Virtual object generation method, device and system

Abstract

The invention provides a virtual object generation method, device and system. The method comprises the steps of obtaining a user demand; determining a generation demand according to the user demand, wherein the generation demand is used for generating a virtual object; the generation demand is decomposed into at least one sub-task, each sub-task in the at least one sub-task corresponds to a demand field, and each demand field comprises at least one demand function; determining a demand function corresponding to the virtual object in at least one demand field; and calling a function model of a demand function corresponding to the virtual object in the at least one demand field to generate the virtual object. According to the scheme, multi-layer decomposition is carried out on the generation demand based on the demand field and the demand function, refining of the generation demand can be achieved, accurate calling of the model is guaranteed, and therefore the more accurate and higher-quality virtual object is generated.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and more specifically, to a method, apparatus, and system for generating virtual objects. Background Technology

[0002] The continuous advancement of computer technology has driven the development of virtual object generation technology. For example, as an important branch of virtual objects, digital humans, relying on technologies such as virtualization, natural language processing (NLP), and computer vision (CV), have broad application prospects. A digital human, a virtual character with a digitized appearance, exists in the non-physical world, needs to be created and used through computers, and is a comprehensive product possessing multiple human characteristics (e.g., physical features, human performance abilities, and interactive abilities). Driven by digital technology, digital humans can possess human-like behavior, including language, facial expressions, and movements. However, current technology generates virtual objects based on general models, resulting in uncontrollable generation outcomes and poor quality.

[0003] Therefore, improving the quality of virtual object generation is an urgent problem to be solved. Summary of the Invention

[0004] This application provides a method, apparatus, and system for generating virtual objects, which can achieve accurate model invocation, thereby improving the generation quality of virtual objects.

[0005] In a first aspect, a method for generating virtual objects is provided, the method comprising: obtaining user requirements; determining generation requirements based on the user requirements, the generation requirements being used to generate virtual objects; decomposing the generation requirements into at least one subtask, each subtask corresponding to a requirement domain, each requirement domain including at least one requirement function; determining the requirement function corresponding to the virtual object under the at least one requirement domain; and invoking the function model of the requirement function corresponding to the virtual object under the at least one requirement domain to generate the virtual object.

[0006] Based on the above scheme, the generation requirements can be decomposed into multiple layers based on the requirement domain and requirement function, which can refine the generation requirements, ensure the accurate invocation of the model, and thus generate more accurate and higher quality virtual objects.

[0007] In conjunction with the first aspect, in some implementations of the first aspect, determining the generation requirements based on the user requirements includes: determining the generation requirements based on the user requirements using a Large Language Model (LLM) and a Virtual Object Knowledge Base.

[0008] Based on the above approach, the rationality of user requirements can be further assessed using LLM and a virtual object knowledge base to determine the final generation requirements. It should be noted that while LLM is a general model with general knowledge, it may lack specific knowledge (e.g., knowledge related to virtual objects). Therefore, specific knowledge can be added to the LLM by externalizing it (e.g., a virtual object knowledge base), thus eliminating the need to retrain the LLM.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, the user requirement includes a first feature; determining the generation requirement based on the user requirement includes: outputting a correction prompt when the virtual object knowledge base does not include the first feature, the correction prompt being used to suggest modifying the first feature to a second feature, wherein the second feature is a feature included in the virtual object knowledge base; obtaining a confirmation message for the correction prompt; and determining the generation requirement based on the confirmation message for the correction prompt, wherein the generation requirement includes the second feature.

[0010] Based on the above scheme, when the virtual object knowledge base does not include the first feature, it indicates that the virtual object involved in the user's requirement is not within the scope of prior knowledge, and the user's requirement is "unreasonable." Therefore, the user can be instructed to correct the requirement based on the content of the virtual object knowledge base, resulting in a generated requirement. Since the second feature involved in the generated requirement is within the virtual object knowledge base, the generated requirement is a "reasonable" requirement. Therefore, the above scheme can improve the reasonableness of the requirement, thereby improving the quality of virtual object generation.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, determining the generation requirement based on the user requirement includes: outputting a selection prompt, the selection prompt being used to prompt the selection of a third feature, wherein the third feature is a feature included in the virtual object knowledge base but not included in the user requirement; obtaining a confirmation message for the selection prompt; and determining the generation requirement based on the confirmation message for the selection prompt, wherein the generation requirement includes the third feature.

[0012] Based on the above scheme, user requirements can be supplemented by the virtual object knowledge base, prompting users to add reasonable features and enrich the content of the generation requirements, so that the final generated virtual object has higher quality.

[0013] In conjunction with the first aspect, in some implementations of the first aspect, before decomposing the generation requirement into at least one subtask, the method further includes: outputting a confirmation prompt, the confirmation prompt being used to prompt confirmation of the generation requirement; and obtaining a confirmation message from the confirmation prompt.

[0014] Based on the above scheme, before generating virtual objects, users can also filter the features involved in the generation requirements, which improves the user's control over the virtual object generation results.

[0015] In conjunction with the first aspect, in some implementations of the first aspect, determining the required functions corresponding to the virtual object under at least one required domain includes: determining the required functions corresponding to the virtual object under each required domain; presenting a selection interface, the selection interface including the required functions corresponding to the virtual object under each required domain; and obtaining the required functions corresponding to the virtual object under the at least one required domain selected through the selection interface.

[0016] Secondly, a virtual object generation device is provided, comprising: an interaction unit for acquiring user needs; and a processing unit, which includes an intelligent agent and a functional agent.

[0017] The intelligent agent is used to perform the following operations: determine generation requirements based on the user requirements, the generation requirements being used to generate virtual objects; decompose the generation requirements into at least one sub-task, each sub-task corresponding to a requirement domain, and each requirement domain including at least one requirement function.

[0018] The functional Agent is used to perform the following operations: determine the required functions corresponding to the virtual object under at least one requirement domain; and call the functional model of the required functions corresponding to the virtual object under the at least one requirement domain to generate the virtual object.

[0019] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit further includes a Large Language Model (LLM) and a virtual object knowledge base.

[0020] The step of determining the generation requirements based on the user's needs includes: the intelligent agent determining the generation requirements based on the user's needs using the LLM and the virtual object knowledge base.

[0021] The step of decomposing the generation requirement into at least one sub-task includes: the intelligent agent using the LLM to decompose the generation requirement into at least one sub-task.

[0022] In conjunction with the second aspect, in some implementations of the second aspect, the user requirement includes the first feature.

[0023] The interaction unit is configured to: output a correction prompt when the virtual object knowledge base does not include the first feature, the correction prompt being used to suggest that the first feature be modified to a second feature, wherein the second feature is a feature included in the virtual object knowledge base; and obtain a confirmation message for the correction prompt.

[0024] The intelligent agent is used to: determine the generation requirement based on the confirmation message of the correction prompt, wherein the generation requirement includes the second feature.

[0025] In conjunction with the second aspect, in some implementations of the second aspect, the interaction unit is used to: output a selection prompt, the selection prompt being used to prompt the selection of a third feature, wherein the third feature is a feature included in the virtual object knowledge base but not included in the user requirements; and obtain a confirmation message for the selection prompt.

[0026] The intelligent agent is used to: determine the generation requirement based on the confirmation message of the selection prompt, wherein the generation requirement includes the third feature.

[0027] In conjunction with the second aspect, in some implementations of the second aspect, the interaction unit is used to: output a confirmation prompt, the confirmation prompt being used to prompt confirmation of the generation requirement; and obtain a confirmation message from the confirmation prompt.

[0028] In conjunction with the second aspect, in some implementations of the second aspect, the functional Agent is used to: determine the required functions corresponding to the virtual object under each requirement domain.

[0029] The interaction unit is used to: present a selection interface, the selection interface including the requirement functions corresponding to the virtual object under each requirement domain; and obtain the requirement functions corresponding to the virtual object under the at least one requirement domain selected through the selection interface.

[0030] In conjunction with the second aspect, in some implementations of the second aspect, the interaction unit is also used to: present the virtual object.

[0031] It should be understood that the beneficial effects of the second aspect and its various implementations are similar to those of the first aspect and its various implementations, and will not be elaborated upon here.

[0032] Thirdly, a computing device is provided, including a processor and a memory, and optionally, an input / output interface. The processor controls the input / output interface to send and receive information, the memory stores a computer program, and the processor retrieves and runs the computer program from the memory, causing the program to execute the method of the first aspect or any possible implementation thereof.

[0033] Optionally, the processor can be a general-purpose processor, which can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, integrated circuit, etc.; when implemented in software, the processor can be a general-purpose processor that reads software code stored in memory. This memory can be integrated into the processor or located outside the processor and exist independently.

