Display device, server and media asset recommendation method

Abstract

The invention provides a display device, a server and a media asset recommendation method. According to the method, after a first media asset recommendation result is displayed on a media asset recommendation interface, real-time behavior data of a user is collected within a preset duration; and generating real-time recommendation data corresponding to the first media asset data according to the real-time behavior data. And when the user sends a switching instruction, updating the first media asset recommendation result into the second media asset recommendation result. And if the second media asset data contains third media asset data which is the same as the first media asset data, taking real-time recommendation data corresponding to the third media asset data as second recommendation data, and displaying an updated second media asset recommendation result on the media asset recommendation interface. According to the process, the real-time behavior data of the user is collected, the real-time recommendation data is generated according to the real-time behavior data, the real-time recommendation data is displayed when the media asset result is updated, the recommendation data in the media asset recommendation result can be adjusted according to the real-time behavior data for dynamic adjustment, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of image and text processing technology, and in particular to a display device, a server, and a media resource recommendation method. Background Art

[0002] The application of personalized recommendation systems in terminal devices is a growing field. They provide customized service experience by analyzing user behavior data. Personalized recommendation systems can deeply analyze user behavior patterns to build user profiles. Based on these user data, personalized recommendation systems can predict the products or services that users may be interested in based on collaborative filtering, content recommendation algorithms, deep learning and other methods.

[0003] Some display devices can be equipped with a user personalized recommendation system. For example, a TV terminal can be equipped with a personalized recommendation system to recommend multimedia resources to users. Existing personalized recommendation systems usually use a unified display format when presenting recommended content to users, such as standard posters and simple text descriptions. However, the unified display format ignores the differences in user needs in different situations and cannot be dynamically adjusted based on real-time user feedback, affecting the user's overall experience of multimedia resource recommendations. Summary of the invention

[0004] The present application provides a display device, a server and a media resource recommendation method, which can accurately reflect the user's immediate interests and behavior patterns by collecting the user's real-time behavior data and generating real-time recommendation data based on the data. In addition, generating real-time recommendation data can continuously optimize the recommendation algorithm and strategy, and improve the user's viewing experience of the media resource recommendation results.

[0005] In a first aspect, the present application provides a display device, including:

[0006] monitor;

[0007] A controller is coupled to the display and is configured to:

[0008] Controlling the display to display a first media asset recommendation result on the media asset recommendation interface, wherein the first media asset recommendation result includes first recommended data corresponding to the first media asset data, and the first recommended data includes a first recommended poster and a first recommended text;

[0009] After the first media resource recommendation result is displayed on the media resource recommendation interface, real-time behavior data of the user within a preset time period is collected;

[0010] Generate real-time recommendation data corresponding to each first media asset data according to the first media asset recommendation result and the real-time behavior data; the real-time recommendation data includes a real-time recommendation poster and a real-time recommendation text;

[0011] In response to the switching instruction, the first media asset recommendation result is updated to a second media asset recommendation result; the second media asset recommendation result includes second recommendation data corresponding to a plurality of second media asset data, and the second recommendation data includes a second recommendation poster and a second recommendation text;

[0012] When the second media asset data includes the third media asset data, the real-time recommended data corresponding to the third media asset data is used as the second recommended data corresponding to the third media asset data; the third media asset data is the same second media asset data as the first media asset data;

[0013] The display is controlled to display the second media resource recommendation result on the media resource recommendation interface.

[0014] According to the above embodiment, by displaying the first media asset recommendation result on the media asset recommendation interface, after displaying the first media asset recommendation result, the user's real-time behavior data is collected within a preset time. According to the collected first media asset recommendation result and real-time behavior data, the real-time recommendation data corresponding to each first media asset data is generated. When the user issues a switching instruction, the first media asset recommendation result is updated to the second media asset recommendation result, and the second media asset recommendation result includes multiple second media asset data and their corresponding second recommendation data. If the second media asset data contains the same media asset data as the first media asset data, that is, the third media asset data, the real-time recommendation data corresponding to the third media asset data is used as the second recommendation data. Finally, the display is controlled to display the updated second media asset recommendation result on the media asset recommendation interface. This process collects the user's real-time behavior data, generates real-time recommendation data based on the real-time behavior data, and displays the real-time recommendation data when the media asset result is updated. It can dynamically adjust the recommendation data in the media asset recommendation result according to the real-time behavior data, thereby improving the user's viewing experience of the media asset recommendation result.

[0015] In some feasible embodiments, the controller generates real-time recommendation data corresponding to each first media asset data according to the first media asset recommendation result and the real-time behavior data, and is specifically configured as follows:

[0016] Determine, according to the first media resource recommendation result and the real-time behavior data, a poster recommendation prompt and a text recommendation prompt corresponding to the first media resource data;

[0017] Processing the text recommendation prompt according to the text generation model to obtain a real-time recommendation text corresponding to the first media asset data;

[0018] The poster recommendation prompt is processed according to the poster generation model to obtain a real-time recommended poster corresponding to the first media asset data.

[0019] According to the above embodiment, the poster recommendation prompt and the text recommendation prompt can be determined according to the first media resource recommendation result and the real-time behavior data. Using the poster generation model to process the poster recommendation prompt and generate personalized and attractive real-time recommendation posters can improve the quality of the recommendation posters and make them more in line with the user's interests and preferences. Using the text generation model to process the text recommendation prompt and generate natural and rich real-time recommendation text can improve the quality of the recommendation text and make it more attractive to users. In this way, improving the poster quality and text recommendation quality can improve the recommendation effect of the media resource recommendation system and improve the user experience.

[0020] In some feasible embodiments, the controller determines the poster recommendation prompt and the text recommendation prompt corresponding to the first media asset data according to the first media asset recommendation result and the real-time behavior data, and is specifically configured as follows:

[0021] Extract user behavior features from real-time behavior data;

[0022] Extracting metadata features of each first media asset data, where the metadata features are used to characterize attributes of the first media asset data;

[0023] Based on user behavior characteristics, metadata characteristics and preset prompt templates, poster recommendation prompts and text recommendation prompts are determined.

[0024] According to the above embodiment, user behavior features can be extracted from real-time behavior data, and combined with metadata features of the first media asset data to generate poster recommendation prompts and text recommendation prompts. In this way, the user's immediate interests and behavior patterns can be reflected, providing a more personalized and accurate recommendation experience, thereby improving the recommendation effect and user satisfaction of the media asset recommendation system.

[0025] In some feasible embodiments, the controller controls the display to display the second media resource recommendation result on the media resource recommendation interface, which is specifically configured as follows:

[0026] Displaying at least one second recommended poster in the first display area of ​​the media resource recommendation interface;

[0027] At least one second recommendation text corresponding to the second recommendation poster is displayed in the second display area of ​​the media resource recommendation interface.

[0028] According to the above embodiment, the second recommended poster displayed in the first display area corresponds to the second recommended text displayed in the second display area one by one. This layout method can effectively utilize the screen space and provide the user with clear information display.

