AI simulation method, device and equipment for transferring entity between meta universe and medium

Abstract

The invention provides an AI simulation method, device and equipment for transferring an entity between meta universe and a medium, and the method comprises the steps: S101, collecting original interaction data, and carrying out the analysis to obtain an original metadata template; s102, N reference entities are selected; s103, collecting reference interaction data of N reference entities, and analyzing to obtain a reference metadata template; s104, generating a mapping relation, and binding a mathematical relation; s105, constructing a target element cosmic sandbox and applying the mapping relation and the mathematical relation, simulating behaviors and interaction of the entity to be transferred in the target element cosmic sandbox in the target element cosmic sandbox, collecting simulation interaction data, and analyzing to obtain a simulation interaction result; and S106, if the balance of the target element universe is damaged, returning to execute the step S103, and replacing the reference entity and / or adjusting the mapping relation until the balance of the target element universe is not damaged. According to the method, the problem of transfer of entities among the meta universe can be effectively solved, and meanwhile, the balance of the target meta universe is kept.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an AI simulation method, device, equipment and medium for transferring entities between metaverses. Background Art

[0002] In virtual reality, augmented reality, and digital worlds, metaverses and closed-view games offer people a world of infinite possibilities. However, each metaverse or game has its own unique worldview and rules, making it a challenging task for entities, such as a user's avatar or artificial intelligence (AI) character, to move across the multiverse. Because each metaverse has its own unique rules and resource management methods, when an entity is transferred from one metaverse to another, it may cause balance issues. Some metaverse and game developers try to maintain balance by restricting the transfer of entities between different metaverses, but this approach limits the user's freedom and operational flexibility. In addition, even if the transfer of entities across metaverses is achieved, it often cannot solve the game balance problems caused by rule differences.

[0003] Therefore, it is necessary to propose an AI simulation method, device, equipment and medium for transferring entities between metaverses to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide an AI simulation method, device, equipment and medium for the transfer of entities between metaverses, so as to improve the balance problem that is easily caused by the transfer of existing entities between metaverses.

[0005] In a first aspect, the present invention provides an AI simulation method for entity transfer between metaverses, the method comprising:

[0006] S101: collecting original interaction data of the entity to be transferred in the original metaverse, analyzing the original interaction data, and obtaining the original metadata template and original result data, wherein the original metadata template includes the performance and result of the interaction of the entity to be transferred;

[0007] S102: Select N reference entities from the target metaverse, where N is a positive integer;

[0008] S103: Collect reference interaction data of N reference entities in the target metaverse, analyze the reference interaction data, and obtain reference metadata templates and reference result data, wherein the reference metadata templates include the performance and results of the reference entity interactions;

[0009] S104: using a heuristic algorithm or a deep learning technique to generate a mapping relationship between the original metadata template and the attribute set of the reference metadata template, and to bind a mathematical relationship between the metadata value of the original metadata template and the metadata value of the reference metadata template;

[0010] S105: construct a target metaverse sandbox, apply the mapping relationship and the mathematical relationship to the target metaverse sandbox, use an artificial intelligence algorithm to simulate the behavior and interaction of the entity to be transferred in the target metaverse in the target metaverse sandbox, collect simulated interaction data of the entity to be transferred in the target metaverse, and analyze the simulated interaction data to obtain a simulated interaction result, wherein the target metaverse sandbox contains the worldview, resources, and a number of simulated entities of the target metaverse;

[0011] S106: If the balance of the target metaverse is destroyed, return to the step of executing S103, wherein the reference entity is replaced and / or the mapping relationship is adjusted according to the simulation interaction result until the balance of the target metaverse is not destroyed.

[0012] The beneficial effects of the method provided by the present invention are: selecting a reference entity from the target metaverse, generating a mapping relationship between the original metadata template of the entity to be transferred and the reference metadata template attribute set of the reference entity, applying the mapping relationship to the target metaverse sandbox, using AI to drive the entity to be transferred to interact in the target metaverse, and collecting simulated interaction data and performing data analysis to verify the impact of the transfer of the entity to be transferred on the balance of the target metaverse, and optimizing the transfer process by adjusting the mapping relationship and the reference entity. This process is iterative and requires multiple simulations, verifications, and parameter adjustments to achieve better balance and interaction effects. Based on this AI simulation method, the problem of entity transfer between metaverses can be effectively solved, while maintaining the balance within each metaverse and the operational capabilities of the entity to be transferred in the target metaverse.

