Virtual resource allocation method and device and electronic equipment

Abstract

The invention discloses a virtual resource allocation method and device and electronic equipment. The method comprises the following steps: receiving a virtual resource allocation request for a target object; in response to the virtual resource allocation request, dynamic interaction data, related to the credit rating, of the target object in the virtual space is determined, and the dynamic interaction data carries a target label; the dynamic interaction data carrying the target label is input into a behavior event analysis model, a first credit level corresponding to the credit level is obtained, a path selection layer of the behavior event analysis model comprises M model paths, and the M model paths correspond to different network architectures; and determining a virtual resource allocated to the target object according to the first credit level. According to the method and the device, the technical problem that the credit rating of the user is difficult to accurately determine because the mode of determining the credit rating of the user is limited in related technologies is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of metaverse, in particular to a virtual resource allocation method and device and electronic equipment. BACKGROUND

[0002] In the existing virtual environment and online platform, the traditional method of determining the credit level of a user faces obvious limitations. These methods often focus on the user's financial transaction records, repayment history or credit score in real life. The traditional credit evaluation system mostly uses fixed rules or single-dimensional data analysis. There is a technical problem that it is difficult to accurately determine the credit level of a user.

[0003] At present, there is no effective solution to the above problems. SUMMARY

[0004] The embodiments of the present application provide a virtual resource allocation method, device and electronic equipment to at least solve the problem in the related art that the way of determining the credit level of a user is limited and it is difficult to accurately determine the credit level of a user.

[0005] According to an aspect of the embodiments of the present application, a virtual resource allocation method is provided, comprising: receiving a virtual resource allocation request for a target object; in response to the virtual resource allocation request, determining dynamic interaction data of the target object related to a credit level in a virtual space, wherein the dynamic interaction data carries a target label, the target label is used to select a path from a path selection layer of a behavior event analysis model, and the target label at least includes a data format type label and a data application scenario label; inputting the dynamic interaction data carrying the target label into the behavior event analysis model to obtain a first credit level corresponding to the credit level, wherein the path selection layer of the behavior event analysis model includes M model paths, the M model paths correspond to different network architectures, and M is a positive integer greater than 1; and determining virtual resources allocated to the target object according to the first credit level.

[0006] Optionally, inputting the dynamic interaction data carrying the target label into the behavior event analysis model to obtain a first credit level corresponding to the credit level comprises: in the behavior event analysis model, performing predetermined processing on the dynamic interaction data according to the feature processing characteristics respectively corresponding to the M model paths to obtain N groups of input data respectively input into different model paths, wherein the N groups of input data all carry corresponding labels, and N is a positive integer greater than 1; inputting the input data carrying the corresponding labels into the corresponding model paths for data processing to obtain N groups of output data, and determining the first credit level corresponding to the credit level according to the N groups of output data.

[0007] Optionally, before the determining the virtual space corresponding to the credit level in response to the virtual resource allocation request, further comprising: in a case that the virtual space comprises a virtual space corresponding to an industry domain, obtaining an industry parameter corresponding to the industry domain, wherein the industry parameter at least comprises an industry architecture parameter, an industry behavior parameter, and an industry site parameter; constructing a virtual site space corresponding to the industry domain according to the industry site parameter; determining a virtual object creation option corresponding to the industry domain according to the industry architecture parameter; creating an interaction activity item in which virtual objects interact according to the industry behavior parameter, wherein the interaction activity item comprises a behavior activity item embodying the corresponding credit level; and constructing the virtual space corresponding to the industry domain according to the virtual site space, the interaction activity item, and the virtual object creation option.

[0008] Optionally, the constructing the virtual site space corresponding to the industry domain according to the industry site parameter comprises: determining site layout information corresponding to the industry domain according to the industry site parameter, wherein the site layout information comprises Q pieces of function area division information corresponding to Q pieces of function areas respectively, P pieces of virtual device contour information corresponding to P pieces of virtual devices respectively, Q is a positive integer greater than 1, and P is a positive integer greater than 1; constructing an initial site layout according to the function area division information; arranging the P pieces of virtual devices in the initial site layout according to the virtual device contour information to obtain a target site layout; and constructing the virtual site space according to the target site layout.

[0009] Optionally, the determining the virtual resource allocated to the target object according to the first credit level further comprises: determining static attribute data of the target object related to the credit level in the virtual space; determining a second credit level value according to a capability mapping relationship, wherein the capability mapping relationship represents a corresponding relationship between attribute data and credit levels; determining a target credit level corresponding to the target object according to the first credit level and the second credit level; and determining the virtual resource allocated to the target object according to the target credit level.

[0010] Optionally, the determining the target credit level corresponding to the target object according to the first credit level and the second credit level comprises: obtaining real world data of the target object related to the credit level; and determining the target credit level corresponding to the target object according to the real world data, the first credit level, and the second credit level.

[0011] Optionally, before the dynamic interaction data carrying the target label is input into the behavior event analysis model to obtain the first credit level corresponding to the credit level, the method further includes: obtaining sample data, wherein the sample data includes sample interaction data and an actual credit level corresponding to the sample interaction data, and the sample interaction data carries a sample label; inputting the sample data into M model paths of the behavior event analysis model respectively to obtain predicted credit levels corresponding to the M model paths respectively; determining an input path corresponding to the sample label from the M model paths according to differences between the M predicted credit levels and the actual credit level.

[0012] According to an aspect of an embodiment of the present application, a virtual resource allocation apparatus is provided, including: a receiving module configured to receive a virtual resource allocation request for a target object; a first determining module configured to determine, in response to the virtual resource allocation request, dynamic interaction data of the target object in a virtual space and related to a credit level, wherein the dynamic interaction data carries a target label, the target label is used to select a path from a path selection layer of a behavior event analysis model, and the target label at least includes a data format type label and a data application scenario label; a second determining module configured to input the dynamic interaction data carrying the target label into the behavior event analysis model to obtain a first credit level corresponding to the credit level, wherein the path selection layer of the behavior event analysis model includes M model paths, the M model paths correspond to different network architectures, and M is a positive integer greater than 1; and a third determining module configured to determine virtual resources allocated to the target object according to the first credit level.

