Cross-platform meta-universe resource intelligent collaborative matching system

Abstract

The invention discloses a cross-platform meta-universe resource intelligent collaborative matching system, and relates to the technical field of meta universe, the system comprises a data acquisition module, a user portrait construction module, a resource classification and labeling module, an intelligent matching algorithm module and a result display module, and the system is used for crossing different meta-universe platforms or ecological systems to carry out resource matching; the user portrait construction module constructs a multi-dimensional user portrait model based on the data acquired by the data acquisition module by using a machine learning algorithm; the user portrait model comprises historical behaviors and preference characteristics of the user; the resource classification and labeling module is used for classifying and labeling resources in the meta universe, extracting key features of the resources and forming a resource feature library; and the intelligent matching algorithm module performs resource matching according to the user portrait model and the resource feature library by adopting an intelligent algorithm based on multi-objective optimization. The method has the positive effects of promoting the ecological development of the universe and improving the user experience and satisfaction.

Description

Technical Field

[0001] The present invention mainly relates to the technical field of metaverse, and specifically to a cross-platform metaverse resource intelligent collaborative matching system. Background Art

[0002] The metaverse is a virtual world that is linked and created by scientific and technological means, mapped and interacted with the real world, and has a digital living space of a new social system. With the rapid development of digital technology, the concept of the metaverse has gradually attracted widespread attention. In the metaverse, users can call up and use the virtual resources they need, which provides a broad application scenario for the cross-platform metaverse resource intelligent collaborative matching system. The Internet of Things technology connects various physical devices in the real world through the Internet to form a huge network. In the metaverse, the Internet of Things can realize the interaction between devices in the real world and the virtual world. This provides a rich source of data and interaction methods for the cross-platform metaverse resource intelligent collaborative matching system. Through the Internet of Things technology, the system can obtain and update the status information of the device in real time, thereby achieving more accurate resource matching.

[0003] In the prior art, there is a resource intelligent matching method and a metaverse system based on the metaverse. The method can automatically and accurately determine the resources required by the resource demand side according to the corresponding identification information and metaverse portrait of the resource demand side, and automatically screen the metaverse data of the resource provider side that can provide the resource in the metaverse resource pool and send it to the resource demand side or display it in the metaverse resource pool to facilitate the resource demand side and the resource provider side to conduct online visual interaction in an immersive manner, no longer limited by the original physical place and the influence of information non-aggregation, while improving the interaction efficiency and accuracy between the resource demand side and the resource provider side.

[0004] However, in the prior art, resource association and resource sharing between platforms are separated, which leads to resource redundancy between each platform and inability to better handle existing resources. Secondly, the needs of users between platforms cannot be better met, resulting in a decline in satisfaction. Summary of the invention

[0005] Based on this, the purpose of the present invention is to provide a cross-platform metaverse resource intelligent collaborative matching system to solve the technical problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A cross-platform Metaverse resource intelligent collaborative matching system, comprising a data collection module, a user portrait construction module, a resource classification and annotation module, an intelligent matching algorithm module and a result display module, the system is used to match resources across different Metaverse platforms or ecosystems;

[0008] The user profile construction module uses machine learning algorithms and constructs a multi-dimensional user profile model based on the data collected by the data collection module; the user profile model includes the historical behaviors and preference characteristics of the user;

[0009] The resource classification and annotation module is used to classify and annotate the resources in the metaverse, extract the key features of the resources, and form a resource feature library;

[0010] The intelligent matching algorithm module adopts an intelligent algorithm based on multi-objective optimization to perform resource matching according to the user profile model and the resource feature library.

[0011] Preferably, the data collection module is used to collect the behavior data, preference settings of the user on the metaverse platform, and the real-time status information of the resources;

[0012] The behavior data includes, but is not limited to, the user's login time, browsing records, purchase records, and social interactions.

[0013] Preferably, the intelligent algorithm based on multi-objective optimization is specifically a combination of deep reinforcement learning DRL and swarm intelligence algorithm.

[0014] Preferably, the goal of the intelligent algorithm based on multi-objective optimization is to minimize the matching error and maximize the user satisfaction:

[0015]

[0016] Among them,

[0017] y i : represents the actual needs of users in the metaverse platform or ecosystem;

[0018] Y i : represents the matching result of the intelligent algorithm based on multi-objective optimization;

[0019] n: represents the number of users in the metaverse platform or ecosystem;

[0020] w j : represents the weight parameter in the intelligent algorithm based on multi-objective optimization,

[0021] λ: represents the regularization coefficient of the intelligent algorithm based on multi-objective optimization;

[0022] The intelligent algorithm based on multi-objective optimization finds the optimal weight parameter through iterative optimization to minimize the matching error.