[0013] In a possible embodiment, collecting the original interaction data of the entity to be transferred in the original Metaverse includes: collecting the original interaction data of the entity to be transferred in the original Metaverse by calling an application program interface, a web crawler, or obtaining it from the original Metaverse database.

[0014] In a possible embodiment, selecting N reference entities from the target metaverse includes: selecting N reference entities from the target metaverse by user specification, classification algorithm, clustering algorithm or deep learning autoencoder.

[0015] In a possible embodiment, constructing a target metaverse sandbox includes: constructing the target metaverse sandbox using a target game engine or a virtual environment creation tool.

[0016] In the second aspect, the present invention also provides an AI simulation device for entity transfer between metaverses, which includes modules / units for executing any possible design method of the first aspect. These modules / units can be implemented by hardware, or by hardware executing corresponding software implementations.

[0017] In a third aspect, an embodiment of the present invention provides an electronic device, including a processor and a memory, wherein the memory is used to store one or more computer programs; when the one or more computer programs stored in the memory are executed by the processor, the electronic device can implement any possible design method of the first aspect.

[0018] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, the computer-readable storage medium comprising a computer program, and when the computer program runs on an electronic device, the electronic device executes any possible design method of the first aspect above.

[0019] In a fifth aspect, an embodiment of the present invention further provides a method comprising a computer program product, which, when running on an electronic device, enables the electronic device to execute any possible design of any of the above aspects.

[0020] For the beneficial effects of the second to fifth aspects mentioned above, reference can be made to the description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 Schematic diagram of the flow of the AI ​​simulation method for transferring entities between metaverses of the present invention.

[0022] Figure 2 A schematic diagram of the AI ​​simulation device for transferring entities between metaverses of the present invention.

[0023] Figure 3 It is a schematic diagram of the structure of the electronic device of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Unless otherwise defined, the technical terms or scientific terms used herein should be understood by people with general skills in the field to which the present invention belongs. "Including" and similar words used in this article mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects.

[0025] In recent years, multiverse and game developers have provided some cross-system data interoperability solutions, such as virtual asset transfer and character migration between metaverses. However, these solutions usually face challenges, such as significant differences in rules between metaverses, destruction of the internal balance of the metaverse, and interruption of user experience. Therefore, these solutions cannot effectively solve the transfer of entities between metaverses.

[0026] In view of the problems existing in the above-mentioned technologies, an embodiment of the present invention provides an AI simulation method for entity transfer between metaverses, see Figure 1 , the method comprising:

[0027] S101: Collecting original interaction data of the entity to be transferred in the original metaverse, analyzing the original interaction data, and obtaining an original metadata template and original result data, wherein the original metadata template includes the performance and result of the interaction of the entity to be transferred.

[0028] Specifically, the original interaction data includes the parameters, values ​​and interaction results involved in the interaction process between the entity to be transferred and the resources of the original metaverse and other entities.

[0029] S102: Select N reference entities from the target metaverse, where N is a positive integer.

[0030] S103: Collect reference interaction data of N reference entities in the target metaverse, analyze the reference interaction data, and obtain reference metadata templates and reference result data, wherein the reference metadata template includes the performance and results of the reference entity interaction.

[0031] Specifically, the reference interaction data includes parameters, values, and interaction results involved in the interaction process between the reference entity and the resources of the target metaverse and other entities.

[0032] S104: Using a heuristic algorithm or deep learning technology, a mapping relationship between the original metadata template and the attribute set of the reference metadata template is generated, and a mathematical relationship between the metadata value of the original metadata template and the metadata value of the reference metadata template is bound.

