Data fusion method and system based on indoor and outdoor virtual reality combination of element universe city golf course

Abstract

The invention relates to a data fusion method and system based on indoor and outdoor virtual reality combination of a meta universe city golf course, and the method comprises the steps: obtaining indoor swing data collected by an indoor induction terminal when a user completes the swing and ball hitting actions indoors, and transmitting the indoor swing data to a user data analysis model; the user data analysis model identifies indoor swing data and generates indoor hitting effect data based on the scene data; pre-stored standard hitting data corresponding to the current scene data are called, and whether an outdoor actual combat training task is generated for the current user or not is judged; if yes, a corresponding actual combat training task is matched and sent to the outdoor sensing terminal; the outdoor sensing terminal obtains task result data of the actual combat training task performed by the user, and sends the task result data to the user data analysis model to analyze and generate a report; the method has the advantages that indoor and outdoor data connection of urban golf sports is achieved, and the accuracy and experience of user sports analysis are improved.

Description

Technical Field

[0001] This application relates to the technical field of virtual golf, and in particular to a data fusion method and system based on the combination of indoor and outdoor virtual reality in a metaverse city golf course. Background Technology

[0002] Currently, most metaverse city golf courses are purely indoor simulations or purely virtual world interactions, that is, providing indoor virtual sports experiences through golf simulators. It is difficult to connect users' indoor practice and hitting results with real outdoor courses, resulting in a relatively monotonous experience. The training process lacks training to cope with uncertainties in real environments such as wind, slope, and grass type. Furthermore, outdoor practice data and indoor practice data are independent of each other, making it difficult to form a unified and integrated user data system. For golfers, it is difficult to provide effective and accurate technical analysis reports and personalized guidance, so improvements are needed. Summary of the Invention

[0003] To achieve seamless integration of indoor and outdoor data for urban golf, obtain a unified and accurate sports data analysis model, and improve the accuracy and user experience of sports analysis, this application provides a data fusion method and system based on the combination of indoor and outdoor virtual reality in urban golf courses within the metaverse framework.

[0004] The above-mentioned objective of this application is achieved through the following technical solution:

[0005] A data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse-themed urban golf course includes the following steps:

[0006] When a user completes a swing motion indoors, the system acquires indoor swing data collected by indoor sensing terminals, representing the user's swing process, and sends the indoor swing data to a pre-trained user data analysis model.

[0007] The user data analysis model identifies scene data associated with indoor swing data and generates indoor hitting effect data based on the scene data;

[0008] The user data analysis model retrieves pre-stored standard hitting data corresponding to the current scenario data, and determines whether the outdoor combat training task is generated by the current user based on indoor swing data, indoor hitting effect data, and standard hitting data.

[0009] If so, based on the scene data, the corresponding practical training task is matched from the preset task database and sent to the outdoor sensing terminal;

[0010] The outdoor sensing terminal acquires the task result data of the user's practical training task and sends the task result data to the user data analysis model;

[0011] The user data analysis model generates a training analysis report that matches the current user based on indoor swing data and task result data, and sends it to the user terminal that is bound to the user's identity information.

[0012] By adopting the above technical solution, when users train using the indoor metaverse golf simulator, the indoor sensing terminal collects the user's swing data and the effect of the indoor swing in the selected scene, obtaining indoor hitting effect data. By comparing it with standard hitting data, it is determined whether the user's swing and shot effect meet the training standard. If not, it is necessary to identify technical shortcomings based on the user's hitting effect and swing, such as poor directionality, or the connection and replication of scene data, and generate corresponding outdoor practical training tasks, such as training in narrow fairway landing areas. The practical training tasks are sent to the outdoor sensing terminal, which is responsible for collecting the swing and shot effects of the outdoor task training, obtaining task result data, and transmitting it back to the same system, i.e., all data is transmitted back to the user for data analysis. The user data analysis model, based on indoor hitting effect data and outdoor practical training task results data, forms a virtual reality combined data analysis of a single user's golf game, enhancing the user experience. Indoor simulation selects scene data to enhance the realism of the simulation training, while outdoor practical training tasks allow users to clearly see the flight trajectory of the golf ball, giving them a more intuitive feel for the hitting effect. The results of outdoor practical training are then combined with indoor swing data, indoor hitting effect data, and standard hitting data for analysis. This determines whether the user has improved after outdoor training and provides suggestions for adjustments, achieving seamless integration of indoor and outdoor data for urban golf, resulting in a unified, accurate, and reliable sports data analysis model, improving the accuracy and user experience of sports analysis.