[0023] Preferably, the intelligent matching algorithm module adopts an intelligent algorithm based on multi-objective optimization to perform resource matching according to the user profile and the resource feature library, output the matching result, and transmit it to the result display module.

[0024] Preferably, the result display module is used to display the matching result to the user in a chart visualization manner; the user can interact and make selections in the metaverse platform or ecosystem according to the matching result.

[0025] Preferably, the system further includes a resource optimization and allocation module, which is used to dynamically optimize and allocate resources according to the matching result and the resource demand situation.

[0026] Preferably, a user feedback unit is further provided in the intelligent matching algorithm module. The user feedback unit is used to construct an immersive user feedback environment by using AR / VR technology, so that users can intuitively express their needs and preferences to actively construct preference features.

[0027] Preferably, the resource optimization and allocation module adopts an optimization algorithm based on reinforcement learning, which is used to adjust strategies according to the historical matching data and user feedback in the system.

[0028] Preferably, the system supports docking with the data interfaces of other metaverse platforms or ecosystems to achieve cross-platform resource sharing and matching.

[0029] In summary, the present invention mainly has the following beneficial effects:

[0030] In the system of the present invention, by constructing an accurate user portrait, it is possible to deeply understand the preferences and needs of users, so as to provide personalized resource recommendations for users; this customized service can significantly improve user satisfaction and loyalty;

[0031] The system dynamically optimizes and allocates resources according to the matching result and the resource demand situation, ensuring the effective utilization and fair distribution of resources, and avoiding the waste and idleness of resources; Cross-platform resource sharing: The system supports docking with the data interfaces of other metaverse platforms or ecosystems, realizing cross-platform resource sharing and matching, breaking down platform barriers, and promoting the flow and integration of resources;

[0032] In order to meet the increasingly diverse needs of users, the system needs to continuously introduce new technologies and new algorithms, thus promoting technological innovation and progress in the metaverse field; Improve user activity and retention rate. By providing personalized resource matching services, the system can attract more users to participate in metaverse activities, improve user activity and retention rate, and lay a foundation for the long-term development of the metaverse platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is the structural framework diagram of the present invention.

[0034] Brief Description of Drawings: 10, data acquisition module; 20, user profile construction module; 30, resource classification and annotation module; 40, intelligent matching algorithm module; 50, result display module; 41, user feedback unit. Detailed Implementation Manner

[0035] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention.

[0036] Embodiment

[0037] As Figure 1 shown, a cross-platform intelligent collaborative matching system for metaverse resources includes a data acquisition module 10, a user profile construction module 20, a resource classification and annotation module 30, an intelligent matching algorithm module 40, and a result display module 50. The system is used to perform resource matching across different metaverse platforms or ecosystems;

[0038] The user profile construction module 20 uses machine learning algorithms and constructs a multi-dimensional user profile model based on the data collected by the data acquisition module 10; the user profile model contains the historical behaviors and preference characteristics of the user;

[0039] The resource classification and annotation module 30 is used to classify and annotate the resources in the metaverse, extract the key features of the resources, and form a resource feature library;

[0040] The intelligent matching algorithm module 40 adopts an intelligent algorithm based on multi-objective optimization and performs resource matching according to the user profile model and the resource feature library.

[0041] The data acquisition module 10 is used to collect the behavior data, preference settings of the user on the metaverse platform, and the real-time status information of the resources;

[0042] The behavior data includes, but is not limited to, the user's login time, browsing record, purchase record, and social interaction.

[0043] The intelligent algorithm based on multi-objective optimization is specifically a combination of deep reinforcement learning DRL and swarm intelligence algorithm.

[0044] The goal of the intelligent algorithm based on multi-objective optimization is to minimize the matching error and maximize the user satisfaction:

[0045]

[0046] Among them,

[0047] y i : represents the actual needs of the user in the metaverse platform or ecosystem;

[0048] Y i : represents the matching result of the intelligent algorithm based on multi-objective optimization;

[0049] n: represents the number of users in the metaverse platform or ecosystem;

[0050] w j : represents the weight parameter in the intelligent algorithm for multi-objective optimization,

[0051] λ: represents the regularization coefficient of the intelligent algorithm for multi-objective optimization;

[0052] The intelligent algorithm for multi-objective optimization finds the optimal weight parameter through iterative optimization to minimize the matching error.

[0053] The intelligent matching algorithm module adopts the intelligent algorithm based on multi-objective optimization, performs resource matching according to the user profile and resource feature library, outputs the matching result, and transmits it to the result display module 50.

[0054] The result display module 50 is used to display the matching result to the user in a graphical visualization manner; the user can interact and make selections in the metaverse platform or ecosystem according to the matching result.

[0055] The system also includes a resource optimization and allocation module, which is used to dynamically optimize and allocate resources according to the matching result and resource demand situation.

