Virtual reality sports training method, device, equipment and storage medium

Abstract

The application discloses a virtual reality sports training method and device, equipment and storage medium, the method comprises the following steps: collecting the training action of a user, and synchronously mapping the training action to a virtual user in a virtual space; based on a preset standard action library, action recognition is performed on the mapping action mapped to the virtual user to obtain a basic action of the mapping action; based on the standard action library, the basic action is judged to obtain a judgment conclusion to correct the training action of the user. The application identifies the basic action from the mapping action through the preset standard action library, judges the basic action according to the standard action in the standard action library, and corrects the training action of the user according to the judgment conclusion, so that the basic action in the mapping action is separated and corrected, and the intelligence of virtual reality is improved.

Description

Technical Field

[0001] This application relates to the field of virtual reality, and more particularly to a virtual reality exercise training method, device, equipment, and storage medium. Background Technology

[0002] With the continuous development of social productivity and science and technology, the demand for virtual reality technology is growing stronger in all walks of life.

[0003] Because virtual reality (VR) technology can more intuitively simulate a user's movements in real time and provide feedback to the user so that they can correct non-standard movements, it is increasingly being used in sports training. Users can pre-record standard training videos, and after the user completes the training, the system can provide training suggestions by comparing the user's movements with the standard videos. However, since each user has their own habitual movements, VR technology cannot recognize these habitual movements and thus defines them as non-standard movements, thereby reducing the intelligence of VR. Summary of the Invention

[0004] The main purpose of this application is to provide a virtual reality sports training method, device, equipment and storage medium, which aims to solve the technical problem that the existing virtual reality technology cannot recognize the user's habitual movements, thus reducing the intelligence of virtual reality.

[0005] To achieve the above objectives, this application provides a virtual reality exercise training method, the virtual reality exercise training method comprising:

[0006] Collect users' training actions and synchronously map the training actions to virtual users in the virtual space;

[0007] Based on a preset standard action library, the mapping actions mapped to the virtual user are identified to obtain the basic actions of the mapping actions.

[0008] Based on the standard action library, the basic actions are evaluated to obtain an evaluation conclusion, which is used to correct the user's training actions.

[0009] Optionally, the step of evaluating the basic movements based on the standard movement library to obtain an evaluation conclusion includes:

[0010] Match the standard action corresponding to the basic action from the standard action library;

[0011] The basic movements are analyzed and compared with the standard movements to identify the non-standard movements in the basic movements.

[0012] The non-standard actions are evaluated to obtain a judgment conclusion that the standard actions should be corrected.

[0013] Optionally, the step of performing corresponding motion analysis on the basic motion and comparing it with the standard motion to determine the non-standard motions in the basic motion includes:

[0014] The basic movements are analyzed to determine the analytical movement groups of the basic movements;

[0015] The parsed action group and the standard action are synchronized through action path processing to identify non-standard actions in the parsed action group that cannot be synchronized with the standard action.

[0016] Optionally, the step of performing action recognition on the mapped actions mapped to the virtual user based on a preset standard action library to obtain the basic actions of the mapped actions includes:

[0017] The mapped action is decomposed to obtain the constituent actions of the mapped action;

[0018] The actions selected from the constituent actions, those contained in the standard action library, are the basic actions in the mapped actions.

[0019] Optionally, historical sports training records may be collected;

[0020] Before the step of performing action recognition on the mapped actions mapped to the virtual user based on a preset standard action library to obtain the basic actions of the mapped actions, the method includes:

[0021] Select custom movements that are not present in the standard movement library from the historical exercise training records;

[0022] Analyze the frequency of use of the custom actions;

[0023] If the usage frequency is higher than the preset base frequency, the custom action is standardized and updated to the standard action library.

[0024] Optionally, the virtual reality motion training method further includes:

[0025] The mapped action is decomposed in real time to determine the decomposed actions in the mapped action;

[0026] A hazard assessment is performed on the connection between two adjacent decomposition actions to obtain the hazard factors of the connection between the two adjacent decomposition actions.

[0027] Determine protective recommendations for the aforementioned risk factors to prompt the user to take safety precautions.

