A method and system for evaluating the psychological state of users in the metaverse

Abstract

The present invention discloses a method and system for evaluating the psychological state of users in the metaverse, specifically related to the technical field of evaluating the psychological state of users. By obtaining the updated data of the virtual scene in the metaverse, it quantifies whether there are abnormal fluctuations in the psychological state of users, determines whether the users are unstable users, and obtains the unstable information of data collection, the fluctuation information of data transmission, and the uneven information of the calculation resource allocation of the user psychological state evaluation model to construct an evaluation result timeliness monitoring model, identify and respond to potential problems, ensure the continuous monitoring of the timeliness of the evaluation results, provide basic data for subsequent risk warnings, and then obtain the timeliness monitoring data information, establish a timeliness monitoring data set, and through the analysis of the timeliness monitoring data set and the calculation of the moving average value, conduct a risk warning on the influence depth of the timeliness hidden danger, ensure intervention before or at the initial stage of the problem occurrence, and improve the overall performance and user experience.

Description

Technical Field

[0001] The present invention relates to the technical field of user mental state assessment, and more specifically, to a method and system for assessing the mental state of users in the metaverse. Background Art

[0002] As a digital space that combines virtual reality and augmented reality, the mental state of users plays a crucial role in the metaverse. Evaluating the mental state of users in the metaverse can significantly improve the user experience. The user mental state assessment system in the metaverse collects the user's behavioral data, physiological data, and emotional data in the metaverse through various devices at the data collection end, constructs a user mental state assessment model, and real-time assesses the user's mental state in the metaverse. The metaverse virtual environment control subsystem adjusts the virtual scene in the metaverse in real time according to the assessment result of the user's mental state.

[0003] Due to the long-term operation of the existing user mental state assessment system in the metaverse, the instability of data collection, the volatility of data transmission, and the uneven distribution of computing resources in the assessment model may all lead to a decrease in the timeliness of the assessment result. For users with relatively stable mental states, the impact of the decrease in timeliness may be minimal, but for some users with rapidly fluctuating mental states, due to the lack of risk warning for the decrease in timeliness, the existing user mental state assessment system in the metaverse may not be able to accurately capture the peak points of the user's mental changes, resulting in the metaverse virtual environment control subsystem being unable to adjust the virtual scene in the metaverse in time according to the assessment result of the user's mental state. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a method and system for assessing the mental state of users in the metaverse to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for assessing the mental state of users in the metaverse includes the following steps: Step S1, obtaining the updated data of the virtual scene in the metaverse and analyzing the obtained updated data of the virtual scene to determine whether the user is an unstable user;

[0007] Step S2, when the user is an unstable user, obtaining the unstable information of data collection, the fluctuation information of data transmission, and the uneven distribution information of computing resources of the user mental state assessment model during the operation of the user mental state assessment system in the metaverse;

[0008] Step S3, construct an evaluation result timeliness monitoring model, analyze the output timeliness of the user mental state evaluation model, and generate a timeliness monitoring index;

[0009] Step S4, compare the timeliness monitoring index with the timeliness monitoring index threshold, classify the output timeliness of the user mental state evaluation model, and generate different timeliness signals, including timeliness hidden danger signals and timeliness stable signals;

[0010] Step S5, when a timeliness hidden danger signal is generated, obtain the corresponding timeliness monitoring data information, establish a timeliness monitoring data set, analyze the timeliness monitoring data in the set, and conduct risk early warning on the influence depth of the timeliness hidden danger.

[0011] In a preferred implementation manner, in step S1, obtain the virtual scene update data in the metaverse, and analyze the obtained virtual scene update data to quantify whether there are abnormal fluctuations in the user mental state and determine whether the user is an unstable user, specifically as follows:

[0012] Obtain the virtual scene update data in the metaverse, including but not limited to the scene existence duration, the number of scene switches, and the number of interactions between the user and the scene objects;

[0013] Preprocess the virtual scene update data, including handling missing values, outliers, and data standardization, to obtain the original virtual scene update data time series based on equal-interval time;

[0014] Use the local regression method to extract the trend component from the original virtual scene update data time series, and the expression is as follows , where represents the trend component, represents the original virtual scene update data, represents the extraction function of the local regression method for extracting the trend component from the original virtual scene update data time series;

[0015] Subtract the trend component from the original data, and use the local regression method to extract the seasonal component, and the expression is as follows , where represents the seasonal component;

[0016] Calculate the residual component according to the trend component and the seasonal component, and the expression is as follows , where represents the residual component;

[0017] Calculate the standard deviation of the residual component, and the expression is as follows , where represents the standard deviation of the residual component, Represents the average value of the residual components, and the expression is as follows , represents the residual component at time , where

[0018] Compare the standard deviation of the residual components with the standard deviation threshold. If the standard deviation of the residual components is greater than the standard deviation threshold, mark the user as a user with unstable status; if the standard deviation of the residual components is less than or equal to the standard deviation threshold, mark the user as a user with stable status.

