Method, apparatus, device, and program product for interaction

Abstract

A method, apparatus, device and program product for interaction are provided. The method presented herein includes receiving a first content, the first content describing a movement manner related to an interaction object in a natural language, the interaction object being associated with a three-dimensional module; presenting a first message, the first message describing a movement logic of the three-dimensional module, the movement logic being generated based on the first content; and presenting a movement of the interaction object in a virtual scene, the movement being based on the movement logic. In this way, the efficiency of creating the interaction object can be improved.

Description

Technical Field

[0001] The examples in this article generally relate to the field of computers, and in particular to methods, devices, equipment, and computer program products for interaction. Background Technology

[0002] With the increasing maturity of internet technology, more and more users are engaging in interactive activities on online platforms. For example, people can control virtual characters to interact with other characters or virtual objects in virtual scenes. Summary of the Invention

[0003] In a first aspect, a method for interaction is provided. The method includes: receiving first content, the first content describing in natural language a motion pattern associated with an interactive object, the interactive object being linked to a 3D module; presenting a first message, the first message describing motion logic of the 3D module, the motion logic being generated based on the first content; and presenting the motion of the interactive object in a virtual scene, the motion being derived from the motion logic.

[0004] In a second aspect, an interactive device is provided. The device includes: a receiving module configured to receive first content, the first content describing in natural language a motion pattern associated with an interactive object, the interactive object being linked to a 3D module; a first generating module configured to present a first message, the first message describing the motion logic of the 3D module, the motion logic being generated based on the first content; and a second presenting module configured to present the motion of the interactive object in a virtual scene, the motion being derived from the motion logic.

[0005] In a third aspect, an electronic device is provided. The device includes: at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the electronic device to perform the method of the first aspect when executed by the at least one processor.

[0006] In a fourth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions that can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect, a computer program product is provided. The computer program product is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a device, cause the device to perform the method of the first aspect.

[0008] In this way, users only need to describe the movement of interactive objects in natural language, and the system can automatically generate the corresponding motion logic. Furthermore, the movement of interactive objects based on this motion logic can be presented in a virtual scene. This lowers the barrier to creating motion behavior for interactive objects, eliminating the need for manual programming, thereby reducing the time cost of creating virtual objects and improving the efficiency of building virtual interactions.

[0009] It should be understood that the content described in this section is not intended to limit the key or important features of the examples in this article, nor is it intended to restrict the scope of the solution. Other features will become readily apparent from the following description. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the various examples herein will become more apparent when taken in conjunction with the accompanying drawings and the following detailed description. In the accompanying drawings, the same or similar reference numerals denote the same or similar elements, wherein: Figure 1 A schematic diagram of the example environment is shown; Figures 2A to 2C Example interfaces for some scenarios are shown; Figures 3A to 3B Example interfaces for some scenarios are shown; Figures 4A to 4D Example interfaces for some scenarios are shown; Figure 5 A schematic block diagram of an example architecture for creating interactive objects based on several scenarios is shown; Figure 6A Flowcharts of example interactive processes are shown in some scenarios; Figure 6B Flowcharts of example interactive processes are shown in some scenarios; Figure 7 Schematic structural block diagrams of example devices for interaction in several scenarios are shown; and Figure 8 A block diagram of an electronic device capable of implementing multiple illustrative scenarios is shown. Detailed Implementation

[0011] The examples in this document will now be described in more detail with reference to the accompanying drawings. While some examples are shown in the drawings, it should be understood that solutions can be implemented in various forms and should not be construed as limited to the examples presented herein. Rather, these examples are provided to provide a more thorough and complete understanding of the solutions. It should be understood that the drawings and examples in this document are for illustrative purposes only and are not intended to limit the scope of protection of the solutions.

[0012] It should be noted that the headings of any section / subsection provided herein are not restrictive. Various examples are described throughout this document, and examples of any type may be included under any section / subsection. Furthermore, examples described in any section / subsection may be combined in any way with any other examples described in the same section / subsection and / or different sections / subsections.

[0013] In the description of the examples in this document, the term "including" and similar terms should be understood as open inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "an example" or "the example" should be understood as "at least one example". The term "some examples" should be understood as "at least some examples". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0014] The examples in this article may involve user data, data acquisition, and / or use. All of these aspects comply with relevant laws, regulations, and rules. In the examples presented here, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, when implementing each example, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained through appropriate means, in accordance with relevant laws and regulations. The specific methods of notification and / or authorization can vary depending on the actual situation and application scenario; the scope of the solution is not limited in this regard.

[0015] In this manual and the sample solutions, any processing of personal information will be conducted only under legal grounds (such as obtaining the consent of the data subject or being necessary for the performance of a contract) and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information beyond what is necessary for basic functions will not affect the user's use of basic functions.

[0016] As mentioned above, with the increasing maturity of internet technology, more and more users are engaging in interactive activities on online platforms. For example, people can control virtual characters to interact with other characters or virtual objects in virtual scenes.

[0017] A scheme for interaction is proposed. This scheme includes: receiving first content. The first content describes the motion of the interactive object in natural language. The interactive object is associated with a 3D module. A first message can be presented. The first message describes the motion logic of the 3D module. The motion logic is generated based on the first content. Furthermore, the motion of the interactive object can be presented in a virtual scene. The motion is derived from the motion logic.

[0018] In this way, user-described movements in natural language can be automatically converted into structured motion logic and presented to the user as a readable first message. This allows the user to understand and confirm whether the generated logic meets expectations before the actual movement is presented in the virtual scene. Based on this, the interaction objects are further driven to perform corresponding movements in the virtual scene according to this motion logic. Thus, a complete mapping from natural language to motion logic and then to visualized motion is achieved. This lowers the technical barrier for users to define complex motion behaviors, improves system transparency and user control over motion behavior through explicit logical messages, avoids invalid movements caused by semantic ambiguity or logical errors, and improves the accuracy of interaction object behavior design and human-computer collaboration efficiency in the virtual scene.

[0019] The following describes various examples of this scheme in further detail with reference to the accompanying drawings.

[0020] Example Environment Figure 1 A schematic diagram of example environment 100 is shown. (e.g.) Figure 1 As shown, example environment 100 may include electronic device 110.

[0021] In this example environment 100, electronic device 110 may run an application 120 that supports interaction. Application 120 may be any suitable type of application for interaction, including but not limited to: media applications, social applications, or other suitable applications. User 140 may interact with application 120 via electronic device 110 and / or its attached devices.

[0022] exist Figure 1 In environment 100, if application 120 is active, electronic device 110 can use application 120 to present interface 150 for supporting the creation of interactive objects.

[0023] In some cases, electronic device 110 communicates with server 130 to provide services to application 120. Electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable gaming terminals, VR / AR devices, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. In some cases, electronic device 110 can also support any type of user-facing interface (such as "wearable" circuitry).

[0024] Server 130 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide backend services for applications 120 in electronic devices 110 that support the construction of virtual scenes.