[0013] Optionally, the step of the user data analysis model identifying scene data associated with indoor swing data and generating indoor hitting effect data based on the scene data includes:

[0014] The user data analysis model identifies the scene data selected by the user, which includes golf course environment data, weather data, and swing scene data.

[0015] After collecting indoor swing data, the indoor sensing terminal adjusts the simulated flight parameters of the golf ball based on the scene data to obtain indoor hitting effect data.

[0016] By adopting the above technical solution, the user data analysis model allows users to choose from various simulation factors, such as different golf course environments, weather conditions, and swing scenarios. The golf course environment includes green speed, rough height, and bunker hardness; weather factors include wind speed, wind direction, temperature, and humidity; and swing scenarios include tee shots, fairway shots, shots from the rough and bunkers, high lobs, and putting. After selecting a scenario, the indoor sensing terminal collects indoor swing data and adjusts the simulated flight parameters of the ball based on the selected scenario to obtain a hitting effect that matches the scenario data, making the indoor simulated golf shot more realistic.

[0017] Optionally, the user data analysis model retrieves pre-stored standard hitting data corresponding to the current scenario data, and determines whether an outdoor practical training task is generated for the current user based on indoor swing data, indoor hitting effect data, and standard hitting data. This step includes:

[0018] Identify the user terminal associated with the indoor swing data, and retrieve the historical swing data and historical hitting effect data of the user terminal under the same scenario data;

[0019] Based on historical swing data and historical hitting effect data, determine the confidence level of the indoor swing data and indoor hitting effect data for this period of time;

[0020] When the confidence level is greater than the threshold, the degree of deviation between the indoor swing data, indoor hitting effect data and standard hitting data is calculated.

[0021] When the deviation is greater than or equal to the preset deviation, it is determined that it is an outdoor practical training task for the current user's production line, and this practical training task is associated with the user's terminal.

[0022] By adopting the above technical solution, each user is bound to a client to store historical indoor and outdoor swing data, as well as historical shot records. Based on historical shot results and swing data, the system first assesses the reliability of the user's current indoor swing data and shot results, evaluating whether it reflects the user's true skill level. This avoids significant deviations from historical records due to external factors, ensuring more accurate and reasonable swing and shot records. Furthermore, when the confidence level exceeds a threshold, the system uses standard swing data and shot results to determine if the shot is acceptable and / or if it hits the designated area. If the shot is unacceptable, resulting in the ball not reaching the designated area, a practice training task associated with the client is generated to provide the user with realistic practice opportunities for repeated training to improve swing accuracy.

[0023] Optionally, if so, the step of matching the corresponding practical training task from the preset task database based on the scene data and sending it to the outdoor sensing terminal includes:

[0024] Match all available practical training tasks for the current scenario data from the preset task database;

[0025] Specific deviation data is obtained from the degree of deviation, and the type of deviation between the indoor swing data, indoor hitting effect data and standard hitting data is determined based on the deviation data;

[0026] The live-fire training tasks that match the deviation type are selected from the candidate live-fire training tasks and sent to the outdoor sensing terminal.

[0027] By adopting the above technical solution, users are provided with intelligent matching of various types of practical training tasks. By comparing specific deviation data in the degree of deviation, such as directional deviation and clubface angle deviation at the time of impact, the corresponding deviation type is output and further matched with the corresponding type of practical training task, which is then sent to the outdoor sensing terminal to sense the user's outdoor training task completion status, thereby providing targeted training for the user and enhancing the user experience.

[0028] Optionally, the step of the outdoor sensing terminal acquiring task result data of the user's practical training task and sending the task result data to the user data analysis model includes:

[0029] Outdoor sensing terminals generate task recognition rules based on actual combat training missions;

[0030] The outdoor sensing terminal collects outdoor swing data from users' practical training tasks and outputs outdoor hitting effect data based on task recognition rules.

[0031] The outdoor swing data and outdoor hitting effect data are packaged to obtain task result data, which is then sent to the user data analysis model.

[0032] By adopting the above technical solution, when conducting outdoor practical training tasks, the outdoor sensing terminal collects outdoor swing data and generates corresponding task recognition rules to determine the effect of outdoor hitting, that is, to determine the accuracy and completion of the swing and hitting during targeted outdoor training. This generates task result data and sends it to the user data analysis model. The user data analysis model further analyzes whether the user's swing and hitting have improved under the current scenario data based on the deviations generated by indoor swing and hitting, as well as the corresponding effect of outdoor training. At the same time, the generation of outdoor practical training tasks can also be a scenario transformation based on indoor swing data and indoor hitting effect data.