[0013] According to an aspect of an embodiment of the present application, a computer readable storage medium is provided, including a stored executable program, wherein the computer readable storage medium controls a device where the computer readable storage medium is located to perform the method according to any one of the above aspects when the executable program is run.

[0014] According to an aspect of an embodiment of the present application, an electronic device is provided, including: a memory storing an executable program; and a processor configured to run the program, wherein the program performs the method according to any one of the above aspects when the program is run.

[0015] According to an aspect of an embodiment of the present application, a computer program product is provided, including computer instructions, wherein the computer instructions are executed by a processor to implement the steps of the method according to any one of the above aspects.

[0016] In the embodiment of the present application, a virtual resource allocation request for a target object is received; in response to the virtual resource allocation request, dynamic interaction data of the target object related to a credit level in a virtual space is determined, wherein the dynamic interaction data carries a target label, the target label is used to select a path from a path selection layer of a behavior event analysis model, and the target label at least includes: a data format type label and a data application scenario label; the dynamic interaction data carrying the target label is input into the behavior event analysis model to obtain a first credit level corresponding to the credit level; and the virtual resource allocated to the target object is determined according to the first credit level. The present application solves the limitations of the traditional credit evaluation method by introducing a multi-model path and dynamic interaction data analysis. The system collects dynamic interaction data of the user in the virtual space, and these data carry specific target labels, reflecting the behavior characteristics of the user. Then, the data is analyzed in multiple levels and multiple angles through the paths of the M different network architectures of the behavior event analysis model, and each path focuses on different aspects of the data, so that the credit level influencing factors are more comprehensively mined. It can be seen that the first credit level output by the model provides more accurate credit evaluation, breaks through the barrier that the traditional ability evaluation is often limited to a single dimension or the direct performance in the real world, overcomes the one-sidedness of the traditional evaluation method in understanding data, ensures the accuracy of the credit level determination, and further solves the technical problems in the related art that the way of determining the credit level of the user is limited and it is difficult to accurately determine the credit level of the user. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and serve to explain the present application. In the drawings:

[0018] Figure 1 is a flowchart of a virtual resource allocation method according to an embodiment of the present application;

[0019] Figure 2 is a structural block diagram of a virtual resource allocation device according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0021] It should be noted that the terms "first", "second", and the like in the description and claims of the application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0022] It should also be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, analyzed data, etc.) involved in the present application are information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data comply with relevant laws, regulations and standards, necessary security measures are taken, do not violate public order and good customs, and provide corresponding operation portal for user to choose authorization or refusal. For example, the system and related users or institutions are provided with an interface to provide the user with a corresponding operation portal for the user to choose to agree or refuse the automatic decision result; if the user chooses to refuse, the expert decision process is entered.

[0023] Embodiment 1

[0024] According to the embodiments of the present application, an embodiment of a virtual resource allocation method is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in a different order.

[0025] Figure 1 is a flowchart of a virtual resource allocation method according to an embodiment of the present application, as shown in Figure 1 the method comprises the following steps:

[0026] Step S102, receiving a virtual resource allocation request for a target object;

[0027] In the present application, the virtual resource allocation request for the target object is received in step S102.

[0028] Among them, the target object refers to the user in the virtual space.

[0029] Among them, the virtual resource allocation request is a request initiated by the target object or an entity representing the target object, aiming to obtain corresponding virtual resources according to the specific ability index of the target object. Virtual resources can be game currency, equipment, virtual items, or special permissions, etc.

[0030] This step indicates that the system will receive the request proposed by the user to obtain resources according to his performance in the virtual world (such as credit level).

[0031] In this way, users can clearly perceive that their virtual behavior and ability have actual value and can be converted into specific resources in the virtual world, enhancing the interactivity and attractiveness of the game or system, and enabling them to perform well in the virtual space.

[0032] Step S104, in response to the virtual resource allocation request, determining the dynamic interaction data related to the credit level of the target object in the virtual space, wherein the dynamic interaction data carries a target tag, the target tag is used to select a path from the path selection layer of the behavior event analysis model, and the target tag at least includes: data format type tag, data application scenario tag;

[0033] In step S104 provided in the present application, in response to the virtual resource allocation request, the dynamic interaction data related to the credit level of the target object in the virtual space is determined.

[0034] Among them, the virtual space is a computer-generated environment based on computer-generated environment, users can access and interact, communicate or perform tasks in this environment through electronic devices. Virtual space is commonly used in online games, virtual reality (VR), augmented reality (AR) applications, social media platforms, virtual education environments, etc. It provides an experience of simulating the real world or a completely fictional world, allowing users to participate in various activities with digital identities. Interact with other users or non-player characters (NPCs). The elements and rules in the virtual space can be adapted according to the designer's needs and creative ideas, from simple game maps to complex structures, to adapt to different credit level determination systems in different industries.

[0035] Among them, the credit level is in the evaluation of the credit of the individual or entity, in the virtual world, the credit level can be calculated according to the user's transaction integrity, task completion, interaction behavior, etc. Data in the game, used to reflect the user's credibility and reliability in the virtual environment. Credit level is a numerical representation of the credit quality of the user. In the virtual environment, it can help the system identify which users are more trustworthy when trading or cooperating, so as to make better decisions in resource allocation, permission granting, etc.

[0036] Among them, dynamic interaction data refers to the data generated by the target object in the virtual world in real time, including transaction records with NPCs, task completion efficiency, and behavior in virtual communities.

