Method and system for evaluating a metaverse virtual scene

Abstract

The application discloses a kind of meta-universe virtual scene evaluation method and system, include: obtaining standard data set;The standard key area set of standard meta-universe virtual scene object is obtained;Standard key area set, fixation point set, fixation time set, fixation frequency set, fixation transfer set and line of sight change data set are associated to analyze to construct data relationship and obtain the standard evaluation result of standard meta-universe virtual scene object corresponding to standard evaluation result establishment mapping relationship database;The class feature and key feature of the meta-universe virtual scene object to be evaluated are extracted and the mapping relationship database is filtered to obtain standard evaluation result, to the meta-universe virtual scene object to be evaluated to carry out evaluation to obtain predicted evaluation result.The meta-universe virtual scene evaluation method and system provided by the application, by obtaining the change trend of real-time fixation point when user watches meta-universe virtual scene, improve the authenticity of standard evaluation result, improve the accuracy of predicted evaluation result.

Description

Technical Field

[0001] This invention belongs to the field of virtual reality technology, specifically relating to a method and system for evaluating metaverse virtual scenes. Background Technology

[0002] In the first year of the metaverse, humanity fully entered the digital world, creating, living, entertaining, and even working. The construction of virtual scenes can be likened to "infrastructure construction" within the metaverse. As the next form of the internet, the metaverse can develop in two ways: firstly, from the real to the virtual, serving as a reproduction and enhanced rendering of the physical world; secondly, from the virtual to the real, achieving a new stage of digital-physical integration through the interaction between the metaverse and the real world. Both paths require the creation of virtual scenes parallel to the physical world, serving as the concrete space and content carrier of the metaverse.

[0003] Virtual scene construction builds the basic space and facilities of the metaverse, which is equivalent to "infrastructure construction" in the metaverse space. The companies involved in digital scene construction are equivalent to the "construction team" of the metaverse. Among them, computing power is the basic productivity, game engine is the toolbox to improve effects and efficiency, and digital creativity is the blueprint for construction, which constitutes the three core elements of digital scene construction.

[0004] Currently, various platforms developing metaverses offer a wide variety of virtual scenes, each presented in diverse ways. However, their appeal to users and the sense of immersion they provide vary significantly. Therefore, effectively evaluating virtual scenes has become a pressing technical challenge. Summary of the Invention

[0005] This invention provides a method and system for evaluating metaverse virtual scenes to solve the aforementioned technical problems, specifically adopting the following technical solution:

[0006] A method for evaluating a metaverse virtual scene includes the following steps:

[0007] Obtain a standard dataset, which contains standard metaverse virtual scene objects of different metaverse virtual scene categories;

[0008] Obtain the set of standard key regions of the standard metaverse virtual scene object;

[0009] The eye movement data set generated when the user cluster observes the standard meta-universe virtual scene object is processed to obtain a gaze point set, a gaze time set, a gaze frequency set, a gaze transfer set and a line of sight change data set, the standard key area set, the gaze point set, the gaze time set, the gaze frequency set, the gaze transfer set and the line of sight change data set are associated and analyzed to construct a data relationship, and the standard evaluation result corresponding to the standard meta-universe virtual scene object is obtained according to the data relationship, and a mapping relationship database is established, which contains each standard meta-universe virtual scene object and the corresponding standard evaluation result in a mapping relationship;

[0010] A to-be-evaluated meta-universe virtual scene object is obtained, the category features and key features of the to-be-evaluated meta-universe virtual scene object are extracted, and the mapping relationship database is filtered according to the category features and key features of the to-be-evaluated meta-universe virtual scene object, and the to-be-evaluated meta-universe virtual scene object is evaluated by using the standard evaluation results corresponding to all the standard meta-universe virtual scene objects after filtering to obtain a predicted evaluation result.

[0011] According to the evaluation result, the to-be-evaluated meta-universe virtual scene object is adjusted.