[0033] Optionally, the outdoor sensing terminal includes a wearable sensing terminal and a visual laser sensing terminal. The step of the outdoor sensing terminal collecting outdoor swing data of the user during practical training tasks and outputting outdoor hitting effect data based on task recognition rules includes:

[0034] The wearable sensor collects the user's outdoor golf swing data;

[0035] The visual laser sensing end is used to emit laser markers to the outdoor training field and to acquire video data recording the trajectory of the golf ball.

[0036] Based on trajectory video data and task recognition rules, the distance change information between the laser marker and the golf ball's trajectory is determined to obtain outdoor hitting effect data.

[0037] By adopting the above technical solution, wearable sensing devices collect users' outdoor swing data. For example, sensing gloves collect the rhythm and amplitude of the swing. Visual laser sensing devices set laser projection lines or ranges, such as narrow lanes for putting training or the target landing area of ​​a golf ball. By acquiring video data of the golf ball's movement trajectory, the system analyzes whether the cue ball deviates from the laser-marked area, thereby acquiring outdoor hitting effect data.

[0038] Optionally, the step of the outdoor sensing terminal collecting outdoor swing data of the user during practical training tasks and outputting outdoor hitting effect data based on task recognition rules further includes the following steps:

[0039] Obtain the user's location information and determine whether the location information matches the preset location for the actual combat training task;

[0040] When the location information matches the preset location, a shot position and tracking instructions are generated and sent to the user's device.

[0041] When the user reaches the hitting position, the hitting direction data and target point data are sent to the user.

[0042] Wearable sensors collect data on the user's outdoor swing, while the user terminal receives the data on the hitting effect uploaded by the user.

[0043] By adopting the above technical solution, the user terminal is used as an outdoor sensing terminal. When the user arrives at a golf course that matches the virtual scene data indoors, the user terminal can select and activate the corresponding outdoor training task. This involves obtaining the user terminal's location information and determining whether the location information matches the preset location of the practical training task, i.e., whether the user has arrived at the corresponding course in the practical training task. If so, the system further generates the hitting position and tracking instructions and sends them to the user terminal. After the user arrives at the designated hitting position through the user terminal, the system generates hitting direction data and target landing point data for the user terminal. For example, if the user selects the scene data corresponding to the real-world course A for training indoors, and the training content is the first shot on the tee, when the user arrives at the real-world course A, the practical training task is activated through the location information. At this time, the system generates location information and direction information consistent with the indoor tee point and tee direction and sends them to the user terminal. The user terminal can then achieve a realistic hitting experience consistent with the indoor training content. The hitting effect data obtained in reality is uploaded to the user data analysis model through the user terminal. The user data analysis model summarizes and analyzes the swing and hitting effects based on the same indoor and outdoor scene data, generates an analysis report, and sends it to the user terminal.

[0044] The second objective of this invention is achieved through the following technical solution:

[0045] A data fusion system based on the combination of indoor and outdoor virtual reality in a metaverse-themed urban golf course includes:

[0046] The indoor sensing module is used to acquire indoor swing data collected by the indoor sensing terminal when the user completes the swing action indoors, representing the user's swing process, and send the indoor swing data to the pre-trained user data analysis model.

[0047] The indoor hitting analysis module is used by the user data analysis model to identify scene data associated with indoor swing data and generate indoor hitting effect data based on the scene data.

[0048] The task judgment module is used by the user data analysis model to retrieve the pre-stored standard hitting data corresponding to the current scene data, and to determine whether the task is an outdoor combat training task generated by the current user based on the indoor swing data, indoor hitting effect data and standard hitting data.

[0049] The task generation module is used to match the corresponding practical training task in the preset task database based on the scene data and send it to the outdoor sensing terminal if the scenario data is true.

[0050] The outdoor impact analysis module is used by the outdoor sensing terminal to acquire the task result data of the user's combat training mission and send the task result data to the user data analysis model.

[0051] The report analysis module is used by the user data analysis model to generate a training analysis report that matches the current user based on indoor swing data and task result data, and send it to the user terminal that is bound to the user's identity information.

[0052] The above-mentioned objective three of this application is achieved through the following technical solution:

[0053] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course.

[0054] The fourth objective of this application is achieved through the following technical solution:

[0055] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course.

