A method and system for enhancing elderly user experience of virtual reality equipment

Abstract

The present invention discloses a method and system for enhancing the experience of elderly users of virtual reality equipment, including: selecting visual fatigue evaluation indicators, constructing a visual fatigue evaluation model based on the visual fatigue evaluation indicators, evaluating the degree of visual fatigue, and obtaining visual fatigue evaluation information; predicting the dizziness of target users, predicting the real-time dizziness of target experience users and adjusting equipment operation parameters; analyzing historical user experience paths of different experience content categories and constructing experience content portraits, and forming an experience content portrait database based on the experience content portraits; monitoring real-time experience users, analyzing the real-time physical load conditions of target experience users, judging whether there is discomfort in the experience, and adjusting the personalized content experience path. Improve the comfort of elderly users when using virtual reality equipment, and improve the integrity of the experience content when experiencing by adjusting the content experience path, so as to avoid experience interruption caused by discomfort in the experience.

Description

Technical Field

[0001] The present invention relates to the technical field of virtual reality device experience enhancement, and in particular to a method and system for enhancing the user experience of elderly people with virtual reality devices. Background Art

[0002] With the rapid development of virtual reality (VR) technology, its application scope has gradually expanded to cover entertainment, education, medical and other fields. However, for elderly users, the use experience of VR devices is somewhat challenging. Due to the deterioration of physical functions, such as changes in vision, hearing, balance and reaction speed, elderly users are often prone to dizziness, eye discomfort, headaches and fatigue when using VR devices. These discomforts not only limit the use of VR devices by elderly users, but also reduce the fun and benefits they get from them to a certain extent.

[0003] At present, although there are some VR devices and applications for elderly users on the market, most of these solutions focus on lightweight hardware design or simple user interface optimization, and fail to fully consider the special physiological and psychological needs of elderly users. For example, when wearing VR headsets, elderly users may feel uncomfortable or oppressive due to the weight of the device and the way it is worn; and during use, virtual scenes that move quickly or change perspectives are more likely to trigger their dizziness. In addition, traditional VR systems usually do not have personalized adjustment functions and cannot optimize the visual, auditory and interactive methods according to the actual experience of elderly users, which further affects their user experience and causes experience interruptions. Therefore, how to better improve the virtual reality device experience of elderly users and improve the experience integrity of the experience content is an urgent problem to be solved. Summary of the invention

[0004] The present invention overcomes the defects of the prior art and provides a method and system for enhancing the elderly user experience of virtual reality equipment. An important purpose of the present invention is to improve the elderly user's virtual reality device experience and enhance the integrity of the elderly user experience.

[0005] To achieve the above-mentioned purpose, the present invention provides a method for enhancing the experience of elderly users of virtual reality equipment in a first aspect, comprising:

[0006] Obtain visual fatigue assessment factors, analyze the correlation between each visual fatigue assessment factor and visual fatigue, select visual fatigue assessment indicators, and obtain visual fatigue assessment indicator information;

[0007] Building a visual fatigue assessment model based on the visual fatigue assessment index information, assessing the visual fatigue degree of the target user, and obtaining visual fatigue degree assessment information;

[0008] Predicting the dizziness of the target user based on the visual fatigue assessment information, predicting the real-time dizziness of the target user and adjusting the device operating parameters;

[0009] Acquire historical usage monitoring information, analyze historical user experience paths of different experience content categories according to the historical usage monitoring information and construct experience content portraits, and form an experience content portrait database according to the experience content portraits;

[0010] Monitor the real-time experience users, analyze the real-time physical load status of the target experience users, determine whether there is any discomfort in the experience, and adjust the personalized content experience path based on the experience content portrait database.

[0011] In this solution, the steps of obtaining visual fatigue assessment factors, analyzing the correlation between each visual fatigue assessment factor and visual fatigue, selecting visual fatigue assessment indicators, and obtaining visual fatigue assessment indicator information specifically include:

[0012] Obtain visual fatigue assessment factors, calculate the Spearman correlation coefficient between each visual fatigue assessment factor and visual fatigue, and form a Spearman correlation coefficient matrix;

[0013] Preset a Spearman correlation coefficient threshold, perform threshold processing on the Spearman correlation coefficient matrix, set data less than the Spearman correlation coefficient threshold to zero, and form an initial set of evaluation factors based on the updated Spearman correlation coefficient matrix;

[0014] Calculating the similarity between the evaluation elements according to the initial set of evaluation elements to form a similarity matrix, constructing a vertex matrix using the sum of the diagonal elements of the similarity matrix, and subtracting the similarity matrix from the vertex matrix to form a Laplace matrix;

[0015] Perform eigendecomposition on the Laplace matrix to obtain eigenvalues ​​and corresponding eigenvectors, preset a number of cluster centers and select a corresponding number of minimum non-zero eigenvalues ​​and eigenvectors, use the selected eigenvectors as new data representations, and construct an eigenvector space;

[0016] Using the K-means algorithm in combination with the feature vector space to perform multiple clustering, classifying each evaluation factor in the initial set of evaluation factors into categories, and obtaining category classification result information;

[0017] The evaluation factors of each category are sorted in combination with the Spearman correlation coefficient matrix and the category division result information, and the visual fatigue evaluation index is selected based on the sorting result to obtain the visual fatigue evaluation index information.