[0012] Further, the specific method for establishing the mapping relationship database is:

[0013] The eye movement data set generated when the user cluster observes the standard meta-universe virtual scene object is collected;

[0014] The eye movement analysis tool is used to process the eye movement data set to obtain a gaze point set, a gaze time set, a gaze frequency set, a gaze transfer set and a line of sight change data set corresponding to the standard meta-universe virtual scene object;

[0015] The standard key area set, the gaze point set, the gaze time set, the gaze frequency set, the gaze transfer set and the line of sight change data set corresponding to the standard meta-universe virtual scene object are input into a statistical analysis tool for analysis to obtain an overlapping area set between the standard key area set and the gaze point set, the overlapping area set contains an overlapping area sub-set corresponding to each user in the user cluster, and a line of sight change trend set is obtained according to the line of sight change data set, the line of sight change trend set contains a line of sight change trend corresponding to each user in the user cluster;

[0016] The standard evaluation result corresponding to the standard meta-universe virtual scene object is obtained according to the line of sight change trend set;

[0017] The mapping relationship database is established.

[0018] Further, the eye movement analysis tool is DataViewer analysis software.

[0019] Further, the statistical analysis tool is SPSS.

[0020] Further, the specific method for obtaining the predicted evaluation result is:

[0021] Obtaining the to-be-evaluated metaverse virtual scene object;

[0022] Extracting the category feature of the to-be-evaluated metaverse virtual scene object, performing category screening on the mapping relationship database according to the category feature, obtaining a first standard metaverse virtual scene object set corresponding to the category feature of the to-be-evaluated metaverse virtual scene object, and the first standard metaverse virtual scene object set contains all the standard metaverse virtual scene objects corresponding to the category feature.

[0023] Extracting the key feature of the to-be-evaluated metaverse virtual scene object, performing key feature screening on the first standard metaverse virtual scene object set according to the key feature, to obtain a second standard metaverse virtual scene object set in the first standard metaverse virtual scene object set that meets the key feature.

[0024] Extracting the evaluation key area of the to-be-evaluated metaverse virtual scene object, and evaluating the to-be-evaluated metaverse virtual scene object according to the standard evaluation result corresponding to each standard metaverse virtual scene object of the second standard metaverse virtual scene object set in combination with the evaluation key area to obtain the predicted evaluation result.

[0025] Further, after obtaining the standard data set, the metaverse virtual scene evaluation method further comprises:

[0026] Obtaining the artificial evaluation result of the user cluster on the standard metaverse virtual scene object;

[0027] When all the standard evaluation results corresponding to the screened standard metaverse virtual scene objects are used to evaluate the to-be-evaluated metaverse virtual scene object, the screened standard evaluation results are adjusted through the artificial evaluation result, and the to-be-evaluated metaverse virtual scene object is evaluated through the adjusted standard evaluation result.

[0028] Further, the eye movement data in the eye movement data set comprises: a fixation point, a total fixation number, a fixation transfer, a duration of each fixation on a fixation point, and a fixation sequence of fixation points.

[0029] Further, the standard metaverse virtual scene object and the to-be-evaluated metaverse virtual scene object each comprises any one of a static virtual scene picture and a virtual scene video.

[0030] Further, the standard key region set and the key features comprise at least one of a metaverse virtual scene subject, a key object and a text key region.

[0031] A metaverse virtual scene evaluation system comprises:

[0032] A standard dataset module is configured to acquire a standard dataset, wherein the standard dataset comprises standard metaverse virtual scene objects of different metaverse virtual scene categories;

[0033] A key region acquisition module is configured to acquire a standard key region set of the standard metaverse virtual scene objects;

[0034] A mapping database module is configured to process an eye movement data set generated when a user cluster observes the standard metaverse virtual scene objects to obtain a gaze point set, a gaze time set, a gaze frequency set, a gaze shift set and a line-of-sight change data set, perform correlation analysis on the standard key region set, the gaze point set, the gaze time set, the gaze frequency set, the gaze shift set and the line-of-sight change data set to construct a data relationship, acquire a standard evaluation result corresponding to the standard metaverse virtual scene objects according to the data relationship, and establish a mapping relationship database, wherein the mapping relationship database comprises each standard metaverse virtual scene object and the corresponding standard evaluation result in a mapping relationship;

[0035] A prediction evaluation module is configured to acquire a to-be-evaluated metaverse virtual scene object, extract a category feature and a key feature of the to-be-evaluated metaverse virtual scene object, and perform screening on the mapping relationship database according to the category feature and the key feature of the to-be-evaluated metaverse virtual scene object to obtain a standard evaluation result corresponding to all the standard metaverse virtual scene objects after screening, and perform evaluation on the to-be-evaluated metaverse virtual scene object by using the standard evaluation result to obtain a prediction evaluation result.

