Digital human system application method and device

Abstract

The invention provides a digital human system application method and device, and the method specifically comprises the steps: connecting a display device, and starting a pre-stored digital human system through a starting script; acquiring three-dimensional model data and human body action data of a digital human in a digital human system; decomposing the three-dimensional model data and the human body action data into a plurality of processing tasks through a rendering engine, and transmitting the plurality of processing tasks to a preset graphics processor; and obtaining a digital human picture generated by the graphics processor based on the plurality of processing tasks, and sending the digital human picture to the display equipment. The application efficiency of the digital human system can be improved.

Description

Technical Field

[0001] The embodiments of the present application belong to the field of Internet technology, and in particular, relate to a digital human system application method and device. Background Art

[0002] The digital human system is a virtual character system built through deep learning and advanced algorithms. The digital human system has a highly simulated appearance, voice and movements, and can interact with natural language, understand complex situations and respond accordingly, just like humans.

[0003] However, existing digital human systems are often highly dependent on large computing devices, especially servers equipped with high-performance graphics cards. Although servers can provide powerful data processing and graphics rendering capabilities, their inherent large size and complex deployment environment limit the usage scenarios and freedom of digital human systems. Because the complex deployment environment often significantly increases the user's manual settings and deployment steps, how to simplify the application process of the digital human system is an issue that needs to be urgently addressed. Summary of the invention

[0004] The present application provides a digital human system application method and device to solve the above-mentioned existing technical problem of how to simplify the application process of the digital human system.

[0005] In a first aspect, an embodiment of the present application provides a digital human system application method, which is applied to a portable device. The digital human system application method includes: Connect the display device and start the pre-stored digital human system through the startup script; Acquire the three-dimensional model data and human motion data of the digital human in the digital human system; Decomposing the three-dimensional model data and the human motion data into a plurality of processing tasks through a rendering engine, and transmitting the plurality of processing tasks to a preset graphics processor; A digital human image generated by the graphics processor based on the plurality of processing tasks is obtained, and the digital human image is sent to the display device.

[0006] The beneficial effects of the embodiments of the present application lie in two aspects. On the one hand, by connecting a display device and starting a pre-stored digital human system through a startup script, since the pre-stored digital human system is started when the display device is connected, it is possible to connect and use the system immediately. This connect and use method is beneficial to improving the use speed of the digital human system. On the other hand, the three-dimensional model data and human motion data of the digital human in the digital human system are obtained, and the three-dimensional model data and the human motion data are decomposed into multiple processing tasks through a rendering engine, and the multiple processing tasks are transmitted to a preset graphics processor, and the digital human image generated by the graphics processor based on the multiple processing tasks is obtained, and the digital human image is sent to the display device, which reduces the user's manual settings and deployment steps, thereby simplifying the application process of the digital human system, and is beneficial to improving the application efficiency of the digital human system.

[0007] In a possible implementation of the first aspect, connecting a display device and starting a pre-stored digital human system through a startup script include: Obtaining a hot plug signal sent by the display device through an input and output interface, wherein the input and output interface includes one or a combination of an HDMI interface, a USB interface, and an Ethernet interface; When the hot plug signal is a high level signal, a data transmission channel is established between the portable device and the display device; When the data transmission channel meets the preset conditions, the pre-stored digital human system is started by starting the script.

[0008] In the embodiment of the present application, a data transmission channel is established between the portable device and the display device to ensure that the portable device can stably transmit the digital human image to the display device, thereby improving the efficiency and stability of the digital human image transmission.

[0009] In a possible implementation of the first aspect, when the data transmission channel meets a preset condition, starting a pre-stored digital human system by starting a script includes: Acquiring the transmission delay time of the data transmission channel, and when the transmission delay time is less than the preset delay time in the preset condition, starting the pre-stored digital human system through a startup script; Alternatively, the transmission rate of the data transmission channel is obtained, and when the transmission rate is greater than the preset rate in the preset condition, the pre-stored digital human system is started by starting the script.

[0010] In the embodiment of the present application, when the data transmission channel meets the preset conditions, the pre-stored digital human system is started by starting the script, and the digital human system can automatically avoid network congestion or unstable periods, effectively reducing adverse situations such as startup failure, data transmission interruption or delay caused by network problems, and enhancing the stability and reliability of the digital human system. From the perspective of user experience, when the transmission delay is less than the preset delay or when the transmission rate is greater than the preset rate, it can provide users with a smoother and faster data interaction experience, enhancing user satisfaction and loyalty.