[0034] Fourthly, a computing device cluster is provided, including at least one computing device, each computing device including a processor and a memory; the processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device, such that the computing device cluster performs the method of the first aspect or any possible implementation thereof.

[0035] Fifthly, a chip is provided that acquires and executes instructions to implement the methods described in the first aspect and any implementation thereof.

[0036] Optionally, as one implementation, the chip includes a processor and a data interface, through which the processor reads instructions stored in the memory and executes the methods in the first aspect and any implementation thereof.

[0037] Optionally, as one implementation, the chip may further include a memory storing instructions, and the processor is used to execute the instructions stored in the memory. When the instructions are executed, the processor is used to perform the method in the first aspect and any implementation thereof.

[0038] In a sixth aspect, a computer program product containing instructions is provided, which, when executed by a computing device, cause the computing device to perform the methods described in the first aspect and any implementation thereof.

[0039] In a seventh aspect, a computer program product containing instructions is provided, which, when run by a cluster of computing devices, cause the cluster of computing devices to perform the methods described in the first aspect and any implementation thereof.

[0040] Eighthly, a computer-readable storage medium is provided, including computer program instructions that, when executed by a computing device, perform the method as described in the first aspect and any implementation thereof.

[0041] As examples, these computer-readable storage devices include, but are not limited to, one or more of the following: read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), flash memory, electrically EPROM (EEPROM), and hard drive.

[0042] Alternatively, as one implementation method, the aforementioned storage medium can specifically be a non-volatile storage medium.

[0043] A ninth aspect provides a computer-readable storage medium including computer program instructions that, when executed by a cluster of computing devices, perform the method as described in the first aspect and any implementation thereof.

[0044] As examples, these computer-readable storage devices include, but are not limited to, one or more of the following: read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), flash memory, electrically EPROM (EEPROM), and hard drive.

[0045] Alternatively, as one implementation method, the aforementioned storage medium can specifically be a non-volatile storage medium.

[0046] In a tenth aspect, a computing device cluster is provided, including at least one computing device, each computing device including a processor and a memory, wherein the processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device to cause the computing device cluster to perform the method as described in the first aspect and any implementation thereof. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the reinforcement learning training process.

[0048] Figure 2 This is a schematic diagram of the architecture 200 of the virtual object generation system applicable to embodiments of this application.

[0049] Figure 3 This is a schematic diagram of the architecture 300 of the virtual object generation system applicable to embodiments of this application.

[0050] Figure 4 This is a schematic diagram of a virtual object generation method 400 applicable to embodiments of this application.

[0051] Figure 5 This is a schematic diagram of a method 500 for generating virtual objects applicable to embodiments of this application.

[0052] Figure 6 This is a flowchart 600 for digital human generation applicable to embodiments of this application.

[0053] Figure 7 This is a schematic block diagram of a virtual object generation device 700 provided in an embodiment of this application.

[0054] Figure 8 This is a schematic diagram of the architecture of a computing device 800 provided in an embodiment of this application.

[0055] Figure 9 This is a schematic diagram of the architecture of a computing device cluster provided in an embodiment of this application.

[0056] Figure 10 This is a schematic diagram showing the connection between computing devices 800A and 800B via a network according to an embodiment of this application. Detailed Implementation

[0057] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0058] Artificial intelligence (AI) is the theory, methods, technology, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to have perception, reasoning, and decision-making capabilities. Research in the field of AI includes robotics, natural language processing, computer vision, decision-making and reasoning, human-computer interaction, recommendation and search, and fundamental AI theories.

[0059] The basic principle of AI is to combine massive amounts of data with powerful computing capabilities and intelligent algorithms to build an AI model that solves specific problems. This AI model can automatically summarize and learn potential patterns or features from the data, thereby achieving a way of thinking that is close to that of humans.

[0060] AI models, also known as AI algorithms (or AI operators), are a collective term for mathematical algorithms built upon the principles of artificial intelligence. They form the foundation for using AI to solve specific problems. Depending on the specific methods and / or technologies used to implement artificial intelligence, AI models can also be called machine learning models, deep learning models, or reinforcement learning models.

[0061] To facilitate understanding of the embodiments of this application, the terms involved in this application will be briefly explained first.

[0062] It should be understood that the related conceptual explanations may be limited by the specific circumstances of the embodiments of this application, but it does not mean that this application can only be limited to the specific circumstances. The specific circumstances of different embodiments may also differ, which are not limited here.

[0063] 1. Neural Networks

[0064] A neural network is a model that can be composed of neural units, which can refer to units like X. s The arithmetic unit takes an intercept of 1 as input, and its output can be:

[0065]

[0066] Where s = 1, 2, ..., n, n is a natural number greater than 1, W s For X s The weights are denoted by b, where b is the bias of the neural unit. f is the activation function of the neural unit, used to introduce nonlinear characteristics into the neural network, converting the input signal in the neural unit into an output signal. The output signal of this activation function can be used as the input to the next convolutional layer. The activation function can be a ReLU function. A neural network is a network formed by connecting multiple of the above-mentioned individual neural units together; that is, the output of one neural unit can be the input of another neural unit. The input of each neural unit can be connected to the local receptive field of the previous layer, thereby extracting the features of the local receptive field, where the local receptive field can be a region composed of several neural units.

[0067] Based on the above, a neural network can be specifically understood as a network composed of neurons, with input layers, hidden layers, and output layers. Generally, the first layer is the input layer, the last layer is the output layer, and the layers in between are hidden layers. The input to a neural network module can be a single frame of image or an image sequence. A neural network with many hidden layers is called a deep neural network (DNN). The operation of each layer in a neural network can be expressed using mathematical expressions. To describe it, from a physical perspective, the work of each layer in a neural network can be understood as transforming the input space (the set of input vectors) to the output space (i.e., from the row space to the column space of a matrix) through five operations on the input space. These five operations include: 1. Dimensionality increase / decrease; 2. Magnification / scaling; 3. Rotation; 4. Translation; 5. "Bending". Operations 1, 2, and 3 are performed by [a], operation 4 is performed by "+b", and operation 5 is performed by "a()". The reason for using the word "space" is that the object being classified is not a single thing, but a class of things, and space refers to the set of all individuals of this class of things. Here, W is the weight matrix of each layer of the neural network, and each value in this matrix represents the weight value of a neuron in that layer. This matrix W determines the spatial transformation from the input space to the output space mentioned above, that is, W of each layer of the neural network controls how the space is transformed. The purpose of training a neural network is to finally obtain the weight matrices of all layers of the trained neural network. Therefore, the training process of a neural network is essentially learning how to control the spatial transformation, more specifically, learning the weight matrix.

[0068] 2. Large Model

[0069] Large models are used to provide large-scale model services. A large model refers to a neural network model containing an extremely large number of parameters. Large models can also be called foundation models. Large models play a crucial role in many fields and applications, with common applications including natural language processing, computer vision, speech recognition and synthesis, recommender systems, financial risk control, intelligent dialogue systems, games, artificial intelligence, and healthcare. In the future, large models will evolve towards multimodal models, which can handle data from multiple modalities; for example, multimodal large models can process natural language as well as text, images, or videos.

[0070] Large language models (LLMs) are a type of large-scale model, specifically neural network models with a large number of parameters trained on vast corpora of text. They are capable of understanding and generating natural language text. Specifically, LLMs are typically based on neural network techniques, learning the syntax, semantics, and contextual information of a language through training on large amounts of text data. During training, the model continuously optimizes its parameters to improve its text understanding and generation capabilities. Due to their powerful ability to understand natural language, LLMs have been widely applied in many fields to solve natural language understanding and generation problems. They have broad applications in artificial intelligence, such as natural language processing, machine translation, and dialogue systems.

[0071] 3. Prompt

[0072] Prompt is an interaction method based on natural language processing. It enables communication between users and machines by parsing natural language. The main implementation of prompt is to convert natural language into machine-recognizable instructions by building a corresponding corpus and semantic parsing model. Prompt can generate finer-grained tasks by piecing together prompts from the original text based on context, thought processes, or cue words, guiding larger models to better complete tasks.

[0073] The design principles of prompts include: writing clear and specific instructions, and giving the model time to think.

[0074] The key design elements of a prompt include: Instruction, Context, Constraint, Example, and Input. Instruction provides the task instructions and states the specific goals. Context allows the AI ​​(or large model) to understand the task from the user's perspective and provides context around the task. Constraint specifies the steps to complete the task (e.g., a chain of thought, COT), clearly defines the language style, and specifies the output template. Example provides concrete examples. It should be noted that this division of design elements in a prompt is merely an example; other division methods are not limited.