[0036] An adjustment module is configured to adjust the to-be-evaluated metaverse virtual scene object according to the evaluation result of the prediction evaluation module.

[0037] Further, the specific method for the mapping database module to establish the mapping relationship database is as follows:

[0038] The eye movement data set generated when the user cluster observes the standard metaverse virtual scene objects is collected;

[0039] processing the eye movement data set by using an eye movement analysis tool to obtain a gaze point set, a gaze time set, a gaze frequency set, a gaze shift set and a line of sight change data set corresponding to the standard meta-universe virtual scene object;

[0040] inputting the standard key area set, the gaze point set, the gaze time set, the gaze frequency set, the gaze shift set and the line of sight change data set corresponding to the standard meta-universe virtual scene object into a statistical analysis tool to analyze to obtain an overlapping area set between the standard key area set and the gaze point set, the overlapping area set containing an overlapping area sub-set corresponding to each user in the user cluster, and obtaining a line of sight change trend set from the line of sight change data set, the line of sight change trend set containing a line of sight change trend corresponding to each user in the user cluster;

[0041] obtaining a standard evaluation result corresponding to the standard meta-universe virtual scene object according to the line of sight change trend set;

[0042] establishing the mapping relationship database.

[0043] Further, the specific method for the prediction evaluation module to obtain the prediction evaluation result is:

[0044] obtaining the meta-universe virtual scene object to be evaluated;

[0045] extracting the category feature of the meta-universe virtual scene object to be evaluated, performing category screening on the mapping relationship database according to the category feature to obtain a first standard meta-universe virtual scene object set corresponding to the category feature of the meta-universe virtual scene object to be evaluated, the first standard meta-universe virtual scene object set containing all the standard meta-universe virtual scene objects corresponding to the category feature;

[0046] extracting the key feature of the meta-universe virtual scene object to be evaluated, performing key feature screening on the first standard meta-universe virtual scene object set according to the key feature to obtain a second standard meta-universe virtual scene object set in the first standard meta-universe virtual scene object set that meets the key feature;

[0047] extracting the evaluation key area of the meta-universe virtual scene object to be evaluated, evaluating the meta-universe virtual scene object to be evaluated according to the standard evaluation result corresponding to each standard meta-universe virtual scene object in the second standard meta-universe virtual scene object set in combination with the evaluation key area to obtain the prediction evaluation result.

[0048] Further, the meta-universe virtual scene evaluation system further comprises:

[0049] An artificial evaluation acquisition module is configured to acquire an artificial evaluation result of the user cluster on the standard meta-universe virtual scene object.

[0050] When the prediction evaluation module evaluates the to-be-evaluated meta-universe virtual scene object by using the standard evaluation results corresponding to all the screened standard meta-universe virtual scene objects, the standard evaluation results screened out are adjusted by the artificial evaluation result, and the to-be-evaluated meta-universe virtual scene object is evaluated by using the adjusted standard evaluation results.

[0051] The meta-universe virtual scene evaluation method and system have the advantages that the change trend of the real-time fixation point of the user when watching the meta-universe virtual scene is acquired, the authenticity of the standard evaluation result is improved, and the accuracy of the prediction evaluation result is improved. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0053] Figure 1 is a flowchart of a meta-universe virtual scene evaluation method of the present application. DETAILED DESCRIPTION

[0054] The embodiments of the present application will be described in detail below, and examples of the embodiments are shown in the drawings, wherein the same or similar reference signs represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0055] As Figure 1 is a flowchart of a meta-universe virtual scene evaluation method of the present application, which includes the following steps:

[0056] S1: Acquire a standard data set, and the standard data set contains standard meta-universe virtual scene objects of different meta-universe virtual scene categories.

[0057] S2: Acquire a standard key region set of the standard meta-universe virtual scene object.