[0019] In a preferred embodiment, in step S2, the unstable information of data collection includes the collection instability coefficient, the fluctuation information of data transmission includes the transmission fluctuation coefficient, and the uneven information of resource allocation in the user mental state evaluation model includes the resource allocation uneven coefficient. Mark the collection instability coefficient, the transmission fluctuation coefficient, and the resource allocation uneven coefficient as , , .

[0020] In a preferred embodiment, by obtaining the unstable information of data collection and analyzing the unstable factors in the data collection process, the collection instability coefficient is obtained. The acquisition logic of the collection instability coefficient is as follows:

[0021] The unstable data obtained for data collection includes, but is not limited to, the data missing rate, the equipment failure rate, and the variance of the data collection interval. Construct an unstable data set, and each data point in the unstable data set includes three types of indicators, namely the data missing rate, the equipment failure rate, and the variance of the data collection interval;

[0022] Calculate the original distance matrix between the data points in the unstable data set , and the expression is as follows , where in the formula , , respectively represent the values of the data missing rate, the equipment failure rate, and the variance of the data collection interval in the data point , , , respectively represent the values of the data missing rate, the equipment failure rate, and the variance of the data collection interval in the data point ;

[0023] Input the original distance matrix into algorithm, map the original distance matrix to a three-dimensional space, and set the objective function , and the expression is as follows , where in the formula, represents the distance in the original distance matrix, Represents the distance in three-dimensional space. By iteratively optimizing and adjusting the positions of data points in three-dimensional space until the objective function converges to the minimum value, the final three-dimensional space is obtained.

[0024] Calculate the variances of all data points in different axes in three-dimensional space. The axes of data points in three-dimensional space include the x-axis, y-axis, and z-axis.

[0025] Calculate the acquisition instability coefficient based on the variances of different axes. The expression is as follows , where represents the variance of the x-axis direction, represents the variance of the y-axis direction, represents the variance of the z-axis direction.

[0026] In a preferred embodiment, by obtaining the fluctuation information of data transmission and analyzing the fluctuation situation of the data transmission process, the transmission fluctuation coefficient is obtained. The acquisition logic of the transmission fluctuation coefficient is as follows:

[0027] Obtain the original time series data during the data transmission process , including but not limited to the arrival time of data packets, transmission delay;

[0028] Perform wavelet decomposition on the original time series data , select wavelet as the wavelet basis function, and mark the decomposition scale level as ;

[0029] Decompose the original time series data into approximation coefficients and detail coefficients. The decomposition formula is as follows , where represents the approximation coefficient of the th layer, represents the detail coefficient of the th layer;

[0030] Calculate the energy value according to the detail coefficients of each layer scale. The expression is as follows , where represents the energy value of the th layer scale;

[0031] Calculate the standard deviation of the energy value , where represents the average value of the energy value;

[0032] Calculate the transmission fluctuation coefficient. The expression is as follows .

[0033] In a preferred embodiment, by obtaining the calculation resource allocation unevenness information of the user mental state evaluation model, analyzing the calculation resource allocation unevenness situation, and obtaining the resource allocation unevenness coefficient, the obtaining logic of the resource allocation unevenness coefficient is as follows:

[0034] Calculate the proportion of the resource usage of each user by the user mental state evaluation model in the total resource usage within the same time period;

[0035] Calculate the actual entropy value , the expression is as follows , where in the formula represents the proportion of the resource usage of the th user in the total resource usage, represents the total number of users;

[0036] Calculate the maximum entropy value , the expression is as follows ;

[0037] Calculate the resource allocation unevenness coefficient, the expression is as follows .

[0038] In a preferred embodiment, in step S3, normalize the acquisition instability coefficient, transmission fluctuation coefficient, and resource allocation unevenness coefficient, and construct an evaluation result timeliness monitoring model based on the normalized acquisition instability coefficient, transmission fluctuation coefficient, and resource allocation unevenness coefficient to generate a timeliness monitoring index , the formula on which the model is based is as follows , where in the formula , , respectively represent the preset proportional coefficients of the acquisition instability coefficient, transmission fluctuation coefficient, and resource allocation unevenness coefficient, and , , are all greater than 0.

[0039] In a preferred embodiment, in step S4, compare the timeliness monitoring index with the timeliness monitoring index threshold. If the timeliness monitoring index is greater than the timeliness monitoring index threshold, generate a timeliness hazard signal;

[0040] If the timeliness monitoring index is less than or equal to the timeliness monitoring index threshold, generate a timeliness stability signal.