[0033] S105: Construct a target metaverse sandbox, apply mapping relationships and mathematical relationships to the target metaverse sandbox, use artificial intelligence algorithms to simulate the behaviors and interactions of the entities to be transferred in the target metaverse in the target metaverse sandbox, collect simulated interaction data of the entities to be transferred in the target metaverse, and analyze the simulated interaction data to obtain simulated interaction results, wherein the target metaverse sandbox contains the worldview, resources, and several simulated entities of the target metaverse.

[0034] S106: If the balance of the target metaverse is destroyed, return to the step of executing S103, wherein the reference entity is replaced and / or the mapping relationship is adjusted according to the simulation interaction result until the balance of the target metaverse is not destroyed.

[0035] Specifically, replacing the reference entity and / or adjusting the mapping relationship according to the simulation interaction result includes: performing at least one of replacing the reference entity, adjusting the mapping relationship and refining the granularity of the metadata attribute set according to the simulation interaction result.

[0036] In this embodiment, the interaction data of the entity to be transferred and the reference entity are collected and analyzed to generate a mapping relationship, which reflects the corresponding relationship between the original metaverse attributes and the target metaverse attributes. The target metaverse sandbox is used to simulate and evaluate the interaction behavior of the entity to be transferred in the target metaverse, and the relevant parameters are automatically adjusted according to the simulated interaction results. The interaction behavior is simulated again, and the performance of the entity to be transferred in the target metaverse is evaluated and feedback is verified to determine whether the entity to be transferred can maintain a balanced and effective interaction capability. The parameters are adjusted again according to the verification results to correct the performance of the entity to be transferred in the target metaverse, and an automatic feedback and adaptation system is implemented, which can provide continuous improvement and optimization to ensure the balance of the target metaverse and enable the entity to be transferred to be effectively transferred in different metaverses, and provide a good user experience.

[0037] In some preferred embodiments, the original interaction data of the entity to be transferred in the original Metaverse is collected, including: collecting the original interaction data of the entity to be transferred in the original Metaverse through application program interface calls, web crawlers, or obtaining from the original Metaverse database.

[0038] In some preferred embodiments, the raw interaction data is analyzed, including: using statistical and machine learning methods, such as linear regression, decision tree, random forest, support vector machine, etc. to analyze and process the raw interaction data.

[0039] In a preferred embodiment, N reference entities are selected from the target metaverse, including: selecting N reference entities from the target metaverse by user specification, classification algorithm, clustering algorithm or deep learning autoencoder. Specifically, the classification algorithm can be k-nearest neighbors (k-NN), which is a commonly used machine learning algorithm for classification and regression problems. The clustering algorithm can be k-means clustering, which is a commonly used clustering algorithm for dividing samples in a data set into multiple clusters. The algorithm determines the cluster assignment of samples by minimizing the distance between the sample point and the center of the cluster to which it belongs.

[0040] In some preferred embodiments, reference interaction data of N reference entities in the target metaverse are collected, including: collecting reference interaction data of N reference entities in the target metaverse through application program interface calls, web crawlers, or obtaining from the original metaverse database.

[0041] In some preferred embodiments, the reference interaction data is analyzed, including: using statistical and machine learning methods, such as linear regression, decision tree, random forest, support vector machine, etc. to analyze and process the reference interaction data.

[0042] In some specific embodiments, the heuristic algorithm includes genetic algorithm, simulated annealing, ant colony algorithm, etc., and the mapping relationship includes mathematical models such as linear mapping, nonlinear mapping, chaotic mapping, etc. In this embodiment,

[0043] In a possible embodiment, there are M entities to be transferred and M is a positive integer greater than 1; deep learning techniques such as neural network models are used to perform complex parameter space fitting on the M entities to be transferred to obtain a mapping relationship between the M entities to be transferred and the N reference entities.

[0044] In a specific embodiment, constructing a target metaverse sandbox includes: constructing the target metaverse sandbox using a target game engine or a virtual environment creation tool.

