Display device and character template generation method

Abstract

The application relates to a display device and a role template generation method. In the role template generation method, a role editing entrance is configured in a content generation application in a display, in response to a trigger operation on the role editing entrance displayed in the content generation application of the display, in a case where a target role is determined, role description prompt information is determined according to the target role; and the role description prompt information is output so that a user inputs role description information according to the role description prompt information, and then a target role template corresponding to the target role can be generated according to the role description information corresponding to the received role description prompt information; the target role template is used to generate a role image of a target role in multimedia content, custom target role templates are realized, the role image of the target role in the multimedia content is enriched, and therefore the user experience is improved.

Description

Technical Field

[0001] The present application relates to the technical field of display devices, and in particular to a display device and a method for generating a character template. Background Art

[0002] Currently, with the continuous development of technology, the functions of display devices are becoming more and more diversified. For example, today's display devices have the function of creating multimedia content (such as multimedia content).

[0003] In traditional technology, during the process of creating multimedia content, the characters in the multimedia content are usually selected from pre-set character templates.

[0004] Since the pre-set character templates are fixed and limited, the character images available for selection are relatively simple, which makes the generated multimedia content relatively limited. Summary of the Invention

[0005] The present application provides a display device and a character template generation method, which can support users to customize character templates, thereby enriching the character images in multimedia content and improving the user experience.

[0006] In a first aspect, some embodiments provide a display device, including:

[0007] a controller configured to receive a control signal from a control device and control a display in the display device to display according to the control signal;

[0008] The display is configured to display a character editing entry in the content generation application;

[0009] The controller is further configured to:

[0010] In response to a trigger operation on the role editing entry, when a target role is determined, role description prompt information is determined according to the target role;

[0011] Controlling the display to present the character description prompt information;

[0012] receiving role description information corresponding to the role description prompt information;

[0013] A target role template corresponding to the target role is generated according to the role description information; wherein the target role template is used to generate a role image of the target role in multimedia content.

[0014] In the above embodiment, the display device includes a controller and a display, wherein the controller is configured to receive a control signal from the control device and control the display of the display device to display according to the control signal; the display is configured to display a character editing entry in the content generation application; the controller is further configured to, in response to a trigger operation on the character editing entry, determine character description prompt information based on the target character, output the character description prompt information, and after receiving the character description information corresponding to the character description prompt information, generate a target character template that can be used to generate a character image of the target character in the multimedia content based on the character description information. On the one hand, the display device of the present application has a character editing entry, thereby enabling the display device to have a custom character template function, thereby increasing the display device's usability; further, the display device of the present application has a custom character template function, which allows users to flexibly use the custom character template function to create character templates, thereby enriching the character image in the multimedia content. On the other hand, the present application determines the character description prompt information based on the character, which can make the output character description prompt information more reasonable, thereby making the received character description information more accurate, so that the character image generated in the multimedia content based on the generated target character template meets the user's actual needs, thereby improving the user experience.

[0015] In some embodiments, before generating a target role template corresponding to the target role according to the role description information, the controller is further configured to:

[0016] controlling the display to present a template card of at least one preset role template in the content generation application;

[0017] In response to a selection operation on a template card of a preset role template corresponding to the target role among the template cards, determining a role template to be adjusted;

[0018] When the controller generates the target role template corresponding to the target role according to the role description information, the controller is further configured to update the role template to be adjusted according to the role description information to obtain the target role template corresponding to the target role.

[0019] In the above embodiment, a method is provided for modifying an existing role template based on the existing role template to generate a new role template, thereby achieving the purpose of customizing the role template and enriching the role image of the target role in the generated multimedia content, thereby improving the user experience.

[0020] In some embodiments, each template card is associated with a role editing entry, and the role description prompt information includes at least one target role description item;

[0021] When the controller responds to a trigger operation on the character editing entry, the controller is further configured to:

[0022] In response to a triggering operation on a role editing entry associated with a template card of the role template to be adjusted;

[0023] When the controller determines the role description prompt information according to the target role, the controller is further configured to:

[0024] Controlling the display to present the role template to be adjusted corresponding to the target role;

[0025] In response to the region selection operation on the role template to be adjusted, determining a role description item to be adjusted of the role template to be adjusted;

[0026] Determining at least one target role description item according to the role description item to be adjusted;

[0027] The role description prompt information is generated according to at least one target role description item.

[0028] In the above embodiment, the role description prompt information can be determined based on the role template to be adjusted and interacted with the user, that is, a process of determining the role description prompt information through human-computer interaction is provided, so that the input of the role description prompt information is more targeted, and the adjustment of the existing role template meets the actual needs of the user, thereby improving the user experience.

[0029] In some embodiments, when the controller generates a target role template corresponding to the target role based on the role description information, the controller is further configured to:

[0030] Controlling the display to present a character guide card; wherein the character guide card is used to instruct the user terminal to send a basic image for the target character to the display device;

[0031] After receiving the basic image sent by the user terminal, a target role template corresponding to the target role is generated according to the basic image and the role description information.

[0032] In the above embodiment, an interaction process between the display device and the mobile terminal is introduced to obtain a basic image, and the basic image is modified based on the character description information to generate a target character template, thereby achieving the purpose of customizing the character template and enriching the character image of the target character in the generated multimedia content, thereby improving the user experience.

[0033] In some embodiments, when the controller controls the display to present the character description prompt information, the controller is further configured to:

[0034] Controlling the display to present a target character creation template; wherein the target character creation template includes character description prompt information;

[0035] When the controller receives the role description information corresponding to the role description prompt information, the controller is further configured to:

[0036] In response to an input operation on the role description prompt information, role description information corresponding to the role description prompt information is received.

[0037] In the above embodiment, a feasible method for obtaining role description information is provided, which facilitates the subsequent generation of a target role template based on the role description information.

[0038] In some embodiments, after generating a target role template corresponding to the target role according to the role description information, the controller is further configured to:

[0039] Obtaining the template card corresponding to the target role template;

[0040] controlling the display, and being further configured to present a template card corresponding to the target role template in the content generation application;

[0041] When the template card corresponding to the target role template is in a selected state, if a content generation event is detected, a content generation instruction for the target role template is sent to the server; wherein the content generation instruction is used to instruct the server to generate the multimedia content according to the target role template;

[0042] The display is controlled to present a playback entry for the multimedia content in the content generation application.

[0043] The above embodiment provides an achievable method for generating multimedia content based on a target character template, and the user can select the character image of the target character in the multimedia content according to their needs, thereby improving the user experience.

[0044] In some embodiments, before executing the sending of the content generation instruction indicating the target role template to the server, the controller is further configured to:

[0045] controlling the display to present a theme editing entrance in the content generation application;

[0046] In response to an operation on the theme editing entry, receiving a target theme of the multimedia content to be generated;

[0047] Accordingly, when the controller sends a content generation instruction for the target role template to the server, it is further configured to:

[0048] Sending a content generation instruction carrying the target theme and the target role and indicating the target role template to the server;

[0049] The content generation instruction is used to instruct the server to generate text description information of the multimedia content according to the target theme and the target role, and to generate the multimedia content according to the text description information and the target role template.

[0050] In the above embodiment, a feasible method for generating multimedia content is provided, which can automatically generate text description information according to the target theme and target role of the multimedia content, so that the generated multimedia content is more story-telling; and generate multimedia content according to the text description information and the target role template, so that the generated multimedia content has a more appropriate combination of text and pictures, thereby improving the readability of the multimedia content.

[0051] In some embodiments, when the controller determines the role description prompt information according to the target role, it is further configured to:

[0052] Selecting at least one reference role creation template that matches the target role from each candidate role creation template; wherein different reference role creation templates contain different role description prompt information;

[0053] A target character creation template is selected from the reference character creation templates according to at least one of the version information of the content generation application, the version information of the display, and the template usage information of the reference character creation templates.

[0054] In the above embodiment, the controller can determine the role description prompt information based on the version information of the content generation application, the version information of the display and at least one of the template usage information of each reference role creation template, so that the determined role description prompt information can be more in line with actual usage needs, and thus the determined role template can be more in line with actual usage needs.

