Visual cognition information training method, device and system based on VR (virtual reality)

Abstract

The invention discloses a visual cognition information training method, device and system based on VR virtual reality, and relates to the technical field of virtual reality and artificial intelligence, and the method comprises the steps: S1, collecting position movement data of a user in a VR environment in real time through a sensor, S2, analyzing a movement mode of the user according to the position movement data, and generating a movement mode report, s3, evaluating spatial memory path characteristics of the user based on the mobile mode report; S4, adjusting a spatial memory path prompting mechanism in a personalized manner according to an evaluation result so as to optimize a memory coding strategy effect; according to the visual cognition information training method, device and system based on VR virtual reality, personalized adjustment is performed on a spatial memory path prompting mechanism according to the position movement mode of the user in the VR environment, so that the problem of poor memory coding strategy effect is solved.

Description

Technical Field

[0001] The present invention relates to the field of virtual reality and artificial intelligence technology, and in particular to a method, device and system for visual cognitive information training based on VR virtual reality. Background Art

[0002] In current cognitive training research, virtual reality technology is widely used in visual cognitive information training, especially in spatial memory and path learning. VR environment can provide an immersive spatial experience, allowing users to simulate real scenes in a virtual environment, thereby conducting spatial cognitive training. However, existing VR visual cognitive training methods still have deficiencies in personalized adaptability, especially for different users' spatial memory abilities and path learning strategies, and lack a dynamic adjustment mechanism.

[0003] In the prior art, spatial memory training usually adopts a fixed path prompt mechanism, such as visual clues (such as arrows, marking points, etc.) or auditory guidance (such as voice prompts) in a VR environment to assist users in completing path learning. Although these prompt mechanisms can help users establish spatial cognition, due to the differences in spatial memory strategies of different users, fixed prompt methods often cannot meet personalized needs. For example, for users with strong spatial memory ability, too many prompts may reduce their active exploration ability, while for users with weak spatial memory ability, insufficient prompts may lead to poor training results. In addition, existing VR cognitive training methods also have limitations in recording and analyzing user behavior. Usually, only the user's final task completion is focused on, and there is a lack of in-depth analysis of their behavioral characteristics such as position movement patterns and path preferences. Due to the lack of personalized data-driven adjustment strategies, the existing training methods cannot dynamically optimize the spatial memory path prompt mechanism according to the user's actual situation, thereby affecting the overall training effect. Summary of the invention

[0004] The purpose of the present invention is to provide a method, device and system for visual cognitive information training based on VR virtual reality, which can personalize the spatial memory path prompt mechanism according to the user's position movement mode in the VR environment to solve the problem of poor effect of memory encoding strategy.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for visual cognitive information training based on VR virtual reality, the method comprising:

[0006] S1, collects the user's position movement data in the VR environment in real time through sensors;

[0007] S2. analyzing the user's movement pattern based on the location movement data and generating a movement pattern report;

[0008] S3. Evaluate the spatial memory path characteristics of the user based on the movement pattern report;

[0009] S4. Personalize and adjust the spatial memory path prompt mechanism according to the evaluation results to optimize the effect of the memory encoding strategy, including calculating the probability of the user getting lost in different areas. The specific formula is: B = A × D × C × G × H;

[0010] Among them, B represents the probability of the user getting lost in different areas, A represents the complexity value of the path in the VR scenario, D represents the user's memory level value, C represents the physical difficulty of the path, G represents the clarity value of the training content, and H represents the optimization degree value of the path prompt.

[0011] Preferably, S1 includes collecting the continuous position data of the user and calculating the proportion of the total moving distance accumulated by the user during the VR training process in the overall moving distance. The specific formula is: E = q m ;

[0012] Among them, E represents the proportion of the total moving distance accumulated by the user during the VR training process to a certain time point in the overall moving distance, q represents the proportion of the time elapsed by the user during the VR training process to a certain time point in the overall training time, and m represents the trajectory parameter.

[0013] Preferably, S2 includes selecting the target point in the VR scenario and calculating the movement trajectory of the user around the target point. The specific formula is: Z = abt;

[0014] Among them, Z represents the spatial area covered by the movement trajectory of the user during the VR training process, a represents the distance from the user's current position to the training target, b represents the moving speed of the user during the VR training, and t represents the time;

[0015] Generate a movement pattern report to determine whether the user has a clear target exploration path.