[0028] Optionally, the step of determining protective recommendations for the hazard factors includes:

[0029] Determine the hazard coefficient of the aforementioned risk factor;

[0030] If the risk factor triggers the safety factor of the preset recommended replacement action, then the replacement action with a risk factor less than the safety factor is obtained from the historical action record;

[0031] By connecting the replacement action and the decomposition action, a coherent suggested action is obtained;

[0032] The protection recommendations include suggested actions.

[0033] This application also provides a virtual reality sports training device, the virtual reality sports training device comprising:

[0034] The acquisition module is used to acquire the user's training actions and synchronously map the training actions to the virtual user in the virtual space;

[0035] The recognition module is used to perform action recognition on the mapped actions mapped to the virtual user based on a preset standard action library, so as to obtain the basic actions of the mapped actions.

[0036] The evaluation module is used to evaluate the basic movements based on the standard movement library, obtain evaluation conclusions, and correct the user's training movements.

[0037] Optionally, the evaluation module includes:

[0038] The matching module is used to match the standard action corresponding to the basic action from the standard action library;

[0039] The parsing module is used to perform corresponding action parsing on the basic action, and then compare it with the standard action to determine the non-standard actions in the basic action;

[0040] The evaluation submodule is used to evaluate the non-standard actions and obtain an evaluation conclusion to correct the standard actions.

[0041] Optionally, the parsing module includes:

[0042] The parsing submodule is used to perform action parsing on the basic action and determine the parsed action group of the basic action;

[0043] The synchronization module is used to perform action path synchronization processing on the parsed action group and the standard action, and to identify non-standard actions in the parsed action group that cannot be synchronized with the standard action.

[0044] Optionally, the identification module includes:

[0045] The decomposition module is used to decompose the mapped action into action components to obtain the mapping action.

[0046] The filtering module is used to filter out the actions contained in the standard action library from the constituent actions, which are the basic actions in the mapped actions.

[0047] Optionally, historical sports training records may be collected;

[0048] The virtual reality sports training device also includes:

[0049] The filtering module is used to select custom movements that do not exist in the standard movement library from the historical exercise training records;

[0050] The analysis module is used to analyze the frequency of use of the custom action;

[0051] The standard processing module is used to standardize the custom action and update the custom action to the standard action library if the usage frequency is higher than the preset base frequency.

[0052] Optionally, the virtual reality motion training device further includes:

[0053] The second decomposition module is used to perform real-time action decomposition on the mapped action and determine the decomposed actions in the mapped action.

[0054] The determination module is used to determine the danger of the connection between two adjacent decomposition actions and obtain the danger factors of the connection between the two adjacent decomposition actions.

[0055] The prompting module is used to determine protective recommendations for the aforementioned hazardous factors, so as to prompt the user to take safety precautions.

[0056] Optionally, the prompting module includes:

[0057] The determination module is used to determine the hazard coefficient of the hazard factor;

[0058] The triggering module is used to obtain a replacement action from the historical action record where the risk factor is less than the safety factor if the risk factor triggers the safety factor of the preset recommended replacement action.

[0059] A connection module is used to connect the replacement action and the decomposition action to obtain a coherent suggested action;

[0060] The protection recommendations include suggested actions.

[0061] This application also provides a virtual reality sports training device, which is a physical node device. The virtual reality sports training device includes: a memory, a processor, and a program of the virtual reality sports training method stored in the memory and executable on the processor. When the program of the virtual reality sports training method is executed by the processor, it can implement the steps of the virtual reality sports training method as described above.

[0062] This application also provides a storage medium storing a program for implementing the above-described virtual reality motion training method. When the program for the virtual reality motion training method is executed by a processor, it implements the steps of the virtual reality motion training method as described above.

[0063] This application provides a virtual reality (VR) motion training method, apparatus, device, and storage medium. Compared with existing VR technologies that cannot recognize users' habitual movements, thus reducing the intelligence of VR, this application collects users' training movements and synchronously maps these movements onto a virtual user in a virtual space. Based on a preset standard movement library, the mapped movements onto the virtual user are identified to obtain the basic movements of the mapped movements. Based on the standard movement library, the basic movements are evaluated to obtain an evaluation conclusion, thereby correcting the user's training movements. In this application, the user's training movements are mapped onto a virtual user in a virtual space. According to the preset standard movement library, the basic movements in the mapped movements are identified, and then the basic movements are evaluated using the standard movement library to correct the user's training movements. That is, in this application, the basic movements are identified from the mapped movements using a preset standard movement library, and the basic movements are evaluated according to the standard movements in the standard movement library, so that the user can correct their training movements based on the evaluation conclusion. Therefore, the basic movements in the mapped movements are separated and corrected, improving the intelligence of VR. Attached Figure Description