[0055] In some embodiments, before selecting a target character creation template from each reference character creation template based on at least one of the version information of the content generation application, the version information of the display, and the template usage information of each reference character creation template, the controller is further configured to:

[0056] controlling the display to present a theme editing entrance in the content generation application;

[0057] In response to a triggering operation on the theme editing entry, receiving a target theme of the multimedia content to be generated;

[0058] The controller is further configured to, when selecting a target character creation template from each reference character creation template based on at least one of version information of the content generation application, version information of the display, and template usage information of each reference character creation template:

[0059] Selecting at least one candidate role creation template that matches the target theme from the reference role creation templates;

[0060] A target character creation template is selected from each candidate character creation template according to at least one of the version information of the content generation application, the version information of the display, and the template usage information of each candidate character creation template.

[0061] In the above embodiment, when determining the target character creation template, on the one hand, the target theme of the multimedia content is taken into consideration, so that the determined target character creation template is more in line with the multimedia content; on the other hand, the target character creation template can be selected from the candidate character creation templates based on the version information of the content generation application, the version information of the display, and at least one of the template usage information of each reference character creation template, so that the target character creation template provided to the user is more in line with the actual character creation needs.

[0062] In some embodiments, when the controller generates a target role template corresponding to the target role based on the role description information, the controller is further configured to:

[0063] Send a first role generation instruction carrying the role description information to the server; wherein the first role generation instruction is used to instruct the server to call a target text graph model and generate a target role template corresponding to the target role based on the role description information; wherein the target text graph model includes a text encoder, a denoising network and an image generator.

[0064] In the above embodiment, the target role template is generated based on the role description information through the target context graph model, which can improve the efficiency of generating the target role template on the one hand, and improve the accuracy of generating the target role template on the other hand.

[0065] In some embodiments, the text encoder is used to extract features from the role description information to obtain a text embedding vector; the denoising network is used to denoise the initial noisy image based on the text embedding vector to obtain a denoised image; the image generator is used to perform an image generation operation based on the denoised image to obtain a target role template corresponding to the target role.

[0066] The above embodiment provides a specific implementation method for generating a target role template based on role description information through a target context graph model, which can improve the efficiency of generating the target role template and improve the accuracy of generating the target role template.

[0067] In some embodiments, the target text graph model is trained by:

[0068] Get a sample person image;

[0069] Extracting sample description information corresponding to the sample person image;

[0070] Training a denoising network in the initial text-based graph model based on sample description information corresponding to the sample person image to obtain a predicted person image;

[0071] Using a face recognition model, determining an image difference between the sample person image and the predicted person image;

[0072] The model parameters of the denoising network in the initial text graph model are adjusted according to the image difference to obtain the target text graph model.

[0073] The above embodiment provides an achievable method for obtaining a target context graph model, which facilitates generating a target role template using the target context graph model and improves the efficiency of generating the target role template.

[0074] In some embodiments, when the controller generates a target role template corresponding to the target role based on the role description information, the controller is further configured to:

[0075] A second role generation instruction carrying the role description information is sent to the server; wherein the second role generation instruction is used to instruct the server to select a target role image with the highest matching degree with the role description information from the candidate role images, and use the target role image as the target role template corresponding to the target role.

[0076] In the above embodiment, by adopting the text similarity matching method, a target role template is generated according to role description information, thereby enriching the role image of the target role in the generated multimedia content, thereby improving the user experience.

[0077] In a second aspect, some embodiments further provide a method for generating a character template, the method being applied to a controller in a display device, the controller being configured to receive a control signal from a control device and control a display in the display device to perform display according to the control signal; the method comprising:

[0078] In response to a triggering operation on a character editing entry displayed on a display in a content generation application, upon determining a target character, determining character description prompt information based on the target character;

[0079] Controlling the display to present the character description prompt information;

[0080] receiving role description information corresponding to the role description prompt information;

[0081] A target role template corresponding to the target role is generated according to the role description information; wherein the target role template is used to generate a role image of the target role in multimedia content.

[0082] As can be seen from the above technical solutions, some embodiments of the present application provide a display device and a method for generating a character template. In the method, a character editing entry is configured in a content generation application on a display. In response to a triggering operation on the character editing entry displayed on the display in the content generation application, after determining a target character, character description prompt information is determined based on the target character and outputted. This allows a user to input a character description according to the character description prompt information. Furthermore, based on the character description information corresponding to the received character description prompt information, a target character template is generated that can be used to generate a character image of the target character in multimedia content. On the one hand, the display device of the present application has a character editing entry, thereby enabling the display device to have a custom character template function, thereby increasing the display device's usability. Furthermore, the display device of the present application has a custom character template function, which allows users to flexibly use the custom character template function to create character templates, thereby enriching the character image in the multimedia content. On the other hand, the present application determines the character description prompt information based on the character, which can make the output character description prompt information more reasonable, thereby making the received character description information more accurate, so that the character image generated in the multimedia content based on the generated target character template meets the user's actual needs, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0084] Figure 1 A schematic diagram of an operation scenario between a display device and a control device provided in some embodiments of the present application;

[0085] Figure 2 A schematic diagram of the hardware configuration of a display device provided in some embodiments of the present application;

[0086] Figure 3 A schematic diagram of the hardware configuration of a control device provided in some embodiments of the present application;

[0087] Figure 4 A schematic diagram of software configuration of a display device provided in some embodiments of the present application;

[0088] Figure 5 A schematic diagram of a character image selection interface provided in some embodiments of the present application;

[0089] Figure 6 A schematic flow chart of the steps of a method for generating a role template according to some embodiments of the present application;

[0090] Figure 7A A schematic diagram of the operating interface of a content generation application provided in some embodiments of the present application;

[0091] Figure 7B A schematic diagram of an interface for inputting multimedia content themes provided in some embodiments of the present application;

[0092] Figure 7C A schematic diagram of an interface for inputting multimedia content roles provided in some embodiments of the present application;

[0093] Figure 7D A schematic diagram of a character image creation interface provided in some embodiments of the present application;

[0094] Figure 8 A schematic diagram of presenting role description prompt information provided in some embodiments of the present application;

[0095] Figure 9A A schematic diagram of a generated target role template provided in some embodiments of the present application;

[0096] Figure 9B A schematic diagram of turning pages of multimedia content provided in some embodiments of the present application;

[0097] Figure 9C A schematic diagram of a regenerated target role template provided in some embodiments of the present application;

[0098] Figure 9D Schematic diagram of multimedia content cover provided in some embodiments of the present application;

[0099] Figure 9E A schematic diagram of multimedia content preview provided in some embodiments of the present application;

[0100] Figure 9FA schematic diagram of multimedia content sharing provided in some embodiments of the present application;

[0101] Figure 10A A schematic diagram of a template for creating a target role provided in some embodiments of the present application;

[0102] Figure 10B Schematic diagram of role description information provided in some embodiments of the present application;

[0103] Figure 11A A schematic diagram of the preset role template editing entry provided in some embodiments of the present application;

[0104] Figure 11B Schematic diagram of selected multimedia content provided in some embodiments of the present application;

[0105] Figure 11C A schematic diagram of deleting multimedia content provided in some embodiments of the present application;

[0106] Figure 11D A schematic diagram of confirming deletion of multimedia content provided in some embodiments of the present application;

[0107] Figure 11E A schematic diagram of multimedia content after deletion provided in some embodiments of the present application;

[0108] Figure 12 A schematic diagram of the target text graph model structure provided in some embodiments of the present application;

[0109] Figure 13 A timing diagram for generating a target role template provided in some embodiments of the present application. DETAILED DESCRIPTION

[0110] The following embodiments are described in detail, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numbers in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following embodiments are not intended to represent all possible implementations consistent with the present application. They are merely examples of systems and methods consistent with certain aspects of the present application, as detailed in the claims.

[0111] It should be noted that the brief descriptions of terms in this application are only for the purpose of facilitating the understanding of the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their ordinary and usual meanings.

