A method, device and system for pushing information resources based on real-scene metaverse

Abstract

The present invention provides a method, device, and system for pushing information resources based on a real-world metaverse, belonging to the field of deep learning technology. The method comprises: collecting a set of real-world user behavior data; obtaining a training data set based on the user behavior data set, and using the training data set to train a deep learning-based neural network to obtain an information resource push model; collecting a set of virtual user behavior data in a real-world metaverse, inputting the virtual user behavior data set into the information resource push model, and outputting metaverse information resource push information. The present invention obtains user behavior data from the real world to train an information resource push model, and then uses data such as user tags collected from the metaverse to utilize the information resource push model trained in the real world to determine information recommendation results that meet the preferences of metaverse users, thereby realizing personalized services for information resources in the metaverse.

Description

Technical Field

[0001] The present invention relates to the field of deep learning technology, and in particular to a method, device and system for pushing information resources based on a real-scene metaverse. Background Art

[0002] The Metaverse is a virtual world constructed by humans using digital technology that maps to or transcends the real world and is a digital living space with a new social system.

[0003] Among the many existing metaverses, the real-world metaverse uses methods such as drone oblique and close-up photogrammetry to scan real scenes, constructing a three-dimensional digital space that authentically reflects and expresses the real world. This fusion of virtual and real is achieved through the metaverse's interactive properties and spatiotemporal mapping. However, while users can freely explore the metaverse as if they were navigating a real scene, the real-world metaverse lacks an information push system similar to the real-world experience, enabling personalized browsing within the virtual world.

[0004] Therefore, how to integrate the real-world information push system with the real-scene metaverse to meet the personalized needs of digital visitors for information acquisition is an urgent problem that needs to be solved. Summary of the Invention

[0005] The present invention provides a method, device and system for pushing information resources based on a real-life metaverse, so as to address the defect in the prior art of lacking information resource push and sharing technology that combines the metaverse with the real-world experience.

[0006] In a first aspect, the present invention provides a method for pushing information resources based on a real-scene metaverse, comprising:

[0007] Collect real-world user behavior data sets;

[0008] A training data set is obtained based on the user behavior data set, and a deep learning-based neural network is trained using the training data set to obtain an information resource push model;

[0009] Collect user virtual behavior data sets in the real-scene metaverse, input the user virtual behavior data sets into the information resource push model, and output metaverse information resource push information.

[0010] According to a method for pushing information resources based on a real-world metaverse provided by the present invention, the method of collecting a set of real-world user behavior data includes:

[0011] Offline data collection and network data collection are used to obtain the user's real behavior data set.

[0012] According to a method for pushing information resources based on a real-life metaverse provided by the present invention, obtaining a training data set based on a user behavior data set includes:

[0013] Determining to use the personal information and action information of the user behavior data set as data set features, and to use the preference information of the user behavior data set as data set labels;

[0014] The training dataset is constructed based on the dataset features and the dataset labels.

[0015] According to a method for pushing information resources based on a real-life metaverse provided by the present invention, the method uses the training data set to train a neural network based on deep learning to obtain an information resource push model, including:

[0016] Constructing an initial neural network structure model and using a deep learning-based sequence recommendation algorithm to extract user historical sequence data from the training data set;

[0017] The initial neural network structure model is trained using the user historical sequence data to obtain the information resource push model.

[0018] According to a method for pushing information resources based on a real-life metaverse provided by the present invention, the method of collecting a user virtual behavior data set in the real-life metaverse includes:

[0019] Collecting Metaverse user login and registration information, and determining Metaverse user identity information based on the Metaverse user login and registration information;

[0020] Obtaining Metaverse user interface setting information, and determining Metaverse user preference information based on the Metaverse user interface setting information;

[0021] Collect multiple movement location nodes of metaverse users, and generate metaverse user behavior trajectories based on the multiple movement location nodes of metaverse users.