[0064] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0065] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0066] Figure 1 This is a flowchart illustrating the first embodiment of the virtual reality sports training method of this application;

[0067] Figure 2 This is a flowchart illustrating the third embodiment of the virtual reality sports training method of this application;

[0068] Figure 3 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application;

[0069] Figure 4 This is a schematic diagram of the device involved in the embodiments of this application.

[0070] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0071] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0072] This application provides a virtual reality sports training method. In the first embodiment of the virtual reality sports training method of this application, refer to... Figure 1 The virtual reality motion training method includes:

[0073] Step S10: Collect the user's training actions and synchronously map the training actions to the virtual user in the virtual space;

[0074] Step S20: Based on a preset standard action library, perform action recognition on the mapped actions mapped to the virtual user to obtain the basic actions of the mapped actions;

[0075] Step S30: Based on the standard action library, the basic actions are evaluated to obtain an evaluation conclusion, so as to correct the user's training actions.

[0076] This embodiment aims to improve the intelligence of virtual reality technology in sports training.

[0077] In this embodiment, it should be noted that the virtual reality sports training method can be applied to a virtual reality sports training device, which is subordinate to a virtual reality sports training equipment, and the virtual reality sports training equipment is a virtual reality sports training system.

[0078] In this embodiment, as Figure 4 As shown, virtual reality sports training devices include motion capture devices, virtual simulators, and synchronization mappers.

[0079] The motion capture device can be an optical device, a wearable device, or something similar; there are no specific limitations.

[0080] Among them, the virtual simulator can project virtual users in a virtual space and map the user's training actions in the virtual simulator.

[0081] The standard action library is set up in the virtual simulator, which can collect the training actions of the user each time and organize the training actions.

[0082] It should be noted that the standard action library can be iteratively updated in real time based on the frequency of use of user-defined actions, and the standard action library is divided into a basic action area and a custom action area. This avoids using automaton actions as basic actions for evaluation.

[0083] It should be noted that the virtual simulator can also be connected to a monitor, allowing users to watch the mapped actions of their corresponding virtual user in real time. Users can also sensorily merge with the virtual user, making them truly believe that they are the virtual user, thus giving them an immersive feeling in the virtual space built by the virtual simulator and enhancing their experience.

[0084] In this embodiment, a specific application scenario may be:

[0085] During training, since instructors cannot observe whether each athlete's movements are standard in a timely manner, virtual reality technology may be used to record and correct the athletes' training. However, athletes may have their own habitual movements. Existing virtual reality technology cannot distinguish between basic movements and habitual movements. It may treat habitual movements as basic movements and make judgments to correct habitual movements. Therefore, the application of virtual reality technology in sports training has low intelligence.

[0086] Alternatively, when dancers or students practice daily, they need to standardize the basic movement paths. Virtual reality technology can compare the basic dance movements with the user's practice movements to point out deficiencies. However, dancers often extend their own custom movements beyond the basic ones, and when training a complete dance, the entire dance needs to be transmitted to a virtual simulator beforehand for analysis and guidance. Furthermore, dancers often review their practiced basic movements through improvisation. The application of virtual reality technology in dance cannot promptly assess the risk factor of connecting basic movements. Therefore, the functionality of virtual reality technology in dance is insufficient.

[0087] In this embodiment, the user's actions can be analyzed to obtain the user's basic actions, habitual actions, or custom actions in the training actions. The basic actions are then compared and evaluated synchronously with a preset standard action library to obtain the evaluation conclusions, which the user can use to correct the basic actions.

[0088] In this embodiment, dance training is used as an example for specific illustration.

[0089] The specific steps are as follows:

[0090] Step S10: Collect the user's training actions and synchronously map the training actions to the virtual user in the virtual space;

[0091] In this embodiment, the user's training actions can be collected by an optical collector and mapped to the virtual user in the virtual simulator through a synchronization mapper, so that the virtual user can perform the same mapped actions.