[0025] A communication connection can be established between server 130 and electronic device 110. This communication connection can be established via wired or wireless means. The communication connection can include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus (USB), and Wireless Fidelity (WiFi) connections. In some cases, server 130 and electronic device 110 can exchange signaling information through their communication connection.

[0026] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of the scheme.

[0027] The following description of the example will continue with reference to the accompanying drawings.

[0028] Example Interaction Figures 2A to 2CExample interfaces 200A to 200C are shown according to some scenarios. Interfaces 200A to 200C can, for example, be provided by... Figure 1 The electronic device 110 shown is provided.

[0029] Figure 2A A sample interface 200A for creating interactive objects is shown. As an example, sample interface 200A can support users in creating interactive objects through dialogue with an object creation system. The object creation system can be deployed locally on electronic device 110 or on a remote device, such as server 130.

[0030] As will be detailed below, users can initiate a request to create an interactive object through interface 200A, and can trigger one or more intelligent components in the object creation system to handle the request and automatically create the interactive object.

[0031] In this paper, "intelligent component" refers to a component or system capable of autonomous control based on a machine learning model. An intelligent component is, for example, a virtual object or physical entity capable of making decisions and autonomously executing actions based on a machine learning model to achieve preset goals or complete preset tasks. In some cases, an intelligent component may also be called an intelligent system, which can be, for example, an automated program that understands the user's intent and can use models or invoke tools to complete various types of tasks. Examples of intelligent components include, but are not limited to, agents, bots, chatbots, digital avatars, intelligent customer service, and digital assistants. Alternatively, an intelligent component can also be an intelligent role implemented based on a machine learning model. An "intelligent component" may, for example, use generative models (e.g., language models, multimodal models) to process user requests to perform specified types of tasks. In some cases, an intelligent component may also be associated with a virtual account, which may have a corresponding avatar or nickname.

[0032] In some examples, such as Figure 2A As shown, interface 200A can support the creation of two different types of 3D modules. Specifically, entry 205 can be used to create the first type of 3D module. In some cases, the first type of 3D module is also called a "topological model". As an example, the first type of 3D module can correspond to a whole 3D model, which can have relatively high precision and can have more detailed textures.

[0033] Entry 210 can be used to create a second type of 3D module. In some cases, the second type of 3D module is also referred to as a "geometric model". As an example, a second type of 3D module may include multiple independent 3D components, which may be obtained by assembling multiple basic geometries (also referred to as basic 3D components). As will be described below, the basic 3D components in a second type of 3D module may, for example, be detachable. Furthermore, some 3D components in a second type of 3D module may, for example, be able to move independently.

[0034] The following sections will describe the process of creating interactive objects based on two types of 3D modules.

[0035] As an example, a user can select entry 205 and trigger the generation of a "topology model" using input component 215 of interface 200A. As an example, electronic device 110 can receive user input via input component 215. As an example, the input may include reference information describing the interactive object to be created.

[0036] In some cases, the input content may include text content, which may describe the interactive object to be created in natural language. As an example, a user may want to create a "rocking horse," and the text content may include "rocking horse with tassels on the handles of the head."

[0037] In other cases, the input may include other appropriate types of reference information. For example, a user may upload or photograph one or more media items as a reference for creating a 3D module. For instance, a user may take a photograph of a real rocking horse as a reference for generating a 3D module.

[0038] Furthermore, such as Figure 2B As shown, the electronic device 110 can display a message area 220 in the interface 200B. The message area 220 can display message interactions between the user and the object creation system. For example, the message area 220 can display a user-inputted message 225, which can describe the shape of the 3D module to be created.

[0039] In some cases, the object creation system can generate a 3D module 235 based on the received message 225. The process of generating the 3D module will be described in detail below.

[0040] As an example, electronic device 110 can display a 3D module 235 generated based on message 225 on interface 200B. In this example, since the user selects "topology model" as the type, the 3D module 235 can be, for example, a single 3D model.

[0041] Furthermore, message area 220 can display messages from the object creation system to represent the processing results of message 225. For example, message area 220 can display messages 230-1, 230-2, and 230-3.

[0042] As an example, message 230-1 could indicate that a 3D module 235 has been generated based on message 225. Message 230-3 could, for example, include a preview image of the generated 3D module 235.

[0043] In some cases, message 230-3 may include reference information associated with the 3D module 235. This reference information may include suggested modes of motion for the 3D module 235. For a “topological model,” it can move as a whole. Figure 2B As an example, message 230-3 can present two candidate motion modes: "floating in mid-air" and "slowly rotating".

[0044] Furthermore, the electronic device 110 can receive first content, which can describe the motion of an interactive object in natural language, the interactive object corresponding to a three-dimensional module.

[0045] As an example, electronic device 110 can receive user input via input component 215. The first input may include, for example, "float the model in mid-air." This input text can express the movement of the 3D module 235 in natural language.

[0046] As another example, electronic device 110 may also receive a user's trigger action on a candidate (e.g., "floating") in message 230-3, and may accordingly send a message to the object creation system such as Figure 2C The message 240 is shown. As an example, message 240 may correspond to a triggered candidate. Accordingly, the first content may include the sent message 240.

[0047] It should be understood that the first content may also include, for example, voice content. For instance, electronic device 110 can receive voice input from a user and can directly send the message corresponding to the voice input to the object creation system.

[0048] Furthermore, such as Figure 2C As shown, the electronic device 110 can present a first message 245, which can describe the motion logic of the three-dimensional module, and the motion logic is generated based on the first content (e.g., message 240).

[0049] As described below, the object creation system can utilize one or more intelligent components to generate motion logic. The process of generating motion logic will be discussed in the following section. Figure 5Detailed description.

[0050] by Figure 2C As shown, the first message 245 may include one or more motion parameters associated with the motion mode of the 3D module 235. For example, taking "floating" as an example, its motion parameters may include, for example, "floating speed" and "displacement distance". Such motion parameters may be automatically determined by the object creation system based on message 240.

[0051] Additionally, the electronic device 110 can also display a motion preview of the 3D module 235 in the preview area of ​​the interface 200C. For example, the electronic device 110 can render a floating effect of the 3D module 235 based on the generated motion logic. In some examples, the motion logic may include a motion script file, and the electronic device 110 can render the motion animation of the 3D module 235 based on the motion script file, thereby allowing users to intuitively view the effect corresponding to the current motion logic.

[0052] In some cases, the electronic device 110 may also receive requests to adjust motion logic. For example, a user may receive text input via input component 215, such as "faster speed" or "larger amplitude". Accordingly, the object creation system may adjust the motion logic in response to the text input, for example, increasing the "floating speed" or increasing the "displacement distance".

[0053] Accordingly, when the motion logic is adjusted, the electronic device 110 can update the motion preview of the 3D module 235 in the preview area so that the motion preview matches the updated motion logic. For example, the 3D module 235 can display a faster motion speed or a larger motion float.

