A method, device, computer equipment, storage medium and computer program product for generating virtual digital human

Abstract

The present application relates to the field of artificial intelligence technology, and in particular to a method, device, computer equipment, storage medium and computer program product for generating a virtual digital human. The method comprises: obtaining an original image to be processed, extracting features from the original image, and obtaining object feature data; in response to the demand information, calling a preset modeling algorithm to create an initial virtual image white model; creating a control point array matching the virtual image white model based on preset prior information, wherein the control point array includes a number of control points; determining key frame animation information to be generated based on the demand information, and determining motion trajectory information of the control points based on the key frame animation information; adding detail features to the virtual image white model based on the object feature data to obtain a target virtual model. The use of this method can improve the dynamic anthropomorphism of the virtual digital human and enhance the vividness of interaction with the user.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, computer equipment, storage medium and computer program product for generating a virtual digital human. Background Art

[0002] Digital customer service is a virtual human that uses artificial intelligence technology to mimic real customer service representatives and interact with users through text, voice or images. They can understand users' questions, provide answers, and handle transactions, thereby improving customer service efficiency and user experience. Digital human technology combines multiple fields such as computer graphics, artificial intelligence, and animation technology to create virtual characters that are almost indistinguishable from real humans. Digital human video refers to video content containing digital human characters, which may be completely virtual or generated through motion capture and expression capture technology of human actors. Digital human videos usually have very high visual quality and realism, and can present vivid character images and movements. The application fields of digital human video technology are very wide, including but not limited to film and TV production, game development, virtual reality and augmented reality, advertising and marketing. In general, digital human video refers to video content containing digital human characters generated by digital human technology, with high realism and visual effects, and is widely used in movies, games, virtual reality and other fields.

[0003] In the relevant technologies, digital customer service virtual people usually have the following characteristics: intelligent interaction: using natural language processing (NLP), machine learning and other technologies to understand user intentions and make corresponding responses; multi-channel support: can provide services on multiple channels such as websites, apps, social media, etc.; 7x24 hours online: not limited by time, respond to user needs at any time; personalized service: can provide customized services based on user portraits; cost-effectiveness: reduce labor costs and improve service efficiency. In short, digital customer service virtual people are an important tool for enterprises to optimize customer service and improve operational efficiency. In the synthesis of digital videos based on digital people, the steps usually include: background production: create or select the background of the video, which can be a static picture, dynamic video or 3D scene; synthesis: synthesize the digital human model with the background. Video editing software (such as AdobeAfter Effects, Premiere Pro, etc.) can be used for synthesis; editing: edit, color, add special effects, etc. to the video to make it more attractive.

[0004] However, the current virtual digital human generation technology has the following technical problems: The existing interactions of digital humans are rather mechanical and need to be optimized. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for generating a virtual digital human that can improve the dynamic anthropomorphism of the virtual digital human and enhance the vividness of the interaction with the user in response to the above-mentioned technical problems.

[0006] In a first aspect, the present application provides a method for generating a virtual digital human. The method comprises: Acquire an original image to be processed, perform feature extraction on the original image, and obtain object feature data; In response to the requirement information, a preset modeling algorithm is called to create an initial virtual image white model, wherein the virtual image white model includes a basic geometric shape matching the requirement information; Creating a control point array matching the virtual image white model based on preset prior information, wherein the control point array includes a plurality of control points distributed in a surrounding space of the virtual image white model; Determine the key frame animation information to be generated based on the demand information, and determine the motion trajectory information of the control point based on the key frame animation information; Detail features are added to the virtual image white model based on the object feature data to obtain a target virtual model.

[0007] In one embodiment, after adding detail features to the virtual image white model based on the object feature data to obtain the target virtual model, the method further includes: The virtual image white model is subjected to interference verification based on the motion trajectory information, and if interference occurs during the motion of the virtual image white model, the virtual image white model is adjusted.

