and accompanying drawings are merely illustrative examples of the technical solution of this invention and should not be considered as the entirety of the invention or as limitations or restrictions on the technical solution of this invention.

[0055] Application Overview

[0056] In existing technologies, traditional motion posture monitoring systems mostly employ two-dimensional planar analysis methods, which struggle to accurately reconstruct the three-dimensional spatial motion characteristics of the human body. While motion capture technology can acquire three-dimensional data, it lacks an effective mechanism for handling posture deviations. When a user exhibits deviations in multiple body parts, current systems typically employ simultaneous multi-dimensional correction prompts, leading to information overload. This approach not only distracts the user but may also cause coordination problems due to simultaneous adjustments of multiple body parts, thus prolonging the correction training cycle.

[0057] To address the aforementioned issues, the research found that a hierarchical processing mechanism is needed to optimize the correction process, especially in scenarios where users exhibit deviations in multiple areas. This mechanism should automatically identify the key correction areas with the highest training priority and provide guidance through progressive prompts, thereby optimizing the learning load and improving posture adjustment efficiency. Based on this, considering correction priorities, key correction targets are selected through a dual evaluation of error ranking and functional importance. Furthermore, to address the issue of traditional visual feedback being unintuitive, augmented reality technology is explored to visualize deviations in key areas, enabling focused and dynamic guidance of the correction task.

[0058] After introducing the basic concept of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0059] Example 1

[0060] like Figure 1 The diagram illustrates a real-time motion posture monitoring and correction system for augmented reality, including a data acquisition module 100, a posture analysis module 200, and an augmented reality display module 300.

[0061] The data acquisition module 100 is used to acquire the user's limb spatial trajectory in standard mode from the motion capture device;

[0062] Attitude analysis module 200, which includes:

[0063] Deviation calculation unit 201 is used to calculate the deviation between the limb spatial trajectory and the preset standard trajectory;

[0064] The proficiency mapping unit 202 is used to determine the user's proficiency level based on the trajectory deviation and proficiency mapping relationship;

[0065] The first mode switching unit 203 is used to switch to the matching training mode according to the proficiency level, and then divide the user's limb spatial trajectory in the training mode into multiple areas according to the body part.

[0066] Error analysis unit 204 is used to calculate the regional error value between the limb spatial trajectory of each region and its corresponding standard trajectory, and sort them in descending order;

[0067] The key part decision unit 205 is used to analyze the importance of the corresponding parts in the entire limb space trajectory based on the sorting results, and determine the key parts to be corrected first by combining the regional error values.

[0068] Augmented reality display module 300 is used to display the posture comparison of key parts and standard trajectory through an augmented reality device, and to display correction prompts.

[0069] Regarding the data acquisition module 100, the motion capture device uses equipment based on inertial measurement unit (IMU), optical tracking system, infrared depth camera or other three-dimensional positioning technology, and has the ability to collect three-dimensional dynamic data such as user joint position, angle change, and motion trajectory in real time.

[0070] It can access raw data collected by external motion capture devices. The data format can be a set of three-dimensional coordinate points in a time series or vector data containing extended information such as velocity and acceleration.

[0071] To eliminate the influence of factors such as equipment installation location and user height and body type differences on the data, the collected trajectory data undergoes attitude normalization processing to ensure data comparability under a unified reference coordinate system. Complete trajectory data for a period of time is cached and transmitted to the attitude analysis module 200. The transmitted data includes limb spatial trajectories composed of multi-joint position sequences and attitude angle sequences.

[0072] The attitude analysis module 200 will be further described below in terms of its constituent units.

[0073] Regarding the deviation calculation unit 201, to ensure the comparability of the deviation calculation, the user trajectory and the standard trajectory need to be aligned in time and space. Then, the spatial deviation and angular deviation are calculated between the two to obtain the final deviation.

[0074]

[0075] in, , These are adjustable weight parameters; For the average spatial deviation, N represents the key point, and T represents the time frame. The Euclidean distance between the user's location and the standard location is given, where t is the index of the current time frame. The average angle deviation, , The angle difference between the user and the standard skeleton vector in the current frame is calculated using the cosine formula.

[0076] Therefore, the deviation calculation unit outputs an overall deviation index based on the input limb spatial trajectory.

[0077] Regarding the proficiency mapping unit 202, a supervised learning model is preferably used to learn the mapping relationship between trajectory features and proficiency labels. Specifically, the feature vector of user trajectory deviation is defined as follows: Taking three levels as an example, the proficiency level (target variable) is represented as y∈{0,1,2}, where 0 represents "beginner", 1 represents "intermediate", and 2 represents "advanced".

[0078] Taking the Softmax classification model as an example, the specific model is as follows:

[0079]

[0080] Where k∈{0,1,2} represents three proficiency levels. The score for the linear combination of class k. For the bias term of the k-th category, This is the normalized denominator after taking the exponent for all categories, so that the output is an effective probability.

[0081] The final output is the proficiency level result.

