User emotion influence condition analysis method and device, equipment, medium and product

Abstract

The embodiment of the invention provides a user emotion influence condition analysis method and device, equipment, a medium and a product, and is applied to the technical field of data science. The method comprises the following steps: grouping a plurality of test users to obtain two test groups; according to a plurality of different types of to-be-tested audio-visual contents, performing a high immersion test on one of the two test groups, and performing a low immersion test on the other group to obtain pre-delivery test data and post-delivery test data corresponding to each test group; based on the put test data corresponding to each test group, analyzing the influence difference of the two immersive tests on the emotion of the user to obtain a first analysis result; and based on the pre-delivery test data and the post-delivery test data corresponding to each test group, analyzing the influence difference of the two immersion tests on the user emotion change under different types of to-be-tested audio-visual contents to obtain a second analysis result. The method is used for achieving the effect of improving the user emotion influence condition analysis accuracy.

Description

Technical Field

[0001] This application relates to the field of data science technology, and in particular, to a method, device, equipment, medium and product for analyzing user emotion influencing conditions. Background Art

[0002] With the development of virtual reality and augmented reality technologies, media technology has achieved a breakthrough from the real world to the virtual world. In the transformation of media technology, an immersive experience is created for users based on virtual reality devices or augmented reality devices. In order to improve the user experience effect, it is necessary to analyze the emotional reactions of users during the experience process, and clarify the main factors that cause changes in user emotions, so as to optimize the main factors and achieve the effect of improving the user experience.

[0003] In the prior art, the main way to analyze emotional reactions for users' immersive experience is: when users experience virtual reality devices or augmented reality devices, physiological data generated by users during the experience is obtained through physiological data detection; the physiological data is analyzed to determine the influence of audio-visual content types on user emotion changes, so as to achieve the purpose of analyzing user emotion influencing conditions.

[0004] Since the method for detecting user emotions in the prior art is single, there is a technical problem of low accuracy in analyzing user emotion influencing conditions in the prior art. Summary of the Invention

[0005] Embodiments of this application provide a method, device, equipment, medium and product for analyzing user emotion influencing conditions, so as to achieve the technical effect of improving the accuracy of analyzing user emotion influencing conditions.

[0006] In a first aspect, embodiments of this application provide a method for analyzing user emotion influencing conditions, including:

[0007] Grouping multiple test users to obtain two test groups;

[0008] According to multiple different types of audio-visual content to be tested, one of the two test groups is subjected to a high-immersion test, and the other group is subjected to a low-immersion test, and pre-placement test data and post-placement test data corresponding to each test group are obtained; among them, the pre-placement test data corresponding to each test group refers to the score of the test users in the test group before experiencing the audio-visual content to be tested, and the post-placement test data corresponding to each test group refers to the score of the test users in the test group after experiencing the audio-visual content to be tested, and the immersion degree of the users in the high-immersion test is greater than that of the users in the low-immersion test;

[0009] Analyze the difference in the impact of high-immersion tests and low-immersion tests on user emotions based on the post-placement test data corresponding to each test group, and obtain the first analysis result;

[0010] Based on the pre-placement test data and post-placement test data corresponding to each test group, analyze the difference in the impact of different types of audiovisual content to be tested on the change of user emotions in the case of high-immersion tests and low-immersion tests, and obtain the second analysis result.

[0011] In a possible implementation manner, analyzing the difference in the impact of high-immersion tests and low-immersion tests on user emotions based on the post-placement test data corresponding to each test group, and obtaining the first analysis result, including:

[0012] Conduct an independent sample test for each type of audiovisual content to be tested, and calculate the first test value of each type of audiovisual content to be tested in high-immersion tests and low-immersion tests;

[0013] Judge whether the first test value of each audiovisual content to be tested is within the first preset test value range;

[0014] If not, determine the first analysis result as that the impact effects of high-immersion tests and low-immersion tests on user emotions are inconsistent;

[0015] If so, determine the first analysis result as that the impact effects of high-immersion tests and low-immersion tests on user emotions are consistent.

[0016] In a possible implementation manner, conducting an independent sample test for each type of audiovisual content to be tested, and calculating the first test value of each type of audiovisual content to be tested in high-immersion tests and low-immersion tests, including:

[0017] For each type of audiovisual content to be tested, based on the post-placement test data corresponding to each test group, determine the first number of test users and the first test score in high-immersion tests, and determine the second number of test users and the second test score in low-immersion tests;

[0018] Based on the first number of test users and the first test score, calculate the first average score and the first score variance;

[0019] Based on the second number of test users and the second test score, calculate the second average score and the second score variance;

[0020] Based on the first average score, the first score variance, the second average score, and the second score variance, calculate the first test value.

[0021] In a possible implementation manner, based on the pre-launch test data and post-launch test data corresponding to each test group, analyze the differences in the impacts on the emotional changes of users of different types of audiovisual content to be tested under high-immersion tests and low-immersion tests, and obtain a second analysis result, including:

[0022] For each type of audiovisual content to be tested, based on the pre-launch test data and post-launch test data corresponding to each test group, determine the first score difference in the high-immersion test and the second score difference in the low-immersion test;

[0023] Based on the first score difference, the second score difference, the number of first test users, and the number of second test users, conduct an independent samples test to generate a second test value;

[0024] Determine whether the second test value is within the second preset test value range;

[0025] If so, determine the type of the audiovisual content to be tested as the target type, and determine the second analysis result as that when the type of the audiovisual content to be tested is the target type, the impact amplitudes of the high-immersion test and the low-immersion test on the emotional changes of users are the same.

[0026] In a possible implementation manner, according to multiple different types of audiovisual content to be tested, conduct a high-immersion test on one of the two test groups and a low-immersion test on the other group, and obtain the pre-launch test data and post-launch test data corresponding to each test group, including:

[0027] Based on the type of each audiovisual content to be tested, determine the preset questionnaire template corresponding to each audiovisual content to be tested;

[0028] Based on multiple different types of audiovisual content to be tested and the preset questionnaire template corresponding to each audiovisual content to be tested, generate a test questionnaire;

[0029] Based on the test questionnaire, obtain the pre-launch test data and post-launch test data corresponding to each test group;

[0030] Based on the pre-launch test data corresponding to each test group, conduct a reliability and validity test on the test questionnaire to obtain a reliability and validity test result;

[0031] When the reliability and validity test result is a failed verification, update the test questionnaire to obtain an updated test questionnaire, and based on the updated test questionnaire, obtain the updated pre-launch test data and post-launch test data of each test group.

[0032] In a possible implementation manner, based on the pre-launch test data corresponding to each test group, conduct a reliability and validity test on the test questionnaire to obtain a reliability and validity test result, including:

[0033] Determine the number of test questions based on the test questionnaire;

[0034] Determine the test score corresponding to each test question based on the pre-launch test data;

[0035] Calculate the reliability coefficient of the test questionnaire based on the number of test questions and the test score corresponding to each test question;

[0036] If the reliability coefficient is greater than or equal to the preset reliability coefficient, determine that the test questionnaire passes the reliability check;

[0037] Calculate the first correlation coefficient and the second correlation coefficient between each pair of test questions based on the pre-launch test data; wherein, the first correlation coefficient is used to indicate the strength of the correlation between each pair of test questions, and the second correlation coefficient is used to indicate whether there is a correlation between each pair of test questions;

[0038] If the first correlation coefficient exceeds the first preset correlation coefficient range and the second correlation coefficient exceeds the second preset correlation coefficient range, determine that the test questionnaire passes the validity check;

[0039] When the test questionnaire passes the reliability check and the validity check, determine the reliability and validity check result as passed.

[0040] In a possible implementation manner, after obtaining the reliability and validity check result, the method further includes:

[0041] When the reliability and validity check result is passed, perform a grouping check on two test groups based on the pre-launch test data to obtain a grouping check result;

[0042] When the grouping check result is not passed, re-group multiple test users to obtain two updated test groups.