[0092] It's important to note that as soon as a user performs a training action, that action is immediately mapped to the virtual user, ensuring the virtual user performs the same action instantly. For example, if the user's training action is to raise their right arm, clench their right fist, raise their right arm until it's parallel to the ground, with their right forearm parallel to their body and their palm facing the ground, and pause for one beat, then the virtual user should also begin raising their right arm as soon as the user begins clenching their fist, and the virtual user should also begin clenching their fist as soon as the user begins, until the virtual user's mapped action is synchronized with the training action and pauses for one beat. In other words, ignoring transmission latency, mapping latency, and network latency, the virtual user will simultaneously begin raising their right arm when the user begins raising their right arm.

[0093] The optical sensor can be composed of multiple sensors and can accurately capture the user's movements. For example, if a user bends one of their fingers at a 45-degree angle, the corresponding finger of the virtual user will also be bent at a 45-degree angle.

[0094] It should be noted that motion capture devices may have errors when capturing movements, and standard movements also have a tolerance. The error of the motion capture device must not exceed the tolerance of the standard movement to avoid non-standard movements caused by the device. For example, in a standard movement, the angle between the index and middle fingers is 5 degrees, and the tolerance is ±0.5 degrees. That is, in a user's training movement, an angle between the index and middle fingers between 5.5 and 4.5 degrees is considered a standard movement. The motion capture device's error must be less than ±0.5 degrees to avoid situations where the angle between the index and middle fingers in a training movement is 5.2 degrees, but the angle captured by the motion capture device exceeds 5.5 degrees.

[0095] In this embodiment, the user's training movements are accurately collected by a motion capture device and mapped onto a virtual user, enabling the virtual user to synchronously perform the mapped movements. This allows the user to view the movements intuitively on a display screen or to feel as if they are in a virtual space, thereby enhancing the user's experience.

[0096] Step S20: Based on a preset standard action library, perform action recognition on the mapped actions mapped to the virtual user to obtain the basic actions of the mapped actions;

[0097] It should be noted that since basic actions are composed of decomposed actions, the standard actions contained in the standard action library are decomposed actions of basic actions. The standard actions in the standard action library can be combined arbitrarily. They can be combined into basic actions or into non-basic actions, such as user's habitual actions or advanced actions that are extensions of basic actions.

[0098] For example, the action of standing splits can be composed of raising the thigh forward, bending the lower leg, holding the ankle with both hands, keeping the thigh in position, raising the lower leg, and lifting the lower leg with both hands. The standard action library contains these decomposed actions, and these decomposed actions are identified through the standard action library.

[0099] In this embodiment, the mapped action is decomposed to determine the decomposed actions of the mapped action. The decomposed actions are identified by standard actions in the standard action library. The basic actions in the mapped action are determined by the frequency of combinations between commonly used decomposed actions. The higher the frequency of combinations between decomposed actions, the more basic the combined action is. While identifying the basic actions in the mapped action, the standard action library also analyzes the frequency of combinations of decomposed actions in the mapped action and identifies the basic actions in the mapped action by the frequency of combinations.

[0100] It should be noted that the identification of basic movements in the mapped movements can also be done by first analyzing the historical movement records from the standard movement library to identify frequently used combination movements that are often used in different dances. These combination movements may all use the same decomposed movements and the same combination order of the decomposed movements, but the movement trajectories of the combination movements may be different. These movement trajectories are standardized and then these combination movements are defined as basic movements. When identifying the mapped movements, similar movements of these combination movements are identified as the basic movements of the mapped movements. Alternatively, basic movements can be marked by the user from the historical movement records, or user-defined standard movements can be used.

[0101] In this embodiment, the standard movement is not only a combination of decomposed movements, but also includes detailed standards such as the movement trajectory, pause position, trajectory angle, pause time, and muscle exertion point of each decomposed movement.

[0102] Specifically, the step of performing action recognition on the mapped actions mapped to the virtual user based on a preset standard action library to obtain the basic actions of the mapped actions includes:

[0103] Step S21: Decompose the mapped action into action components to obtain the component actions of the mapped action;

[0104] Step S22: Select the actions contained in the standard action library from the constituent actions, which are the basic actions in the mapped actions.