[0082] Regarding the first mode switching unit 203, the training modes include at least a first mode, a second mode, and a third mode with different training speeds. The first mode corresponds to the beginner proficiency level, the second mode is the standard mode corresponding to the intermediate proficiency level, and the third mode corresponds to the advanced proficiency level. Furthermore, the first mode is primarily a coarse guidance mode, with voice prompts for each step; its correction frequency is low, focusing on large movements and main axis alignment. The second mode is a normal guidance mode, with voice prompts only for key steps. The third mode is a fine guidance mode, without voice prompts.

[0083] For example, taking fitness as an example, if the user is identified as being in the first mode, then each action under each step will be equipped with voice prompts to guide the user's operation; if it is the second mode, then there will only be step prompts; if it is the third mode, then there will be no voice prompts.

[0084] When dividing regions, division can be based on the skeletal nodes of the body parts, as shown in the table below:

[0085] Table 1: Regional Division Table

[0086] After region segmentation, each trajectory region is pre-aligned with its corresponding standard template region. Temporal normalization (DTW) or keyframe alignment methods are used to ensure temporal / phase consistency in region error calculation. If the error of a certain region is consistently higher than the threshold, the region is automatically refined into multiple sub-regions. If the error is low, neighboring regions can be merged to improve overall feedback efficiency.

[0087] Regarding error analysis unit 204, the user's limb spatial trajectory after regionalization (from training mode):

[0088]

[0089] Corresponding standard trajectory templates (each region corresponds to a standard trajectory):

[0090]

[0091] Where N is the number of regions (e.g., 6 main parts).

[0092] The spatial trajectory error for each region can be calculated by the mean of the Euclidean distances between aligned trajectory points:

[0093]

[0094] in, This represents the error value for the i-th region; This represents the total number of frames in the trajectory. Let be the key coordinates of the user in region i at time frame t. These are the coordinates corresponding to the standard trajectory.

[0095] To capture attitude differences, an angle error between attitude vectors is introduced:

[0096]

[0097] in, Let be the user's pose vector in the i-th region at time frame t. This corresponds to the standard attitude vector.

[0098] Then the average angle error was calculated. .

[0099] Dynamic Time Warping (DTW) distance is used to handle unaligned sequences:

[0100]

[0101] Final area error value: ;in , , These are weighting coefficients, which can be set through training or expert experience.

[0102] Sort all area errors from largest to smallest:

[0103]

[0104] Simultaneously record the corresponding region index: .

[0105] Regarding decision-making unit 205 for key areas, the importance and degree of error of each area are comprehensively evaluated by combining the error value and regional weight, i.e., the joint scoring function:

[0106]

[0107] in, The spatial contribution weight for the i-th region (obtained through preset or dynamic learning); λ∈[0,1]: weight coefficient; This represents the maximum error value across all regions. This represents the maximum spatial weight value across all regions.

[0108] Select the part with the highest combined score as the key part. Output the key part, its region number, corresponding region error value, comprehensive score, and key prompt information.

[0109] Regarding the augmented reality display module 300, it obtains the key part region index, the user's current limb spatial trajectory data, the corresponding standard posture trajectory, the timing of the corresponding frame at the current moment, the region error value, and the correction suggestion text or image model output by the key part decision unit 205.

[0110] Using a 3D skeleton driving engine, based on the current limb spatial trajectory and the standard trajectory, the following are constructed respectively:

[0111] Real-time user 3D skeleton model and standard reference 3D pose model.

[0112] Based on the differences between the two models in key areas, the magnitude and direction of the error are presented using color coding, heatmaps, or error arrows; the differences are highlighted using methods such as "semi-transparent overlap" or "mirror comparison".

[0113] Correction prompts can be provided through text, icons, animations, or audio / voice prompts. All rendering results are overlaid onto the user's real-world field of view via augmented reality devices. During rendering, different colors are used to distinguish error levels, and vector arrows pointing from the current user position to the standard trajectory position are drawn at key locations; or trajectory residual animations are used to demonstrate the dynamic offset path between the "current action" and the "standard trajectory". Figure 9 Simulation diagrams of different regions of the 3D skeleton model are shown.

[0114] It should be noted that the augmented reality device supports devices including but not limited to: Microsoft HoloLens, Meta Quest, iPad ARKit, and Android ARCore devices; is compatible with mainstream AR SDKs; and supports latency optimization and rendering quality adjustment strategies (such as lightweight pose model compression and resolution adaptation) under different hardware.

[0115] Based on this, the above solution can solve the problem of distraction caused by simultaneous correction of multiple body parts. A key body part selection mechanism focuses the correction target on the body area that has the greatest impact on movement quality, reducing interference from irrelevant information. Dynamic training mode adaptation ensures that the user is always at an appropriate training difficulty level, avoiding over-correction or under-correction. 3D augmented reality feedback helps users intuitively understand the spatial characteristics of movement deviations, improving the accuracy and efficiency of movement imitation.