[0043] In a possible implementation manner, perform a grouping check on two test groups based on the pre-launch test data and obtain a grouping check result, including:

[0044] Based on the pre-launch test data, perform an independent sample check on each test question in the test questionnaire to generate a third check value for each test question; wherein, the third check value is used to indicate whether the distribution of test users in the two test groups corresponding to the high-immersion test and the low-immersion test is balanced;

[0045] Judge whether the third check value corresponding to each test question is within the third preset check value range;

[0046] If so, determine that the grouping check result is passed.

[0047] Second aspect, an analysis device for user emotion influence conditions provided by an embodiment of the present application includes:

[0048] A first processing module, configured to group multiple test users to obtain two test groups;

[0049] A second processing module, configured to perform a high-immersion test on one of the two test groups according to multiple different types of audiovisual content to be tested, and perform a low-immersion test on the other group, and obtain pre-placement test data and post-placement test data corresponding to each test group; wherein, the pre-placement test data corresponding to each test group refers to the scores of the test users in the test group before experiencing the audiovisual content to be tested, and the post-placement test data corresponding to each test group refers to the scores of the test users in the test group after experiencing the audiovisual content to be tested, and the immersion degree of the users in the high-immersion test is greater than the immersion degree of the users in the low-immersion test;

[0050] A third processing module, configured to analyze the influence difference of the high-immersion test and the low-immersion test on user emotions based on the post-placement test data corresponding to each test group, and obtain a first analysis result;

[0051] A fourth processing module, configured to analyze the influence difference of different types of audiovisual content to be tested on the change of user emotions in the case of high-immersion test and low-immersion test based on the pre-placement test data and the post-placement test data corresponding to each test group, and obtain a second analysis result.

[0052] In a possible implementation manner, the third processing module is further configured to:

[0053] Perform an independent sample check for each type of audiovisual content to be tested, and calculate a first check value of each type of audiovisual content to be tested in the high-immersion test and the low-immersion test;

[0054] Judge whether the first check value of each audiovisual content to be tested is within a first preset check value range;

[0055] If not, determine the first analysis result as that the influence effects of the high-immersion test and the low-immersion test on user emotions are inconsistent;

[0056] If so, determine the first analysis result as that the influence effects of the high-immersion test and the low-immersion test on user emotions are consistent.

[0057] In a possible implementation manner, the third processing module is further configured to:

[0058] For each type of audiovisual content to be tested, based on the post-placement test data corresponding to each test group, determine the number of first test users and the first test score in the high-immersion test, and determine the number of second test users and the second test score in the low-immersion test;

[0059] Calculate the first average score and the first variance of scores based on the first number of test users and the first test scores.

[0060] Calculate the second average score and the second variance of scores based on the second number of test users and the second test scores.

[0061] Calculate the first verification value based on the first average score, the first variance of scores, the second average score, and the second variance of scores.

[0062] In a possible implementation manner, the fourth processing module is further configured to:

[0063] For each type of audiovisual content to be tested, determine the first score difference in the high-immersion test and the second score difference in the low-immersion test based on the pre-test data and the post-test data corresponding to each test group.

[0064] Conduct an independent samples test based on the first score difference, the second score difference, the first number of test users, and the second number of test users, and generate a second verification value.

[0065] Determine whether the second verification value is within the second preset verification value range.

[0066] If so, determine the type of the audiovisual content to be tested as the target type, and determine the second analysis result as that when the type of the audiovisual content to be tested is the target type, the influence amplitudes of the high-immersion test and the low-immersion test on the user's emotional change are consistent.

[0067] In a possible implementation manner, the second processing module is further configured to:

[0068] Based on the type of each audiovisual content to be tested, determine the preset questionnaire template corresponding to each audiovisual content to be tested.

[0069] Generate a test questionnaire based on multiple different types of audiovisual content to be tested and the preset questionnaire template corresponding to each audiovisual content to be tested.

[0070] Obtain the pre-test data and the post-test data corresponding to each test group based on the test questionnaire.

[0071] Conduct a reliability and validity test on the test questionnaire based on the pre-test data corresponding to each test group, and obtain the reliability and validity test result.

[0072] When the reliability and validity test result is that the test fails, update the test questionnaire to obtain the updated test questionnaire, and obtain the updated pre-test data and the updated post-test data corresponding to each test group based on the updated test questionnaire.

[0073] In a possible implementation, the second processing module is further configured to:

[0074] Determine the number of test questions based on the test questionnaire;

[0075] Determine the test score corresponding to each test question based on the pre-launch test data;

[0076] Calculate the reliability coefficient of the test questionnaire based on the number of test questions and the test score corresponding to each test question;

[0077] If the reliability coefficient is greater than or equal to the preset reliability coefficient, determine that the test questionnaire passes the reliability check;

[0078] Calculate the first correlation coefficient and the second correlation coefficient between each pair of test questions based on the pre-launch test data; wherein, the first correlation coefficient is used to indicate the strength of the correlation between each pair of test questions, and the second correlation coefficient is used to indicate whether there is a correlation between each pair of test questions;

[0079] If the first correlation coefficient exceeds the first preset correlation coefficient range and the second correlation coefficient exceeds the second preset correlation coefficient range, determine that the test questionnaire passes the validity check;

[0080] When the test questionnaire passes the reliability check and the validity check, determine the reliability and validity check result as passed.

[0081] In a possible implementation, the second processing module is further configured to:

[0082] When the reliability and validity check result is passed, perform a grouping check on the two test groups based on the pre-launch test data to obtain a grouping check result;

[0083] When the grouping check result is not passed, re-group the multiple test users to obtain two updated test groups.

[0084] In a possible implementation, the second processing module is further configured to:

[0085] Perform an independent sample check on each test question in the test questionnaire based on the pre-launch test data to generate a third check value for each test question; wherein, the third check value is used to indicate whether the distribution of test users in the two test groups corresponding to the high-immersion test and the low-immersion test is balanced;

[0086] Judge whether the third check value corresponding to each test question is within the third preset check value range;

[0087] If so, determine that the grouping check result is passed.

[0088] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor;

[0089] The memory stores computer-executable instructions;

[0090] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and various possible implementation manners in the first aspect.

[0091] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the above first aspect and various possible implementation manners in the first aspect.

[0092] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the above first aspect and various possible implementation manners in the first aspect.

[0093] The method, device, equipment, medium and product for analyzing the influencing conditions of user emotions provided by the embodiments of the present application. The method groups multiple test users to obtain two test groups; based on the audio-visual content to be tested of a type, immersion tests are performed on the two test groups, one group undergoes a high-immersion test and the other group undergoes a low-immersion test. In the high-immersion test and the low-immersion test, the pre-placement test data and the post-placement test data corresponding to the two test groups are respectively obtained; wherein, the pre-placement test data refers to the scores of the test users in the test group for the audio-visual content to be tested before experiencing the audio-visual content to be tested; the post-placement test data refers to the scores of the test users in the test group for the audio-visual content to be tested after experiencing the audio-visual content to be tested. Using the obtained post-placement test data, analyze the differences in the influence on user emotions in the high-immersion test and the low-immersion test; using the test data before and after placement, obtain the dynamic change information of user emotions before and after experiencing the audio-visual content to be tested, and analyze the differences in the influence of the high-immersion test and the low-immersion test on the change of user emotions in different audio-visual content to be tested. Compared with the prior art, the present application obtains the dynamic data of the emotional changes of users before and after experiencing the audio-visual content to be tested by obtaining the pre-placement test data and the post-placement test data corresponding to each test group, analyzes the post-placement test data of the two test groups to determine whether there are differences in the influence on user emotions in the case of high-immersion test and low-immersion test; using the test data before and after placement, determine whether the emotional changes of users in different types of audio-visual content to be tested are consistent in the high-immersion test and the low-immersion test scenarios, so as to determine whether there are differences in the influence of the high and low immersion levels and the type of audio-visual content to be tested on user emotions; achieving the technical effect of improving the accuracy of analyzing the influencing conditions of user emotions. Description of the Drawings

[0094] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0095] Figure 1 Schematic flowchart of the analysis method for user emotion influence conditions provided by this application Figure 1 ;

[0096] Figure 2 Schematic flowchart of the analysis method for user emotion influence conditions provided by this application Figure 2 ;

[0097] Figure 3 Schematic flowchart of the analysis method for user emotion influence conditions provided by this application Figure 3 ;

[0098] Figure 4 Schematic flowchart of the user emotion analysis method applied to immersive experience provided by an embodiment of this application;

[0099] Figure 5 Schematic structural diagram of the analysis device for user emotion influence conditions provided by this application;

[0100] Figure 6 Schematic structural diagram of the electronic device provided by this application.