[0056] The intelligent matching algorithm module 40 also has a user feedback unit 41. The user feedback unit 41 is used to adopt AR / VR technology to construct an immersive user feedback environment for users to intuitively express their needs and preferences to actively construct preference features.

[0057] The resource optimization and allocation module adopts an optimization algorithm based on reinforcement learning, which is used to adjust strategies according to the historical matching data in the system and user feedback.

[0058] The system supports docking with the data interfaces of other metaverse platforms or ecosystems to achieve cross-platform resource sharing and matching.

[0059] Embodiment 1:

[0060] It should be noted that this embodiment is described with the intelligent matching of cross-platform game resources:

[0061] Application scenario:

[0062] In an ecosystem composed of multiple metaverse game platforms, players need to find game resources that match their interests and skill levels, such as game characters, equipment, tasks, etc., among different platforms; the cross-platform game resource intelligent matching system in this embodiment aims to help players quickly and accurately find suitable game resources.

[0063] The data collection module 10 collects data such as the login time, game duration, browsing records, purchase records, social interactions, etc. of players on various game platforms, as well as the real-time status information of game resources such as the remaining quantity and price changes.

[0064] Based on the collected data, the user profile construction module 20 constructs player profiles using machine learning algorithms, including features such as players' game preferences, skill levels, social habits, etc.; at the same time, the resource classification and annotation module 30 classifies and annotates game resources according to criteria such as types (such as characters, equipment, tasks, levels, rarity, etc.) to form a resource feature library.

[0065] The intelligent matching algorithm module 40 adopts a multi-objective optimization intelligent algorithm that combines deep reinforcement learning DRL and swarm intelligence algorithms to perform resource matching based on the player profile and the resource feature library.

[0066] The algorithm aims to minimize the matching error, that is, the deviation between the resource and the player's needs, and to maximize user satisfaction; through iterative optimization, the algorithm continuously adjusts the weight parameters and regularization coefficients to achieve the optimal matching effect.

[0067] The result display module 50 displays the matching results to players in the form of charts, such as a recommended resource list, a resource distribution map, etc.; players can interact and make selections within the game platform according to the displayed results, such as purchasing, exchanging, or completing tasks.

[0068] The user feedback unit 41 uses AR / VR technology to build an immersive user feedback environment, allowing players to directly express their needs and preferences in the game to actively construct or update preference features.

[0069] Implementation effect.

[0070] This system significantly improves the efficiency of players in finding resources among different metaverse game platforms, while enhancing players' gaming experience and satisfaction.

[0071] Example two:

[0072] It should be noted that this example is described in terms of cross-platform educational resource sharing:

[0073] Application scenario:

[0074] In an ecosystem composed of multiple metaverse educational platforms, learners need to find suitable learning resources, such as courses, textbooks, experiments, etc. among different platforms; the cross-platform educational resource sharing system in this example aims to help learners quickly and accurately find the required learning resources.

[0075] The data collection module 10 collects the learning behavior data of learners on various educational platforms, such as login time, course browsing records, learning progress, test scores, etc., as well as the real-time status information of learning resources such as course opening status, teaching material inventory, etc.

[0076] The user portrait construction module 20 constructs a learner portrait based on the collected data, including features such as learning style, interest field, knowledge level, etc.; the resource classification and annotation module 30 classifies and annotates learning resources according to criteria such as subject, difficulty, type, etc.; the intelligent matching algorithm module 40 uses a multi-objective optimization intelligent algorithm for resource matching, with the goal of minimizing the matching error and maximizing learner satisfaction; the result display module 50 displays the matching results to learners in a visual way, such as course recommendation diagrams, learning resource distribution diagrams, etc.

[0077] The resource optimization and allocation module dynamically optimizes and allocates learning resources according to the matching results and resource requirements, ensuring the effective utilization and fair distribution of resources; the user feedback unit 41 uses AR / VR technology to construct an immersive feedback environment, allowing learners to directly express their learning needs and preferences within the educational platform.

[0078] Implementation effect:

[0079] This system effectively promotes the sharing and utilization of cross-platform educational resources, and improves the learning efficiency and satisfaction of learners.

[0080] Example 3: Cross-platform virtual goods trading platform

[0081] Application scenario:

[0082] In an ecosystem composed of multiple metaverse e-commerce platforms, users need to trade virtual goods such as virtual clothing, decorations, in-game currency, etc. between different platforms; the cross-platform virtual goods trading platform in this example aims to provide a safe, efficient, and personalized trading environment.

[0083] The data collection module 10 collects the trading behavior data of users on various e-commerce platforms, such as purchase records, browsing histories, favorite items, etc., as well as information such as the real-time prices and inventories of virtual goods; the user portrait construction module 20 constructs a user portrait, including features such as shopping preferences, consumption levels, trading habits, etc.; the resource classification and annotation module 30 classifies and annotates virtual goods, such as by type, style, price range, etc.