[0056] In summary, this application includes at least one of the following beneficial technical effects:

[0057] 1. Indoor sensor terminals collect user swing data and the effects of indoor swings in selected scenarios to obtain indoor hitting effect data. By comparing this data with standard hitting data, it determines whether the user's swing and shot performance meet training standards. If not, it identifies technical weaknesses based on the user's swing and shot performance, such as poor directionality, or issues with the integration and replication of scenario data. Corresponding outdoor practical training tasks are then generated, such as training in narrow fairway landing areas. These tasks are sent to outdoor sensor terminals, which collect the swing and shot performance data from the outdoor training, obtain the task results data, and transmit it back to the same system—specifically, back to the user data analysis model. The user data is then divided into... The analysis model is based on indoor hitting effect data and outdoor practical training task results data to form a virtual reality combined data analysis of a single user's golf game, enhancing the user experience. By selecting scene data through indoor simulation, the realism of the simulation training is enhanced. By setting outdoor practical training tasks, users can clearly know the flight trajectory of the golf ball, allowing them to more intuitively feel the hitting effect. Then, the results of outdoor practical training are combined with indoor swing data, indoor hitting effect data, and standard hitting data for analysis to determine whether the user has made progress after outdoor training and to provide suggestions for adjustments. This achieves the connection between indoor and outdoor data in urban golf, resulting in a unified, accurate, and reliable sports data analysis model.

[0058] 2. First, assess the authenticity and reliability of the user's indoor swing data and hitting performance. This involves evaluating whether the data reflects the user's actual skill level and avoiding discrepancies with historical records due to external factors. This ensures more accurate and reasonable records of the user's swing and hitting performance. Furthermore, when the confidence level exceeds a threshold, determine the quality of the shot and / or whether it hits the designated area based on standard swing data and hitting performance. If the shot is substandard and the ball misses the designated area, generate a practice training task linked to the user's device to provide realistic training opportunities for repeated practice and improvement of swing accuracy.

[0059] 3. Provide users with intelligent matching of various types of practical training tasks. By comparing specific deviation data in the degree of deviation, such as directional deviation and clubface angle deviation at the time of impact, the corresponding deviation type is output and further matched with the corresponding type of practical training task. The task is then sent to the outdoor sensing terminal to sense the user's completion of the outdoor training task, thereby providing targeted training to the user and enhancing the user experience.

[0060] 4. Wearable sensors collect outdoor swing data from users. For example, sensor gloves collect the rhythm and amplitude of the swing. A visual laser sensor is used to set the laser projection line or range, such as a narrow lane for putting training or the target landing area of ​​the golf ball. By acquiring video data of the golf ball's movement trajectory, the system analyzes whether the cue ball deviates from the laser-marked area, thereby obtaining outdoor hitting effect data. Attached Figure Description

[0061] Figure 1 This is a flowchart illustrating an implementation of the data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course, as described in this application.

[0062] Figure 2 This is a flowchart of step S30 in an embodiment of the data fusion method for combining indoor and outdoor virtual reality in a metaverse city golf course, as described in this application.

[0063] Figure 3 This is a flowchart of step S50 in an embodiment of the data fusion method for combining indoor and outdoor virtual reality in a metaverse city golf course, as described in this application.

[0064] Figure 4 This is a schematic block diagram of a computer device according to this application. Detailed Implementation

[0065] The following is in conjunction with the appendix Figure 1-4 This application will be described in further detail.

[0066] In the following embodiments, such as Figure 1 As shown, this application discloses a data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse-themed urban golf course, which specifically includes the following steps:

[0067] S10: When a user completes a swing action indoors, acquire indoor swing data collected by the indoor sensing terminal representing the user's swing process, and send the indoor swing data to the pre-trained user data analysis model;

[0068] In this embodiment, a user in the Metaverse City Golf Indoor Training Room swings a golf ball in front of a screen displaying a virtual golf course. An indoor sensing terminal located to the user's side captures the entire swing process. The indoor sensing terminal includes a high-speed visual sensor, a Doppler radar, and a pressure sensing device. The high-speed visual sensor is a camera with a resolution of at least 1000fps, which uses computer vision algorithms to capture and calculate indoor swing data such as clubhead speed, clubface angle, and impact point. The Doppler radar analyzes reflected signals to calculate the ball's initial velocity, launch angle, backspin, and simulates the complete ball trajectory and landing point. The pressure sensing device includes a pressure pad used to collect data on foot pressure distribution and weight transfer during the user's swing, which also falls under indoor swing data.

[0069] The user data analysis model is a pre-trained Gaussian mixture model. It forms a dynamically updated personal ability model by clustering the features of indoor and outdoor swing data. This model can predict the typical shot performance distribution of a user using a specific club.

[0070] S20: The user data analysis model identifies scene data associated with indoor swing data and generates indoor hitting effect data based on the scene data;

[0071] In this embodiment, the scene data includes the golf course, climate, hitting position, and swing scene selected by the user. The indoor hitting effect data includes the initial velocity, launch angle, and backspin of the golf ball, as well as the simulation of the complete ball flight trajectory and landing point, and the evaluation and analysis of the swing data.