[0054] In some cases, the object creation system may also support user configuration of conditions that trigger the interactive object to display the movement. As an example, the first message 245 may present multiple candidate conditions for triggering the interactive object to display the movement, such as "proximity interaction" or "autonomous interaction".

[0055] As an example, the candidate condition "proximity interaction" can characterize that when a virtual object operated by a user approaches the interactive object in a virtual scene, the interactive object can display the motion based on the created motion logic.

[0056] As another example, the candidate condition "autonomous interaction" can characterize that the virtual object can autonomously display the movement in the virtual scene, without relying on the interaction between the virtual object and the interactive object.

[0057] In some cases, electronic device 110 may receive second content, which represents the first condition that triggers the movement. For example, electronic device 110 may receive a user's selection of the first condition (e.g., "proximity interaction") from candidate conditions and may also receive the second content. As an example, the second content may include a message sent to an object creation system, such as "movement after character proximity".

[0058] As another example, the electronic device 110 can also receive a second piece of content input by the user via the input component 215. For example, the user can input the text "Move after the character approaches", and this text can be sent to the object creation system to indicate that the condition for triggering the movement is "the character approaches".

[0059] Therefore, this paper also allows users to further configure the motion triggering conditions of interactive objects, thereby improving the interaction flexibility of interactive objects.

[0060] As described above, interactive objects can be published to a virtual scene to support interaction between virtual objects and the interactive objects. Accordingly, the object creation system can also support users in configuring the interaction logic of the interactive objects. In some cases, the electronic device 110 can also receive third-party content. The third-party content describes the interaction between the virtual objects and the interactive objects in natural language.

[0061] For example, electronic device 110 can receive user input 250 via input component 215. As an example, the third content may include input 250. For example, input 250 may describe the interaction logic between a virtual object and an interactive object, such as, "The character is close enough to ride the horse."

[0062] Accordingly, electronic device 110 can trigger interaction logic to generate interactive objects based on third-party content. As described below, the object creation system can utilize one or more intelligent components to process input content 250 to generate interaction logic for interactive objects. As an example, the interaction logic may include an interaction script file, which can define how virtual objects interact with interactive objects in a virtual scene. The interaction process between virtual objects and interactive objects will be discussed in detail below. Figures 3A to 3B To describe.

[0063] Based on the process described above, the object creation system allows users to create 3D modules through interactive dialogue, and further configures the motion and interaction logic of these modules. This reduces the time cost for users to create interactive objects, lowers the learning curve for developing virtual objects, thereby improving creation efficiency and increasing creative freedom.

[0064] Furthermore, it should be understood that the process of configuring the motion and interaction logic of the 3D module described above can be based on an existing 3D module, and does not necessarily have to be based on one generated by the object creation system. For example, the object creation system can also support users uploading pre-created 3D modules, and the motion or interaction logic can be configured for the uploaded 3D modules through the process described above.

[0065] In some cases, after the creation of the interactive object is completed, the electronic device 110 can receive the user's publishing request and associate it with the virtual scene so that the interactive object can be presented in the virtual scene.

[0066] In some contexts, a "virtual scene" can also be called a "virtual environment," a "virtual world," or a "virtual map," providing an environment for users to interact with virtual objects and interactive objects. "Interactive objects" can also be referred to as virtual interactive elements within a "virtual scene," and examples may include, but are not limited to, virtual props, virtual locations, and virtual NPCs (non-player characters).

[0067] The following will be further combined Figures 3A to 3B To describe interaction examples in a virtual scene. In some cases, Figures 3A to 3B The corresponding interfaces 300A to 300B can be provided by a first electronic device, which may be the same as or different from a second electronic device that provides interfaces 200A to 200C. As an example, the second electronic device can correspond to the creator of the virtual object, while the first electronic device can correspond to the player user in the virtual scene.

[0068] like Figure 3A As shown, the electronic device 110 can present an interactive object 315 in a virtual scene 320. As an example, the interactive object 315 can correspond to a three-dimensional module 235 created through interfaces 200A to 200C.

[0069] In some cases, the electronic device 110 can also present a virtual object 305 in a virtual scene 320, the movement of which is triggered by user actions. As an example, the virtual object 305 may correspond to an object manipulated by the user, also known as a virtual character. For instance, the user can control the virtual object 305 to move or perform specified actions in the virtual scene using graphical controls provided in the interface 300A.

[0070] Accordingly, electronic device 110 can control the movement of interactive object 315 based on the motion logic created by the process described above. As introduced above, if the first condition for triggering the movement of interactive object 315 is met, electronic device 110 can present the movement of interactive object 315, for example, "floating".

[0071] For example, if the first condition indicates that the interactive object 315 moves autonomously, the electronic device 110 can always display the movement of the interactive object 315, regardless of the interaction state between the virtual object 305 and the interactive object 315.

[0072] As another example, if the first condition indicates that the virtual object 305 is close to the interactive object 315, then when the interaction state between the virtual object 305 and the interactive object 315 meets the first condition, the electronic device 110 can present the movement of the interactive object 315, for example, "floating in mid-air".

[0073] For example, the interaction state can represent the distance between the virtual object and the interactive object 315. If the distance is less than a first threshold, the interactive object 315 can exhibit "floating" based on motion logic.

[0074] In some cases, virtual scenes can also support interaction between virtual objects and interactive objects. For example, electronic device 110 can receive interactive operations associated with interactive object 315 and can accordingly present virtual interaction between virtual object 305 and interactive object 315. This virtual interaction is based on the interaction logic described above.

[0075] For example, as described above, the interaction logic could include "the character approaches and can ride the horse." Accordingly, in response to the interaction state between the virtual object 305 and the interactive object 315 satisfying the second condition, the electronic device 110 can present the interactive control 310, the second condition being related to the interaction logic.

[0076] For example, when the distance between the virtual object 305 and the interactive object 315 in the virtual scene is less than a second threshold, the electronic device 110 can present the interactive control 310. As an example, the interactive control 310 can describe the type of interactive operation that can be triggered. For example, the interactive control 310 can present the text "riding a horse" to indicate that the interactive operation of "riding a horse" can be performed by triggering the interactive control 310.

[0077] In some cases, the interactive control 310 and its corresponding interaction logic are determined based on the interaction script file described above. That is, the creator of the virtual object does not need to write code manually, and can use the object creation system to automatically create the interaction script file to display the corresponding control through dialogue interaction.

[0078] Furthermore, such as Figure 3B As shown, when electronic device 110 receives a trigger operation on interactive control 310, electronic device 110 can present virtual interaction between virtual object 305 and interactive object 315. For example, virtual object 305 can ride on interactive object 315.

[0079] In some cases, interfaces 300A to 300B may also be provided by a second electronic device. For example, interfaces 300A to 300B may be debugging interfaces for the creator, which can support the creator to test interactive objects in a virtual scene.

[0080] The following will be further combined Figures 4A to 4D This describes how to create interactive objects corresponding to the second type of 3D module.

