Digital human contents creation system and digital human contents creation method using the same

Abstract

The present invention relates to a digital human content generation system (1) and a digital human content generation method using the same. According to a preferred embodiment of the present invention, a method for generating digital human content is provided in a digital human content generation system (1) comprising a digital human server (100), a content management server (200), and a metaverse cloud server (300) network-connected thereto, comprising: a) a step in which the digital human server (100) configures a virtual model based on a pre-set virtual model configuration method; b) a step in which the digital human server (100) generates digital human information by matching pre-collected motion information with the virtual model; c) a step in which the digital human server (100) transmits the digital human information to the metaverse cloud server (300); and d) a step in which the metaverse cloud server (300) generates digital human content by combining virtual reality content information received from the content management server (200) and the digital human information.

Description

Technology Field

[0001] The present invention relates to a digital human content generation system and a digital human content generation method using the same. More specifically, the invention relates to a digital human content generation system and a digital human content generation method using the same, which generates digital human information by matching a virtual model configured based on a pre-set virtual model configuration method with pre-collected motion information, and combines this with virtual reality content information to enable natural movement of the virtual model within virtual reality and to efficiently generate digital human content within a single system. Background Technology

[0003] Due to the global spread of infectious diseases such as COVID-19, the demand for online and non-face-to-face environments in education, meetings, exhibitions, and competitions is increasing, and research and demand related to this are also surging.

[0004] Conventional technology is limited to targeting specific content and delivering one-way content to users, so technology that creates and utilizes digital humans based on virtual reality but enables diverse user participation is attracting attention.

[0005] As an example of prior art, there is Korean Registered Patent No. 10-2373608, "Electronic device and method for forming a digital human image and a program stored on a computer-readable recording medium to perform the same."

[0006] The above-described prior art comprises acquiring an image of a subject, extracting a first feature point for forming a face image of a digital human video and a second feature point for forming a hair image of a digital human video from the image of the subject, assigning a first weight to the first feature point considering the affinity between the subject and the digital human video and the age of the subject, assigning a second weight to the second feature point considering the movement of the subject, wind, and forces acting from outside the subject, assigning a third weight to the first feature point and the second feature point considering the real-time face shape and real-time posture of the subject, selecting a band model with the highest degree of agreement with the subject using the first feature point reflecting the first weight and the third weight and the second feature point reflecting the second weight and the third weight, 3D scanning the band model, forming first 3D data by capturing images from various angles, forming a first image of the subject using the first 3D data, forming second 3D data by capturing a preset expression template with a depth camera, and forming a second image representing the expression of the subject using the second 3D data. It is configured to form a digital human image by synthesizing the first image and the second image using three-dimensional animation points.

[0007] Although the aforementioned prior art has the advantage of being able to form more sophisticated and realistic digital human images by assigning weights to the digital human images based on the intimacy between the subject and the digital human image and the subject's age, it has limitations in that, due to the many considerations such as intimacy, age, and multiple weights in composing the digital human image, a large amount of resources are required to create high-resolution images of the entire body, including the face and body, and it is difficult to provide seamless video and require a significant amount of time to generate digital human content through combination with virtual reality content, and there is a problem that the improvement in the efficiency of video composition based on intimacy and weights is not significant. The problem to be solved

[0009] The present invention aims to solve the problems of the prior art described above by providing a digital human content generation system and method that enables the entire process, from image collection through a user model to the creation of virtual reality-based digital human content, to be carried out in a single system.

[0010] In addition, the present invention aims to provide an automated post-processing process that minimizes post-processing processes such as texturing and / or rigging by humans, and to provide a technology for efficiently managing various digital human content. means of solving the problem

[0012] According to a preferred embodiment of the present invention for solving the above-mentioned problems, a method for generating digital human content is provided in a digital human content generation system comprising a digital human server, a content management server, and a metaverse cloud server connected thereto, the method comprising: a) a step in which the digital human server configures a virtual model based on a pre-set virtual model configuration method; b) a step in which the digital human server generates digital human information by matching pre-collected motion information with the virtual model; c) a step in which the digital human server transmits the digital human information to the metaverse cloud server; and d) a step in which the metaverse cloud server generates digital human content by combining virtual reality content information received from the content management server and the digital human information.