[0011] In a possible implementation of the first aspect, the acquiring the three-dimensional model data and the human motion data of the digital human in the digital human system includes: Acquire a first file and a second file of the digital human system; In the first file, the three-dimensional model data of the digital human is obtained, and in the second file, the human body motion data of the digital human is obtained.

[0012] In the embodiment of the present application, the digital human can be reconstructed through three-dimensional model data and human motion data to ensure that the motion performance of the digital human is completely consistent with the digital human system. This instant feedback mechanism not only improves the user experience, but also enhances the interactivity and immersion of the digital human.

[0013] In a possible implementation manner of the first aspect, decomposing the three-dimensional model data and the human motion data into a plurality of processing tasks by a rendering engine, and transmitting the plurality of processing tasks to a preset graphics processor, includes: Combining the three-dimensional model data and the human body motion data into rendering data; The rendering engine decomposes the rendering task of the rendering data into a plurality of processing tasks, and transmits the plurality of processing tasks to a preset graphics processor.

[0014] In the embodiment of the present application, the graphics processor has a powerful parallel computing capability, and contains a large number of processing units and multiple stream processors. When multiple processing tasks are sent to the graphics processor at the same time, these processing tasks can be executed in parallel on multiple processing units of the graphics processor. This parallel processing method significantly improves the computing efficiency, so that processing tasks that originally took a long time to complete can be processed in a shorter time, thereby speeding up the overall workflow.

[0015] In a possible implementation of the first aspect, after acquiring the digital human picture generated by the graphics processor based on the multiple processing tasks and sending the digital human picture to the display device, the digital human system application method further includes: Collecting user voice and converting the user voice into first text information; Inputting the first text information into a deep learning model, and obtaining second text information output by the deep learning model based on the first text information; The second text information is converted into a response voice, and the response voice is sent to the display device.

[0016] In the embodiments of the present application, in the digital age, users expect the interaction with the display device to be more natural and smooth. By broadcasting the answering voice through the display device, it not only responds to the user's voice, but also provides feedback in a more humane way, thereby enhancing the user's sense of participation and immersion.

[0017] In a possible implementation manner of the first aspect, inputting the first text information into a deep learning model, and obtaining second text information output by the deep learning model based on the first text information includes: Obtain a model file of the deep learning model, and load the deep learning model from the model file by using a loading script; The first text information is input into the deep learning model, and the second text information output by the deep learning model based on the first text information is obtained. In an embodiment of the present application, the model file serves as a carrier of the deep learning model, and contains the network parameters and structural information optimized by the deep learning model during the training process. These parameters and structural information are the basis for the deep learning model to perform prediction and reasoning. By loading the model file, the deep learning model can quickly restore the complete state of the model without having to re-perform the time-consuming training process, thereby improving the convenience and efficiency of the deep learning model application.

[0018] In a possible implementation of the first aspect, after acquiring the digital human picture generated by the graphics processor based on the multiple processing tasks and sending the digital human picture to the display device, the digital human system application method further includes: An update command is obtained, and update content is obtained from a server through the update command. An update operation is performed on the digital human system through the update content to obtain the updated digital human system.

[0019] In the embodiments of the present application, the updated digital human system generally has stronger interactive capabilities, including more accurate natural language processing technology, which enables the digital human to better understand the user's intentions and emotions and give more appropriate and humane responses.

[0020] In a possible implementation of the first aspect, after acquiring the digital human picture generated by the graphics processor based on the multiple processing tasks and sending the digital human picture to the display device, the digital human system application method further includes: A push instruction is obtained, the push instruction is executed, and the digital human image is pushed to a preset database.

[0021] In the embodiment of the present application, the push instruction is executed to push the digital human image to a preset database. The database, as a persistent storage medium for data, can store the digital human image on a disk for a long time, ensuring that the digital human image will not be lost even in the event of a power outage or system crash. This persistent storage mechanism provides a strong guarantee for the long-term preservation and reliability of the digital human image.

[0022] In a second aspect, an embodiment of the present application provides a digital human system application device, including: A connection module is used to connect to a display device and start a pre-stored digital human system through a startup script; An acquisition module, used to acquire the three-dimensional model data and human motion data of the digital human in the digital human system; A transmission module, used for decomposing the three-dimensional model data and the human motion data into a plurality of processing tasks through a rendering engine, and transmitting the plurality of processing tasks to a preset graphics processor; The sending module is used to obtain the digital human image generated by the graphics processor based on the multiple processing tasks, and send the digital human image to the display device.