[0116] The above describes the overall system solution. The system also includes a feedback and interaction module, such as... Figure 2 As shown below, the feedback interaction module will be described in detail.

[0117] The feedback interaction module 400 is used to provide vibration feedback through the interactive device based on the user's limb spatial trajectory under the correction prompts, and to provide feedback to the first mode switching unit based on the user's proficiency during the interaction, so as to recalculate the area error value.

[0118] The feedback interaction module recognizes the user's interaction intent by collecting the user's physiological signals and operational feedback. The interaction device refers to a wearable device with tactile feedback functionality, specifically a smart bracelet or joint strap with an integrated micro-vibration motor, encoding different correction intensities through preset vibration frequencies.

[0119] After receiving the user's latest action trajectory, the system recalculates the trajectory deviation of key parts. If the trajectory deviation of key parts is greater than the error tolerance, the system immediately sends a vibration signal to the interactive device to remind the user that the part has not been corrected.

[0120] Regarding vibration feedback parameter control, vibration feedback can be intensity-coded according to the degree of error, defining the vibration intensity. :

[0121]

[0122] in, This is the scaling factor (sets the maximum vibration value). This is a normalized reference value. This represents the regional error.

[0123] The actual vibration time or frequency can also be encoded, i.e., micro error: short single vibration; medium error: double vibration; severe deviation: continuous vibration until the action is corrected.

[0124] During the training phase, users can subjectively provide feedback on their adaptation to the current training intensity through the following methods:

[0125] Click-based feedback (such as virtual buttons on AR glasses, controllers, and app interfaces):

[0126] Example options:

[0127] "Too difficult", "Just right", "Too easy".

[0128] Voice recognition feedback:

[0129] Example statements: "I think this set of movements is okay" / "This is too difficult".

[0130] The system sends subjective feedback values ​​to the first mode switching unit 203 to correct the proficiency level assigned by the system. The subjective feedback values ​​are combined with the error trend value of the current action to re-correct the score, which is used for iterative adjustment of the feedback mechanism. The corrected error will update the area ranking, prompting the re-evaluation and re-ranking of key parts.

[0131] For example, a 5 cm error in the shoulder joint area triggers continuous vibration, while a 3 cm error in the waist area triggers a short, single vibration. After sensing the vibration, the user provides feedback on their self-assessed proficiency level for the currently trained area via voice commands or gestures. This feedback data, along with the area error value automatically calculated by the system, is input into the first mode switching unit. When the difference between the two exceeds a preset threshold, a recalculation of the training mode is triggered. For instance, if the user self-assesses their shoulder proficiency as intermediate while the system calculates an error value corresponding to beginner, the area error value is recalculated to generate a new priority list for key areas.

[0132] This solution establishes a cross-validation mechanism between user subjective assessment and system objective calculation. When a significant deviation occurs between the two, the training mode parameters are automatically optimized to ensure the accuracy of key part identification. This dynamic adjustment mechanism allows the training process to adapt to changes in the user's actual ability in real time, avoiding ineffective training cycles caused by fixed modes.

[0133] The above provides a detailed introduction to the feedback interaction module 400, such as... Figure 3 and Figure 4 As shown, the verification unit 206, which is also included in the attitude analysis module 200, will be described in detail below. The verification unit 206 includes:

[0134] The key part proficiency determination subunit 2061 is used to obtain the deviation between the user's limb spatial trajectory of the key parts under the correction prompts and the standard trajectory calculated by the edge computing device after the feedback interaction module learns the proficiency given by the user, and then determine the corresponding proficiency.

[0135] The proficiency judgment subunit 2062 is used to determine whether the proficiency determined by the key part proficiency determination subunit is consistent with the proficiency reported by the user.

[0136] The proficiency decision subunit 2063 is used to determine the actual proficiency based on the confidence level when the judgment results are inconsistent, and to feed back the actual proficiency to the first mode switching unit, while providing prompts to the user through the augmented reality display module.

[0137] The role of the verification unit is to obtain the deviation of key parts from the edge computing device after the feedback interaction module 400 collects the user's subjective proficiency feedback, and determine the objective proficiency level according to the established proficiency mapping model.

[0138] The system receives subjective proficiency levels and compares them with objective judgments to determine if they match. If they do not match, a decision is made.

[0139] Let the proficiency level be represented numerically:

[0140] "Advanced Proficiency" = 2;

[0141] "Intermediate Proficiency" = 1;

[0142] "Beginner proficiency" = 0.

[0143] The fusion score is as follows:

[0144]

[0145] in, This indicates subjective confidence (which can be appropriately increased if the user has a long training history or stable historical performance). Indicates objective confidence level (e.g., stable edge computing environment and sufficient sensor data); Indicates subjective proficiency; It indicates an objective judgment result.

[0146] The fusion result is then mapped to a proficiency level:

[0147] 2 → "Advanced Proficiency";

[0148] 1 → "Intermediate Proficiency";

[0149] 0 → "Beginner Proficient".