[0041] In a preferred embodiment, in step S5, when a timeliness hazard signal is generated, obtain the corresponding timeliness monitoring data information, and the timeliness monitoring data information includes the timeliness monitoring index difference ;

[0042] The calculation expression of the timeliness monitoring index difference is as follows: Timeliness monitoring index difference = Timeliness monitoring index - Timeliness monitoring index threshold;

[0043] According to the timeliness monitoring index difference obtained each time a timeliness hidden danger signal is generated, a timeliness monitoring data set is established. The timeliness monitoring index differences in the set are arranged in the order of the generation of the timeliness hidden danger signals. Analyze the timeliness monitoring data in the set and conduct risk early warning on the influence depth of the timeliness hidden danger, specifically as follows:

[0044] Set a moving window size , and calculate the moving average of the timeliness monitoring data set. The expression is as follows , where represents the th calculated moving average, represents the timeliness monitoring index difference with the th number in the timeliness monitoring data set;

[0045] Compare the moving average with the moving average threshold. When the calculated moving average is greater than the moving average threshold, a risk early warning signal is generated; when the calculated moving average is less than or equal to the moving average threshold, there is no need to take corrective measures immediately.

[0046] In a preferred embodiment, a user mental state evaluation system for the metaverse, which is used to implement a user mental state evaluation method for the metaverse described in any one of claims 1-9, is characterized in that: it includes a user division module, which is used to obtain the virtual scene update data in the metaverse and analyze the obtained virtual scene update data to determine whether the user is an unstable user;

[0047] A data generation module, when the user is an unstable user, obtains the unstable information collected during the operation of the user mental state evaluation system in the metaverse, the fluctuation information of data transmission, and the uneven information of the calculation resource allocation of the user mental state evaluation model;

[0048] A model construction module, which constructs an evaluation result timeliness monitoring model, analyzes the output timeliness of the user mental state evaluation model, and generates a timeliness monitoring index;

[0049] A timeliness classification module, which compares the timeliness monitoring index with the timeliness monitoring index threshold, classifies the output timeliness of the user mental state evaluation model, and generates different timeliness signals, including timeliness hidden danger signals and timeliness stable signals;

[0050] Risk warning module, when generating a timeliness hidden danger signal, obtain the corresponding timeliness monitoring data information, establish a timeliness monitoring data set, analyze the timeliness monitoring data in the set, and conduct risk warning on the influence depth of the timeliness hidden danger.

[0051] The technical effects and advantages of the present invention:

[0052] 1. The present invention obtains the virtual scene update data in the metaverse, analyzes the obtained virtual scene update data to quantify whether there are abnormal fluctuations in the user's mental state, and determines whether the user is an unstable user. When the user is an unstable user, obtain the unstable information of data collection during the operation of the user mental state evaluation system in the metaverse, the fluctuation information of data transmission, and the uneven information of computing resource allocation of the user mental state evaluation model to construct an evaluation result timeliness monitoring model. Analyze the output timeliness of the user mental state evaluation model, compare the timeliness monitoring index with the threshold value, generate a timeliness hidden danger signal and a timeliness stability signal, identify and respond to potential problems in a timely manner, ensure the real-time nature of the evaluation result, ensure that the timeliness of the evaluation result can be continuously monitored, provide basic data for subsequent risk warning. When generating a timeliness hidden danger signal, obtain the corresponding timeliness monitoring data information, establish a timeliness monitoring data set, and conduct risk warning on the influence depth of the timeliness hidden danger through the analysis of the timeliness monitoring data set and the calculation of the moving average value, so as to ensure intervention before or at the initial stage of the problem occurrence, and improve the overall performance and user experience. Description of the Drawings

[0053] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the accompanying drawings;

[0054] Figure 1 It is a schematic structural diagram of the method of Embodiment 1 of the present invention;

[0055] Figure 2 It is a schematic structural diagram of the system of Embodiment 2 of the present invention. Specific Embodiments

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying 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 making creative efforts shall fall within the protection scope of the present invention.

[0057] Embodiment 1: Figure 1The present invention provides a method for evaluating the psychological state of users in the metaverse, including the following steps: Step S1, obtaining the updated data of the virtual scene in the metaverse, and analyzing the obtained updated data of the virtual scene to determine whether the user is an unstable user;

[0058] When the user is in the metaverse space, the user psychological state evaluation system in the metaverse will collect the user's behavior data, physiological data, and emotional data in the metaverse through various devices at the data collection end, construct a user psychological state evaluation model, and evaluate the user's psychological state in the metaverse in real time. The metaverse virtual environment control subsystem will adjust the virtual scene in the metaverse in real time according to the evaluation result of the user's psychological state. The change of the virtual scene in the metaverse comes from the evaluation of the user's psychological state. Therefore, by obtaining the updated data of the virtual scene in the metaverse and analyzing the obtained updated data of the virtual scene, it is possible to quantify whether there are abnormal fluctuations in the user's psychological state and determine whether the user is an unstable user, as follows:

[0059] Obtaining the updated data of the virtual scene in the metaverse includes, but is not limited to, the duration of the scene existence, the number of scene switches, and the number of interactions between the user and the scene objects;

[0060] Preprocessing the updated data of the virtual scene, including handling missing values, outliers, and data standardization, to obtain the original virtual scene updated data time series based on equal-interval time;