[0013] According to another preferred embodiment of the present invention, the pre-set virtual model configuration method of step a) comprises: a1) a step of collecting user image information by capturing a user model through a full-body capture device provided in a virtual model generation studio network-connected to the digital human server; a2) a step of generating virtual model basic modeling information based on the user image information; and a3) a step of configuring a virtual model by post-processing the generated virtual model basic modeling information.

[0014] According to another preferred embodiment of the present invention, step a3) comprises a31) a texturing step of applying color and texture to the virtual model basic modeling information; and a32) a rigging step of applying joints and bones to the virtual model basic modeling information; wherein at least one of step a31) and step a32) is automatically performed by an artificial intelligence processing module.

[0015] According to another preferred embodiment of the present invention, the step a31) is characterized by being automatically processed based on at least two user image information captured by at least one different position or a plurality of different wavelengths provided in the full-body capture device.

[0016] According to another preferred embodiment of the present invention, the user image information includes a plurality of preset pose image information of the user model, and the step a32) is characterized by being automatically processed based on the pose image information of the user model.

[0017] According to another preferred embodiment of the present invention, the pre-collected motion information is movement information of a user model collected through a motion capture device provided in a motion information collection studio networked with the digital human server, and is characterized by including at least one of face motion information representing facial movement and body motion information representing body and hand movement.

[0018] According to another preferred embodiment of the present invention, the digital human information is composed of a plurality of digital human information by combining at least one motion information for a plurality of virtual models, and each of the plurality of digital human information includes one or more signature motion information such that at least one of the face motion information and body motion information in the previously collected motion information can be distinguished from other digital human information.

[0019] According to another preferred embodiment of the present invention, the digital human content further includes preset event information, and the preset event information is characterized by being generated based on the signature motion information.

[0020] According to another preferred embodiment of the present invention, the digital human information is characterized by further comprising voice information of a user model collected in the motion information collection studio.

[0021] According to another preferred embodiment of the present invention, a digital human content generation system is provided, comprising a digital human server, a content management server, and a metaverse cloud server networked thereto, wherein the digital human server performs the function of configuring a virtual model based on a pre-set virtual model configuration method, generating digital human information by matching pre-collected motion information with the virtual model, and transmitting the digital human information to the metaverse cloud server; a content management server performs the function of managing a plurality of virtual reality content information and transmitting at least one virtual reality content information to the metaverse cloud server upon a request from the metaverse cloud server; and a metaverse cloud server performs the function of generating digital human content by combining the virtual reality content information received from the content management server and the digital human information. Effects of the invention

[0023] According to the present invention, by enabling the configuration of a virtual model, the generation of digital human information, and the creation of digital human content through the combination of virtual reality content and digital human information to be carried out in a single system, there is an effect of enabling the creation of virtual reality-based digital human content that minimizes necessary resources.

[0024] In particular, the present invention has the advantage of enabling rapid and efficient virtual model construction by allowing post-processing steps, such as texturing and / or rigging for constructing a virtual model, to be automatically performed by artificial intelligence.

[0025] In addition, the present invention has the advantage that digital human content configuration and management can be easily achieved through signature motions. Brief explanation of the drawing

[0027] FIG. 1 is a configuration diagram of a digital human content generation system according to an embodiment of the present invention, FIG. 2 is a configuration diagram of a digital human content generation system according to another embodiment of the present invention, FIG. 3 is a flowchart of a method for generating digital human content according to an embodiment of the present invention, FIG. 4 is a flowchart of a method for generating digital human content according to another embodiment of the present invention, FIG. 5 is a configuration diagram of a digital human server according to an embodiment of the present invention, FIG. 6 is a schematic diagram showing the configuration of a virtual model generation studio and a network connection with a digital human server according to an embodiment of the present invention. FIG. 7 is a schematic diagram showing the configuration of a motion information collection studio and a network connection with a digital human server according to an embodiment of the present invention. FIG. 8 is a flowchart illustrating the steps of constructing a virtual model according to an embodiment of the present invention, FIG. 9 is a schematic diagram showing the configuration of a virtual model generation studio according to another embodiment of the present invention, FIG. 10 is a schematic diagram illustrating the steps of constructing a virtual model according to another embodiment of the present invention, FIG. 11 is a schematic diagram illustrating a pose image of a user model according to an embodiment of the present invention, FIG. 12 is a schematic diagram illustrating signature motion information of a user model according to an embodiment of the present invention. Specific details for implementing the invention