[0018] In this solution, the visual fatigue assessment model is constructed based on the visual fatigue assessment index information, the visual fatigue degree of the target user is assessed, and the visual fatigue degree assessment information is obtained, which specifically includes:

[0019] Obtain historical visual fatigue assessment instances with different fatigue levels, extract assessment parameters of corresponding visual assessment indicators in each historical visual fatigue assessment instance according to the visual fatigue assessment indicator information, and associate them with the fatigue level to form an assessment instance data set;

[0020] Constructing a visual fatigue assessment model based on a support vector machine, using the assessment instance data set to construct a training data set to train the visual fatigue assessment model, and using a cross-validation method to perform hyperparameter optimization to obtain a visual fatigue assessment model that meets expectations;

[0021] Monitor the target user to obtain real-time monitoring information, the real-time monitoring information including eye movement monitoring information and physiological monitoring information, and perform data preprocessing on the real-time monitoring information;

[0022] The pre-processed real-time monitoring information is input into the visual fatigue assessment model for analysis, and feature extraction is performed on the input data to obtain eye movement features and physiological features and form a feature vector;

[0023] The corresponding decision function value is calculated based on the constructed feature vector, and the decision function value is the distance between the target feature vector and the decision hyperplane. The visual fatigue degree of the target user is determined based on the decision function value to obtain visual fatigue degree evaluation information.

[0024] In this solution, the dizziness condition of the target user is predicted according to the visual fatigue degree assessment information, the real-time dizziness condition of the target experience user is predicted and the device operation parameters are adjusted, specifically including:

[0025] Constructing a dizziness prediction model based on a convolutional neural network, obtaining visual fatigue assessment information and real-time monitoring information, and inputting them into the dizziness prediction model for analysis;

[0026] Taking the visual fatigue state as a priori feature, feature extraction is performed on the input visual fatigue degree assessment information, and a feature matrix of various dizziness conditions corresponding to the visual fatigue degree feature is retrieved in a preset search space according to the extracted visual fatigue degree feature;

[0027] Performing similarity calculation between the acquired feature matrices of various dizziness conditions and the real-time monitoring information to obtain similarity values, using the similarity values ​​as confidence indicators of various dizziness conditions, sorting the various dizziness conditions, and obtaining a dizziness condition sorting table;

[0028] According to the dizziness condition ranking table, the dizziness condition category with the highest confidence is selected for output to obtain dizziness condition prediction information; according to the dizziness condition prediction information, it is determined whether the virtual reality device needs to be regulated, and if regulation is required, a regulation plan is formulated;

[0029] The real-time device usage parameters of the target user are obtained, and the historical control scheme under the corresponding dizziness condition is obtained in combination with the dizziness condition prediction information. A matching analysis is performed according to the obtained real-time device usage parameters, and the most frequently used control scheme is selected to adjust the operating parameters of the target virtual reality device.

[0030] In this solution, the acquisition of historical usage monitoring information, analyzing historical user experience paths of different experience content categories according to the historical usage monitoring information and constructing experience content portraits, and forming an experience content portrait database according to the experience content portraits specifically include:

[0031] Acquire historical usage monitoring information of the target virtual device, wherein the historical usage monitoring information includes device experience modes and experience durations of different experience contents when historical users use the target virtual device, as well as dizziness monitoring information and physiological status monitoring information;

[0032] Taking the experience content as the first category, the historical usage monitoring information is divided, the Euclidean distance between each experience content is calculated according to the historical usage monitoring information, and the distance is compared with a preset threshold to obtain first category division information;

[0033] Performing feature extraction on the first category classification information, extracting device experience mode features and experience duration features corresponding to each experience content category, and obtaining first category feature information;

[0034] According to the first category feature information, the time node features of experience mode switching during a single experience and the experience duration features of the corresponding switching mode and the switched mode are obtained to obtain historical user experience paths of different experience content categories;

[0035] An experience content portrait is constructed based on the historical user experience paths of different experience content categories. The dizziness condition monitoring information and physiological condition monitoring information are associated with the corresponding experience content portrait as subsidiary features to form an experience content portrait database.

[0036] In this solution, the real-time experience user is monitored, the real-time physical load status of the target experience user is analyzed, whether there is discomfort in the experience is determined, and the personalized content experience path is adjusted in combination with the experience content portrait database, specifically including:

[0037] Monitor the target user who uses the virtual reality device in real time, obtain the target user's real-time usage monitoring information, extract features from the target user's real-time usage monitoring information, and obtain the target user's experience content features, experience mode features, experience duration features, and user physical condition monitoring features of the content experienced by the target user through the virtual device in real time;

[0038] Based on the user's physical condition monitoring characteristics, the target user's visual fatigue degree and dizziness condition are evaluated, and the real-time load condition of the target user under the current experience content is analyzed to obtain real-time load condition analysis information;

[0039] Determine whether the target user has an uncomfortable experience based on the real-time load status analysis information, and if so, adjust the experience path of the target user based on the experience content portrait database;

[0040] The real-time experience path of the target user is constructed according to the experience content characteristics, experience mode characteristics and experience duration characteristics of the target user, and is searched in the experience content portrait database, and matched with each experience content portrait in the experience content portrait database to obtain matching portrait information;

[0041] Extracting the dizziness condition monitoring features and the physiological condition monitoring features corresponding to each matching portrait according to the matching portrait information, performing similarity calculation with the real-time load analysis information, and sorting the matching portraits according to the similarity;

[0042] Select the best matching portrait through sorting results and extract the corresponding historical user experience path to formulate an experience mode adjustment plan to regulate the target virtual reality device

[0043] A second aspect of the present invention provides a system for enhancing the user experience of elderly users of virtual reality devices, the system comprising: a memory and a processor, the memory containing a method program for enhancing the user experience of elderly users of virtual reality devices, the method program for enhancing the user experience of elderly users of virtual reality devices being executed by the processor to implement the following steps:

[0044] Obtain visual fatigue assessment factors, analyze the correlation between each visual fatigue assessment factor and visual fatigue, select visual fatigue assessment indicators, and obtain visual fatigue assessment indicator information;

[0045] Building a visual fatigue assessment model based on the visual fatigue assessment index information, assessing the visual fatigue degree of the target user, and obtaining visual fatigue degree assessment information;

[0046] Predicting the dizziness of the target user based on the visual fatigue assessment information, predicting the real-time dizziness of the target user and adjusting the device operating parameters;

[0047] Acquire historical usage monitoring information, analyze historical user experience paths of different experience content categories according to the historical usage monitoring information and construct experience content portraits, and form an experience content portrait database according to the experience content portraits;

[0048] Monitor the real-time experience users, analyze the real-time physical load status of the target experience users, determine whether there is any discomfort in the experience, and adjust the personalized content experience path based on the experience content portrait database.