[0061] Using the local regression method to extract the trend component from the original virtual scene updated data time series, and the expression is as follows , where represents the trend component, represents the original virtual scene updated data, represents the extraction function of the local regression method for extracting the trend component from the original virtual scene updated data time series;

[0062] Subtracting the trend component from the original data and using the local regression method to extract the seasonal component, and the expression is as follows , where represents the seasonal component;

[0063] The seasonal component is used to identify the periodic fluctuations of the virtual scene update in the metaverse, so as to quantify the periodic fluctuations of the user's psychological state;

[0064] Calculating the residual component according to the trend component and the seasonal component, and the expression is as follows , where represents the standard deviation of the residual component, represents the average value of the residual component, and the expression is as follows , represents Residual component at a moment For a positive integer, compare the standard deviation of the residual component with the standard deviation threshold. If the standard deviation of the residual component is greater than the standard deviation threshold, it indicates that there are abnormal fluctuations in the virtual scene update within the metaverse, that is, it means that there are also abnormal fluctuations in the user's mental state, and mark this user as an unstable state user; if the standard deviation of the residual component is less than or equal to the standard deviation threshold, it indicates that the virtual scene update within the metaverse is relatively stable, that is, it means that the user's mental state has not shown abnormal fluctuations, and mark this user as a stable state user.

[0065] Step S2, when the user is an unstable state user, obtain the unstable information of data collection during the operation of the user mental state evaluation system in the metaverse, the fluctuation information of data transmission, and the uneven information of computing resource allocation of the user mental state evaluation model;

[0066] The unstable information of data collection includes the collection instability coefficient, the fluctuation information of data transmission includes the transmission fluctuation coefficient, and the uneven information of computing resource allocation of the user mental state evaluation model includes the resource allocation uneven coefficient. Mark the collection instability coefficient, the transmission fluctuation coefficient, and the resource allocation uneven coefficient as , , ;

[0067] The collection instability coefficient is an important indicator for measuring the unstable situations that occur when various devices at the data collection end collect the user's behavioral data, physiological data, and emotional data. By analyzing various unstable factors in the data collection process, the reliability and accuracy of the data can be improved, thereby ensuring the accuracy of the user mental state evaluation and avoiding the user mental state evaluation system in the metaverse spending more time repeatedly processing various unstable factors that occur in the data collection process, resulting in a decrease in the timeliness of the output of the user mental state evaluation model. When the collection instability coefficient is larger, it indicates that there are more abnormal situations in the data collection process. The specific impacts include:

[0068] High data missing rate: A high collection instability coefficient usually means a high data missing rate. The missing data points require additional filling or processing, increasing the complexity and time of data preprocessing.

[0069] Uneven collection intervals: The unevenness of the collection time intervals will affect the continuity and consistency of the data, further increasing the difficulty of data processing and affecting the input quality of the mental state evaluation model.

[0070] High device failure frequency: A high collection instability coefficient may reflect that the collection devices frequently malfunction, which not only affects the continuity of data collection, reduces the timeliness of the output of the mental state evaluation results, but also may lead to data breaks and incompleteness, affecting the accuracy of the evaluation results;

[0071] When the instability coefficient of data collection is relatively large, the user mental state evaluation system in the metaverse requires more time for data cleaning and preprocessing, resulting in the untimely output of the mental state evaluation results. For users with severely fluctuating mental states, such delays may cause the user mental state evaluation system in the metaverse to fail to capture the peak of users' mental changes in a timely manner, affecting the real-time adjustment of the virtual scene in the metaverse;

[0072] Therefore, by obtaining the unstable information of data collection and analyzing the unstable factors in the data collection process, the collection instability coefficient is obtained. The acquisition logic of the collection instability coefficient is as follows:

[0073] The unstable data obtained for data collection includes, but is not limited to, the data missing rate, equipment failure rate, and variance of data collection intervals. An unstable data set is constructed, and each data point in the unstable data set includes three types of indicators, namely the data missing rate, equipment failure rate, and variance of data collection intervals;

[0074] Calculate the original distance matrix between data points in the unstable data set , and the expression is as follows , where in the formula , , respectively represent the values of the data missing rate, equipment failure rate, and variance of data collection intervals in the data point , , , respectively represent the values of the data missing rate, equipment failure rate, and variance of data collection intervals in the data point ;

[0075] Input the original distance matrix into algorithm, map the original distance matrix to a three-dimensional space, and set the objective function , and the expression is as follows , where in the formula, represents the distance in the original distance matrix, represents the distance in the three-dimensional space. By iteratively optimizing and adjusting the positions of data points in the three-dimensional space until the objective function converges to the minimum value, the final three-dimensional space is obtained;

[0076] Calculate the variances of all data points in different axes in the three-dimensional space. The axes of data points in the three-dimensional space include the x-axis, y-axis, and z-axis;