[0022] According to a method for pushing information resources based on a real-life metaverse provided by the present invention, the method of inputting the user virtual behavior data set into the information resource push model and outputting metaverse information resource push information includes:

[0023] The metaverse user preference information is used as the metaverse user tag, and the metaverse user identity information and the metaverse user behavior trajectory are used as the metaverse user features;

[0024] Inputting the Metaverse user tag and the Metaverse user characteristics into the information resource push model to obtain Metaverse user preference information;

[0025] The metaverse information resource push information is determined according to the metaverse user preference information.

[0026] In a second aspect, the present invention further provides an information resource push device based on a real-scene metaverse, comprising:

[0027] The login and registration module, user interaction module, information resource acquisition module, and information visualization module deployed on the client, and the model calculation module deployed on the server, including:

[0028] Login registration module, obtain the account registration information or account login information of the Metaverse user;

[0029] User interaction module, which enables interaction between Metaverse users and the Metaverse system;

[0030] The information resource acquisition module integrates user input information based on the Metaverse user location update information;

[0031] A model calculation module performs network model calculation based on the user input information to obtain metaverse user preference information;

[0032] The information visualization module performs visual rendering of the metaverse and realizes user interface visualization.

[0033] In a third aspect, the present invention further provides an information resource push system based on a real-life metaverse, comprising:

[0034] The collection module is used to collect real-world user behavior data sets;

[0035] A training module is used to obtain a training data set based on a user behavior data set, and use the training data set to train a neural network based on deep learning to obtain an information resource push model;

[0036] The processing module is used to collect the user virtual behavior data set in the real-scene metaverse, input the user virtual behavior data set into the information resource push model, and output the metaverse information resource push information.

[0037] In a fourth aspect, the present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for pushing information resources based on the real-scene metaverse as described above is implemented.

[0038] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for pushing information resources based on the real-scene metaverse as described above is implemented.

[0039] The information resource push method, device and system based on the real-life metaverse provided by the present invention obtain an information resource push model by training user behavior data from the real world, and then use data such as user tags collected from the metaverse to utilize the information resource push model trained in the real world to determine information recommendation results that meet the preferences of metaverse users, thereby realizing personalized services for information resources in the metaverse, and effectively utilizing existing data as a training set, thereby reducing the cost of data collection, and having strong practical value in the construction of the real-life metaverse platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 This is one of the flow charts of the information resource push method based on the real-scene metaverse provided by the present invention;

[0042] Figure 2 This is the second flow chart of the information resource push method based on the real-scene metaverse provided by the present invention;

[0043] Figure 3 This is a schematic diagram of the structure of the information resource push device based on the real-scene metaverse provided by the present invention;

[0044] Figure 4 This is a schematic diagram of the structure of the information resource push system based on the real-scene metaverse provided by the present invention;

[0045] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0046] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0047] The embodiment of the present invention aims to integrate the information push mode of the real world with the real-scene metaverse to provide metaverse visitors with a personalized information acquisition experience, and proposes an information resource push method based on the real-scene metaverse.

[0048] Figure 1 This is one of the flow charts of the information resource push method based on the real-scene metaverse provided by the embodiment of the present invention. Figure 1 Shown, including:

[0049] Step 100: Collecting a real-world user behavior data set;

[0050] Step 200: obtaining a training data set based on the user behavior data set, and using the training data set to train a neural network based on deep learning to obtain an information resource push model;

[0051] Step 300: Collect user virtual behavior data sets in the real-scene metaverse, input the user virtual behavior data sets into the information resource push model, and output metaverse information resource push information.

[0052] Specifically, the embodiment of the present invention is illustrated by analyzing tourists' touring behavior as an example. In the real world, tourists' touring trajectories, preference information, gender, age and other information of relevant real building areas are collected, and the above information is integrated to produce a training data set and a verification data set based on real-world data. The above data set is used to train a sequence recommendation algorithm neural network based on deep learning to obtain a trained and verified network model, namely, an information resource push model. Then, the gender, age, preference, action trajectory and other information of the metaverse users are obtained in the real-scene metaverse. Finally, the information collected in the above metaverse is input into the previously trained neural network, and the user's personalized push resources are obtained through model calculation for personalized push.