[0023] The beneficial effects of the embodiments of the present application lie in two aspects. On the one hand, by connecting a display device and starting a pre-stored digital human system through a startup script, since the pre-stored digital human system is started when the display device is connected, it is possible to connect and use the system immediately. This connect and use method is beneficial to improving the use speed of the digital human system. On the other hand, the three-dimensional model data and human motion data of the digital human in the digital human system are obtained, and the three-dimensional model data and the human motion data are decomposed into multiple processing tasks through a rendering engine, and the multiple processing tasks are transmitted to a preset graphics processor, and the digital human image generated by the graphics processor based on the multiple processing tasks is obtained, and the digital human image is sent to the display device, which reduces the user's manual settings and deployment steps, thereby simplifying the application process of the digital human system, and is beneficial to improving the application efficiency of the digital human system. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. Some specific embodiments of the present application will be described in detail in an illustrative and non-restrictive manner with reference to the drawings. The same reference numerals in the drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the drawings: Figure 1 is a flow chart of a digital human system application method provided by an embodiment of the present application; Figure 2 It is a schematic block diagram of a digital human system application device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0026] The digital human system application method provided in the embodiment of the present application can be applied to a portable device, which refers to an electronic device that is small in size, light in weight, and easy to carry and move.

[0027] Among them, the portable device is equipped with a general deep learning model, inference chip, graphics processor, storage device, data IO interface, and power interface.

[0028] The deep learning model of the digital human is deployed on the storage device, and the inference chip completes the inference operation of the deep learning model.

[0029] To ensure that the inference chip supports the operators included in the trained deep learning model, the inference chip needs to adopt general CPU architecture and GPU architecture.

[0030] Among them, the IO interface includes but is not limited to an HDMI interface, a USB interface, and an Ethernet interface.

[0031] Among them, the Chinese abbreviation of IO interface is input / output interface.

[0032] Among them, the HDMI interface, Chinese name: High Definition Multimedia Interface, English name: High Definition Multimedia Interface. The HDMI interface is a digital video / audio interface that can transmit audio and image signals at the same time without the need for digital / analog or analog / digital conversion before signal transmission.

[0033] Among them, USB interface, Chinese name: Universal Serial Bus, English name: Universal Serial Bus, USB interface is a widely used interface standard for connecting external devices such as keyboard, mouse, printer, storage device, etc.

[0034] Among them, the Ethernet interface, English name: Ethernet Interface, Ethernet interface is the interface for network data connection and is one of the most widely used LAN communication methods.

[0035] The operating system of the portable device adds mounting scripts for the USB interface and the HDMI interface. The mounting scripts are used to detect whether the software deployed by the box contains a startup script.

[0036] The startup script is a code file, in which the content required for executing and loading the pre-stored digital human system is written.

[0037] The display of digital humans relies on the graphics processor to provide high-quality graphics rendering capabilities. Graphics processors have significant advantages in graphics rendering, image processing, and modeling, and can process complex graphics data in real time.

[0038] In the field of travel guides, users can obtain local guide information and voice navigation services through the digital human system of portable devices; Among them, in the field of personal assistants, users can carry the digital human system of portable devices with them and conduct voice interaction to obtain personalized services such as schedule reminders and weather forecasts.

[0039] Figure 1 is a flow chart of the digital human system application method provided by the embodiment of the present application, such as Figure 1 As shown, the digital human system application method provided in the embodiment of the present application is applied to the above-mentioned portable device. The digital human system application method includes the following steps, which are described in detail as follows: S101, connecting a display device and starting a pre-stored digital human system through a startup script; In a possible implementation of the first aspect, connecting a display device and starting a pre-stored digital human system through a startup script include: Obtaining a hot plug signal sent by the display device through an input and output interface, wherein the input and output interface includes one or a combination of an HDMI interface, a USB interface, and an Ethernet interface; When the hot plug signal is a high level signal, a data transmission channel is established between the portable device and the display device; When the data transmission channel meets the preset conditions, the pre-stored digital human system is started by starting the script.

[0040] In the embodiment of the present application, a data transmission channel is established between the portable device and the display device to ensure that the portable device can stably transmit the digital human image to the display device, thereby improving the efficiency and stability of the digital human image transmission.

[0041] In a possible implementation of the first aspect, when the data transmission channel meets a preset condition, starting a pre-stored digital human system by starting a script includes: Acquiring the transmission delay time of the data transmission channel, and when the transmission delay time is less than the preset delay time in the preset condition, starting the pre-stored digital human system through a startup script; Alternatively, the transmission rate of the data transmission channel is obtained, and when the transmission rate is greater than the preset rate in the preset condition, the pre-stored digital human system is started by starting the script.