[0077] Calculate the collection instability coefficient according to the variances of different axes, and the expression is as follows , where in the formula represents the variance of the x-axis, represents the variance of the y-axis, Represents the variance in the z-axis direction;

[0078] The transmission fluctuation coefficient is used to measure the degree of fluctuation in the user's behavioral data, physiological data, and emotional data during the data transmission process. By analyzing various fluctuation factors in the data transmission process, the stability and reliability of data transmission can be improved, ensuring the accuracy and timeliness of user mental state assessment. The larger the transmission fluctuation coefficient, the greater the degree of fluctuation in the data transmission process, and the greater the impact on the real-time and integrity of the data, which may lead to a decrease in the timeliness and accuracy of mental state assessment and affect the virtual scene and user experience in the metaverse. Therefore, reducing the transmission fluctuation coefficient is crucial for improving system performance and user experience;

[0079] By obtaining the fluctuation information of data transmission and analyzing the fluctuation situation of the data transmission process, the transmission fluctuation coefficient is obtained. The acquisition logic of the transmission fluctuation coefficient is as follows:

[0080] Obtain the original time series data during the data transmission process , including but not limited to the arrival time and transmission delay of data packets;

[0081] Perform wavelet decomposition on the original time series data and select the wavelet as the wavelet basis function, and mark the decomposed scale layer as ;

[0082] Decompose the original time series data into approximation coefficients and detail coefficients. The decomposition formula is as follows , where represents the approximation coefficient of the th layer, and represents the detail coefficient of the th layer;

[0083] Calculate the energy value according to the detail coefficients of each layer scale. The expression is as follows , where represents the energy value of the th layer scale;

[0084] Calculate the standard deviation of the energy value , where represents the average value of the energy value;

[0085] Calculate the transmission fluctuation coefficient. The expression is as follows The resource allocation unevenness coefficient is an index used to measure the degree of uneven resource allocation when the user mental state evaluation model predicts the user's mental state. By analyzing the resource allocation situation of the user mental state evaluation model when predicting the user's mental state, the utilization efficiency of computing resources can be improved, ensuring the accuracy and timeliness of mental state evaluation. By obtaining the resource allocation unevenness coefficient, the resource allocation of the user mental state evaluation model can be optimized, improving system performance and user experience, and ensuring the accuracy and timeliness of user mental state evaluation. The larger the resource allocation unevenness coefficient, the lower the utilization efficiency of computing resources when the user mental state evaluation model conducts user mental state evaluation, and the worse the timeliness and accuracy of the evaluation results, thus affecting the virtual scene and user experience in the metaverse. Therefore, reducing the resource allocation unevenness coefficient is crucial for optimizing system performance and improving user experience.

[0086] By obtaining the information on the uneven allocation of computing resources of the user mental state evaluation model, analyzing the situation of uneven computing resource allocation, and obtaining the resource allocation unevenness coefficient, the acquisition logic of the resource allocation unevenness coefficient is as follows:

[0087] Calculate the proportion of the resource usage of each user by the user mental state evaluation model to the total resource usage within the same time period;

[0088] Calculate the actual entropy value , and the expression is as follows , where represents the proportion of the resource usage of the th user to the total resource usage, and represents the total number of users;

[0089] The actual entropy value is an index to measure the uncertainty or chaos degree of resource allocation. Specifically, the actual entropy value represents the actual unevenness of resource allocation among users. It is calculated by considering the proportion of each user's resource usage to the total resource usage;

[0090] Calculate the maximum entropy value , and the expression is as follows ;

[0091] Calculate the resource allocation unevenness coefficient, and the expression is as follows ;

[0092] Step S3, construct a timeliness monitoring model for evaluation results, analyze the output timeliness of the user mental state evaluation model, and generate a timeliness monitoring index;

[0093] Normalize the acquisition instability coefficient, transmission fluctuation coefficient, and resource allocation unevenness coefficient, and construct an evaluation result timeliness monitoring model based on the normalized acquisition instability coefficient, transmission fluctuation coefficient, and resource allocation unevenness coefficient to generate a timeliness monitoring index , and the formula on which the model is based is as follows , where in the formula , , respectively represent the preset proportional coefficients of the acquisition instability coefficient, transmission fluctuation coefficient, and resource allocation unevenness coefficient, and , , are all greater than 0;

[0094] It can be seen from the above calculation expressions that the larger the acquisition instability coefficient, the larger the transmission fluctuation coefficient, and the larger the resource allocation unevenness coefficient, the larger the timeliness monitoring index, indicating that the instability of data acquisition, the volatility of data transmission, and the unevenness of resource allocation have a greater impact on the timeliness of the output of the user mental state evaluation model. On the contrary, the smaller the acquisition instability coefficient, the smaller the transmission fluctuation coefficient, and the smaller the resource allocation unevenness coefficient, the smaller the timeliness monitoring index, indicating that the instability of data acquisition, the volatility of data transmission, and the unevenness of resource allocation have a smaller impact on the timeliness of the output of the user mental state evaluation model;