[0112] In the specification and claims of this application and the accompanying drawings, the terms "first," "second," and the like are used to distinguish similar or similar objects or entities and are not necessarily intended to limit a particular order or precedence, unless otherwise noted. It should be understood that the terms used in this manner are interchangeable under appropriate circumstances.

[0113] The terms "comprise," "include," and "have," and any variations thereof, are intended to cover but not exclude inclusion; for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0114] The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functionality associated with that element.

[0115] In the embodiments of the present application, the display device 200 generally refers to a device capable of displaying images and processing data. For example, the display device 200 includes but is not limited to a smart TV, a mobile terminal, a computer, a monitor, an advertising screen, a wearable device, a virtual reality device, an augmented reality device, etc.

[0116] Figure 1 This is a schematic diagram of an operation scenario between a display device and a control device provided in some embodiments of the present application. Figure 1 As shown in FIG, a user can operate the display device 200 through touch operation, the mobile terminal 300 and the control device 100. For example, the control device 100 can be a remote controller, a stylus pen, a handle, etc.

[0117] The mobile terminal 300 can function as a control device for performing human-computer interaction between a user and the display device 200. The mobile terminal 300 can also function as a communication device for establishing a communication connection with the display device 200 and exchanging data. In some embodiments, the mobile terminal 300 can install software applications with the display device 200, enabling connection and communication via a network communication protocol, enabling one-to-one control operations and data communication. Audio and video content displayed on the mobile terminal 300 can also be transmitted to the display device 200 for synchronized display.

[0118] like Figure 1 As shown in FIG, the display device 200 also communicates data with the server 400 through various communication methods. The display device 200 may be allowed to communicate via a local area network (LAN), a wireless local area network (WLAN), and other networks.

[0119] The display device 200 can provide a broadcast receiving television function and a multimedia content creation function; wherein the multimedia content can be multimedia content, and can also additionally provide an intelligent network television function that provides computer support functions, including but not limited to network television, smart TV, Internet Protocol Television (IPTV), etc.

[0120] Figure 2 Some embodiments of this application provide Figure 1 2 is a block diagram of the hardware configuration of the display device 200.

[0121] In some embodiments, the display device 200 may include at least one of a tuner 210 , a communication device 220 , a detector 230 , a device interface 240 , a controller 250 , a display 260 , an audio output device 270 , a memory, a power supply, and a user input interface 280 .

[0122] In some embodiments, detector 230 is used to collect signals from the external environment or external interactions. For example, detector 230 may include a light receiver, such as a sensor for collecting ambient light intensity; or an image collector, such as a camera, for collecting external environmental scenes, user attributes, or user interaction gestures; or a sound collector, such as a microphone, for receiving external sounds.

[0123] In some embodiments, the display 260 includes a display component for presenting images and a driver component for driving image display. The display 260 is configured to receive image signals output from the controller 250 for display. For example, the display 260 can be used to display video content, image content, menu control interface components, and user control UI interfaces.

[0124] In some embodiments, the communication device 220 is a component used to communicate with an external device or server 400 according to various communication protocol types. The display device 200 can be provided with multiple communication devices 220 depending on the supported communication methods. For example, if the display device 200 supports wireless network communication, the display device 200 can be provided with a communication device 220 including WiFi functionality. If the display device 200 supports Bluetooth connection communication, the display device 200 needs to be provided with a communication device 220 including Bluetooth functionality.

[0125] The communication device 220 can establish a communication connection between the display device 200 and an external device or server 400 via a wireless or wired connection. A wired connection can connect the display device 200 to an external device via a data cable, an interface, or other components. A wireless connection can connect the display device 200 to an external device via a wireless signal or wireless network. The display device 200 can establish a connection with an external device directly or indirectly through a gateway, router, or connection device.

[0126] In some embodiments, the controller 250 may include at least one of a central processing unit (CPU), a video processor, an audio processor, a graphics processor, and a power processor, and first to nth interfaces for input / output. The controller 250 controls the operation of the display device and responds to user operations through various software control programs stored in a memory. The controller 250 controls the overall operation of the display device 200.

[0127] In some embodiments, the controller 250 and the tuner 210 may be located in different separate devices, that is, the tuner 210 may also be located in an external device of the main device where the controller 250 is located, such as an external set-top box.

[0128] In some embodiments, the user may input a user command through a graphical user interface (GUI) displayed on the display 260 , and the user input interface receives the user input command through the GUI.

[0129] In some embodiments, the audio output device 270 may be a local speaker of the display device 200, or an external audio output device connected to the display device 200. For the external audio output device connected to the display device 200, the display device 200 may further be provided with an external audio output terminal, through which the audio output device may be connected to the display device 200 to output the sound of the display device 200.

[0130] In some embodiments, the user input interface 280 may be configured to receive instructions from a user.

[0131] Figure 3 Some embodiments of this application provide Figure 1 The hardware configuration diagram of the control device in the figure is as follows. Figure 3 As shown, the control device 100 may include: a controller 110, a communication interface 130, a user input / output interface, a memory, and a power supply.

[0132] The control device 100 is configured to control the display device 200 , and can receive user input operation instructions, and convert the operation instructions into instructions that the display device 200 can recognize and respond to, playing the role of an interactive intermediary between the user and the display device 200 .

[0133] In some embodiments, the control device 100 may be a smart device. For example, the control device 100 may be installed with various applications for controlling the display device 200 according to user needs.

[0134] In some embodiments, as Figure 1 As shown, the mobile terminal 300 or other intelligent electronic devices can play a similar function as the control device 100 after installing the application for controlling the display device 200 .

[0135] Controller 110 includes a processor 112, random-access memory (RAM) 113, read-only memory (ROM) 114, a communication interface 130, and a communication bus. Controller 110 is used to control the operation and functionality of control device 100, facilitate communication between its components, and process both internal and external data.

[0136] Under the control of the controller 110, the communication interface 130 communicates control signals and data signals with the display device 200. The communication interface 130 may include at least one of a WiFi chip 131, a Bluetooth module 132, a near field communication (NFC) module 133, or other near field communication modules.

[0137] The user input / output interface 140 includes at least one of a microphone 141 , a touch panel 142 , a sensor 143 , a button 144 and other input interfaces.

[0138] In some embodiments, the control device 100 includes at least one of a communication interface 130 and an input / output interface 140. The control device 100 is configured with the communication interface 130, such as a WiFi, Bluetooth, or NFC module, to encode user input commands via the WiFi protocol, Bluetooth protocol, or NFC protocol and transmit them to the display device 200.

[0139] The memory 190 is used to store various operating programs, data and applications for driving and controlling the control device 100 under the control of the controller. The memory 190 can store various control signal instructions input by the user.

[0140] The power supply 180 is used to provide operating power support for each component of the control device 100 under the control of the controller.

[0141] To facilitate user interaction, in some embodiments, the display device 200 may run an operating system. The operating system is a computer program used to manage and control the hardware and software resources of the display device 200. The operating system may provide a user interface (to control the display device), allow the user to interact with the display device 200, and support the running of various application programs.

[0142] It should be noted that the operating system may be a native operating system based on a specific operating platform, or a third-party operating system deeply customized based on a specific operating platform, or an independent operating system specially developed for the display device.

[0143] The operating system can be divided into different modules or layers according to the functions implemented, e.g. Figure 4 As shown, in some embodiments, the system is divided into four layers, from top to bottom: the application layer (abbreviated as "application layer"), the application framework layer (abbreviated as "framework layer"), the system library layer and the kernel layer.

[0144] In some embodiments, the application layer provides services and interfaces for applications, enabling the display device 200 to run applications and interact with the user based on these applications. The application layer can host at least one application, which can include built-in window programs, system settings programs, clock programs, and other applications provided by the operating system, or applications developed by third-party developers. In specific implementations, the application packages in the application layer are not limited to the examples above.

[0145] The framework layer provides applications with an application programming interface (API) and programming framework. The application framework layer includes predefined functions. The application framework layer acts as a processing center, determining the actions taken by applications in the application layer. Through the API, applications can access system resources and services during execution.