[0042] In the embodiment of the present application, when the data transmission channel meets the preset conditions, the pre-stored digital human system is started by starting the script, and the digital human system can automatically avoid network congestion or unstable periods, effectively reducing adverse situations such as startup failure, data transmission interruption or delay caused by network problems, and enhancing the stability and reliability of the digital human system. From the perspective of user experience, when the transmission delay is less than the preset delay or when the transmission rate is greater than the preset rate, it can provide users with a smoother and faster data interaction experience, enhancing user satisfaction and loyalty.

[0043] S102, acquiring the three-dimensional model data and human motion data of the digital human in the digital human system; The step of obtaining the three-dimensional model data and human motion data of the digital human in the digital human system includes: Acquire a first file and a second file of the digital human system; In the first file, the three-dimensional model data of the digital human is obtained, and in the second file, the human body motion data of the digital human is obtained.

[0044] In the embodiment of the present application, the digital human can be reconstructed through three-dimensional model data and human motion data to ensure that the motion performance of the digital human is completely consistent with the digital human system. This instant feedback mechanism not only improves the user experience, but also enhances the interactivity and immersion of the digital human.

[0045] S103, decomposing the three-dimensional model data and the human motion data into a plurality of processing tasks through a rendering engine, and transmitting the plurality of processing tasks to a preset graphics processor; The method of decomposing the three-dimensional model data and the human motion data into a plurality of processing tasks by a rendering engine and transmitting the plurality of processing tasks to a preset graphics processor comprises: Combining the three-dimensional model data and the human body motion data into rendering data; The rendering engine decomposes the rendering task of the rendering data into a plurality of processing tasks, and transmits the plurality of processing tasks to a preset graphics processor.

[0046] In the embodiment of the present application, the graphics processor has a powerful parallel computing capability, and contains a large number of processing units and multiple stream processors. When multiple processing tasks are sent to the graphics processor at the same time, these processing tasks can be executed in parallel on multiple processing units of the graphics processor. This parallel processing method significantly improves the computing efficiency, so that processing tasks that originally took a long time to complete can be processed in a shorter time, thereby speeding up the overall workflow.

[0047] S104, obtaining a digital human image generated by the graphics processor based on the plurality of processing tasks, and sending the digital human image to the display device.

[0048] Exemplarily, obtaining a digital human image generated by the graphics processor based on the plurality of processing tasks, and sending the digital human image to the display device includes: A digital human image generated by the graphics processor based on the plurality of processing tasks is obtained, the content of the digital human image is decomposed into image frames, and the image frames are sent to the display device.

[0049] Among them, after the display device receives the digital human image, it can present the digital human's appearance, movements, and expressions to the user in a smooth manner by displaying the digital human image.

[0050] The portable device may be directly connected to the display device or may be indirectly connected to the display device.

[0051] For the sake of illustration, an example is given below: For example, when there is only a display device, the portable device can be directly connected to the display device. When in use, the HDMI interface of the portable device is connected to the HDMI interface of the display device, the Ethernet interface is connected to the network, and the power interface is connected to the power supply. The HDMI mounting script detects the startup script and starts the digital human system. The portable device transmits the digital human screen of the digital human system to the display device through the HDMI interface, and the display device displays the digital human screen of the digital human system.

[0052] For example, when there is a computer, the portable device is connected to the computer, and the computer is connected to the display device, so the portable device is indirectly connected to the display device. When used, the USB interface of the portable device is connected to the computer, the Ethernet interface is connected to the network, and the power interface is connected to the power supply. The mount script of the USB interface detects the startup script and starts the digital human system.

[0053] The portable device transmits the digital human image of the digital human system to the computer through the USB interface, the computer transmits the digital human image of the digital human system to the display device, and the display device displays the digital human image of the digital human system.

[0054] Wherein, after acquiring the digital human picture generated by the graphics processor based on the plurality of processing tasks and sending the digital human picture to the display device, the digital human system application method further includes: Step A, collecting user voice and converting the user voice into first text information; Inputting the first text information into a deep learning model, and obtaining second text information output by the deep learning model based on the first text information; The second text information is converted into a response voice, and the response voice is sent to the display device.

[0055] Exemplarily, converting the second text information into a response voice, and sending the response voice to the display device includes: The second text information is converted into a response voice, and the second text information and the response voice are sent to the display device, so that the display device displays the second text information and plays the response voice.