[0029] In some feasible embodiments, the controller controls the display to display the second media resource recommendation result on the media resource recommendation interface, and is specifically configured as follows:

[0030] Displaying at least one second recommended poster in the third display area of ​​the media resource recommendation interface;

[0031] When the second recommended poster is selected as the focus of the media resource recommendation interface, the second recommended text corresponding to the selected second recommended poster is displayed in the fourth display area of ​​the media resource recommendation interface.

[0032] According to the above embodiment, the second recommended text displayed in the fourth display area corresponds to the second recommended poster focused on in the third display area. This layout method can effectively utilize the screen space and provide users with clear information display.

[0033] In some feasible embodiments, the controller controls the display to display the second media resource recommendation result on the media resource recommendation interface, and is specifically configured as follows:

[0034] Displaying at least one second recommended poster in the fifth display area of ​​the media resource recommendation interface;

[0035] When the second recommended poster is selected as the focus of the media resource recommendation interface, a first pop-up window is displayed according to the position of the selected second recommended poster; the first pop-up window includes a second recommended text corresponding to the selected second recommended poster.

[0036] According to the above embodiment, the fifth display area is used to display the second recommended posters, and when the user focuses on a second recommended poster, a first pop-up window is displayed according to the position of the selected second recommended poster, and the pop-up window includes the third recommended text corresponding to the selected second recommended poster. Such a layout can increase the user's attention to the recommended content and enhance the user's interactive experience with the recommended content.

[0037] In some feasible embodiments, the controller controls the display to display the first media resource recommendation result on the media resource recommendation interface, and is specifically configured as follows:

[0038] In the case where there is historical data of the media assets watched by the user, the historical data of the media assets watched by the user and a media asset database are obtained, where the media asset database includes a plurality of media asset data;

[0039] Using the media asset recommendation model, the historical data and all the media asset data are processed to obtain a plurality of first media asset data to be recommended;

[0040] Acquire a first media asset feature of the first media asset data;

[0041] Obtain historical user portrait features and historical user behavior features of historical data;

[0042] Using a text generation model, the first media asset feature, the historical user portrait feature, and the historical user behavior feature are processed to obtain a first recommended text for the first media asset data;

[0043] Using the poster generation model, the first media asset feature, the historical user portrait feature, and the user behavior feature are processed to obtain a first recommended poster for the first media asset data;

[0044] taking all first media asset data, first recommended texts corresponding to the first media asset data, and first recommended posters as first media asset recommendation results;

[0045] The display is controlled to display the first media resource recommendation result on the media resource recommendation interface.

[0046] According to the above embodiment, the user's interests and preferences can be accurately understood based on the user's historical data. An explanatory first recommendation text can also be provided for the first media data based on the text generation model to help the user better understand and select recommended content. The poster generation model is used to generate attractive visual materials for each recommended content, thereby increasing the user's willingness to click and improving the user experience.

[0047] In some feasible embodiments, the controller controls the display to display the first media resource recommendation result on the media resource recommendation interface, and is specifically configured as follows:

[0048] In the absence of historical data of the user watching the media assets, obtaining a media asset database; the media asset database includes a plurality of media asset data;

[0049] Using the media asset recommendation model, all media asset data are processed to obtain a plurality of first media asset data to be recommended;

[0050] Acquire a first media asset feature of the first media asset data;

[0051] Generate first recommended texts corresponding to the first media asset data according to the first media asset features by using a text generation model;

[0052] Using the initial poster of the first media asset data as the first recommended poster;

[0053] taking all first media asset data, first recommended texts corresponding to the first media asset data, and first recommended posters as first media asset recommendation results;

[0054] The display is controlled to display the first media resource recommendation result on the media resource recommendation interface.

[0055] According to the above embodiment, in the absence of historical data of the user, the media asset recommendation model is used to generate the first media asset data according to the media asset data in the media asset database, and the first media asset feature of the first media asset data is extracted. Then, the first media asset feature is respectively input into the text generation model and the image generation model to obtain the first recommendation data of the first media asset data. In this way, an explanatory first recommendation text can be provided for the first media asset data based on the text generation model to help users better understand and select the recommended content, and the poster generation model is used to generate attractive visual materials for each recommended content, thereby increasing the user's willingness to click and improving the user experience.

[0056] In a second aspect, the present application provides a display device, including:

[0057] monitor;

[0058] A communicator configured to communicate with the server;

[0059] A controller is coupled to the display and the communicator and is configured to:

[0060] Controlling the display to display a first media asset recommendation result on the media asset recommendation interface, wherein the first media asset recommendation result includes first recommended data corresponding to the first media asset data, and the first recommended data includes a first recommended poster and a first recommended text;

[0061] After the first media resource recommendation result is displayed on the media resource recommendation interface, real-time behavior data of the user within a preset time period is collected;

[0062] Controlling the communicator to send the real-time behavior data to the server, so that the server obtains the real-time behavior data corresponding to the first media asset data according to the first media asset recommendation data and the real-time behavior data; the real-time recommendation data includes a real-time recommendation poster and a real-time recommendation text;

[0063] receiving a switching instruction, and controlling the communicator to send the switching instruction to the server, so that the server updates the first media asset recommendation result to a second media asset recommendation result according to the switching instruction; the second media asset recommendation result includes second recommendation data corresponding to a plurality of second media asset data, and the second recommendation data includes a second recommendation poster and a second recommendation text;

[0064] Controlling the communicator to receive a second media resource recommendation result;

[0065] The display is controlled to display the second media resource recommendation result on the media resource recommendation interface.

[0066] In a third aspect, the present application provides a server, including:

[0067] A communicator configured to be communicatively connected with a display device;

[0068] A processor is coupled to the communicator and is configured to:

[0069] Controlling the communicator to receive the real-time behavior data from the display device, and generating real-time recommendation data corresponding to each first media asset data according to the first media asset recommendation result and the real-time behavior data; the real-time recommendation data includes a real-time recommendation poster and a real-time recommendation text;

[0070] Controlling the communicator to receive a switching instruction from the display device, and updating the first media asset recommendation result to a second media asset recommendation result in response to the switching instruction; the second media asset recommendation result includes second recommendation data corresponding to a plurality of second media asset data, and the second recommendation data includes a second recommendation poster and a second recommendation text;

[0071] When the second media asset data includes the third media asset data, the real-time recommended data corresponding to the third media asset data is used as the second recommended data corresponding to the third media asset data; the third media asset data is the same second media asset data as the first media asset data;

[0072] The communicator is controlled to send the second media resource recommendation result to the display device, so that the display of the display device displays the second media resource recommendation result on the media resource recommendation interface.