[0037] Among them, target labels are used to classify and label dynamic interaction data so that the behavior event analysis model can correctly process these data. Labels may include data format types, data application scenarios, etc.

[0038] Among them, data format type labels represent the format type of dynamic interaction data when saving and transmitting. For example, text data may be labeled as "TXT", image data as "JPEG", video data as "MP4", etc. These labels are crucial for correct parsing and processing of data, ensuring that data can be correctly used in appropriate application scenarios.

[0039] Among them, data application scenario labels refer to the specific scenarios in which data is used in virtual space. For example, data may be records in role-playing tasks, transaction market behavior, virtual social interaction, etc. These labels help the system understand the scenario behind the data, making more accurate analysis and evaluation.

[0040] Among them, the behavior event analysis model is a machine learning model used to analyze user dynamic interaction data and predict their ability index. The path selection layer of the model can automatically select the optimal analysis path according to the target label.

[0041] Among them, the path selection layer is part of the behavior event analysis model, which selects the most suitable analysis path in the model according to the specific labels of the input data. Each path may correspond to different model architectures and algorithms to adapt to various types of data and application scenarios.

[0042] In this step, by analyzing dynamic interaction data, the system can update and adjust the user's ability index in real time, providing more accurate credit rating evaluation. Target labels help the system understand the specific behavior of users in the virtual environment, such as transaction habits, task completion methods, etc., to achieve more detailed behavior insight and personalized evaluation.

[0043] Step S106, input the dynamic interaction data carrying the target label into the behavior event analysis model to obtain the first credit rating corresponding to the credit rating, wherein the path selection layer of the behavior event analysis model includes M model paths, and the M model paths correspond to different network architectures, and M is a positive integer greater than 1;

[0044] In step S106 provided by the present application, the dynamic interaction data carrying the target label is input into the behavior event analysis model to obtain a first credit level corresponding to the credit level.

[0045] Among them, M model paths are involved, which means that the analysis paths inside the behavior event analysis model are not fixed, but there are multiple possible network architectures, each architecture is for different types of data and application scenarios. That is, each path is specially designed to handle different types of data or for different data characteristics. For example, one path may focus on handling time series data (such as transaction record time series), while another path may be better at handling classification data (such as the interaction type of users with different NPCs).

[0046] Among them, the first credit level is the preliminary score of the user credit level obtained by analyzing the dynamic interaction data through the behavior event analysis model. It is based on the real-time behavior data of users in the virtual space and the direct result after model processing.

[0047] Through this step, the generalization ability of the model can be enhanced. Through the design of M model paths, the model can handle a wider range of data types and application scenarios, enhancing its generalization ability and enabling more accurate assessment of credit levels for different users in different virtual environments. The automatic path selection mechanism ensures that data is processed by the most effective model architecture, thereby improving the efficiency and accuracy of the assessment.

[0048] Step S108, according to the first credit level, determine the virtual resources allocated to the target object.

[0049] In step S108 provided by the present application, the first credit level is used to determine the virtual resources allocated to the target object.

[0050] Through this step, the system determines the type and amount of virtual resources allocated to the target object based on the first credit level obtained from the behavior event analysis model. This ensures that resource allocation is not only based on user requests, but also directly related to their credit performance in the virtual world, embodying a fair resource allocation mechanism based on ability. By closely linking resource allocation with credit levels, the system encourages users to exhibit good and responsible behavior in the virtual world, helping to build a positive and healthy virtual community. Ensuring that virtual resources are reasonably allocated to users with higher credit levels, avoiding resource waste, and improving the resource use efficiency of the entire virtual environment.

[0051] By the above steps S102-S108, the virtual resource allocation request for the target object is received; in response to the virtual resource allocation request, the dynamic interaction data of the target object in the virtual space related to the credit level is determined, wherein the dynamic interaction data carries a target label, the target label is used to select a path from a path selection layer of a behavior event analysis model, and the target label at least includes: a data format type label and a data application scenario label; the dynamic interaction data carrying the target label is input into the behavior event analysis model to obtain a first credit level corresponding to the credit level, wherein the path selection layer of the behavior event analysis model includes M model paths, the M model paths correspond to different network architectures, and M is a positive integer greater than 1. According to the first credit level, the virtual resource allocated to the target object is determined. The present application solves the limitation of the traditional credit evaluation method by introducing a multi-model path and dynamic interaction data analysis. The system collects the dynamic interaction data of the user in the virtual space, and these data carry specific target labels, reflecting the behavior characteristics of the user. Then, through the M different network architecture paths of the behavior event analysis model, the data is analyzed from multiple levels and multiple angles, and each path focuses on different aspects of the data, so that the credit level influencing factors are more comprehensively mined. It can be seen that the first credit level output by the model provides more accurate credit evaluation, breaks through the barrier that the traditional ability evaluation is often limited to a single dimension or the direct performance in the real world, overcomes the one-sidedness of the traditional evaluation method in understanding data, ensures the accuracy of the credit level determination, and further solves the technical problem that the way of determining the credit level of the user is limited in the related art, and it is difficult to accurately determine the credit level of the user.

[0052] As an optional embodiment, inputting the dynamic interaction data carrying the target label into the behavior event analysis model to obtain the first credit level corresponding to the credit level includes: in the behavior event analysis model, according to the feature processing characteristics corresponding to the M model paths respectively, performing predetermined processing on the dynamic interaction data to obtain N groups of input data respectively input into different model paths, wherein the N groups of input data all carry corresponding labels, and N is a positive integer greater than 1; inputting the input data carrying the corresponding labels into the corresponding model paths for data processing to obtain N groups of output data, and determining the first credit level corresponding to the credit level according to the N groups of output data.

[0053] In this embodiment, the way of determining the first credit level is explained.