[0028] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. However, in describing the present invention, if the technical concept of the present invention is obscured or made unclear by specifically describing known configurations, such description of known configurations will be omitted.

[0029] The 'user model' according to the present invention is a real-world model that is the subject of collecting user image information, which forms the basis for constituting a virtual model, and motion information and / or voice information included in digital human information. The user image information, motion information, and voice information may be provided by two or more types of information by a single user model, or different user models may each provide their respective information. For example, one user model may be configured to provide user image information that forms the basis for constituting a virtual model, and another user model may be configured to provide motion information and voice information.

[0030] Hereinafter, a digital human content creation system (1) and a method for creating digital human content using the same will be described in detail based on the drawings.

[0032] FIG. 1 is a configuration diagram of a digital human content generation system according to one embodiment of the present invention, FIG. 2 is a configuration diagram of a digital human content generation system according to another embodiment of the present invention, FIG. 5 is a configuration diagram of a digital human server according to one embodiment of the present invention, FIG. 6 is a schematic diagram showing the configuration of a virtual model generation studio and a network connection with a digital human server according to one embodiment of the present invention, FIG. 7 is a schematic diagram showing the configuration of a motion information collection studio and a network connection with a digital human server according to one embodiment of the present invention, and FIG. 9 is a schematic diagram showing the configuration of a virtual model generation studio according to another embodiment of the present invention.

[0033] A digital human content generation system (1) according to an example of the present invention includes, as shown in FIG. 1, a digital human server (100), a content management server (200), and a metaverse cloud server (300) connected to the same.

[0034] The digital human server (100) configures a virtual model based on a pre-set virtual model configuration method. The digital human server (100) generates digital human information by matching pre-collected motion information with the virtual model and performs the function of transmitting the digital human information to the metaverse cloud server (300).

[0035] A digital human server (100) according to an example of the present invention, as illustrated in FIG. 5, includes a memory unit (104) for storing user image information collected from a virtual model creation studio (120) described later, motion information collected from a motion information collection studio (140), as well as data (information) temporarily generated during the virtual model configuration and digital human creation process, a communication unit (105) configured to include a communication module, a virtual model configuration / management unit (106) for configuring and managing a virtual model, a digital human information creation / management unit (107) for creating and managing digital human information, and an operation unit (102) for overall operation of the server.

[0036] The above content management server (200) is a server responsible for managing the overall content, such as managing multiple virtual reality content information, various user model information, and digital human information, and performs the function of transmitting at least one virtual reality content information to the metaverse cloud server (300) upon the request of the above metaverse cloud server (300).

[0037] The above content management server (200) may be equipped with an operation module responsible for the overall function of server operation, a user model management module, a digital human information management module, a virtual reality content information management module, and a communication module.

[0038] For example, the content management server (200) may be configured to relay the metaverse cloud server (300) and the streaming server (500, see FIG. 5) described later to transmit digital human content from the metaverse cloud server (300) to the streaming server (500), and in this case, a digital human content management module (not shown) for managing the digital human content may be further provided.

[0039] The above multiple virtual reality content information may be stored in advance on a storage medium (not shown) provided in the content management server (200), but preferably may be stored in a separate virtual reality content information DB (not shown) network-connected to the content management server (200), and may be received from a streaming server (500) described later in the form of streamable video content. For example, the above virtual reality content information relates to video content that allows one to experience virtual reality directly or indirectly in various fields, including educational content and performance content, and may be generated and stored on various content servers.