[0081] As an example, electronic device 110 may receive user input such as... Figure 2A The selection of entry 210 shown can be used to receive message 405 in a manner similar to that described above. Figure 4A As shown, message 405 may include "a rocking horse with tassels on the handles at the head and a windmill on the tail".

[0082] Accordingly, the object creation system can create a 3D module 410 based on the received message 405. Unlike the 3D module 235 described above, the 3D module 410 is constructed using multiple 3D components. Each 3D component may, for example, include one or more basic geometries.

[0083] As an example, the 3D module 410 may include multiple geometries, and it may include a 3D component 415. As an example, the 3D component 415 may be a 3D windmill.

[0084] In some cases, the 3D module 410 may include one or more 3D components that support disassembly. For example, it may support the disassembly of the 3D component 415 from the 3D module 410.

[0085] As an example, the electronic device 110 may provide an editing component for the 3D module 410 and may receive user movement operations on the 3D component 415 to, for example, remove the 3D component 415 from the 3D module 410. As an example, the user may also use the editing component to delete the 3D component 415 from the 3D module 410. As another example, the electronic device 110 may also support moving the 3D component 415 to other locations within the 3D module 410. For example, the user may remove the 3D component 415 from the 3D module 410 and move it to the head of a rocking horse.

[0086] As yet another example, the electronic device 110 may also support replacing the 3D component 415 with other types of 3D components. For example, a user may be able to remove the 3D component 415 from the 3D module 410 and replace the 3D component 415 with other 3D components in the asset library, for example.

[0087] In some cases, each 3D component in 3D module 410 can be provided as an independently managed asset, allowing users to independently edit such 3D components or reuse such 3D components to create other 3D modules.

[0088] As an example, after acquiring the 3D Component 415 asset, a user can select 3D Component 415 from the asset library and use it to build or edit other 3D modules.

[0089] In some cases, it is similar to a reference. Figures 2A to 2C The described process allows electronic device 110 to generate motion logic for 3D module 410 based on the received first content. Figure 4A For example, the motion logic of the 3D module 410 may be generated based on message 405. That is, the first content may include message 405, wherein message 405 may be a motion mode related to the interactive object described in natural language in the form of a dialogue.

[0090] Specifically, the motion logic of the 3D module 410 can describe the component motion logic of at least one of a plurality of 3D components. For example... Figure 4A As shown, the motion logic of the three-dimensional module 410 may include the component motion logic of the three-dimensional component 415, that is, the windmill component can "rotate continuously".

[0091] In some cases, the 3D module 410 may include one or more independently moving 3D components. As an example, the first motion logic of 3D component 415 (also referred to as the first 3D component) may be independent of the second motion logic of 3D component 417 (also referred to as the second 3D component, e.g., the torso component of a rocking horse). In some cases, the object creation system may also support users configuring the motion logic of each 3D component independently. For example, a user can input the text "windmill rotates automatically" through an input component (e.g., the input component 215 mentioned above), thereby configuring the motion logic of 3D component 415 to "rotate continuously." Furthermore, a user can input the text "torso sways left and right" through an input component, thereby configuring the motion logic of 3D component 417 to "sway left and right."

[0092] For example, the three-dimensional component 415 can move independently of the three-dimensional component 417. For example, a first motion logic can instruct the rotational motion of the three-dimensional component 415 (i.e., the first motion), and a second motion logic can instruct the three-dimensional component 417 to oscillate along with the three-dimensional module 410 as a whole (i.e., the second motion). Thus, the three-dimensional component 415 can exhibit rotational motion independent of the three-dimensional component 417. That is, the first motion can be different from the second motion.

[0093] As another example, the second motion logic could also instruct the three-dimensional component 417 to remain stationary. That is, while the three-dimensional component 415 is undergoing rotational motion, one or more other three-dimensional components of the three-dimensional module 410 can remain stationary.

[0094] Figure 4B Another example of creating an interactive object corresponding to the second type of 3D module is shown. For example... Figure 4B As shown, the electronic device 110 can receive a message 425 from a user. As an example, message 425 may include a text description about the windmill to be generated.

[0095] Accordingly, the object creation system can create a second type of 3D module 435. For example... Figure 4B As shown, the three-dimensional module 435 may include multiple three-dimensional components, such as a three-dimensional component 440 corresponding to a windmill component. As an example, the three-dimensional component 440 may be detachable from the three-dimensional module 435. Additionally or alternatively, the three-dimensional component 440 may also exhibit movement independent of other three-dimensional components (e.g., a house section).

[0096] In other cases, electronic device 110 may also receive input content 430. For example... Figure 4C As shown, electronic device 110 can send a message corresponding to input content 430 to object creation system.

[0097] Input 430 can be used to trigger the interaction logic that generates interactive objects. As an example, input 430 can indicate that when a character approaches the windmill, a button will appear, and this button will trigger the windmill to rotate.

[0098] Accordingly, the electronic device 110 may display message 445, which may describe the interaction logic generated based on the input content 430. For example, message 445 may describe the specific implementation of the interaction logic, such as which interfaces were called to implement the interaction logic.

[0099] Figure 4D A virtual environment 460 is shown based on some examples. As an example, an interactive object 465 corresponding to a created 3D module 435 can be added to the virtual environment 460. Figure 4D The interface 400D shown can be, for example, a test interface for the creators, or an interactive interface for players.

[0100] like Figure 4DAs shown, the electronic device 110 can present a virtual object 450, which can be operated by the user. Based on the motion logic and interaction logic of the interactive object 465, when the interaction state between the virtual object 450 and the interactive object 465 meets a second condition (e.g., the distance between them is less than a threshold), the electronic device 110 can present an interactive control 455.

[0101] Furthermore, the electronic device 110 can receive a trigger operation on the interactive control 455 and can trigger the interactive object 465 to exhibit motion configured based on motion logic. Specifically, the motion logic can instruct the component motion logic of a specific three-dimensional component (e.g., a windmill component) in the interactive object 465. Accordingly, after triggering the interactive control 455, the motion exhibited by the interactive object 465 includes the house component remaining stationary and the windmill component exhibiting rotational motion.

[0102] In some other examples, when the interaction state of the interactive object 465 in the virtual scene 460 meets the third condition, the electronic device 110 can separate at least one three-dimensional component from the interactive object 465.

[0103] As an example, electronic device 110 may receive a user click interaction and trigger virtual object 450 to perform a virtual attack on interactive object 465. Accordingly, after interactive object 465 is attacked, the windmill component may detach from interactive object 465. Accordingly, interactive object 465 may retain only the house component, and the detached windmill component may exhibit a third movement.

[0104] In some cases, the third motion exhibited by the separated three-dimensional components can also be derived from the generated motion logic. For example, the motion logic could instruct that the windmill components can exhibit rolling motion on the ground after detachment.

[0105] In some cases, the virtual object 450 can also interact with the detached 3D component. For example, the electronic device 110 can present interactive controls (e.g., "push") corresponding to the detached 3D component, thereby enabling the virtual object to push the detached windmill component to roll along a specified route.