[0054] Among them, the feature processing characteristics are involved, which means that different model paths can process different features in the data set according to their designed algorithms. For example, some paths may be sensitive to the edges and textures of image data, while other paths may be better able to understand the semantics of text data.

[0055] Where N sets of input data are involved, the pre-processed dynamic interaction data is divided into N sets, and each set of data will be processed by a specific model path. This division ensures that each aspect of the data is fully analyzed, improving the depth and accuracy of the evaluation.

[0056] Where input data carrying corresponding labels are involved, the pre-processed dynamic interaction data is divided into N sets, and each set of data is labeled with its type and application scenario, so that the model can identify and correctly process it.

[0057] Where N sets of output data are involved, each model path will independently generate a set of output data from the N sets of input data, reflecting the analysis results of the input data by the path.

[0058] Through this step, based on the diversity of dynamic interaction data, the system decomposes it into multiple parts, and each part is assigned to the path in the model that is most suitable for processing this type of data according to its characteristics. In this way, each type of data can be analyzed in the most effective way, resulting in a more comprehensive credit rating evaluation. Through the characteristic processing characteristics of M model paths, the system can more accurately analyze the data, improve the accuracy and comprehensiveness of credit rating evaluation, and avoid the bias that may be caused by a single processing method. By integrating N sets of output data to determine the first credit rating, the system can provide a more comprehensive and objective credit evaluation, which helps to reduce bias and error in the evaluation.

[0059] It should be noted that in actual application, M model paths may include deep neural networks, traditional machine learning algorithms (such as support vector machines, decision trees), statistical analysis methods, etc. Each path has different characteristics and advantages, and the system needs to select the most suitable path according to the specific content and format of the dynamic interaction data to achieve the best analysis effect. When determining the first credit rating, the system can also use weighted average, voting mechanism or more complex machine learning algorithms to integrate N sets of output data. In addition, the system can also combine the user's static data (such as registration information, historical credit records) to correct the first credit rating, to form a more comprehensive user credit profile.

[0060] As an optional embodiment, before determining the dynamic interaction data of the target object in the virtual space related to the credit level, it further includes: in the case that the virtual space includes a virtual space corresponding to an industry field, obtaining industry parameters corresponding to the industry field, wherein the industry parameters at least include: industry architecture parameters, industry behavior parameters, and industry site parameters; constructing a virtual site space corresponding to the industry field according to the industry site parameters; determining virtual object creation options corresponding to the industry field according to the industry architecture parameters; creating interaction activity items in which virtual objects interact in the industry field according to the industry behavior parameters, wherein the interaction activity items include behavior activity items reflecting the corresponding credit level; and constructing a virtual space corresponding to the industry field according to the virtual site space, the interaction activity items, and the virtual object creation options.

[0061] In this embodiment, a virtual space corresponding to an industry field is constructed to evaluate the credit level of a user in a virtual space corresponding to different industry fields.

[0062] Among them, the industry parameters refer to a set of parameters used to guide and regulate the design of virtual environment architecture, behavior and site when constructing a virtual space of a specific industry. These parameters capture important features of a specific industry in the real world, such as requirements of the financial industry, standards of the education field, etc.

[0063] Among them, the industry architecture parameters are used to define parameters of industry-related objects, roles and rules in the virtual space. For example, when constructing a virtual bank, the industry architecture parameters will guide how to set up virtual counters, virtual ATMs, virtual bank staff, etc., and the interaction rules between them.

[0064] Among them, the industry behavior parameters describe typical behaviors and activities that users and virtual objects may perform in a specific industry field. For example, in a virtual education space, industry behavior parameters may include credit counseling, repayment behavior, risk assessment interaction, and task completion transaction behavior patterns.

[0065] Among them, the industry site parameters are used to construct parameters of virtual sites specific to an industry, such as virtual loan departments, virtual trading markets, etc. These site parameters must ensure that the virtual site accurately reflects the industry characteristics and functional requirements.

[0066] Among them, the interaction activity items include behavior activities that can reflect the credit level of the user, such as timely payment of virtual loans, compliance with virtual contract terms, etc. Through these activities, data can be collected to evaluate and adjust the credit level of the user.

[0067] In this step, a set of specialized industry parameters is first obtained according to the industry field, which includes understanding the industry-specific architectural requirements, typical behaviors, and site design. These parameters will guide the subsequent virtual space construction, ensuring that the virtual environment can accurately simulate the industry environment in the real world, providing a realistic and professional experience. Industry parameters ensure the industry characteristics of virtual space construction, improve the realism of the virtual environment, and enable users to accurately simulate and learn in the virtual world. By providing industry-related virtual sites and interactive activities, users' experience in the virtual space is more rich and targeted, increasing participation and satisfaction. In addition, users participating in industry activities in the corresponding virtual space can cultivate and demonstrate their expertise and ability in a specific industry field, which is beneficial to personal career development and the dissemination of industry knowledge. Through industry behavior parameter guided interactive activities, the system can more accurately assess the user's credit level in the industry field, thereby reasonably allocating virtual resources or permissions and promoting the effective use of resources in the virtual space.

[0068] As an optional embodiment, according to the industry site parameter, a virtual site space corresponding to the industry field is constructed, including: determining site layout information corresponding to the industry field according to the industry site parameter, wherein the site layout information includes Q function area division information corresponding to Q function areas respectively, P virtual device contour information corresponding to P virtual devices respectively, Q is a positive integer greater than 1, and P is a positive integer greater than 1; constructing an initial site layout according to the function area division information; arranging P virtual devices in the initial site layout according to the virtual device contour information to obtain a target site layout; and constructing a virtual site space according to the target site layout.

[0069] In this embodiment, the specific way of constructing a virtual site space is described.