[0101] Through the above accompanying drawings, specific embodiments of this application have been shown, and there will be more detailed descriptions hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments. Detailed Description of Specific Embodiments

[0102] Here, the exemplary embodiments will be described in detail, and the examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. On the contrary, they are merely examples of devices and methods consistent with some aspects of this application as detailed in the appended claims.

[0103] First, the nouns involved in this application will be explained:

[0104] Independent sample test: The independent sample test in this application refers to the independent sample T-test, which is a statistical method used to compare whether there are significant differences in the means of two independent samples. It is used to conduct a null hypothesis and calculate the T-value under the null hypothesis, and then compare the T-value with its corresponding critical value to determine whether to reject the null hypothesis. Here, the T in the independent sample T-test only exists as an identifier.

[0105] p-value: The p-value is usually used to represent the probability of observing the statistical result or a more extreme result under the premise that the null hypothesis holds, quantifying the possibility of obtaining the same or a more extreme result when the null hypothesis is true.

[0106] Cronbach's Alpha: It is a statistical index used to test the internal consistency or reliability of a scale (such as a questionnaire). It reflects the correlation between each item in the scale, thereby testing the reliability of the scale measurement.

[0107] Kaiser-Meyer-Olkin (KMO) value: It is a value for the sampling adequacy test, which is a statistical index used to judge whether the data is suitable for factor analysis. It measures the correlation structure between variables, reflecting the correlation and independence between variables in the data. The value range of the KMO value is between 0 and 1. The higher the value, the higher the suitability for factor analysis.

[0108] Bartlett's Test of Sphericity: Bartlett's spherical test is a statistical test method used to test whether the variables in a data set are suitable for factor analysis. Specifically, it tests whether the correlation matrix between sample variables is an identity matrix (i.e., there is no correlation between variables). If the correlation matrix is close to the identity matrix, it indicates that the data is not suitable for factor analysis. Here, the Bartlett statistic refers to the calculation result of Bartlett's spherical test.

[0109] In the prior art, when users have an immersive experience in a virtual reality scenario or an augmented reality scenario, in order to improve the user experience effect, it is necessary to obtain the user's experience feedback information, analyze the conditions that affect the user's experience emotions based on the experience feedback information, and optimize at the technical level, scenario level, and device level for these conditions, so as to achieve the effect of improving the user experience. Among them, the main way to analyze the emotional impact using the user's experience feedback information is: during the user's experience process, through the method of physiological data detection, obtain the physiological data generated by the user during the experience process; analyze the physiological data to determine the impact effect of the current experienced audiovisual content on the user's emotions.

[0110] However, in actual user emotion analysis, if physiological data of users needs to be obtained, corresponding physiological data detection devices need to be configured for each user participating in the experience, so as to collect the physiological data generated by users during the process of experiencing audiovisual content. Since the existing technologies mainly collect physiological data for a single test environment and a single type of audiovisual content, lacking the collection of data on the dynamic changes of emotions during the user experience process, the final analysis results are limited by the test environment and the type of audiovisual content, lacking comparability, thus leading to the technical problem of low accuracy in the analysis of user emotion influence conditions in the existing technologies.

[0111] In view of the above technical problems, the present application proposes the following technical concept: aiming at the technical problem of low accuracy in the analysis of user emotion influence conditions caused by the limitations of the test environment and the type of audiovisual content in the existing technologies. The present application proposes a method for improving the accuracy of the analysis of user emotion influence conditions, specifically: grouping a plurality of test users participating in the test, and according to the level of immersion, dividing one group of test groups for participating in high-immersion tests and the other group of test groups for participating in low-immersion tests. Based on each test group, obtain the scores of the test users before experiencing the audiovisual content to be tested and determine them as pre-release test data; obtain the scores of the test users after experiencing the audiovisual content to be tested and determine them as post-release test data. Based on the post-release test data, analyze the differences in user emotion influence in the cases of high-immersion tests and low-immersion tests; for different types of audiovisual content to be tested, based on the post-release test data and the pre-release test data, analyze the differences in the influence of high-immersion tests and low-immersion tests on user emotion changes; thus obtaining a first analysis result for reflecting whether the high-immersion test and the low-immersion test have the same influence on user emotions, and a second analysis result for whether the high-immersion test and the low-immersion test have the same tendency on user emotion changes in different audiovisual contents. Compared with the existing technologies, the present application analyzes the influence effects of different immersion levels on user emotions, and the influence effects of different immersion levels on user emotion changes in different types of audiovisual contents, through the test data before and after the test users experience the audiovisual content to be tested, analyzing the user emotion influence conditions from two levels, so as to achieve the technical effect of improving the accuracy of the analysis of user emotion influence conditions.

[0112] The following uses specific embodiments to elaborate in detail on the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems. These several specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The following will describe the embodiments of the present application with reference to the accompanying drawings.

[0113] Figure 1 Flow schematic of the analysis method for user emotion influence conditions provided by the present application Figure 1 as Figure 1As shown, the method includes:

[0114] S101. Group multiple test users to obtain two test groups.

[0115] In this step, the number and distribution characteristics of the test users in the two test groups are kept consistent. The distribution characteristics of the test users can be: the proportion of user preferences, the proportion of user ages, and the proportion of user identities.

[0116] Exemplarily, the number of test users is 1000, and the identities of 400 test users are male participants, and 600 test users are female participants. When grouping multiple test users, it is necessary to ensure that the identity proportion in each test group is consistent with the identity proportion between the groups, and at the same time, it is necessary to ensure that the number of test users is the same, that is, there are 500 test users in each test group, and the ratio of male participants to female participants in each test group is 2 to 3.

[0117] S102. According to multiple different types of audiovisual contents to be tested, conduct a high-immersion test on one of the two test groups and a low-immersion test on the other group, and obtain the pre-placement test data and post-placement test data corresponding to each test group.

[0118] In this step, the pre-placement test data corresponding to each test group refers to the scores of the test users in the test group before experiencing the audiovisual contents to be tested, and the post-placement test data corresponding to each test group refers to the scores of the test users in the test group after experiencing the audiovisual contents to be tested. The immersion degree of the users in the high-immersion test is greater than that of the users in the low-immersion test.

[0119] Optionally, a possible implementation manner of obtaining the pre-placement test data and post-placement test data through the high-immersion test and the low-immersion test in this step is: generating a test questionnaire based on multiple different types of audiovisual contents to be tested, using the test questionnaire to obtain the scores of the users before experiencing the audiovisual contents to be tested, and obtaining the pre-placement test data of each test group; using the test questionnaire to obtain the scores of the users after experiencing the audiovisual contents to be tested, and obtaining the post-placement test data of each test group.

[0120] Among them, the type of the audiovisual contents to be tested refers to the theme type to which the audiovisual contents to be tested belong; exemplarily, the theme type can be: scenery, humanities, art, road, thriller.

[0121] It should be noted that in this step, the method of obtaining test data using the test questionnaire is further elaborated in the embodiments shown below Figure 2 and no redundant elaboration is made here.

[0122] S103. Analyze the difference in the impact of high-immersion tests and low-immersion tests on user emotions based on the post-placement test data corresponding to each test group to obtain the first analysis result.