[0150] This solution can automatically identify the discrepancy between user self-assessment and system-calculated proficiency, generating accurate proficiency judgments through a credibility-weighted decision-making mechanism. For example, in dance teaching applications, it can accurately identify cognitive biases in students' mastery of specific movements, provide targeted reinforcement training for error-prone areas, and help students establish correct movement perceptions through visual comparison prompts.

[0151] The verification unit 206 has been described in detail above, such as Figure 5 and Figure 6 As shown below, the second mode switching unit, which is also included in the attitude analysis module 200, will be described in detail. The second mode switching unit 207 includes:

[0152] The instruction acquisition subunit 2071 is used to receive the mode switching instruction given by the target object collected by the feedback interaction module during the interaction process;

[0153] The instruction judgment subunit 2072 is used to determine whether the mode switching instruction is a switch from single-player mode to team mode.

[0154] The instruction decision subunit 2073 is used to make the following decision based on the judgment result:

[0155] (1) If the determination is yes, then based on the user's key physical characteristics and the pre-established character model, virtual objects in different proficiency states are generated through deep learning and displayed through the augmented reality display module. When the user starts training, the virtual objects synchronously display the training status.

[0156] (2) If the determination is negative, the augmented reality display module will only display the user's posture comparison with the standard trajectory.

[0157] The instruction acquisition subunit 2071 listens in real time to voice commands, gesture commands, or touch commands issued by the user through the feedback interaction module 400; the command forms include, but are not limited to:

[0158] Voice message: "Switch to team mode";

[0159] Gestures: Specify training actions for multiple people (such as making the "cooperation" gesture);

[0160] UI Operation: Click the "Multi-person Training" button.

[0161] Instruction decision subunit 2073 executes two types of strategies based on the judgment result:

[0162] (1) Team mode

[0163] The user's (target's) proficiency level, body movement characteristics, and posture stability are obtained as personalized tag features and represented as vectors.

[0164] A character template library is built based on training data. A matching group of virtual training characters is generated through deep learning (such as Transformer or GAN). The character template library contains M virtual characters, each of which is defined as a feature vector. The weighted Euclidean distance is used to measure the similarity between the current user's feature vector and the feature vector of the virtual character template, and the best matching character is obtained.

[0165] Each virtual character has different settings:

[0166] Proficiency level (Beginner / Intermediate / Advanced).

[0167] The augmented reality display module 300 maps the virtual objects into the user's field of vision, allowing the user to intuitively perceive the rhythm and posture of the virtual characters' movements, creating an immersive contrast environment. Multiple characters can be displayed side by side or around each other, improving feedback accuracy and interactive experience.

[0168] (2) If it is not a team mode request (such as returning to single training), send a “cancel collaborative training” instruction to the augmented reality display module 300; clear the virtual character display and only retain the posture comparison screen between the user and the standard trajectory.

[0169] This solution enables intelligent switching between training scenarios and dynamic adjustment of the virtual-real integration level. In team mode, by generating virtual objects with skill gradients, it solves the problem of insufficient immersion caused by the lack of real interactive objects in traditional systems. In single-player mode, by simplifying the displayed content, it avoids redundant information from distracting the user's attention. The intelligent switching between the two modes allows the same system to adapt to the needs of multiple scenarios, including individual training and team collaboration, thus improving the environmental adaptability of the training system.

[0170] The second mode switching unit 207 has been described in detail above. The feedback adjustment module 500, which is also included in the system, will be described in detail below. Figure 7 and Figure 8 As shown, the feedback adjustment module 500 includes:

[0171] The requirement acquisition unit 501 is used to acquire the training mode requirements fed back by the user through the feedback interaction module;

[0172] The deviation determination unit 502 is used to retrieve the deviation calculated by the deviation calculation unit and determine whether the deviation exceeds the deviation required by the training mode.

[0173] The mode determination unit 503 is used to prioritize the user's feedback training mode requirement and feed it back to the first mode switching unit if the determination result is negative; if the determination result is positive, the training mode determined by the first mode switching unit is prioritized and fed back to the user through the augmented reality display module.

[0174] For example, when a user selects "Mode 3 (Advanced)," the system first retrieves the maximum allowable deviation threshold for that mode (e.g., joint angle deviation not exceeding 3 degrees). Real-time monitoring reveals that the user's current waist rotation angle deviation reaches 5 degrees, exceeding the preset threshold. At this point, the mode determination unit automatically switches to the system-recommended "Mode 2 (Standard)," and displays a message on the augmented reality interface: "Insufficient stability detected in the current movement; you have been switched to the appropriate training mode." As another example, if a user selects "Mode 2" and the measured deviation value (e.g., arm extension deviation of 2cm) is lower than the mode's allowable threshold (e.g., 3cm), the system will maintain the user's selected mode and record their training preference.