[0040] The above metaverse cloud server (300) performs the function of creating digital human content by combining virtual reality content information received from the content management server (200) and the digital human information.

[0041] For example, the above metaverse cloud server (300) may be equipped with an operation module responsible for the overall function of server operation, a digital human content DB, a digital human content management module, an event information management module, and a communication module.

[0042] The above event information management module can be integrated into the digital human content management module, and pre-configured event information can be stored together in the digital human content DB.

[0043] A digital human content generation system (1) according to another embodiment of the present invention may further include a display device (400) capable of displaying digital human content generated from the metaverse cloud server (300) in addition to the digital human server (100), content management server (200), and metaverse cloud server (300), and may further include a virtual model generation studio (120) capable of collecting user images of a user model to configure a virtual model and / or a motion information collection studio (140) capable of collecting motion information of a user model.

[0044] The above network may be configured as a 5G-based network. Since there is a high possibility of data loss or time delay occurring in the process of efficiently transmitting data of the virtual reality content information as well as digital human information when configured as a 5G-based network compared to an existing low-speed network, it is desirable to configure it as a 5G-based network in order to enable faster and larger-capacity data transmission.

[0046] FIG. 3 is a flowchart of a method for generating digital human content according to one embodiment of the present invention, FIG. 4 is a flowchart of a method for generating digital human content according to another embodiment of the present invention, FIG. 8 is a flowchart explaining the steps for configuring a virtual model according to one embodiment of the present invention, and FIG. 10 is a schematic diagram explaining the steps for configuring a virtual model according to another embodiment of the present invention.

[0047] A method for generating digital human content according to a preferred embodiment of the present invention is performed in a digital human content generation system (1) comprising a digital human server (100), a content management server (200), and a metaverse cloud server (300) network-connected thereto.

[0048] As illustrated in FIG. 4, the digital human content generation method comprises the following steps: a step (a) in which the digital human server (100) configures a virtual model based on a pre-set virtual model configuration method; b) in which the digital human server (100) generates digital human information by matching pre-collected motion information with the virtual model; c) in which the digital human server (100) transmits the digital human information to the metaverse cloud server (300); and d) in which the metaverse cloud server (300) generates digital human content by combining virtual reality content information received from the content management server (200) with the digital human information. The collection of motion information in step b may be performed simultaneously with step a or before step a.

[0049] As another example, the digital human content generation method described above may further include the step (e) in which the metaverse cloud server (300) transmits the digital human content to the streaming server (500), as illustrated in FIG. 5.

[0050] The streaming server (500) is network-connected to the metaverse cloud server (300), and, for example, can receive digital human content from the metaverse cloud server (300) and provide it to a user terminal, etc., in the form of real-time streaming. Various users can watch the corresponding digital human content provided by the streaming server (500) through their user terminals.

[0051] In addition, the streaming server (500) may possess various types of video content in addition to the real-time streaming service of the digital human content, and may provide video content to the content management server (200).

[0052] For example, the digital human content may be transmitted directly from the metaverse cloud server (300) to the streaming server (500) via a network, or, as another example, the aforementioned content management server (200) may be configured to relay between the metaverse cloud server (300) and the streaming server (500). The configuration in which the metaverse cloud server (300) transmits the digital human content to the streaming server (500) via the content management server (200) through a network reduces the load on the metaverse cloud server (300) and enables unified content management at the content management server (200), thereby allowing for efficient and accurate content management.

[0053] The above-mentioned user terminal may be understood as the aforementioned display device (400) and / or a computer including the display device (400), and may be various types of devices capable of viewing virtual reality content, such as a smartphone, tablet, PC monitor, or HMD (Head mount display), used by a user viewing digital human content. It is desirable to configure the above-mentioned user terminal to be movable so that various digital human content can be utilized anytime and anywhere, and to this end, it is desirable to configure a wireless network.

[0054] In the above step e, pre-set event information described below may be displayed together, and the user can view virtual reality content and digital human content including digital human information more realistically through the event information.