[0095] Step S4: Compare the timeliness monitoring index with the timeliness monitoring index threshold to classify the output timeliness of the user mental state evaluation model and generate different timeliness signals, including timeliness hazard signals and timeliness stable signals;

[0096] Compare the timeliness monitoring index with the timeliness monitoring index threshold. If the timeliness monitoring index is greater than the timeliness monitoring index threshold, there is a risk of a decrease in the output timeliness of the user mental state evaluation model, and a timeliness hazard signal is generated;

[0097] If the timeliness monitoring index is less than or equal to the timeliness monitoring index threshold, it indicates that the output timeliness of the user mental state evaluation model is relatively normal and there is no obvious decrease in timeliness, and a timeliness stable signal is generated;

[0098] Step S5: When a timeliness hazard signal is generated, obtain the corresponding timeliness monitoring data information, establish a timeliness monitoring data set, analyze the timeliness monitoring data in the set, and conduct a risk warning on the influence depth of the timeliness hazard.

[0099] The timeliness monitoring data information includes the timeliness monitoring index difference zsc;

[0100] The difference in the timeliness monitoring index refers to the degree of deviation between the timeliness monitoring index and the timeliness monitoring index threshold when a timeliness hazard signal is generated; the calculation expression of the difference in the timeliness monitoring index is as follows: Difference in timeliness monitoring index = Timeliness monitoring index - Timeliness monitoring index threshold;

[0101] Based on the difference in the timeliness monitoring index obtained each time a timeliness hazard signal is generated, a timeliness monitoring data set is established. The differences in the timeliness monitoring index within the set are arranged in the order of the generation of the timeliness hazard signals. The timeliness monitoring data within the set is analyzed to conduct risk early warning on the impact depth of the timeliness hazard. Specifically as follows:

[0102] Set a moving window size , and calculate the moving average of the timeliness monitoring data set. The expression is as follows , where represents the calculated th moving average, represents the difference in the timeliness monitoring index with the th number in the timeliness monitoring data set;

[0103] Compare the moving average with the moving average threshold. When the calculated moving average is greater than the moving average threshold, it indicates that the impact depth of the timeliness hazard is continuously deepening, and a risk early warning signal is generated to conduct early warning on potential risks and improve the performance and user experience of the metaverse user mental state evaluation system; when the calculated moving average is less than or equal to the moving average threshold, it indicates that the timeliness output by the user mental state evaluation model at this stage is relatively stable, and the impact depth of the timeliness hazard is within an acceptable range, and no immediate corrective measures need to be taken;

[0104] The present invention obtains the virtual scene update data in the metaverse, analyzes the obtained virtual scene update data to quantify whether there are abnormal fluctuations in the user's mental state, and determines whether the user is an unstable user. When the user is an unstable user, it obtains the unstable information of data collection during the operation of the user mental state evaluation system in the metaverse, the fluctuation information of data transmission, and the uneven information of computing resource allocation of the user mental state evaluation model to construct an evaluation result timeliness monitoring model, analyzes the output timeliness existing in the user mental state evaluation model, compares the timeliness monitoring index with the threshold value, generates a timeliness hidden danger signal and a timeliness stability signal, timely identifies and responds to potential problems, ensures the real-time nature of the evaluation result, ensures the continuous monitoring of the timeliness of the evaluation result, provides basic data for subsequent risk early warning. When a timeliness hidden danger signal is generated, it obtains the corresponding timeliness monitoring data information, establishes a timeliness monitoring data set, analyzes the timeliness monitoring data set and calculates the moving average value to conduct a risk early warning on the influence depth of the timeliness hidden danger, ensuring intervention before or at the initial stage of the problem occurrence, and improving the overall performance and user experience.

[0105] Embodiment 2: This embodiment is an introduction to a user mental state evaluation system for the metaverse. As Figure 2 shown, it includes a user classification module for obtaining the virtual scene update data in the metaverse and analyzing the obtained virtual scene update data to determine whether the user is an unstable user;

[0106] a data generation module, when the user is an unstable user, obtaining the unstable information of data collection during the operation of the user mental state evaluation system in the metaverse, the fluctuation information of data transmission, and the uneven information of computing resource allocation of the user mental state evaluation model;

[0107] a model construction module for constructing an evaluation result timeliness monitoring model, analyzing the output timeliness existing in the user mental state evaluation model, and generating a timeliness monitoring index;

[0108] a timeliness classification module for comparing the timeliness monitoring index with the timeliness monitoring index threshold value, classifying the output timeliness of the user mental state evaluation model, and generating different timeliness signals, including a timeliness hidden danger signal and a timeliness stability signal;

[0109] a risk early warning module, when a timeliness hidden danger signal is generated, obtaining the corresponding timeliness monitoring data information, establishing a timeliness monitoring data set, analyzing the timeliness monitoring data in the set, and conducting a risk early warning on the influence depth of the timeliness hidden danger;

[0110] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula that is closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0111] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0112] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0113] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described system and method can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0114] In several embodiments provided in the present application, it should be understood that the disclosed system and method can be implemented in other ways.