[0008] In one embodiment, the control point array matching the virtual image white model is created based on preset prior information, and the control point array includes a plurality of control points distributed in the surrounding space of the virtual image white model, including: Creating an associated skeleton system based on the virtual image white model, binding the skeleton system to the virtual image white model, wherein the skeleton system includes a plurality of skeleton objects corresponding to the motion structure of the virtual image white model, wherein the skeleton objects include a parent skeleton object and a child skeleton object that are relatively arranged, and the motion of the parent skeleton object affects the rotation and movement of the child skeleton object; The control point array is simplified based on the skeleton system, so that the control points associated with the same skeleton object are simplified to the control of several of the control points.

[0009] In one embodiment, determining the key frame animation information to be generated based on the demand information, and determining the motion trajectory information of the control point based on the key frame animation information includes: Determine the motion control information of the skeleton object based on the key frame animation, and determine the weight configuration between the vertices of the virtual image white model and the skeleton object, wherein the farther the distance between the vertex and the skeleton object is, the lower the weight is; Based on the motion control information and weight information of the skeleton object, the deformation information of the surface of the virtual image white model is determined.

[0010] In one embodiment, after adding detail features to the virtual image white model based on the object feature data to obtain the target virtual model, the method further includes: Calling a pre-built natural language model, and acquiring semantic information input by the target object in the interaction based on the automatic language model; Feedback information matching the semantic information is acquired, and based on the feedback information and key frame animation information matching the feedback information, the target virtual model is controlled to perform feedback interaction.

[0011] In one embodiment, the obtaining feedback information matching the semantic information, and controlling the target virtual model to perform feedback interaction based on the feedback information and key frame animation information matching the feedback information includes: configuring personality characteristics for the target virtual model based on the demand information; The feedback information is converted into personalized form according to the personality traits, so that the feedback information performs personalized expression corresponding to the personality traits while retaining the original semantics, and feedback interaction is performed based on the converted feedback information.

[0012] In a second aspect, the present application also provides a virtual digital human generation device. The device comprises: A feature extraction module is used to obtain an original image to be processed, perform feature extraction on the original image, and obtain object feature data; A white model building module, used to call a preset modeling algorithm in response to the demand information to create an initial virtual image white model, wherein the virtual image white model includes a basic geometric shape matching the demand information; A control point configuration module, used to create a control point array matching the virtual image white model based on preset prior information, wherein the control point array includes a plurality of control points distributed in the surrounding space of the virtual image white model; A motion control module, used to determine key frame animation information to be generated based on the demand information, and determine motion track information of the control point based on the key frame animation information; The detail carving module is used to add detail features to the virtual image white model based on the object feature data to obtain a target virtual model.

[0013] In one embodiment, after the detail engraving module, it also includes: The interference verification module is used to perform interference verification on the virtual image white model based on the motion trajectory information, and if the virtual image white model has interference during motion, the virtual image white model is adjusted.

[0014] In one embodiment, the control point configuration module includes: A skeleton system module, used for creating an associated skeleton system based on the virtual image white model, binding the skeleton system to the virtual image white model, wherein the skeleton system includes a plurality of skeleton objects corresponding to the motion structure of the virtual image white model, wherein the skeleton objects include a relatively arranged parent skeleton object and a child skeleton object, and the motion of the parent skeleton object affects the rotation and movement of the child skeleton object; A simplification module is used to simplify the control point array based on the skeleton system, so that the control points associated with the same skeleton object are simplified to the control of several of the control points.

[0015] In one embodiment, the motion control module includes: A weight configuration module, used to determine the motion control information of the skeleton object based on the key frame animation, and determine the weight configuration between the vertices of the virtual image white model and the skeleton object, wherein the farther the distance between the vertex and the skeleton object is, the lower the weight is; The deformation information module is used to determine the deformation information of the virtual image white model surface based on the motion control information and weight information of the skeleton object.

[0016] In one embodiment, after the detail engraving module, it also includes: An interaction processing module, used to call a pre-built natural language model and obtain semantic information input by the target object in the interaction based on the automatic language model; A feedback information module is used to obtain feedback information matching the semantic information, and control the target virtual model to perform feedback interaction based on the feedback information and key frame animation information matching the feedback information.