[0049] The present invention discloses a method and system for enhancing the experience of elderly users of virtual reality equipment, including: selecting visual fatigue evaluation indicators, constructing a visual fatigue evaluation model based on the visual fatigue evaluation indicators, evaluating the degree of visual fatigue, and obtaining visual fatigue evaluation information; predicting the dizziness of the target user, predicting the real-time dizziness of the target experience user and adjusting the equipment operation parameters; analyzing the historical user experience paths of different experience content categories and constructing experience content portraits, and forming an experience content portrait database according to the experience content portraits; monitoring real-time experience users, analyzing the real-time physical load conditions of the target experience users, judging whether there is discomfort in the experience, and adjusting the personalized content experience path. Improve the comfort of elderly users when using virtual reality equipment, and improve the integrity of the experience content when experiencing by adjusting the content experience path, so as to avoid experience interruption caused by discomfort in the experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the drawings required for use in the embodiments or exemplary descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained according to the drawings without paying creative work.

[0051] Figure 1 A flow chart of a method for enhancing the user experience of elderly users of virtual reality devices provided by an embodiment of the present invention;

[0052] Figure 2 A personalized content experience path adjustment flow chart provided by an embodiment of the present invention;

[0053] Figure 3 A system block diagram of an embodiment of the present invention for enhancing the user experience of elderly users of virtual reality equipment;

[0054] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0056] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0057] Figure 1 A flow chart of a method for enhancing the user experience of elderly users of virtual reality devices provided by an embodiment of the present invention;

[0058] like Figure 1 As shown, the present invention provides a flow chart of a method for enhancing the experience of elderly users of virtual reality equipment, including:

[0059] S102, obtaining visual fatigue assessment factors, analyzing the correlation between each visual fatigue assessment factor and visual fatigue, selecting visual fatigue assessment indicators, and obtaining visual fatigue assessment indicator information;

[0060] S104, constructing a visual fatigue assessment model based on the visual fatigue assessment index information, assessing the visual fatigue degree of the target user, and obtaining visual fatigue degree assessment information;

[0061] S106, predicting the dizziness of the target user according to the visual fatigue degree assessment information, predicting the real-time dizziness of the target user and adjusting the device operation parameters;

[0062] S108, obtaining historical usage monitoring information, analyzing historical user experience paths of different experience content categories according to the historical usage monitoring information and constructing experience content portraits, and forming an experience content portrait database according to the experience content portraits;

[0063] S110, monitor the real-time experience user, analyze the real-time physical load status of the target experience user, determine whether there is any discomfort in the experience, and adjust the personalized content experience path in combination with the experience content portrait database.

[0064] It should be noted that in a method and system for enhancing the user experience of elderly users of virtual reality devices provided by the present invention, first, by obtaining evaluation factors related to visual fatigue, such as eye movement characteristics, pupil changes, blinking frequency, etc., evaluation indicators with high correlation with visual fatigue are selected to construct a visual fatigue evaluation model. Then, the visual fatigue degree evaluation information is used to further predict the dizziness of the target user when using the virtual reality device. And the operating parameters of the device, such as the screen refresh rate, field of view, etc., are adjusted accordingly to reduce the dizziness and discomfort of the user. In addition, the historical user experience paths under different experience content categories are analyzed using historical usage monitoring information to construct experience content portraits. These portraits are stored in the experience content portrait database. When the user is experiencing in real time, the user's physiological data and behavioral data are continuously monitored, the user's real-time physical load status is analyzed, and it is determined whether there is any discomfort in the experience. If discomfort is detected, the experience path of the current content is automatically adjusted in combination with the experience content portrait database. Minimize the user's discomfort in the virtual reality experience and improve the overall experience effect and experience completeness.

[0065] Further, in a preferred embodiment of the present invention, the steps of obtaining visual fatigue assessment factors, analyzing the correlation between each visual fatigue assessment factor and visual fatigue, selecting visual fatigue assessment indicators, and obtaining visual fatigue assessment indicator information specifically include:

[0066] Obtain visual fatigue assessment factors, calculate the Spearman correlation coefficient between each visual fatigue assessment factor and visual fatigue, and form a Spearman correlation coefficient matrix;

[0067] Preset a Spearman correlation coefficient threshold, perform threshold processing on the Spearman correlation coefficient matrix, set data less than the Spearman correlation coefficient threshold to zero, and form an initial set of evaluation factors based on the updated Spearman correlation coefficient matrix;

[0068] Calculating the similarity between the evaluation elements according to the initial set of evaluation elements to form a similarity matrix, constructing a vertex matrix using the sum of the diagonal elements of the similarity matrix, and subtracting the similarity matrix from the vertex matrix to form a Laplace matrix;

[0069] Perform eigendecomposition on the Laplace matrix to obtain eigenvalues ​​and corresponding eigenvectors, preset a number of cluster centers and select a corresponding number of minimum non-zero eigenvalues ​​and eigenvectors, use the selected eigenvectors as new data representations, and construct an eigenvector space;

[0070] Using the K-means algorithm in combination with the feature vector space to perform multiple clustering, classifying each evaluation factor in the initial set of evaluation factors into categories, and obtaining category classification result information;

[0071] The evaluation factors of each category are sorted in combination with the Spearman correlation coefficient matrix and the category division result information, and the visual fatigue evaluation index is selected based on the sorting result to obtain the visual fatigue evaluation index information.