[0075] 4. Artificial Intelligence Agent (AI Agent)

[0076] An AI Agent is an intelligent entity capable of perceiving its environment, making decisions, and executing actions. Typically based on machine learning and artificial intelligence technologies, it possesses autonomy and adaptability, enabling it to learn and improve autonomously in specific tasks or domains. AI Agents can not only quickly search for relevant information based on user needs but also leverage their learning capabilities to provide increasingly personalized and thoughtful solutions. In an LLM-based autonomous agent system (LLM Agent), the LLM acts as the agent's brain, collaborating with several key components. Specifically, the task execution process of an LLM Agent can include planning, memory, tool use, and action.

[0077] (1) Planning

[0078] Sub-goal decomposition: The agent breaks down large tasks into smaller, manageable sub-goals, thus enabling it to effectively handle complex tasks.

[0079] Reflection and Improvement: Agents can self-criticize and reflect on their past actions, learn from mistakes and improve in subsequent steps, thereby improving the quality of the final result.

[0080] (2) Memory

[0081] Short-term memory: Contextual learning is short-term memory learning that utilizes models.

[0082] Long-term memory: Provides agents with the ability to retain and recall long-term information, which can be achieved using external vector storage and retrieval.

[0083] (3) Tool usage

[0084] For information about missing model weights, the agent learns to call external APIs to obtain additional information, including current information, code execution capabilities, and access to proprietary information sources.

[0085] (4) Action

[0086] The action module is the part of the intelligent agent that actually executes decisions or responses. Faced with different tasks, the intelligent agent system has a complete set of action strategies, allowing it to select the actions to be performed during decision-making. Examples include memory retrieval, reasoning, learning, and programming.

[0087] 5. Reinforcement learning (RL)

[0088] RL, also known as reinforcement learning, evaluative learning, or enhancement learning, is used to describe and solve the problem of agents learning strategies to maximize rewards or achieve specific goals during their interactions with the environment.

[0089] Reinforcement learning is a learning process where an agent learns through trial and error. Rewards obtained from interactions with the environment guide behavior, with the goal of maximizing the agent's reward. Reinforcement learning does not require a training dataset. Instead of telling the reinforcement learning system how to produce the correct action, the reinforcement signals (rewards) provided by the environment evaluate the quality of the action. Because the external environment provides limited information, the agent must learn through its own experience. In this way, the agent acquires knowledge in the action-reward environment and improves its actions to adapt to the environment.

[0090] Figure 1 This is a schematic diagram of the reinforcement learning training process.

[0091] like Figure 1 As shown, reinforcement learning mainly includes four elements: agent, environment, state, action, and reward. The agent's input is the state, and its output is the action.

[0092] In current technology, the training process of reinforcement learning is as follows: the agent interacts with the environment multiple times to obtain the action, state, and reward of each interaction; these multiple sets of information (action, state, reward) are used as training data to train the agent once. This process is repeated for the next round of training until the convergence condition is met.

[0093] The process of obtaining the action, state, and reward of an interaction is as follows: Figure 1 As shown, the current state s(t) of the environment is input to the agent to obtain the action a(t) output by the agent. The reward r(t) for this interaction is calculated based on the relevant performance indicators of the environment under the action a(t). Thus, the action a(t), state s(t), and reward r(t) for this interaction are obtained. The action a(t), state s(t), and reward r(t) of this interaction are recorded for subsequent training of the agent. The next state s(t+1) of the environment under the action a(t) is also recorded to enable the next interaction between the agent and the environment.

[0094] In this context, an intelligent agent is an entity capable of thought and interaction with its environment. For example, an intelligent agent can be a computer system or part of a computer system within a specific environment. Based on its own perception of the environment, following existing instructions or through autonomous learning, and by communicating and collaborating with other intelligent agents, an intelligent agent can autonomously complete set goals within its environment. An intelligent agent can be software or a combination of software and hardware.

[0095] 6. Multimodal technology

[0096] Multimodal technology, as a subfield of AI, is used to process multiple types of data simultaneously; different data types can be considered different modalities. For example, multimodal data can include text, images, audio, video, and sensor data. Multimodal technology aims to better understand and interpret the complex real world, providing users with richer and more comprehensive information.

[0097] 7. Digital Human Technology

[0098] A digital human is a virtual character with a digitized appearance. It exists in the non-physical world, requires computer creation and use, and possesses multiple human characteristics (e.g., physical features, human performance abilities, and interactive abilities). Driven by digital technology, digital humans can exhibit human-like behavior, including language, facial expressions, and movements. For example, AIGC technology can simulate human speech, facial expressions, and body movements to generate realistic virtual characters. Based on the dimension of the character's appearance, digital humans can be categorized into 2D cartoon digital humans, 2D realistic digital humans, 3D cartoon digital humans, and 3D hyper-realistic digital humans, among others.

[0099] The relevant terms used in the embodiments of this application have been described above. The following is a description of the terms used in conjunction with the embodiments of this application. Figure 3 and Figure 4 The system architecture applicable to the embodiments of this application is described.

[0100] Figure 2 This is a schematic diagram of the architecture 200 of the virtual object generation system applicable to embodiments of this application.

[0101] like Figure 2 As shown, the data acquisition device 260 is used to collect training data and store the training data in the database 230. The training device 220 trains the target model / rule 201 based on the training data maintained in the database 230.

[0102] It should be noted that the data acquisition device 260, the execution device 210, and the training device 220 may be the same or different devices.

[0103] The following describes in more detail how the training device 220 obtains a target model / rule 201 based on training data, which can be used to implement the image processing method provided in the embodiments of this application.

[0104] It should be noted that, in practical applications, the training data maintained in the database 230 can come from the data acquisition device 260 or other devices. The training device 220 does not necessarily train the target model / rule 201 entirely based on the training data maintained in the database 230; it can also obtain training data from the cloud or other sources for model training. The above description should not be construed as limiting the embodiments of this application. The target model / rule 201 trained by the training device 220 can be applied to different systems or devices, for example, applied to... Figure 2 The execution device 210 shown.

[0105] It should be understood that the execution device 210 may be a terminal. Exemplarily, the terminal may be, for example, a digital camera, surveillance camera, mobile phone, personal computer (PC), laptop computer, server, tablet computer, smart TV, in-vehicle terminal, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, etc., or it may be an edge device (e.g., a box carrying a chip with processing capabilities); the execution device 210 may also be a server or cloud, etc.

[0106] The execution device 210 is equipped with an I / O interface 212 for data interaction with external devices. Users can input data into the I / O interface 212 through the client device 240. Furthermore, the input data can be user-inputted data, data uploaded by the user through a camera, or data from a database; this application does not impose any limitations on these aspects.

[0107] As one possible embodiment, execution device 210 and training device 220 are different processors deployed on different physical devices (e.g., servers in a server or cluster). For example, execution device 210 may be a graphics processing unit (GPU), a central processing unit (CPU), other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors may be microprocessors or any conventional processor. Training device 220 may be a graphics processing unit (GPU), a neural network processing unit (NPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program according to this application. Training device 220 can configure the trained neural network to multiple execution devices 210. Each execution device 210 utilizes the trained neural network to implement functions such as super-resolution reconstruction.

[0108] In another possible embodiment, the execution device 210 and the training device 220 are deployed on the same physical device, or the execution device 210 and the training device 220 are on the same physical device. The computing device can configure the trained neural network to itself and use the trained neural network to achieve functions such as super-resolution reconstruction.

[0109] Training device 220 is used to train a neural network using training data until the loss function in the neural network converges and its value is less than a certain threshold, at which point the neural network training is complete, thus achieving a certain level of accuracy. Alternatively, all training data in database 230 can be used for training, completing the neural network training and enabling it to perform functions such as super-resolution reconstruction. Then, training device 220 configures the trained neural network to execution device 210. Execution device 210 is used to process application data based on the trained neural network.

[0110] The preprocessing module 213 is used to preprocess the input data received by the I / O interface 212. During the preprocessing of input data by the execution device 210, or during the calculation module 211 of the execution device 210 performing calculations or other related processing, the execution device 210 can call data, code, etc., from the data storage system 250 for corresponding processing, and can also store the processed data, instructions, etc., into the data storage system 250. Finally, the I / O interface 212 returns the processing result to the client device 240, thereby providing it to the user.

[0111] It should be understood that Figure 2 This is merely a schematic diagram of a system architecture. The positional relationships between the devices, components, modules, etc., shown in the diagram do not constitute any limitation. For example, in Figure 2 In this context, the data storage system 250 is an external memory relative to the execution device 210. In other cases, the data storage system 250 may also be placed within the execution device 210.

[0112] Figure 3 This is a schematic diagram of the architecture 300 of the virtual object generation system applicable to embodiments of this application.

[0113] like Figure 3 As shown, architecture 300 includes a model layer, an agent layer, and a user layer. The model layer may include an LLM and at least one functional model; the agent layer may include at least one AI agent and at least one functional agent; and the user layer is used to implement information interaction between the user and agent layers and between the user and model layers.