[0056] As illustrated in FIG. 8, the pre-set virtual model configuration method of step a can be performed by including the step (a1) of collecting user image information by capturing a user model through a full-body capture device provided in a virtual model generation studio (120) network-connected to the digital human server (100), the step (a2) of generating virtual model basic modeling information based on the user image information, and the step (a3) ​​of configuring a virtual model by post-processing the generated virtual model basic modeling information.

[0057] The virtual model generation studio (120) described above includes a full-body capture device (122) as illustrated in FIG. 6, and the full-body capture device (122) is equipped with at least a plurality of cameras (124) and lights (126, 126'), and is configured to include a control unit (129) equipped with a communication module that controls the plurality of cameras (124) and lights (126, 126') and performs the function of acquiring user image information and transmitting it to the digital human server (100) through a network.

[0058] For example, the full-body capture device (122) may be configured such that 16 to 64 volumetric cameras or 32 to 128 photogrammetric cameras are evenly distributed on the outside of a steel frame (not shown in the drawing) in which a user model can be accommodated, thereby capturing the user model's 360-degree full body. For example, the volumetric cameras may be cameras capable of generating depth values, such as RGB-D cameras or RGB cameras combined with a Kinect sensor.

[0059] The above lights (126, 126') may be provided in multiple numbers so as not to cause shadows on the user model, and it is desirable to arrange and set them so that the texture of the user model is clearly visible while preventing the quality of the user image from being degraded due to unnecessary shadows. The above lights (126, 126') may be provided in various locations or configured to irradiate two or more wavelengths for texturing and rigging automation described later.

[0060] The step (a2) of generating virtual model basic modeling information based on the above user image information is to collect user images of the 360-degree full body of the user model (UM), and to generate virtual model basic modeling information through an automated modeling process by combining each image using artificial intelligence.

[0061] For example, the above virtual model basic modeling information can be understood as a 360-degree external view of a user model (UM) without depth. As another example, when a volumetric camera is used in the full-body capture device (122), the above virtual model basic modeling information may be a 360-degree external view in which colors and textures or joints and bones are simply applied by measuring depth values ​​from the user image of the user model and performing low-quality texturing and / or rigging.

[0062] The above virtual model basic modeling information can be used to construct a three-dimensional virtual model with a sense of depth through post-processing such as texturing and rigging.

[0063] For example, the above step a3 may include a texturing step (a31) that creates a sense of depth by applying color and texture to the virtual model basic modeling information, and a rigging step (a32) that enables movement of the virtual model by applying joints and bones to the virtual model basic modeling information and combining them with motion information described later. At this time, at least one of the above step a31 (texturing step) and step a32 (rigging step) may be performed automatically by an artificial intelligence processing module.

[0064] For example, as illustrated in FIG. 10, a user image of a user model (UM) can be collected, and virtual model basic modeling information (AM1) can be generated based on the user image, and a textured virtual model basic modeling information (AM2) and a virtual model (AM) that has been sculpted through rigging can be sequentially constructed. The unexplained reference numeral RGM is a rigging basic model for providing joints and bones to the textured virtual model basic modeling information (AM2).

[0065] Conventionally, the texturing and rigging steps mentioned above had the problem of consuming a lot of time and manpower in creating digital human content because designers or graphic engineers had to manually post-process the virtual model to construct (create) it, and even when using a volumetric camera, the quality of texturing and rigging was poor, requiring additional work.

[0066] However, the post-processing process according to the present invention can efficiently generate digital human content by enabling the texturing step (a31) and / or rigging step (a32) to be performed automatically.

[0067] For example, the above step a31 can be automatically processed based on at least two user image information captured by at least one different position or a plurality of lights having different wavelengths equipped in the full-body capture device.

[0068] As illustrated in FIG. 9, first, a user image is acquired (see FIG. 9 (a)) while controlling the lighting (126) so that no shadow is generated on the user model (UM), and then a user image modified from the existing collected user image is acquired (see FIG. 9 (b)) by turning the lighting at a specific location on or off, or by adjusting the wavelength of the lighting so that some lighting (126') has a different wavelength, and by performing an analysis of the difference between the original user image and the modified user image using an artificial intelligence processing module, the texturing is further highlighted and the texturing can be automatically processed in the virtual model basic modeling information.