[0084] The intelligent matching algorithm module 40 uses a multi-objective optimization intelligent algorithm for commodity matching, taking into account user portraits and commodity characteristics, as well as factors such as the creditworthiness and historical trading records of both trading parties; the resource optimization and allocation module dynamically optimizes and allocates virtual goods according to the matching results and trading requirements, improving trading efficiency and success rates.

[0085] The user feedback unit 41 uses AR / VR technology to construct an immersive transaction feedback environment, allowing users to directly express their needs and opinions during the transaction process.

[0086] Cross-platform data interface docking realizes the docking of data interfaces with multiple metaverse e-commerce platforms, enabling cross-platform transactions and resource sharing of virtual goods.

[0087] Implementation effect:

[0088] This system provides users with a safe, efficient, and personalized cross-platform virtual goods trading environment, promoting the healthy development of the metaverse e-commerce ecosystem.

[0089] The above embodiments are only used to illustrate the technical idea of the present invention, and the protection scope of the present invention cannot be limited thereby. Any modifications made on the basis of the technical solution according to the technical idea proposed by the present invention shall fall within the protection scope of the present invention.

Claims

1. An intelligent collaborative matching system for cross-platform metaverse resources, characterized in that , including a data collection module (10), a user profile construction module (20), a resource classification and annotation module (30), an intelligent matching algorithm module (40), and a result display module (50). The system is used for resource matching across different metaverse platforms or ecosystems; The user profile construction module (20) uses machine learning algorithms and constructs a multi-dimensional user profile model based on the data collected by the data collection module (10); the user profile model contains the historical behaviors and preference characteristics of the user; The resource classification and annotation module (30) is used to classify and annotate the resources in the metaverse, extract the key features of the resources, and form a resource feature library; The intelligent matching algorithm module (40) adopts an intelligent algorithm based on multi-objective optimization and performs resource matching according to the user profile model and the resource feature library.

2. The intelligent collaborative matching system for cross-platform metaverse resources according to claim 1, wherein The data collection module (10) is used to collect the behavior data of users on the metaverse platform, preference settings, and real-time status information of resources; The behavior data includes, but is not limited to, the login time, browsing records, purchase records, and social interactions of users.

3. An intelligent collaborative matching system for cross-platform metaverse resources according to claim 1, characterized in that, The intelligent algorithm for multi-objective optimization is specifically a combination of deep reinforcement learning DRL and swarm intelligence algorithms.

4. An intelligent collaborative matching system for cross-platform metaverse resources according to claim 1, characterized in that, The objectives of the intelligent algorithm for multi-objective optimization are to minimize the matching error and maximize user satisfaction: Wherein, y i : represents the actual needs of users in the metaverse platform or ecosystem; Y i : represents the matching result of the intelligent algorithm for multi-objective optimization; n: represents the number of users in the metaverse platform or ecosystem; w j : Represents the weight parameter in the intelligent algorithm for multi-objective optimization, λ: represents the regularization coefficient of the intelligent algorithm for multi-objective optimization; The intelligent algorithm for multi-objective optimization finds the optimal weight parameters through iterative optimization to minimize the matching error.

5. An intelligent collaborative matching system for cross-platform metaverse resources according to claim 1, characterized in that, The intelligent matching algorithm module adopts an intelligent algorithm based on multi-objective optimization, performs resource matching according to the user profile and the resource feature library, outputs the matching result, and transmits it to the result display module (50).

6. A cross-platform metaverse resource intelligent collaborative matching system according to claim 1, characterized in that The result display module (50) is used to display the matching result to the user in a graphical visualization manner; the user can interact and make selections in the metaverse platform or ecosystem according to the matching result.

7. An intelligent collaborative matching system for cross-platform metaverse resources according to claim 1, characterized in that, The system further includes a resource optimization and allocation module, which is used to dynamically optimize and allocate resources according to the matching result and the resource demand situation.

8. An intelligent collaborative matching system for cross-platform metaverse resources according to claim 1, characterized in that, A user feedback unit (41) is further provided in the intelligent matching algorithm module (40). The user feedback unit (41) is used to adopt AR / VR technology to construct an immersive user feedback environment for users to intuitively express their needs and preferences to actively construct preference characteristics.

9. An intelligent collaborative matching system for cross-platform metaverse resources according to claim 1, characterized in that, The resource optimization and allocation module adopts an optimization algorithm based on reinforcement learning, which is used to adjust the strategy according to the historical matching data and user feedback in the system.

10. A cross-platform metaverse resource intelligent collaborative matching system according to claim 1, characterized in that, The system supports docking with the data interfaces of other metaverse platforms or ecosystems to achieve cross-platform resource sharing and matching.

Images