[0115] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for evaluating the psychological state of a user in a metaverse, characterized in that: The method comprises the following steps: Step S1, obtaining virtual scene update data in the metaverse, and analyzing the obtained virtual scene update data to determine whether the user is an unstable user; Step S2, when the user is in an unstable state, obtain the instability information of data collection, the fluctuation information of data transmission, and the uneven distribution information of computing resources of the user psychological state evaluation model when the Metaverse user psychological state evaluation system is running; Step S3, constructing an evaluation result timeliness monitoring model, analyzing the output timeliness of the user psychological state evaluation model, and generating a timeliness monitoring index; Step S4, comparing the timeliness monitoring index with the timeliness monitoring index threshold, classifying the output timeliness of the user psychological state assessment model, and generating different timeliness signals, including a timeliness hidden danger signal and a timeliness stable signal; Step S5, when a timeliness hidden danger signal is generated, the corresponding timeliness monitoring data information is obtained, a timeliness monitoring data set is established, the timeliness monitoring data in the set is analyzed, and a risk warning is issued for the impact depth of the timeliness hidden danger; When the user is in the Metaverse space, the Metaverse's user psychological state assessment system will collect the user's behavioral data, physiological data, and emotional data in the Metaverse through various devices on the data collection end, build a user psychological state assessment model, and assess the user's psychological state in the Metaverse in real time. The Metaverse virtual environment control subsystem will adjust the virtual scene in the Metaverse in real time according to the user's psychological state assessment results. The changes in the virtual scene in the Metaverse come from the user's psychological state assessment. Therefore, by obtaining the virtual scene update data in the Metaverse and analyzing the obtained virtual scene update data, it is possible to quantify whether there are abnormal fluctuations in the user's psychological state and determine whether the user is an unstable user, as follows: Obtain virtual scene update data in the Metaverse, including scene existence duration, scene switching times, and user interaction times with scene objects; Preprocessing the virtual scene update data, including processing missing values, outliers, and data standardization, to obtain the original virtual scene update data time series based on equal intervals; The local regression method is used to extract the trend component from the original virtual scene update data time series. The expression is as follows , where Represents the trend component, Represents the original virtual scene update data, An extraction function representing a local regression method for extracting trend components from the original virtual scene update data time series; Subtract the trend component from the original data and use the local regression method to extract the seasonal component. The expression is as follows , where Indicates seasonal component; The residual component is calculated based on the trend component and seasonal component. The expression is as follows , where represents the residual component; Calculate the standard deviation of the residual component, the expression is as follows , where represents the standard deviation of the residual component, Represents the average value of the residual component, and the expression is as follows , represents the residual component at time t, and n is a positive integer; The standard deviation of the residual component is compared with the standard deviation threshold. If the standard deviation of the residual component is greater than the standard deviation threshold, the user is marked as an unstable user; if the standard deviation of the residual component is less than or equal to the standard deviation threshold, the user is marked as a stable user.

2. A user psychological state assessment method for a metaverse according to claim 1, characterized in that: In step S2, the unstable information of data collection includes the unstable coefficient of data collection, the fluctuation information of data transmission includes the transmission fluctuation coefficient, and the uneven resource allocation information calculated by the user psychological state evaluation model includes the uneven resource allocation coefficient. The unstable coefficient of data collection, the transmission fluctuation coefficient, and the uneven resource allocation coefficient are marked as .

3. A user psychological state assessment method for a metaverse according to claim 2, characterized in that: By obtaining the unstable information of data collection and analyzing the unstable factors of the data collection process, the acquisition instability coefficient is obtained. The acquisition logic of the acquisition instability coefficient is as follows: The unstable data of data collection are obtained, including data missing rate, equipment failure rate, and data collection interval variance, and an unstable data set is constructed. Each data point in the unstable data set includes three types of indicators, namely, data missing rate, equipment failure rate, and data collection interval variance; Compute the raw distance matrix between data points in an unstable dataset , the expression is as follows: , where , , They represent the data missing rate, equipment failure rate, and data collection interval variance in data point i, respectively. , , They represent the values ​​of data missing rate, equipment failure rate, and data collection interval variance in data point j, respectively; Input the original distance matrix into the MDS algorithm, map the original distance matrix into three-dimensional space, and set the objective function , the expression is as follows , where represents the distance in the original distance matrix, Represents the distance in three-dimensional space. The position of data points in three-dimensional space is adjusted through iterative optimization until the objective function converges to the minimum value to obtain the final three-dimensional space. Calculate the variance of all data points in three-dimensional space along different axes. The axes of data points in three-dimensional space include x-axis, y-axis, and z-axis. The acquisition instability coefficient is calculated based on the variance of different axes. The expression is as follows , where represents the variance along the x-axis, represents the variance along the y-axis, Indicates the variance along the z-axis.