[0073] In a fourth aspect, the present application provides a media resource recommendation method, which is applied to a display device, the display device including a display and a controller, and is characterized in that it includes:

[0074] Controlling the display to display a first media asset recommendation result on the media asset recommendation interface, wherein the first media asset recommendation result includes first recommended data corresponding to the first media asset data, and the first recommended data includes a first recommended poster and a first recommended text;

[0075] After the first media resource recommendation result is displayed on the media resource recommendation interface, real-time behavior data of the user within a preset time period is collected;

[0076] Generate real-time recommendation data corresponding to each first media asset data according to the first media asset recommendation result and the real-time behavior data; the real-time recommendation data includes a real-time recommendation poster and a real-time recommendation text;

[0077] In response to the switching instruction, the first media asset recommendation result is updated to a second media asset recommendation result; the second media asset recommendation result includes second recommendation data corresponding to a plurality of second media asset data, and the second recommendation data includes a second recommendation poster and a second recommendation text;

[0078] When the second media asset data includes the third media asset data, the real-time recommended data corresponding to the third media asset data is used as the second recommended data corresponding to the third media asset data; the third media asset data is the same second media asset data as the first media asset data;

[0079] The display is controlled to display the second media resource recommendation result on the media resource recommendation interface.

[0080] It can be understood that the beneficial effects that can be achieved by the technical solutions provided in the second to fourth aspects mentioned above can refer to the beneficial effects in the first aspect and any optional implementation method thereof, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0082] Figure 1 A schematic diagram of an operation scenario between a display device and a control device provided in an embodiment of the present application;

[0083] Figure 2 A hardware configuration block diagram of a display device provided in an embodiment of the present application;

[0084] Figure 3 A schematic diagram of software configuration of a display device provided in an embodiment of the present application;

[0085] Figure 4 A schematic diagram of the structure of a media resource recommendation system for a display device provided in an embodiment of the present application;

[0086] Figure 5 A schematic diagram of a process for a display device provided in an embodiment of the present application to update media resource recommendation results according to real-time behavior data of a user;

[0087] Figure 6 A schematic diagram of a process of displaying a first media resource recommendation result on a media resource recommendation interface of a first display device provided in an embodiment of the present application;

[0088] Figure 7 A schematic diagram of a process of displaying a first media resource recommendation result on a media resource recommendation interface of a second display device provided in an embodiment of the present application;

[0089] Figure 8 A schematic diagram of a process for a display device according to an embodiment of the present application to generate real-time recommendation data based on a first media resource recommendation result and real-time behavior data;

[0090] Fig. 9 A schematic diagram of a process for determining a preset prompt template provided in an embodiment of the present application;

[0091] Fig.10 A schematic diagram of a first display provided in an embodiment of the present application displaying a second media resource recommendation result on a media resource recommendation interface;

[0092] Fig.11A schematic diagram of a second display provided in an embodiment of the present application displaying a second media resource recommendation result on a media resource recommendation interface;

[0093] Fig.12 A schematic diagram of a third display provided in an embodiment of the present application displaying a second media resource recommendation result on a media resource recommendation interface;

[0094] Fig.13 A schematic diagram of a process for updating media resource recommendation results according to real-time behavior data of a user provided in an embodiment of the present application;

[0095] Fig.14 A schematic diagram of a process for communicating with a server to update media resource recommendation results according to real-time behavior data of a user provided in an embodiment of the present application. DETAILED DESCRIPTION

[0096] The following embodiments are described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following embodiments do not represent all implementations consistent with the present application. They are only examples of systems and methods consistent with some aspects of the present application as detailed in the claims.

[0097] It should be noted that the brief description of terms in this application is only for the convenience of understanding the embodiments described below, and is not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their ordinary and common meanings.

[0098] The terms "first", "second", "third", etc. in the specification and claims of this application and the above drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances.

[0099] The terms "including" and "having" and any variations thereof are intended to cover but not be exclusive, for example, a product or device comprising a series of components is not necessarily limited to all the components explicitly listed, but may include other components not explicitly listed or inherent to these products or devices. 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 functions associated with the element.

[0100] The display device 200 provided in the embodiment of the present application generally refers to a device with image display and data processing capabilities, and can have various implementation forms, for example, it can be a television, a smart TV, a computer, a laser projection device, a display (monitor), an electronic whiteboard (electronic bulletin board), an electronic desktop (electronic table), a monitor, an advertising screen, a wearable device, a virtual reality device, an augmented reality device, etc.

[0101] Figure 1 Schematic diagram of an operation scenario between a display device 200 and a control device 100 provided in an embodiment of the present application. Figure 1 As shown, the user can operate the display device 200 through the terminal device 300 or the control device 100 .

[0102] In some embodiments, the control device 100 is used to receive operation instructions input by the user and convert the operation instructions into control instructions that the display device 200 can recognize and respond to. The control device 100 can be a remote control, a stylus, a handle, etc., wherein the communication between the remote control and the display device 200 includes infrared protocol communication or Bluetooth protocol communication, and other short-range communication methods, and the display device 200 is controlled wirelessly or wired. The user can input user instructions through buttons on the remote control, voice input, control panel input, etc. to control the display device 200.

[0103] In some embodiments, a terminal device 300 (such as a mobile terminal, a tablet computer, a computer, a laptop computer, etc.) can also be used as a control device for performing human-computer interaction between a user and the display device 200. The mobile terminal 300 can also be used as a communication device for establishing a communication connection with the display device 200 and performing data interaction. The mobile terminal 300 can install the same software application as the display device 200, and then achieve connection and communication through a network communication protocol to achieve the purpose of one-to-one control operation and data communication. The audio and video content displayed on the mobile terminal 300 can also be transmitted to the display device 200 to achieve a synchronous display function.

[0104] In some embodiments, the mobile terminal 300 or other electronic devices may also simulate the functions of the control device 100 by running an application program for controlling the display device 200 .

[0105] In some embodiments, the display device 200 may also be controlled in a manner other than the control device 100 and the terminal device 300, for example, the user's voice command control may be directly received through a module for acquiring voice commands configured inside the display device 200, or the user's voice command control may be received through a voice control device provided outside the display device 200. The display device 200 may also receive user control through touch or gestures.

[0106] In some embodiments, 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. The server 400 may provide various content and interactions to the display device 200. The server 400 may be one cluster or multiple clusters, and may include one or more types of servers.

[0107] The display device 200 may provide a broadcast receiving television function, and may also additionally provide an intelligent network television function with a computer support function, including but not limited to network television, smart television, Internet Protocol television (IPTV), and the like.

[0108] Figure 2 Some embodiments of the present application provide Figure 1 2 is a block diagram of the hardware configuration of the display device 200.

[0109] like Figure 2 As shown, the display device 200 may include at least one of a tuner 210, a communication device 220, a detector 230, an external device interface 240, a controller 250, a display 260, an audio output interface 270, a memory, a power supply, and a user interface.

[0110] In some embodiments, the tuner-demodulator 210 receives broadcast television signals via wired or wireless reception, and demodulates audio and video signals, such as EPG data signals, from a plurality of wireless or wired broadcast television signals.

[0111] In some embodiments, the communication device 220 is a component for communicating with an external device or server according to various communication protocol types. The display device 200 can be provided with a plurality of communication devices 220 according to the different communication modes supported. For example, when the display device 200 supports wireless network communication, the display device 200 can be provided with a communication device 220 including a WiFi function. When the display device 200 supports Bluetooth connection communication, the display device 200 needs to be provided with a communication device 220 including a Bluetooth function. The communication device 220 may include at least one of a Wifi module, a Bluetooth module, a wired Ethernet module, and other network communication protocol chips or near field communication protocol chips, and an infrared receiver. The display device 200 can establish the sending and receiving of control signals and data signals with the external control device 100 or the server 400 through the communication device 220.