[0114] In the requirement generation phase, user requirements can be obtained through the user layer, and the final requirements are determined through the interaction of the user layer, agent layer, and model layer. In the requirement decomposition and virtual object generation phase, requirements can be decomposed through the model layer and agent layer, and the final virtual object is generated through the model layer.

[0115] It should be understood that the system architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0116] With the development of AI technology, virtual object generation technology has become increasingly mature and popular in recent years. Taking digital human generation technology as an example, the platform services provided by digital human manufacturers can support users to generate virtual characters using various forms of input. The platform-side digital human generation solutions mainly include the following two types:

[0117] (1) Users upload voice recordings, select pre-made models / upload videos, and the interface selects human body information such as clothing, hair, and skin color to generate digital human videos with movements and the ability to speak. The disadvantage of this solution is that the user operation steps are fixed and cumbersome, the degree of operational freedom is low, and the types of digital humans generated are limited.

[0118] (2) Users control the generation of digital humans through dialogue using natural language, including generated speech, lip movements, actions, clothing, hair, skin color, and other information. Based on this approach, users can interact with the system using only natural language to generate the desired digital human. The system uses a language model to parse the user's natural language and, after parsing the user's commands, the generation of the digital human is completed by calling specialized models (e.g., a clothing model generates clothing, a lip movement model handles lip movements, an action model generates actions, and a speech model parses speech). The final generation of the digital human is completed by combining the results of multiple models. The drawback of this approach is that the quality of the generated digital human strictly depends on the accuracy of the user interface input. It is impossible to control the generation of detailed elements of the digital human at the user level, resulting in weak controllability of the digital human generation process. Calling a general model to generate the digital human cannot guarantee the desired effect.

[0119] For example, a user requests a blue-skinned digit being generated, which is clearly not a reasonable digit being imaged. The digit being model has not learned from the experience of blue-skinned digits, resulting in poor generation quality. Another example is that users cannot control whether speech generation is needed, and if not specified in the prompt, the type of speech generated cannot be controlled, making the speech generation process uncontrollable. Yet another example is that a user wants a digit being generated wearing ethnic minority clothing, but because only a general clothing-changing model can be used, the generated effect is poor.

[0120] As can be seen from the above, in the current multimodal conversational digital human generation system, users can use only natural language to interact with the system to generate the desired digital human. The LLM parses the user's natural language and, after parsing the user's commands, the digital human generation task is completed by calling proprietary models and combining the results of multiple proprietary models to complete the final generation of the digital human.

[0121] In this scenario, the generation of virtual objects is based on a generic model, resulting in uncontrollable outcomes and poor object quality. Furthermore, the generation of virtual objects depends on user-level input; inappropriate input leads to the generation of unsuitable virtual objects, further reducing their quality. Additionally, because the user cannot control the generation of detailed elements within the virtual object, the generation process itself has limited controllability.

[0122] In view of this, this application proposes a method for generating virtual objects, which can achieve accurate model invocation, thereby improving the quality of generated virtual objects. Furthermore, during the virtual object generation process, the generation requirements can be optimized through requirement rationality judgment, further improving the quality of generated virtual objects.

[0123] The technical solution provided in this application will be described in detail below with reference to the accompanying drawings.

[0124] Figure 4 This is a schematic diagram of a virtual object generation method 400 applicable to embodiments of this application.

[0125] It should be understood that Figure 4 The steps or operations of the method for generating the virtual object are illustrated, but these steps or operations are merely to help those skilled in the art understand the embodiments of this application, and are not intended to limit the embodiments of the application to... Figure 4 The specific numerical values ​​or specific scenarios illustrated. Those skilled in the art will understand based on... Figure 4 The examples given below can obviously be modified or varied in various ways, and such modifications and variations also fall within the scope of the embodiments of this application. The embodiments of this application can also perform other operations or... Figure 4 Variations of various operations within it.

[0126] It should be understood that the embodiments shown below do not particularly limit the specific structure of the execution subject of the method provided in the embodiments of this application. As long as a program containing the code of the method provided in the embodiments of this application can be run to generate virtual objects according to the method provided in the embodiments of this application, it is acceptable. For example, the method provided in the embodiments of this application can be executed by a processing device, which can be... Figure 2 The execution device in the text can also be a component of the execution device (e.g., a processor, chip, or chip system). This execution device can be a cloud device or a terminal device (e.g., a mobile phone). Of course, the method provided in the embodiments of this application can also be executed by a system that includes both cloud devices and terminal devices.

[0127] Optionally, the method can be processed by the CPU in the execution device, or by both the CPU and GPU, or it can be processed without a GPU, using other processors suitable for neural network computing. This application does not impose any restrictions.

[0128] like Figure 4 As shown, method 400 may include the following steps:

[0129] S401: Obtain user requirements.

[0130] Optionally, the user requirements are proposed by the user directly or indirectly for generating the first virtual object. For example, the user requirements can be directly input by the user, or they can be the result of processing the user's input requirements; this application does not limit this.

[0131] S402: Determine the generation requirements based on the user requirements, the generation requirements being used to generate virtual objects.

[0132] It should be understood that the user requirements may be the same as or different from the generation requirements. Therefore, the first virtual object may be the same as or different from the virtual object. This application does not impose any limitations in this regard.

[0133] Optionally, determining the generation requirements based on the user requirements includes: determining the generation requirements using a Large Language Model (LLM) and a virtual object knowledge base based on the user requirements.

[0134] It should be noted that LLM is a general model with general knowledge, but it may not have specific knowledge (e.g., knowledge about virtual objects). Therefore, specific knowledge can be added to LLM by attaching specific knowledge (e.g., a virtual object knowledge base), so that LLM does not need to be retrained.

[0135] In this case, the rationality of user requirements can be further assessed through LLM and virtual object knowledge bases to determine the final generation requirements.

[0136] For example, step S402 can be implemented based on a smart agent. Specifically, the smart agent can utilize prior knowledge from the virtual object knowledge base, invoke the LLM to filter and correct user requests, and return the corrected requests to the user.

[0137] Optionally, the user requirement includes a first feature; determining the generation requirement based on the user requirement includes: outputting a correction prompt when the virtual object knowledge base does not include the first feature, the correction prompt being used to suggest modifying the first feature to a second feature, wherein the second feature is a feature included in the virtual object knowledge base; obtaining a confirmation message for the correction prompt; and determining the generation requirement based on the confirmation message for the correction prompt, wherein the generation requirement includes the second feature.

[0138] In this scenario, when the virtual object knowledge base does not include the first feature, it indicates that the virtual object involved in the user's request is not within the scope of prior knowledge, and the user's request is considered "unreasonable." Therefore, the user can be instructed to correct their request based on the content of the virtual object knowledge base, resulting in a generated request. Since the second feature involved in the generated request is within the virtual object knowledge base, the generated request is considered "reasonable." Thus, the above solution can improve the reasonableness of the request, thereby improving the quality of virtual object generation.

[0139] It should be noted that the steps described above for determining "reasonable generation requirements" can be performed at least once. In other words, method 400 can also interact with the user multiple times based on user needs to ensure the reasonableness of the generation requirements.

[0140] Optionally, determining the generation requirement based on the user's requirements includes: outputting a selection prompt, the selection prompt being used to prompt the selection of a third feature, wherein the third feature is a feature included in the virtual object knowledge base but not included in the user's requirements; obtaining a confirmation message for the selection prompt; and determining the generation requirement based on the confirmation message for the selection prompt, wherein the generation requirement includes the third feature.

[0141] In this case, user requirements can be supplemented based on the virtual object knowledge base, prompting users to add reasonable features and enrich the content of the generation requirements, so that the final generated virtual object has higher quality.

[0142] It should be noted that the steps described above for determining "supplementary generation requirements" can be performed at least once. In other words, method 400 can also interact with the user multiple times based on user needs to expand those needs and obtain generation requirements with richer content.

[0143] S403: Decompose the generated requirements into at least one subtask, each of the at least one subtask corresponding to a requirement domain, and each requirement domain including at least one requirement function.

[0144] For example, step S403 can be implemented based on a smart agent and an LLM. Specifically, the smart agent can be used to instruct the LLM to decompose the generation requirements into at least one subtask, and to perform subtask decomposition based on the decomposed subtask guidance function agent.

[0145] Optionally, the requirement domains and requirement functions are implemented based on a multi-layered architecture. That is, the characteristics of virtual objects can be classified and layered according to different domains (or dimensions), and each domain can be further divided into multi-layered structures corresponding to different requirement functions. For example, the mapping relationship between the requirement domains and requirement functions can be determined based on an Agent (or the mapping relationship between the requirement domains and requirement functions can be stored through an Agent); or the mapping relationship between the requirement domains and requirement functions can be determined based on a list (or the mapping relationship between the requirement domains and requirement functions can be stored through a list), or the mapping relationship between the requirement domains and requirement functions can be determined in other ways, which are not limited in this embodiment.