[0105] In this embodiment, the mapping action is decomposed into actions, which can be done by mapping the training action while simultaneously decomposing the training action upon receiving it, or by decomposing the training action as a whole after the user has completed the training.

[0106] In this embodiment, the mapped action is decomposed into component actions, and then the basic actions in the mapped action are selected from the component actions according to the standard action table.

[0107] Step S30: Based on the standard action library, the basic actions are evaluated to obtain an evaluation conclusion, so as to correct the user's training actions.

[0108] The evaluation criteria can be set. For example, when a user first starts practicing a set of movements, they may not be clear about the location of some pauses and may not be able to perform them correctly from the beginning. In this case, the tolerance for error in the standard movements can be increased. This can increase the user's confidence and sense of accomplishment, encouraging them to continue training.

[0109] In this embodiment, basic movements can be evaluated based on the movement trajectory of the decomposed movements, the pause points of the movements, or the positions of the pauses. The standard movements and mapped movements are compared and evaluated, and the evaluation results are displayed on the screen or in virtual space, allowing users to more intuitively observe the deficiencies of the training movements.

[0110] It should be noted that the correction of the mapped movements can be done immediately after a series of continuous movements are completed, or it can be done after the user has finished the entire dance.

[0111] Specifically, the step of evaluating the basic movements based on the standard movement library and obtaining an evaluation conclusion includes:

[0112] Step S31: Match the standard action corresponding to the basic action from the standard action library;

[0113] Step S32: Perform corresponding action analysis on the basic action, and then compare it with the standard action to determine the non-standard actions in the basic action;

[0114] Step S33: Evaluate the non-standard action to obtain a judgment conclusion on correcting the standard action.

[0115] The evaluation results can be demonstrated through a correction user set up in a virtual simulator, allowing users to more intuitively correct their training movements.

[0116] In this embodiment, since the user's actions may be non-standard, when matching standard actions from the standard action library, the variation of the action can be estimated based on the standard action to identify the basic action. The standard action with the highest matching degree with the basic action is matched from the standard action library. After decomposing the basic action, it is compared with the standard action to mark the non-standard actions in the basic action.

[0117] Specifically, the step of performing corresponding motion analysis on the basic motion and comparing it with the standard motion to determine the non-standard motions in the basic motion includes:

[0118] Step S321: Perform motion analysis on the basic motion to determine the analysis motion group of the basic motion;

[0119] Step S322: Perform action path synchronization processing on the parsed action group and the standard action to determine the non-standard actions in the parsed action group that cannot be synchronized with the standard action.

[0120] In this embodiment, the basic action is decomposed, the parsed action group contained in the basic action is determined, the parsed action and the standard action are synchronized, and the non-standard actions that cannot be synchronized in the parsed action group are identified.

[0121] It should be noted that asynchronous actions can be caused by the different times taken to decompose the actions. For example, if the standard time for action one is 5 seconds, but the user takes 6 seconds to perform action one, then the actions can be considered inconsistent.

[0122] In this embodiment, the user's training actions are mapped onto a virtual user. By analyzing the mapped actions performed by the virtual user, the system comments on whether the user's training actions are standard and provides corrective suggestions for non-standard actions, so that the user can make corrections more intuitively.

[0123] This application provides a virtual reality (VR) motion training method, apparatus, device, and storage medium. Compared with existing VR technologies that cannot recognize users' habitual movements, thus reducing the intelligence of VR, this application collects users' training movements and synchronously maps these movements onto a virtual user in a virtual space. Based on a preset standard movement library, the mapped movements onto the virtual user are identified to obtain the basic movements of the mapped movements. Based on the standard movement library, the basic movements are evaluated to obtain an evaluation conclusion, thereby correcting the user's training movements. In this application, the user's training movements are mapped onto a virtual user in a virtual space. According to the preset standard movement library, the basic movements in the mapped movements are identified, and then the basic movements are evaluated using the standard movement library to correct the user's training movements. That is, in this application, the basic movements are identified from the mapped movements using a preset standard movement library, and the basic movements are evaluated according to the standard movements in the standard movement library, so that the user can correct their training movements based on the evaluation conclusion. Therefore, the basic movements in the mapped movements are separated and corrected, improving the intelligence of VR.