[0016] Preferably, S3 includes modeling the VR training environment and calculating the connectivity of the path used by the user during the VR training process. The specific formula is: X = U / V;

[0017] Among them, X represents the connectivity of the path used by the user during the VR training process, U represents the number of paths actually walked by the user during the VR training process, and V represents the total number of paths that can be selected theoretically in the VR training environment;

[0018] Generate a spatial memory path feature report.

[0019] Preferably, the sensors in S1 include an inertial measurement unit, an optical tracking system, and a lidar, which are used to collect the position, orientation, and speed data of the user in the VR environment in real time.

[0020] Preferably, the calculation formula for the complexity value A of this path in the VR scenario in S4 is:

[0021] A = (L + Q) × R;

[0022] Among them, A represents the complexity value of this path in the VR scenario, L represents the number of fork roads that the user may encounter in the VR scenario, Q represents the path curvature, and R represents the dynamic obstacle influence coefficient.

[0023] Preferably, S4 further includes determining a preset time window length in the VR environment and calculating the position deviation of the user within the time window. The specific formula is:

[0024] Among them, d represents the position deviation of the user within the time window, x i represents the user coordinates of each time node, x0 represents the coordinates of the first node, and n represents the number of records within the time window;

[0025] Set a threshold S. Mark the key attention areas for all position deviations greater than the threshold S and increase the number of memory assistance icons in these areas.

[0026] Preferably, the calculation formula for the memory level value D of the user in S4 is:

[0027]

[0028] Among them, D represents the memory level value of the user, R1 represents the number of correct recalls, R2 represents the number of incorrect recalls, e represents the base of the natural logarithm, W represents the time elapsed after training, and W0 represents the memory decay time constant.

[0029] A visual cognitive information training device based on VR virtual reality, which is used to implement the steps of the visual cognitive information training method based on VR virtual reality. The device includes:

[0030] A data acquisition module, which is used to collect the position movement data of the user in the VR environment in real time through sensors;

[0031] A movement pattern analysis module connected to the data acquisition module, which is used to analyze the movement pattern of the user according to the position movement data and generate a movement pattern report;

[0032] A spatial memory evaluation module connected to the movement pattern analysis module, which is used to evaluate the spatial memory path characteristics of the user based on the movement pattern report;

[0033] A path prompt optimization module connected to the spatial memory evaluation module, which is used to adjust the spatial memory path prompt mechanism personalized according to the evaluation results to optimize the effect of the memory encoding strategy.

[0034] A visual cognitive information training system based on VR virtual reality, the system includes a server, and the server includes:

[0035] A memory, on which a computer program is stored;

[0036] A processor, configured to execute the computer program in the memory to implement the steps of the visual cognitive information training method based on VR virtual reality.

[0037] From the above technical solutions, it can be seen that the present invention has the following beneficial effects:

[0038] The visual cognitive information training method, device and system based on VR virtual reality collect the position movement data of the user in the VR environment in real time through a sensor, analyze the movement pattern of the user according to the position movement data and generate a movement pattern report, evaluate the spatial memory path characteristics of the user based on the movement pattern report, and personalize and adjust the spatial memory path prompting mechanism according to the evaluation result to optimize the memory encoding strategy effect. It can dynamically adjust the path prompting intensity according to the user's spatial memory ability, can accurately identify the learning characteristics of the user, and then provide a targeted path optimization scheme. It can evaluate the spatial memory path characteristics of the user in real time and adjust the prompting strategy during the training process, can effectively improve the user's spatial cognitive ability, enable the user to establish a clearer spatial memory structure in the VR training, make the VR training process more natural, enable the user to perform spatial cognitive training under conditions closer to the real environment, thereby improving the practicability and effectiveness of the training. Through real-time data collection, personalized path prompt optimization, dynamic adjustment of training strategies and in-depth behavior analysis, it makes up for the deficiencies of the existing VR visual cognitive training methods in terms of personalized adaptability, significantly improves the user's spatial memory ability and path learning effect, and personalizes and adjusts the spatial memory path prompting mechanism according to the position movement pattern of the user in the VR environment to solve the problem of poor memory encoding strategy effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flowchart of the method of the present invention;

[0040] Figure 2 It is a schematic diagram of module connection of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0042] As Figure 1 shown, the present invention provides a technical solution: a visual cognitive information training method based on VR virtual reality, the method comprising:

[0043] S1. Real-time collect the position movement data of the user in the VR environment through a sensor;

[0044] S2. Analyze the movement pattern of the user according to the position movement data and generate a movement pattern report;

[0045] S3. Evaluate the spatial memory path characteristics of the user based on the movement pattern report;

[0046] S4. Personalize and adjust the spatial memory path prompt mechanism according to the evaluation result to optimize the effect of the memory encoding strategy, including calculating the probability of the user getting lost in different regions, and the specific formula is: B = A × D × C × G × H;

[0047] wherein, B represents the probability of the user getting lost in different regions, A represents the complexity value of the path in the VR scene, D represents the memory level value of the user, C represents the physical difficulty of the path, G represents the clarity value of the training content, and H represents the optimization degree value of the path prompt.

[0048] This method is based on a VR virtual reality environment. It uses sensors to collect the position movement data of users in the virtual space in real time, so as to accurately record the movement trajectories and behavior patterns of users. Through data analysis technology, the movement patterns of users are analyzed to identify their spatial exploration behaviors, and a movement pattern report is generated. This report reflects the users' path selection habits, turning preferences, and possible lost areas. Further, the system evaluates the spatial memory path characteristics of users based on this report, including the stay time of users in different areas, path backtracking situations, and the frequency of incorrect navigation, etc. Combining the evaluation results, the system dynamically adjusts the prompting mechanism of the spatial memory path, such as increasing visual guiding signs, enhancing audio prompts, or appropriately reducing environmental interference, so as to optimize the memory encoding strategy of users. The core optimization basis is the lost probability calculation formula, which combines path complexity, the memory level of users, physical difficulty, the clarity of training content, and the optimization degree of path prompts, ensuring the personalization and scientific nature of the path guiding mechanism. Through this method, it can help users build spatial memory more efficiently in the VR environment, improve their navigation ability and cognitive training effect. The present invention can effectively improve the spatial cognitive training effect of users in the VR environment. Through accurate analysis based on sensor data, this method can evaluate the spatial exploration ability of users in real time and adjust the path prompting strategy accordingly, so as to optimize the memory encoding method of users. The personalized path optimization mechanism can reduce the lost probability of users in complex environments, improve the spatial positioning ability and memory retention ability. In addition, this method uses a scientific calculation model to quantitatively analyze multi-dimensional factors such as path complexity, physical difficulty, and the cognitive ability of users, so as to provide the optimal guiding strategy. Compared with traditional spatial memory training methods, this method is more intelligent and adaptive, and can dynamically adjust the training content according to the ability levels of different users, making the cognitive training more accurate and efficient. At the same time, this method can also be extended to multiple application scenarios such as rehabilitation training and virtual navigation assistance, with broad application prospects and market value.

[0049] S1 includes collecting the continuous position data of users and calculating the proportion of the total accumulated movement distance of users during the VR training process in the overall movement distance. The specific formula is: E = q m ;

[0050] where E represents the proportion of the total accumulated movement distance of users during the VR training process up to a certain time point in the overall movement distance, q represents the proportion of the time elapsed by users during the VR training process up to a certain time point in the overall training time, and m represents the trajectory parameter.

[0051] This method records the user's location information in real time through sensors in the VR environment and analyzes the user's trajectory during the training process. The system first collects the user's continuous location data to ensure accurate tracking of their movement trajectory throughout the training process and calculates the user's cumulative moving distance. By comparing the moving distance of the user before a certain time point with the total moving distance in the overall training, the moving distance ratio E can be obtained. Combining the time ratio q of the user and the trajectory parameter m, the movement characteristics of the user at different time stages can be evaluated. The trajectory parameter m can be determined by factors such as the complexity of the training environment, the user's movement pattern, and path deviation to ensure that the calculated E value can accurately reflect the user's spatial exploration during the VR training process. This calculation method helps to analyze the user's behavior patterns at different training stages and provides data support for personalized optimization of training strategies. This method can effectively improve the accuracy and personalization of VR training. By calculating the ratio of the user's cumulative moving distance, the user's movement behavior can be dynamically evaluated, enabling the system to adjust the training difficulty and hint strategy according to the user's movement. For example, if the E value is low, it may indicate that the user lacks exploration during the training process. At this time, the system can increase path guidance or adjust the training tasks to enhance the user's movement participation. If the E value is high, it may mean that the user has excessive movement or repeated exploration during the training. At this time, the system can optimize the path design to reduce unnecessary movement loss. In addition, this method provides a data-driven approach, enabling the training system to monitor the user's behavior patterns in real time, ensuring that the training content matches the user's capabilities, and improving the scientificity and effectiveness of training. At the same time, this method is also applicable to other VR-based sports training, rehabilitation training, and behavior analysis fields, with high application value.