[0146] For example, in a scenario of digital human generation, the demand domain can be the different dimensions of features that constitute the digital human image. For instance, the demand domain could include: actions, skin color, voice, and / or clothing. The demand functions can be the subdivided features that constitute each demand domain. For example, the demand functions corresponding to "actions" in the demand domain could include: running, dancing, and / or walking; the demand functions corresponding to "skin color" could include: yellow skin, white skin, and / or black skin; the demand functions corresponding to "voice" could include: Chinese voice and / or English voice; and the demand functions corresponding to "clothing" could include: men's clothing and / or women's clothing.

[0147] It should be noted that the embodiments of this application do not limit the number of layers in the multi-layer architecture. For example, the required function "men's clothing" may further include required functions such as shirts, T-shirts, and / or trousers; the required function "women's clothing" may further include required functions such as dresses and / or skirts.

[0148] It should be understood that the above examples are only used to illustrate the scenario of digital human generation and do not constitute a limitation on the content of virtual objects. For example, virtual objects applicable to this application can also be virtual plants or virtual items, etc., and this application does not limit them.

[0149] Optionally, the mapping relationship between the requirement domain and the requirement function can be obtained by training a virtual object knowledge base.

[0150] Optionally, before decomposing the generation requirement into at least one subtask, the method further includes: outputting a confirmation prompt, the confirmation prompt being used to prompt confirmation of the generation requirement; and obtaining a confirmation message of the confirmation prompt.

[0151] In this scenario, users can filter the features involved in the generation requirements before generating virtual objects, thus improving the user's control over the generated virtual objects.

[0152] S404: Determine the required functions corresponding to the virtual object under at least one requirement domain.

[0153] Optionally, after determining the required functions corresponding to the generated requirements, the user can filter the required functions to ultimately determine the required functions involved in the virtual object.

[0154] For example, determining the required functions corresponding to the virtual object under at least one required domain includes: determining the required functions corresponding to the virtual object under each required domain; presenting a selection interface, the selection interface including the required functions corresponding to the virtual object under each required domain; and obtaining the required functions corresponding to the virtual object under the at least one required domain selected through the selection interface.

[0155] S405: Invoke the functional model of the requirement function corresponding to the virtual object under the at least one requirement domain to generate the virtual object.

[0156] In this context, multi-level decomposition of generation requirements based on the requirement domain and function can refine the generation requirements, ensure accurate model invocation, and thus generate more accurate and higher-quality virtual objects.

[0157] Figure 5 This is a schematic diagram of a method 500 for generating virtual objects applicable to embodiments of this application.

[0158] It should be noted that the embodiments of this application use a digital human as an example for illustration, which does not constitute a limitation on the content of the virtual object. For example, the virtual object applicable to this application can also be a virtual animal or plant or a virtual item, etc., and this application does not limit it in this regard.

[0159] like Figure 5 As shown in (a) above, method 500 may include two steps: “digital human requirement generation” and “digital human requirement decomposition and digital human generation”, which will be described in detail below.

[0160] Step 1: Digital Human Requirements Generation

[0161] like Figure 5 As shown in (b), the "digital human requirements generation" step involves interaction between the user layer, the agent layer, and the model layer. The user layer may include a user dialog box 510, the agent layer may include an intelligent agent 520 and a digital human knowledge base 521, and the model layer may include...

[0162] User dialog box 510: Used to obtain user needs and realize information interaction between the digital human generation system and the user. It should be understood that the specific form of the user dialog box 510 is not limited in this application embodiment, that is, the user can realize information interaction with the Agent layer and the Model layer through text, voice or other means based on the user dialog box 510.

[0163] Intelligent Agent 520: Intelligent Agent 520 can utilize the prior knowledge of the digital human knowledge base 521, call LLM 530 to filter and correct user requirements, and return the corrected requirements to the user through the user dialog box 510.

[0164] It should be noted that after the user dialog box 510 obtains the user's original requirements, the user dialog box 510, the intelligent agent 520, and the LLM 530 can generate the final requirements through multiple iterations.

[0165] Digital Human Knowledge Base 521: Includes knowledge related to digital humans as prior information to assist LLM 530 in judging whether user needs are reasonable, ensuring that users put forward accurate and reasonable digital human generation requirements.

[0166] For example, the digital human knowledge base 521 includes the actions, appearance, skin color and other human characteristics that a "reasonable digital human" should have, and the LLM 530 can determine whether the user's needs are reasonable based on the prior knowledge in the digital human knowledge base 521.

[0167] LLM530: Used to parse user requests submitted in natural language. It should be understood that the specific process of LLM parsing natural language can be found in existing technical descriptions, and will not be elaborated upon here.

[0168] It should be understood that "digital human requirement generation" is used to guide users to generate accurate and reasonable digital human generation requirements. The intelligent agent 520 can interact with users in both directions, and the LLM 530 can also be used to correct users' digital human generation requirements and ultimately generate reasonable requirements.

[0169] In one possible implementation, after the user dialog box 510 obtains the user's original requirement (requirement #1), it passes requirement #1 to the intelligent agent 520. The intelligent agent 520 uses the LLM 530 to understand the content of requirement #1. Specifically, the LLM 530 parses requirement #1, and can further determine the rationality of requirement #1 based on the prior information of the digital human knowledge base 521 (i.e., whether the digital human to be generated by requirement #1 belongs to the scope of the digital human knowledge base 521).

[0170] Optionally, when LLM 530 determines that requirement #1 is unreasonable, it can correct requirement #1 based on prior information to obtain requirement #2, and return requirement #2 to the user through intelligent agent 520 and user dialog box 510. It should be noted that the above process can be repeated multiple times. This embodiment does not limit the number of interactions between user dialog box 510, intelligent agent 520, digital human knowledge base 521, and LLM 530, as long as the final generated requirement (requirement #n) is reasonable. That is, the user can also determine a new requirement #3 based on requirement #2, and then user dialog box 510 can pass requirement #3 to intelligent agent 520, which further utilizes LLM 530 to understand the content of requirement #3. The above scheme can ensure the rationality of the final generated requirement and solve the problem of uncontrollable generation results due to unclear user-side requirements.

[0171] Optionally, when LLM 530 determines that requirement #1 is a reasonable requirement, it can also return the determination result to the intelligent agent 520 and present the relevant content of requirement #1 to the user through the user layer so that the user can further confirm or update requirement #1.

[0172] Optionally, users can be presented with other characteristics that a “reasonable digital human” can possess as prompts through LLM 530, digital human knowledge base 521 and intelligent agent 520 to enrich the final generation requirements.

[0173] Step Two: Decomposition of Digital Human Needs and Generation of Digital Humans

[0174] like Figure 5 As shown in (c), the "Digital Human Requirements Decomposition and Digital Human Generation" step also involves the interaction between the user layer, the agent layer, and the model layer. The user layer may include a functional interface 511, the agent layer may include an intelligent agent 520 and a functional agent 522, and the model layer may include an LLM 530 and a functional model 531.

[0175] It should be understood that "Digital Human Requirements Decomposition and Digital Human Generation" is used to decompose the generation requirements of digital humans and generate corresponding digital humans based on the decomposed generation requirements. Specifically, LLM 530 and Function Agent 522 are used to decompose the requirements layer by layer, thereby achieving requirement decoupling and generating higher quality digital humans.

[0176] Intelligent Agent 520: It can also be used to instruct LLM 530 to decompose the final requirements of digital human generation generated in step one, to obtain at least one sub-task, and to decompose the sub-task based on the decomposed sub-task guidance function Agent 522.

[0177] LLM 530: It is also used to receive instructions sent by the intelligent agent 520, and return the final requirements to the intelligent agent 520 after decomposing them into multiple sub-tasks according to the instructions.

[0178] Functional Agent 522: Functional Agent 522 is implemented based on a multi-layered agent architecture and can be composed of at least one functional agent module. Specifically, functional agent 522 classifies and layers the characteristics of the digital human according to different dimensions (or domains), thereby further decomposing the sub-tasks indicated by intelligent agent 520, determining the underlying functional agents involved in generating the digital human required for the final demand, and thus calling the corresponding functional model 531.

[0179] It should be noted that the specific structure of the functional Agent 522 can be obtained by training based on the digital human knowledge base 521.

[0180] Optionally, the functional model 531 may have at least one layer structure. In this embodiment, the number of layers of the functional model 531 is not limited.