[0112] The communication device 220 can enable the display device 200 to communicate with the external device or server 400 by wireless or wired connection. Among them, the wired connection can connect the display device 200 with the external device through components such as data cables and interfaces. The wireless connection can connect the display device 200 with the external device through wireless signals or wireless networks. The display device 200 can establish a connection relationship with the external device directly, or indirectly establish a connection relationship through a gateway, a router, a connection device, etc.

[0113] In some embodiments, the detector 230 is used to collect signals of the external environment or external interaction. For example, the detector 230 includes a light receiver, a sensor for collecting the intensity of ambient light; or, the detector 230 includes an image collector, such as a camera, which can be used to collect external environment scenes, user attributes or user interaction gestures; or, the detector 230 includes a sound collector, such as a microphone, etc., for receiving external sounds.

[0114] In some embodiments, the external device interface 240 may include, but is not limited to, any one or more of the following interfaces: a high-definition multimedia interface (HDMI), an analog or digital high-definition component input interface (component), a composite video input interface (CVBS), a USB input interface (USB), an RGB port, etc. It may also be a composite input / output interface formed by the above multiple interfaces.

[0115] In some embodiments, the controller 250 controls the operation of the display device 200 and responds to user operations through various software control programs stored in the memory. The controller 250 controls the overall operation of the display device 200. For example, in response to receiving a user command for selecting a UI object to be displayed on the display 260, the controller 250 can perform operations related to the object selected by the user command.

[0116] In some embodiments, the controller 250 includes at least one of a central processing unit (CPU), a video processor, an audio processor, a graphics processing unit (GPU), a random access memory (RAM), a read-only memory (ROM), a first interface to an nth interface for input / output, a communication bus, etc. The controller 250 controls the operation of the display device and responds to the user's operation through various software control programs stored in the memory. The controller 250 controls the overall operation of the display device 200.

[0117] In some embodiments, the controller 250 and the tuner-demodulator 210 may be located in different separate devices, that is, the tuner-demodulator 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.

[0118] In some embodiments, the user may input a user command in a graphical user interface (GUI) displayed on the display 260, and the user input interface receives the user input command through the graphical user interface (GUI). Alternatively, the user may input a user command by inputting a specific sound or gesture, and the user input interface receives the user input command by recognizing the sound or gesture through a sensor.

[0119] In some embodiments, the display 260 includes a display screen component for presenting a picture, and a driving component for driving an image display. The display 260 is used to receive an image signal output from the controller 250 for display. For example, the display 260 can be used to display video content, image content, and components of a menu control interface and a user control UI interface.

[0120] In some embodiments, the "user interface" is a medium interface for interaction and information exchange between an application or operating system and a user, which realizes the conversion between the internal form of information and the form acceptable to the user. The commonly used form of user interface is the graphical user interface (GUI), which refers to a user interface related to computer operation displayed in a graphical manner. It can be an interface element such as an icon, window, control, etc. displayed on the display screen of an electronic device, where the control can include icons, buttons, menus, tabs, text boxes, dialog boxes, status bars, navigation bars, widgets, and other visual interface elements.

[0121] In some embodiments, the display 260 may be a liquid crystal display, an OLED display, and a projection display, and may also be a projection device and a projection screen.

[0122] In some embodiments, the audio output device 270 may be a local speaker of the display device 200, or may be an external audio output device of the display device 200. In particular, for the external audio output device of the display device 200, the display device 200 may also be provided with an external audio output terminal, and the audio output device may be connected to the display device 200 through the external audio output terminal to output the sound of the display device 200.

[0123] In some embodiments, the user interface may be used to receive a control signal from the control device 100 (eg, an infrared remote controller, etc.).

[0124] In order to perform user interaction, in some embodiments, the display device 200 may run an operating system. The operating system is a computer program for managing and controlling hardware resources and software resources in the display device 200. The operating system can control the display device to provide a user interface. For example, the operating system can directly control the display device to provide a user interface, or provide a user interface by running an application program. The operating system also allows the user to interact with the display device 200.

[0125] It should be noted that the operating system can be a native operating system based on a specific operating platform, a third-party operating system deeply customized based on a specific operating platform, or an independent operating system specially developed for the display device.

[0126] The operating system can be divided into different modules or layers according to the functions implemented, for example Figure 3 As shown, in some embodiments, the system is divided into four layers, from top to bottom, namely, the application layer (Applications) layer (referred to as "application layer"), the application framework layer (Application Framework) layer (referred to as "framework layer"), the system library layer and the kernel layer.

[0127] In some embodiments, the application layer is used to provide services and interfaces for applications so that the display device 200 can run applications and interact with users based on the applications. At least one application can be run in the application layer, and these applications can be window programs, system settings programs, clock programs, etc. that come with the operating system; they can also be applications developed by third-party developers. In specific implementations, the application packages in the application layer are not limited to the above examples.

[0128] The framework layer provides application programming interfaces (APIs) and programming frameworks for applications. The application framework layer includes some predefined functions. The application framework layer is equivalent to a processing center that determines the actions that applications in the application layer take. Through the API interface, applications can access system resources and obtain system services during execution.

[0129] Figure 3 A schematic diagram of the software configuration of the display device 200 provided in an embodiment of the present application.

[0130] In some embodiments, Figure 3 As shown, the system of the display device 200 may include a kernel, a command parser (shell), a file system, and an application. The kernel, shell, and file system together constitute the basic operating system structure, which allows users to manage files, run programs, and use the system. After power-on, the kernel starts, activates the kernel space, abstracts the hardware, initializes the hardware parameters, etc., runs and maintains the virtual memory, scheduler, signal, and inter-process communication (IPC). After the kernel starts, the shell and user application are loaded. After startup, the application is compiled into machine code to form a process.

[0131] like Figure 3 As shown, the system of the display device 200 is divided into three layers, namely, an application layer, a middleware layer, and a hardware layer from top to bottom. In some embodiments, the system of the display device 200 also includes a UI layer (not shown in the figure), which is located above the application layer and receives data transmission from the application layer to realize the screen presentation of the display 260.

[0132] The application layer mainly includes commonly used applications on TV and application frameworks. Common applications are mainly applications developed based on browsers, such as HTML5 APPs and native APPs.

[0133] The Application Framework is a complete program model that has all the basic functions required by standard application software, such as file access, data exchange, and the user interfaces of these functions (toolbars, status bars, menus, dialog boxes).

[0134] Native apps can support online or offline, message push or local resource access.

[0135] The middleware layer includes various TV protocols, multimedia protocols, system components and other middleware. The middleware can use the basic services (functions) provided by the system software to connect various parts of the application system or different applications on the network, and can achieve the purpose of resource sharing and function sharing.