[0052] S2 includes selecting a target point in the VR scene and calculating the user's movement trajectory around the target point. The specific formula is: Z = abt;

[0053] Among them, Z represents the spatial area covered by the user's movement trajectory during VR training, a represents the distance from the user's current position to the training target, b represents the user's movement speed during VR training, and t represents time;

[0054] Generate a movement pattern report to determine whether the user has a clear target exploration path.

[0055] This method selects target points in the VR scene, calculates the movement trajectories of the user around these target points during training, and quantitatively analyzes the user's movement behavior through the mathematical formula Z = abt. Here, a represents the straight-line distance from the user's current position to the target point, which is used to measure the degree of proximity between the user and the target point during training; b represents the user's movement speed, reflecting the action efficiency during exploration; t is a time variable, and in combination with b, it calculates the movement distance of the user within a certain period of time. By calculating the Z value, it is possible to judge the user's movement range and path coverage, and analyze whether their exploration pattern is goal-oriented. After collecting these data, the system generates a movement pattern report to further evaluate the user's navigation behavior in the VR training environment. If the Z value is small, it indicates that the user moves within a small range, and there may be path repetition or insufficient exploration; if the Z value is large, it means that the user moves in a wider area and may have a more explicit goal-oriented behavior. This analysis can be used to optimize the user's training content and improve the effectiveness of path exploration. This method can effectively improve the path exploration efficiency and cognitive training quality of users in VR training. By calculating the Z value, the system can evaluate the user's movement range and target exploration in real time, providing a scientific basis for training optimization. Compared with traditional qualitative analysis methods, this method provides precise quantitative indicators, enabling the training system to more accurately judge the user's exploration pattern and adjust the training strategy in a timely manner. For example, if the user's Z value remains low, the system can guide the user to approach the target point more actively and optimize the difficulty setting of the training task; if the Z value is too high, it may indicate that the user has excessive movement during training, and the system can improve the training efficiency through path optimization or visual cues. In addition, this method can be widely applied to fields such as virtual reality cognitive training, vocational skill simulation training, and navigation ability assessment, providing scientific support for the application of VR technology in cognitive training.

[0056] S3 includes modeling the VR training environment and calculating the connectivity of the paths used by the user during VR training. The specific formula is: X = U / V;

[0057] Where X represents the connectivity of the paths used by the user during VR training, U represents the number of paths actually walked by the user during VR training, and V represents the total number of paths that can be selected theoretically in the VR training environment;

[0058] Generate a spatial memory path feature report.

[0059] This method first models the VR training environment to construct a complete path network, including all possible travel routes and passable areas. During the training process, the system records the user's movement path in real time, calculates the number of paths U actually selected by the user in the virtual environment, and extracts the total number of theoretically selectable paths V in the entire VR training scene. By calculating the path connectivity X = U / V, the user's path utilization can be quantified, reflecting their spatial exploration ability and path memory level. If the X value is high, it indicates that the user makes more use of the selectable paths, which may represent a more comprehensive exploration strategy and good spatial cognitive ability; if the X value is low, it indicates that the user's path selection is limited, and there may be a situation of relying on a single path or lacking exploration behavior. Based on this data, the system generates a spatial memory path feature report to analyze the user's navigation pattern in the training environment and provide targeted optimization suggestions, such as adding path hints, adjusting the difficulty of training tasks, or guiding the user to explore more paths, so as to improve the effect of their spatial cognitive training. This method provides a scientific quantitative index for VR cognitive training by calculating the path connectivity, enabling the training system to accurately evaluate the user's exploration strategy and path utilization. Compared with the traditional qualitative evaluation method, this method can dynamically adjust the training strategy based on the user's actual path behavior data, improving the effectiveness of VR cognitive training. For example, if the user's X value is low, the system can introduce a dynamic guidance mechanism to encourage the user to try unexplored paths and enhance spatial memory ability; if the X value is high, path interference factors can be appropriately increased to enhance the challenge of training. In addition, this method can also be used for the formulation of personalized training programs, enabling users with different cognitive levels to obtain the best training effect. At the same time, it can also be used in fields such as neurorehabilitation and vocational navigation training, providing extensive application value for VR cognitive training technology.