[0072] Specifically, step S20 includes the following steps:

[0073] S21: The user data analysis model identifies the scene data selected by the user, including golf course environment data, weather data, and swing scene data;

[0074] S22: After the indoor sensing terminal collects indoor swing data, it adjusts the simulated flight parameters of the golf ball based on the scene data to obtain indoor hitting effect data.

[0075] The course environment data includes the selected course name, the corresponding hitting position in the selected course and its corresponding surface material, such as deep grass, bunkers and hard surfaces, and the position of the tee or second shot of the xth hole of the course, the green, etc. The meteorological data includes parameters such as temperature, humidity and wind speed, wind force and wind direction. The swing scenario data includes parameters such as green speed, rough height and bunker hardness.

[0076] After the indoor swing data is generated, an indoor hitting effect data will be generated without considering wind speed, wind direction, temperature, humidity and the golf course environment. That is, a flight trajectory will be generated without considering the golf course environment data and meteorological data. Then, based on the parameter adjustment rules in the user data analysis model, the direction, trajectory, distance and landing position of the ball flight will be adjusted. For example, the ball flight trajectory needs to be calculated by function fitting in combination with wind direction and wind speed.

[0077] S30: The user data analysis model retrieves the pre-stored standard hitting data corresponding to the current scene data, and determines whether the indoor swing data, indoor hitting effect data and standard hitting data are generated for the current user's outdoor combat training task.

[0078] In this embodiment, standard hitting data is used to determine whether the effect of the current indoor swing and hitting meets the training requirements by setting parameter ranges. This includes the standard parameter range of clubhead speed, the standard range of clubface closure, and the range of hitting positions. From the perspective of hitting effect, it sets the typical landing point distribution area for the current specific ball feel. By comparing the parameters in the indoor swing data and the landing points in the indoor hitting effect data with the parameter ranges in the standard hitting data, it is determined whether to generate a practical training task.

[0079] The generation and judgment of practical training tasks include two types. One is based on indoor swing data and / or poor indoor hitting performance, which generates an outdoor practical training task. The other is based on the scene data changes caused by the hitting sequence, which generates a practical training task. For example, if the current user's indoor hitting performance results in the ball landing on the green during indoor training, a practical training task corresponding to the green scene is generated, and the user then goes to the actual outdoor green for hitting practice.

[0080] Specifically, refer to Figure 2 Step S30 includes the following steps:

[0081] S31: Identify the user terminal associated with the indoor swing data, and retrieve the historical swing data and historical hitting effect data of the user terminal under the same scenario data;

[0082] S32: Based on historical swing data and historical hitting effect data, determine the confidence level of the current indoor swing data and indoor hitting effect data;

[0083] S33: When the confidence level is greater than the threshold, calculate the degree of deviation between the indoor swing data, indoor hitting effect data and standard hitting data.

[0084] S34: When the deviation is greater than or equal to the preset deviation, it is determined that it is an outdoor practical training task for the current user's production line, and this practical training task is associated with the user terminal.

[0085] The user terminal refers to the smart mobile terminal used by training golfers and users. When a user swings but is interfered with by equipment failure, or when it is not the user who is practicing the swing, the confidence level of the indoor swing data and indoor hitting effect is low. In this case, the data will not be included in the user's ability analysis. If the confidence level is greater than the threshold, the degree of deviation is obtained by calculating the deviation of parameters between the indoor swing data, indoor hitting effect and standard hitting data. If the deviation is large, it is determined that a practical training task needs to be generated.

[0086] S40: If so, then based on the scene data, match the corresponding practical training task in the preset task database and send it to the outdoor sensing terminal;

[0087] In this embodiment, the corresponding practical training tasks include two types. The first type is a targeted practical training task output based on the deviation of the user's indoor swing data and indoor hitting effect data. The second type is a practical training task that connects the user's indoor swing data and indoor hitting effect to the corresponding scenario and environment, such as the situation of attacking the ball onto the green.

[0088] Specifically, step S40 includes the following steps:

[0089] S41: Match all available practical training tasks for the current scenario data from the preset task database;

[0090] S42: Obtain specific deviation data from the degree of deviation, and determine the type of deviation between the indoor swing data, indoor hitting effect data and standard hitting data based on the deviation data;

[0091] S43: Select the practical training tasks that match the deviation type from the candidate practical training tasks and send them to the outdoor sensing terminal.

[0092] The steps detail the matching method for one type of practical training task: generating practical training tasks based on the degree of deviation. First, all practical training tasks for the current scenario data are matched. Then, the deviation type is located based on parameters in the deviation degree section, such as deviation in directional control, generating a corresponding practical training task of narrow-slope shot. For inaccurate putting, a practical training task of complex slope putting is generated.