[0124] Furthermore, based on the first embodiment of this application, another embodiment of this application is provided. In this embodiment, before the step of performing action recognition on the mapped actions mapped to the virtual user based on a preset standard action library to obtain the basic actions of the mapped actions, the method includes:

[0125] Step A10: Select custom movements that do not exist in the standard movement library from the historical exercise training records;

[0126] Step A20: Analyze the usage frequency of the custom action;

[0127] Step A30: If the usage frequency is higher than the preset base frequency, then the custom action is standardized and updated to the standard action library.

[0128] In this embodiment, the user's training movements are collected and organized, and custom movements that are not in the standard movement library are filtered from the collected movements, that is, from the historical exercise training records. The pause points, pause positions, and pause times of the training movements are recorded as standards. The frequency of use of these movements is analyzed, and custom movements with a frequency higher than the preset base frequency and the standard are updated to the standard movement library in real time.

[0129] In this embodiment, by selecting historical action records, the standard action library can be updated in real time. User-defined actions can also be recorded, and actions that appear in different dances can be identified from the user-defined actions and marked as basic actions.

[0130] It should be noted that as users' movements improve continuously after training, and their movements become more and more standardized, users may extend their basic movements to more difficult ones. These more difficult movements can be regarded as the basic movements for the current stage. Since some movements are user-defined, these movements are selected and organized, and the standard movement library is updated regularly. In this embodiment, the standard movement library has been made capable of real-time learning, which can meet the user's training intensity in real time.

[0131] Furthermore, based on the first embodiment of this application, another embodiment of this application is provided, in which the virtual reality motion training method further includes:

[0132] Step S01: Perform real-time action decomposition on the mapped action to determine the decomposed actions in the mapped action;

[0133] Step S02: Determine the risk of the connection between two adjacent decomposition actions to obtain the risk factors of the connection between two adjacent decomposition actions;

[0134] Step S03: Determine protective recommendations for the aforementioned risk factors to prompt the user to take safety precautions.

[0135] Among the protective recommendations, there may be combinations that minimize the risk factors and risk coefficients in the process of decomposing and connecting actions, as well as protective methods to reduce injuries.

[0136] In this embodiment, since users will improvise during training to combine and connect the basic movements they have learned, in order to review and flexibly apply the basic movements, the connection between each pair of movements is attempted by the user himself, and the difficulty and potential risk of connecting each pair of movements are different. Therefore, after the first attempt at connecting the movements, the user may be at risk of injury if he continues to practice. The system performs real-time decomposition of the user's mapped movements, determines the risk factors in the combination and connection process of each pair of decomposed movements, determines the risk factor based on the risk factor, and provides protective suggestions during the training process based on the risk factor.

[0137] Specifically, the step of determining protective recommendations for the hazard factors includes:

[0138] Step B10: Determine the hazard coefficient of the hazard factor;

[0139] Step B20: If the risk factor triggers the safety factor of the preset recommended replacement action, then obtain the replacement action with a risk factor less than the safety factor from the historical action record;

[0140] Step B30: Connect the replacement action and the decomposition action to obtain a coherent suggested action;

[0141] The protection recommendations include suggested actions.

[0142] In this embodiment, by assessing the risk coefficient of the combination of decomposed actions, it is determined whether the action combination is suitable for the user's current training stage. Alternative actions with the same difficulty and lower risk coefficient are proposed to the user for practice. The alternative actions are then added to the decomposed actions to obtain recommended actions suitable for the user's training.

[0143] In this embodiment, it should be noted that in order to prevent users from continuing to practice custom action combinations despite not accepting the suggested actions, the user needs to be reminded immediately after the first practice session. Since the user is only trying to combine and connect actions during the first practice session, and will only actually practice after confirming that the combination can be connected, reminding the user immediately after the first practice session can effectively prevent the user from getting injured.

[0144] Reference Figure 3 , Figure 3 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application.