[0017] In one embodiment, the feedback information module includes: A personality characteristic module, used for configuring personality characteristics for the target virtual model based on the demand information; The personality expression module is used to perform personalized conversion on the feedback information according to the personality characteristics, so that the feedback information performs personalized expression corresponding to the personality characteristics while retaining the original semantics, and performs feedback interaction based on the converted feedback information.

[0018] In a third aspect, the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps in the method for generating a virtual digital human as described in any one of the embodiments in the first aspect are implemented.

[0019] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in a method for generating a virtual digital human as described in any one of the embodiments in the first aspect.

[0020] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps in the method for generating a virtual digital human as described in any one of the embodiments in the first aspect are implemented.

[0021] The above-mentioned method, device, computer equipment, storage medium and computer program product for generating a virtual digital human can achieve the beneficial effects of the technical problems in the corresponding background technology by deducing the technical features in the claims: The embodiment of the present application provides a method for generating a virtual digital human, including: obtaining an original image to be processed, extracting features from the original image, and obtaining object feature data; in response to the demand information, calling a preset modeling algorithm to create an initial virtual image white model, the virtual image white model including a basic geometric shape matching the demand information; creating a control point array matching the virtual image white model based on preset prior information, the control point array including a number of control points distributed in the enclosed space of the virtual image white model; determining key frame animation information to be generated based on the demand information, and determining the motion trajectory information of the control point based on the key frame animation information; adding detail features to the virtual image white model based on the object feature data to obtain a target virtual model. In implementation, first, the original image to be processed is obtained from a camera or other device, and these images will serve as the basis for modeling and animation generation; the original image is extracted through image processing technology (such as edge detection, color analysis, etc.) to obtain object feature data. These features may include information such as shape, texture, color, etc.; according to the feature data and demand information (such as design requirements, target style, etc.), the preset modeling algorithm is called to create an initial virtual image white model. This white model contains basic geometric shapes that match the requirements and is the basis for subsequent modeling. According to the preset prior information (such as the typical structure and behavior of the object), control points are distributed in the enclosed space of the virtual image white model to form a control point array. These control points will be used for subsequent animation and shape changes. Based on the required information, the key frame animation information to be generated is determined, such as the main actions and state changes in the animation. Then, the key frame information is used to determine the motion trajectory of the control points in order to achieve a natural and smooth animation effect. Finally, the previously extracted object feature data is used to add details to the virtual image white model to form a target virtual model. These details can include surface texture, color depth, subtle motion features, etc., making the model more realistic and visually attractive. Through the above steps, a high-quality target virtual model that meets the required information can be obtained. The model not only has basic shapes, but also contains detailed features, which can be used in various applications, such as game characters, virtual experiments, animated films, etc. At the same time, the design of key frame animation ensures that the model's actions and performances in the application are more vivid and flexible. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1A diagram of an application environment of a method for generating a virtual digital human in one embodiment; Figure 2 A first flow chart of a method for generating a virtual digital human in one embodiment; Figure 3 It is a structural block diagram of a virtual digital human generating device in one embodiment; Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0025] In the relevant technologies, digital customer service virtual people usually have the following characteristics: intelligent interaction: using natural language processing (NLP), machine learning and other technologies to understand user intentions and make corresponding responses; multi-channel support: can provide services on multiple channels such as websites, apps, social media, etc.; 7x24 hours online: not limited by time, respond to user needs at any time; personalized service: can provide customized services based on user portraits; cost-effectiveness: reduce labor costs and improve service efficiency. In short, digital customer service virtual people are an important tool for enterprises to optimize customer service and improve operational efficiency. In the synthesis of digital videos based on digital people, the steps usually include: background production: create or select the background of the video, which can be a static picture, dynamic video or 3D scene; synthesis: synthesize the digital human model with the background. Video editing software (such as AdobeAfter Effects, Premiere Pro, etc.) can be used for synthesis; editing: edit, color, add special effects, etc. to the video to make it more attractive.

[0026] However, the current virtual digital human generation technology has the following technical problems: The existing interactions of digital humans are rather mechanical and need to be optimized.

[0027] Based on this, the embodiments of the present application provide a method, apparatus, computer device, storage medium and computer program product for generating a virtual digital human.