[0045] In a specific embodiment, the artificial intelligence algorithm may be reinforcement learning or a model-based decision-making method, wherein the model may be a knowledge graph model, a Transformer attention model and its variants commonly used in large language models (LLM), or Google's BERT. BERT (Bidirectional Encoder Representations from Transformers) is a bidirectional Transformer model. This type of model is used for worldview modal learning and supports multimodal expression of long contexts.

[0046] In some specific embodiments, the balance of the target metaverse is destroyed, including: the entity to be transferred is restricted in the target metaverse, the resources of the target metaverse are not replenished enough to be consumed, etc.

[0047] The AI ​​simulation method of entity transfer between metaverses of the present invention can be combined with cross-system entity recognition or cross-system data interoperability solutions, such as distributed identity and other technical solutions. Cross-system entity recognition can ensure the continuity and consistency of entities in different metaverses or games. For example, a virtual image created by a user in one metaverse can be accurately identified and transferred in other metaverses without re-creation or re-authentication. Through cross-system data interoperability, the relevant data of the entity, such as attributes, capabilities, resources, etc., can be transmitted and shared between different metaverses or games. In this way, when an entity is transferred from one metaverse to another, its relevant data can be effectively transferred and retained to support the entity's interactive capabilities in the target metaverse. In addition, it can also be combined with technical solutions such as automatic migration of multiverse appearance style expression. By learning the appearance features and style of the entity and applying it to the target metaverse, the appearance consistency and coherence of the entity in different metaverses can be achieved. This technical solution can help the entity maintain its personality and recognition in the target metaverse while meeting the visual style and requirements of the target metaverse. Integrating these technical solutions can help achieve seamless transfer and interaction between entities in different metaverses or games, and maintain the balance and experience quality of the target metaverse or game. This requires comprehensive consideration of entity identification, data transmission, appearance style transfer, skill learning and balance maintenance, etc., to provide a comprehensive and complete solution.

[0048] In particular, for games, this is manifested as learning multiple game-specific skills in different games, and maintaining the balance of the target game when using these skills in the target game. For entities in the game, combined with reinforcement learning technology, it is possible to learn and master multiple game-specific skills, and use these skills in the target game while maintaining the balance of the target game. This requires the design of corresponding training algorithms and evaluation mechanisms to ensure that the entities meet the balance requirements of the game when using skills in different games. For example, reinforcement learning algorithms can be used to train the decision-making strategies of entities in different games to adapt to the rules and balance of different games.

[0049] Taking a virtual reality game as an example, the following describes in detail the principles of the AI ​​simulation method for transferring entities between metaverses of the present invention.

[0050] Suppose there are two virtual reality games: Game A and Target Game B. Game A is a magic adventure game where players can play the role of a magician. Target Game B is a sci-fi shooting game where players can play the role of a robot. Now it is necessary to use the magic skills learned in Game A in Target Game B and maintain the balance of Target Game B. The specific entity transfer process is as follows:

[0051] 1. Collect magician character data: Collect the original interaction data of the magician character in Game A through Game A's API calls and other methods, including information such as different magic skills used by the magician, skill usage frequency, damage effects, etc. After analysis, the original metadata template and original result data are obtained.

[0052] 2. Select N reference entities: select N robot characters with similar behaviors and attributes to the magician character in game A from a group of robot characters in the target game B through classification algorithms and other methods.

[0053] 3. Collect reference entity data: Collect reference interaction data of N robot characters in target game B through API calls of target game B, including shooting skills, shooting frequency, damage effects and other information of robot characters. After analysis, obtain reference metadata template and reference result data.

[0054] 4. Define the mapping relationship: Use a heuristic algorithm to define the mapping relationship between the metadata template of the magician role and the attribute set of the metadata template of the robot role. For example, map the magician's attack power to the robot's shooting damage, map the magician's mana consumption to the robot's energy consumption, etc. At the same time, bind the mathematical relationship between the metadata value of the original metadata template and the metadata value of the reference metadata template. In the game, this metadata value can be understood as the attribute value of the game character.

[0055] 5. Construct a sandbox that simulates target game B: Use the engine or virtual environment creation tool of target game B to build a sandbox that simulates target game B. Apply mapping relationships and mathematical relationships in the sandbox to allow artificial intelligence (AI) algorithms to drive the magician character to interact and use skills in target game B.