[0145] like Figure 3 As shown, the virtual reality motion training device may include: a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to establish communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM or a stable, non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0146] Optionally, the virtual reality sports training device may also include a rectangular user interface, a network interface, a camera, RF (Radio Frequency) circuitry, sensors, audio circuitry, a WiFi module, etc. The rectangular user interface may include a display screen and an input submodule such as a keyboard. Optionally, the rectangular user interface may also include a standard wired interface or a wireless interface. The network interface may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0147] Those skilled in the art will understand that Figure 3The virtual reality sports training device structure shown in the figure does not constitute a limitation on the virtual reality sports training device. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0148] like Figure 3 As shown, the memory 1005, serving as a storage medium, may include an operating system, a network communication module, and a virtual reality sports training program. The operating system is a program that manages and controls the hardware and software resources of the virtual reality sports training device, supporting the operation of the virtual reality sports training program and other software and / or programs. The network communication module is used to enable communication between the various components within the memory 1005, as well as communication with other hardware and software in the virtual reality sports training system.

[0149] exist Figure 3 In the virtual reality motion training device shown, the processor 1001 is used to execute the virtual reality motion training program stored in the memory 1005 to implement the steps of the virtual reality motion training method described in any of the above claims.

[0150] The specific implementation of the virtual reality sports training device in this application is basically the same as the embodiments of the virtual reality sports training method described above, and will not be repeated here.

[0151] This application also provides a virtual reality sports training device, the virtual reality sports training device comprising:

[0152] The acquisition module is used to acquire the user's training actions and synchronously map the training actions to the virtual user in the virtual space;

[0153] The recognition module is used to perform action recognition on the mapped actions mapped to the virtual user based on a preset standard action library, so as to obtain the basic actions of the mapped actions.

[0154] The evaluation module is used to evaluate the basic movements based on the standard movement library, obtain evaluation conclusions, and correct the user's training movements.

[0155] Optionally, the evaluation module includes:

[0156] The matching module is used to match the standard action corresponding to the basic action from the standard action library;

[0157] The parsing module is used to perform corresponding action parsing on the basic action, and then compare it with the standard action to determine the non-standard actions in the basic action;

[0158] The evaluation submodule is used to evaluate the non-standard actions and obtain an evaluation conclusion to correct the standard actions.

[0159] Optionally, the parsing module includes:

[0160] The parsing submodule is used to perform action parsing on the basic action and determine the parsed action group of the basic action;

[0161] The synchronization module is used to perform action path synchronization processing on the parsed action group and the standard action, and to identify non-standard actions in the parsed action group that cannot be synchronized with the standard action.

[0162] Optionally, the identification module includes:

[0163] The decomposition module is used to decompose the mapped action into action components to obtain the mapping action.

[0164] The filtering module is used to filter out the actions contained in the standard action library from the constituent actions, which are the basic actions in the mapped actions.

[0165] Optionally, historical sports training records may be collected;

[0166] The virtual reality sports training device also includes:

[0167] The filtering module is used to select custom movements that do not exist in the standard movement library from the historical exercise training records;

[0168] The analysis module is used to analyze the frequency of use of the custom action;

[0169] The standard processing module is used to standardize the custom action and update the custom action to the standard action library if the usage frequency is higher than the preset base frequency.

[0170] Optionally, the virtual reality motion training device further includes:

[0171] The second decomposition module is used to perform real-time action decomposition on the mapped action and determine the decomposed actions in the mapped action.

[0172] The determination module is used to determine the danger of the connection between two adjacent decomposition actions and obtain the danger factors of the connection between the two adjacent decomposition actions.

[0173] The prompting module is used to determine protective recommendations for the aforementioned hazardous factors, so as to prompt the user to take safety precautions.

[0174] Optionally, the prompting module includes:

[0175] The determination module is used to determine the hazard coefficient of the hazard factor;

[0176] The triggering module is used to obtain a replacement action from the historical action record where the risk factor is less than the safety factor if the risk factor triggers the safety factor of the preset recommended replacement action.

[0177] A connection module is used to connect the replacement action and the decomposition action to obtain a coherent suggested action;

[0178] The protection recommendations include suggested actions.

[0179] The specific implementation of the virtual reality sports training device of this application is basically the same as the embodiments of the virtual reality sports training method described above, and will not be repeated here.

[0180] This application provides a storage medium that stores one or more programs, which can be executed by one or more processors to implement the steps of the virtual reality motion training method described above.

[0181] The specific implementation of the storage medium in this application is basically the same as the embodiments of the virtual reality motion training method described above, and will not be repeated here.