[0070] FIG. 11 is a schematic diagram illustrating a pose image of a user model according to an embodiment of the present invention.

[0071] For example, the user image information includes a plurality of preset pose image information (PI1, PI2, PI3) of the user model, and the a32 step can be automatically processed based on the pose image information (PI1, PI2, PI3) of the user model.

[0072] For example, a digital human content generation system (1) according to an example of the present invention may additionally collect user images based on each preset pose while causing a user model to assume a preset pose in the virtual model generation studio (120).

[0073] In this case, by comparing the user image information (PI0) before taking the preset pose with the pose image information (PI1, PI2, PI3) of the user model, the shape of the joints and bones of the user model for rigging work can be easily identified.

[0074] Data comparing the user image information (PI0) before assuming these preset poses with the user model's pose image information (PI1, PI2, PI3), i.e., difference analysis information, can be continuously stored in the digital human server. As difference analysis information is accumulated through preset poses of user models having various sizes and shapes, the rigging work on the virtual model basic modeling information can be advanced (precise rigging work). In particular, by performing a comparative analysis of each user image information (PI0) and the user model's preset pose image information (PI1, PI2, PI3) using an artificial intelligence processing module, rigging on the virtual model basic modeling information can be automatically processed. The texturing step (a31) and the rigging step (a32) can be performed simultaneously or sequentially, and step a32 may be performed before step a31.

[0076] For example, the pre-collected motion information is movement information (expressions and / or movements) of a user model collected through a motion capture device provided in a motion information collection studio (140) network-connected to the digital human server (100), and may include at least one of face motion information representing facial movements and body motion information representing body and hand movements.

[0077] The above face motion information enables the user model's emotions or psychological state to be conveyed through the user model's gaze or facial expressions, and the body motion information enables the user model's movements to be conveyed.

[0078] The motion information collection studio (140) comprises, as illustrated in FIG. 7, motion capture devices (142, 142', 144', 146', 148'), and a control unit (149) equipped with a communication module that controls the motion capture devices (142, 142', 144', 146', 148') and performs the function of acquiring at least one of face motion information representing the movement of the face (UF) of the user model (UM) and body motion information representing the movement of the hand / body (UB) of the user model (UM) and transmitting it to the digital human server (100) via a network.

[0079] For example, the motion capture device may be configured in the form of a camera (142) to capture the entire body of a user model (UM) and to recognize and store the movements of the face (UF) and the body (UB) separately.

[0080] As another example, the motion capture device may be configured to include a face motion capture (detection) device (142') that collects movement of the user model's face (UF) and / or voice information of the user model described later, or a body motion capture (detection) device (144', 146', 148') in the form of a sensor (144'), a glove (146'), and a smart watch (148') that is attached to the user model's body (UB) to collect movement information of the user model's body (UB).

[0081] The above camera (142) or face motion capture device (142') captures the gaze processing and facial expressions of the user model's face and allows for the identification of feature points based on changes in gaze or facial expression, and the above digital human server (100) can collect face motion information of the user model through changes in these feature points.

[0082] For example, body motion information of the user model can be collected by detecting the user model's body movement by comparing the user model's movement before and after using the camera (142).

[0083] As another example, when using a body motion capture device (144') that is wired or wirelessly connected to a control unit (149) provided in the motion information collection studio (140), the body motion capture device (144') may be a sensor of various types, such as a position sensor or a tilt sensor, and is attached to the body of a user model. When the position changes according to the user model's movements, the changed state information is transmitted to the control unit (149), thereby enabling the collection of user model body motion information according to the user model's movements.

[0084] The control unit (149) transmits the face motion information of the user model and / or the body motion information of the user model collected by the camera (142), the face motion detection device (142') and / or the body motion detection device (144', 146', 148') through the communication module to the digital human server (100).

[0086] FIG. 12 is a schematic diagram illustrating signature motion information of a user model according to an embodiment of the present invention.

[0087] The digital human information of the present invention may be composed of multiple items by combining at least one motion information for a plurality of virtual models.