[0028] The method for generating a virtual digital human provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0029] In one embodiment, Figure 2 As shown, a method for generating a virtual digital human is provided, and the method is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps: Step 202: obtaining an original image to be processed, performing feature extraction on the original image, and obtaining object feature data; Step 204: In response to the requirement information, a preset modeling algorithm is called to create an initial virtual image white model, wherein the virtual image white model includes a basic geometric shape matching the requirement information; Step 206: creating a control point array matching the virtual image white model based on preset prior information, wherein the control point array includes a plurality of control points distributed in the surrounding space of the virtual image white model; Step 208: determining key frame animation information to be generated based on the demand information, and determining motion track information of the control point based on the key frame animation information; Step 2010: Adding detail features to the virtual image white model based on the object feature data to obtain a target virtual model.

[0030] In the above-mentioned method for generating a virtual digital human, reasonable deduction is performed in combination with the technical features in the embodiment, which can achieve the beneficial effect of solving the technical problems raised in the background technology: The embodiment of the present application provides a method for generating a virtual digital human, including: obtaining an original image to be processed, extracting features from the original image, and obtaining object feature data; in response to the demand information, calling a preset modeling algorithm to create an initial virtual image white model, the virtual image white model including a basic geometric shape matching the demand information; creating a control point array matching the virtual image white model based on preset prior information, the control point array including a number of control points distributed in the enclosed space of the virtual image white model; determining key frame animation information to be generated based on the demand information, and determining the motion trajectory information of the control point based on the key frame animation information; adding detail features to the virtual image white model based on the object feature data to obtain a target virtual model. In implementation, first, the original image to be processed is obtained from a camera or other device, and these images will serve as the basis for modeling and animation generation; the original image is extracted through image processing technology (such as edge detection, color analysis, etc.) to obtain object feature data. These features may include information such as shape, texture, color, etc.; according to the feature data and demand information (such as design requirements, target style, etc.), the preset modeling algorithm is called to create an initial virtual image white model. This white model contains basic geometric shapes that match the requirements and is the basis for subsequent modeling. According to the preset prior information (such as the typical structure and behavior of the object), control points are distributed in the enclosed space of the virtual image white model to form a control point array. These control points will be used for subsequent animation and shape changes. Based on the required information, the key frame animation information to be generated is determined, such as the main actions and state changes in the animation. Then, the key frame information is used to determine the motion trajectory of the control points in order to achieve a natural and smooth animation effect. Finally, the previously extracted object feature data is used to add details to the virtual image white model to form a target virtual model. These details can include surface texture, color depth, subtle motion features, etc., making the model more realistic and visually attractive. Through the above steps, a high-quality target virtual model that meets the required information can be obtained. The model not only has basic shapes, but also contains detailed features, which can be used in various applications, such as game characters, virtual experiments, animated films, etc. At the same time, the design of key frame animation ensures that the model's actions and performances in the application are more vivid and flexible.

[0031] In one embodiment, after step 2010, the method further includes: Step 302: performing interference verification on the virtual image white model based on the motion trajectory information, and if interference occurs in the motion of the virtual image white model, adjusting the virtual image white model.

[0032] Exemplarily, the terminal can extract motion trajectory information from previously determined key frame animation information. This information indicates the position, direction and posture of the virtual image at different time points; in a computer environment, the entire motion process of the virtual image is simulated. With the help of a physics engine or animation software, the position information of the virtual image at each moment in the animation process is generated in real time; using a collision detection algorithm (such as AABB, OBB or particle system, etc.), check whether the virtual image overlaps or collides with surrounding objects (which may be other objects in the scene) on its motion path; analyze whether the various parts of the virtual image exceed the expected physical range or enclosing volume at different time points to ensure its stability and consistency in motion.

[0033] For example, if interference is detected, the specific area and time point where the problem occurs need to be clearly identified. Record relevant parameters for subsequent adjustment; adjust the motion trajectory according to the specific situation of the interference; adjust the key frame position during the motion process to ensure that the avatar does not touch other objects during the motion; adjust the speed or direction of the avatar to avoid the interference area; simplify the animation path according to the motion logic and physical rules to avoid unnecessary complex movements.