[0146] like Figure 4 As shown, in the embodiment of the present application, the application layer includes various applications. For example, the various applications include content generation applications to support users in generating multimedia content in the content generation applications. The content generation applications include preset multimedia content. The images and audio contained in the multimedia content are related to the content text. When playing the multimedia content, the playback duration of the images and content text corresponds to the playback duration of the audio content corresponding to the image.

[0147] In the embodiment of the present application, the application framework layer includes a view system, managers, content providers, etc., wherein the view system can design and implement the interface and interaction of the application, and the view system includes lists, grids, text boxes, buttons, etc. The manager includes at least one of the following modules: an activity manager for interacting with all activities running in the system; a location manager for providing system services or applications with access to the system location service; a package manager for retrieving various information related to the application packages currently installed on the device; a notification manager for controlling the display and clearing of notification messages; and a window manager for managing icons, windows, toolbars, wallpapers, and desktop widgets on the user interface.

[0148] In some embodiments, the activity manager is used to manage the lifecycle of each application and common navigation back functions, such as controlling application exit, opening, and back. The window manager is used to manage all window programs, such as obtaining the display screen size, determining whether there is a status bar, locking the screen, taking screenshots, and controlling changes in display windows, such as shrinking, shaking, or distorting the display window.

[0149] In some embodiments, the system runtime layer can provide support for the framework layer. When the framework layer is used, the operating system will run the instruction library contained in the system runtime layer, such as the C / C++ instruction library, to implement the functions to be implemented by the framework layer.

[0150] In some embodiments, the kernel layer is a functional layer between the hardware and software of the display device 200. The kernel layer can implement functions such as hardware abstraction, multitasking, and memory management. Figure 4 As shown, the kernel layer can be configured with hardware drivers, and the drivers included in the kernel layer can be at least one of the following drivers: audio driver, display driver, Bluetooth driver, camera driver, WIFI driver, USB driver, High-Definition Multimedia Interface (HDMI) driver, sensor driver (such as fingerprint sensor, temperature sensor, pressure sensor, etc.), and power driver, etc.

[0151] It should be noted that the above example is only a simple division of the operating system functions and does not constitute a limitation on the specific operating system form of the display device 200 in the embodiment of the present application. Depending on factors such as the function of the display device and the type of operating system, the number of levels and specific level types contained in the operating system may be expressed in other forms.

[0152] The above embodiments illustrate the hardware / software architecture and functional implementation of a display device 200. In some embodiments, the display device 200 is configured with a content generation application, and the display in the display device 200 can display the content generation application. The controller in the display device can receive control signals from the control device 100 and control the display in the display device to display the content generation application based on the control signals. The user can control the display device 200 through the control device 100 to generate multimedia content in the content generation application. Alternatively, the user's voice can be received through the sound collector in the detector 230, allowing interaction with the user to generate multimedia content in the content generation application.

[0153] See also Figure 5 When generating multimedia content, users need to input the theme and character, and then select a character image. Existing technologies only allow users to select from pre-set character templates within the content generation application, which is quite limited. For example, pre-set character templates include "My dad," "My mom," and "My family." Users are limited to selecting from these few pre-set character templates, which reduces the user experience.

[0154] Based on this, in some embodiments, the present application provides a display device comprising a display and a controller. The controller is configured to receive a control signal from the control device and control the display in the display device to display according to the control signal; the display is configured to display a character editing entry in a content generation application; and the controller is further configured to execute a character template generation method. The method can respond to a triggering operation on the character editing entry, interact with the user based on the character description prompt information corresponding to the target character, obtain the character description information provided by the user, and then generate a target character template corresponding to the target character, thereby realizing customized character templates, enriching the character image of the character in the generated multimedia content, and improving the user experience.

[0155] Optional, reference Figure 6 , the role template generation method includes the following steps:

[0156] Step 602 : In response to a triggering operation on a character editing entry displayed on a display in a content generation application, when a target character is determined, character description prompt information is determined according to the target character.

[0157] For example, when generating multimedia content, the user can manipulate the control device 100 to interact with the display device 200. For example, the user can manipulate the control device 100 to open the content generation application in the display device 200, wherein the operation interface of the content generation application is as shown in FIG. Figure 7A After that, the user controls the control device 100 to trigger the multimedia content creation button "Create now" in the operation interface, and enters the Figure 7B The user can also manipulate the control device 100 in Figure 7B Enter the theme of the multimedia content in the subject column and the role in the multimedia content in the role column, trigger "Next" and enter Figure 7C interface.

[0158] In some embodiments, the user can also directly control the opening of the content generation application through the voice interaction function. For example, the user can first wake up the voice assistant in the display device, and then use voice input "open content generation application" to enter Figure 7A The interface shown; users can enter the voice content "create multimedia content" and then enter Figure 7B Further, the user can also voice input multimedia content theme, for example, the theme can be "family", enter Figure 7C Then voice input multimedia content target role, for example, the target role can be "my dad", and then enter Figure 7D In the interface shown, select the character image.

[0159] Optionally, users can Figure 7D In the interface shown, a pre-set character template is selected. For example, the pre-set character templates may include "My dad," "My mom," and "My family." There may be one or more templates for the same character. The user may select one of the templates corresponding to the target character to generate the character image of the target character in the multimedia content. In some embodiments, if there are multiple templates for the same character, the multiple templates may be displayed in an overlay, and the order of overlay may be determined based on information such as the frequency of use of each template.

[0160] In some embodiments, the content generation application further integrates a role editing portal. The so-called role editing portal is an entrance to the role template customization function, which can be presented in the form of a button or a link, etc., and the embodiments of the present application do not limit this.

[0161] Optionally, the user can also trigger the role editing entrance to customize the corresponding role template. For example, the user can input "create role" through voice input, or manipulate the control device 100 to trigger the role editing entrance, for example, it can be Figure 7D Click the "plus sign" in the dialog to enter the role template customization function to customize the corresponding role template.

[0162] For example, the controller needs to determine the target role before executing the specific role template customization. In the embodiment of the present application, there is no limitation on the specific time of determining the target role. For example, the user can input the target role corresponding to the multimedia content before triggering the role editing entrance, that is, Figure 7C Alternatively, the controller can also determine the target role when the user creates a role template, that is, after triggering the role editing entrance, the user first enters the target role, at which time the controller can determine the target role.

[0163] In some embodiments, upon determining a target role, the controller may determine role description prompt information based on the target role. The role description prompt information is used to prompt the user to enter specific content of the corresponding role description item. Optionally, in embodiments of the present application, the role description prompt information may be one, in which case the role description prompt information may include multiple role description items; alternatively, the role description prompt information may be multiple, in which case one role description prompt information may include one role description item.

[0164] Optionally, the so-called role description items are characteristic dimensions used to describe the role. Different roles correspond to different role description items. After determining the target role, multiple role description items associated with the target role can be obtained based on the correspondence between the roles and the role description items. Some or all of the multiple role description items associated with the target role can then be used as the target role description items. Corresponding role description prompt information can then be generated based on the target role description items.

[0165] For example, the pre-set multiple character description items may include "hairstyle," "clothing," "face," "body type," "size," "shape," "age," "personality," "skin color," "hobbies," "emotions," "name," "fur color," "behavior," etc. In this case, multiple character description items associated with the target character may be obtained based on the correspondence between the characters and the character description items.

[0166] Step 604: Control the display to present role description prompt information.

[0167] Optionally, the display may be controlled to present the role description prompt information; alternatively, the role description prompt information may be presented through voice playback and display on the display.

[0168] In some embodiments, after determining the role description prompt information corresponding to the target role, the display may be controlled to present the role description prompt information. Figure 8 , Figure 8 A schematic diagram of a display presenting character description prompt information is shown, wherein the character description prompt information can be displayed in one interface or in multiple interfaces. For example, Figure 8 The character description prompt information is displayed in one interface. Figure 8 The character description prompt displayed in the game is "Hey kiddo, what does your dad look like? Can you tell me about his hair, skin color, height, and if he's big or small?" It should be noted that Figure 8 The role description prompt information is only an example and is not used to limit the role description prompt information.