[0060] In S1, the sensors include an inertial measurement unit, an optical tracking system, and a lidar, which are used to collect the position, orientation, and velocity data of the user in the VR environment in real time. This method utilizes multiple sensor technologies to improve the accuracy of collecting the user's motion data in the VR training environment. The inertial measurement unit mainly consists of an accelerometer and a gyroscope, which can measure the user's attitude changes, acceleration, and angular velocity, providing fine-grained motion tracking data. The optical tracking system captures the physical position information of the user through a camera and uses computer vision algorithms to analyze the user's movement trajectory and direction changes, improving the accuracy of spatial positioning. The lidar measures the relative position of the user and the surrounding environment by emitting laser pulses and receiving reflected signals, ensuring the high accuracy and stability of the positioning data. The combination of the three enables the system to obtain the user's position information, orientation angle, and motion speed in real time, achieving high-precision spatial motion data collection and providing basic data support for subsequent functions such as mobile mode analysis and spatial memory path evaluation. By integrating the inertial measurement unit, the optical tracking system, and the lidar, this method enables the VR training system to collect the user's motion data in real time and with high precision. Compared with a single-sensor solution, this multi-sensor fusion technology can make up for their respective limitations. For example, the IMU may have a drift problem during long-term use, while the optical tracking system may be affected by light, and the lidar has higher ranging accuracy in complex environments. Through data fusion and calibration, the system can effectively improve the measurement accuracy of the user's position, orientation, and velocity, thus ensuring that the navigation and cognitive training in the VR training environment are more accurate and smooth. In addition, this method can adapt to different types of VR applications, such as spatial cognitive training, motion rehabilitation training, immersive game experiences, etc., enhancing the applicability and reliability of VR technology in multiple scenarios.

[0061] In S4, the calculation formula for the complexity value A of this path in the VR scene is:

[0062] A = (L + Q) × R;

[0063] Among them, A represents the complexity value of this path in the VR scene, L represents the number of fork roads that the user may encounter in the VR scene, Q represents the path curvature, and R represents the dynamic obstacle influence coefficient.

[0064] This method quantifies the complexity of paths in a VR scenario through a mathematical model to optimize the path hint mechanism and enhance the user's cognitive training effect. The calculation of the path complexity value A comprehensively considers the number of bifurcations L of the path, the curvature Q, and the dynamic obstacle influence coefficient R. The number of bifurcations L is used to measure the number of decision points that the user may encounter during the movement. The more bifurcations there are, the greater the difficulty of path selection, thus increasing the user's cognitive load. The path curvature Q represents the degree of bending of the path. A curved path is more challenging than a straight path because the user needs to make more frequent direction adjustments and maintain spatial awareness. The dynamic obstacle influence coefficient R is used to quantify the possible moving obstacles in the VR environment, such as virtual pedestrians, vehicles, or environmental changes. The presence of these obstacles will affect the user's decision-making and path selection, increasing the difficulty of training. Through this calculation formula, the system can adjust the training strategy according to the complexity of different paths, such as enhancing path guidance, optimizing visual hints, or adjusting the distribution of dynamic obstacles, to ensure the personalization and effectiveness of training. This method provides a scientific and quantifiable way to evaluate the path complexity in a VR training environment, thereby optimizing the adaptability and effectiveness of cognitive training. Compared with the traditional empirical judgment method, this mathematical model can measure the path difficulty more accurately, enabling the system to dynamically adjust the training content and improve the user's spatial cognitive ability. For example, when the value of A is high, the system can appropriately increase path hints or reduce the influence of dynamic obstacles to reduce the user's cognitive burden and ensure the executability of training; when the value of A is low, the system can increase the path complexity, such as increasing the number of bifurcations or adjusting the path curvature, to enhance the training challenge. In addition, this method is not only applicable to VR cognitive training but can also be extended to multiple application scenarios such as autonomous driving simulation, robot path planning, and virtual reality navigation assistance, improving the path evaluation accuracy and training efficiency in a VR environment.