[0072] It should be noted that, first, a variety of evaluation factors related to visual fatigue are obtained, key indicators are screened from a large number of visual fatigue evaluation factors, and the Spearman correlation coefficient between these factors and visual fatigue is calculated. The Spearman correlation coefficient is a non-parametric statistical method for measuring the relationship between variables, which is used to determine the correlation between each evaluation factor and visual fatigue. A threshold of the Spearman correlation coefficient is preset, and the correlation coefficients in the matrix that are less than the threshold are set to zero to eliminate those evaluation factors with weak correlation with visual fatigue. The updated Spearman correlation coefficient matrix is ​​used to form an initial set of evaluation factors. Next, a similarity matrix is ​​constructed by calculating the similarity between the evaluation factors. The sum of the diagonal elements is used to form a vertex matrix. The Laplace matrix is ​​constructed by subtracting the vertex matrix from the similarity matrix. The Laplace matrix is ​​used to capture the structural relationship between the evaluation factors, and the eigenvalues ​​and their corresponding eigenvectors are obtained by eigendecomposition. The number of cluster centers is preset, and the minimum non-zero eigenvalues ​​and their eigenvectors corresponding to the number of these centers are selected. The selected eigenvectors are used to create a new data representation, namely the eigenvector space. On this basis, the K-means algorithm is used to perform multiple clustering of the feature vector space, and the various evaluation elements in the initial set of evaluation elements are classified into categories. Finally, the Spearman correlation coefficient matrix is ​​combined with the category division result information, the evaluation elements in each category are sorted, and the most representative visual fatigue evaluation index is determined, so as to obtain the final visual fatigue evaluation index information. Among them, the visual fatigue evaluation elements can be classified into eye movement categories and physiological categories. The eye movement categories include gaze point, scanning speed, number of gazes, percentage of gaze time, etc., and the physiological categories include heart rate, limb reaction speed, posture change, etc.

[0073] Further, in a preferred embodiment of the present invention, the visual fatigue assessment model is constructed based on the visual fatigue assessment index information, the visual fatigue degree of the target user is assessed, and the visual fatigue degree assessment information is obtained, which specifically includes:

[0074] Obtain historical visual fatigue assessment instances with different fatigue levels, extract assessment parameters of corresponding visual assessment indicators in each historical visual fatigue assessment instance according to the visual fatigue assessment indicator information, and associate them with the fatigue level to form an assessment instance data set;

[0075] Constructing a visual fatigue assessment model based on a support vector machine, using the assessment instance data set to construct a training data set to train the visual fatigue assessment model, and using a cross-validation method to perform hyperparameter optimization to obtain a visual fatigue assessment model that meets expectations;

[0076] Monitor the target user to obtain real-time monitoring information, the real-time monitoring information including eye movement monitoring information and physiological monitoring information, and perform data preprocessing on the real-time monitoring information;

[0077] The pre-processed real-time monitoring information is input into the visual fatigue assessment model for analysis, and feature extraction is performed on the input data to obtain eye movement features and physiological features and form a feature vector;

[0078] The corresponding decision function value is calculated based on the constructed feature vector, and the decision function value is the distance between the target feature vector and the decision hyperplane. The visual fatigue degree of the target user is determined based on the decision function value to obtain visual fatigue degree evaluation information.

[0079] It should be noted that, first, data is obtained from historical visual fatigue evaluation instances with different fatigue levels. According to the previously selected visual fatigue evaluation index information, the corresponding evaluation parameters in each historical instance are extracted, and the fatigue levels in the instance are associated to form an evaluation instance data set. Next, a visual fatigue evaluation model is constructed using a support vector machine (SVM). SVM is suitable for processing complex multidimensional data. A training data set is constructed based on the evaluation instance data set to train the SVM model. During the training process, the hyperparameters of the model are optimized by cross-validation to ensure that the model has good generalization ability in practical applications, and finally a visual fatigue evaluation model that meets expectations is obtained. When the target user is monitored in real time, the monitoring information obtained includes the user's eye movement monitoring information and physiological monitoring information, and the real-time monitoring information is preprocessed, including denoising, standardization, and missing value processing. The preprocessed data is input into the previously trained visual fatigue evaluation model. The model extracts features from the input data, extracts the user's eye movement features and physiological features, and combines these features into a feature vector. The decision function value is calculated based on the feature vector, and the decision function value reflects the distance between the target feature vector and the model decision hyperplane. This distance is used to determine the visual fatigue degree of the target user. The current visual fatigue degree of the user is evaluated according to the value of the decision function, and visual fatigue degree evaluation information is generated.

[0080] Further, in a preferred embodiment of the present invention, the method of predicting the dizziness of the target user according to the visual fatigue level assessment information, predicting the real-time dizziness of the target user and adjusting the device operation parameters specifically includes:

[0081] Constructing a dizziness prediction model based on a convolutional neural network, obtaining visual fatigue assessment information and real-time monitoring information, and inputting them into the dizziness prediction model for analysis;

[0082] Taking the visual fatigue state as a priori feature, feature extraction is performed on the input visual fatigue degree assessment information, and a feature matrix of various dizziness conditions corresponding to the visual fatigue degree feature is retrieved in a preset search space according to the extracted visual fatigue degree feature;

[0083] Performing similarity calculation between the acquired feature matrices of various dizziness conditions and the real-time monitoring information to obtain similarity values, using the similarity values ​​as confidence indicators of various dizziness conditions, sorting the various dizziness conditions, and obtaining a dizziness condition sorting table;

[0084] According to the dizziness condition ranking table, the dizziness condition category with the highest confidence is selected for output to obtain dizziness condition prediction information; according to the dizziness condition prediction information, it is determined whether the virtual reality device needs to be regulated, and if regulation is required, a regulation plan is formulated;

[0085] The real-time device usage parameters of the target user are obtained, and the historical control scheme under the corresponding dizziness condition is obtained in combination with the dizziness condition prediction information. A matching analysis is performed according to the obtained real-time device usage parameters, and the most frequently used control scheme is selected to adjust the operating parameters of the target virtual reality device.