[0136] The hardware layer mainly includes HAL interface, hardware and driver. Among them, HAL interface is the unified interface for all TV chips to connect, and the specific logic is implemented by each chip. Drivers mainly include: audio driver, display driver, Bluetooth driver, camera driver, WIFI driver, USB driver, HDMI driver, sensor driver (such as fingerprint sensor, temperature sensor, pressure sensor, etc.), and power driver, etc.

[0137] In some embodiments, the display device may further include a media resource recommendation system. Figure 4 A structural diagram of a media resource recommendation system for a display device provided in an embodiment of the present application, such as Figure 4 As shown, the system includes, from top to bottom, a front-end layer 401, a service layer 402, a data layer 403, and a model service layer 404.

[0138] In some embodiments, the front-end layer 401 includes an operation management front-end and a user front-end. The operation management front-end provides a visual interface for operators to manage the recommendation strategy of media asset data, the generation strategy of recommended data, and the review strategy of recommended data. The user front-end is used to display the media asset recommendation results and interact with the user of the display device.

[0139] In some embodiments, the service layer 402 includes a recommendation data review service, a recommendation data generation service, a manual review service, and a media asset recommendation result delivery service. Here, the recommendation data generation service can process business logic related to the recommendation data, such as creation, editing, deletion, and other operations of the recommendation data, and interact with the review data table in the MySQL database to store and obtain the recommended data that has been reviewed and approved. The recommendation data generation service includes a column text generation module, a recommendation text generation module, and a recommendation poster generation module. The recommendation data review service includes a column text review module, a recommendation text review module, and a recommendation poster review module. The manual review service provides a column text manual review module, a recommendation copy manual review module, and a recommendation poster manual review module. The media asset recommendation result delivery service can deliver the media asset recommendation results to the user front-end for display.

[0140] In some embodiments, the data layer 403 may include audit data, policy data, content data, user data, and media asset recommendation result data. Among them, the audit data includes the process log and results of the audit based on the text audit model and the poster audit model and the manual audit. The policy data includes the audit strategy of the operator to configure the text audit model and the poster audit model, and the generation strategy of the configuration text generation model and the poster generation model. The content data includes column attribute data and media asset metadata, etc. Exemplarily, the column attribute data includes the category, country / region, language, classification, supplier and other information of the column, which can be configured by the operator. The media asset metadata can be provided by the supplier and imported into the media asset recommendation system, including title, duration, format, resolution, file size, creation date, description, label, copyright information, language, subtitle, thumbnail, etc. User data includes user basic attributes and user behavior data. User basic attributes include user name, email address, mobile phone number, gender, age, birthday, country / region, city, occupation, education level, marital status, hobbies, registration date, etc. User behavior data includes user behavior data when browsing media assets, such as likes, comments, etc. Media resource recommendation result data, including recommendation text, recommendation poster, column list and media resource data to be recommended.

[0141] In some embodiments, the model service layer 404 may include a media asset recommendation model, a text generation model, a poster generation model, a text review model, and a poster review model. The media asset recommendation model is used to obtain media asset recommendation results based on user data and media asset metadata, the text generation model is used to obtain recommended texts corresponding to media asset data based on user data and media metadata, the poster generation model is used to obtain recommended posters corresponding to media asset data based on user data and media metadata, the text review model is used to review recommended texts, and the poster review model is used to review recommended posters.

[0142] 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.

[0143] At present, with the popularization of the Internet and mobile devices, audio and video services such as video on demand and live broadcast are becoming increasingly popular, greatly enriching people's entertainment life. In order to meet the different viewing needs of users, personalized recommendation systems can provide customized service experience by analyzing user behavior data. However, existing media resource recommendation systems rely on basic collaborative filtering or content-based recommendation methods, which fail to fully consider the individual differences of users and lack personalized experience for each user.

[0144] In addition, existing personalized recommendation systems usually display standard posters and simple text descriptions to users, without recommendation text corresponding to the media data, and cannot explain to users the reasons for recommending the media data. In addition, the media posters in the media recommendation results are usually provided by suppliers, and the media posters viewed by users are the same, without highlighting the key points for users. The unified display format ignores the differences in user needs in different situations, and cannot be dynamically adjusted according to real-time feedback from users, affecting the overall user experience of multimedia resource recommendations.

[0145] In view of the above problems, Figure 5 A flow chart of a display device according to an embodiment of the present application updating media resource recommendation results based on real-time behavior data of a user. Figure 5 As shown, some embodiments of the present application provide a display device 200, which includes: a display and a controller. The controller is coupled to the display and is configured to perform the following program steps:

[0146] S100: Controlling the display to display a first media resource recommendation result on the media resource recommendation interface.

[0147] In some embodiments, when a user turns on a display device, a media asset recommendation system of the display device may generate a first media asset recommendation result based on user data and media asset data in a media asset database, and control the display to display the first media asset recommendation result on a media asset display page.

[0148] In some embodiments, the first media asset recommendation result includes a plurality of first media asset data and first recommendation data corresponding to the first media asset data, and the first recommendation data includes a first recommendation poster and a first recommendation text. Here, the first recommendation poster and the first recommendation text can be generated according to the user data and the media asset data. The first recommendation poster can be used to attract users and increase the click-through rate of users clicking on the first media asset data. The first recommendation text is a text description introducing the first media asset data, which can help users quickly understand the main content of the first media asset data.

[0149] In some embodiments, when the controller controls the display to display the first media asset recommendation result on the media asset recommendation interface, if the user has used the display device, that is, if the controller can obtain the historical data of the user watching the media asset data, the first media asset recommendation result can be generated based on the historical data of the user watching the media asset data and the media asset data. If the user has not used the display device, the controller cannot obtain the historical data of the user, and the first media asset recommendation result can be generated based on the metadata features of the media asset data.

[0150] In some embodiments, Figure 6 A schematic diagram of a process of displaying a first media resource recommendation result on a media resource recommendation interface of a first display device provided in an embodiment of the present application, such as Figure 6As shown, in the case where the user has used the display device, the controller can obtain the historical data of the user's viewing of media and all the media data in the media database. The historical data may include the user ID, the ID of the media that has been viewed, the viewing time, the viewing duration, and the historical behavior data when viewing the media, such as clicks, browsing, etc. The media data may include the media ID, title, description, type (such as movies, TV series, documentaries, etc.), director, etc. Next, the historical user portrait features and historical user behavior features of the historical data are extracted, and the metadata features of the media data are extracted. The historical user portrait features are used to describe the user portrait, and may include the user's age, gender, and region, etc. The historical user behavior features are features related to user behavior, and may include the number of clicks, time spent, frequency of scrolling pages, number of likes or favorites, etc. Afterwards, the extracted user features and metadata features are input into the media recommendation model, and the media recommendation model outputs the recommendation score or probability of each media, and sorts the output results, and selects the top N media with the highest scores as the first media data.

[0151] Further, after determining the first media asset data, extract the first media asset feature of the first media asset data, the first media asset feature being a metadata feature used to characterize the first media asset data. Extract the historical user portrait feature and the historical user behavior feature of the historical data. Then, input the first media asset feature, the historical user portrait feature, and the historical user behavior feature into the text generation model and the poster generation model, respectively, to obtain the first recommended text and the first recommended poster of the first media asset data. Then, use the first recommended text and the first recommended poster corresponding to the first media asset data as the first media asset recommendation result, and display the first media asset recommendation result on the display.