[0065] S4 also includes determining the length of a preset time window in the VR environment and calculating the position deviation of the user within the time window. The specific formula is:

[0066] where d represents the position deviation of the user within the time window, x i represents the user coordinates at each time node, x0 represents the coordinates of the first node, and n represents the number of records within the time window;

[0067] Set a threshold S. Mark the key attention areas for all position deviations greater than the threshold S and increase the number of memory assistance icons in these areas.

[0068] This method conducts a local analysis of the user's motion data by setting a time window to evaluate their spatial cognitive stability. First, a time window of a fixed length is set in the VR environment. Within this window, the user's position information is collected, and the position deviation d is calculated to measure the spatial movement stability of the user during this time period. Specifically, the system records multiple position points within the time window and calculates the average value of the offsets of these points relative to the first node to obtain the overall deviation level. When the value of d is large, it means that the user's movement path within this time window is relatively discrete, and there may be unclear exploration behavior or unstable path selection; when the value of d is small, it indicates that the user's path is relatively stable, which may suggest that they have established a relatively clear spatial memory. Based on this, the system sets a threshold S. When the position deviation exceeds S, the area is marked as a key attention area, and memory assistance icons are added in this area to strengthen the user's spatial memory, optimize the path hint mechanism, and improve the training effect. This method dynamically analyzes the user's position information by setting a time window, enabling the VR training system to accurately evaluate the user's spatial stability and path memory ability. Compared with traditional global path analysis methods, this time window deviation calculation model can provide a more refined local behavior assessment, enabling the system to adjust the training strategy in real time and improve the pertinence of spatial cognitive training. For example, for areas with a large position deviation, the system can increase visual assistance information such as signs, color changes, or virtual guiding lines to help the user better establish spatial memory; for areas with a small deviation, the system can reduce the hint information to enhance the user's independent exploration ability. In addition, this method can be applied to multiple fields such as navigation training, cognitive rehabilitation, and complex path planning to improve the training accuracy and intelligent level in the VR environment.

[0069] The calculation formula for the memory level value D of the user in S4 is as follows:

[0070] Among them, D represents the memory level value of the user, R1 represents the number of correct recalls, R2 represents the number of incorrect recalls, e represents the base of the natural logarithm, W represents the time elapsed after training, and W0 represents the memory decay time constant.

[0071] This method evaluates the training effect by quantitatively analyzing the user's memory performance in VR training and calculating their memory level value D. The first part of the formula reflects the user's recall accuracy rate, that is, the ratio of the number of correct recalls to the total number of recalls. The higher this ratio, the better the user's memory accuracy. The second part It represents the memory decay effect over time and uses an exponential decay model to simulate the forgetting curve of human memory. W represents the time elapsed after training, and W0 is the time constant of memory decay, whose value can be set according to experiments or user cognitive characteristics to reflect the memory retention ability of different individuals. The finally calculated D value can dynamically reflect the user's memory retention ability, and then be used to adjust the training strategy. For example, when the memory level drops, the review training can be enhanced, or when the memory level is relatively high, new content learning can be increased. This method provides a scientific and reasonable quantitative index to evaluate the user's memory level in VR cognitive training. Compared with traditional subjective evaluation or simple calculation of correct rate, this method combines the recall correct rate and the memory decay model, enabling the training system to more accurately adjust the content and difficulty. For example, if the D value drops rapidly, the system can increase the review training frequency or provide additional memory cues to enhance the user's long-term memory retention ability; if the D value is relatively high, indicating that the user has a good memory effect, the system can appropriately increase the training difficulty or introduce more complex cognitive tasks. In addition, this method can be applied to various memory training scenarios, such as medical rehabilitation, vocational skills training, VR education, etc., to improve the scientific and personalized level of VR cognitive training.

[0072] As Figure 2 shown, there is also provided a visual cognitive information training device based on VR virtual reality for implementing the steps of the visual cognitive information training method based on VR virtual reality. The device includes:

[0073] A data acquisition module for real-time collecting the position movement data of the user in the VR environment through sensors;

[0074] A movement pattern analysis module connected to the data acquisition module for analyzing the user's movement pattern based on the position movement data and generating a movement pattern report;

[0075] A spatial memory evaluation module connected to the movement pattern analysis module for evaluating the spatial memory path characteristics of the user based on the movement pattern report;

[0076] A path prompt optimization module connected to the spatial memory evaluation module for personalized adjusting the spatial memory path prompt mechanism according to the evaluation result to optimize the memory encoding strategy effect.