[0123] Optionally, a possible implementation of obtaining the first analysis result by analyzing the difference in the impact on the emotions of test users under high-immersion tests and low-immersion tests is as follows:

[0124] S1031. Conduct an independent-samples test for each type of audiovisual content to be tested, and calculate the first test value of each type of audiovisual content to be tested in high-immersion tests and low-immersion tests.

[0125] In this step, an independent-samples test means that for each type of audiovisual content to be tested, the scores given by each test user in the two test groups after experiencing this type of audiovisual content to be tested are obtained. According to the scores of multiple test users in the two test groups, the scores of the two test groups are compared, and the first test value of each audiovisual content to be tested is calculated by combining the scores of multiple test users using the independent-samples test method. The first test value is used to indicate whether there is a difference in the scores of the two test groups on this audiovisual content to be tested.

[0126] S1032. Determine whether the first test value of each audiovisual content to be tested is within the first preset test value range.

[0127] In this step, the first test value refers to the difference value between high-immersion tests and low-immersion tests calculated based on post-placement test data in an independent-samples test; the first preset test value range can be obtained by looking up a table.

[0128] Optionally, in a possible implementation, the p-value corresponding to the first test value can be calculated based on the first test value, where the p-value refers to the probability of the occurrence of extreme sample data in the two sets of post-placement test data obtained from the test questionnaire. When the p-value is higher than the significance level, there are differences caused by random fluctuations between the two test groups observed from the test data, and the test data of the two test groups can be regarded as consistent; when the p-value is lower than or equal to the significance level, it can be determined that the test data of the two test groups can be regarded as inconsistent.

[0129] S1033. If not, determine the first analysis result as that the impact effects of high-immersion tests and low-immersion tests on user emotions are inconsistent.

[0130] In this step, the first verification value is calculated based on the following: assuming that the test data corresponding to the two test groups is the same, on the premise of this assumption, calculate the difference between the means of the test data corresponding to the two test groups, so as to obtain the first verification value for measuring the difference. Using the first verification value and its corresponding critical value table, find the critical value range corresponding to the first verification value, so as to determine the first preset verification value range; when the first verification value does not belong to the first preset verification value range, it indicates that there is an obvious difference in the test data of the two test groups statistically, and it is determined that the effects of the high-immersion test and the low-immersion test on the user's emotion are inconsistent.

[0131] S1034. If so, determine the first analysis result as that the effects of the high-immersion test and the low-immersion test on the user's emotion are consistent.

[0132] In this step, when the first verification value belongs to the first preset verification value range, it indicates that there is no obvious difference in the test data corresponding to the two test groups statistically, and it can be determined that the effects of the high-immersion test and the low-immersion test on the user's emotion are consistent.

[0133] S104. Based on the pre-launch test data and post-launch test data corresponding to each test group, analyze the difference in the impact on the change of the user's emotion under the high-immersion test and the low-immersion test for different types of audiovisual content to be tested, and obtain the second analysis result.

[0134] In this step, the way to obtain the second analysis result can be:

[0135] S1041. Using the pre-launch test data and post-launch test data, calculate the changes in the pre-launch and post-launch test data generated for each type of audiovisual content to be tested in the high-immersion test and the low-immersion test respectively, that is, calculate the change value of the user's score for the audiovisual content to be tested.

[0136] S1042. For the mean value of the score change values of each audiovisual content to be tested in each test group, conduct an independent sample verification on this audiovisual content to be tested, and calculate the second verification value corresponding to each audiovisual content to be tested.

[0137] S1043. Determine whether the second verification value exceeds this range through the second preset verification value range; when the second verification value exceeds the second preset verification value range, determine that there is an obvious difference between the mean values of the score changes corresponding to the two test groups, that is, for this type of audiovisual content to be tested, the impact amplitudes on the change of the user's emotion under the high-immersion test and the low-immersion test are inconsistent; when the second verification value is within the second preset verification value range, determine that there is no obvious difference between the mean values of the score changes corresponding to the two test groups, that is, for this type of audiovisual content to be tested, the impact amplitudes on the change of the user's emotion under the high-immersion test and the low-immersion test are consistent.

[0138] Among them, the purpose of analyzing using the pre-launch test data and the post-launch test data is to quantify the influence range of high-immersion tests and low-immersion tests on the user's emotional changes based on the score changes of the test users' ratings of the audiovisual content to be tested before and after experiencing it, so as to achieve an independent sample verification of the user's emotional changes.

[0139] It should be noted that the calculation of the first verification value and the calculation of the second verification value in this embodiment are further explained in the embodiments shown below, and no redundant elaboration will be made here. Figure 3 as shown below, and no redundant elaboration will be made here.

[0140] The analysis method for the user emotion influence conditions provided in the embodiments of the present application conducts immersion tests on two test groups based on the type of audiovisual content to be tested. One group conducts high-immersion tests, and the other group conducts low-immersion tests. In the high-immersion test and the low-immersion test, the pre-launch test data and the post-launch test data corresponding to the two test groups are respectively obtained; among them, the pre-launch test data refers to the ratings of the audiovisual content to be tested by the test users in the test group before experiencing the audiovisual content to be tested; the post-launch test data refers to the ratings of the audiovisual content to be tested by the test users in the test group after experiencing the audiovisual content to be tested. Using the obtained post-launch test data, analyze the influence differences on the user's emotions in the high-immersion test and the low-immersion test; using the test data before and after, obtain the dynamic change information of the user's emotions before and after experiencing the audiovisual content to be tested, and analyze the influence differences of the high-immersion test and the low-immersion test on the user's emotional changes in different audiovisual contents to be tested. Compared with the prior art, the present application obtains the dynamic data of the user's emotional changes before and after experiencing the audiovisual content to be tested by obtaining the pre-launch test data and the post-launch test data corresponding to each test group, analyzes the post-launch test data of the two test groups to determine whether there are differences in the influence on the user's emotions in the high-immersion test and the low-immersion test cases; uses the test data before and after to determine whether the user's emotional changes in different types of audiovisual contents to be tested are consistent in the high-immersion test and the low-immersion test scenarios, so as to determine whether there are differences in the influence of the immersion level and the type of audiovisual content to be tested on the user's emotions; achieving the technical effect of improving the analysis accuracy of the user emotion influence conditions.

[0141] Figure 2 is a flowchart of the analysis method for the user emotion influence conditions provided by the present application Figure 2 Based on the above Figure 1 shown embodiments, this embodiment further explains how to obtain test data using a test questionnaire for step S102, as Figure 2 shown, the method includes:

[0142] S201. Determine the preset questionnaire template corresponding to each audiovisual content to be tested based on the type of each audiovisual content to be tested.

[0143] In this step, the types of the preset questionnaire templates can be: Likert scale, multiple-choice questions, rating scale, binary multiple-choice questions. The types of the audiovisual content to be tested and the preset questionnaire templates correspond one by one, and the preset questionnaire templates corresponding to the audiovisual content to be tested of each type belong to the same type, which is used to ensure the unity of the test questionnaire.

[0144] Exemplarily, when the type of the preset questionnaire template is the Likert scale and the type of the audiovisual content to be tested is "thriller", the preset questionnaire template corresponding to the audiovisual content to be tested can be: {Question: Does the movie you watched make you feel scared? The higher the score, the more terrifying it is. Rating options: Not terrifying (1 point), hardly terrifying (2 points), somewhat terrifying (3 points), quite terrifying (4 points), very terrifying (5 points)}

[0145] S202. Generate a test questionnaire based on multiple different types of audiovisual content to be tested and the preset questionnaire template corresponding to each audiovisual content to be tested.

[0146] In this step, the test questionnaire contains the preset questionnaire template corresponding to each audiovisual content to be tested, and there is a corresponding test question for the audiovisual content to be tested in the test questionnaire.