[0053] Another example Figure 2 As shown, the embodiment of the present invention starts from two dimensions. On the one hand, it collects real-world user data, including the user's gender, age, preferences and trajectory, and creates a training set based on the collected real-world user data. The training set is then used to train a neural network based on a sequence recommendation algorithm based on deep learning to obtain a trained network model, namely, an information resource push model. On the other hand, it is the real-scene metaverse, which obtains user information including gender, age and preferences through user registration, and user information including trajectory records through user free movement, and then puts them into the information resource push model for model calculation to output personalized push resources.

[0054] The present invention obtains user behavior data from the real world to train an information resource push model, and then uses user tags and other data collected from the metaverse to utilize the information resource push model trained in the real world to determine the information recommendation results that meet the metaverse user preferences, thereby realizing personalized services for information resources in the metaverse and effectively utilizing existing data as a training set, thereby reducing the cost of data collection. It has strong practical value in the construction of a real-life metaverse platform.

[0055] Based on the above embodiment, step 100 includes:

[0056] Offline data collection and network data collection are used to obtain the user's real behavior data set.

[0057] It should be noted that in the real world, there are two main collection methods for collecting real user behavior data sets: offline collection and online collection.

[0058] Taking tourism information collection as an example, a large amount of tourist behavior information can be obtained by using offline collection methods such as questionnaires, real-name registration at scenic spots, and ticket information inquiries at scenic spots. In addition, due to the rise of online reservations and online ordering, relevant personal information of tourists can also be obtained conveniently and quickly through network data collection.

[0059] Based on the above embodiment, the step 200 of obtaining a training data set based on the user behavior data set includes:

[0060] Determining to use the personal information and action information of the user behavior data set as data set features, and to use the preference information of the user behavior data set as data set labels;

[0061] The training dataset is constructed based on the dataset features and the dataset labels.

[0062] Specifically, based on the collection of real user behavior data sets, the embodiment of the present invention uses the tourists' gender, age, trajectory information, etc. as the features of the data set, and uses the tourists' preference information as the labels of the data set to construct a training data set.

[0063] Based on the above embodiment, the step 200 of using the training data set to train a neural network based on deep learning to obtain an information resource push model includes:

[0064] Constructing an initial neural network structure model and using a deep learning-based sequence recommendation algorithm to extract user historical sequence data from the training data set;

[0065] The initial neural network structure model is trained using the user historical sequence data to obtain the information resource push model.

[0066] Specifically, the deep learning-based sequential recommendation algorithm used in the embodiments of the present invention generates personalized item recommendations by analyzing a user's historical sequence data using a deep neural network. These algorithms learn from user behavior sequences to predict items the user might like in the future and generate a recommendation list. These algorithms typically use mainstream technologies such as recurrent neural networks (RNNs), long short-term memory networks (LSTMs), or attention mechanisms to predict personalized user information.

[0067] Based on the above embodiment, the step 300 of collecting the user virtual behavior data set in the real-life metaverse includes:

[0068] Collecting Metaverse user login and registration information, and determining Metaverse user identity information based on the Metaverse user login and registration information;

[0069] Obtaining Metaverse user interface setting information, and determining Metaverse user preference information based on the Metaverse user interface setting information;

[0070] Collect multiple movement location nodes of metaverse users, and generate metaverse user behavior trajectories based on the multiple movement location nodes of metaverse users.

[0071] Specifically, the embodiment of the present invention obtains the user's age and gender through the basic information when the user logs in and registers in the metaverse, obtains the user's preference information through the preferences set by the user in the personal information setting interface, and generates the user's behavior trajectory through the location nodes passed by the user continuously recorded in the user background.

[0072] Based on the above embodiment, the step 300 of inputting the user virtual behavior data set into the information resource push model and outputting the metaverse information resource push information includes:

[0073] The metaverse user preference information is used as the metaverse user tag, and the metaverse user identity information and the metaverse user behavior trajectory are used as the metaverse user features;

[0074] Inputting the Metaverse user tag and the Metaverse user characteristics into the information resource push model to obtain Metaverse user preference information;

[0075] The metaverse information resource push information is determined according to the metaverse user preference information.