[0070] Among them, the site layout information is related to the planning and design of the virtual site, including the distribution of functional areas and the arrangement of virtual devices. Site layout information is the basis for constructing virtual space, ensuring that all industry characteristics and functions are realized.

[0071] Among them, Q function areas are involved, which refer to different areas in the virtual site divided by purpose, each area undertakes a specific function.

[0072] The functional area division information describes the size, shape, location, and connection mode of each functional area. For example, in the virtual bank scenario, by finely dividing the credit consultation area, simulated loan department, and other functional areas, the layout is ensured to be reasonable and effective in collecting user credit behavior data. Independent credit testing room and virtual trading market are used to monitor user risk preference and transaction integrity, providing multi-dimensional information support for credit evaluation.

[0073] The P virtual devices are tools or facilities simulated in the virtual place. In the virtual bank scenario, at least two virtual devices such as virtual credit evaluation machines and simulated trading terminals are set up. These devices can simulate the credit evaluation and transaction process in the real bank environment, thereby capturing the user's behavior characteristics in credit management in detail. With the help of virtual loan approval tables and interactive education exhibition tables, not only the functionality of the place is strengthened, but also the learning of user credit knowledge and dynamic evaluation of credit level are promoted.

[0074] The virtual device outline information includes the appearance design, size, and specific location of the virtual device in the place. The outline information ensures that the virtual device is integrated into the place layout, which is not only beautiful but also practical.

[0075] In this step, the process of how to determine the place layout information according to the industry place parameters is explained, that is, first determine the division of Q functional areas in the place, and then arrange the positions of P virtual devices according to the outline information of these devices, thereby constructing a virtual place space that meets the industry characteristics. The layout of functional areas and virtual devices is designed according to the experience and needs of real-world industry places, ensuring the functionality and authenticity of the virtual environment.

[0076] By reasonably arranging the functional areas and virtual devices, the virtual place space can highly imitate the real-world industry place, improving the user's sense of immersion and authenticity in the virtual environment. The place layout information ensures the logical connection between functional areas and devices, making it more efficient and convenient for users to perform industry-related tasks.

[0077] The virtual space can be expanded and the functional areas can be dynamically adjusted. When building the virtual space, the characteristics of the industry space changing over time can be considered. In the virtual bank scene, the functional areas such as the credit evaluation area and the loan service area can be dynamically adjusted according to the user active period. For example, virtual loan consultants can be increased during the peak period of fund demand at the beginning of the month to quickly respond to user demand. At the same time, the virtual education space layout can be adjusted at the beginning of the semester to provide more credit knowledge learning resources, and at the end of the semester, the credit test area is focused on to help users self-evaluate and improve the credit level, thereby realizing the flexible adaptation of the virtual bank space to the user demand and the activity period. Therefore, the functional area division information can be designed to be dynamically adjustable to adapt to the needs in different situations.

[0078] The interaction design of the virtual device can also be performed. The virtual device not only has an outline, but more importantly, the interaction logic is designed to enable the user to interact with it and complete industry-related tasks. In the virtual bank environment, the interaction design such as the virtual credit scoring machine needs to simulate the real credit query process to enable the user to input personal information and obtain a credit report in real time to experience the credit management process. The virtual loan simulator should be designed to have a complete interaction link of application, approval, and repayment. The virtual industry experience can be dynamically adjusted according to the industry demand and user behavior to provide richer, more real, and more efficient virtual industry experience.

[0079] As an optional embodiment, the virtual resource allocated to the target object according to the first credit level further includes: determining static attribute data of the target object in the virtual space related to the credit level; determining a second credit level value according to the static attribute data and the capability mapping relationship, wherein the capability mapping relationship represents the corresponding relationship between the attribute data and the credit level; determining a target credit level corresponding to the target object according to the first credit level and the second credit level; and determining the virtual resource allocated to the target object according to the target credit level.

[0080] In this embodiment, the virtual resource allocated to the target object is determined.

[0081] The static attribute data is involved, which is relatively stable information of the target object in the virtual space and will not change rapidly due to short-term behavior. It can include personal information of the user (such as age, gender), account status (such as registration duration), historical credit records (such as credit evaluation of past transactions), and the like. The static attribute data provides a basis for long-term credit evaluation. The static attribute data reflects the background information of the target object before entering the virtual space or some basic information that exists continuously in the space. It helps to establish a long-term stable credit evaluation system.

[0082] Among them, the ability mapping relationship is involved, which is a conversion rule or model that converts user static attribute data into credit levels in a virtual space. It is based on industry experience, data analysis and expert opinions, and defines the association between different attribute data and credit levels.

[0083] Among them, the second credit level value is involved, which is a credit level value converted from static attribute data through the ability mapping relationship.

[0084] Through this step, the second credit level value is determined through static attribute data, which makes up for the short-term fluctuations that may be caused by relying only on dynamic behavior data, ensuring the long-term stability and fairness of credit assessment.

[0085] The final credit level is obtained after integrating the first credit level and the second credit level. It is a more comprehensive and reliable credit level that reflects the overall credit status of the user in the virtual space. That is, the target credit level considers both the user's immediate behavior and long-term performance, and through comprehensive consideration, it helps to build a more comprehensive and accurate credit assessment system in the virtual space.

[0086] As an optional embodiment, determining the target credit level corresponding to the target object according to the first credit level and the second credit level comprises: obtaining real world data related to the credit level of the target object; determining the target credit level corresponding to the target object according to the real world data, the first credit level and the second credit level.

[0087] In this embodiment, how to determine the target credit level of the target object is explained.

[0088] Among them, the real world data is involved, which refers to the data collected from the user's real life and network behavior outside the virtual environment. Such data may include but not limited to user's educational background, work experience, social media activity, online payment history, credit report, etc. These data provide direct evidence of the user's credit status in real life. When assessing the credit level of the user in the virtual space, the system will actively collect or request access to real world data to enhance the accuracy and depth of virtual credit assessment. The collection of real world data is usually carried out on the premise of user authorization, ensuring data security and protection of personal privacy.