[0169] Step 606: Receive role description information corresponding to the role description prompt information.

[0170] For example, after the character description prompt is presented, the user can input the character description corresponding to the character description prompt through the control device 100 based on the character description prompt, or input the character description corresponding to the character description prompt through voice interaction. For example, if the character description prompt is "What is the hairstyle like?", the user can input the character description as "Black, shoulder-length hair." After the user enters the character description, the controller can receive the character description corresponding to the character description prompt.

[0171] Step 608: Generate a target role template corresponding to the target role based on the role description information.

[0172] For example, the controller can generate a target role template corresponding to the target role based on a preset algorithm or a preset model according to the role description information. The target role template is used to generate the character image of the target role in the multimedia content. For example, if the target role is "my dad" and the role description information is "yellow hair, glasses, very cute, likes reading", the generated target role template is as follows: Figure 9A shown.

[0173] Furthermore, if the user is satisfied with the generated target role template, he or she can click Figure 9A Press button 901 in the dialog box, or input "Continue or Next" by voice to enter Figure 9B Interface. Figure 9BClick button 902 or 903, or input "next page or previous page" by voice, to turn the page up or down; the purpose is to apply the generated target character template to each frame image containing the target character in the multimedia content. If the user is not satisfied with the generated target character template, he can click Figure 9A The regenerate button 904 in the menu or the voice input "regenerate" is used to regenerate the target role template. Figure 9C As shown; click Figure 9C Press button 905, or input "Continue or Next" by voice to enter Figure 9B When you turn to the last page of multimedia content, click the next step or input "Continue or Next" by voice to enter Figure 9D The interface shown, Figure 9D The interface shown shows the generated multimedia content cover to the user.

[0174] Furthermore, the user can click the save button 906 or input “save” by voice to save the generated multimedia content and jump to Figure 9E The interface shown, that is, the newly generated multimedia content is displayed on the homepage of the content generation application in the order of generation.

[0175] For example, the user can also click Figure 9D The share button 907 in the interface shown, or voice input "share" to enter Figure 9F The interface shown; Figure 9F A shared QR code is shown. Users can scan the QR code through a terminal device to download multimedia content. The downloaded multimedia content can be in image format or video format, and the format of the downloaded multimedia content can be selected as needed.

[0176] In the above-mentioned character template generation method, a character editing entry is configured in a content generation application on a display. In response to a triggering operation on the character editing entry displayed on the display in the content generation application, after determining a target character, a controller determines character description prompt information based on the target character and outputs the character description prompt information so that a user can input character description information according to the character description prompt information. Then, the controller can generate a target character template that can be used to generate a character image of the target character in multimedia content based on the character description information corresponding to the received character description prompt information. On the one hand, the display device of the present application has a character editing entry, thereby enabling the display device to have a custom character template function, thereby increasing the display device's usability. Furthermore, the display device of the present application has a custom character template function, which allows users to flexibly use the custom character template function to create character templates, thereby enriching the character image in the multimedia content. On the other hand, the present application determines the character description prompt information based on the character, which can make the output character description prompt information more reasonable, thereby making the received character description information more accurate, so that the character image generated in the multimedia content based on the generated target character template meets the user's actual needs, thereby improving the user experience.

[0177] In some exemplary embodiments, step 604 outputs the role description prompt information and receives the role description information corresponding to the role description prompt information, which may specifically include the following steps:

[0178] 1. Control the display to present the target character creation template.

[0179] For example, the target role creation template includes role description prompt information, that is, the target role creation template can be multiple role description prompt information. For example, see Figure 10A , Figure 10A A schematic diagram of a target role creation template is shown, wherein: Figure 10A For example, "Hey kiddo, what does your dad look like? Can you tell meabout his hair, skin color, height, and if he's big or small?" can create a template for the target character.

[0180] 2. In response to an input operation on the role description prompt information, receiving role description information corresponding to the role description prompt information.

[0181] Furthermore, the user can input the role description information corresponding to the role description prompt information by operating the control device 100 or by voice input, see Figure 10B , Figure 10BIn the example, "He has golden hair, is very cute, wears glasses, and loves to read." is the character description information. This allows us to generate a target character template based on the character description information.

[0182] In the above embodiment, a feasible method for obtaining role description information is provided, which facilitates the subsequent generation of a target role template based on the role description information.

[0183] In some exemplary embodiments, step 602 determines role description prompt information according to the target role, which may specifically include the following steps:

[0184] 1. From each candidate role creation template, select at least one reference role creation template that matches the target role.

[0185] For example, the candidate character creation templates may be pre-set templates corresponding to different characters, wherein different candidate character creation templates include different character description prompts. For example, the character description prompts for a person may include prompts for hairstyle, height, weight, age, occupation, etc.; the character description prompts for an animal may include prompts for body shape, color, personality, etc.

[0186] Optionally, even if roles belong to the same type, roles with different identities can have different role description prompts. For example, a father and a child may both belong to the same persona, but the father's role description prompts may include work-related information, while the child's role description prompts do not. This makes the generated role template more unique and better suited to user needs.

[0187] It should be noted that the reference role creation template is the role creation template that matches the target role among the candidate role creation templates. There can be one or more reference role creation templates, and different reference role creation templates contain different role description prompts. A correspondence between the candidate role creation templates and the roles can be pre-established, and then, based on the target role, at least one reference role creation template that matches the target role can be selected from the candidate role creation templates.

[0188] 2. Select a target character creation template from each reference character creation template based on at least one of the version information of the content generation application, the version information of the display, and the template usage information of each reference character creation template.

[0189] It should be noted that the granularity of character image display varies depending on the version information of the content generation application and the version information of the display. For example, higher-level content generation application versions and higher-level display versions can display more granular character images, such as hairstyles that can display hair strands, skin that can display pores and wrinkles, and clothing that can display textures.

[0190] The template usage information of each reference role creation template may include the usage frequency of the reference role creation template. A higher usage frequency indicates that the reference role creation template is more popular and can be used preferentially.

[0191] Based on this, the controller can select a target role creation template from each reference role creation template based on at least one of the version information of the content generation application, the version information of the display, and the template usage information of each reference role creation template. The target role creation template includes role description prompt information for prompting the user to enter role description information.

[0192] In the above embodiment, the controller can determine the role description prompt information based on the version information of the content generation application, the version information of the display and at least one of the template usage information of each reference role creation template, so that the determined role description prompt information can be more in line with actual usage needs, and thus the determined role template can be more in line with actual usage needs.

[0193] In some exemplary embodiments, before executing the selection of the target character creation template from each reference character creation template based on the version information of the content generation application, the version information of the display and at least one of the template usage information of each reference character creation template, the controller can control the display to present a theme editing entrance in the content generation application to support the user to input the theme of the multimedia content; the controller receives the target theme of the multimedia content to be generated in response to the trigger operation for the theme editing entrance; exemplarily, the user can manipulate the control device 100 to input the target theme of the multimedia content, or can input the target theme of the multimedia content by voice.

[0194] Based on this, the embodiment of the present application provides another feasible method for selecting a target character creation template from various reference character creation templates. The difference between the embodiment and the above embodiment is that the target character creation template can be selected based on the theme of the multimedia content. Specifically, the following steps are included:

[0195] 1. From the reference role creation templates, select at least one candidate role creation template that matches the target theme.

[0196] Exemplarily, a correspondence between each candidate role creation template and the theme can be established in advance. After multiple reference role creation templates are screened out according to the target role in the candidate role creation templates, the controller can screen out at least one candidate role creation template that matches the target theme in the reference role creation templates based on the correspondence between each reference role creation template and the theme.

[0197] Alternatively, keywords may be extracted from the target theme, and at least one candidate role creation template corresponding to the keywords may be determined from each reference role creation template based on the extracted keywords.

[0198] 2. Select a target character creation template from each candidate character creation template based on at least one of the version information of the content generation application, the version information of the display, and the template usage information of each candidate character creation template.