[0034] In this embodiment, by implementing the above steps, it is possible to ensure that the motion path of the virtual image during the animation process is smooth and without physical staggering. This not only improves the realism and visual coherence of the animation, but also avoids unexpected display errors in real-time applications. In addition, after successful adjustment, the performance of the virtual image will be more professional, enhancing the user experience.

[0035] In one embodiment, step 206 includes: Step 402: creating an associated skeleton system based on the virtual image white model, and binding the skeleton system to the virtual image white model, wherein the skeleton system includes a plurality of skeleton objects corresponding to the motion structure of the virtual image white model, wherein the skeleton objects include a relatively arranged parent skeleton object and a child skeleton object, and the motion of the parent skeleton object affects the rotation and movement of the child skeleton object; Step 404: Simplify the control point array based on the skeleton system, so that the control points associated with the same skeleton object are simplified to the control of several of the control points.

[0036] For example, the terminal can design a corresponding skeleton system according to the motion requirements of the virtual image white model. This system should include multiple skeleton objects, each of which corresponds to the motion structure of the model (such as hands, arms, legs, etc.); identify key parts (such as joints, wrists, knees, etc.) as the main connection points of the skeleton.

[0037] Exemplarily, the terminal can set the relationship between the parent and child bone objects in the skeletal system. For example, the movement of the arm will affect the movement of the elbow and wrist, so the arm bone can be used as the parent bone of the elbow and wrist. After setting these hierarchical relationships, the movement of the parent bone will automatically affect the rotation and position change of its child bone objects, forming a hierarchical control. The terminal can bind the skeletal system to the virtual image white model, that is, connect each bone object to a different part of the model, so that when the bone moves, the corresponding part of the model also changes. The terminal can achieve this through "skinning" technology to ensure that the vertices on the surface of the model match the movement of the bones.

[0038] Then, the terminal can assign a control point group to each skeleton object, which consists of a plurality of simplified control points. Through these control point groups, the movement of the avatar can be more effectively managed and controlled without having to process each control point one by one.

[0039] In this embodiment, by implementing the above steps, the efficient combination of the skeleton system and the control point array of the virtual image can be ensured to achieve a delicate animation effect. The design of the skeleton system enables animators to easily control the virtual character, and the simplified control point array can effectively improve the efficiency of animation production. Overall, this will provide greater flexibility and controllability for animation production, while improving the fluency and naturalness of the model animation.

[0040] In one embodiment, step 208 includes: Step 502: determining the motion control information of the skeleton object based on the key frame animation, and determining the weight configuration between the vertices of the virtual image white model and the skeleton object, wherein the farther the distance between the vertex and the skeleton object is, the lower the weight is; Step 504: Determine the deformation information of the surface of the virtual image white model based on the motion control information and weight information of the skeleton object.

[0041] In this embodiment, bones with higher weight values ​​will have a more obvious effect on the corresponding model part, and vice versa. Effective weight distribution is the key to achieving natural movement and deformation, and ultimately helps to enhance the expressiveness and interactivity of the model.

[0042] In one embodiment, after step 2010, the method further includes: Step 602: calling a pre-built natural language model, and acquiring semantic information input by the target object in the interaction based on the automatic language model; Step 604: Acquire feedback information matching the semantic information, and control the target virtual model to perform feedback interaction based on the feedback information and key frame animation information matching the feedback information.

[0043] In one embodiment, step 604 includes: Step 702: configuring personality characteristics for the target virtual model based on the demand information; Step 704: Perform personalized conversion on the feedback information according to the personality characteristics, so that the feedback information performs personalized expression corresponding to the personality characteristics while retaining the original semantics, and feedback interaction is performed based on the converted feedback information.

[0044] For example, the terminal can determine which personality traits the target virtual model should have based on the demand information, such as liveliness, introversion, humor, seriousness, etc. These characteristics will affect the performance and reaction of the model in the interaction. Consider personality traits that match the character background of the virtual image to enhance consistency and credibility. Develop specific behavioral indicators and language styles for each personality trait. For example, a lively character may use more body language and cheerful intonation, while a serious character may prefer to express himself concisely. Design corresponding expressions, voice intonations, and movements to reflect these personality traits, so that the virtual model can appear more immersive and realistic in various situations.