[0152] In view of this, in some embodiments, the controller executing S100 may be configured to: in the presence of historical data of the user watching media, obtain the historical data of the user watching media and a media database, the media database including multiple media data; use a media recommendation model to process the historical data and all media data to obtain multiple first media data to be recommended; obtain the first media feature of the first media data; obtain the historical user portrait feature and the historical user behavior feature of the historical data; use a text generation model to process the first media feature, the historical user portrait feature and the historical user behavior feature to obtain the first recommended text for the first media data; use a poster generation model to process the first media feature, the historical user portrait feature and the user behavior feature to obtain the first recommended poster for the first media data; use all the first media data, the first recommended text corresponding to the first media data and the first recommended poster as the first media recommendation result; control the display to display the first media recommendation result on the media recommendation interface.

[0153] According to the above embodiment, the first media asset data to be recommended is determined by using the media asset recommendation model based on the historical data and the media asset data in the media asset library. Then, the first media asset feature of the first media asset data is extracted and the historical user portrait feature and the historical user behavior feature of the historical data are extracted. The above features are respectively input into the text generation model and the image generation model to obtain the first recommendation data of the first media asset data. In this way, not only can the user's interests and preferences be accurately understood based on the user's historical data, but also an explanatory first recommendation text can be provided for the first media asset data based on the text generation model to help users better understand and select recommended content. The poster generation model is used to generate attractive visual materials for each recommended content, increase the user's willingness to click, and thus improve the user experience.

[0154] In some embodiments, Figure 7 A schematic diagram of a process of displaying a first media resource recommendation result on a media resource recommendation interface of a second display device provided in an embodiment of the present application. Figure 7 As shown, when the user has not used the display device, that is, the controller cannot obtain the historical data of the user watching media, the controller can obtain multiple media data in the media database, extract metadata features of each media data, and input the metadata features into the media recommendation model to obtain the first media recommendation data generated based on the media data.

[0155] Furthermore, after determining the first media asset data, extract the first media asset feature of the first media asset data. Then, input the first media asset feature into the text generation model and the poster generation model respectively to obtain the first recommended text and the first recommended poster of the first media asset data. And all the first media asset data, the first recommended text and the first recommended poster corresponding to the first media asset data are taken as the first media asset recommendation result, and the first media asset recommendation result is displayed on the display.

[0156] For example, taking the movie "Forrest Gump" as the first media asset data, the first media asset feature extracted from "Forrest Gump" is that the movie genre is drama and romance, the director is Robert Zemeckis, the starring actors are Tom Hanks and Robin Wright, the country is the United States, the language is English, and the era background is the American society in the mid-20th century. Inputting the first media asset feature into the text generation model, the first recommended text that can be obtained is: "A precious life journey, an epic legend of the times. Tom Hanks passionately plays Forrest Gump, a small man with low intelligence but a pure heart, and composes his legendary life in the turbulent torrent of the times. Director Zemeckis cleverly incorporates the various changes in American society in the mid-20th century, presenting a magnificent picture of the times. "Forrest Gump" allows us to witness the extraordinary life of ordinary people and understand the kindness and wisdom of human nature." In this way, the first recommended text generated only based on the first media asset feature can summarize the theme and main clues of the movie, such as the legendary life journey of ordinary people, highlight the wonderful interpretation of the leading actor Tom Hanks and the uniqueness of the character setting, mention the director Robert Zemeckis's directorial skills and the social focus of the movie, and echo the era background shown in the movie, the American society in the mid-20th century. At the same time, it uses attractive rhetoric techniques such as "precious life journey" and "epic legend of the times" to increase poetry and appeal. The first recommended text can well highlight the core features of the film, such as the theme, the main creative team, and the background of the times, and improve the relevance of the content. At the same time, it combines a positive, profound and touching emotional tone, has a certain poetic beauty, and can attract potential audiences to be interested in the film.

[0157] In view of this, in some embodiments, the controller executing S100 may be configured to: obtain a media database in the absence of historical data of users watching media; the media database includes multiple media data; use a media recommendation model to process all media data to obtain multiple first media data to be recommended; obtain first media features of the first media data; use a text generation model to generate first recommendation texts corresponding to each first media data according to each first media feature; use an initial poster of the first media data as a first recommendation poster; use all first media data, the first recommendation texts corresponding to the first media data, and the first recommendation poster as first media recommendation results; control the display to display the first media recommendation results on the media recommendation interface.

[0158] According to the above embodiment, in the absence of user historical data, the media asset recommendation model is used to generate first media asset data based on the media asset data in the media asset database, and the first media asset feature of the first media asset data is extracted. Then, the first media asset feature is input into the text generation model and the image generation model respectively to obtain the first recommendation data of the first media asset data. In this way, an explanatory first recommendation text can be provided for the first media asset data based on the text generation model, so as to help users better understand and select the recommended content, increase the user's willingness to click, and thus improve the user experience.

[0159] S200: After the first media resource recommendation result is displayed on the media resource recommendation interface, real-time behavior data of the user within a preset time period is collected.

[0160] In some embodiments, after displaying the first media recommendation result on the media recommendation interface, in order to further optimize the recommendation system and provide a better personalized experience, the display device may collect the user's real-time behavior data over time. The real-time behavior data can help the recommendation system understand the user's immediate preferences and behavior patterns, thereby providing accurate recommendations.

[0161] In some embodiments, the preset time for collecting the user's real-time behavior data can be set according to actual business needs, and can be set to 5 minutes or the time from the current display device being turned on to being turned off, and this application does not limit this. For example, the display device can collect the user's real-time behavior data within 5 minutes of displaying the first media resource recommendation result, or it can collect the user's real-time behavior data from the time the first media resource recommendation result is displayed to the time the display device is turned off.

[0162] In some embodiments, the user's real-time behavior data is all the user's behavior record data, including but not limited to clicking on recommended content, browsing time, scrolling pages, search operations, viewing time, comments, likes, and any other user interaction behavior data related to the first media resource recommendation result.

[0163] In this way, after the user sees the first media resource recommendation result, the controller continuously tracks and records the user's real-time behavior data within the next preset period of time to further analyze the user's preferences and behavior patterns, thereby providing accurate data support when recommending media resource recommendation results to the user.

[0164] S300: Generate real-time recommendation data corresponding to each first media asset data according to the first media asset recommendation result and the real-time behavior data.