[0093] S50: The outdoor sensing terminal acquires the task result data of the user's practical training task and sends the task result data to the user data analysis model;

[0094] In this embodiment, the task result data includes outdoor swing data and outdoor hitting effect data of the user's outdoor combat training. The outdoor sensing terminal includes wearable sensing equipment and sensing devices for laser, vision, and GPS positioning, used to sense the user's outdoor swing data and outdoor hitting effect data.

[0095] Specifically, refer to Figure 3 Step S50 includes the following steps:

[0096] S51: Outdoor sensing terminals generate task recognition rules based on actual combat training tasks;

[0097] S52: The outdoor sensing terminal collects outdoor swing data of users during practical training tasks, and outputs outdoor hitting effect data based on task recognition rules;

[0098] S53: Package the outdoor swing data and outdoor hitting effect data to obtain task result data, and send it to the user data analysis model.

[0099] The task recognition rules are calculation rules generated in conjunction with the outdoor sensing terminal to accurately record and determine the ball's trajectory and landing point after being struck. Different outdoor sensing terminals are adapted to different task recognition rules.

[0100] Furthermore, the outdoor sensing terminal includes a wearable sensing terminal and a visual laser sensing terminal, and step S52 includes the following steps:

[0101] S521: The wearable sensing device collects the user's outdoor swing data;

[0102] S522: The visual laser sensing end is used to emit laser markers to the outdoor training field and to acquire video data recording the trajectory of the golf ball.

[0103] S523: Based on trajectory video data and task recognition rules, determine the distance change information between the laser marker and the golf ball's movement trajectory to obtain outdoor hitting effect data.

[0104] In this embodiment, the wearable sensing end is a wearable sensing glove used to collect the user's swing contact and backswing amplitude; the visual laser sensing end is used to project laser marks onto the actual training field to form a training area, such as generating the two boundary limits of the training channel during putting training, or generating the landing area of ​​the ball, and acquiring the trajectory video data of the ball through a camera device. Based on the trajectory video data and task recognition rules, the distance between the ball and the laser mark is determined to obtain outdoor hitting effect data. For example, if the ball falls into the landing area in the laser mark, the hitting effect is judged to be qualified; if it does not enter the landing area, it is judged to be unqualified.

[0105] In another embodiment, step S52 further includes the step:

[0106] S521A: Obtain the user's location information and determine whether the location information matches the preset location of the actual combat training task;

[0107] S522A: When the positioning information matches the preset positioning, a hitting position and tracking instructions are generated and sent to the user terminal;

[0108] S523A: When the user terminal reaches the hitting position, it sends the hitting direction data and target point data to the user terminal;

[0109] S524A: Wearable sensor collects outdoor swing data from users, while the user terminal receives the hit effect data uploaded by the user.

[0110] In this embodiment, the outdoor sensing terminal is also the user terminal bound to the user. It requests the user terminal's location information via GPS and determines whether the location information matches the location of the venue specified in the actual combat training mission. If so, it sends a hitting position and tracking command to the user terminal to guide the user to the hitting position, and further sends hitting direction data to the user terminal, including a hitting direction diagram or arrow guidance diagram from the user's perspective. The wearable sensing terminal is also a wearable sensing glove.

[0111] S60: The user data analysis model generates a training analysis report that matches the current user based on indoor swing data and task result data, and sends it to the user terminal that is bound to the user's identity information.

[0112] In this embodiment, the training analysis report includes analysis of indoor swing data, indoor hitting effect data, outdoor swing data, and outdoor hitting effect data for each training shot under different scenario data. It can be customized to be a time-evolutionary ability trend waveform.

[0113] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0114] In one embodiment, a data fusion system based on the combination of indoor and outdoor virtual reality in a metaverse city golf course is provided. This data fusion system corresponds to the data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course described in the previous embodiment. The data fusion system based on the combination of indoor and outdoor virtual reality in a metaverse city golf course includes:

[0115] The indoor sensing module is used to acquire indoor swing data collected by the indoor sensing terminal when the user completes the swing action indoors, representing the user's swing process, and send the indoor swing data to the pre-trained user data analysis model.

[0116] The indoor hitting analysis module is used by the user data analysis model to identify scene data associated with indoor swing data and generate indoor hitting effect data based on the scene data.

[0117] The task judgment module is used by the user data analysis model to retrieve the pre-stored standard hitting data corresponding to the current scene data, and to determine whether the task is an outdoor combat training task generated by the current user based on the indoor swing data, indoor hitting effect data and standard hitting data.

[0118] The task generation module is used to match the corresponding practical training task in the preset task database based on the scene data and send it to the outdoor sensing terminal if the scenario data is true.