[0147] Exemplarily, there are three audiovisual contents to be tested, and the types of these three audiovisual contents to be tested are: horror, adventure, and scenery; then determine the respective corresponding preset questionnaire templates according to the three audiovisual contents to be tested, generate corresponding test questions based on the preset questionnaire templates and the types of the audiovisual contents to be tested; combine the test questions corresponding to the three audiovisual contents to be tested to obtain the test questionnaire.

[0148] The information in this test questionnaire is:

[0149] Question 1: (Before experience: horror movie / After experience: the horror movie you watched) Does it make you feel scared? The higher the score, the more terrifying it is.

[0150] Rating option 1: Not terrifying (1 point), hardly terrifying (2 points), somewhat terrifying (3 points), quite terrifying (4 points), very terrifying (5 points).

[0151] Question 2: (Before: adventure movie / After: the adventure movie you watched) Does it make you feel excited? The higher the score, the more exciting it is.

[0152] Rating option 2: Not exciting (1 point), hardly exciting (2 points), a bit exciting (3 points), quite exciting (4 points), very exciting (5 points).

[0153] Question 3: (Before: Scenic Video / After: The scenic video you watched) Did it make you feel that the scenery was beautiful? A higher score means you felt more beautiful scenery.

[0154] Rating Option 3: Not beautiful (1 point), hardly beautiful (2 points), a bit beautiful (3 points), quite beautiful (4 points), very beautiful (5 points).

[0155] S203. Obtain the pre - placement test data and post - placement test data corresponding to each test group based on the test questionnaire.

[0156] In this step, the method of obtaining the pre - placement test data and post - placement test data using the test questionnaire can be:

[0157] Determine the device used by the user to experience the audiovisual content to be tested, and push the test questionnaire to the user interface of this device before and after the experience, so as to obtain the pre - placement test data and post - placement test data submitted by the test users.

[0158] Among them, the pre - placement test data of each test group includes: the number of test users participating in the test in this test group, and the ratings given by each test user for each test question in the test questionnaire.

[0159] S204. Based on the pre - placement test data corresponding to each test group, perform reliability and validity verification on the test questionnaire to obtain the reliability and validity verification results.

[0160] In this step, performing reliability and validity verification on the test questionnaire means using the pre - placement test data to detect the rationality of each test question in the test questionnaire.

[0161] Optionally, a possible implementation method for performing reliability and validity verification on the test questionnaire to obtain the reliability and validity test results is:

[0162] S2041. Based on the test questionnaire, determine the number of test questions.

[0163] S2042. Based on the pre - placement test data, determine the test ratings corresponding to each test question.

[0164] In this step, the test ratings of each test question include: the test ratings given by each test user for this question in the high - immersion test, and the test ratings given by each test user for this question in the low - immersion test.

[0165] S2043. Based on the number of test questions and the test ratings corresponding to each test question, calculate the reliability coefficient of the test questionnaire.

[0166] In this step, the Cronbach's alpha coefficient is used as the index for reliability verification, and the reliability coefficient α is calculated using Formula 1. Here, α refers to the reliability coefficient; n refers to the number of test questions; S2i refers to the variance of the scores of the i-th question, which is used to measure the degree of score variation of this question; S2t refers to the variance of the total scores of all questions, that is, the degree of variation of the total score obtained by adding up the scores of all questions.

[0167]

[0168] S2044. If the reliability coefficient is greater than or equal to the preset reliability coefficient, it is determined that the test questionnaire passes the reliability verification.

[0169] In this step, the higher the reliability coefficient, the higher the reliability of the test questionnaire. The value of the preset reliability coefficient is related to the application scenario of the test questionnaire, and different application scenarios correspond to different values of the preset reliability coefficient.

[0170] Exemplarily, the value of the preset reliability coefficient is 0.8, and the value of the reliability coefficient calculated using the pre-launch test data is 0.9, which is greater than the preset reliability coefficient, indicating that the current test questionnaire passes the reliability verification.

[0171] S2045. Calculate the first correlation coefficient and the second correlation coefficient between each test question based on the pre-launch test data.

[0172] In this step, the first correlation coefficient is used to indicate the strength of the correlation between each test question, and the second correlation coefficient is used to indicate whether there is a correlation between each test question.

[0173] Among them, the first correlation coefficient refers to the KMO value, and the second correlation coefficient refers to the Bartlett test statistic.

[0174] In this step, the calculation method of the first correlation coefficient is as follows: Based on the pre-launch test data, determine the scores of each test question. Each test question has multiple scores, and each score corresponds to a test user. Calculate the first correlation coefficient based on the scores of each test question, as shown in Formula 2:

[0175]

[0176] Among them, KMO refers to the second correlation coefficient, r2ij is the square of the simple correlation coefficient between test question i and test question j, and α2ij refers to the square of the partial correlation coefficient between test question i and test question j.

[0177] Exemplarily, there are two test questions, numbered x and y. Each test question has three scores. By corresponding the three scores one by one, the score groups of the two test questions are obtained, which are (x1, y1), (x2, y2), and (x3, y3) respectively; where x refers to the score of the test question numbered x, and y refers to the score of the test question numbered y. Based on the scores of the two test questions, calculate the square of the simple correlation coefficient between the two test questions. Obtain the three scores of the third test question, and use the three scores of the third test question to calculate the square of the partial correlation coefficient between the two test questions numbered x and y. When there are multiple test questions, calculate the square of the simple correlation coefficient and the square of the partial correlation coefficient between each pair of test questions, and sum them respectively, and use Formula 2 to calculate the first correlation coefficient.

[0178] The calculation method of the second correlation coefficient is as follows: Determine the score of each test question based on the pre-launch test data. Each test question has multiple scores, and each score corresponds to a test user. Calculate the second correlation coefficient based on the scores of each test question, as shown in Formula 3:

[0179]

[0180] where, X 2 refers to the second correlation coefficient, N refers to the number of test user scores collected in the two test groups, m refers to the number of test questions in the test questionnaire, det(R) refers to the determinant of the correlation matrix R, ln refers to the natural logarithm, and λ i refers to the eigenvalue of the correlation matrix R; the correlation matrix R refers to the linear relationship between all test questions in the test questionnaire.

[0181] Exemplarily, there are five questions in the test questionnaire, so the value of m is 5, and the correlation matrix R is a 5×5 matrix; the number of test users in both test groups is 10, so the value of N is 20; determine the correlation matrix R according to the scores of each test question, and thus calculate the eigenvalue λ corresponding to each test question in the correlation matrix i .

[0182] S2046. If the first correlation coefficient exceeds the first preset correlation coefficient range and the second correlation coefficient exceeds the second preset correlation coefficient range, it is determined that the test questionnaire passes the validity check.

[0183] In this step, based on S2046, the first correlation coefficient and the second correlation coefficient are calculated. The first correlation coefficient indicates the gap between the sum of the squares of the simple correlation coefficients and the sum of the squares of the partial correlation coefficients. When the first correlation coefficient is close to 1, it indicates that the sum of the squares of the simple correlation coefficients is much larger than the sum of the squares of the partial correlation coefficients, and thus it is determined that the correlation between the test questions is strong and the partial correlation is weak. The second correlation coefficient is used to indicate whether there is a correlation between the test questions. When the second correlation coefficient exceeds the second preset correlation coefficient range, it indicates that there is a correlation between the test questions.

[0184] Exemplarily, the first preset correlation coefficient range is [0, 0.9], and the second preset correlation coefficient range is [-2.5, 2.5]. The calculated first correlation coefficient is 0.8, and the second correlation coefficient is 2.6. Since the first correlation coefficient is within the first preset correlation coefficient range and the second correlation coefficient exceeds the second preset correlation coefficient range, it is determined that there is a correlation between the test questions, and at the same time, the correlation between the test questions is weak and the validity check fails. Only when the first correlation coefficient exceeds the first preset correlation coefficient range and the second correlation coefficient exceeds the second preset correlation coefficient range can it be determined that the validity check passes.