[0106] Figure 5 A schematic block diagram of an example architecture 500 for creating interactive objects based on several scenarios is shown. Architecture 500 can be implemented in... Figure 1 The electronic device 110 shown, additionally or alternatively, part or all of the architecture 500 can also be implemented at the server 130. See below for reference. Figure 5 This describes an example process for creating interactive objects.

[0107] In some cases, interactive objects can be created based on the following process: creating multiple tasks using intelligent planning components based on requirement information, the requirement information being at least based on a first set of content; and executing multiple tasks using multiple intelligent execution components to create interactive objects, the multiple tasks being used to generate different attributes of the interactive objects.

[0108] like Figure 5 As shown, architecture 500 can receive user input 530, which may include the first content described above. Architecture 500 may include an intelligent planning system 505. As an example, the intelligent planning component may include an agent configured specifically for planning tasks.

[0109] As an example, the intelligent planning system 505 can create multiple tasks based on requirement information, which is at least based on the first content. As an example, the intelligent planning system 505 can perform task planning 532, requirement clarification 534, and multi-intelligent object orchestration 536. In some cases, when the requirement information is unclear, the intelligent planning system 505 can use requirement clarification 534 to inquire about relevant details.

[0110] For example, follow-up messages can be presented to users through dialogue interactions as described above to obtain a more specific expression of their needs. For instance, if the user's input is a general type, such as "vehicle," then the follow-up message could include, for example, "What type of vehicle do you want to create, a sports car or a truck?" In this way, more specific user needs can be obtained, thereby improving the accuracy of object creation.

[0111] In some cases, architecture 500 may also include multiple intelligent execution components, which may include a first intelligent execution system 510, a second intelligent execution system 515, and a third intelligent execution system 520. As an example, the multiple intelligent execution components may correspond to multiple intelligent agents performing different tasks.

[0112] Multiple intelligent execution components can execute multiple tasks created by the intelligent planning system 505 to create interactive objects. These multiple tasks are used to generate different attributes of the interactive objects. In this way, the creation process of interactive objects is decomposed into multiple tasks executed by different intelligent execution components, which facilitates the generation of different attributes of interactive objects and improves the efficiency of creating interactive objects.

[0113] In some scenarios, performing multiple tasks using multiple intelligent execution components may include: determining structural description information from requirement information; and generating a 3D module based on the structural description information using a first intelligent execution component. As an example, the first intelligent execution system 510 may perform skill loading 538 and static module generation 540 to determine structural description information from requirement information and generate a 3D module based on the structural description information, thereby obtaining a static module file 542. Thus, the structure of the 3D module can be automatically generated based on the structural description information, reducing the operational cost of creating 3D modules.

[0114] In some scenarios, performing multiple tasks using multiple intelligent execution components may include: determining motion description information from requirement information; and using a second intelligent execution component to generate a first script based on the motion description information, the first script describing motion logic. As an example, the second intelligent execution system 515 may execute skill loading 544 and motion state generation 546 to determine motion description information from requirement information and generate a first script describing motion logic based on the motion description information, thereby obtaining a motion state script 548. Thus, the motion logic of a 3D component can be automatically generated based on the motion description information.

[0115] In some scenarios, performing multiple tasks using multiple intelligent execution components may include: determining interaction description information from requirement information; and using a third intelligent execution component to generate a second script based on the interaction description information, the second script describing the interaction logic associated with the virtual object. As an example, the third intelligent execution system 520 can execute skill loading 550 and interactive gameplay generation 552 to determine the interaction description information from the requirement information and generate a second script describing the interaction logic based on the interaction description information, thereby obtaining an interactive gameplay script 554. Thus, the interaction logic between the 3D component and the virtual object can be automatically generated based on the interaction description information.

[0116] In some cases, architecture 500 may also include an intelligent evaluation system 525. The intelligent evaluation system 525 can evaluate 556 the outputs generated by multiple intelligent execution components and determine if any problems exist 558. If a problem is identified, the intelligent evaluation system 525 can feed the evaluation results back to the intelligent planning system 505 to redistribute and execute the corresponding tasks; if no problem is identified, a movable and interactive module file 560 can be obtained. In this way, the creation process of interactive objects can form an automated closed loop, improving the degree of conformity between the created interactive objects and the requirement information.

[0117] In some cases, the aforementioned architecture 500 supports the generation of two types of 3D modules: topological models and geometric models. A topological model corresponds to a monolithic 3D structure with continuous and indivisible surfaces, similar to the high-precision models output by traditional 3D modeling software. A geometric model, on the other hand, is assembled from multiple independent basic 3D components (e.g., cuboids, spheres, cones, tori, etc.), each of which is an independently editable and controllable asset.

[0118] As an example, when the user inputs requirement information (e.g., user input 530) instructing the generation of a topological model of a "rocking horse with tassels on its head and handles"), the intelligent planning system 505 decomposes the requirement information into multiple tasks. Among them, the first intelligent execution system 510 (static module generator) extracts structural description information (such as the overall shape of the "horse" and the decorative features of the "tassels") from the requirement information, generates a continuous, indivisible, overall 3D mesh using a basic geometry library or parametric surfaces, and outputs it as a static module file 542 in GLB (Binary GL Transmission Format) format.

[0119] Subsequently, the second intelligent execution system 515 (motion state generator) generates a first script (e.g., a Lua script) describing the overall motion logic based on the user's subsequent first content (e.g., the instruction "float in mid-air"). This script defines the motion parameters of the entire topology model in the virtual scene, such as the floating rate and displacement distance. The third intelligent execution system 520 then generates an interaction logic script based on the third content (e.g., "The character is approaching, and can ride the horse"). Finally, the intelligent evaluation system 525 evaluates the aesthetics and the rationality of the motion logic of the generated topology model to ensure that it meets the user's expectations.

[0120] As another example, when a user inputs a requirement (e.g., the user inputs 530) instructing the generation of a geometric model of a "rocking horse with tassels on the handle at the head and a windmill at the tail," the processing flow differs significantly from that of a topological model. The first intelligent execution system 510 will parse that the "windmill" is an independent component and call the corresponding basic geometry from the basic component library (e.g., assembling windmill blades with multiple cuboids and assembling the shaft with cylinders). By specifying the relative positions and connections between the components, it assembles a geometric model composed of multiple independent three-dimensional components.

[0121] Each component (e.g., windmill blades, horse body, tassels) is recorded as an individually addressable asset. For example, the windmill component is identified as a component that can be detached from the 3D module. When generating motion logic, the second intelligent execution system 515, unlike the overall motion of the topology model, generates motion scripts that describe component-level motion logic. For example, the generated first script can cause the windmill component to rotate independently of the horse body component, while the horse body component can remain stationary or perform a separate set of swaying motions. This means that the motion logic of the first 3D component (windmill) is independent of the second 3D component (horse body). The third intelligent execution system 520 can generate specific interaction scripts; for example, when a virtual character approaches, interactive controls are displayed only for the windmill component, triggering the windmill component to begin rotating.