[0175] This solution can resolve training conflicts caused by the mismatch between users' subjective needs and objective abilities. For example, in yoga training, when a user overestimates their flexibility and chooses advanced poses, the system can detect joint overextension in a timely manner and switch to a suitable beginner pose, thus avoiding sports injuries and maintaining training continuity. Or, in rehabilitation training, when a patient conservatively chooses a low-intensity mode but actually recovers well, the system maintains the patient's choice while recording progress data, providing a basis for subsequent mode upgrades.

[0176] The feedback adjustment module 500 has been described in detail above. The correction prompt unit 208 of the attitude analysis module 200 will be described in detail below.

[0177] Before displaying correction prompts, the augmented reality display module obtains correction prompts for key parts through the correction prompt unit of the posture analysis module. The correction prompt unit is used to obtain the user's current training target, use the current training target as a conditional code to match the error correction model with the highest relevance in the error correction model library, and input the regional error value of the area where the key part is located into the error correction model to obtain the corresponding correction prompt.

[0178] Specifically, conditional coding refers to the process of transforming the current training objective into multi-dimensional vector parameters. This can be achieved by using natural language processing techniques to semantically encode the training requirement text input by the user, or by generating corresponding numerical encoding vectors through preset training objective classification labels.

[0179] An error correction model library refers to a database that stores error correction strategies corresponding to different training objectives. It can be a set of decision tree models built on an expert knowledge base, or a group of neural network models trained by machine learning. For example, clustering algorithms can be used to classify and manage historical successful correction cases.

[0180] The training objective is encoded as a conditional vector. This serves as a selection criterion for the error correction model. Each model in the error correction model library... Having an associated condition vector Using cosine similarity or vector distance pairs With each Perform a match:

[0181]

[0182] Select the model corresponding to the highest score.

[0183] The regional error value of the key part is obtained from the error analysis unit 204, and its vector is input into the matched model. The model output includes the following fields:

[0184] Adjust the direction (e.g., "lift up", "retract");

[0185] Suggested range (e.g., "raise it by 5°");

[0186] Precautionary text (e.g., "Keep your torso stable").

[0187] Compare the correction prompts with the coordinate data of key parts and the standard trajectory. Figure 1 It is then encapsulated and transmitted to the augmented reality display module 300 for rendering and presentation in an augmented reality format within the user's field of vision.

[0188] For example, a user's training objective is "stability priority." This objective is transformed into a conditional encoding vector, and the system matches the error correction model with the highest cosine similarity to the encoded vector in the error correction model library. Subsequently, the posture analysis module inputs the region error values ​​calculated for key areas (e.g., the waist region) into the model. Based on the error distribution characteristics, the model outputs visual cues for adjusting the force angle of the core muscles in the waist. The resulting correction cues focus only on the most relevant key areas in the current training phase, avoiding the simultaneous display of error information from multiple non-key areas. Furthermore, by matching appropriate error correction models through conditional encoding, the system overcomes the limitations of single-strategy error correction, addressing the practical need for different correction methods for the same incorrect movement under different training objectives.

[0189] This solution uses a training objective-oriented model matching mechanism to dynamically select key error information most relevant to the current training stage for prompting. Simultaneously, based on quantified input of regional error values, it ensures that the generated correction prompts accurately match the degree of deviation in the user's actual movements, avoiding over- or under-adjustment of movements due to overly general prompts, and effectively shortening the posture correction cycle.

[0190] To facilitate understanding of the above embodiments, specific application scenarios of the above embodiments will be described below:

[0191] Scene 1

[0192] The user is a beginner, and the training program is classical dance "hand position training".

[0193] Standard movement: Slowly raise your right arm from your side to a horizontal position, with a slight bend in the elbow, a light flick of the wrist, and a relaxed shoulder.

[0194] Current training objective: To imitate standard movements and correct their trajectory.

[0195] The system uses motion capture equipment (such as IMU + camera fusion) to collect the user's right arm 3D trajectory, sampling a total of 100 frames. Each frame contains the spatial coordinates of the right shoulder (P1), right elbow (P2), and right wrist (P3), in centimeters.

[0196] In the calculation of frame 30: the spatial coordinates are as follows:

[0197] Table 2: Comparison of User Location and Standard Location

[0198] Attitude vector (elbow → wrist):

[0199] User vector: (7.0, 2.0, 2.0);

[0200] Standard vector: (7.5, 1.5, 1.5).

[0201] The Euclidean distances between the three points are as follows: Take the average. .

[0202] To calculate the attitude angle deviation, first calculate the inner product:

[0203] ;

[0204] Calculate the modulus again: ;

[0205] .

[0206] Calculate the included angle: .

[0207] therefore: .

[0208] Set weighting factors: =0.6, =0.4.

[0209] =0.6⋅0.77+0.4⋅5.74≈0.462+2.296=2.758.

[0210] According to the predefined criteria: an average deviation of 0-2.0 corresponds to advanced proficiency, 2.0-4.0 corresponds to intermediate proficiency, and 4.0-6.0 corresponds to basic proficiency.