[0086] It should be noted that a convolutional neural network is used to construct a dizziness prediction model, and the dizziness that may occur in the user during the use of the virtual reality device is predicted by analyzing the user's visual fatigue assessment information and real-time monitoring information. The user's visual fatigue assessment information and real-time monitoring information are input into the dizziness prediction model for analysis. In this process, the visual fatigue state is used as a priori feature, and the model extracts features from the visual fatigue assessment information. Based on the extracted visual fatigue features, the model searches in the preset search space to obtain the feature matrix of various dizziness conditions corresponding to these features. This feature matrix contains the feature performance under different dizziness conditions. Then, the feature matrix and the real-time monitoring information are similarly calculated to obtain a similarity value. The higher the similarity value, the closer the dizziness condition corresponding to the feature matrix is ​​to the user's current condition. Different dizziness conditions are sorted based on the similarity calculation results, a dizziness condition sorting table is generated, and dizziness condition prediction information is output. It is determined whether the virtual reality device needs to be regulated based on the dizziness condition prediction information. If the prediction result shows that the user is at a high risk of dizziness, the regulation process is started and a corresponding regulation plan is formulated. Including dynamic adjustment of parameters such as picture refresh rate, brightness, and motion blur to reduce user dizziness and improve the overall user experience.

[0087] Further, in a preferred embodiment of the present invention, the acquisition of historical usage monitoring information, analyzing historical user experience paths of different experience content categories according to the historical usage monitoring information and constructing experience content portraits, and forming an experience content portrait database according to the experience content portraits specifically includes:

[0088] Acquire historical usage monitoring information of the target virtual device, wherein the historical usage monitoring information includes device experience modes and experience durations of different experience contents when historical users use the target virtual device, as well as dizziness monitoring information and physiological status monitoring information;

[0089] Taking the experience content as the first category, the historical usage monitoring information is divided, the Euclidean distance between each experience content is calculated according to the historical usage monitoring information, and the distance is compared with a preset threshold to obtain first category division information;

[0090] Performing feature extraction on the first category classification information, extracting device experience mode features and experience duration features corresponding to each experience content category, and obtaining first category feature information;

[0091] According to the first category feature information, the time node features of experience mode switching during a single experience and the experience duration features of the corresponding switching mode and the switched mode are obtained to obtain historical user experience paths of different experience content categories;

[0092] An experience content portrait is constructed based on the historical user experience paths of different experience content categories. The dizziness condition monitoring information and physiological condition monitoring information are associated with the corresponding experience content portrait as subsidiary features to form an experience content portrait database.

[0093] It should be noted that in the process of elderly users experiencing virtual reality devices, they often cannot fully experience the complete content due to their own discomfort. When starting to use the device for experience, based on the use of the initial experience mode, discomfort may occur. At this time, adjustments need to be made to reduce the discomfort and ensure the complete experience of all the content. First, the historical usage monitoring information of the target virtual device is obtained, which includes the device experience mode, experience duration, dizziness monitoring information and physiological status monitoring information of historical users for different experience contents when using the device. Then, the historical usage monitoring information is divided with the experience content as the first category, and the usage information of different experience contents is separated. The Euclidean distance between each experience content is calculated, and these distances are compared with the preset threshold to obtain the first category division information. Subsequently, the first category information is feature extracted to extract features related to the device experience mode and experience duration from each experience content category, and the first category feature information is generated. Next, the switching of the experience mode during a single experience is analyzed. Identify the time nodes for switching experience modes under each experience content category, extract the corresponding switching modes and the experience duration characteristics of the switched modes, and construct historical user experience paths for different experience content categories. These paths reflect the user's switching between different modes due to discomfort during the experience process. Construct experience content portraits based on historical user experience paths. Each experience content portrait represents a different experience path under an experience content category. For example, if the initial experience mode is mode a, and dizziness and other discomforts occur after 10 minutes of experience, mode a is adjusted to other modes, and the experience continues or the mode is adjusted until all content is fully experienced.

[0094] Further, in a preferred embodiment of the present invention, the real-time experience user is monitored, the real-time physical load status of the target experience user is analyzed, whether there is discomfort in the experience is determined, and the personalized content experience path is adjusted in combination with the experience content portrait database, specifically including:

[0095] Monitor the target user who uses the virtual reality device in real time, obtain the target user's real-time usage monitoring information, extract features from the target user's real-time usage monitoring information, and obtain the target user's experience content features, experience mode features, experience duration features, and user physical condition monitoring features of the content experienced by the target user through the virtual device in real time;

[0096] Based on the user's physical condition monitoring characteristics, the target user's visual fatigue degree and dizziness condition are evaluated, and the real-time load condition of the target user under the current experience content is analyzed to obtain real-time load condition analysis information;

[0097] Determine whether the target user has an uncomfortable experience based on the real-time load status analysis information, and if so, adjust the experience path of the target user based on the experience content portrait database;

[0098] The real-time experience path of the target user is constructed according to the experience content characteristics, experience mode characteristics and experience duration characteristics of the target user, and is searched in the experience content portrait database, and matched with each experience content portrait in the experience content portrait database to obtain matching portrait information;

[0099] Extracting the dizziness condition monitoring features and the physiological condition monitoring features corresponding to each matching portrait according to the matching portrait information, performing similarity calculation with the real-time load analysis information, and sorting the matching portraits according to the similarity;

[0100] The best matching portrait is selected through the sorting results, and the corresponding historical user experience path is extracted to formulate an experience mode adjustment plan to regulate the target virtual reality device.