[0058] S3: processing the eye movement data set generated when the user cluster observes the standard meta-universe virtual scene object to obtain a gaze point set, a gaze time set, a gaze frequency set, a gaze transfer set and a line of sight change data set, performing correlation analysis on the standard key region set, the gaze point set, the gaze time set, the gaze frequency set, the gaze transfer set and the line of sight change data set to construct a data relationship, obtaining a standard evaluation result corresponding to the standard meta-universe virtual scene object according to the data relationship, and establishing a mapping relationship database, the mapping relationship database comprising each standard meta-universe virtual scene object and the corresponding standard evaluation result in a mapping relationship.

[0059] S4: obtaining a to-be-evaluated meta-universe virtual scene object, extracting category features and key features of the to-be-evaluated meta-universe virtual scene object, and filtering the mapping relationship database according to the category features and the key features of the to-be-evaluated meta-universe virtual scene object, and using the standard evaluation results corresponding to all the filtered standard meta-universe virtual scene objects to evaluate the to-be-evaluated meta-universe virtual scene object to obtain a predicted evaluation result.

[0060] S5: adjusting the to-be-evaluated meta-universe virtual scene object according to the evaluation result.

[0061] It can be understood that the relevant elements in the to-be-evaluated meta-universe virtual scene can be deleted, modified and replaced according to the evaluation result.

[0062] In the embodiments of the present application, after adjusting the to-be-evaluated meta-universe virtual scene object according to the evaluation result, the adjusted to-be-evaluated meta-universe virtual scene is re-evaluated by the above method. The above process is repeated until the evaluation result reaches the expectation.

[0063] In the above embodiments, by analyzing the eye movement data of the user, the gaze point of the user when watching the meta-universe virtual scene can be objectively and real-timely monitored, and the change trend of the real-time gaze point of the user when watching the meta-universe virtual scene can be obtained, thereby improving the authenticity of the standard evaluation result and improving the accuracy of the predicted evaluation result.

[0064] In the above embodiments, the standard key region set of the standard meta-universe virtual scene object and the eye movement data set generated when the user cluster observes the standard meta-universe virtual scene object are associated and processed, the standard meta-universe virtual scene object is evaluated according to the data relationship obtained after the association and processing, and the standard evaluation result corresponding to the standard meta-universe virtual scene object is obtained, so as to realize the combination of the eye movement data set and the standard meta-universe virtual scene object to obtain the standard evaluation result corresponding to the meta-universe virtual scene object, and further realize the evaluation of the meta-universe virtual scene effect through the eye movement signal, avoiding the interference of subjective factors in the traditional way.

[0065] In the above embodiment, first, the standard evaluation result corresponding to each standard meta-universe virtual scene object is obtained through eye movement data acquisition, then the meta-universe virtual scene category of the to-be-evaluated meta-universe virtual scene object and the standard key area set are obtained, the corresponding standard meta-universe virtual scene object is obtained through category screening and key area screening according to the meta-universe virtual scene category of the to-be-evaluated meta-universe virtual scene object and the standard key area set, and the to-be-evaluated meta-universe virtual scene object is evaluated according to the standard evaluation result corresponding to the standard meta-universe virtual scene object, to obtain the predicted evaluation result, so that the eye movement data of the user cluster needs to be collected when the standard evaluation result is obtained, but the eye movement data of the user cluster when observing the to-be-evaluated meta-universe virtual scene object does not need to be collected again when the predicted evaluation result is obtained, reducing the labor cost and accelerating the acquisition speed of the evaluation result.

[0066] In the embodiment of the present application, the specific method for establishing the mapping relationship database is:

[0067] S31: Collect the eye movement data set generated when the user cluster observes the standard meta-universe virtual scene object.

[0068] Specifically, the eye movement data set generated when the user cluster observes the standard meta-universe virtual scene object is obtained by using an eye tracker. For example, the mandibular fixator of the eye tracker is adjusted, and the human eye camera of the eye tracker is adjusted so that the human eye camera can well capture the pupil of the user. The virtual reality technology is used to simulate a shopping mall environment and put different design methods of standard meta-universe virtual scene objects, and the eye tracker automatically collects the eye movement data of the user when observing the standard meta-universe virtual scene object.