[0122] In some cases, the component-level independence of the geometric model also supports richer dynamic effects. For example, in response to an interactive object's state in a virtual scene (such as being attacked by a virtual character) satisfying a third condition (e.g., the collision force exceeds a threshold), at least one 3D component can be detached from the interactive object (e.g., a windmill component detaches). The detached component can continue to move based on its own third motion logic (e.g., rolling, falling), which can be generated in advance or in real time by the second intelligent execution system 515. This ability to disassemble components allows the geometric model to have a higher degree of interactive freedom and gameplay diversity than traditional monolithic models.

[0123] In some cases, the aforementioned architecture 500 also supports the generation of animation modules with skeletal animation. When a user inputs an instruction to generate an animal character (e.g., "a goose"), the intelligent planning system 505 schedules a dedicated animation generation agent (not shown) or collaborates with the second intelligent execution system 515 to first generate the skeletal structure and animation data of the object. Then, instead of generating a continuous skinned mesh, the first intelligent execution system 510 decomposes the character into multiple rigid basic shape components (e.g., a sphere for the head, cylinders for the limbs, and a cuboid for the torso).

[0124] These rigid components are assembled based on the skeletal information to form the complete character shape. The final module product includes the external structure assembled from the basic shape, the embedded skeletal animation logic (driven by Lua scripts), and interactive properties (such as the ability to destroy parts). For example, under certain conditions, the "goose's" wings can fall off and become independent interactive objects.

[0125] Example process Figure 6A A flowchart of an example process 600A for interaction is shown, based on some scenarios. Process 600A can be implemented at electronic device 110. See below for reference. Figure 1 To describe process 600A.

[0126] like Figure 6A As shown, in box 610, electronic device 110 can receive first content, which describes the motion of an interactive object in natural language, and the interactive object is associated with a 3D module.

[0127] In frame 620, electronic device 110 can present a first message, which describes the motion logic of the three-dimensional module. The motion logic is generated based on the first content.

[0128] In box 630, electronic device 110 can present the movement of interactive objects in a virtual scene, and the movement is obtained based on motion logic.

[0129] In some cases, process 600A further includes: receiving second content, the second content representing a first condition that triggers movement; and, in response to the first condition being met, presenting the movement of the interactive object.

[0130] In this way, specific triggering conditions can be set for movement, so that the movement of interactive objects is no longer an unconditional automatic playback, but is bound to events in the virtual scene, which enhances the rationality of the movement and the immersion of the scene.

[0131] In some cases, receiving the second content includes: presenting multiple candidate conditions in relation to the first message; and receiving the second content based on the selection of the first condition among the multiple candidate conditions.

[0132] In this way, by proactively presenting candidate conditions for users to choose from, the threshold for users to manually write trigger conditions is lowered, while ensuring semantic consistency between trigger conditions and motion logic, and improving the convenience and accuracy of interaction settings.

[0133] In some cases, in response to the first condition being met, presenting the motion of the interactive object includes: in response to the interaction state between the virtual object and the interactive object satisfying the first condition, presenting the motion of the interactive object, wherein the motion of the virtual object in the virtual scene is triggered based on user operation.

[0134] In this way, the movement of interactive objects is associated with the behavior state of virtual objects controlled by the user, making the movement triggering more natural and dynamic, and enhancing the real-time interactive experience between the user and the virtual scene.

[0135] In some cases, process 600A may also include: receiving third content, which describes the interaction between the virtual object and the interactive object in natural language; and triggering the interaction logic to generate the interactive object based on the third content.

[0136] In this way, users can define complex interactive behaviors between virtual objects and interactive objects without writing code, simply by using natural language descriptions. This significantly lowers the barrier to interaction design and improves the efficiency of content creation.

[0137] In some cases, process 600A also includes: receiving an interactive operation associated with an interactive object; and presenting a virtual interaction between a virtual object and an interactive object, the virtual interaction being derived from the interaction logic.

[0138] In this way, the system can present the corresponding interactive effects in real time based on the automatically generated interactive logic when the user actually performs the interactive operation, realizing a closed loop from language description to runnable interactive behavior, and improving the integrity and usability of the system.

[0139] In some cases, receiving an interaction operation associated with an interaction object includes: presenting an interaction control in response to a second condition being met between the virtual object and the interaction object, the second condition being related to the interaction logic; and receiving a trigger operation on the interaction control.

[0140] In this way, interactive controls are only displayed when specific interaction conditions are met, avoiding redundant display of interface elements and allowing users to naturally obtain interactive prompts based on the scene state, thus enhancing the guidance of the interaction and the simplicity of the interface.

[0141] In some cases, a 3D module is created using multiple 3D components, and the multiple 3D components include at least one 3D component that supports detachment from the 3D module.

[0142] In this way, by breaking down the 3D module into multiple detachable 3D components, not only is the construction complexity of a single model reduced, but a structural foundation is also provided for subsequent component-level movement, separation and reuse, enhancing the system's flexibility and scalability.

[0143] In some cases, the motion logic of a 3D module describes the component motion logic of at least one of a plurality of 3D components.

[0144] In this way, motion logic can be refined to the component level, allowing different components to have independent motion behaviors, such as wheel rotation and robotic arm swing, thereby superimposing rich local movements on the overall motion and enhancing the realism of the animation.

[0145] In some cases, multiple three-dimensional components include at least a first three-dimensional component and a second three-dimensional component, and the first motion logic of the first three-dimensional component is independent of the second motion logic of the second three-dimensional component.

[0146] In this way, the motion between components can be decoupled, allowing the first component to move according to one set of rules while the second component moves according to another set of rules or even remains stationary, greatly enriching the motion performance capabilities of interactive objects.

[0147] In some cases, presenting the motion of an interactive object in a virtual scene includes: presenting a first motion corresponding to a first part of a plurality of three-dimensional components in the virtual scene, wherein a second part of the plurality of three-dimensional components is in a stationary state, or the second part presents a second motion, the first motion being different from the second motion.

[0148] In this way, users can intuitively see the different motion states of different components within the same interactive object, such as the body moving while the turret rotates, making the motion performance more delicate and realistic, and increasing the amount of information in the visual feedback.

[0149] In some cases, process 600A further includes: in response to the state of the interactive object in the virtual scene satisfying a third condition, separating at least one three-dimensional component from the interactive object.

[0150] In this way, components can be automatically disassembled under specific conditions, such as parts scattering after a collision, deforming and reassembling, or breaking off, providing a basis for building dynamically variable interactive objects and enhancing the drama and physical credibility of the scene.

[0151] In some cases, process 600A further includes: in response to at least one three-dimensional component being separated from the interactive object, presenting a third motion of at least one three-dimensional component, the third motion being derived based on motion logic.

[0152] In this way, the separated components can continue to move according to the preset motion logic (such as projecting, rotating, and floating), instead of immediately stopping or disappearing, thus continuing physical inertia and enhancing visual continuity and realism.