[0211] Once the user's proficiency level is determined to be intermediate, training will then be conducted in the corresponding training mode.

[0212] Divide the area according to the right arm:

[0213] Area A: shoulder-elbow;

[0214] Area B: elbow-wrist.

[0215] Calculate the area error:

[0216] Area A: Average error value between shoulder and elbow = 2.5cm;

[0217] Region B: Average error value between elbow and wrist = 4.8cm.

[0218] Sorting result: Region B (preferred) > Region A.

[0219] Calculate joint score Taking 0.6, the calculated joint score of region A is 1.66, which is lower than the joint score of region B, which is 3.2.

[0220] Therefore, region B was identified as the critical area.

[0221] In the augmented reality module, the system retrieves the error correction model to generate prompts:

[0222] "If the wrist angle is insufficient, please gently raise your wrist to approximately 12° and hold for 3 seconds."

[0223] The user subjectively reports "proficiency has improved," and the system confirms that the proficiency has improved to "intermediate proficiency," then proceeds to the next level of training.

[0224] Scene 2

[0225] Patients at a rehabilitation center need gait correction training after hip surgery, with the goal of restoring natural stride length and center of gravity stability.

[0226] The motion capture device collects the patient's lower limb trajectory and stride rhythm during walking; the deviation calculation unit compares the deviation with the preoperative standard gait template.

[0227] The proficiency mapping unit determines that the current stage is "beginner proficiency" and switches to "first mode" (assisted walking) from the first mode switching unit.

[0228] The error analysis unit divides the trajectory into three regions based on the leg: "ankle-knee-hip," and prioritizes the "hip control region" as the primary area for improvement.

[0229] The decision-making unit for key parts designates it as a key part and prepares corrective prompts.

[0230] The augmented reality module displays a real-time comparison of the current gait and the skeletal model of a standard gait within the AR glasses worn by the patient, and provides prompts. The interactive device emits a slight vibration to alert the patient when there is insufficient push-off.

[0231] When a patient subjectively reports that their movements are "too exaggerated," the feedback interaction module records the feedback and transmits it to the verification unit.

[0232] The verification unit found that the actual error had decreased and determined that "the feedback was effective and the progress of proficiency was stable";

[0233] If the feedback adjustment module analyzes the patient's gait deviation and finds it to be below the selected rehabilitation plan target, then the patient is allowed to proceed to the next training level; otherwise, the current pace is maintained.

[0234] like Figure 10 As shown, if the user's leg lifts below the standard trajectory, a prompt will appear to lift the leg upwards. Figure 10 As shown in the first image, if the user's trajectory matches the standard trajectory, it will display something similar. Figure 10 The second image shows that if the user raises their leg above the standard trajectory, a prompt will appear to lower it. Figure 10 As shown in the third image.

[0235] In summary, this embodiment solves the problem of unclear correction priorities in traditional systems by dividing the limb spatial trajectory area and calculating the area error value, combining the importance analysis of the parts to determine the key parts to be corrected first, and finally using augmented reality devices to intuitively display posture comparison and correction prompts, thereby improving the efficiency and accuracy of posture correction.

[0236] Example 2

[0237] like Figure 11 This embodiment illustrates a method for real-time monitoring and correction of motion posture for augmented reality, including the following steps:

[0238] S601. Obtain the user's limb spatial trajectory in standard mode from the motion capture device;

[0239] S602. Calculate the deviation between the limb spatial trajectory and the preset standard trajectory;

[0240] S603. Determine the user's proficiency level based on the mapping relationship between trajectory deviation and proficiency;

[0241] S604. Switch to the matching training mode according to the proficiency level, and then divide the user's limb spatial trajectory in the training mode into multiple areas according to the body parts;

[0242] S605. Calculate the regional error value between the limb spatial trajectory of each region and its corresponding standard trajectory, and sort them in descending order;

[0243] S606. Based on the sorting results, analyze the importance of each part of the corresponding region in the entire limb spatial trajectory, and determine the key parts to be corrected first by combining the regional error values;

[0244] S607. Display the posture comparison between key parts and standard trajectory using augmented reality devices, and display correction prompts.

[0245] This solution uses a processor as the execution entity, which avoids the distraction caused by simultaneous reminders for multiple body parts, shortens the overall correction cycle, and improves the efficiency of exercise training and rehabilitation therapy.

[0246] Example 3

[0247] like Figure 12 As shown in the figure, this embodiment introduces a method for real-time monitoring and correction of motion posture for augmented reality, including the following steps:

[0248] S701. Responding to the system's correction prompts, obtain the user's key body parts from the system, and then obtain the limb spatial trajectory of the key body parts from the motion capture device;

[0249] S702. Retrieve the standard trajectory corresponding to the key parts from the system and calculate the deviation between the limb spatial trajectory and the standard trajectory;

[0250] S703. Feedback the deviation to the system until a stop correction command is received from the system.

[0251] This solution uses edge computing as the execution subject and has the same beneficial effects as Example 2.