[0069] S32: The eye movement analysis tool is used to process the eye movement data set to obtain the gaze point set, the gaze time set, the gaze frequency set, the gaze transfer set and the line of sight change data set corresponding to the standard meta-universe virtual scene object. Specifically, the eye movement analysis tool is a DataViewer analysis software.

[0070] It can be understood that the collected eye movement data set can be preprocessed by the eye movement analysis tool, and then the complete eye image and the hot spot map (the hot spot map is used to obtain the trend of the group attention distribution of the user cluster) are obtained. Through the hot spot map, the line of sight change trend of each user for the standard meta-universe virtual scene object can be obtained, and the line of sight change trend corresponding to each user is used to display the gaze condition of the overlapping area when a single user observes the standard meta-universe virtual scene object. As a preferred embodiment, the gaze condition in the first 20 seconds can be analyzed.

[0071] S33: input the standard key area set, the gaze point set, the gaze time set, the gaze frequency set, the gaze transfer set and the line-of-sight change data set corresponding to the standard metaverse virtual scene object into a statistical analysis tool for analysis to obtain an overlapping area set between the standard key area set and the gaze point set, the gaze time set, the gaze frequency set and the gaze transfer set, the overlapping area set including an overlapping area sub-set corresponding to each user in the user cluster, and obtain a line-of-sight change trend set from the line-of-sight change data set, the line-of-sight change trend set including a line-of-sight change trend corresponding to each user in the user cluster. Specifically, the line-of-sight change trend is used to represent the user's observation of the standard metaverse virtual scene object for the overlapping area sub-set.

[0072] In an embodiment of the present application, the statistical analysis tool is SPSS (Statistical Product and Service Solutions).

[0073] S34: obtain a standard evaluation result corresponding to the standard metaverse virtual scene object according to the line-of-sight change trend set.

[0074] S35: establish a mapping relationship database.

[0075] In an embodiment of the present application, the specific method for obtaining the predicted evaluation result is:

[0076] S41: obtain a metaverse virtual scene object to be evaluated.

[0077] S42: extract a category feature of the metaverse virtual scene object to be evaluated, perform category screening on the mapping relationship database according to the category feature, and obtain a first standard metaverse virtual scene object set corresponding to the category feature of the metaverse virtual scene object to be evaluated, the first standard metaverse virtual scene object set including all standard metaverse virtual scene objects corresponding to the category feature.

[0078] Specifically, the category screening on the metaverse virtual scene object to be evaluated can specifically include the following steps: performing category screening on the mapping relationship database according to the category feature to obtain each metaverse virtual scene category corresponding to the category feature in the mapping relationship database, scoring the metaverse virtual scene categories, then sorting the scores of each metaverse virtual scene category, and selecting the standard metaverse virtual scene objects corresponding to the second preset number of metaverse virtual scene categories with the highest scores, thereby reducing the data amount during evaluation, further accelerating the acquisition speed of the predicted evaluation result, and improving the user experience.

[0079] S43: Extract the key features of the to-be-evaluated metaverse virtual scene object, and perform key feature screening on the first set of standard metaverse virtual scene objects according to the key features to obtain a second set of standard metaverse virtual scene objects in the first set of standard metaverse virtual scene objects that meet the key features. The key features include keywords such as metaverse virtual scene theme and metaverse virtual scene purpose.

[0080] S44: Extract the evaluation key area of the to-be-evaluated metaverse virtual scene object, and evaluate the to-be-evaluated metaverse virtual scene object according to the standard evaluation result corresponding to each standard metaverse virtual scene object in the second set of standard metaverse virtual scene objects in combination with the evaluation key area to obtain a predicted evaluation result.

[0081] Specifically, the evaluation key area of the to-be-evaluated metaverse virtual scene object is compared with the standard key area in the screened standard metaverse virtual scene object, and the comparison result is calculated according to the standard evaluation result corresponding to the standard metaverse virtual scene object to obtain a predicted evaluation result.