[0076] Specifically, the user preferences in the above-mentioned metaverse are used as labels, and other information is used as features, which are input into the neural network model previously trained in the real world. The user's preference for various types of information is calculated, and information resources with a higher degree of preference are pushed to the user on the information push interface to achieve personalized push.

[0077] Figure 3 Schematic diagram of the structure of the information resource push device based on the real-scene metaverse provided by the embodiment of the present invention. Figure 3 Shown, including:

[0078] The login and registration module, user interaction module, information resource acquisition module, and information visualization module deployed on the client, and the model calculation module deployed on the server, including:

[0079] Login registration module, obtain the account registration information or account login information of the Metaverse user;

[0080] User interaction module, which enables interaction between Metaverse users and the Metaverse system;

[0081] The information resource acquisition module integrates user input information based on the Metaverse user location update information;

[0082] A model calculation module performs network model calculation based on the user input information to obtain metaverse user preference information;

[0083] The information visualization module performs visual rendering of the metaverse and realizes user interface visualization.

[0084] Specifically, the information resource push device based on the real-scene metaverse proposed in an embodiment of the present invention includes a client and a server. The client module includes the following parts: a user registration and login module, a user interaction module, an information resource acquisition module and an information visualization module. The information resource acquisition module transmits the user input information to the server after parameterized processing. The server uses the training set collected in the real world mapped by the real-scene metaverse, and uses the sequence recommendation algorithm neural network based on deep learning for pre-training, and then uses the user tags (action trajectory, preference information, gender, age, etc.) collected in the metaverse to determine the information recommendation results that meet the user preferences, and transmits the processed information resources back to the client in the form of data packets to realize personalized services of information resources in the metaverse.

[0085] Login and Registration: Users who use the system for the first time need to register an account. When registering, they need to fill in basic personal information including gender and age. After registration, users can log in to the system with the corresponding account and password.

[0086] User Interaction Module: This module primarily facilitates user-system interaction, such as character control, information input, and output. By providing interactive functionality based on input devices (keyboard, mouse, VR controller, etc.), user input controls the movement and interaction of Metaverse virtual characters. Through this module, users can freely move around the Metaverse, browse information, and set or modify their basic information, preferences, and interaction methods within the system's personalized information settings.

[0087] Information Resource Acquisition Module: This module's main function is to obtain and integrate user input information. It's worth noting that the user location tracking in this module continuously acquires the user's location coordinates (every 0.01 seconds) to generate the user's trajectory information.

[0088] Model calculation module: This module mainly uses the information obtained from the information resource module to calculate the network model, calculate the user's preference for various types of information, and then select content information with greater preference to push.

[0089] Information visualization module: This module mainly performs visual rendering of the metaverse and visualization of various interfaces. According to the user's preference, the information resources that the user prefers will be pushed to the information push interface.

[0090] The information resource push system based on the real-scene metaverse provided by the present invention is described below. The information resource push system based on the real-scene metaverse described below and the information resource push method based on the real-scene metaverse described above can refer to each other.

[0091] Figure 4 This is a structural diagram of the information resource push system based on the real-scene metaverse provided by the present invention. Figure 4 As shown, it includes: an acquisition module 41, a training module 42 and a processing module 43, wherein:

[0092] The acquisition module 41 is used to collect the user's real behavior data set in the real world; the training module 42 is used to obtain a training data set based on the user behavior data set, and use the training data set to train a neural network based on deep learning to obtain an information resource push model; the processing module 43 is used to collect the user's virtual behavior data set in the real-scene metaverse, input the user's virtual behavior data set into the information resource push model, and output the metaverse information resource push information.

[0093] Figure 5 An example of a physical structure diagram of an electronic device is shown below. Figure 5As shown, the electronic device may include: a processor (processor) 510, a communication interface (Communications Interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 830 communicate with each other via the communication bus 540. The processor 510 can call the logic instructions in the memory 530 to execute the information resource push method based on the real-world metaverse, which includes: collecting a set of real-world user behavior data; obtaining a training data set based on the user behavior data set, and using the training data set to train a neural network based on deep learning to obtain an information resource push model; collecting a set of virtual user behavior data in the real-world metaverse, inputting the set of virtual user behavior data into the information resource push model, and outputting metaverse information resource push information.