[0252] Example 4

[0253] This embodiment describes a real-time motion posture monitoring and correction device for augmented reality, including a motion capture device, a processor, an interactive device, an augmented reality device, and an edge computing device.

[0254] Motion capture devices are installed on various parts of the user's body to collect the user's spatial trajectories;

[0255] The processor is used to receive the spatial trajectory of the limbs collected by the motion capture device, and generate a comparison of the user's posture with the standard trajectory and correction prompts.

[0256] The interactive device is embedded in the motion capture device to receive instructions from the processor and provide vibration feedback to the user, while also receiving feedback information from the user.

[0257] Augmented reality devices are worn on the user's head to display gesture comparisons and correction prompts generated by the processor;

[0258] Edge computing devices are used to receive correction prompts from the processor and calculate the deviation of the user's limb spatial trajectory from the standard trajectory for key body parts;

[0259] When the processor is working, it executes the steps of the real-time motion posture monitoring and correction method for augmented reality as described in Example 2; when the edge computing device is working, it executes the steps of the real-time motion posture monitoring and correction method for augmented reality as described in Example 3.

[0260] Motion capture equipment refers to a device that collects three-dimensional spatial motion data through an inertial measurement unit and a camera. Specifically, it can be implemented using a wearable node integrating a nine-axis sensor to acquire the three-dimensional motion trajectory of the user's joints in real time. For example... Figure 13 As shown, the performance of the motion capture device used in this embodiment is verified in a Matlab simulation environment using real image sequences. The system tracking device consists of a camera and an inertial sensor. The inertial sensor and camera are mounted together, and their relative spatial positions have been precisely calibrated. In the translational state, the results are as follows... Figure 13 As shown in the figure, it can be seen that the motion capture device using this embodiment can obtain smoother motion estimation results.

[0261] The processor refers to the computing unit that runs the trajectory comparison algorithm and pattern decision logic. Specifically, it can be implemented using a multi-core CPU and GPU collaborative architecture to transform raw trajectory data into an operable correction strategy. The interactive device refers to an embedded module with haptic feedback and input functions. Specifically, it can be implemented using a combination of a linear motor and a pressure sensor to trigger physical prompts and collect subjective user feedback during key correction stages.

[0262] Augmented reality devices refer to display terminals that support 3D spatial rendering, specifically binocular perspective-based head-mounted displays, used to transform abstract trajectory differences into visual guidance overlaid on the real field of vision. The logic of visual guidance is as follows: Figure 14 As shown. Edge computing devices refer to dedicated computing modules deployed near the user end, which can be implemented using FPGA chips, and are used to quickly process data in critical areas locally to reduce the latency of the main system.

[0263] This embodiment has the same beneficial effects as Embodiment 2.

[0264] Example 5

[0265] This embodiment introduces a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the real-time motion posture monitoring and correction method for augmented reality as described in Embodiment 2.

[0266] The real-time motion posture monitoring and correction method for augmented reality described in Example 2 can be applied in software form, such as by designing it as a standalone program and installing it on a computer device, which can be a computer, smartphone, or similar device. Alternatively, it can be designed as an embedded program and installed on a computer terminal, such as a microcontroller.

[0267] The technical scope of this invention is not limited to the content described above. Those skilled in the art can make various modifications and variations to the above embodiments without departing from the technical concept of this invention, and all such modifications and variations should fall within the protection scope of this invention.

Claims

1. A motion posture real-time monitoring correction system for augmented reality, characterized in that, It comprises: a data acquisition module for acquiring the limb space trajectory of a user in a standard mode from a motion capture device; a posture analysis module comprising: a deviation calculation unit for calculating the deviation of the limb space trajectory from a preset standard trajectory; a proficiency mapping unit for determining the proficiency level of the user based on the trajectory deviation and a proficiency mapping relationship; a first mode switching unit for switching to a matched training mode according to the proficiency level, and then dividing the limb space trajectory of the user in the training mode into multiple regions according to the parts; an error analysis unit for calculating the regional error value of the limb space trajectory of each region and its corresponding standard trajectory, and sorting in descending order; a key part decision unit for analyzing the importance of the corresponding region of the part in the entire limb space trajectory based on the sorting result, and determining the key part to be corrected in priority based on the regional error value; an augmented reality display module for displaying the posture comparison of the key part and the standard trajectory through an augmented reality device, and displaying a correction prompt.

2. The motion posture real-time monitoring correction system for augmented reality according to claim 1, characterized in that, The motion posture real-time monitoring and correction system for augmented reality further comprises a feedback interaction module for giving vibration feedback through an interactive device according to the limb space trajectory of the user under the correction prompt, and feeding back the proficiency level of the user to the first mode switching unit based on the interactive process, so as to recalculate the regional error value.