[0089] In this way, the comprehensiveness of credit evaluation is improved, and the addition of real-world data enables credit evaluation to reflect users' broader life habits and credit history, helping to build a more comprehensive credit profile. Moreover, since real-world data is objective and directly reflects users' credit status, incorporating it into the credit evaluation system can improve the credibility and fairness of the evaluation results. By integrating real-world data with virtual space credit evaluation, the system can assess users' credit status from multiple dimensions, avoiding evaluation bias caused by a single data source and improving evaluation accuracy.

[0090] As an optional embodiment, before the dynamic interaction data carrying the target label is input into the behavior event analysis model to obtain the first credit level corresponding to the credit level, the method further includes: obtaining sample data, wherein the sample data includes sample interaction data and an actual credit level corresponding to the sample interaction data, and the sample interaction data carries a sample label; inputting the sample data into M model paths corresponding to the behavior event analysis model respectively to obtain predicted credit levels corresponding to the M model paths respectively; determining an input path corresponding to the sample label from the M model paths according to differences between the M predicted credit levels and the actual credit level respectively.

[0091] In this embodiment, the training process of the behavior event analysis model is described.

[0092] Among them, the sample data is used for the data set of training the behavior event analysis model, and contains the interaction behavior records of users with known credit levels in the virtual space. Sample data is the basis for training machine learning models. Through learning these data, the model can identify the relationship between credit level and behavior pattern.

[0093] Among them, the sample interaction data refers to the specific behavior records of users in the virtual space, such as interaction with NPCs, task completion, transaction records, etc. These data carry sample labels to guide model learning.

[0094] Among them, the actual credit level refers to the real credit level matched with the sample interaction data, which is used as a reference standard for model training.

[0095] Among them, the predicted credit level refers to the credit level value predicted by the model after analyzing the sample data in the training process, which is used to compare with the actual credit level to evaluate the prediction ability of the model.

[0096] Among them, the sample label is used to identify the sample data characteristic label, which can be a user category, a behavior type, a credit level classification, etc., to help the model identify and process data.

[0097] Among them, the input path is determined as the model path most suitable for processing sample label corresponding data, which will be used for subsequent credit evaluation process.

[0098] In this step, before credit level prediction, the system first needs to collect sample data sets, which contain user interaction behavior in virtual space and the actual credit level corresponding to these behaviors. The collection of sample data is to train the behavior event analysis model, so that the model can learn the association between behavior patterns and credit levels, so as to accurately evaluate the credit level of the user in subsequent prediction. High-quality sample data sets can improve the accuracy and effectiveness of model training, so that the model has higher credibility when predicting credit levels. Sample labels help the model identify key behavior features and adjust the weight of these features in credit evaluation, improving the intelligent analysis capability of the model. The system sends the sample data into M processing paths of the behavior event analysis model respectively, and each path processes the data according to its specific analysis algorithm and parameters and generates a predicted credit level. In order to evaluate the prediction accuracy of different paths when processing the same data set, the optimal path is selected for subsequent credit evaluation.

[0099] Extensible, as the accumulation of user behavior data in virtual space and the deepening of model training, the system can periodically reevaluate the prediction ability of M model paths, dynamically adjust the selection of the optimal input path, to adapt to the changing behavior patterns and credit evaluation needs. In addition, M model paths can process different data sets at the same time, realizing parallel computing, further improving the efficiency of credit evaluation and the processing capacity of the system.

[0100] Based on the above embodiment and optional embodiment, an optional implementation is provided, which is described in detail as follows.

[0101] In the optional embodiment of the present application, a virtual resource allocation method is provided, which is introduced as follows.

[0102] S1, receiving a virtual credit rating request;

[0103] S2, in response to the virtual credit rating request, obtaining the virtual social relationship of the user in the metaverse and the virtual behavior, wherein the virtual behavior is a behavior representing credit, and different virtual behaviors represent different credit indexes;

[0104] For virtual behavior:

[0105] For example, when interacting with an NPC in a virtual world, check the task situation related to the NPC's credit. If the task situation is good, it indicates that the user has good credit in terms of social interaction. If the task situation is not good, it can be determined whether the user simply does not like that type of task or other situations, and if so, it can be indicated that the user has poor credit or that the user has poor credit in that type.

[0106] For virtual social relationships:

[0107] Different users have different credit levels, and different users have different credit levels in different aspects. Since users interact together or play together, they can affect each other, so this parameter data can be considered.

[0108] S3, based on the user's virtual social relationship and virtual behavior, determine the user's credit score for different types of events;

[0109] It should be noted that when determining the credit score, the behavior event analysis model can be used to determine the score to achieve more accurate score determination.

[0110] S4, if the credit score for a certain type of event is higher than a predetermined threshold, then recommend that type of business to the user.

[0111] S5, based on the user's credit score for different types of events, exchange virtual points in the virtual world corresponding to different types of events to exchange different items.

[0112] It should be noted that for virtual resources, the user's interest in what items can be determined first. When the user's credit score in a certain type is low, the corresponding exchange item of that type can be inferred, which meets the user's preferences, to help the user improve the credit of that type and also get the desired items.

[0113] When determining what items the user is interested in, the user's various data can be observed, such as the data of the items placed in the user's virtual space. Different virtual furniture, virtual decorative lights, and other components are configured with parameter values for each parameter component, and in addition to type, color, style, and other factors can also be considered to greatly mobilize customer interest.

[0114] In addition, a simulated trading game can be set up in the virtual space to see if the user will engage in illegal operations in the simulated trading game, will put others at risk while keeping himself safe, and so on, to assist in determining the credit rating.