[0181] For example, when the digital human knowledge base 521 includes information about people running, dancing, speaking Chinese, wearing men's clothing, and wearing women's clothing, the functional agent 522 trained based on the digital human knowledge base 521 can have a two-layer structure, including: a clothing agent, an action agent, and a voice agent. The clothing agent includes a men's clothing agent and a women's clothing agent; the action agent includes a dance agent and a running agent; and the voice agent includes a Chinese voice agent.

[0182] Functional model 531: Used to invoke the corresponding model to generate a digital human based on the instructions of functional agent 522. Functional model 531 may include at least one functional model, which corresponds to the underlying functional agent in functional agent 522.

[0183] For example, corresponding to the men's clothing agent, women's clothing agent, dance agent, running agent and Chinese voice agent mentioned above, the functional model 531 may include a men's clothing model, a women's clothing model, a dance model, a running model and a Chinese voice model.

[0184] Functional interface 511: used to present to the user the underlying functional agent obtained by decomposing the sub-tasks indicated by the intelligent agent 520 into functional agent 522, and the user can further filter the underlying functional agent to generate the final digital human.

[0185] In one possible implementation, after obtaining the user's final requirement (requirement #n), the intelligent agent 520 sends an instruction to the LLM 530 to decompose requirement #n. Upon receiving the instruction, the LLM 530 decomposes requirement #n into multiple subtasks and returns the decomposition results to the intelligent agent 520. After receiving the subtasks derived from the decomposition of requirement #n, the intelligent agent 520 instructs the functional agent 522 to further decompose the subtasks to determine the underlying functional agents involved in requirement #n. Compared to existing solutions that directly call the corresponding model based on LLM decomposition, further decomposing the requirement through the functional agent 531 and then using the decomposition results of the functional agent 531 to function the model 531 improves the accuracy of model selection and significantly enhances the quality of the generated digital human.

[0186] Optionally, the functional agent 522 can present the underlying functional agents related to the requirement #n to the user through the functional interface 511. The user can further filter the underlying functional agents to determine the underlying functional agents involved in the final generated digital human, thereby effectively improving the user's controllability over the digital human generation result.

[0187] It should be understood that after determining the underlying functional agent involved in the final generated digital human, functional agent 522 calls the corresponding functional model 531 to generate the digital human and presents the final generation result at the user level.

[0188] Figure 6 This is a flowchart 600 for digital human generation applicable to embodiments of this application.

[0189] For ease of understanding, only... Figure 6The digital human generation system shown is used as an example for illustration. The digital human knowledge base includes information such as people with white skin, yellow skin, black skin, dancers, runners, Chinese speakers, people wearing short skirts, and people wearing dresses. Functional agents trained based on this knowledge base include skin color agents, clothing agents, action agents, and voice agents. Specifically, skin color agents include white skin agents, yellow skin agents, and black skin agents; clothing agents include dress agents and short skirt agents; action agents include dance agents and running agents; and voice agents include Chinese voice agents. Correspondingly, functional models include white skin models, yellow skin models, black skin models, dress models, short skirt models, dance models, running models, and Chinese voice models. It should be understood that the content of the digital human knowledge base, the composition of the functional agents, and the composition of the functional models described above are only for the purpose of more clearly describing the digital human generation process and do not constitute a limitation on the embodiments of this application. In the technical solution of this application, the digital human knowledge base may also contain more information, and correspondingly, the functional agents and functional models may also include more content.

[0190] like Figure 6 As shown, the user's original requirement was: "Generate a digital human with orange skin dancing."

[0191] During the digital human requirement generation phase, since the prior information in the digital human knowledge base does not include content related to orange skin, the LLM will determine the original requirement as "unreasonable" based on the prior information in the digital human knowledge base and return the judgment result to the intelligent agent. The intelligent agent calls the LLM to correct the original requirement and then provides feedback to the user through a user dialog box: "Orange skin is not human skin. Do you want to generate a yellow-skinned digital human?"

[0192] After the user updates their requirements based on the feedback (e.g., to generate a yellow-skinned digital human), the intelligent agent can further confirm with the user, based on information from the digital human knowledge base, whether it is "women's clothing or men's clothing", "dress or short skirt" and "whether to use Chinese voice", etc. After multiple interactions between the user and the digital human generation system, the digital human generation requirement is confirmed as: "Please generate a girl with yellow skin, Chinese voice, dancing and wearing a short skirt".

[0193] In the digital human requirement decomposition and digital human generation stages, through LLM decomposition, the digital human generation requirements involve skin color agent, motion agent, voice agent, and clothing agent in the functional agents. Through the decomposition of functional agents, the digital human generation requirements involve yellow skin agent, dancing agent, Chinese voice agent, and short skirt agent in the underlying functional agents. The functional agents can further confirm the requirements with the user through the functional interface. That is, the user can filter the results of the functional agent decomposition to obtain the final digital human generation requirements (for example, the functional agent presents the decomposed agents to the user through the functional interface, including yellow skin agent, dancing agent, Chinese voice agent, and short skirt agent. After the user filters, the Chinese voice agent is removed, so the final digital human generation requirements only involve yellow skin agent, dancing agent, and short skirt agent). After confirming the final digital human generation requirements, the functional agents call the corresponding functional models (e.g., short skirt model, dancing model, and yellow skin model) to generate the final digital human image and present the generated result to the user layer.

[0194] To facilitate understanding of the above embodiments provided in this application, the following points are made.

[0195] (1) In the embodiments of this application, "instruction" may include direct instruction, indirect instruction, explicit instruction, and implicit instruction. When describing a certain instruction information for the purpose of indicating A, it can be understood that the instruction information carries A, directly indicates A, or indirectly indicates A.

[0196] In this application, the information indicated by the instruction information is called the information to be instructed. In specific implementations, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly indicate the information to be instructed by indicating other information, where there is a relationship between the other information and the information to be instructed. It can also indicate only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. Furthermore, the information to be instructed can be sent as a whole or divided into multiple sub-information pieces, and the sending period and / or timing of these sub-information pieces can be the same or different.

[0197] (2) In this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which may include direct transmission via the air interface or indirect transmission via the air interface by other units or modules. "Receive information from YY" can be understood as the source of the information being YY, which may include direct reception from YY via the air interface or indirect reception from YY via the air interface by other units or modules. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface. In other words, sending and receiving can occur between devices, such as between network devices and terminal devices, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via a bus, wiring, or interface.

[0198] (3) In the various embodiments of this application, unless otherwise specified or logically conflicting, the terms and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0199] (4) In this application, "first" and "second" are used for descriptive convenience only to distinguish objects and are not intended to limit the scope of the embodiments of this application. They are not used to describe the order or sequence of features. It should be understood that the objects described in this way can be interchanged where appropriate so as to describe solutions other than those in the embodiments of this application.

[0200] (5) In this application, “predefined” can be achieved by pre-storing the corresponding code, table or other means that can be used to indicate relevant information in the device. This application does not limit the specific implementation method.

[0201] (6) In this application, the words “exemplary,” “for example,” “exemplary,” “as another example,” etc., are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design that is described as an “exemplary” in this application should not be construed as being more preferred or advantageous than other embodiments or designs.

[0202] (7) In this application, “comprising,” “including,” “having,” and variations thereof mean “including but not limited to,” unless otherwise specifically emphasized. “At least one” means one or more, and “more” means two or more.

[0203] (8) In this application, "and / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can mean: a, or, b, or, c, or, a and b, or, a and c, or, b and c, or, a, b, and c. Where a, b, and c can be single or multiple.

[0204] (9) In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terms and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0205] (10) Some optional features in the various embodiments of this application may not depend on other features in some scenarios, or may be combined with other features in some scenarios, without limitation.

[0206] The above text combined Figures 4 to 6 The present application describes in detail the virtual object generation method provided in the embodiments. The following will be combined with... Figures 7-10 The embodiments of the apparatus of this application are described in detail below. It should be understood that the descriptions of the method embodiments correspond to the descriptions of the apparatus embodiments; therefore, any parts not described in detail can be referred to the foregoing method embodiments.

[0207] Figure 7 This is a schematic block diagram of a virtual object generation device 700 provided in an embodiment of this application.

[0208] The device 700 can be implemented through software, hardware, or a combination of both. The device 700 provided in this application embodiment can implement the embodiments of this application. Figure 4 The method flow shown includes an interaction unit 710 and a processing unit 720.

[0209] The interaction unit 710 is used to obtain user needs.

[0210] The processing unit 720 includes an intelligent agent and a functional agent.

[0211] The intelligent agent is used to perform the following operations: determine generation requirements based on the user requirements, the generation requirements being used to generate virtual objects; decompose the generation requirements into at least one sub-task, each sub-task corresponding to a requirement domain, and each requirement domain including at least one requirement function.