[0165] In some embodiments, the controller may generate new recommendation data of the first media asset data, i.e., real-time recommendation data, based on the analysis results of the real-time behavior data. On the one hand, the user's interest score may be determined according to the user's real-time behavior data, and then a real-time recommendation poster that attracts the user may be generated according to the user's interest score. For example, through the analysis of the real-time behavior data, it is concluded that the user is particularly interested in suspense-type content, and the suspenseful features may be highlighted in the real-time recommendation poster. Targeted real-time recommendation posters may also be generated in combination with factors such as the user's geographic location and viewing time. On the other hand, the user's interest score may be determined according to the user's real-time behavior data, and then a real-time recommendation text that attracts the user to watch may be generated. Exemplarily, through the analysis of the real-time behavior data, it is concluded that the user shows a high interest in a certain movie, and the highlights of the movie may be emphasized in the real-time recommendation text. For example, if the user often watches horror movies at night, the features suitable for watching at night may be emphasized in the real-time recommendation text.

[0166] In this way, real-time recommendation data of the first media asset data is generated according to the first media asset recommendation result and the real-time behavior data, which can reflect the user's immediate interests and behavior patterns, thereby providing a personalized and accurate recommendation experience.

[0167] In some embodiments, Figure 8 A flow chart of a display device according to an embodiment of the present application generating real-time recommendation data based on a first media resource recommendation result and real-time behavior data. Figure 8 As shown, a first media resource recommendation result is determined according to a media resource recommendation system, and real-time behavior data of a user within a preset time period is received, metadata features of the first media resource data in the first media resource recommendation result are extracted, and user behavior features in the real-time behavior data are extracted, the metadata features and the user behavior features are applied to a preset recommendation prompt template to obtain a poster recommendation prompt and a text recommendation prompt, the poster recommendation prompt and the text recommendation prompt are respectively input into a poster generation model and a text generation model to obtain a real-time recommendation poster and a real-time recommendation text.

[0168] In some embodiments, the controller executing S300 may be configured to perform the following steps:

[0169] S301: Determine, according to the first media asset recommendation result and the real-time behavior data, a poster recommendation prompt and a text recommendation prompt corresponding to the first media asset data.

[0170] In some embodiments, the recommendation prompt corresponding to the first media asset data can be determined based on the metadata features of the first media asset data in the first media asset recommendation result and the user behavior features in the real-time behavior data. The recommendation prompt may include a poster recommendation prompt and a text recommendation prompt. The poster recommendation prompt is input into the poster generation model to generate the prompt for the first recommendation poster; the text recommendation prompt is input into the text generation model to generate the prompt for the first recommendation text.

[0171] In some embodiments, user behavior features for characterizing user interests and behavior patterns are extracted from real-time behavior data. The user behavior features may specifically include the number of clicks on each media asset by the user, the time the user spends on each media asset, the frequency of user scrolling pages, the number of likes or favorites for each media asset by the user, and keywords in the user's comments on the media asset.

[0172] Furthermore, the metadata features extracted from the first media asset data can characterize the attributes of the first media asset data, and can be used to analyze and classify the first media asset data. Exemplarily, the metadata features include, but are not limited to, type, name, style, director, actor, rating, etc. Among them, the type may include movies, TV series, documentaries, etc., the style may include comedy, action, romance, science fiction, etc., and the rating is a user rating or a professional rating. It can be understood that all features used to characterize the attributes of the first media asset data are metadata features, and this application does not limit this.

[0173] In some embodiments, in order to more accurately generate recommendation posters and recommendation texts that meet user preferences, user behavior characteristics and metadata characteristics of media assets may be substituted into a preset prompt template. Fig. 9 A schematic diagram of a process for determining a preset prompt template provided in an embodiment of the present application, such as Fig. 9 As shown, the step of determining a preset prompt template may include:

[0174] S901: Obtain sample user data and sample media asset data.

[0175] Here, sample user data and sample media data are obtained as training data to ensure that the data covers different types of users and media content, so as to improve the accuracy of subsequent analysis and modeling.

[0176] S902: Extract sample user portrait features and sample user behavior features from sample user data.

[0177] In some embodiments, in order to analyze the interests and behavior patterns of users, sample user portrait features and sample user behavior features of sample user data may be extracted. The sample user portrait features may include basic information such as age, gender, geographic location, occupation, etc., and the sample user behavior features may include the user's click rate, viewing time, collection and sharing behavior, etc.

[0178] S903: Extracting sample metadata features of sample media asset data.

[0179] In some embodiments, in order to improve the accuracy of recommending media data to users, sample metadata features of sample media data may be extracted to accurately understand the content of the media, wherein the sample metadata features may include the title, tag, category, duration, resolution, etc. of the video.

[0180] S904: Determine a first prompt based on the sample user portrait features, the sample user behavior features, and the sample metadata features.

[0181] Here, a preliminary first prompt is generated by combining sample user portrait features, sample user behavior features, and sample metadata features using natural language processing technology, wherein the first prompt can be used to guide the generation of recommendation data.

[0182] S905: Input the first prompt word into the text generation model and the poster generation model to obtain a sample recommendation text and a sample recommendation poster.

[0183] S906: Based on preset evaluation indicators, the generation effect of the sample recommendation text and the sample recommendation poster is evaluated.

[0184] Here, a combination of automated evaluation (such as natural language processing model scoring) and manual evaluation can be used to evaluate the generation effect of sample recommendation texts and sample recommendation posters based on preset evaluation indicators. The preset evaluation indicators are used to evaluate the content quality of sample recommendation texts and sample recommendation posters, which may include the relevance, quality, diversity, novelty, etc. of the content.

[0185] S907: Adjust the first prompt according to the generated effect.

[0186] Here, the first prompt can be optimized according to the generated effect to improve the quality of the recommended data. For example, the keywords, sentence structure, etc. of the first prompt can be adjusted according to the feedback of the evaluation index, and multiple adjustments and evaluations can be performed until the recommended data achieves a satisfactory effect.

[0187] S908: Determine a preset prompt template based on the adjusted first prompt.

[0188] Here, the optimized first prompt is used as a template to ensure that when the first prompt is input into the text generation model and the poster generation model, high-quality recommendation text and recommendation data can be obtained. At the same time, the generation process and optimization strategy of the preset prompt template are recorded to facilitate subsequent maintenance and improvement. Among them, the preset prompt template may include a poster recommendation prompt template and a text recommendation prompt template.

[0189] According to the above embodiment, a preset prompt template can be generated so that the recommendation data generated based on the prompt can accurately meet the needs and expectations of the user.

[0190] In some embodiments, user behavior characteristics and metadata characteristics of media assets can be substituted into a preset prompt template to generate personalized poster recommendation prompts and text recommendation prompts. Exemplarily, the poster recommendation prompt template can be "Create a poster about [name]. Please combine [style] style, [language] language and user viewing preferences [user preferences] to generate the first recommended poster for [name]". Taking the movie "Titanic" as an example, according to the user behavior characteristics and metadata characteristics substituted into the poster recommendation prompt template, the generated poster recommendation prompt can be: "I want to recommend the movie "Titanic" to users. The main movie type labels of this movie are: love, romance, disaster; the main movie type labels that users like to watch are: disaster; users mainly like to watch English movies. Please combine the characteristics of the movie and the user's preferences to generate a poster to make users have a greater desire to watch this movie."