[0115] When the above settings are made, the index classification, basic index definition, and derivative index formula can be determined to ensure that there is a clear basis for determining the credit score.

[0116] The extensible virtual space includes different virtual spaces according to different professional fields in real life, and further determines credit levels in different virtual spaces and a virtual credit distribution mechanism.

[0117] Through the above optional implementation, at least the following beneficial effects can be achieved: the scheme provided in the application uses credit scores as a channel for virtual resource exchange, which improves the credit awareness of users and is conducive to building a harmonious and honest environment. Using data in the virtual world to assist in determining the credit level of users and configuring corresponding resources for them. The user increases the virtual life experience. And the credit level is determined by combining static attribute data and dynamic interaction data, so that the determination of the credit level is more accurate.

[0118] It should be noted that, for the above-mentioned method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0119] Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above-mentioned embodiments can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of software products, and the computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a plurality of instructions to make a terminal device (which can be a mobile phone, computer, server, or network device, etc.) execute the method of each embodiment of the present application.

[0120] Embodiment 2

[0121] According to the embodiments of the present application, a device for implementing the above virtual resource allocation method is also provided, Figure 2 is a structural block diagram of the virtual resource allocation device according to the embodiments of the present application, as Figure 2 shown, the device includes a receiving module 202, a first determining module 204, a second determining module 206 and a third determining module 208, which will be described in detail below.

[0122] The receiving module 202 is configured to receive a virtual resource allocation request for a target object; the first determining module 204 is connected to the receiving module 202 and is configured to determine, in response to the virtual resource allocation request, dynamic interaction data of the target object in a virtual space in relation to a credit level, wherein the dynamic interaction data carries a target label used to select a path from a path selection layer of a behavior event analysis model, and the target label at least includes a data format type label and a data application scenario label; the second determining module 206 is connected to the first determining module 204 and is configured to input the dynamic interaction data carrying the target label into the behavior event analysis model to obtain a first credit level corresponding to the credit level, wherein the path selection layer of the behavior event analysis model includes M model paths, the M model paths correspond to different network architectures, and M is a positive integer greater than 1; and the third determining module 208 is connected to the second determining module 206 and is configured to determine virtual resources allocated to the target object according to the first credit level.

[0123] Optionally, the second determining module 206 is further configured to perform predetermined processing on the dynamic interaction data in the behavior event analysis model according to feature processing characteristics respectively corresponding to the M model paths, to obtain N groups of input data respectively input into different model paths, wherein the N groups of input data all carry corresponding labels, N is a positive integer greater than 1; input the input data carrying the corresponding labels into the corresponding model paths for data processing to obtain N groups of output data, and determine the first credit level corresponding to the credit level according to the N groups of output data.

[0124] Optionally, the first determining module 204 is further configured to, in a case where the virtual space includes a virtual space corresponding to an industry field, acquire industry parameters corresponding to the industry field, wherein the industry parameters at least include industry architecture parameters, industry behavior parameters, and industry site parameters; construct a virtual site space corresponding to the industry field according to the industry site parameters; determine virtual object creation options corresponding to the industry field according to the industry architecture parameters; create interaction activity items in which virtual objects in the industry field interact according to the industry behavior parameters, wherein the interaction activity items include behavior activity items reflecting the corresponding credit level; and construct the virtual space corresponding to the industry field according to the virtual site space, the interaction activity items, and the virtual object creation options.

[0125] Optionally, the first determining module 204 is further configured to determine, according to the industry site parameter, site layout information corresponding to the industry field, wherein the site layout information comprises function area division information corresponding to Q function areas respectively, virtual device contour information corresponding to P virtual devices respectively, Q is a positive integer greater than 1, and P is a positive integer greater than 1; construct an initial site layout according to the function area division information; arrange the P virtual devices in the initial site layout according to the virtual device contour information to obtain a target site layout; and construct a virtual site space according to the target site layout.

[0126] Optionally, the third determining module 208 is further configured to determine static attribute data of the target object related to the credit level in the virtual space; determine a second credit level value according to the static attribute data and a capability mapping relationship, wherein the capability mapping relationship represents a corresponding relationship between the attribute data and the credit level; determine a target credit level corresponding to the target object according to the first credit level and the second credit level; and determine virtual resources allocated to the target object according to the target credit level.

[0127] Optionally, the third determining module 208 is further configured to obtain real world data related to the credit level of the target object; and determine a target credit level corresponding to the target object according to the real world data, the first credit level and the second credit level.

[0128] Optionally, the second determining module 206 is further configured to obtain sample data, wherein the sample data comprises sample interaction data and an actual credit level corresponding to the sample interaction data, and the sample interaction data carries a sample label; input the sample data into M model paths corresponding to the behavior event analysis model respectively to obtain predicted credit levels corresponding to the M model paths respectively; determine an input path corresponding to the sample label from the M model paths according to differences between the M predicted credit levels and the actual credit level respectively.

[0129] It should be noted that the above receiving module 202, the first determining module 204, the second determining module 206 and the third determining module 208 correspond to steps S102 to S108 in the implementation of the virtual resource allocation method, and the multiple modules have the same instances and application scenarios as the corresponding steps, but are not limited to the content disclosed in the above embodiment 1.

[0130] Embodiment 3

[0131] According to another aspect of the embodiments of the present application, an electronic device is provided, comprising: a memory storing an executable program; and a processor configured to run the program, wherein the program, when running, performs the method of any one of the above.

[0132] Embodiment 4

[0133] According to another aspect of the embodiments of the present application, a computer readable storage medium is provided, including a stored executable program, wherein the executable program, when executed, controls the device where the computer readable storage medium is located to perform the method of any of the above.

[0134] Embodiment 5

[0135] According to another aspect of the embodiments of the present application, a computer program product is provided, including computer instructions, which, when executed by a processor, implement the steps of the method of any of the above.