[0153] In some cases, interactive objects are created based on the following process: creating multiple tasks using intelligent planning components based on requirement information, which is at least based on a first set of content; and executing multiple tasks using multiple intelligent execution components to create interactive objects, where the multiple tasks are used to generate different attributes of the interactive objects.

[0154] In this way, by using task planning and multi-agent collaboration, the complex process of creating interactive objects is broken down into sub-tasks that can be executed in parallel, which improves generation efficiency and resource utilization, while ensuring the coordination and consistency between different attributes (such as appearance, motion, and interaction).

[0155] In some cases, multiple tasks are performed using multiple intelligent execution components, including: determining structural description information from requirement information; and generating a 3D module based on the structural description information using a first intelligent execution component.

[0156] In this way, structural description information is specifically used to drive the intelligent component responsible for geometric modeling, ensuring that the generated 3D module meets the semantic requirements of natural language input in terms of appearance, parts and assembly method, and realizing the automated conversion from text to 3D model.

[0157] In some cases, using multiple intelligent execution components to perform multiple tasks includes: determining motion description information from demand information; and using a second intelligent execution component to generate a first script based on the motion description information, the first script describing motion logic.

[0158] In this way, motion description information is directed to the intelligent component responsible for generating motion logic, automatically outputting executable script code, transforming the motion intent in natural language into procedural behavior, without the need for manual programming, thus improving the efficiency and accuracy of motion definition.

[0159] In some cases, using multiple intelligent execution components to perform multiple tasks includes: determining interaction description information from requirement information; and using a third intelligent execution component to generate a second script based on the interaction description information, the second script describing the interaction logic associated with the virtual object.

[0160] In this way, the interactive description information is used specifically to generate interactive logic scripts, enabling behaviors such as collisions, clicks, and proximity between virtual objects and interactive objects to be automatically implemented according to natural language descriptions, thus constructing a complete chain of interactive behaviors.

[0161] Figure 6B A flowchart of an example process 600B for interaction is shown, based on some scenarios. Process 600B can be implemented at electronic device 110. See below for reference. Figure 1 To describe process 600B.

[0162] like Figure 6B As shown in box 610, electronic device 110 presents interactive objects in a virtual scene.

[0163] In frame 620, electronic device 110 presents the movement of interactive objects. The interactive objects are associated with a 3D module. The movement is obtained based on motion logic, which is generated based on first content. The first content describes the movement of the interactive objects in natural language.

[0164] In some cases, process 600B further includes: presenting a virtual object in a virtual scene; and, in response to the interaction state between the virtual object and the interactive object satisfying a first condition, presenting the motion of the interactive object, wherein the motion of the virtual object in the virtual scene is triggered by a user operation.

[0165] In this way, the movement of interactive objects is associated with the behavior state of virtual objects controlled by the user, making the movement triggering more natural and dynamic, and enhancing the real-time interactive experience between the user and the virtual scene.

[0166] In some cases, process 600B also includes: receiving an interactive operation associated with an interactive object; and presenting a virtual interaction between a virtual object and an interactive object, the virtual interaction being derived from interaction logic generated based on third content.

[0167] In this way, the system can present the corresponding interactive effects in real time based on the automatically generated interactive logic when the user actually performs the interactive operation, realizing a closed loop from language description to runnable interactive behavior, and improving the integrity and usability of the system.

[0168] In some cases, receiving an interaction operation associated with an interaction object includes: presenting an interaction control in response to a second condition being met between the virtual object and the interaction object, the second condition being related to the interaction logic; and receiving a trigger operation on the interaction control.

[0169] In this way, interactive controls are only displayed when specific interaction conditions are met, avoiding redundant display of interface elements and allowing users to naturally obtain interactive prompts based on the scene state, thus enhancing the guidance of the interaction and the simplicity of the interface.

[0170] Example devices and equipment A corresponding apparatus for implementing the above methods or processes is also provided. Figure 7 A schematic structural block diagram of an example interactive device 700 is shown, depending on several scenarios. Device 700 can be implemented as or included in electronic device 110. The various modules / components in device 700 can be implemented by hardware, software, firmware, or any combination thereof.

[0171] like Figure 7 As shown, the device 700 includes: a receiving module 710 configured to receive first content, the first content describing the motion of an interactive object in natural language, the interactive object being associated with a 3D module; a first generating module 720 configured to present a first message, the first message describing the motion logic of the 3D module, the motion logic being generated based on the first content; and a second presenting module 730 configured to present the motion of the interactive object in a virtual scene, the motion being obtained based on the motion logic.

[0172] In some cases, the second presentation module 730 is also configured to: receive second content, the second content representing a first condition that triggers movement; and, in response to the first condition being met, present the movement of the interactive object.

[0173] In some cases, the second presentation module 730 is also configured to: present multiple candidate conditions in association with the first message; and receive second content based on the selection of the first condition among the multiple candidate conditions.

[0174] In some cases, the second presentation module 730 is also configured to: in response to the interaction state between the virtual object and the interactive object satisfying a first condition, present the motion of the interactive object, wherein the motion of the virtual object in the virtual scene is triggered based on user operation.

[0175] In some cases, the device 700 also includes an interaction logic module configured to: receive third content, which describes the interaction between the virtual object and the interactive object in natural language; and trigger interaction logic to generate the interactive object based on the third content.

[0176] In some cases, device 700 also includes an interactive presentation module configured to: receive interactive operations associated with interactive objects; and present virtual interactions between virtual objects and interactive objects, the virtual interactions being derived from interactive logic.

[0177] In some cases, the interactive presentation module is also configured to: present interactive controls in response to the second condition being met in the interaction state between the virtual object and the interactive object, the second condition being related to the interaction logic; and receive trigger operations on the interactive controls.

[0178] In some cases, a 3D module is created using multiple 3D components, and the multiple 3D components include at least one 3D component that supports detachment from the 3D module.

[0179] In some cases, the motion logic of a 3D module describes the component motion logic of at least one of a plurality of 3D components.

[0180] In some cases, multiple three-dimensional components include at least a first three-dimensional component and a second three-dimensional component, and the first motion logic of the first three-dimensional component is independent of the second motion logic of the second three-dimensional component.

[0181] In some cases, the second presentation module 730 is also configured to: present a first motion corresponding to a first part of a plurality of three-dimensional components in a virtual scene, wherein a second part of the plurality of three-dimensional components is in a stationary state, or the second part presents a second motion, the first motion being different from the second motion.

[0182] In some cases, the device 700 also includes a separation module configured to separate at least one three-dimensional component from the interactive object in response to the state of the interactive object in the virtual scene satisfying a third condition.

[0183] In some cases, the separation module is also configured to: in response to at least one 3D component being separated from the interactive object, present a third motion of at least one 3D component, the third motion being derived based on motion logic.

[0184] In some cases, interactive objects are created based on the following process: creating multiple tasks using intelligent planning components based on requirement information, which is at least based on a first set of content; and executing multiple tasks using multiple intelligent execution components to create interactive objects, where the multiple tasks are used to generate different attributes of the interactive objects.