[0077] This device constructs an intelligent visual cognitive training system based on a VR environment. Through the collaborative work of four core modules: data collection, pattern analysis, spatial memory assessment, and path optimization hint, it realizes personalized cognitive training. First, the data collection module uses various sensors (such as inertial measurement units, optical tracking systems, lidar, etc.) to collect the position, direction, and speed data of the user in the VR environment in real time, ensuring high-precision recording of the user's movement trajectory. Subsequently, the movement pattern analysis module processes this data, identifies the user's movement patterns, extracts key features, and generates a movement pattern report, which reflects the user's path selection, exploration behavior, and spatial perception ability. Then, the spatial memory assessment module analyzes the spatial memory path features of the user based on this report, such as calculating indicators such as path connectivity, trajectory coverage, and memory retention level, to evaluate the user's spatial cognitive ability. Finally, the path hint optimization module dynamically adjusts the spatial memory path hint mechanism according to the evaluation results, such as by adjusting the intensity of the path guidance, optimizing visual or auditory hints, or even changing the difficulty of the training tasks, to optimize the memory encoding strategy and improve the user's spatial memory ability and VR navigation skills. This device provides an efficient and intelligent VR cognitive training solution. Compared with traditional cognitive training methods, this device can improve the user's spatial perception ability and path memory level through real-time data analysis and adaptive training optimization. Its core advantages include: through the data collection module, the system can monitor the user's movement data in real time and quickly feedback the analysis results to achieve dynamic adjustment of the training strategy. The system can provide personalized path hint optimization strategies according to the user's movement patterns and spatial memory characteristics, making the training more in line with individual needs. By quantitatively calculating indicators such as the user's path complexity, movement deviation, and memory retention rate, the training is more accurate and scientific, avoiding relying solely on subjective judgment. By continuously adjusting the path hint mechanism, it helps the user establish a stronger spatial memory ability, improve the navigation efficiency in the VR environment, and can also be used in fields such as neurorehabilitation, vocational training, and immersive learning.

[0078] There is also provided a visual cognitive information training system based on VR virtual reality. The system includes a server, and the server includes:

[0079] A memory, on which a computer program is stored;

[0080] A processor, configured to execute the computer program in the memory to implement the steps of the visual cognitive information training method based on VR virtual reality.

[0081] This system is based on a server architecture, combines a storage unit and a computing unit, and realizes visual cognitive information training in a VR virtual reality environment. The memory in the server stores a computer program, which includes multiple core algorithm modules for data acquisition, user movement pattern analysis, spatial memory path evaluation, path hint optimization, etc. When the processor executes this computer program, it can analyze and calculate the real-time data in the VR environment to achieve dynamic training adjustment. First, the server receives data from VR devices or related sensors, stores and processes the user's location information, movement patterns, and behavioral data during the training process. Subsequently, the computer program runs various analysis models, such as path complexity calculation, position deviation measurement, memory level evaluation, etc., to quantify the user's cognitive training performance. Based on the analysis results, the processor executes training optimization strategies, such as adjusting the path hint mechanism, optimizing the VR scene layout, or dynamically modifying the training tasks, to provide a personalized training plan that better meets the user's needs. In addition, the server can also achieve cross-device training synchronization through cloud data storage and computing, improving the continuity and adaptability of training. This system is based on a server architecture to achieve efficient and scalable VR visual cognitive training. Compared with traditional VR training methods, it has the following advantages: The processor in the server can efficiently execute complex computing tasks, such as path optimization, memory evaluation, etc., to ensure the real-time and accuracy of training feedback. The memory can store the user's training data, support long-term tracking of the user's cognitive training progress, and optimize personalized training strategies based on historical data. The server can be deployed locally or in the cloud, enabling the VR training system to support cross-device synchronous training, improving data sharing and training coherence. The system can dynamically adjust path hints, training task difficulty, etc. based on the user's real-time training performance, improving training adaptability and scientificity. This system can not only be used for VR cognitive training, but also be extended to multiple application scenarios such as intelligent navigation, medical rehabilitation, and vocational training, enhancing the versatility and commercial value of VR training technology.