4. A user psychological state assessment method for a metaverse according to claim 2, characterized in that: By obtaining the fluctuation information of data transmission and analyzing the fluctuation of the data transmission process, the transmission fluctuation coefficient is obtained. The logic for obtaining the transmission fluctuation coefficient is as follows: Get the original time series data during data transmission , including the arrival time and transmission delay of data packets; For the original time series data Perform wavelet decomposition, select Symlets wavelet as the wavelet basis function, and mark the decomposition scale layer as ; The original time series data Decomposed into approximate coefficients and detail coefficients, the decomposition formula is as follows , where Indicates The approximation coefficient of the layer, Indicates Layer detail factor; The energy value is calculated according to the detail coefficient of each layer scale. The expression is as follows , where Indicates Energy values ​​at the layer scale; Calculate the standard deviation of energy values , where Indicates the average value of energy value; Calculate the transmission fluctuation coefficient, the expression is as follows .

5. A user psychological state assessment method for Metaverse according to claim 2, characterized in that: By obtaining the uneven resource allocation information of the user psychological state evaluation model, the uneven resource allocation situation is analyzed to obtain the uneven resource allocation coefficient. The logic for obtaining the uneven resource allocation coefficient is as follows: Calculate the ratio of resource usage of each user to total resource usage by the user psychological state evaluation model in the same time period; Calculating the actual entropy , the expression is as follows , where represents the ratio of resource usage of the fth user to total resource usage, and F represents the total number of users; Calculate the maximum entropy value , the expression is as follows ; Calculate the resource inequality coefficient, the expression is as follows .

6. A method for evaluating user psychological state in a metaverse according to claim 2, characterized in that: In step S3, the acquisition instability coefficient, transmission fluctuation coefficient, and resource allocation unevenness coefficient are normalized, and an evaluation result timeliness monitoring model is constructed based on the normalized acquisition instability coefficient, transmission fluctuation coefficient, and resource allocation unevenness coefficient to generate a timeliness monitoring index. The model is based on the following formula , where They represent the preset proportional coefficients of the acquisition instability coefficient, the transmission fluctuation coefficient, and the resource allocation unevenness coefficient, respectively, and Both are greater than 0.

7. A method for evaluating user psychological state in a metaverse according to claim 6, characterized in that: In step S4, the timeliness monitoring index is compared with the timeliness monitoring index threshold, and if the timeliness monitoring index is greater than the timeliness monitoring index threshold, a timeliness hidden danger signal is generated; If the timeliness monitoring index is less than or equal to the timeliness monitoring index threshold, a timeliness stability signal is generated.

8. A method for evaluating user psychological state in a metaverse according to claim 7, characterized in that: In step S5, when a timeliness hidden danger signal is generated, corresponding timeliness monitoring data information is obtained, and the timeliness monitoring data information includes a timeliness monitoring index difference zsc; The calculation expression of the timeliness monitoring index difference is as follows: timeliness monitoring index difference = timeliness monitoring index - timeliness monitoring index threshold; A timeliness monitoring data set is established based on the timeliness monitoring index difference obtained each time a timeliness hidden danger signal is generated. The timeliness monitoring index difference in the set is arranged in the order in which the timeliness hidden danger signal is generated. The timeliness monitoring data in the set is analyzed, and a risk warning is issued for the impact depth of the timeliness hidden danger, as follows: Set a moving window size CK and calculate the moving average of the timeliness monitoring data set. The expression is as follows , where represents the calculated fth moving average, Indicates the difference in the timeliness monitoring index of the bth number in the timeliness monitoring data set; The moving average is compared with the moving average threshold. When the calculated moving average is greater than the moving average threshold, a risk warning signal is generated; when the calculated moving average is less than or equal to the moving average threshold, no immediate corrective action is required.

9. A user psychological state assessment system for a metaverse, used to implement a user psychological state assessment method for a metaverse as claimed in any one of claims 1 to 8, characterized in that: It includes a user classification module, which is used to obtain virtual scene update data in the metaverse, and analyze the obtained virtual scene update data to determine whether the user is an unstable user; The data generation module, when the user is in an unstable state, obtains the instability information of data collection during the operation of the user psychological state evaluation system of the Metaverse, the fluctuation information of data transmission, and the uneven distribution information of computing resources of the user psychological state evaluation model; Model building module, which builds a timeliness monitoring model for evaluation results, analyzes the timeliness of the output of the user psychological state evaluation model, and generates a timeliness monitoring index; The timeliness classification module compares the timeliness monitoring index with the timeliness monitoring index threshold, classifies the output timeliness of the user psychological state evaluation model, and generates different timeliness signals, including timeliness hidden danger signals and timeliness stable signals; The risk warning module, when a timeliness hidden danger signal is generated, obtains the corresponding timeliness monitoring data information, establishes a timeliness monitoring data set, analyzes the timeliness monitoring data in the set, and issues a risk warning on the depth of impact of the timeliness hidden danger.

Images