[0199] Furthermore, after determining at least one candidate character creation template, the controller may continue to select a target character creation template from each candidate character creation template. Specifically, the controller may select a target character creation template from each candidate character creation template based on at least one of the version information of the content generation application, the version information of the display, and the template usage information of each candidate character creation template. In this way, in the process of determining the target character creation template, not only the fine-grained dimensions of the character image that can actually be displayed by the content generation application and the display can be taken into account; the frequency of use of each candidate character creation template can also be taken into account, thereby making the determined target character creation template more in line with actual character creation needs.

[0200] In the above embodiment, when determining the target character creation template, on the one hand, the target theme of the multimedia content is taken into consideration, so that the determined target character creation template is more in line with the multimedia content; on the other hand, the target character creation template can be selected from the candidate character creation templates based on the version information of the content generation application, the version information of the display, and at least one of the template usage information of each reference character creation template, so that the target character creation template provided to the user is more in line with the actual character creation needs.

[0201] It should be noted that generating a target role template can be a process of creating one from scratch, that is, the above embodiment provides a content generation application with a role editing entrance (eg Figure 7D ), a new role template can be created based on the role editing portal, enabling a custom target role template. Generating a target role template can also be a process of creating a new template based on an existing role template.

[0202] In some exemplary embodiments, before generating a target character template corresponding to the target character based on the character description information, the controller may further control the display to present at least one template card of a preset character template in the content generation application; and in response to a selection operation on a template card of a preset character template corresponding to the target character among the template cards, the controller determines the character template to be adjusted. A preset character template is a pre-set character template, and a template card can be understood as an image corresponding to the character template.

[0203] For example, in the above embodiment, Figure 7D The template card of each preset role template in the display interface supports editing operations. The user can select a template card of a preset role template, and the preset role template corresponding to the selected template card is regarded as the role template to be adjusted.

[0204] Furthermore, after selecting the role template to be adjusted, the controller updates the role template to be adjusted according to the role description information input by the user, and obtains the target role template corresponding to the target role. For example, if the role template to be adjusted selected by the user is the role template corresponding to "My dad", the controller updates the role template to be adjusted according to the role description information input by the user based on a preset algorithm or a preset model, and the target role template corresponding to the target role obtained can be Figure 9A The role template shown.

[0205] In the above embodiment, a method is provided for modifying an existing role template based on the existing role template to generate a new role template, thereby achieving the purpose of customizing the role template and enriching the role image of the target role in the generated multimedia content, thereby improving the user experience.

[0206] In some exemplary embodiments, each template card is associated with a role editing entry, and the role description prompt information includes at least one target role description item.

[0207] Among them, the role editing entrance can be understood as Figure 11A The "plus sign" corresponding to each character template in the target character description items may include hairstyle, clothing, height, weight, age, job, hobbies, personality, etc. The character description prompt information is used to prompt the user to enter content related to the target character description items. For example, the character description prompt information may be what color the hairstyle is, what clothes are worn, how tall, how heavy, how old, etc.

[0208] For example, the user can trigger the character editing entrance by manipulating the control device 100, or select a template card and voice input "adjust character template" to trigger the character editing entrance.

[0209] At this time, the controller may determine role description prompt information based on the target role in response to a triggering operation on the role editing entry associated with the template card of the role template to be adjusted. Alternatively, the controller may control the display to present the role template to be adjusted corresponding to the target role in response to a triggering operation on the role editing entry associated with the template card of the role template to be adjusted.

[0210] In some embodiments, the display device only displays the template card of the character template; that is, the display device does not store the character template itself. Therefore, in response to a triggering operation of a character editing entry associated with the template card of the character template to be adjusted, the controller can retrieve the character template to be adjusted from the server. The controller can then control the display to magnify the character template to be adjusted. In some embodiments, the magnification factor can be determined based on the display resolution, the resolution of the character template to be adjusted, and other factors.

[0211] After the controller displays the character template to be adjusted on the display, the user can select areas in the character template to be adjusted, such as hair, clothing, eyes, nose, etc. Accordingly, in response to the area selection operation for the character template to be adjusted, the controller can determine the character description items to be adjusted for the character template to be adjusted; for example, if the user selects hair and clothing as the areas to be adjusted, the controller can determine the character description items to be adjusted for the character template to be adjusted as hairstyle and clothing.

[0212] After determining the character description item to be adjusted, the controller may determine at least one target character description item based on the character description item to be adjusted, and generate character description prompt information based on the at least one target character description item. For example, the character description item to be adjusted selected by the user may be used as the target character description item, and information may be encapsulated based on the target character description item to obtain the character description prompt information.

[0213] In the above embodiment, the role description prompt information can be determined based on the role template to be adjusted and interacted with the user, that is, a process of determining the role description prompt information through human-computer interaction is provided, so that the input of the role description prompt information is more targeted, and the adjustment of the existing role template meets the actual needs of the user, thereby improving the user experience.

[0214] In some exemplary embodiments, the present application provides another achievable method for generating a target role template, which specifically includes the following steps:

[0215] 1. Control the display to present the character guide card.

[0216] Exemplarily, the character guide card is used to instruct the mobile terminal to send a basic image for the target character to the display device. For example, the character guide card can be a QR code. Exemplarily, if the character template the user wants to generate is "My Dad", the character guide card can be scanned by the mobile terminal to send the basic image to the display device.

[0217] 2. After receiving the basic image sent by the mobile terminal, a target role template corresponding to the target role is generated according to the basic image and role description information.

[0218] Furthermore, after receiving the basic image sent by the mobile terminal, the controller may update the basic image according to the role description information to obtain a target role template corresponding to the target role.

[0219] For example, after receiving the base image sent by the mobile terminal, the controller can call a preset algorithm to update the base image based on the character description information to obtain a target character template corresponding to the target character. Alternatively, the controller can call a preset model to update the base image based on the character description information to obtain a target character template corresponding to the target character.

[0220] In the above embodiment, an interaction process between the display device and the mobile terminal is introduced to obtain a basic image, and the basic image is modified based on the character description information to generate a target character template, thereby achieving the purpose of customizing the character template and enriching the character image of the target character in the generated multimedia content, thereby improving the user experience.

[0221] In some exemplary embodiments, the present application provides an implementable method for generating multimedia content, wherein the controller is further configured to obtain a template card corresponding to a target character template; and control a display to present the template card corresponding to the target character template in a content generation application; the specific implementation process is as follows:

[0222] When the template card corresponding to the target role template is in a selected state, if a content generation event is detected, a content generation instruction indicating the target role template is sent to the server; wherein the content generation instruction is used to instruct the server to generate multimedia content according to the target role template.

[0223] For example, when the template card corresponding to the target role template is in the selected state, a content generation event can be triggered. For example, the user can voice input "generate multimedia content" to trigger the content generation event; the user can also manipulate the control device 100 to trigger the role selection interface displayed by the display device (such as Figure 7D ) in the Generate Now button ( Figure 7D Not shown), to trigger a content generation event.

[0224] For example, the content generation instruction is used to instruct the server to generate multimedia content according to the target role template.

[0225] Furthermore, the controller controls the display to present a playback entry for the multimedia content in the content generation application. Figure 9E In the interface shown, the playback entrance of the multimedia content can be the cover of the multimedia content. The user can play the multimedia content by operating the control device to select the cover of the multimedia content, or by voice input to play the multimedia content.

[0226] It should be noted that the content generation application includes multiple pre-set multimedia content and supports user creation of new multimedia content. Each multimedia content includes multiple multimedia content images, with the character images across the images being consistent. Each multimedia content image is generated based on a section of the multimedia content story, and each multimedia content image is accompanied by an audio narration based on the story text associated with the multimedia content image.

[0227] In the content generation application, select multimedia content and confirm to play. The selected multimedia content can be played in video mode.

[0228] During the playback of multimedia content videos, multimedia content pictures can be displayed statically or with sliding effects. The story text corresponding to the picture on the page is also displayed on the multimedia content picture, and the display duration of each multimedia content picture corresponds to the broadcast audio duration of the multimedia content picture.

[0229] As an example, the switching display of two adjacent multimedia content pictures can be continuous, but the broadcast audio of the two adjacent multimedia content pictures is played at an interval of 1 second.