[0082] In an embodiment of the present application, after obtaining the standard data set, the metaverse virtual scene evaluation method further comprises: obtaining a manual evaluation result of the user cluster on the standard metaverse virtual scene object. When all the standard evaluation results corresponding to the screened standard metaverse virtual scene objects are used to evaluate the to-be-evaluated metaverse virtual scene object, the screened standard evaluation results are adjusted by the manual evaluation result, and the to-be-evaluated metaverse virtual scene object is evaluated by the adjusted standard evaluation result. The manual evaluation result is obtained by questionnaire and interview investigation, and the manual evaluation result and the standard evaluation result are combined to adjust the standard evaluation result, thereby improving the accuracy of the standard evaluation result.

[0083] In an embodiment of the present application, the eye movement data in the eye movement data set comprises: a fixation point, a total fixation number, a duration of each fixation on a fixation point, and a fixation sequence of the fixation points.

[0084] In an embodiment of the present application, the standard metaverse virtual scene object and the to-be-evaluated metaverse virtual scene object each comprise: any one of a static virtual scene picture and a virtual scene video.

[0085] In an embodiment of the present application, the standard key area set and the key features comprise: at least one of a metaverse virtual scene subject, a key object, and a text key area.

[0086] The application also discloses a meta universe virtual scene evaluation system for implementing the meta universe virtual scene evaluation method.

[0087] Specifically, the standard data set module is configured to obtain a standard data set, and the standard data set comprises standard meta universe virtual scene objects of different meta universe virtual scene categories.

[0088] The key area acquisition module is configured to obtain a standard key area set of the standard meta universe virtual scene objects.

[0089] The mapping database module is configured to process a set of eye movement data generated when a user cluster observes the standard meta universe virtual scene objects to obtain a set of fixation points, a set of fixation times, a set of fixation times, a set of fixation transfers and a set of line-of-sight change data, and to perform correlation analysis on the standard key area set, the set of fixation points, the set of fixation times, the set of fixation times, the set of fixation transfers and the set of line-of-sight change data to construct a data relationship, obtain a standard evaluation result corresponding to the standard meta universe virtual scene objects according to the data relationship, and establish a mapping relationship database, wherein the mapping relationship database comprises each standard meta universe virtual scene object and the corresponding standard evaluation result in a mapping relationship.

[0090] The prediction evaluation module is configured to obtain a meta universe virtual scene object to be evaluated, extract category features and key features of the meta universe virtual scene object to be evaluated, and filter the mapping relationship database according to the category features and key features of the meta universe virtual scene object to be evaluated, and use the standard evaluation results corresponding to all the standard meta universe virtual scene objects after the filtering to evaluate the meta universe virtual scene object to be evaluated to obtain a prediction evaluation result.

[0091] The adjustment module is configured to adjust the meta universe virtual scene object to be evaluated according to the evaluation result of the prediction evaluation module. It can be understood that the adjustment module can delete, modify or replace relevant elements in the meta universe virtual scene to be evaluated according to the evaluation result. In the embodiment of the application, after adjusting the meta universe virtual scene object to be evaluated according to the evaluation result, the prediction evaluation module is used to re-evaluate the adjusted meta universe virtual scene to be evaluated. The above process is repeated until the evaluation result reaches the expectation.

[0092] In the embodiment of the application, the specific method for the mapping database module to establish the mapping relationship database is as follows:

[0093] The set of eye movement data generated when a user cluster observes the standard meta universe virtual scene objects is collected.

[0094] The eye movement data set is processed by using an eye movement analysis tool to obtain a gaze point set, a gaze time set, a gaze frequency set, a gaze transfer set and a line-of-sight change data set corresponding to the standard meta-universe virtual scene object.

[0095] The standard key region set, the gaze point set, the gaze time set, the gaze frequency set, the gaze transfer set and the line-of-sight change data set corresponding to the standard meta-universe virtual scene object are input into a statistical analysis tool for analysis to obtain an overlapping region set between the standard key region set and the gaze point set, the gaze time set, the gaze frequency set and the gaze transfer set, the overlapping region set including an overlapping region sub-set corresponding to each user in the user cluster, and a line-of-sight change trend set is obtained according to the line-of-sight change data set, the line-of-sight change trend set including a line-of-sight change trend corresponding to each user in the user cluster.

[0096] The standard evaluation result corresponding to the standard meta-universe virtual scene object is obtained according to the line-of-sight change trend set.