[0045] Exemplarily, the terminal can collect user feedback information, such as questions or requests raised by the user, which should retain the original semantic content. Subsequently, the terminal can personalize the feedback information based on the configured personality characteristics; modify the tone of the feedback according to the personality characteristics, for example, a model with a humorous personality can use playful language, while a model with an introverted personality may be more cautious; insert emotional vocabulary or expressions to make the feedback more in line with the personality characteristics of the virtual model; adjust the complexity of the sentence according to the personality characteristics, for example, complex sentences or concise answers to highlight its personality characteristics, and ensure that the core meaning of the feedback information is not changed when performing the above conversion. Maintain the essence of the information through changes in grammar, vocabulary, and tone, while being consistent with the character's personality characteristics.

[0046] In this embodiment, through the above steps, the virtual model can provide a more personalized interactive experience that meets the user's expectations, avoiding a single, mechanical response method, making the interaction process more natural, vivid and interesting. The user can not only feel the personality of the model, but also feel the emotional connection in the communication, improving the overall interactive experience.

[0047] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0048] Based on the same inventive concept, the embodiment of the present application also provides a virtual digital human generation device for implementing the virtual digital human generation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the virtual digital human generation device provided below can refer to the limitations of the virtual digital human generation method above, and will not be repeated here.

[0049] In one embodiment, Figure 3 As shown, a virtual digital human generation device is provided, including: a feature extraction module, a white model construction module, a control point configuration module, a motion control module and a detail carving module, wherein: A feature extraction module is used to obtain an original image to be processed, perform feature extraction on the original image, and obtain object feature data; A white model building module, used to call a preset modeling algorithm in response to the demand information to create an initial virtual image white model, wherein the virtual image white model includes a basic geometric shape matching the demand information; A control point configuration module, used to create a control point array matching the virtual image white model based on preset prior information, wherein the control point array includes a plurality of control points distributed in the surrounding space of the virtual image white model; A motion control module, used to determine key frame animation information to be generated based on the demand information, and determine motion track information of the control point based on the key frame animation information; The detail carving module is used to add detail features to the virtual image white model based on the object feature data to obtain a target virtual model.

[0050] In one embodiment, after the detail engraving module, it also includes: The interference verification module is used to perform interference verification on the virtual image white model based on the motion trajectory information, and if the virtual image white model has interference during motion, the virtual image white model is adjusted.

[0051] In one embodiment, the control point configuration module includes: A skeleton system module, used for creating an associated skeleton system based on the virtual image white model, binding the skeleton system to the virtual image white model, wherein the skeleton system includes a plurality of skeleton objects corresponding to the motion structure of the virtual image white model, wherein the skeleton objects include a relatively arranged parent skeleton object and a child skeleton object, and the motion of the parent skeleton object affects the rotation and movement of the child skeleton object; A simplification module is used to simplify the control point array based on the skeleton system, so that the control points associated with the same skeleton object are simplified to the control of several of the control points.

[0052] In one embodiment, the motion control module includes: A weight configuration module, used to determine the motion control information of the skeleton object based on the key frame animation, and determine the weight configuration between the vertices of the virtual image white model and the skeleton object, wherein the farther the distance between the vertex and the skeleton object is, the lower the weight is; The deformation information module is used to determine the deformation information of the virtual image white model surface based on the motion control information and weight information of the skeleton object.

[0053] In one embodiment, after the detail engraving module, it also includes: An interaction processing module, used to call a pre-built natural language model and obtain semantic information input by the target object in the interaction based on the automatic language model; A feedback information module is used to obtain feedback information matching the semantic information, and control the target virtual model to perform feedback interaction based on the feedback information and key frame animation information matching the feedback information.