[0119] The outdoor impact analysis module is used by the outdoor sensing terminal to acquire the task result data of the user's combat training mission and send the task result data to the user data analysis model.

[0120] The report analysis module is used by the user data analysis model to generate a training analysis report that matches the current user based on indoor swing data and task result data, and send it to the user terminal that is bound to the user's identity information.

[0121] Optional indoor impact models include:

[0122] The scene selection submodule is used by the user data analysis model to identify the scene data selected by the user. The scene data includes golf course environment data, weather data, and swing scene data.

[0123] The indoor effects submodule is used to collect indoor swing data from the indoor sensing terminal, and then adjust the simulated flight parameters of the golf ball based on the scene data to obtain indoor hitting effect data.

[0124] Optionally, the task determination module includes:

[0125] The historical data submodule is used to identify the user terminal associated with indoor swing data and retrieve the historical swing data and historical hitting effect data of the user terminal under the same scenario data.

[0126] The confidence submodule is used to determine the confidence level of the current indoor swing data and indoor hitting effect data based on historical swing data and historical hitting effect data;

[0127] The deviation analysis submodule is used to calculate the degree of deviation between the indoor swing data, indoor hitting effect data and standard hitting data when the confidence level is greater than the threshold.

[0128] The task generation submodule is used to determine whether an outdoor practical training task for the current user needs to be generated when the deviation degree is greater than or equal to the preset deviation degree. This practical training task is then associated with the user terminal.

[0129] Optionally, the task generation module includes:

[0130] The task matching submodule is used to match all available practical training tasks for the current scene data from the preset task database.

[0131] The Deviation Type submodule is used to obtain specific deviation data from the degree of deviation, and to determine the deviation type between the indoor swing data, indoor hitting effect data and standard hitting data based on the deviation data;

[0132] The task filtering submodule is used to select practical training tasks that match the deviation type from the candidate practical training tasks and send them to the outdoor sensing terminal.

[0133] Optional, the outdoor impact analysis module includes:

[0134] The rule generation submodule is used by outdoor sensing terminals to generate task recognition rules based on actual combat training tasks.

[0135] The outdoor effects submodule is used by the outdoor sensing terminal to collect outdoor swing data of users during practical training tasks, and output outdoor hitting effect data based on task recognition rules.

[0136] The outdoor task data submodule is used to package outdoor swing data and outdoor hitting effect data to obtain task result data, and send it to the user data analysis model.

[0137] Optional, the outdoor effects submodule includes:

[0138] Wearable sensing unit, used for wearable sensing devices to collect outdoor swing data from users;

[0139] The visual sensing subunit is used by the visual laser sensing end to emit laser markers to the outdoor training field and to acquire video data recording the trajectory of the golf ball.

[0140] The first effect generation unit is used to determine the distance change information between the laser marker and the golf ball's movement trajectory based on trajectory video data and task recognition rules, and obtain outdoor hitting effect data.

[0141] Optionally, the outdoor effects submodule also includes:

[0142] The location acquisition unit is used to acquire the user's location information and determine whether the location information matches the preset location of the actual training task.

[0143] The positioning and tracking unit is used to generate the hitting position and tracking instructions and send them to the user terminal when the positioning information matches the preset positioning.

[0144] The direction determination unit is used to send the hitting direction data and target point data to the user terminal when the user terminal reaches the hitting position;

[0145] The second effect generation unit is used to collect outdoor swing data from the user via a wearable sensor, while the user terminal is used to receive the hit effect data uploaded by the user.

[0146] Specific limitations regarding the data fusion system combining indoor and outdoor virtual reality in a metaverse-themed urban golf course can be found in the limitations of the data fusion method described above, and will not be repeated here. Each module in the aforementioned data fusion system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0147] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course.

[0148] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course.

[0149] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course.

[0150] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0151] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0152] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse-themed urban golf course, characterized in that: When a user completes a swing motion indoors, the system acquires indoor swing data collected by indoor sensing terminals, representing the user's swing process, and sends the indoor swing data to a pre-trained user data analysis model. The user data analysis model identifies scene data associated with indoor swing data and generates indoor hitting effect data based on the scene data; The user data analysis model retrieves pre-stored standard hitting data corresponding to the current scenario data, and determines whether the outdoor combat training task is generated by the current user based on indoor swing data, indoor hitting effect data, and standard hitting data. If so, based on the scene data, the corresponding practical training task is matched from the preset task database and sent to the outdoor sensing terminal; The outdoor sensing terminal acquires the task result data of the user's practical training task and sends the task result data to the user data analysis model; The user data analysis model generates a training analysis report that matches the current user based on indoor swing data and task result data, and sends it to the user terminal that is bound to the user's identity information.