[0088] For example, as illustrated in FIG. 12, the plurality of digital human information may each include one or more signature motion information (SM1, SM2, SM3) such that at least one of the face motion information and body motion information in the previously collected motion information can be distinguished from other digital human information.

[0089] For example, the above signature motion information (SM1, SM2, SM3) can be pre-set according to the user model. For instance, depending on each user model, the user model itself or through consultation can set the signature motion and determine it as the user model's unique signature motion, and the motion can be performed at least once to combine the motion information with the corresponding digital human information.

[0090] As another example, the above signature motion information (SM1, SM2, SM3) may compare and analyze various motion information collected by the movement of a user model with motion information collected by the movement of another user model, and automatically determine the motion information that differs from the motion information collected by the movement of another user model as the signature motion of the corresponding user model.

[0091] The above signature motion information (SM1, SM2, SM3) enables multiple digital human information to be distinguished from other digital human information, thereby allowing for efficient management of digital human information and the setting and management of event information described below.

[0092] For example, the digital human content may further include pre-set event information (not shown). The pre-set event information may be generated so that the event information is displayed in a specific situation pre-set when the virtual reality content is created, and, for example, may be configured to be displayed based on the signature motion information.

[0093] The above event information is additionally displayed in the virtual reality content information in a specific action or situation when the digital human content is displayed on the display device (400), and can be displayed in various forms (shape, color, etc.) depending on the motion of the digital human. The above event information can be stored in the metaverse cloud server (300) either independently or while included in the digital human content.

[0094] In particular, the above event information can be generated based on the signature motion information (SM1, SM2, SM3) that allows the digital human to be distinguished from other digital humans, thereby displaying unique event information for each digital human, which has the advantage of further diversifying digital human content.

[0095] For example, the above event information may be included in the digital human content and displayed whenever the digital human information displayed on the display device (400) includes signature motion information (SM1, SM2, SM3), that is, whenever the user model performs the corresponding signature motion, and may be configured so that each event information is displayed more maximally when other digital human information is displayed simultaneously including its own signature motion information (SM1, SM2, SM3).

[0097] For example, the digital human information may be configured to further include voice information of a user model collected in the motion information collection studio (140).

[0098] The voice information of the above user model enables the management of two or more digital human information and / or digital human content to be provided in more diverse forms.

[0099] For example, the voice information of the user model may include information on the timbre, tone, or speech style of the user model, and in addition to the face motion information and body motion information, the timbre, tone, or speech style may be configured as signature motion information.

[0100] In this case, when voice information of another user model is combined with the digital human information, if the corresponding signature motion information, such as timbre, tone, or manner of speech, is included, the aforementioned event information may be configured to be included.

[0102] A method for generating digital human content according to one embodiment of the present invention is implemented in the form of program instructions that can be executed on various computers and is recorded on a computer-readable recording medium.

[0103] The above-mentioned recording medium may include program instructions, data files, data structures, etc., either alone or in combination, and may be, for example, a magnetic recording medium such as a hard disk or floppy disk, an optical recording medium such as a CD or DVD, a magneto-optical medium such as a floptical disk, ROM, RAM, flash memory, etc.

[0104] The program instructions recorded on the above-mentioned recording medium may be specifically designed or configured for the present invention and may be known and available. For example, the program instructions may include machine code or high-level language code.

[0106] Although the present invention has been described in detail above with reference to specific embodiments, the above embodiments are merely examples to facilitate understanding of the invention. Therefore, substitutions, additions, and modifications made within the scope of the technical concept of the invention are also considered to fall within the scope of protection of the present invention as defined by the following claims. Explanation of the symbols

[0108] 1 : Digital Human Content Creation System 100 : Digital Human Server 120: Virtual Model Creation Studio 140: Motion Data Collection Studio 200: Content Management Server 300: Metaverse Cloud Server 400 : Display device