[0094] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0095] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the information resource push method based on the real-scene metaverse provided by the above-mentioned methods. The method includes: collecting a set of real-world user behavior data; obtaining a training data set based on the user behavior data set, and using the training data set to train a deep learning-based neural network to obtain an information resource push model; collecting a set of virtual user behavior data in the real-scene metaverse, inputting the set of virtual user behavior data into the information resource push model, and outputting metaverse information resource push information.

[0096] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0097] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for pushing information resources based on a real-life metaverse, characterized in that: include: Collect real-world user behavior data sets; A training data set is obtained based on the user behavior data set, and a deep learning-based neural network is trained using the training data set to obtain an information resource push model; Collecting a user virtual behavior data set in the real-life metaverse, inputting the user virtual behavior data set into the information resource push model, and outputting metaverse information resource push information; The collection of user virtual behavior data in the real-life metaverse includes: Collecting Metaverse user login and registration information, and determining Metaverse user identity information based on the Metaverse user login and registration information; Obtaining Metaverse user interface setting information, and determining Metaverse user preference information based on the Metaverse user interface setting information; Collecting multiple movement location nodes of a metaverse user, and generating a metaverse user behavior trajectory based on the multiple movement location nodes of the metaverse user; The step of inputting the user virtual behavior data set into the information resource push model and outputting metaverse information resource push information includes: The metaverse user preference information is used as the metaverse user tag, and the metaverse user identity information and the metaverse user behavior trajectory are used as the metaverse user features; Inputting the Metaverse user tag and the Metaverse user characteristics into the information resource push model to obtain Metaverse user preference information; The metaverse information resource push information is determined according to the metaverse user preference information.

2. The information resource push method based on the real-scene metaverse according to claim 1, characterized in that: The collection of real-world user behavior data includes: Offline data collection and network data collection are used to obtain the user's real behavior data set.

3. The information resource push method based on the real-scene metaverse according to claim 1, characterized in that: The step of obtaining a training data set based on the user behavior data set includes: Determining to use the personal information and action information of the user behavior data set as data set features, and to use the preference information of the user behavior data set as data set labels; The training dataset is constructed based on the dataset features and the dataset labels.

4. The information resource push method based on the real-scene metaverse according to claim 1 is characterized in that: The method of using the training data set to train a deep learning-based neural network to obtain an information resource push model includes: Constructing an initial neural network structure model and using a deep learning-based sequence recommendation algorithm to extract user historical sequence data from the training data set; The initial neural network structure model is trained using the user historical sequence data to obtain the information resource push model.

5. An information resource push device based on a real-scene metaverse, used to execute the information resource push method based on a real-scene metaverse according to any one of claims 1 to 4, characterized in that: include: The login and registration module, user interaction module, information resource acquisition module, and information visualization module deployed on the client, and the model calculation module deployed on the server, including: Login registration module, obtain the account registration information or account login information of the Metaverse user; User interaction module, which enables interaction between Metaverse users and the Metaverse system; The information resource acquisition module integrates user input information based on the Metaverse user location update information; A model calculation module performs network model calculation based on the user input information to obtain metaverse user preference information; The information visualization module performs visual rendering of the metaverse and realizes user interface visualization.

6. A real-life metaverse-based information resource push system, based on the real-life metaverse-based information resource push method according to any one of claims 1 to 4, characterized in that: include: The collection module is used to collect real-world user behavior data sets; A training module is used to obtain a training data set based on a user behavior data set, and use the training data set to train a neural network based on deep learning to obtain an information resource push model; The processing module is used to collect the user virtual behavior data set in the real-scene metaverse, input the user virtual behavior data set into the information resource push model, and output the metaverse information resource push information.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the information resource pushing method based on the real-scene metaverse as described in any one of claims 1 to 4 is implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the information resource pushing method based on the real-scene metaverse as described in any one of claims 1 to 4 is implemented.

Images