3. The motion posture real-time monitoring correction system for augmented reality according to claim 2, characterized in that, The posture analysis module further comprises a verification unit, which comprises: a key part proficiency determination subunit for acquiring the deviation of the limb space trajectory of the key part of the user under the correction prompt from the standard trajectory calculated by the edge computing device after the feedback interaction module learns the proficiency level given by the user, and then determining the corresponding proficiency level; a proficiency judgment subunit for judging whether the proficiency level determined by the key part proficiency determination subunit is consistent with the proficiency level fed back by the user; a proficiency decision subunit for determining the actual proficiency level according to the confidence level when the judgment result is inconsistent, and feeding back the actual proficiency level to the first mode switching unit, and giving a prompt to the user through the augmented reality display module.

4. The motion posture real-time monitoring correction system for augmented reality according to claim 2, wherein, The posture analysis module further comprises a second mode switching unit, which comprises: an instruction acquisition subunit for receiving the mode switching instruction given by the target object collected by the feedback interaction module in the interactive process; an instruction judgment subunit for judging whether the mode switching instruction is a single-person mode switching to a team mode; an instruction decision subunit for making the following decisions according to the judgment result: (1) if the judgment result is yes, generating a virtual object in different proficiency states based on the key signs of the user and a pre-established character model through deep learning, and displaying the virtual object through the augmented reality display module, and synchronously displaying the training state of the virtual object when the user starts training; (2) if the judgment result is no, feeding back to the augmented reality display module to display only the posture comparison of the user and the standard trajectory.

5. The motion posture real-time monitoring correction system for augmented reality according to claim 2, wherein, The motion posture real-time monitoring and correction system for augmented reality further comprises a feedback adjustment module, which comprises: a demand acquisition unit for acquiring the training mode demand of the user fed back through the feedback interaction module; The bias determination unit is configured to call the bias calculated by the bias calculation unit, and determine whether the bias exceeds the bias corresponding to the training mode requirement; The mode determination unit is configured to, if the determination result is no, take the training mode requirement fed back by the user as the priority and feed back to the first mode switching unit; if the determination result is yes, take the training mode determined by the first mode switching unit as the priority and feed back to the user through the augmented reality display module.

6. The motion posture real-time monitoring correction system for augmented reality according to claim 1, wherein, The augmented reality display module acquires the correction prompt of the key part through the correction prompt unit of the posture analysis module before displaying the correction prompt; the correction prompt unit is configured to acquire the current training target of the user, encode the current training target as a condition, match the highest relevant error correction model in the error correction model library, and input the area error value of the region where the key part is located into the error correction model to obtain the corresponding correction prompt.

7. The method for real-time monitoring and correction of motion posture for augmented reality, applied to the system for real-time monitoring and correction of motion posture for augmented reality according to any one of claims 1-6, characterized in that, The motion posture real-time monitoring and correction method for augmented reality includes the following steps: Obtain the limb space trajectory of the user in the standard mode from the motion capture device; Calculate the bias of the limb space trajectory and the preset standard trajectory; Determine the proficiency level of the user based on the mapping relationship between the trajectory bias and the proficiency; Switch to the matched training mode according to the proficiency level, and then divide the limb space trajectory of the user in the training mode into multiple regions according to the part; Calculate the area error value of the limb space trajectory of each region and the corresponding standard trajectory, and sort them in descending order; Based on the sorting result, analyze the importance of the part of the corresponding region in the entire limb space trajectory one by one, and determine the key part to be corrected jointly based on the area error value; Display the posture comparison of the key part and the standard trajectory through the augmented reality device, and display the correction prompt.

8. The method for real-time monitoring and correction of motion posture for augmented reality, applied to the system for real-time monitoring and correction of motion posture for augmented reality according to any one of claims 1-6, characterized in that, The motion posture real-time monitoring and correction method for augmented reality includes the following steps: In response to the correction prompt of the system, obtain the key part of the user from the system, and then obtain the limb space trajectory of the key part from the motion capture device; Call the standard trajectory corresponding to the key part from the system, and calculate the bias of the limb space trajectory of the key part and the standard trajectory; Feed back the bias to the system until the stop correction instruction is received.

9. A motion posture real-time monitoring and correction device for augmented reality, comprising: A motion capture device mounted on each part of the user for collecting the limb space trajectory of the user; A processor for receiving the limb space trajectory collected by the motion capture device, and generating the posture comparison of the user and the standard trajectory and the correction prompt; An interactive device embedded in the motion capture device for receiving the instruction of the processor and giving the user a vibration feedback, and receiving the feedback information of the user; An augmented reality device worn on the head of the user for displaying the posture comparison and the correction prompt generated by the processor; An edge computing device for receiving the correction prompt of the processor and calculating the bias of the limb space trajectory of the key part of the user and the standard trajectory. The processor executes the steps of the motion posture real-time monitoring correction method for augmented reality as claimed in claim 7. 10.A computer device, comprising a memory and a processor, the memory storing a computer program, and the computer device is characterized in that, The processor executes the steps of the motion posture real-time monitoring correction method for augmented reality as claimed in claim 7.

Images