[0056] 6. Observation and verification: Observe the interaction and skill usage of the magician character in the target game B in the sandbox. Collect the interaction data between the magician character and the target game B, and conduct feedback verification. Compare whether the balance in the target game B is destroyed and whether the magician character can effectively operate and use magic skills.

[0057] 7. Automatic correction and optimization: Based on the results of observation and verification, the mapping relationship and mathematical relationship are corrected by using the method of automatic parameter adjustment and iterative optimization. By replacing the reference entity, adjusting the mapping relationship and refining the granularity of the metadata attribute set, the balance transfer and skill use effect of the magician character in the target game B are optimized.

[0058] As a result, the magic skills learned in game A can be transferred to the robot character in the target game B, and the balance of the target game B can be ensured. This solution continuously optimizes the transfer and interaction effects of entities in different games through the iterative cycle of data collection, mapping relationship definition, sandbox simulation, and observation verification, achieving balanced transfer and effective use of skills.

[0059] In addition, the present invention also proposes an AI simulation device for transferring entities between metaverses, see Figure 2 The device includes: an original data processing unit 201, which is used to collect the original interaction data of the entity to be transferred in the original metaverse, analyze the original interaction data, and obtain the original metadata template and original result data, wherein the original metadata template includes the performance and result of the interaction of the entity to be transferred; a selection unit 202, which is used to select N reference entities from the target metaverse, wherein N is a positive integer; a reference data processing unit 203, which is used to collect the reference interaction data of the N reference entities in the target metaverse, analyze the reference interaction data, and obtain the reference metadata template and reference result data, wherein the reference metadata template includes the performance and result of the interaction of the reference entity; a mapping relationship generation unit 204, which is used to generate the original metadata using a heuristic algorithm or a deep learning technology The mapping relationship between the template and the reference metadata template attribute set; the simulation interaction unit 205 is used to construct the target metaverse sandbox, apply the mapping relationship to the target metaverse sandbox, use the artificial intelligence algorithm to simulate the behavior and interaction of the entity to be transferred in the target metaverse in the target metaverse sandbox, collect the simulated interaction data of the entity to be transferred in the target metaverse, and analyze the simulated interaction data to obtain the simulated interaction result, wherein the target metaverse sandbox contains the worldview, resources and several simulated entities of the target metaverse; the feedback correction unit 206 is used to return to the step of executing the reference data processing unit if the balance of the target metaverse is destroyed, wherein the reference entity is replaced and / or the mapping relationship is adjusted according to the simulated interaction result until the balance of the target metaverse is not destroyed. All relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0060] In some other embodiments of the present invention, an electronic device is disclosed. Figure 3, the electronic device may include: one or more processors 301; memory 302; display 303; one or more applications (not shown); and one or more computer programs 304, and the above components may be connected via one or more communication buses 305. The one or more computer programs 304 are stored in the above memory 302 and configured to be executed by the one or more processors 301, and the one or more computer programs 304 include instructions, which can be used to execute the following: Figure 1 and Figure 2 And each step in the corresponding embodiment.

[0061] Through the description of the above implementation methods, technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0062] Each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0063] If the integrated unit 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 embodiment of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: flash memory, mobile hard disk, read-only memory, random access memory, disk or optical disk, etc., various media that can store program codes.

[0064] Although the embodiments of the present invention are described in detail above, it is obvious to those skilled in the art that various modifications and variations can be made to these embodiments. However, it should be understood that such modifications and variations are within the scope and spirit of the present invention in the claims. Moreover, the present invention described herein may have other embodiments and may be implemented or realized in a variety of ways.