[0212] The functional Agent is used to perform the following operations: determine the required functions corresponding to the virtual object under at least one requirement domain; and call the functional model of the required functions corresponding to the virtual object under the at least one requirement domain to generate the virtual object.

[0213] Optionally, the processing unit further includes a Large Language Model (LLM) and a virtual object knowledge base. Determining the generation requirements based on the user needs includes: the intelligent agent determining the generation requirements using the LLM and the virtual object knowledge base based on the user needs. Decomposing the generation requirements into at least one sub-task includes: the intelligent agent decomposing the generation requirements into at least one sub-task using the LLM.

[0214] Optionally, the user requirement includes a first feature. The interaction unit is configured to: output a correction prompt if the virtual object knowledge base does not include the first feature, the correction prompt suggesting that the first feature be modified to a second feature, wherein the second feature is a feature included in the virtual object knowledge base; and obtain a confirmation message for the correction prompt. The intelligent agent is configured to: determine the generation requirement based on the confirmation message for the correction prompt, the generation requirement including the second feature.

[0215] Optionally, the interaction unit is configured to: output a selection prompt, the selection prompt being used to suggest selecting a third feature, wherein the third feature is a feature included in the virtual object knowledge base but not included in the user requirement; and obtain a confirmation message for the selection prompt. The intelligent agent is configured to: determine the generation requirement based on the confirmation message for the selection prompt, the generation requirement including the third feature.

[0216] Optionally, the interaction unit is configured to: output a confirmation prompt, the confirmation prompt being used to prompt confirmation of the generation requirement; and obtain a confirmation message for the confirmation prompt.

[0217] Optionally, the functional agent is used to: determine the required functions corresponding to the virtual object under each requirement domain. The interaction unit is used to: present a selection interface, the selection interface including the required functions corresponding to the virtual object under each requirement domain; and obtain the required functions corresponding to the virtual object under the at least one requirement domain selected through the selection interface.

[0218] Optionally, the interaction unit is further configured to: present the virtual object.

[0219] The device 700 here can be embodied in the form of a functional module. The term "unit" here can be implemented in software and / or hardware, without specific limitations.

[0220] For example, a "unit" can be a software program, a hardware circuit, or a combination of both that implements the above functions. The units in device 700 are described in detail below.

[0221] For example, the implementation of the interaction unit 710 in device 700 will be described below. Similarly, the implementation of other units in device 700, such as processing unit 720, can refer to the implementation of interaction unit 710.

[0222] Interaction unit 710, as an example of a software functional unit, may include code running on a computing instance. The computing instance may include at least one of a physical host (computing device), a virtual machine, and a container. Further, the aforementioned computing instance may be one or more. For example, interaction unit 710 may include code running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers used to run the code may be distributed in the same region or in different regions. Further, the multiple hosts / virtual machines / containers used to run the code may be distributed in the same availability zone (AZ) or in different AZs, each AZ including one or more geographically proximate data centers. Typically, a region may include multiple AZs.

[0223] Similarly, multiple hosts / virtual machines / containers used to run this code can be distributed within the same Virtual Private Cloud (VPC) or across multiple VPCs. Typically, a VPC is set up within a region. Communication between two VPCs within the same region, as well as between VPCs in different regions, requires a communication gateway to be set up within each VPC to enable interconnection between VPCs.

[0224] The interaction unit 710, as an example of a hardware functional unit, may include at least one computing device, such as a server. Alternatively, the interaction unit 710 may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be implemented using a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), generic array logic (GAL), or any combination thereof.

[0225] The multiple computing devices included in the interaction unit 710 can be distributed in the same region or in different regions. Similarly, the multiple computing devices included in the interaction unit 710 can be distributed in the same Availability Zone (AZ) or in different AZs. Likewise, the multiple computing devices included in the interaction unit 710 can be distributed in the same Virtual Private Cloud (VPC) or in multiple VPCs. These multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0226] Therefore, the modules of the various examples described in the embodiments of this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0227] It should be noted that the above embodiments of the device 700, when executing the above methods, are only illustrative examples of the division of functional units. In practical applications, the above functions can be assigned to different functional units as needed, that is, the internal structure of the device 700 can be divided into different functional units to complete all or part of the functions described above. For example, the interaction unit 710 can be used to execute any step in the above methods, and the processing unit 720 can be used to execute any step in the above methods. The steps implemented by the interaction unit 710 and the processing unit 720 can be specified as needed, and all the functions of the device 700 can be realized by implementing different steps in the above methods through the interaction unit 710 and the processing unit 720 respectively.

[0228] Furthermore, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments above, which will not be repeated here.

[0229] The method provided in this application can be executed by a computing device, which can also be referred to as a computer system. It includes a hardware layer, an operating system layer running on top of the hardware layer, and an application layer running on the operating system layer. The hardware layer includes hardware such as processing units, memory, and memory control units; the functions and structure of this hardware will be described in detail later. The operating system can be any one or more computer operating systems that implement business processing through processes, such as Linux, Unix, Android, iOS, or Windows. The application layer includes applications such as browsers, address books, word processing software, and instant messaging software. Optionally, the computer system can be a handheld device such as a smartphone, or a terminal device such as a personal computer; this application does not particularly limit this, as long as the method provided in this application can be used. The executing entity of the method provided in this application can be a computing device, or a functional module within the computing device capable of calling and executing programs.

[0230] The following is combined with Figure 8 This application provides a detailed description of a computing device provided in an embodiment.

[0231] Figure 8 This is a schematic diagram of the architecture of a computing device 800 provided in an embodiment of this application.

[0232] The computing device 800 can be a server, a computer, or other device with computing capabilities. Figure 8 The computing device 800 shown includes at least one processor 810 and a memory 820.

[0233] It should be understood that this application does not limit the number of processors and memories in the computing device 800.

[0234] The processor 810 executes instructions in the memory 820, causing the computing device 800 to implement the method provided in this application. Alternatively, the processor 810 executes instructions in the memory 820, causing the computing device 800 to implement the various functional modules provided in this application, thereby implementing the method provided in this application.

[0235] Optionally, the computing device 800 also includes a communication interface 830. The communication interface 830 uses a transceiver module, such as, but not limited to, a network interface card or a transceiver, to enable communication between the computing device 800 and other devices or communication networks.

[0236] Optionally, the computing device 800 also includes a system bus 840, wherein the processor 810, memory 820, and communication interface 830 are respectively connected to the system bus 840. The processor 810 can access the memory 820 through the system bus 840; for example, the processor 810 can perform data read / write or code execution in the memory 820 through the system bus 840. The system bus 840 is a peripheral component interconnect express (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus 840 is divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0237] In one possible implementation, the processor 810 primarily functions to interpret the instructions (or code) of a computer program and process data within the computer software. The instructions of the computer program and the data within the computer software can be stored in memory 820 or cache 1316.

[0238] Optionally, the processor 810 may be an integrated circuit chip with signal processing capabilities. By way of example and not limitation, the processor 810 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. Among these, a general-purpose processor is a microprocessor, etc. For example, the processor 810 may be a central processing unit (CPU).

[0239] Optionally, each processor 810 includes at least one processing unit 812 and a memory control unit 814.

[0240] Optionally, the processing unit 812, also known as the core, is the most important component of the processor. The processing unit 812 is manufactured from single-crystal silicon using a specific production process. All calculations, command reception, command storage, and data processing are performed by the core. Each processing unit independently executes program instructions, utilizing parallel computing capabilities to accelerate program execution. Various processing units have fixed logical structures; for example, a processing unit includes logical units such as a Level 1 cache, a Level 2 cache, an execution unit, an instruction-level unit, and a bus interface.

[0241] In one implementation example, the memory control unit 814 controls the data interaction between the memory 820 and the processing unit 812. Specifically, the memory control unit 814 receives memory access requests from the processing unit 812 and controls access to memory based on the memory access requests. By way of example and not limitation, the memory control unit is a device such as a memory management unit (MMU).

[0242] In one implementation example, each memory control unit 814 addresses the memory 820 via the system bus. An arbitrator is configured in the system bus. Figure 8 (Not shown in the image), the arbitrator is responsible for handling and coordinating competing accesses by multiple processing units 812.

[0243] In one implementation example, the processing unit 812 and the memory control unit 814 are connected via internal chip connection lines, such as address lines, thereby enabling communication between the processing unit 812 and the memory control unit 814.

[0244] Optionally, each processor 810 also includes a cache 816, which is a buffer for data exchange (called a cache). When the processing unit 812 needs to read data, it first looks for the required data in the cache. If the data is found, it is executed directly; otherwise, it looks for the data in memory. Since the cache operates much faster than memory, its role is to help the processing unit 812 run faster.