[0097] A mapping relationship database is established.

[0098] In an embodiment of the present application, the specific method for the prediction evaluation module to obtain the prediction evaluation result is:

[0099] A meta-universe virtual scene object to be evaluated is obtained.

[0100] The category feature of the meta-universe virtual scene object to be evaluated is extracted, the mapping relationship database is category-filtered according to the category feature, a first standard meta-universe virtual scene object set corresponding to the category feature of the meta-universe virtual scene object to be evaluated is obtained, and the first standard meta-universe virtual scene object set includes all standard meta-universe virtual scene objects corresponding to the category feature.

[0101] The key feature of the meta-universe virtual scene object to be evaluated is extracted, the first standard meta-universe virtual scene object set is key-feature-filtered according to the key feature, so as to obtain a second standard meta-universe virtual scene object set in the first standard meta-universe virtual scene object set that meets the key feature.

[0102] The evaluation key region of the meta-universe virtual scene object to be evaluated is extracted, and the meta-universe virtual scene object to be evaluated is evaluated according to the standard evaluation result corresponding to each standard meta-universe virtual scene object of the second standard meta-universe virtual scene object set in combination with the evaluation key region to obtain the prediction evaluation result.

[0103] In an embodiment of the present application, the meta-universe virtual scene evaluation system further includes an artificial evaluation obtaining module.

[0104] The artificial evaluation acquisition module is configured to acquire artificial evaluation results of the user cluster on the standard meta-universe virtual scene objects. When the prediction evaluation module evaluates the to-be-evaluated meta-universe virtual scene object by using the standard evaluation results corresponding to all the screened standard meta-universe virtual scene objects, the artificial evaluation results are used to adjust the screened standard evaluation results, and the to-be-evaluated meta-universe virtual scene object is evaluated by using the adjusted standard evaluation results.

[0105] The basic principles, main features and advantages of the present application are shown and described above. Those skilled in the art should understand that the above embodiments do not limit the present application in any form, and any technical solutions obtained by equivalent replacement or equivalent transformation fall within the protection scope of the present application.

Claims

1. A method for evaluating a meta-universe virtual scene, characterized in that, The method comprises the following steps: acquiring a standard dataset comprising standard metaverse virtual scene objects of different metaverse virtual scene categories; acquiring a standard key region set of the standard metaverse virtual scene objects; processing a set of eye movement data generated when a user cluster observes the standard metaverse virtual scene objects to obtain a set of fixation points, a set of fixation times, a set of fixation frequencies, a set of fixation transfers, and a set of line-of-sight change data, performing correlation analysis on the standard key region set, the set of fixation points, the set of fixation times, the set of fixation frequencies, the set of fixation transfers, and the set of line-of-sight change data to construct a data relationship, acquiring a standard evaluation result corresponding to the standard metaverse virtual scene objects according to the data relationship, and establishing a mapping relationship database comprising each standard metaverse virtual scene object and the corresponding standard evaluation result in a mapping relationship; acquiring a metaverse virtual scene object to be evaluated, extracting category features and key features of the metaverse virtual scene object to be evaluated, and screening the mapping relationship database according to the category features and the key features of the metaverse virtual scene object to be evaluated, and using the standard evaluation results corresponding to all the standard metaverse virtual scene objects after screening to evaluate the metaverse virtual scene object to be evaluated to obtain a predicted evaluation result; adjusting the metaverse virtual scene object to be evaluated according to the evaluation result.

2. The metaverse virtual scene evaluation method according to claim 1, wherein a specific method for establishing a mapping relationship database is: collecting the set of eye movement data generated when a user cluster observes the standard metaverse virtual scene objects; using an eye movement analysis tool to process the set of eye movement data to obtain a set of fixation points, a set of fixation times, a set of fixation frequencies, a set of fixation transfers, and a set of line-of-sight change data corresponding to the standard metaverse virtual scene objects; inputting the standard key region set, the set of fixation points, the set of fixation times, the set of fixation frequencies, the set of fixation transfers, and the set of line-of-sight change data corresponding to the standard metaverse virtual scene objects into a statistical analysis tool to analyze and obtain a set of overlapping regions between the standard key region set and the set of fixation points, the set of overlapping regions comprising a set of overlapping regions corresponding to each user in the user cluster, and acquiring a set of line-of-sight change trends from the set of line-of-sight change data, the set of line-of-sight change trends comprising a line-of-sight change trend corresponding to each user in the user cluster; acquiring a standard evaluation result corresponding to the standard metaverse virtual scene objects according to the set of line-of-sight change trends; establishing the mapping relationship database.