[0185] In this step, based on the second correlation coefficient, the p-value of the second correlation coefficient can also be calculated. When the calculated p-value is less than the significance level, it is determined that the validity check passes. The p-value is used to indicate the possibility of the occurrence of extreme samples in the test questions.

[0186] S2047. When the test questionnaire passes the reliability check and the validity check, the reliability and validity check result is determined to be passed.

[0187] In this step, when both the reliability check and the validity check pass, the reliability and validity check result is determined to be passed. When at least one of the reliability check and the validity check fails, the reliability and validity check is determined to be failed.

[0188] S205. When the reliability and validity check result is determined to be failed, the test questionnaire is updated to obtain the updated test questionnaire, and the updated pre-launch test data and post-launch test data for each test group are obtained based on the updated test questionnaire.

[0189] In this step, if the reliability and validity check fails, it indicates that the design of the test questionnaire is unreasonable, and the test questionnaire needs to be updated based on the audiovisual content to be tested.

[0190] Exemplarily, the ways to update the test questionnaire can be: updating the scoring setting rules in each test question and updating the scoring setting options in each test question.

[0191] Optionally, after the reliability and validity check passes, the test groups can also be updated according to the grouping check results of the two test groups. A possible implementation of updating the test groups is as follows:

[0192] S2051. When the reliability and validity check result is a pass, perform a grouping check on the two test groups based on the pre-launch test data to obtain the grouping check result.

[0193] In this step, the purpose of the grouping check is to determine whether the distribution of test users in the two test groups is balanced for the two test groups. Through the pre-launch test data, the scoring information of each test user in the two test groups is determined, and the scoring information is used to compare the differences between the two test groups. If the difference exceeds the limit, it indicates that the grouping is unbalanced. The specific grouping check method can adopt an independent sample check, calculate the third check value corresponding to each test question in the test questionnaire, and use the third check value to judge the rationality of the grouping.

[0194] Optionally, a possible implementation of obtaining the grouping check result through the grouping check is as follows:

[0195] A1. Based on the pre-launch test data, perform an independent sample check on each test question in the test questionnaire to generate the third check value for each test question.

[0196] In this step, the third check value is used to indicate whether the distribution of test users in the two test groups corresponding to the high-immersion test and the low-immersion test is balanced.

[0197] A2. Judge whether the third check value corresponding to each test question is within the range of the third preset check value.

[0198] A3. If so, determine that the grouping check result is a pass.

[0199] S2052. When the grouping check result is a fail, re-group multiple test users to obtain two updated test groups.

[0200] In this step, the re-grouping method can be to extract user characteristics based on multiple test users, and allocate multiple test users based on the user characteristics to ensure that the number of characteristics and the number of users in the two test groups are the same, and two updated test groups are obtained.

[0201] In this embodiment, the rationality of the test questionnaire is detected by means of reliability and validity verification. When the reliability and validity verification fails, the test questionnaire is updated; after the reliability and validity verification passes, group verification is performed on the two test groups to determine whether the distribution of test users in the two test groups is consistent. When the group verification fails, the two test groups are updated to ensure balanced grouping, thereby ensuring the credibility of the pre-launch test data and post-launch test data collected, which is conducive to further analysis of the pre-launch test data and post-launch test data.

[0202] Figure 3 Schematic flow of the analysis method for user emotion influence conditions provided by this application Figure 3 , based on the above Figure 1 On the basis of the embodiment shown, the calculation of the first verification value in step S103 and the calculation of the second verification value in step S104 are further elaborated in detail

[0203] S301. For each type of audiovisual content to be tested, based on the post-launch test data corresponding to each test group, determine the number of first test users and the first test score in the high-immersion test, and determine the number of second test users and the second test score in the low-immersion test.

[0204] In this step, the number of first test users refers to the number of test users in the high-immersion test, and the first test score refers to the score given by each test user to the audiovisual content to be tested in the high-immersion test. The number of second test users refers to the number of test users in the low-immersion test, and the second test score refers to the score given by each test user to the audiovisual content to be tested in the low-immersion test.

[0205] S302. Based on the number of first test users and the first test score, calculate the first score mean and the first score variance.

[0206] Exemplarily, the number of first test users is 5, and the first test scores are 5, 8, 10, 7, 6. The calculated first score mean is 7.2. Calculate the square difference between each first test score and the first score mean, and calculate the sum of the square differences. Based on the number of first test users, calculate the mean of the sum of the square differences to obtain the first score variance of 2.96.

[0207] S303. Based on the number of second test users and the second test score, calculate the second score mean and the second score variance.

[0208] In this step, the calculation method of the second score variance refers to S302.

[0209] S304. Based on the first score mean, the first score variance, the second score mean, and the second score variance, calculate the first verification value.

[0210] In this step, the first check value is calculated based on Formula 4, and Formula 4 is:

[0211]

[0212] where T refers to the first check value, n1 is the number of the first test users, n2 is the number of the second test users, S21 is the first score variance, S22 is the second score variance, is the first score mean, is the second score mean.

[0213] S305. For each type of audiovisual content to be tested, based on the pre - placement test data and post - placement test data corresponding to each test group, determine the first score difference in the high - immersion test and the second score difference in the low - immersion test.

[0214] In this step, the first score difference is the score difference of each test user before and after experiencing the audiovisual content to be tested in the high - immersion test, and the second score difference is the score difference of each test user before and after experiencing the audiovisual content to be tested in the low - immersion test.

[0215] S306. Conduct an independent - samples test based on the first score difference, the second score difference, the number of the first test users, and the number of the second test users to generate the second check value.

[0216] In this step, the calculation process of the second check value is the same as that of the first check value. Replace the first test score in the calculation process of the first check value with the first score difference, and the second test score with the second score difference. Calculate the mean value, variance using the first score difference, the second score difference, the number of the first users, and the number of the second users, and calculate the second check value in combination with Formula 4.

[0217] S307. Determine whether the second check value is within the second preset check - value range.

[0218] In this step, the method for determining the second preset check - value range is as follows: Calculate the degree of freedom of the second check value based on the number of the first test users and the number of the second test users. Based on the significance level and the degree of freedom, look up the critical value corresponding to the second check value from the preset critical - value table, and determine the second preset check - value range based on the critical value. Among them, the significance level can be set to 0.05.

[0219] S308. If so, determine the type of the audiovisual content to be tested as the target type, and determine the second analysis result as that when the type of the audiovisual content to be tested is the target type, the influence amplitudes of the high - immersion test and the low - immersion test on the user's emotional change are the same.

[0220] In this step, the second verification value is used to determine whether there is a difference in the influence amplitude of the two test methods on the user's emotional change under the audiovisual content to be measured of a specific type.

[0221] Exemplarily, when the type of the audiovisual content to be measured is the landscape type, if the calculated second verification value is within the second preset verification value range, it is determined that when the type of the audiovisual content to be measured is the landscape type, the amplitude of the user's emotional change is the same under the high-immersion test and the low-immersion test, and the influence of the immersion level on the amplitude of the emotional change is weak.

[0222] In this embodiment, the first verification value and the second verification value are calculated by means of independent sample verification. The first verification value can be used to judge whether the influence effects of different immersion levels on the user's emotion are the same, and the second verification value can be used to judge whether the influence amplitudes of different immersion levels on the user's emotional change are the same in different types of audiovisual content, so as to determine the influence of these two conditions, namely the immersion level and the type of the audiovisual content to be measured, on the user's emotion.

[0223] Based on the above embodiments, the present application proposes a user emotion analysis method applied to immersive audiovisual experience. Figure 4 As the schematic flowchart of the user emotion analysis method applied to immersive experience provided by the embodiment of the present application, as Figure 4 shown, the method includes:

[0224] B1. Optimize the questionnaire based on the type of the audiovisual content to be measured.

[0225] Determine the corresponding preset questionnaire template according to the type of the audiovisual content to be measured, and generate a test questionnaire for different types by using the preset questionnaire template to ensure the usability of the test questionnaire.