[0056] In the embodiments of the present application, in the digital age, users expect the interaction with the display device to be more natural and smooth. By broadcasting the answering voice through the display device, it not only responds to the user's voice, but also provides feedback in a more humane way, thereby enhancing the user's sense of participation and immersion.

[0057] The step of inputting the first text information into a deep learning model and obtaining second text information output by the deep learning model based on the first text information includes: Obtain a model file of the deep learning model, and load the deep learning model from the model file by using a loading script; The first text information is input into the deep learning model, and the second text information output by the deep learning model based on the first text information is obtained. In an embodiment of the present application, the model file serves as a carrier of the deep learning model, and contains the network parameters and structural information optimized by the deep learning model during the training process. These parameters and structural information are the basis for the deep learning model to perform prediction and reasoning. By loading the model file, the deep learning model can quickly restore the complete state of the model without having to re-perform the time-consuming training process, thereby improving the convenience and efficiency of the deep learning model application.

[0058] Wherein, after acquiring the digital human picture generated by the graphics processor based on the plurality of processing tasks and sending the digital human picture to the display device, the digital human system application method further includes: Step B, obtaining an update command, obtaining update content from a server through the update command, performing an update operation on the digital human system through the update content, and obtaining the updated digital human system.

[0059] In the embodiments of the present application, the updated digital human system generally has stronger interactive capabilities, including more accurate natural language processing technology, which enables the digital human to better understand the user's intentions and emotions and give more appropriate and humane responses.

[0060] Wherein, after acquiring the digital human picture generated by the graphics processor based on the plurality of processing tasks and sending the digital human picture to the display device, the digital human system application method further includes: Step C, obtaining a push instruction, executing the push instruction, and pushing the digital human image to a preset database.

[0061] In the embodiment of the present application, the push instruction is executed to push the digital human image to a preset database. The database, as a persistent storage medium for data, can store the digital human image on a disk for a long time, ensuring that the digital human image will not be lost even in the event of a power outage or system crash. This persistent storage mechanism provides a strong guarantee for the long-term preservation and reliability of the digital human image.

[0062] Among them, step A, step B, and step C can be executed simultaneously, or step A, step B, and step C can be executed at different times.

[0063] For example, step A can be executed before or after steps B and C, step B can be executed before or after steps A and C, and step C can be executed before or after steps A and B. The specific execution order is not limited here.

[0064] The beneficial effects of the embodiments of the present application lie in two aspects. On the one hand, by connecting a display device and starting a pre-stored digital human system through a startup script, since the pre-stored digital human system is started when the display device is connected, it is possible to connect and use the system immediately. This connect and use method is beneficial to improving the use speed of the digital human system. On the other hand, the three-dimensional model data and human motion data of the digital human in the digital human system are obtained, and the three-dimensional model data and the human motion data are decomposed into multiple processing tasks through a rendering engine, and the multiple processing tasks are transmitted to a preset graphics processor, and the digital human image generated by the graphics processor based on the multiple processing tasks is obtained, and the digital human image is sent to the display device, which reduces the user's manual settings and deployment steps, thereby simplifying the application process of the digital human system, and is beneficial to improving the application efficiency of the digital human system.

[0065] Corresponding to the digital human system application method described in the above embodiment, please refer to Figure 2 , Figure 2 A schematic block diagram of a digital human system application device provided in an embodiment of the present application, Figure 2 The digital human system application device 200 shown in the figure can be applied to the above-mentioned electronic devices. Figure 2 The digital human system application device 200 shown is described in detail. The digital human system application device 200 may include a connection module 201, an acquisition module 202, a transmission module 203, and a sending module 204.

[0066] The connection module 201 is used to connect the display device and start the pre-stored digital human system through the startup script; An acquisition module 202 is used to acquire the three-dimensional model data and human motion data of the digital human in the digital human system; A transmission module 203, used for decomposing the three-dimensional model data and the human motion data into multiple processing tasks through a rendering engine, and transmitting the multiple processing tasks to a preset graphics processor; The sending module 204 is used to obtain the digital human image generated by the graphics processor based on the multiple processing tasks, and send the digital human image to the display device.