Claims

Claim 1 A method for generating digital human content performed in a digital human content generation system (1), comprising a digital human server (100), a content management server (200), and a metaverse cloud server (300) networked therewith, wherein the digital human server (100) configures a virtual model based on a pre-set virtual model configuration method; b) the digital human server (100) generates digital human information by matching pre-collected motion information with the virtual model; c) the digital human server (100) transmits the digital human information to the metaverse cloud server (300). and d) a step in which the metaverse cloud server (300) generates digital human content by combining virtual reality content information received from the content management server (200) and the digital human information; wherein the pre-set virtual model configuration method of step a) comprises: a1) a step of collecting user image information by photographing a user model through a full-body capture device provided in a virtual model generation studio (120) network-connected to the digital human server (100); a2) a step of generating virtual model basic modeling information based on the user image information; and a3) a step of constructing a virtual model by post-processing the generated virtual model basic modeling information; and step a3) comprises: a31) a texturing step of applying color and texture to the virtual model basic modeling information; and a32) a rigging step of applying joints and bones to the virtual model basic modeling information;A method for generating digital human content, comprising: a31) and a32), wherein at least one of the steps a31) and a32) is automatically performed by an artificial intelligence processing module; wherein the step a31) is automatically processed based on at least two user image information captured by at least one or more lights having different positions or different wavelengths equipped in the full-body capture device, wherein the user image is acquired while controlling the lights so that no shadow is generated on the user model, and then a user image modified from the previously collected user image is acquired by turning the lights at a specific position on or off or adjusting the wavelength of the lights so that some lights have different wavelengths, and the difference analysis between the initial user image and the modified user image is performed by an artificial intelligence processing module. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 A method for generating digital human content according to claim 1, wherein the user image information includes a plurality of preset pose image information of the user model, and the step a32) is automatically processed based on the pose image information of the user model. Claim 6 A method for generating digital human content according to claim 1, wherein the pre-collected motion information is motion information of a user model collected through a motion capture device provided in a motion information collection studio (140) network-connected to the digital human server (100), and is characterized by including at least one of face motion information representing facial movement and body motion information representing body and hand movement. Claim 7 A method for generating digital human content according to claim 6, wherein the digital human information is composed of a plurality of digital human information by combining at least one motion information for a plurality of virtual models, and each of the plurality of digital human information includes one or more signature motion information such that at least one of the face motion information and body motion information in the previously collected motion information is distinguishable from other digital human information. Claim 8 A method for generating digital human content according to claim 7, wherein the digital human content further includes preset event information, and the preset event information is generated based on the signature motion information. Claim 9 A method for generating digital human content according to claim 6, wherein the digital human information further comprises voice information of a user model collected in the motion information collection studio (140). Claim 10 A digital human content creation system (1) comprising a digital human server (100), a content management server (200), and a metaverse cloud server (300) network-connected thereto, wherein the digital human server (100) performs the function of configuring a virtual model based on a pre-set virtual model configuration method, generating digital human information by matching pre-collected motion information with the virtual model, and transmitting the digital human information to the metaverse cloud server (300); a content management server (200) performs the function of managing a plurality of virtual reality content information and transmitting at least one virtual reality content information to the metaverse cloud server (300) upon a request from the metaverse cloud server (300); and a metaverse cloud server (300) performs the function of generating digital human content by combining the virtual reality content information received from the content management server (200) and the digital human information.A digital human content generation system comprising: a pre-configured virtual model configuration method comprising: collecting user image information by capturing a user model through a full-body capture device provided in a virtual model generation studio (120) network-connected to the digital human server (100); generating virtual model basic modeling information based on the user image information; and constructing a virtual model by post-processing the generated virtual model basic modeling information. The post-processing of the generated virtual model basic modeling information includes texturing to provide color and texture to the virtual model basic modeling information. The texturing is automatically processed based on at least two user image information captured by at least one or more lights having different positions or different wavelengths provided in the full-body capture device. The system is characterized by acquiring a user image while controlling the lights so that no shadows of the user model are generated, then acquiring a user image modified from the previously collected user image by turning the lights at specific positions on or off or adjusting the wavelengths of the lights so that some lights have different wavelengths, and performing an analysis of the difference between the initial user image and the modified user image using an artificial intelligence processing module.

Images