[0226] B2. Divide the test users into two test groups according to the high-immersion test and the low-immersion test, namely the high-immersion group and the low-immersion group.

[0227] B3. Use the test questionnaire to collect the pre-placement test data of the high-immersion group and the pre-placement test data of the low-immersion group.

[0228] B4. Use the test questionnaire to collect the post-placement test data of the high-immersion group and the post-placement test data of the low-immersion group.

[0229] B5. Perform reliability and validity verification on the test questionnaire based on the pre-placement test data of the two test groups, and obtain the reliability and validity verification results.

[0230] B6. Judge whether the verification passes based on the reliability and validity verification results. If not, return to B1 to regenerate the test questionnaire.

[0231] B7. When the new validity check passes, perform an inter-group check on the two test groups based on the pre-launch test data of the two test groups to obtain an inter-group check result.

[0232] B8. Determine whether the check passes based on the inter-group check result. If not, return to B2 to re-group.

[0233] B9. Analyze the post-launch test data of the two test groups to determine whether there are differences in the effects of high-immersion testing and low-immersion testing on user emotions, and obtain a first analysis result.

[0234] B10. Based on the pre- and post-launch test data of the two test groups, determine whether there are differences in the effects of high-immersion testing and low-immersion testing on user emotion changes for each type of audiovisual content to be tested, and obtain a second analysis result.

[0235] Figure 5 is a schematic structural diagram of an analysis device for user emotion influence conditions provided by the present application. As Figure 5 shown, the analysis device for user emotion influence conditions provided in this embodiment includes:

[0236] The first processing module 501 is used to group multiple test users into two test groups;

[0237] The second processing module 502 is used to perform high-immersion testing on one of the two test groups and low-immersion testing on the other group according to multiple different types of audiovisual content to be tested, and obtain the pre-launch test data and post-launch test data corresponding to each test group; wherein, the pre-launch test data corresponding to each test group refers to the score of the test users in the test group before experiencing the audiovisual content to be tested, and the post-launch test data corresponding to each test group refers to the score of the test users in the test group after experiencing the audiovisual content to be tested. The immersion degree of the users in the high-immersion test is greater than that of the users in the low-immersion test;

[0238] The third processing module 503 is used to analyze the influence difference between high-immersion testing and low-immersion testing on user emotions based on the post-launch test data corresponding to each test group to obtain a first analysis result;

[0239] The fourth processing module 504 is used to analyze the influence difference of different types of audiovisual content to be tested on user emotion changes in the case of high-immersion testing and low-immersion testing based on the pre-launch test data and post-launch test data corresponding to each test group to obtain a second analysis result.

[0240] In a possible implementation manner, the third processing module 503 is further used for:

[0241] Perform independent sample verification for each type of audiovisual content to be tested, and calculate the first verification value of each type of audiovisual content to be tested in the high-immersion test and the low-immersion test;

[0242] Determine whether the first verification value of each audiovisual content to be tested is within the first preset verification value range;

[0243] If not, determine the first analysis result as that the effects of the high-immersion test and the low-immersion test on the user's mood are inconsistent;

[0244] If so, determine the first analysis result as that the effects of the high-immersion test and the low-immersion test on the user's mood are consistent.

[0245] In a possible implementation, the third processing module 503 is further configured to:

[0246] For each type of audiovisual content to be tested, based on the post-placement test data corresponding to each test group, determine the first number of test users and the first test score in the high-immersion test, and determine the second number of test users and the second test score in the low-immersion test;

[0247] Based on the first number of test users and the first test score, calculate the first score mean and the first score variance;

[0248] Based on the second number of test users and the second test score, calculate the second score mean and the second score variance;

[0249] Based on the first score mean, the first score variance, the second score mean, and the second score variance, calculate the first verification value.

[0250] In a possible implementation, the fourth processing module 504 is further configured to:

[0251] For each type of audiovisual content to be tested, based on the pre-placement test data and the post-placement test data corresponding to each test group, determine the first score difference in the high-immersion test and the second score difference in the low-immersion test;

[0252] Based on the first score difference, the second score difference, the first number of test users, and the second number of test users, perform independent sample verification to generate a second verification value;

[0253] Determine whether the second verification value is within the second preset verification value range;

[0254] If so, determine the type of the audiovisual content to be tested as the target type, and determine the second analysis result as that when the type of the audiovisual content to be tested is the target type, the influence ranges of the high-immersion test and the low-immersion test on the user's mood change are consistent.

[0255] In a possible implementation, the second processing module 502 is further configured to:

[0256] Based on the type of each audiovisual content to be tested, determine the preset questionnaire template corresponding to each audiovisual content to be tested;

[0257] Based on multiple different types of audiovisual content to be tested and the preset questionnaire template corresponding to each audiovisual content to be tested, generate a test questionnaire;

[0258] Based on the test questionnaire, obtain the pre-launch test data and post-launch test data corresponding to each test group;

[0259] Based on the pre-launch test data corresponding to each test group, perform reliability and validity verification on the test questionnaire to obtain a reliability and validity verification result;

[0260] When the reliability and validity verification result is verification failed, update the test questionnaire to obtain an updated test questionnaire, and based on the updated test questionnaire, obtain the updated pre-launch test data and post-launch test data corresponding to each test group.

[0261] In a possible implementation, the second processing module 502 is further configured to:

[0262] Based on the test questionnaire, determine the number of test questions;

[0263] Based on the pre-launch test data, determine the test score corresponding to each test question;

[0264] Based on the number of test questions and the test score corresponding to each test question, calculate the reliability coefficient of the test questionnaire;

[0265] If the reliability coefficient is greater than or equal to the preset reliability coefficient, determine that the test questionnaire passes the reliability verification;

[0266] Based on the pre-launch test data, calculate the first correlation coefficient and the second correlation coefficient between each test question; wherein, the first correlation coefficient is used to indicate the strength of the correlation between each test question, and the second correlation coefficient is used to indicate whether there is a correlation between each test question;

[0267] If the first correlation coefficient exceeds the first preset correlation coefficient range and the second correlation coefficient exceeds the second preset correlation coefficient range, determine that the test questionnaire passes the validity verification;

[0268] When the test questionnaire passes the reliability verification and the validity verification, determine the reliability and validity verification result as verification passed.

[0269] In a possible implementation, the second processing module 502 is further configured to:

[0270] When the reliability and validity verification result is verified to pass, perform group verification on the two test groups based on the pre-launch test data to obtain the group verification result;

[0271] When the group verification result is verified to fail, re-group multiple test users to obtain two updated test groups.

[0272] In a possible implementation manner, the second processing module 502 is further configured to:

[0273] Based on the pre-launch test data, perform independent sample verification on each test question in the test questionnaire to generate a third verification value for each test question; wherein, the third verification value is used to indicate whether the distribution of test users in the two test groups corresponding to the high-immersion test and the low-immersion test is balanced;

[0274] Determine whether the third verification value corresponding to each test question is within the third preset verification value range;

[0275] If so, determine that the group verification result is verified to pass.

[0276] The analysis device for user emotion influence conditions provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0277] Figure 6 It is a schematic structural diagram of the electronic device provided in this application. As Figure 6 shown, the electronic device provided in this embodiment includes: at least one processor 601 and a memory 602. Optionally, the device further includes a communication component 603. Among them, the processor 601, the memory 602, and the communication component 603 are connected through a bus 604.

[0278] In the specific implementation process, at least one processor 601 executes the computer execution instructions stored in the memory 602, so that at least one processor 601 executes the above-mentioned analysis method for user emotion influence conditions or the test case generation method.

[0279] The specific implementation process of the processor 601 can refer to the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0280] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU for short), or other general-purpose processors, digital signal processors (DSP for short), application specific integrated circuits (ASIC for short), etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly implemented by the execution of the hardware processor, or by the combination of hardware and software modules in the processor.

[0281] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0282] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the buses in the drawings of this application are not limited to only one bus or one type of bus.