[0245] The memory 820 provides runtime space for processes in the computing device 800. For example, the memory 820 stores the computer program (specifically, the program code) used to generate the process. After the computer program is run by the processor to generate a process, the processor allocates corresponding storage space for the process in the memory 820. Furthermore, the aforementioned storage space further includes text segments, initialized data segments, bit initialized data segments, stack segments, heap segments, etc. The memory 820 stores data generated during the process's execution, such as intermediate data or process data, in the aforementioned process-specific storage space.

[0246] Optionally, the memory, also known as RAM, is used to temporarily store the data processed by the processor 810, as well as data exchanged with external storage devices such as hard disks. As long as the computer is running, the processor 810 will load the data that needs to be processed into RAM for processing, and after the processing is completed, the processing unit 812 will send the result out.

[0247] By way of example and not limitation, memory 820 is volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory is read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory is random access memory (RAM) used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DRRAM). It should be noted that the memory 820 of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0248] The structures of the computing device 800 listed above are merely illustrative and are not limited thereto. The computing device 800 in this application includes various hardware components in existing computer systems. For example, the computing device 800 also includes other memories besides the memory 820, such as disk storage. Those skilled in the art should understand that the computing device 800 may also include other devices necessary for normal operation. Furthermore, depending on specific needs, those skilled in the art should understand that the computing device 800 may also include hardware devices for implementing other additional functions. In addition, those skilled in the art should understand that the computing device 800 may only include the devices necessary for implementing the embodiments of this application, and may not necessarily include... Figure 8All the devices shown.

[0249] Figure 9 This is a schematic diagram of the architecture of a computing device cluster provided in an embodiment of this application.

[0250] The computing device cluster includes at least one computing device. This computing device may be a server. In some embodiments, the computing device may also be a terminal device such as a desktop computer, laptop computer, or smartphone.

[0251] like Figure 9 As shown, the computing device cluster includes at least one computing device 800. The memory 820 of one or more computing devices 800 in the computing device cluster may store the same instructions for performing the methods described above.

[0252] In some possible implementations, the memory 820 of one or more computing devices 800 in the computing device cluster may also each store a portion of the instructions for executing the above-described method. In other words, a combination of one or more computing devices 800 can jointly execute the instructions of the above-described method.

[0253] It should be noted that the memories 820 in different computing devices 800 within the computing device cluster can store different instructions, each used to execute a portion of the functions of the aforementioned device. That is, the instructions stored in the memories 820 of different computing devices 800 can implement the functions of one or more modules within the aforementioned device.

[0254] In some possible implementations, one or more computing devices in a computing device cluster can be connected via a network. This network can be a wide area network (WAN) or a local area network (LAN), etc.

[0255] Figure 10 This is a schematic diagram showing the connection between computing devices 800A and 800B via a network according to an embodiment of this application.

[0256] like Figure 10 As shown, the two computing devices 800A and 800B are connected via a network. Specifically, they are connected to the network through the communication interfaces in each computing device.

[0257] It should be understood that Figure 10 The functions of the computing device 800A shown can also be performed by multiple computing devices 800. Similarly, the functions of the computing device 800B can also be performed by multiple computing devices 800.

[0258] This application also provides a computer program product containing instructions, which may be a software or program product containing instructions capable of running on a computing device or stored on any usable medium. When run on a computing device, it causes the computing device to perform the methods provided above, or causes the computing device to perform the functions of the apparatus provided above.

[0259] This application also provides a computer-readable storage medium, which can be any available medium capable of being stored by a computing device or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that, when executed on a computing device, cause the computing device to perform the method provided above.

[0260] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0261] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0262] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0263] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0264] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0265] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0266] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0267] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method of virtual object generation, the method comprising: The method comprises the following steps: obtaining a user demand; determining a generation demand according to the user demand, the generation demand being used to generate a virtual object; decomposing the generation demand into at least one subtask, each of the at least one subtask corresponding to a demand field, and each demand field comprising at least one demand function; determining a demand function corresponding to the virtual object under at least one demand field; calling a function model of the demand function corresponding to the virtual object under the at least one demand field to generate the virtual object.

2. The method of claim 1, wherein, The step of determining the generation demand according to the user demand comprises the following steps: determining the generation demand by using a large language model (LLM) and a virtual object knowledge base according to the user demand.

3. The method according to claim 1 or 2, characterized in that, The user demand comprises a first feature. The step of determining the generation demand according to the user demand comprises the following steps: in the case that the virtual object knowledge base does not comprise the first feature, outputting a correction prompt, the correction prompt being used to prompt to modify the first feature into a second feature, wherein the second feature is a feature comprised in the virtual object knowledge base; obtaining a confirmation message of the correction prompt; determining the generation demand according to the confirmation message of the correction prompt, the generation demand comprising the second feature.

4. The method according to any one of claims 1 to 3, characterized in that, The step of determining the generation demand according to the user demand comprises the following steps: outputting a selection prompt, the selection prompt being used to prompt to select a third feature, wherein the third feature is a feature comprised in the virtual object knowledge base and not comprised in the user demand; obtaining a confirmation message of the selection prompt; determining the generation demand according to the confirmation message of the selection prompt, the generation demand comprising the third feature.

5. The method according to any one of claims 1 to 4, characterized in that, Before the step of decomposing the generation demand into at least one subtask, the method further comprises the following steps: outputting a confirmation prompt, the confirmation prompt being used to prompt to confirm the generation demand; obtaining a confirmation message of the confirmation prompt.

6. The method according to any one of claims 1 to 5, characterized in that, The step of determining a demand function corresponding to the virtual object under at least one demand field comprises the following steps: determining a demand function corresponding to the virtual object under each demand field; presenting a selection interface, the selection interface comprising a demand function corresponding to the virtual object under each demand field; obtaining a demand function corresponding to the virtual object under the at least one demand field selected through the selection interface.

7. A virtual object generation apparatus characterized by comprising: The system comprises: an interaction unit, configured to obtain a user demand; a processing unit, the processing unit comprising an intelligent agent (Agent) and a function Agent; wherein the intelligent Agent is configured to perform the following operations: determining a generation demand according to the user demand, the generation demand being used to generate a virtual object; decomposing the generation demand into at least one subtask, each of the at least one subtask corresponding to a demand field, and each demand field comprising at least one demand function; the function Agent is configured to perform the following operations: determining a demand function corresponding to the virtual object under at least one demand field; calling a function model of the demand function corresponding to the virtual object under the at least one demand field to generate the virtual object.

8. The apparatus of claim 7, wherein, The processing unit further comprises a large language model (LLM) and a virtual object knowledge base; The generating requirement is determined according to the user requirement, and the determining includes: The intelligent agent determines the generating requirement according to the user requirement, by using the LLM and the virtual object knowledge base; The generating requirement is decomposed into at least one subtask, and the decomposing includes: The intelligent agent decomposes the generating requirement into at least one subtask by using the LLM.

9. The apparatus of claim 7 or 8, wherein, The user requirement includes a first feature; The interaction unit is configured to: In a case where the virtual object knowledge base does not include the first feature, output a correction prompt, the correction prompt being used to prompt to modify the first feature into a second feature, wherein the second feature is a feature included in the virtual object knowledge base; Obtain a confirmation message of the correction prompt; The intelligent agent is configured to: According to the confirmation message of the correction prompt, determine the generating requirement, and the generating requirement includes the second feature.

10. The apparatus of any one of claims 7 to 9, wherein, The interaction unit is configured to: Output a selection prompt, the selection prompt being used to prompt to select a third feature, wherein the third feature is a feature included in the virtual object knowledge base and not included in the user requirement; Obtain a confirmation message of the selection prompt; The intelligent agent is configured to: According to the confirmation message of the selection prompt, determine the generating requirement, and the generating requirement includes the third feature.

11. The apparatus of any one of claims 7 to 10, wherein, The interaction unit is configured to: Output a confirmation prompt, the confirmation prompt being used to prompt to confirm the generating requirement; Obtain a confirmation message of the confirmation prompt.

12. The apparatus of any one of claims 7-11, wherein, The functional agent is configured to: Determine a requirement function corresponding to the virtual object under each requirement field; The interaction unit is configured to: Present a selection interface, the selection interface including a requirement function corresponding to the virtual object under each requirement field; Obtain a requirement function corresponding to the virtual object under the at least one requirement field selected through the selection interface.

13. The apparatus of any one of claims 7-12, wherein, The interaction unit is further configured to: Present the virtual object.

14. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and the computer program is executed by a computer to implement the method in any one of claims 1 to 6.

15. A computer program product, characterised in that, The computer program product includes computer program code, and when the computer program code is run on a computer, the method in any one of claims 1 to 6 is implemented.

16. A cluster of computing devices, characterized in that, At least one computing device is included, each computing device including a processor and a memory, and the processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster executes the method in any one of claims 1 to 6.

Images