[0101] It should be noted that when elderly users experience through virtual reality devices, the target users are monitored to obtain real-time usage monitoring information, and the experience content features, experience mode features, experience duration features and user physical condition monitoring features are further extracted. Based on the user physical condition monitoring features, the visual fatigue degree of the target user is evaluated and the dizziness condition is predicted, and the real-time load condition of the target user under the current experience content is analyzed to determine whether the experience mode adopted in the initial experience period causes discomfort to the user. If there is discomfort, in order to improve the user experience and increase the user experience time, the initial experience mode needs to be adjusted. Among them, the experience mode corresponds to the operating parameters of the virtual reality device such as the screen refresh rate, brightness, and motion blur. According to the experience content features, experience mode features and experience duration features of the target user, the user's real-time experience path is constructed, and the search is performed in the experience content portrait database, and the user's real-time experience path is matched with each experience content portrait in the experience content portrait database to obtain matching portrait information. The corresponding dizziness condition monitoring features and physiological condition monitoring features are extracted from these matching portraits, and the similarity is measured with the user's real-time load analysis information, and sorted. The best matching portrait is selected through the sorting results, and the corresponding historical user experience path is extracted based on this portrait, and an experience mode adjustment plan suitable for the current user is formulated, and the target virtual reality device is adjusted accordingly. This reduces the user's discomfort, further prolongs the user's experience time, and ensures the integrity of the experience content.

[0102] Figure 2 A personalized content experience path adjustment flow chart provided by an embodiment of the present invention;

[0103] like Figure 2 As shown, the present invention provides a personalized content experience path adjustment flow chart, including:

[0104] S202, monitoring a target user who uses the virtual reality device in real time, and obtaining real-time usage monitoring information of the target user;

[0105] S204, extracting features from the real-time usage monitoring information of the target user to obtain experience content features, experience mode features, experience duration features, and user physical condition monitoring features of the target user's real-time content experience through the virtual device;

[0106] S206, evaluating the visual fatigue degree and dizziness condition of the target user based on the user's physical condition monitoring characteristics, analyzing the real-time load condition of the target user under the current experience content, and obtaining real-time load condition analysis information;

[0107] S208, judging whether the target user has an uncomfortable experience according to the real-time load status analysis information, and if so, adjusting the experience path of the target user based on the experience content portrait database;

[0108] S210, constructing a real-time experience path for the target user based on the experience content characteristics, experience mode characteristics, and experience duration characteristics of the target user, and formulating an experience mode adjustment plan in combination with the experience content portrait database to regulate the target virtual reality device.

[0109] It should be noted that the discomfort is judged according to the visual fatigue and dizziness of the target user when experiencing the virtual reality device. When discomfort occurs, it means that the current experience mode of the virtual device is not compatible with the target user and needs to be changed. The real-time experience path of the target user is formed by using the experience content characteristics, experience mode characteristics and experience duration characteristics of the target user. The real-time experience path represents the user portrait of the target user when experiencing. It can understand the discomfort of the target user under what experience mode and experience time, so as to match the corresponding historical experience portrait. The dizziness monitoring characteristics and physiological condition monitoring characteristics corresponding to each matching portrait are extracted, and the real-time load analysis information is combined to determine which experience mode the real-time physical condition of the target user is suitable for, and the experience mode adjustment plan is formulated to regulate the target virtual reality device. Enhance the experience of elderly users when using virtual reality devices for experience. At the same time, through personalized mode switching, further reduce the discomfort when using the device, so as to ensure that the target elderly users experience more content in a comfortable state.

[0110] Figure 3A system 3 for enhancing the user experience of the elderly using a virtual reality device is provided in one embodiment of the present invention. The system includes: a memory 31 and a processor 32. The memory 31 includes a method program for enhancing the user experience of the elderly using a virtual reality device. When the method program for enhancing the user experience of the elderly using a virtual reality device is executed by the processor 32, the following steps are implemented:

[0111] Obtain visual fatigue assessment factors, analyze the correlation between each visual fatigue assessment factor and visual fatigue, select visual fatigue assessment indicators, and obtain visual fatigue assessment indicator information;

[0112] Building a visual fatigue assessment model based on the visual fatigue assessment index information, assessing the visual fatigue degree of the target user, and obtaining visual fatigue degree assessment information;

[0113] Predicting the dizziness of the target user based on the visual fatigue assessment information, predicting the real-time dizziness of the target user and adjusting the device operating parameters;

[0114] Acquire historical usage monitoring information, analyze historical user experience paths of different experience content categories according to the historical usage monitoring information and construct experience content portraits, and form an experience content portrait database according to the experience content portraits;

[0115] Monitor the real-time experience users, analyze the real-time physical load status of the target experience users, determine whether there is any discomfort in the experience, and adjust the personalized content experience path based on the experience content portrait database.