[0182] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0183] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0184] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0185] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A virtual reality exercise training method, characterized in that, The virtual reality motion training method includes: Collect users' training actions and synchronously map the training actions to virtual users in the virtual space; Based on a preset standard action library, the mapping actions mapped to the virtual user are identified to obtain the basic actions of the mapping actions. Based on the standard action library, the basic actions are evaluated to obtain an evaluation conclusion, so as to correct the user's training actions; The step of performing action recognition on the mapped actions mapped to the virtual user based on a preset standard action library to obtain the basic actions of the mapped actions includes: The mapped action is decomposed to obtain the constituent actions of the mapped action; The standard action library is selected from the constituent actions. The actions are the basic actions in the mapped actions. While identifying the basic actions in the mapped actions, the standard action library also analyzes the frequency of the combination of decomposed actions of the mapped actions. The basic actions in the mapped actions are identified by the frequency of the combination. The standard actions are combinations of decomposed actions.

2. The virtual reality motion training method as described in claim 1, characterized in that, The step of evaluating the basic movements based on the standard movement library and obtaining an evaluation conclusion includes: Match the standard action corresponding to the basic action from the standard action library; The basic movements are analyzed and compared with the standard movements to identify the non-standard movements in the basic movements. The non-standard actions are evaluated to obtain a judgment conclusion that the standard actions should be corrected.

3. The virtual reality motion training method as described in claim 2, characterized in that, The step of performing corresponding motion analysis on the basic motion, comparing it with the standard motion, and identifying non-standard motions in the basic motion includes: The basic movements are analyzed to determine the analytical movement groups of the basic movements; The parsed action group and the standard action are synchronized through action path processing to identify non-standard actions in the parsed action group that cannot be synchronized with the standard action.

4. The virtual reality sports training method as described in claim 1, characterized in that, Before the step of performing action recognition on the mapped actions mapped to the virtual user based on a preset standard action library to obtain the basic actions of the mapped actions, the method includes: Select custom movements that are not present in the standard movement library from the historical exercise training records; Analyze the frequency of use of the custom actions; If the usage frequency is higher than the preset base frequency, the custom action is standardized and updated to the standard action library.

5. The virtual reality motion training method as described in claim 1 further includes: The mapped action is decomposed in real time to determine the decomposed actions in the mapped action; A hazard assessment is performed on the connection between two adjacent decomposition actions to obtain the hazard factors of the connection between the two adjacent decomposition actions. Determine protective recommendations for the aforementioned risk factors to prompt the user to take safety precautions.

6. The virtual reality motion training method as described in claim 5, characterized in that, The step of determining protective recommendations for the hazard factors includes: Determine the hazard coefficient of the aforementioned risk factor; If the risk factor triggers the safety factor of the preset recommended replacement action, then the replacement action with a risk factor less than the safety factor is obtained from the historical action record; By connecting the replacement action and the decomposition action, a coherent suggested action is obtained; The protection recommendations include suggested actions.

7. A virtual reality sports training device, characterized in that, The virtual reality sports training device includes: The acquisition module is used to acquire the user's training actions and synchronously map the training actions to the virtual user in the virtual space; The recognition module is used to perform action recognition on the mapped actions mapped to the virtual user based on a preset standard action library, so as to obtain the basic actions of the mapped actions. The evaluation module is used to evaluate the basic movements based on the standard movement library, obtain an evaluation conclusion, and correct the user's training movements. The decomposition module is used to decompose the mapped action into action components to obtain the mapping action. The filtering module is used to filter out the actions contained in the standard action library from the constituent actions, wherein the actions are the basic actions in the mapped actions. The standard action library, while identifying the basic actions in the mapped actions, also analyzes the frequency of the combination of decomposed actions of the mapped actions. The basic actions in the mapped actions are identified by the frequency of the combination. The standard actions are combinations of decomposed actions.

8. A virtual reality sports training device, characterized in that, The virtual reality motion training device includes: a memory, a processor, and a program stored in the memory for implementing the virtual reality motion training method. The memory is used to store programs for implementing motion training methods in virtual reality; The processor is configured to execute a program that implements the motion training method for virtual reality, to implement the steps of the motion training method for virtual reality as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores a program for implementing a virtual reality motion training method, which is executed by a processor to implement the steps of the virtual reality motion training method as described in any one of claims 1 to 6.

Images