[0230] There can be background music during the playback of multimedia content, and the background music matches the story content of the multimedia content.

[0231] The above embodiment provides an achievable method for generating multimedia content based on a target character template, and the user can select the character image of the target character in the multimedia content according to their needs, thereby improving the user experience.

[0232] In some exemplary embodiments, the present application provides an implementable method for automatically generating text description information of multimedia content based on the theme and target role of the multimedia content. The specific implementation process is as follows:

[0233] Before executing the content generation instruction for the target character template sent to the server, the controller controls the display to present a theme editing portal in the content generation application, allowing the user to enter a theme for the multimedia content in the theme editing portal. In response to an operation on the theme editing portal, the controller receives a target theme for the multimedia content to be generated. The user can enter the target theme for the multimedia content by manipulating the control device 100 or by voice input.

[0234] The controller then sends a content generation instruction to the server that carries the target theme and target role and indicates the target role template; wherein the content generation instruction is used to instruct the server to generate text description information of the multimedia content according to the target theme and target role, and to generate multimedia content according to the text description information and the target role template.

[0235] It can be understood that the server can generate text description information of multimedia content according to the target theme and target role based on the text generation model, wherein the text generation model can be pre-trained with sample themes and sample roles as input data and sample text description information as label data to obtain the text generation model.

[0236] Furthermore, the server may generate multimedia content according to the text description information and the target role template, for example, by matching the text description information with each frame of the multimedia content, thereby generating the multimedia content.

[0237] In the above embodiment, a feasible method for generating multimedia content is provided, which can automatically generate text description information according to the target theme and target role of the multimedia content, so that the generated multimedia content is more story-telling; and generate multimedia content according to the text description information and the target role template, so that the generated multimedia content has a more appropriate combination of text and pictures, thereby improving the readability of the multimedia content.

[0238] In some exemplary embodiments, if the user wants to delete the generated multimedia content, the user may first select the multimedia content, such as Figure 11B As shown, trigger the "ok" button in the control device 100 to enter Figure 11C The interface shown triggers the deletion event and enters Figure 11D In the interface shown, trigger the delete button "Remove", confirm the deletion, and jump to Figure 11E interface, the multimedia content has been deleted.

[0239] In some exemplary embodiments, the present application provides an implementable method for generating a target role template corresponding to a target role based on role description information. The specific implementation process is as follows:

[0240] A first role generation instruction carrying role description information is sent to the server; wherein the first role generation instruction is used to instruct the server to call a target text graph model and generate a target role template corresponding to the target role according to the role description information; wherein the target text graph model includes a text encoder, a denoising network and an image generator.

[0241] Exemplarily, the target text graph model is trained using the sample role description information as input and the sample role template as labeled data. Based on this, the server inputs the first role generation instruction carrying the role description information into the target text graph model and outputs the target role template corresponding to the target role.

[0242] In the above embodiment, the target role template is generated based on the role description information through the target context graph model, which can improve the efficiency of generating the target role template on the one hand, and improve the accuracy of generating the target role template on the other hand.

[0243] In some exemplary embodiments, see Figure 12 , Figure 12 A structural diagram of a target text-based graph model is provided, wherein the target text-based graph model includes a text encoder, a denoising network, and an image generator; Z T is the initial noise image, Z T-1 is the first denoised image, and Z0 is the Tth denoised image.

[0244] The embodiment of the present application provides an achievable method for a server to generate a target role template corresponding to a target role based on a target text graph model and according to role description information. The specific implementation process is as follows:

[0245] Exemplarily, the server may input the role description information into a text editor, and the text encoder is used to extract features from the role description information to obtain a text embedding vector.

[0246] The server then inputs the text embedding vector into the denoising network, which denoises the initial noisy image based on the text embedding vector to produce a denoised image. The initial noisy image can be understood as a preset noisy image, either a randomly generated one or a fixed input one, which is then denoised based on the text embedding vector to produce the denoised image used to generate the target character template.

[0247] Furthermore, the server inputs the denoising network into the image generator, and the image generator is used to perform an image generation operation based on the denoised image to obtain a target role template corresponding to the target role.

[0248] The above embodiment provides a specific implementation method for generating a target role template based on role description information through a target context graph model, which can improve the efficiency of generating the target role template and improve the accuracy of generating the target role template.

[0249] In some exemplary embodiments, the present application provides an achievable method for a server to train a target document graph model, specifically comprising the following steps:

[0250] 1. Get sample person images.

[0251] For example, the server can first obtain sample person images, for example, from film and television resources, publicly available online, and third-party data sources. The sample person images should include both Chinese and Western faces, taking into account age distribution and gender ratio. These images are then annotated with information such as hairstyle, face shape, body shape, clothing, makeup, accessories, and posture.

[0252] 2. Extract the sample description information corresponding to the sample person image.

[0253] Furthermore, the server extracts sample description information corresponding to the sample character image, for example, extracts information on dimensions such as hairstyle, face shape, body shape, clothing, makeup, accessories, and posture corresponding to the sample character image.

[0254] 3. According to the sample description information corresponding to the sample person image, the denoising network in the initial text image model is trained to obtain the predicted person image.

[0255] Furthermore, the server uses the sample description information as input data and the sample character image corresponding to the sample description information as label data, and trains the denoising network in the initial text-based graph model to obtain a predicted character image.

[0256] 4. Use the face recognition model to determine the image difference between the sample person image and the predicted person image.

[0257] Exemplarily, the server may use a face recognition model to determine the image difference between the sample person image and the predicted person image.

[0258] 5. Adjust the model parameters of the denoising network in the initial text image model according to the image differences to obtain the target text image model.

[0259] Furthermore, the server uses the image difference as a loss to adjust the model parameters of the denoising network in the initial text-based graph model until the number of training times reaches a preset number or the image difference is less than a preset difference, thereby obtaining the target text-based graph model.

[0260] The above embodiment provides an achievable method for obtaining a target context graph model, which facilitates generating a target role template using the target context graph model and improves the efficiency of generating the target role template.

[0261] In some exemplary embodiments, the present application provides another achievable method for generating a target role template, and the specific implementation process is as follows:

[0262] A second role generation instruction carrying role description information is sent to the server; wherein the second role generation instruction is used to instruct the server to select a target role image with the highest matching degree with the role description information from the candidate role images, and use the target role image as a target role template corresponding to the target role.

[0263] Exemplarily, the candidate character images may be a plurality of pre-stored character images; the server may use text image similarity matching technology to score each candidate image according to the character description information, and use the candidate character image with a score greater than a set score threshold, or the candidate character image with the highest score, as the target character image, and use the target character image as the target character template corresponding to the target character.

[0264] In the above embodiment, by adopting the text similarity matching method, a target role template is generated according to role description information, thereby enriching the role image of the target role in the generated multimedia content, thereby improving the user experience.

[0265] It should be noted that the above-mentioned voice input content is only an exemplary description and is not intended to limit the voice input content of each step. The voice input content corresponding to each specific operation step can be pre-set or user-defined.

[0266] In some exemplary embodiments, see Figure 13 ,13 provides a timing diagram of a role template generation method, and the specific ,implementation process is as follows:

[0267] 1. The user manipulates the control device 100 to trigger an instruction to open the content generating application, or triggers an instruction to open the content generating application by voice inputting "open content generating application".

[0268] 2. The content generation application responds to the opening content generation instruction and synchronizes the instruction to enter the content generation application to the controller.

[0269] 3. Based on the instruction to enter the content generation application, the controller controls the display to display the operation interface of the content generation application.

[0270] 4. The display presents the operation page of the content generation application.

[0271] 5. The content generation application responds to the instruction to generate multimedia content and synchronizes the instruction to generate multimedia content to the controller.

[0272] 6. Based on the instruction to generate multimedia content, the controller controls the display to display an operation page for inputting multimedia themes and roles.

[0273] 7. The display sequentially presents the operation pages for inputting multimedia themes and roles.

[0274] 8. The content generation application responds to the input target theme and target role of the multimedia content and synchronizes instructions for generating the target theme and target role of the multimedia content to the controller.