2. The data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course according to claim 1, characterized in that, The steps of the user data analysis model to identify scene data associated with indoor swing data and to generate indoor hitting effect data based on the scene data include: The user data analysis model identifies the scene data selected by the user, which includes golf course environment data, weather data, and swing scene data. After collecting indoor swing data, the indoor sensing terminal adjusts the simulated flight parameters of the golf ball based on the scene data to obtain indoor hitting effect data.

3. The data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course according to claim 1, characterized in that, The user data analysis model retrieves pre-stored standard hitting data corresponding to the current scenario data. Based on indoor swing data, indoor hitting effect data, and standard hitting data, the step of determining whether it is an outdoor practical training task generated by the current user includes: Identify the user terminal associated with the indoor swing data, and retrieve the historical swing data and historical hitting effect data of the user terminal under the same scenario data; Based on historical swing data and historical hitting effect data, determine the confidence level of the indoor swing data and indoor hitting effect data for this period of time; When the confidence level is greater than the threshold, the degree of deviation between the indoor swing data, indoor hitting effect data and standard hitting data is calculated. When the deviation is greater than or equal to the preset deviation, it is determined that it is an outdoor practical training task for the current user's production line, and this practical training task is associated with the user's terminal.

4. The data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course according to claim 1, characterized in that, If so, the step of matching the corresponding practical training task from the preset task database based on the scene data and sending it to the outdoor sensing terminal includes: Match all available practical training tasks for the current scenario data from the preset task database; Specific deviation data is obtained from the degree of deviation, and the type of deviation between the indoor swing data, indoor hitting effect data and standard hitting data is determined based on the deviation data; The live-fire training tasks that match the deviation type are selected from the candidate live-fire training tasks and sent to the outdoor sensing terminal.

5. The data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course according to claim 1, characterized in that, The steps of the outdoor sensing terminal acquiring task result data of the user's practical training task and sending the task result data to the user data analysis model include: Outdoor sensing terminals generate task recognition rules based on actual combat training missions; The outdoor sensing terminal collects outdoor swing data from users' practical training tasks and outputs outdoor hitting effect data based on task recognition rules. The outdoor swing data and outdoor hitting effect data are packaged to obtain task result data, which is then sent to the user data analysis model.

6. The data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course according to claim 1, characterized in that, The outdoor sensing terminal includes a wearable sensing terminal and a visual laser sensing terminal. The steps of the outdoor sensing terminal collecting outdoor swing data of users during practical training tasks and outputting outdoor hitting effect data based on task recognition rules include: The wearable sensor collects the user's outdoor golf swing data; The visual laser sensing end is used to emit laser markers to the outdoor training field and to acquire video data recording the trajectory of the golf ball. Based on trajectory video data and task recognition rules, the distance change information between the laser marker and the golf ball's trajectory is determined to obtain outdoor hitting effect data.

7. The data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course according to claim 1, characterized in that, The step of the outdoor sensing terminal collecting outdoor swing data from users' practical training tasks and outputting outdoor hitting effect data based on task recognition rules also includes the following steps: Obtain the user's location information and determine whether the location information matches the preset location for the actual combat training task; When the location information matches the preset location, a shot position and tracking instructions are generated and sent to the user's device. When the user reaches the hitting position, the hitting direction data and target point data are sent to the user. Wearable sensors collect data on the user's outdoor swing, while the user terminal receives the data on the hitting effect uploaded by the user.

8. A data fusion system based on the combination of indoor and outdoor virtual reality in a metaverse-themed urban golf course, characterized in that: The indoor sensing module is used to acquire indoor swing data collected by the indoor sensing terminal when the user completes the swing action indoors, representing the user's swing process, and send the indoor swing data to the pre-trained user data analysis model. The indoor hitting analysis module is used by the user data analysis model to identify scene data associated with indoor swing data and generate indoor hitting effect data based on the scene data. The task judgment module is used by the user data analysis model to retrieve the pre-stored standard hitting data corresponding to the current scene data, and to determine whether the task is an outdoor combat training task generated by the current user based on the indoor swing data, indoor hitting effect data and standard hitting data. The task generation module is used to match the corresponding practical training task in the preset task database based on the scene data and send it to the outdoor sensing terminal if the scenario is true. The outdoor impact analysis module is used by the outdoor sensing terminal to acquire the task result data of the user's combat training mission and send the task result data to the user data analysis model. The report analysis module is used by the user data analysis model to generate a training analysis report that matches the current user based on indoor swing data and task result data, and send it to the user terminal that is bound to the user's identity information.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the data fusion method based on the combination of indoor and outdoor virtual reality in a metaverse city golf course as described in any one of claims 1 to 7.

Images