[0082] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A visual cognitive information training method based on VR virtual reality, characterized in that: The method comprises: S1, collects the user's position movement data in the VR environment in real time through sensors; S2. analyzing the user's movement pattern based on the location movement data and generating a movement pattern report; S3, assessing users’ spatial memory path characteristics based on mobility pattern reports; S4. Personalize and adjust the spatial memory path prompt mechanism according to the evaluation results to optimize the effect of the memory encoding strategy, including calculating the probability of users getting lost in different areas. The specific formula is: B = A × D × C × G × H; Among them, B represents the probability of the user getting lost in different areas, A represents the complexity value of the path in the VR scene, D represents the user's memory level value, C represents the physical difficulty of the path, G represents the clarity value of the training content, and H represents the optimization degree value of the path prompt.

2. The method for visual cognitive information training based on VR virtual reality according to claim 1, characterized in that: S1 includes collecting the user's continuous position data and calculating the proportion of the user's accumulated total moving distance in the overall moving distance during the VR training process. The specific formula is: E=q m ; Among them, E represents the proportion of the total moving distance accumulated by the user in the VR training process up to a certain point in time in the overall moving distance, q represents the proportion of the time elapsed by the user in the VR training process up to a certain point in time in the overall training time, and m represents the trajectory parameter.

3. The method for visual cognitive information training based on VR virtual reality according to claim 1, characterized in that: S2 includes selecting a target point in the VR scene and calculating the motion trajectory of the user around the target point. The specific formula is: Z=abt; Where Z represents the spatial area covered by the user's moving trajectory during VR training, a represents the distance from the user's current position to the training target, b represents the user's moving speed during VR training, and t represents time; Generate movement pattern reports to determine whether users have a clear path to explore.

4. The method for visual cognitive information training based on VR virtual reality according to claim 1, characterized in that: S3 includes modeling the VR training environment and calculating the connectivity of the paths used by the user during the VR training process, and the specific formula is: X=U / V; Among them, X represents the connectivity of the paths used by the user during VR training, U represents the number of paths actually walked by the user during VR training, and V represents the total number of paths that can be theoretically selected in the VR training environment; Generates a spatial memory path characteristics report.

5. The method for visual cognitive information training based on VR virtual reality according to claim 1, characterized in that: The sensors in S1 include an inertial measurement unit, an optical tracking system and a lidar, which are used to collect the user's position, direction and speed data in the VR environment in real time.

6. The method for visual cognitive information training based on VR virtual reality according to claim 1, characterized in that: The calculation formula of the complexity value A of the path in the VR scene in S4 is: A = (L + Q) × R; Among them, A represents the complexity value of the path in the VR scene, L represents the number of forks that the user may encounter in the VR scene, Q represents the path curvature, and R represents the dynamic obstacle influence coefficient.

7. The method for visual cognitive information training based on VR virtual reality according to claim 1, characterized in that: The S4 also includes determining a preset time window length in the VR environment and calculating the position deviation of the user within the time window. The specific formula is: Among them, d represents the position deviation of the user in the time window, x i represents the user coordinates of each time node, x0 represents the coordinates of the first node, and n represents the number of records in the time window; A threshold S is set, and all position deviations greater than the threshold S are marked as key areas of interest, and the number of memory aid icons in these areas is increased.

8. The method for visual cognitive information training based on VR virtual reality according to claim 1, characterized in that: The calculation formula of the user's memory level value D in S4 is: Where D represents the user's memory level, R1 represents the number of correct recalls, R2 represents the number of incorrect recalls, e represents the natural logarithm base, W represents the time after training, and W0 represents the memory decay time constant.

9. A visual cognition information training device based on VR virtual reality, used to implement the steps of the visual cognition information training method based on VR virtual reality according to any one of claims 1 to 8, characterized in that: The device comprises: A data acquisition module is used to collect the user's position movement data in the VR environment in real time through sensors; A mobility pattern analysis module connected to the data acquisition module, for analyzing the user's mobility pattern based on the location movement data and generating a mobility pattern report; a spatial memory evaluation module connected to the movement pattern analysis module, for evaluating the user's spatial memory path characteristics based on the movement pattern report; The path cue optimization module connected to the spatial memory evaluation module is used to personalize the spatial memory path cue mechanism according to the evaluation results to optimize the effect of the memory encoding strategy.

10. A visual cognitive information training system based on VR virtual reality, characterized in that: The system comprises a server, wherein the server comprises: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of the visual cognitive information training method based on VR virtual reality as described in any one of claims 1 to 8.

Images