Claims

1. An AI simulation method for entity transfer between metaverses, characterized in that: The method comprises: S101: collecting original interaction data of the entity to be transferred in the original metaverse, analyzing the original interaction data, and obtaining the original metadata template and original result data, wherein the original metadata template includes the performance and result of the interaction of the entity to be transferred; S102: Select N reference entities from the target metaverse, where N is a positive integer; S103: Collect reference interaction data of N reference entities in the target metaverse, analyze the reference interaction data, and obtain reference metadata templates and reference result data, wherein the reference metadata templates include the performance and results of the reference entity interactions; S104: using a heuristic algorithm or a deep learning technique to generate a mapping relationship between the original metadata template and the attribute set of the reference metadata template, and to bind a mathematical relationship between the metadata value of the original metadata template and the metadata value of the reference metadata template; S105: construct a target metaverse sandbox, apply the mapping relationship and the mathematical relationship to the target metaverse sandbox, use an artificial intelligence algorithm to simulate the behavior and interaction of the entity to be transferred in the target metaverse in the target metaverse sandbox, collect simulated interaction data of the entity to be transferred in the target metaverse, and analyze the simulated interaction data to obtain a simulated interaction result, wherein the target metaverse sandbox contains the worldview, resources, and a number of simulated entities of the target metaverse; S106: If the balance of the target metaverse is destroyed, return to the step of executing S103, wherein the reference entity is replaced and / or the mapping relationship is adjusted according to the simulation interaction result until the balance of the target metaverse is not destroyed.

2. The method according to claim 1, characterized in that Collect the original interaction data of the entity to be transferred in the original Metaverse, including: The original interaction data of the entity to be transferred in the original Metaverse is collected by calling an application program interface, crawling a web crawler, or obtaining it from the original Metaverse database.

3. The method according to claim 1, characterized in that Select N reference entities from the target metaverse, including: N reference entities are selected from the target metaverse by user specification, classification algorithm, clustering algorithm or deep learning autoencoder.

4. The method according to claim 1, characterized in that: Construct the target metaverse sandbox, including: Construct the target metaverse sandbox using the target game engine or virtual environment creation tool.

5. An AI simulation device for entity transfer between metaverses, characterized in that: The device comprises: An original data processing unit, used to collect the original interaction data of the entity to be transferred in the original metaverse, analyze the original interaction data, and obtain the original metadata template and original result data, wherein the original metadata template includes the performance and result of the interaction of the entity to be transferred; A selection unit, used to select N reference entities from the target metaverse, where N is a positive integer; A reference data processing unit, configured to collect reference interaction data of N reference entities in the target metaverse, analyze the reference interaction data, and obtain a reference metadata template and reference result data, wherein the reference metadata template includes the performance and result of the reference entity interaction; A mapping relationship generating unit, configured to generate a mapping relationship between the original metadata template and the reference metadata template attribute set by using a heuristic algorithm or a deep learning technique; A simulation interaction unit, used to construct a target metaverse sandbox, apply the mapping relationship to the target metaverse sandbox, simulate the behavior and interaction of the entity to be transferred in the target metaverse in the target metaverse sandbox by using an artificial intelligence algorithm, collect simulated interaction data of the entity to be transferred in the target metaverse, and analyze the simulated interaction data to obtain a simulation interaction result, wherein the target metaverse sandbox contains the worldview, resources and a number of simulated entities of the target metaverse; A feedback correction unit is used to return to the steps of executing the reference data processing unit if the balance of the target metaverse is destroyed, wherein the reference entity is replaced and / or the mapping relationship is adjusted according to the simulation interaction result until the balance of the target metaverse is not destroyed.

6. The device according to claim 5, characterized in that The original data processing unit collects the original interaction data of the entity to be transferred in the original metaverse, and is specifically used to: The original interaction data of the entity to be transferred in the original Metaverse is collected by calling an application program interface, crawling a web crawler, or obtaining it from the original Metaverse database.

7. The device according to claim 5, characterized in that The selection unit selects N reference entities from the target metaverse, specifically for: N reference entities are selected from the target metaverse by user specification, classification algorithm, clustering algorithm or deep learning autoencoder.

8. The device according to claim 5, characterized in that The simulation interaction unit constructs a target metaverse sandbox, specifically for: Construct the target metaverse sandbox using the target game engine or virtual environment creation tool.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store a computer program; The processor is configured to execute the computer program stored in the memory so as to enable the electronic device to perform the method according to any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images