[0283] This application also provides a computer program product, including a computer program, which when executed by a processor implements the above-mentioned analysis method of user emotion influence conditions or test case generation method.

[0284] This application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When the processor executes the computer-executable instructions, the above-mentioned analysis method of user emotion influence conditions or test case generation method is implemented.

[0285] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk or an optical disk. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0286] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an Application Specific Integrated Circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0287] The division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings, direct couplings, or communication connections shown or discussed between each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms.

[0288] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0289] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can physically exist alone, or two or more units can be integrated in one unit.

[0290] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or this part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0291] Those of ordinary skill in the art will understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments; and the foregoing storage medium includes: various media such as ROM, RAM, magnetic disks, or optical disks that can store program codes.

[0292] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention, which follow the general principles of the present invention and include common general knowledge or conventional technical means in the technical field not disclosed by the present invention. It is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A method for analyzing conditions affecting user emotions, characterized in that: include: Group multiple test users to obtain two test groups; According to multiple different types of audio-visual contents to be tested, a high immersion test is performed on one of the two test groups, and a low immersion test is performed on the other group, and pre-delivery test data and post-delivery test data corresponding to each test group are obtained; wherein the pre-delivery test data corresponding to each test group refers to the score of the test users in the test group before experiencing the audio-visual contents to be tested, and the post-delivery test data corresponding to each test group refers to the score of the test users in the test group after experiencing the audio-visual contents to be tested, and the immersion degree of the users in the high immersion test is greater than the immersion degree of the users in the low immersion test; Based on the post-launch test data corresponding to each test group, the difference in the impact of the high immersion test and the low immersion test on user emotions is analyzed to obtain a first analysis result; Based on the pre-launch test data and post-launch test data corresponding to each test group, the difference in the impact of different types of audio-visual content to be tested on user emotional changes in the high immersion test and the low immersion test is analyzed to obtain a second analysis result.

2. The method according to claim 1, characterized in that The analysis of the difference in the impact of the high immersion test and the low immersion test on the user's emotions based on the post-delivery test data corresponding to each test group to obtain a first analysis result includes: Performing independent sample verification for each type of audio-visual content to be tested, and calculating a first verification value of each type of audio-visual content to be tested in the high immersion test and the low immersion test; Determining whether the first verification value of each of the audio-visual contents to be tested is within a first preset verification value range; If not, determining the first analysis result as that the high immersion test and the low immersion test have different effects on the user's emotions; If so, the first analysis result is determined as that the high immersion test and the low immersion test have the same effect on the user's emotions.

3. The method according to claim 2, characterized in that The performing independent sample verification for each type of audio-visual content to be tested, and calculating a first verification value of each type of audio-visual content to be tested in the high immersion test and the low immersion test, comprises: For each type of audio-visual content to be tested, based on the post-delivery test data corresponding to each test group, determine the number of first test users and the first test score in the high immersion test, and determine the number of second test users and the second test score in the low immersion test; Calculate a first score mean and a first score variance based on the first test user number and the first test score; Calculate a second score mean and a second score variance based on the number of the second test users and the second test scores; The first verification value is calculated based on the first score mean, the first score variance, the second score mean, and the second score variance.

4. The method according to claim 3, characterized in that The method analyzes the difference in the impact of different types of audio-visual content to be tested on user emotion changes in the high immersion test and the low immersion test based on the pre-delivery test data and the post-delivery test data corresponding to each test group, and obtains a second analysis result, including: For each type of audio-visual content to be tested, based on the pre-delivery test data and the post-delivery test data corresponding to each test group, determine a first score difference in the high immersion test and a second score difference in the low immersion test; Perform an independent sample verification based on the first score difference, the second score difference, the first number of test users, and the second number of test users to generate a second verification value; Determining whether the second verification value is within a second preset verification value range; If so, the type of the audio-visual content to be tested is determined as the target type, and the second analysis result is determined as that when the type of the audio-visual content to be tested is the target type, the high immersion test and the low immersion test have the same impact on the user's emotional changes.

5. The method according to claim 1, characterized in that According to the multiple different types of audio-visual contents to be tested, a high immersion test is performed on one of the two test groups, and a low immersion test is performed on the other group, and pre-delivery test data and post-delivery test data corresponding to each test group are obtained, including: Based on the type of each audio-visual content to be tested, determining a preset questionnaire template corresponding to each audio-visual content to be tested; Generate a test questionnaire based on a plurality of different types of the audio-visual content to be tested and a preset questionnaire template corresponding to each of the audio-visual content to be tested; Based on the test questionnaire, obtain pre-delivery test data and post-delivery test data corresponding to each test group; Based on the pre-launch test data corresponding to each test group, the test questionnaire is verified for reliability and validity to obtain a reliability and validity verification result; When the reliability and validity verification result is failure, the test questionnaire is updated to obtain an updated test questionnaire, and updated pre-delivery test data and post-delivery test data of each test group are obtained based on the updated test questionnaire.

6. The method according to claim 5, characterized in that The reliability and validity verification of the test questionnaire is performed based on the pre-delivery test data corresponding to each test group to obtain the reliability and validity verification results, including: Based on the test questionnaire, determining the number of test questions; Determine a test score corresponding to each of the test questions based on the pre-launch test data; Calculating the reliability coefficient of the test questionnaire based on the number of test questions and the test score corresponding to each test question; If the reliability coefficient is greater than or equal to the preset reliability coefficient, it is determined that the test questionnaire passes the reliability check; Calculate a first correlation coefficient and a second correlation coefficient between each of the test questions based on the pre-launch test data; wherein the first correlation coefficient is used to indicate the strength of the correlation between each of the test questions, and the second correlation coefficient is used to indicate whether there is a correlation between each of the test questions; If the first correlation coefficient exceeds a first preset correlation coefficient range, and the second correlation coefficient exceeds a second preset correlation coefficient range, then determining that the test questionnaire passes the validity check; When the test questionnaire passes the reliability verification and the validity verification, the reliability and validity verification results are determined as verification passed.

7. The method according to claim 5, characterized in that After obtaining the reliability and validity verification results, the method further includes: When the reliability and validity verification result is verification passed, performing group verification on the two test groups based on the pre-delivery test data to obtain a group verification result; When the group verification result is verification failure, the multiple test users are regrouped to obtain two updated test groups.

8. The method according to claim 7, characterized in that The performing group verification on the two test groups based on the pre-delivery test data and obtaining group verification results includes: Based on the pre-launch test data, an independent sample check is performed on each test question in the test questionnaire to generate a third check value for each test question; wherein the third check value is used to indicate whether the distribution of the test users in the two test groups corresponding to the high immersion test and the low immersion test is balanced; Determining whether the third check value corresponding to each of the test questions is within a third preset check value range; If so, it is determined that the group verification result is passed.

9. A device for analyzing conditions affecting user emotions, characterized in that: include: A first processing module, used for grouping multiple test users to obtain two test groups; A second processing module is used to perform a high immersion test on one of the two test groups and a low immersion test on the other group according to multiple different types of audio-visual content to be tested, and obtain pre-delivery test data and post-delivery test data corresponding to each test group; wherein the pre-delivery test data corresponding to each test group refers to the score of the test users in the test group before experiencing the audio-visual content to be tested, and the post-delivery test data corresponding to each test group refers to the score of the test users in the test group after experiencing the audio-visual content to be tested, and the immersion degree of the users in the high immersion test is greater than the immersion degree of the users in the low immersion test; The third processing module is used to analyze the difference in the impact of the high immersion test and the low immersion test on the user's emotions based on the post-delivery test data corresponding to each test group, and obtain a first analysis result; The fourth processing module is used to analyze the difference in the impact of different types of audio-visual content to be tested on user emotional changes in high immersion tests and low immersion tests based on the pre-delivery test data and post-delivery test data corresponding to each test group, and obtain a second analysis result.

10. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

12. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 8 when being executed by a processor.

Images