[0136] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0137] In the above-mentioned embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0138] In several embodiments provided in the present application, it should be understood that the disclosed technical contents can be implemented by other ways. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units can be a logical function division, and actual implementation can have another division way, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or modules shown or discussed can be indirect coupling or communication connection through some interfaces, units or modules, which can be electrical or other forms.

[0139] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed to multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment scheme.

[0140] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0141] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0142] The above is only the preferred embodiment of the present application, and it should be pointed out that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A method of virtual resource allocation, characterized by, Comprising: receiving a virtual resource allocation request for a target object; in response to the virtual resource allocation request, determining dynamic interaction data of the target object in a virtual space related to a credit level, wherein the dynamic interaction data carries a target label used to select a path from a path selection layer of a behavior event analysis model, and the target label at least includes: a data format type label, a data application scenario label; inputting the dynamic interaction data carrying the target label into the behavior event analysis model to obtain a first credit level corresponding to the credit level, wherein the path selection layer of the behavior event analysis model includes M model paths, and the M model paths correspond to different network architectures, and M is a positive integer greater than 1; determining a virtual resource allocated to the target object according to the first credit level.

2. The method of claim 1, wherein, inputting the dynamic interaction data carrying the target label into the behavior event analysis model to obtain a first credit level corresponding to the credit level, comprising: in the behavior event analysis model, performing predetermined processing on the dynamic interaction data according to the feature processing characteristics respectively corresponding to the M model paths to obtain N groups of input data respectively input into different model paths, wherein the N groups of input data all carry corresponding labels, and N is a positive integer greater than 1; inputting the input data carrying the corresponding labels into the corresponding model paths for data processing to obtain N groups of output data; determining the first credit level corresponding to the credit level according to the N groups of output data.

3. The method of claim 1, wherein, Before determining the dynamic interaction data of the target object in the virtual space related to the credit level in response to the virtual resource allocation request, further comprising: in the case that the virtual space includes a virtual space corresponding to an industry field, obtaining an industry parameter corresponding to the industry field, wherein the industry parameter at least includes: an industry architecture parameter, an industry behavior parameter, and an industry site parameter; constructing a virtual site space corresponding to the industry field according to the industry site parameter; determining a virtual object creation option corresponding to the industry field according to the industry architecture parameter; creating an interaction activity item in which a virtual object in the industry field interacts according to the industry behavior parameter, wherein the interaction activity item includes a behavior activity item embodying a corresponding credit level; constructing a virtual space corresponding to the industry field according to the virtual site space, the interaction activity item, and the virtual object creation option.

4. The method of claim 3, wherein, constructing a virtual site space corresponding to the industry field according to the industry site parameter, comprising: determining site layout information corresponding to the industry field according to the industry site parameter, wherein the site layout information includes Q function area division information respectively corresponding to Q function areas, and P virtual device contour information respectively corresponding to P virtual devices, Q is a positive integer greater than 1, and P is a positive integer greater than 1; constructing an initial site layout according to the function area division information; arranging the P virtual devices in the initial site layout according to the virtual device profile information, to obtain a target site layout; constructing the virtual site space according to the target site layout.

5. The method of claim 1, wherein, The determining the virtual resource allocated to the target object according to the first credit level further includes: determining static attribute data of the target object related to the credit level in the virtual space; determining a second credit level value according to the static attribute data and a capability mapping relationship, wherein the capability mapping relationship represents a corresponding relationship between attribute data and credit levels; determining a target credit level corresponding to the target object according to the first credit level and the second credit level; determining the virtual resource allocated to the target object according to the target credit level.

6. The method of claim 5, wherein, The determining the target credit level corresponding to the target object according to the first credit level and the second credit level includes: obtaining real world data related to the target object and the credit level; determining the target credit level corresponding to the target object according to the real world data, the first credit level and the second credit level.

7. The method according to any one of claims 1 to 6, characterized in that, Before the inputting the dynamic interaction data carrying the target label into the behavior event analysis model to obtain the first credit level corresponding to the credit level, further includes: obtaining sample data, wherein the sample data includes sample interaction data and an actual credit level corresponding to the sample interaction data, and the sample interaction data carries a sample label; inputting the sample data into M model paths of the behavior event analysis model respectively to obtain predicted credit levels corresponding to the M model paths respectively; determining an input path corresponding to the sample label from the M model paths according to M difference values between the M predicted credit levels and the actual credit level. includes:

8. A virtual resource allocation apparatus, characterized by comprising: a receiving module configured to receive a virtual resource allocation request for a target object; a first determining module configured to determine, in response to the virtual resource allocation request, dynamic interaction data of the target object related to a credit level in a virtual space, wherein the dynamic interaction data carries a target label, the target label is used to select a path from a path selection layer of a behavior event analysis model, and the target label at least includes a data format type label and a data application scenario label; a second determining module configured to input the dynamic interaction data carrying the target label into the behavior event analysis model to obtain a first credit level corresponding to the credit level, wherein the path selection layer of the behavior event analysis model includes M model paths, the M model paths correspond to different network architectures, and M is a positive integer greater than 1; a third determining module configured to determine a virtual resource allocated to the target object according to the first credit level. The computer readable storage medium includes a stored executable program, wherein the executable program controls the device where the computer readable storage medium is located to execute the method of any one of claims 1-7 when the executable program is running.

9. A computer-readable storage medium, characterized in that, includes:

10. An electronic device, comprising: ​ a memory storing an executable program; a processor configured to execute the program, wherein the program, when executed, performs the method of any one of claims 1 to 7.

11. A computer program product comprising computer instructions, characterized in that, the computer instructions, when executed by a processor, implement the steps of the method of any one of claims 1 to 7.

Images