[0185] In some cases, multiple tasks are performed using multiple intelligent execution components, including: determining structural description information from requirement information; and generating a 3D module based on the structural description information using a first intelligent execution component.

[0186] In some cases, using multiple intelligent execution components to perform multiple tasks includes: determining motion description information from demand information; and using a second intelligent execution component to generate a first script based on the motion description information, the first script describing motion logic.

[0187] In some cases, using multiple intelligent execution components to perform multiple tasks includes: determining interaction description information from requirement information; and using a third intelligent execution component to generate a second script based on the interaction description information, the second script describing the interaction logic associated with the virtual object.

[0188] The modules included in device 700 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some cases, one or more modules can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units in device 700 can be implemented at least partially by one or more hardware logic components. By way of example, and not limitation, exemplary types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and so on.

[0189] Figure 8 A block diagram of an electronic device 800 in which one or more examples may be implemented is shown. It should be understood that... Figure 8 The electronic device 800 shown is merely exemplary and should not be construed as limiting the functionality and scope of the examples described herein. Figure 8 The illustrated electronic device 800 can be used to implement the electronic device 110 discussed above.

[0190] like Figure 8 As shown, electronic device 800 is in the form of a general-purpose electronic device. Components of electronic device 800 may include, but are not limited to, one or more processing units or processors 810, memory 820, storage devices 830, one or more communication units 840, one or more input devices 850, and one or more output devices 860. Processor 810 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 820. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 800.

[0191] Electronic device 800 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 800, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 820 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof). Storage device 830 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 800.

[0192] Electronic device 800 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 8 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 820 may include computer program product 825 having one or more program modules configured to perform various methods or actions of various examples.

[0193] The communication unit 840 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 800 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 800 can operate in a networked environment using logical connections to one or more other servers, networked personal computers, or another network node.

[0194] Input device 850 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 860 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 800 can also communicate with one or more external devices (not shown) via communication unit 840 as needed. External devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 800, or with any device that enables electronic device 800 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0195] A computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. A computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0196] The flowcharts and / or block diagrams of the methods, apparatus, devices, and computer program products referred to herein describe various aspects. It should be understood that each block of the flowcharts and / or block diagrams, as well as combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0197] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0198] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0199] The flowcharts and block diagrams in the accompanying figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products under various scenarios. In this respect, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the figures. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0200] Various examples have been described above. The foregoing descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for interaction, comprising: Receive first content, which describes the movement of an interactive object in natural language, the interactive object being associated with a 3D module; A first message is presented, which describes the motion logic of the three-dimensional module. The motion logic is generated based on the first message. as well as The motion of the interactive object is presented in a virtual scene, and the motion is obtained based on the motion logic.

2. The method according to claim 1, wherein presenting the motion of the interactive object in the virtual scene includes: Receive second content, the second content representing a first condition that triggers the motion; as well as In response to the first condition being met, the motion of the interactive object is presented.

3. The method of claim 2, wherein receiving the second content includes: Related to the first message, multiple candidate conditions are presented; as well as Based on the selection of the first condition among the plurality of candidate conditions, the second content is received.

4. The method of claim 2, wherein presenting the motion of the interactive object in response to the first condition being satisfied comprises: In response to the interaction state between the virtual object and the interactive object satisfying the first condition, the motion of the interactive object is presented, wherein the motion of the virtual object in the virtual scene is triggered based on user operation.

5. The method according to claim 1, further comprising: Receive third content, which describes the interaction method between the virtual object and the interactive object in natural language; as well as Based on the aforementioned third content, the interaction logic for generating the interactive object is triggered.

6. The method of claim 5, further comprising: Receive interactive operations associated with the interactive object; as well as The virtual interaction between the virtual object and the interactive object is presented, and the virtual interaction is obtained based on the interaction logic.

7. The method of claim 6, wherein receiving the interaction operation associated with the interaction object comprises: In response to the interaction state between the virtual object and the interactive object satisfying a second condition, an interactive control is presented, wherein the second condition is related to the interaction logic; as well as Receive trigger operations on the interactive control.

8. The method of claim 1, wherein the three-dimensional module is created using a plurality of three-dimensional components, and the plurality of three-dimensional components includes at least one three-dimensional component that supports detachment from the three-dimensional module.

9. The method of claim 8, wherein the motion logic of the three-dimensional module describes the component motion logic of at least one of the plurality of three-dimensional components.

10. The method of claim 9, wherein the plurality of three-dimensional components include at least a first three-dimensional component and a second three-dimensional component, and the first motion logic of the first three-dimensional component is independent of the second motion logic of the second three-dimensional component.

11. The method of claim 8, wherein presenting the motion of the interactive object in the virtual scene comprises: In the virtual scene, a first motion is presented corresponding to a first part of the plurality of three-dimensional components. In this process, the second part of the plurality of three-dimensional components is in a static state, or the second part exhibits a second motion, the first motion being different from the second motion.

12. The method according to claim 8, further comprising: In response to the state of the interactive object in the virtual scene satisfying a third condition, the at least one three-dimensional component is detached from the interactive object.

13. The method of claim 12, further comprising: In response to the separation of the at least one 3D component from the interactive object, a third motion of the at least one 3D component is presented, the third motion being derived based on the motion logic.

14. The method of claim 1, wherein the interactive object is created based on the following process: Based on demand information, multiple tasks are created using intelligent planning components, wherein the demand information is obtained at least based on the first content; and The multiple tasks are executed using multiple intelligent execution components to create the interactive object, the multiple tasks being used to generate different attributes of the interactive object.

15. The method of claim 14, wherein executing the plurality of tasks using a plurality of intelligent execution components comprises: Determine the structural description information from the aforementioned requirements information; as well as The three-dimensional module is generated using the first intelligent execution component based on the structural description information.

16. The method of claim 14, wherein executing the plurality of tasks using a plurality of intelligent execution components comprises: Determine motion description information from the aforementioned demand information; as well as Using a second intelligent execution component, a first script is generated based on the motion description information, and the first script describes the motion logic.

17. The method of claim 14, wherein executing the plurality of tasks using a plurality of intelligent execution components comprises: Determine the interaction description information from the aforementioned requirement information; as well as Using a third intelligent execution component, a second script is generated based on the interaction description information. The second script describes the interaction logic associated with the virtual object.

18. An interactive device, comprising: The receiving module is configured to receive first content, which describes the motion of an interactive object in natural language, the interactive object being associated with a 3D module; The first generation module is configured to present a first message, which describes the motion logic of the 3D module, and the motion logic is generated based on the first content. as well as The second presentation module is configured to present the motion of the interactive object in a virtual scene, the motion being obtained based on the motion logic.

19. An electronic device comprising: At least one processor; as well as At least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the electronic device to perform the method according to any one of claims 1 to 17 when executed by the at least one processor.

20. A computer program product tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method according to any one of claims 1 to 17.

Images