3. The metaverse virtual scene evaluation method according to claim 2, wherein the eye movement analysis tool is a DataViewer analysis software.

4. The metaverse virtual scene evaluation method according to claim 2, wherein the statistical analysis tool is SPSS. ​ ​ ​ 5. The method of claim 1, wherein the method further comprises: obtaining a prediction evaluation result of the to-be-evaluated metaverse virtual scene object, the method comprising: obtaining the to-be-evaluated metaverse virtual scene object; extracting a category feature of the to-be-evaluated metaverse virtual scene object, and performing category filtering on the mapping relationship database according to the category feature to obtain a first set of standard metaverse virtual scene objects corresponding to the category feature, the first set of standard metaverse virtual scene objects comprising all standard metaverse virtual scene objects corresponding to the category feature; extracting a key feature of the to-be-evaluated metaverse virtual scene object, and performing key feature filtering on the first set of standard metaverse virtual scene objects according to the key feature to obtain a second set of standard metaverse virtual scene objects in the first set of standard metaverse virtual scene objects that meet the key feature; extracting an evaluation key area of the to-be-evaluated metaverse virtual scene object, and evaluating the to-be-evaluated metaverse virtual scene object according to the standard evaluation result corresponding to each standard metaverse virtual scene object in the second set of standard metaverse virtual scene objects and the evaluation key area to obtain the prediction evaluation result.

6. The method of claim 1, wherein the method further comprises: obtaining a user cluster artificial evaluation result of the standard metaverse virtual scene object after obtaining the standard dataset.

7. The method of claim 1, wherein the eye movement data in the eye movement data set comprises: a fixation point, a total fixation number, a fixation transfer, a duration of each fixation on a fixation point, and a fixation sequence of fixation points.

8. The method of claim 1, wherein the standard metaverse virtual scene object and the to-be-evaluated metaverse virtual scene object each comprises: any one of a static virtual scene picture and a virtual scene video.

9. The method of claim 1, wherein the standard key area set and the key feature comprise: at least one of a metaverse virtual scene subject, a key object, and a text key area.

10. The method of claim 1, wherein the method further comprises: a standard dataset module configured to obtain a standard dataset, the standard dataset comprising standard metaverse virtual scene objects of different metaverse virtual scene categories; a key area obtaining module configured to obtain a standard key area set of the standard metaverse virtual scene object. ​ ​ 10. A metaverse virtual scene evaluation system, characterized in that, ​ ​ ​ The mapping database module is configured to process a set of eye movement data generated by a user cluster observing the standard metaverse virtual scene object to obtain a set of gaze points, a set of gaze times, a set of gaze frequencies, a set of gaze shifts, and a set of line-of-sight change data, perform correlation analysis on the set of standard key areas, the set of gaze points, the set of gaze times, the set of gaze frequencies, the set of gaze shifts, and the set of line-of-sight change data to construct a data relationship, obtain a standard evaluation result corresponding to the standard metaverse virtual scene object according to the data relationship, and establish a mapping relationship database, wherein the mapping relationship database includes each standard metaverse virtual scene object and a corresponding standard evaluation result in a mapping relationship; The prediction evaluation module is configured to obtain a to-be-evaluated metaverse virtual scene object, extract a category feature and a key feature of the to-be-evaluated metaverse virtual scene object, and perform screening on the mapping relationship database according to the category feature and the key feature of the to-be-evaluated metaverse virtual scene object, and perform evaluation on the to-be-evaluated metaverse virtual scene object by using the standard evaluation results corresponding to all the standard metaverse virtual scene objects after the screening to obtain a prediction evaluation result; The adjustment module is configured to adjust the to-be-evaluated metaverse virtual scene object according to the evaluation result of the prediction evaluation module.

Images