[0067] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0068] The beneficial effects of the embodiments of the present application lie in two aspects. On the one hand, by connecting a display device and starting a pre-stored digital human system through a startup script, since the pre-stored digital human system is started when the display device is connected, it is possible to connect and use the system immediately. This connect and use method is beneficial to improving the use speed of the digital human system. On the other hand, the three-dimensional model data and human motion data of the digital human in the digital human system are obtained, and the three-dimensional model data and the human motion data are decomposed into multiple processing tasks through a rendering engine, and the multiple processing tasks are transmitted to a preset graphics processor, and the digital human image generated by the graphics processor based on the multiple processing tasks is obtained, and the digital human image is sent to the display device, which reduces the user's manual settings and deployment steps, thereby simplifying the application process of the digital human system, and is beneficial to improving the application efficiency of the digital human system.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A digital human system application method, characterized in that: The digital human system application method comprises: Connect the display device and start the pre-stored digital human system through the startup script; Acquire the three-dimensional model data and human motion data of the digital human in the digital human system; Decomposing the three-dimensional model data and the human motion data into a plurality of processing tasks through a rendering engine, and transmitting the plurality of processing tasks to a preset graphics processor; A digital human image generated by the graphics processor based on the plurality of processing tasks is obtained, and the digital human image is sent to the display device.

2. The digital human system application method according to claim 1, characterized in that: Connect the display device and start the pre-stored digital human system through the startup script, including: Obtaining a hot plug signal sent by the display device through an input and output interface, wherein the input and output interface includes one or a combination of an HDMI interface, a USB interface, and an Ethernet interface; When the hot plug signal is a high level signal, a data transmission channel between the portable device and the display device is established; When the data transmission channel meets the preset conditions, the pre-stored digital human system is started by starting the script.

3. The digital human system application method according to claim 2, characterized in that: When the data transmission channel meets the preset conditions, the pre-stored digital human system is started by starting the script, including: Acquiring the transmission delay time of the data transmission channel, and when the transmission delay time is less than the preset delay time in the preset condition, starting the pre-stored digital human system through a startup script; Alternatively, the transmission rate of the data transmission channel is obtained, and when the transmission rate is greater than the preset rate in the preset condition, the pre-stored digital human system is started by starting the script.

4. The digital human system application method according to claim 1, characterized in that: The step of obtaining the three-dimensional model data and human motion data of the digital human in the digital human system includes: Acquire a first file and a second file of the digital human system; In the first file, the three-dimensional model data of the digital human is obtained, and in the second file, the human body motion data of the digital human is obtained.

5. The digital human system application method according to claim 1, characterized in that: Decomposing the three-dimensional model data and the human motion data into a plurality of processing tasks through a rendering engine, and transmitting the plurality of processing tasks to a preset graphics processor, comprises: Combining the three-dimensional model data and the human body motion data into rendering data; The rendering engine decomposes the rendering task of the rendering data into a plurality of processing tasks, and transmits the plurality of processing tasks to a preset graphics processor.

6. The digital human system application method according to claim 1, characterized in that: After acquiring the digital human image generated by the graphics processor based on the plurality of processing tasks and sending the digital human image to the display device, the method further includes: Collecting user voice and converting the user voice into first text information; Inputting the first text information into a deep learning model, and obtaining second text information output by the deep learning model based on the first text information; The second text information is converted into a response voice, and the response voice is sent to the display device.

7. The digital human system application method according to claim 6, characterized in that: Inputting the first text information into a deep learning model, and obtaining second text information output by the deep learning model based on the first text information, includes: Obtain a model file of the deep learning model, and load the deep learning model from the model file by using a loading script; The first text information is input into the deep learning model, and second text information output by the deep learning model based on the first text information is obtained.

8. The digital human system application method according to claim 1, characterized in that: After acquiring the digital human image generated by the graphics processor based on the plurality of processing tasks and sending the digital human image to the display device, the method further includes: An update command is obtained, and update content is obtained from a server through the update command. An update operation is performed on the digital human system through the update content to obtain the updated digital human system.

9. The digital human system application method according to claim 1, characterized in that: After acquiring the digital human image generated by the graphics processor based on the plurality of processing tasks and sending the digital human image to the display device, the method further includes: A push instruction is obtained, the push instruction is executed, and the digital human image is pushed to a preset database.

10. A digital human system application device, characterized in that: include: A connection module is used to connect to a display device and start a pre-stored digital human system through a startup script; An acquisition module, used for acquiring the three-dimensional model data and human motion data of the digital human in the digital human system; A transmission module, used for decomposing the three-dimensional model data and the human motion data into a plurality of processing tasks through a rendering engine, and transmitting the plurality of processing tasks to a preset graphics processor; The sending module is used to obtain the digital human image generated by the graphics processor based on the multiple processing tasks, and send the digital human image to the display device.

Images