[0275] 9. The controller controls the display to display the target theme and target role based on the instruction for generating the target theme and target role of the multimedia content.

[0276] 10. The display presents the target subject and target role.

[0277] 11. The content generation application responds to the operation that triggers the role editing portal and synchronizes the instruction to generate the target role template to the controller.

[0278] 12. The controller determines the role description prompt information corresponding to the target role template based on the instruction to generate the target role template, and controls the display to display the role description prompt information.

[0279] 13. The display shows the character description prompt information.

[0280] 14. The content generation application responds to the operation of inputting the role description information and synchronizes the role description information to the controller.

[0281] 15. The controller controls the server to generate a target role template based on the role description information, and controls the display to display the target role template.

[0282] 16. The display presents the target role template.

[0283] 17. The controller controls the server to generate multimedia content based on the target role template.

[0284] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0285] Based on the same inventive concept, the present application also provides a character template generation device for implementing the aforementioned character template generation method. The device provides a similar solution to the problem described in the aforementioned method. For specific limitations, refer to the limitations on character template generation above and will not be repeated here.

[0286] In one embodiment, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above-mentioned character template generation method when executed by a processor.

[0287] In one embodiment, the present application further provides a computer program product, including a computer program, which implements the steps of the above-mentioned character template generation method when executed by a processor.

[0288] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. 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. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory 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), magnetic 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. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0289] The technical features of the above embodiments can be combined arbitrarily. In order 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 application.

[0290] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A display device, characterized in that: include: a controller configured to receive a control signal from a control device and control a display in the display device to display according to the control signal; The display is configured to display a character editing entry in the content generation application; The controller is further configured to: In response to a trigger operation on the role editing entry, when a target role is determined, role description prompt information is determined according to the target role; Controlling the display to present the character description prompt information; receiving role description information corresponding to the role description prompt information; Generating a target role template corresponding to the target role according to the role description information; wherein the target role template is used to generate a role image of the target role in the multimedia content; Obtaining the template card corresponding to the target role template; controlling a display to present a template card corresponding to the target role template in the content generation application; When the template card corresponding to the target role template is in a selected state, if a content generation event is detected, a content generation instruction carrying a target theme and a target role and indicating the target role template is sent to a server; wherein the content generation instruction is used to instruct the server to generate text description information of multimedia content according to the target theme and the target role, and generate the multimedia content according to the text description information and the target role template; The display is controlled to present a playback entry for the multimedia content in the content generation application.

2. The display device according to claim 1, wherein Before generating a target role template corresponding to the target role according to the role description information, the controller is further configured to: controlling the display to present a template card of at least one preset role template in the content generation application; In response to a selection operation on a template card of a preset role template corresponding to the target role among the template cards, determining a role template to be adjusted; When the controller generates a target role template corresponding to the target role according to the role description information, the controller is further configured to: The role template to be adjusted is updated according to the role description information to obtain a target role template corresponding to the target role.

3. The display device according to claim 2, wherein Each template card is associated with a role editing entry, and the role description prompt information includes at least one target role description item; When the controller responds to a trigger operation on the character editing entry, the controller is further configured to: In response to a triggering operation on a role editing entry associated with a template card of the role template to be adjusted; When the controller determines the role description prompt information according to the target role, the controller is further configured to: Controlling the display to present the role template to be adjusted corresponding to the target role; In response to the region selection operation on the role template to be adjusted, determining a role description item to be adjusted of the role template to be adjusted; Determining at least one target role description item according to the role description item to be adjusted; The role description prompt information is generated according to at least one target role description item.

4. The display device according to claim 1, wherein When the controller generates a target role template corresponding to the target role according to the role description information, the controller is further configured to: Controlling the display to present a character guide card; wherein the character guide card is used to instruct the mobile terminal to send a basic image for the target character to the display device; After receiving the basic image sent by the mobile terminal, a target role template corresponding to the target role is generated according to the basic image and the role description information.

5. The display device according to claim 1, wherein When the controller controls the display to present the character description prompt information, the controller is further configured to: Controlling the display to present a target character creation template; wherein the target character creation template includes character description prompt information; When the controller receives the role description information corresponding to the role description prompt information, the controller is further configured to: In response to an input operation on the role description prompt information, role description information corresponding to the role description prompt information is received.

6. The display device according to claim 1, wherein Before executing the sending of a content generation instruction carrying a target theme and a target role and indicating the target role template to the server, the controller is further configured to: A controller display presents a theme editing entry in the content generation application; In response to an operation on the theme editing entry, a target theme of the multimedia content to be generated is received.

7. The display device according to claim 1, wherein When the controller determines the role description prompt information according to the target role, the controller is further configured to: Selecting at least one reference role creation template that matches the target role from each candidate role creation template; wherein different reference role creation templates contain different role description prompt information; A target character creation template is selected from the reference character creation templates according to at least one of the version information of the content generation application, the version information of the display, and the template usage information of the reference character creation templates.

8. The display device according to claim 7, wherein: Before selecting a target character creation template from each reference character creation template based on at least one of the version information of the content generation application, the version information of the display, and the template usage information of each reference character creation template, the controller is further configured to: controlling the display to present a theme editing entrance in the content generation application; In response to a triggering operation on the theme editing entry, receiving a target theme of the multimedia content to be generated; The controller is further configured to, when selecting a target character creation template from each reference character creation template based on at least one of version information of the content generation application, version information of the display, and template usage information of each reference character creation template: Selecting at least one candidate role creation template that matches the target theme from the reference role creation templates; A target character creation template is selected from each candidate character creation template according to at least one of the version information of the content generation application, the version information of the display, and the template usage information of each candidate character creation template.

9. The display device according to claim 1, wherein When the controller generates a target role template corresponding to the target role according to the role description information, the controller is further configured to: Send a first role generation instruction carrying the role description information to the server; wherein the first role generation instruction is used to instruct the server to call a target text graph model and generate a target role template corresponding to the target role based on the role description information; wherein the target text graph model includes a text encoder, a denoising network and an image generator.

10. The display device according to claim 9, wherein The text encoder is used to extract features from the role description information to obtain a text embedding vector; the denoising network is used to denoise the initial noisy image based on the text embedding vector to obtain a denoised image; the image generator is used to perform an image generation operation based on the denoised image to obtain a target role template corresponding to the target role.

11. The display device according to claim 9, wherein The target cultural graph model is trained in the following way: Get a sample person image; Extracting sample description information corresponding to the sample person image; Training a denoising network in the initial text-based graph model based on sample description information corresponding to the sample person image to obtain a predicted person image; Using a face recognition model, determining an image difference between the sample person image and the predicted person image; The model parameters of the denoising network in the initial text graph model are adjusted according to the image difference to obtain the target text graph model.

12. The display device according to claim 1, wherein When the controller generates a target role template corresponding to the target role according to the role description information, the controller is further configured to: A second role generation instruction carrying the role description information is sent to the server; wherein the second role generation instruction is used to instruct the server to select a target role image with the highest matching degree with the role description information from the candidate role images, and use the target role image as the target role template corresponding to the target role.

13. A method for generating a role template, characterized in that: The method is applied to a controller in a display device, the controller being configured to receive a control signal from a control device and control a display in the display device to perform display according to the control signal. The method includes: In response to a triggering operation on a character editing entry displayed on a display in a content generation application, upon determining a target character, determining character description prompt information based on the target character; Controlling the display to present the character description prompt information; receiving role description information corresponding to the role description prompt information; Generating a target role template corresponding to the target role according to the role description information; wherein the target role template is used to generate a role image of the target role in the multimedia content; Obtaining the template card corresponding to the target role template; controlling a display to present a template card corresponding to the target role template in the content generation application; When the template card corresponding to the target role template is in a selected state, if a content generation event is detected, a content generation instruction carrying a target theme and a target role and indicating the target role template is sent to a server; wherein the content generation instruction is used to instruct the server to generate text description information of multimedia content according to the target theme and the target role, and generate the multimedia content according to the text description information and the target role template; The display is controlled to present a playback entry for the multimedia content in the content generation application.

Images