[0054] In one embodiment, the feedback information module includes: A personality characteristic module, used for configuring personality characteristics for the target virtual model based on the demand information; The personality expression module is used to perform personalized conversion on the feedback information according to the personality characteristics, so that the feedback information performs personalized expression corresponding to the personality characteristics while retaining the original semantics, and performs feedback interaction based on the converted feedback information.

[0055] Each module in the above-mentioned virtual digital human generation device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0056] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for generating a virtual digital human is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0057] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0058] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0059] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0060] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0061] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0062] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0063] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0064] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for generating a virtual digital human, characterized in that: The method comprises: Acquire an original image to be processed, perform feature extraction on the original image, and obtain object feature data; In response to the demand information, a preset modeling algorithm is called to create an initial virtual image white model, wherein the virtual image white model includes a basic geometric shape matching the demand information; Creating a control point array matching the virtual image white model based on preset prior information, wherein the control point array includes a plurality of control points distributed in a surrounding space of the virtual image white model; Determine the key frame animation information to be generated based on the demand information, and determine the motion trajectory information of the control point based on the key frame animation information; Detail features are added to the virtual image white model based on the object feature data to obtain a target virtual model.

2. The method according to claim 1, characterized in that After adding detail features to the virtual image white model based on the object feature data to obtain the target virtual model, the method further includes: The virtual image white model is subjected to interference verification based on the motion trajectory information, and if interference occurs during the motion of the virtual image white model, the virtual image white model is adjusted.

3. The method according to claim 1, characterized in that The control point array matching the virtual image white model is created based on the preset prior information, and the control point array includes a plurality of control points distributed in the surrounding space of the virtual image white model, including: Creating an associated skeleton system based on the virtual image white model, binding the skeleton system to the virtual image white model, wherein the skeleton system includes a plurality of skeleton objects corresponding to the motion structure of the virtual image white model, wherein the skeleton objects include a parent skeleton object and a child skeleton object that are relatively arranged, and the motion of the parent skeleton object affects the rotation and movement of the child skeleton object; The control point array is simplified based on the skeleton system, so that the control points associated with the same skeleton object are simplified to the control of several of the control points.

4. The method according to claim 3, characterized in that: The determining of the key frame animation information to be generated based on the demand information, and the determining of the motion track information of the control point based on the key frame animation information comprises: Determine the motion control information of the skeleton object based on the key frame animation, and determine the weight configuration between the vertices of the virtual image white model and the skeleton object, wherein the farther the distance between the vertex and the skeleton object is, the lower the weight is; Based on the motion control information and weight information of the skeleton object, the deformation information of the surface of the virtual image white model is determined.

5. The method according to any one of claims 1 to 4, characterized in that: After adding detail features to the virtual image white model based on the object feature data to obtain the target virtual model, the method further includes: Calling a pre-built natural language model, and acquiring semantic information input by the target object in the interaction based on the natural language model; Feedback information matching the semantic information is acquired, and based on the feedback information and key frame animation information matching the feedback information, the target virtual model is controlled to perform feedback interaction.

6. The method according to claim 5, characterized in that The obtaining of feedback information matching the semantic information, and controlling the target virtual model to perform feedback interaction based on the feedback information and key frame animation information matching the feedback information includes: configuring personality characteristics for the target virtual model based on the demand information; The feedback information is converted into personalized form according to the personality characteristics, so that the feedback information performs personalized expression corresponding to the personality characteristics while retaining the original semantics, and feedback interaction is performed based on the converted feedback information.

7. A virtual digital human generation device, characterized in that: The device comprises: A feature extraction module is used to obtain an original image to be processed, perform feature extraction on the original image, and obtain object feature data; A white model building module, used to call a preset modeling algorithm in response to the demand information to create an initial virtual image white model, wherein the virtual image white model includes a basic geometric shape matching the demand information; A control point configuration module, used to create a control point array matching the virtual image white model based on preset prior information, wherein the control point array includes a plurality of control points distributed in the surrounding space of the virtual image white model; A motion control module, used to determine key frame animation information to be generated based on the demand information, and determine motion track information of the control point based on the key frame animation information; The detail carving module is used to add detail features to the virtual image white model based on the object feature data to obtain a target virtual model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images