[0116] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0117] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0118] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0119] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0120] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0121] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for enhancing the experience of elderly users of virtual reality equipment, characterized in that: include: Obtain visual fatigue assessment factors, analyze the correlation between each visual fatigue assessment factor and visual fatigue, select visual fatigue assessment indicators, and obtain visual fatigue assessment indicator information; Building a visual fatigue assessment model based on the visual fatigue assessment index information, assessing the visual fatigue degree of the target user, and obtaining visual fatigue degree assessment information; Predicting the dizziness of the target user based on the visual fatigue assessment information, predicting the real-time dizziness of the target user and adjusting the device operating parameters; Acquire historical usage monitoring information, analyze historical user experience paths of different experience content categories according to the historical usage monitoring information and construct experience content portraits, and form an experience content portrait database according to the experience content portraits; Monitor the real-time experience user, analyze the real-time physical load status of the target experience user, determine whether there is any discomfort in the experience, and adjust the personalized content experience path in combination with the experience content portrait database; The obtaining of historical usage monitoring information, analyzing historical user experience paths of different experience content categories according to the historical usage monitoring information and constructing experience content portraits, and forming an experience content portrait database according to the experience content portraits specifically includes: Acquire historical usage monitoring information of the target virtual device, wherein the historical usage monitoring information includes device experience modes and experience durations of different experience contents when historical users use the target virtual device, as well as dizziness monitoring information and physiological status monitoring information; Taking the experience content as the first category, the historical usage monitoring information is divided, the Euclidean distance between each experience content is calculated according to the historical usage monitoring information, and the distance is compared with a preset threshold to obtain first category division information; Performing feature extraction on the first category classification information, extracting device experience mode features and experience duration features corresponding to each experience content category, and obtaining first category feature information; According to the first category feature information, the time node features of experience mode switching during a single experience and the experience duration features of the corresponding switching mode and the switched mode are obtained to obtain historical user experience paths of different experience content categories; Based on the historical user experience paths of different experience content categories, experience content portraits are formed, and the dizziness condition monitoring information and physiological condition monitoring information are associated with the corresponding experience content portraits as subsidiary features to form an experience content portrait database; The monitoring of the real-time experience user, analyzing the real-time physical load status of the target experience user, determining whether there is discomfort in the experience, and adjusting the personalized content experience path in combination with the experience content portrait database specifically includes: Monitor the target user who uses the virtual reality device in real time, obtain the target user's real-time usage monitoring information, extract features from the target user's real-time usage monitoring information, and obtain the target user's experience content features, experience mode features, experience duration features, and user physical condition monitoring features of the content experienced by the target user through the virtual device in real time; Based on the user's physical condition monitoring characteristics, the target user's visual fatigue degree and dizziness condition are evaluated, and the real-time load condition of the target user under the current experience content is analyzed to obtain real-time load condition analysis information; Determine whether the target user has an uncomfortable experience based on the real-time load status analysis information, and if so, adjust the experience path of the target user based on the experience content portrait database; The real-time experience path of the target user is constructed according to the experience content characteristics, experience mode characteristics and experience duration characteristics of the target user, and is searched in the experience content portrait database, and matched with each experience content portrait in the experience content portrait database to obtain matching portrait information; Extracting the dizziness condition monitoring features and the physiological condition monitoring features corresponding to each matching portrait according to the matching portrait information, performing similarity calculation with the real-time load analysis information, and sorting the matching portraits according to the similarity; The best matching portrait is selected through the sorting results, and the corresponding historical user experience path is extracted to formulate an experience mode adjustment plan to regulate the target virtual reality device.

2. The method for enhancing the experience of elderly users of virtual reality devices according to claim 1, characterized in that: The obtaining of visual fatigue assessment factors, analyzing the correlation between each visual fatigue assessment factor and visual fatigue, selecting visual fatigue assessment indicators, and obtaining visual fatigue assessment indicator information specifically include: Obtain visual fatigue assessment factors, calculate the Spearman correlation coefficient between each visual fatigue assessment factor and visual fatigue, and form a Spearman correlation coefficient matrix; Preset a Spearman correlation coefficient threshold, perform threshold processing on the Spearman correlation coefficient matrix, set data less than the Spearman correlation coefficient threshold to zero, and form an initial set of evaluation factors based on the updated Spearman correlation coefficient matrix; Calculating the similarity between the evaluation elements according to the initial set of evaluation elements to form a similarity matrix, constructing a vertex matrix using the sum of the diagonal elements of the similarity matrix, and subtracting the similarity matrix from the vertex matrix to form a Laplace matrix; Perform eigendecomposition on the Laplace matrix to obtain eigenvalues ​​and corresponding eigenvectors, preset a number of cluster centers and select a corresponding number of minimum non-zero eigenvalues ​​and eigenvectors, use the selected eigenvectors as new data representations, and construct an eigenvector space; Using the K-means algorithm in combination with the feature vector space to perform multiple clustering, classifying each evaluation factor in the initial set of evaluation factors into categories, and obtaining category classification result information; The evaluation factors of each category are sorted in combination with the Spearman correlation coefficient matrix and the category division result information, and the visual fatigue evaluation index is selected based on the sorting result to obtain the visual fatigue evaluation index information.

3. The method for enhancing the experience of elderly users of virtual reality devices according to claim 1, characterized in that: The step of constructing a visual fatigue assessment model based on the visual fatigue assessment index information, assessing the visual fatigue degree of the target user, and obtaining visual fatigue degree assessment information specifically includes: Obtain historical visual fatigue assessment instances with different fatigue levels, extract assessment parameters of corresponding visual assessment indicators in each historical visual fatigue assessment instance according to the visual fatigue assessment indicator information, and associate them with the fatigue level to form an assessment instance data set; A visual fatigue assessment model is constructed based on a support vector machine, a training data set is constructed using the assessment instance data set to train the visual fatigue assessment model, and a cross-validation method is used to optimize hyperparameters to obtain a visual fatigue assessment model that meets expectations; Monitor the target user to obtain real-time monitoring information, the real-time monitoring information including eye movement monitoring information and physiological monitoring information, and perform data preprocessing on the real-time monitoring information; The pre-processed real-time monitoring information is input into the visual fatigue assessment model for analysis, and feature extraction is performed on the input data to obtain eye movement features and physiological features and form a feature vector; The corresponding decision function value is calculated according to the constructed feature vector, and the decision function value is the distance between the target feature vector and the decision hyperplane. The visual fatigue degree of the target user is determined according to the decision function value to obtain visual fatigue degree evaluation information.

4. The method for enhancing the user experience of elderly users of virtual reality equipment according to claim 1, characterized in that: The method of predicting the dizziness of the target user according to the visual fatigue degree assessment information, predicting the real-time dizziness of the target user and adjusting the device operation parameters specifically includes: Constructing a dizziness prediction model based on a convolutional neural network, obtaining visual fatigue assessment information and real-time monitoring information, and inputting them into the dizziness prediction model for analysis; Taking the visual fatigue state as a priori feature, feature extraction is performed on the input visual fatigue degree assessment information, and a feature matrix of various dizziness conditions corresponding to the visual fatigue degree feature is retrieved in a preset search space according to the extracted visual fatigue degree feature; Performing similarity calculation between the acquired feature matrices of various dizziness conditions and the real-time monitoring information to obtain similarity values, using the similarity values ​​as confidence indicators of various dizziness conditions, sorting the various dizziness conditions, and obtaining a dizziness condition sorting table; Selecting the dizziness condition category with the highest confidence level according to the dizziness condition ranking table for output, and obtaining dizziness condition prediction information; judging whether it is necessary to regulate the virtual reality device according to the dizziness condition prediction information, and formulating a regulation plan if regulation is necessary; The real-time device usage parameters of the target user are obtained, and the historical control scheme under the corresponding dizziness condition is obtained in combination with the dizziness condition prediction information. A matching analysis is performed based on the obtained real-time device usage parameters, and the most frequently used control scheme is selected to adjust the operating parameters of the target virtual reality device.

5. A system for enhancing the elderly user experience of virtual reality equipment, characterized in that: The system includes: a memory and a processor, wherein the memory contains a method program for enhancing the user experience of the elderly using a virtual reality device, and when the method program for enhancing the user experience of the elderly using a virtual reality device is executed by the processor, the following steps are implemented: Obtain visual fatigue assessment factors, analyze the correlation between each visual fatigue assessment factor and visual fatigue, select visual fatigue assessment indicators, and obtain visual fatigue assessment indicator information; Building a visual fatigue assessment model based on the visual fatigue assessment index information, assessing the visual fatigue degree of the target user, and obtaining visual fatigue degree assessment information; Predicting the dizziness of the target user based on the visual fatigue assessment information, predicting the real-time dizziness of the target user and adjusting the device operating parameters; Acquire historical usage monitoring information, analyze historical user experience paths of different experience content categories according to the historical usage monitoring information and construct experience content portraits, and form an experience content portrait database according to the experience content portraits; Monitor the real-time experience user, analyze the real-time physical load status of the target experience user, determine whether there is any discomfort in the experience, and adjust the personalized content experience path in combination with the experience content portrait database; The obtaining of historical usage monitoring information, analyzing historical user experience paths of different experience content categories according to the historical usage monitoring information and constructing experience content portraits, and forming an experience content portrait database according to the experience content portraits specifically includes: Acquire historical usage monitoring information of the target virtual device, wherein the historical usage monitoring information includes device experience modes and experience durations of different experience contents when historical users use the target virtual device, as well as dizziness monitoring information and physiological status monitoring information; Taking the experience content as the first category, the historical usage monitoring information is divided, the Euclidean distance between each experience content is calculated according to the historical usage monitoring information, and the distance is compared with a preset threshold to obtain first category division information; Performing feature extraction on the first category classification information, extracting device experience mode features and experience duration features corresponding to each experience content category, and obtaining first category feature information; According to the first category feature information, the time node features of experience mode switching during a single experience and the experience duration features of the corresponding switching mode and the switched mode are obtained to obtain historical user experience paths of different experience content categories; Based on the historical user experience paths of different experience content categories, experience content portraits are formed, and the dizziness condition monitoring information and physiological condition monitoring information are associated with the corresponding experience content portraits as subsidiary features to form an experience content portrait database; The monitoring of the real-time experience user, analyzing the real-time physical load status of the target experience user, determining whether there is discomfort in the experience, and adjusting the personalized content experience path in combination with the experience content portrait database specifically includes: Monitor the target user who uses the virtual reality device in real time, obtain the target user's real-time usage monitoring information, extract features from the target user's real-time usage monitoring information, and obtain the target user's experience content features, experience mode features, experience duration features, and user physical condition monitoring features of the content experienced by the target user through the virtual device in real time; Based on the user's physical condition monitoring characteristics, the target user's visual fatigue degree and dizziness condition are evaluated, and the real-time load condition of the target user under the current experience content is analyzed to obtain real-time load condition analysis information; Determine whether the target user has an uncomfortable experience based on the real-time load status analysis information, and if so, adjust the experience path of the target user based on the experience content portrait database; The real-time experience path of the target user is constructed according to the experience content characteristics, experience mode characteristics and experience duration characteristics of the target user, and is searched in the experience content portrait database, and matched with each experience content portrait in the experience content portrait database to obtain matching portrait information; Extracting the dizziness condition monitoring features and the physiological condition monitoring features corresponding to each matching portrait according to the matching portrait information, performing similarity calculation with the real-time load analysis information, and sorting the matching portraits according to the similarity; The best matching portrait is selected through the sorting results, and the corresponding historical user experience path is extracted to formulate an experience mode adjustment plan to regulate the target virtual reality device.

Images