[0191] After generating the poster recommendation prompt, the generated text recommendation prompt can be substituted into the text recommendation prompt template according to the user behavior characteristics and metadata characteristics. Exemplarily, the text recommendation prompt template can be: "Create a description text about [name]. The description text can include an introduction to [name] [introduction]. The description text content needs to be particularly attractive to users who are interested in [hobbies] and like [genre] types." Taking the movie "Interstellar" as an example, according to the user behavior characteristics and metadata characteristics, the generated text recommendation prompt can be: "I want to recommend the movie "Interstellar" to the user. The user often watches [science fiction, space exploration] type movies, likes the acting skills of actor [Matthew McConaughey], and is interested in [artificial intelligence, singularity theory]. Please use the characteristics of the movie and the user's preferences to generate a recommendation text to make the user have a greater desire to watch this movie."

[0192] In view of this, in some embodiments, the controller executing S301 can be configured to: extract user behavior characteristics of real-time behavior data; extract metadata characteristics of each first media asset data, the metadata characteristics are used to characterize the attributes of the first media asset data; based on the user behavior characteristics, metadata characteristics and preset prompt templates, determine poster recommendation prompts and text recommendation prompts.

[0193] According to the above embodiment, user behavior features can be extracted from real-time behavior data, and combined with metadata features of the first media asset data to generate poster recommendation prompts and text recommendation prompts. In this way, the user's immediate interests and behavior patterns can be reflected, providing a more personalized and accurate recommendation experience, thereby improving the recommendation effect and user satisfaction of the media asset recommendation system.

[0194] S302: Process the text recommendation prompt according to the text generation model to obtain the real-time recommended text corresponding to the first media asset data.

[0195] In some embodiments, after obtaining the text recommendation prompt, the text recommendation prompt can be input into the text generation model to obtain real-time recommended text. For example, taking the movie "Interstellar" as an example, the text recommendation prompt corresponding to "Interstellar" is input into the text generation model to obtain real-time recommended text: "Are you interested in artificial intelligence and singularity theory? Nolan's sci-fi masterpiece "Interstellar" just explores these cutting-edge concepts. Matthew McConaughey contributed impressive acting skills, leaving eternal questions for human interstellar exploration. Come and relive this sci-fi masterpiece that you were once crazy about!" Here, the text generation model can be obtained based on deep learning or natural language processing technology, etc., and this application does not limit this.

[0196] S303: Process the poster recommendation prompt according to the poster generation model to obtain a real-time recommended poster corresponding to the first media asset data.

[0197] In some embodiments, after obtaining the poster recommendation prompt, the poster recommendation prompt can be input into the poster generation model to obtain a real-time recommended poster. Here, the poster generation model can be based on a model of Generative Adversarial Networks (GANs) or a model of Variational Autoencoders (VAEs), or can be obtained based on other neural network training, and this application does not limit this.

[0198] According to the above embodiment, the poster recommendation prompt and the text recommendation prompt can be determined according to the first media resource recommendation result and the real-time behavior data. Using the poster generation model to process the poster recommendation prompt and generate personalized and attractive real-time recommendation posters can improve the quality of the recommendation posters and make them more in line with the user's interests and preferences. Using the text generation model to process the text recommendation prompt and generate natural and rich real-time recommendation text can improve the quality of the recommendation text and make it more attractive to users. In this way, improving the poster quality and text recommendation quality can improve the recommendation effect of the media resource recommendation system and improve the user experience.

[0199] S400: In response to the switching instruction, updating the first media asset recommendation result to the second media asset recommendation result.

[0200] In some embodiments, the controller may receive a switching instruction input by a user for updating the media asset recommendation result, and the switching instruction may be generated when the user clicks a control for updating the recommendation result in the media asset display page. When the controller receives the switching instruction, the first media asset recommendation result may be updated to a second media asset recommendation result. Here, the second media asset recommendation result may be generated based on the historical data of the user watching the media asset, and the second media asset recommendation result includes second recommendation data corresponding to multiple second media asset data, and the second recommendation data includes a second recommendation poster and a second recommendation text.

[0201] In some embodiments, after the first media asset recommendation result is updated to the second media asset recommendation result based on the switching instruction, the user's real-time behavior data can continue to be collected and used to further generate real-time recommendation data of the second media asset data based on the user's real-time behavior data to optimize the media asset recommendation system.

[0202] S500: When the second media asset data includes third media asset data, taking the real-time recommended data corresponding to the third media asset data as the second recommended data corresponding to the third media asset data.

[0203] In some embodiments, the third media asset data is the same second media asset data as the first media asset data. When the second media asset data includes the same media asset data as the first media asset data, that is, the third media asset data, the real-time recommendation data corresponding to the third media asset data is used as the new second recommendation data.

[0204] That is to say, after real-time recommendation data of the first media asset data is generated based on the user's real-time data, if a certain media asset data in the first media asset recommendation result appears again in the second media asset recommendation result, then the real-time recommendation data of the media asset data is used as the second recommendation data in the second media asset recommendation result. Exemplarily, the first media asset result displayed on the media asset recommendation interface by the display includes the first recommendation poster and the first recommendation text corresponding to the first media asset data "Movie 1", and also includes the first recommendation poster and the first recommendation text corresponding to "Movie 2". Afterwards, within a preset time period, the display device collects the user's real-time behavior data, and generates real-time recommendation data for the movies "Movie 1" and "Movie 2" based on the real-time behavior data. When the second media asset recommendation result is updated based on the switching instruction, if the second media asset data of the second media asset recommendation result contains "Movie 1", the real-time recommendation data corresponding to "Movie 1" is used as the second recommendation data in the second media asset recommendation result.

[0205] In some embodiments, at least two recommendation data fields may be stored in the media database for each media asset data. The first recommendation data field may be used to store recommendation data generated based on user historical data, and the second recommendation data field may be used to store recommendation data generated based on user real-time behavior data.

[0206] When the controller generates the first media asset recommendation result, the first recommended data in the first media asset recommendation result can be stored in the first recommended data field corresponding to the first media asset data. When the controller generates the real-time recommended data of the first media asset data according to the real-time behavior data, the real-time recommended data is saved in the second recommended data field corresponding to the first media asset data.

[0207] After the controller updates the first media asset recommendation result to the second media asset recommendation result based on the switching instruction, it can determine whether the second recommended data field corresponding to the second media asset data in the second media asset recommendation result includes real-time recommended data. If the second recommended data field includes real-time recommended data, the real-time recommended data is used as the second recommended data in the second media asset recommendation result.

[0208] In this way, it can be ensured that when the same media asset data appears in multiple recommendation results, it can be displayed using the recommendation data generated based on real-time behavior data, thereby providing an accurate and personalized recommendation experience.

[0209] S600: Control the display to display the second media resource recommendation result on the media resource recommendation interface.

[0210] In some embodiments, after confirming the second recommendation data of the second media asset data in the second media asset recommendation result, the controller controls the display to implement the second media asset recommendation result on the media asset recommendation interface. The media asset recommendation result can be displayed in a variety of forms on the media asset recommendation interface to meet different design requirements and user experience.

[0211] In some embodiments, the display format may include a list layout, which is suitable for displaying a large amount of recommended content, and the user can scroll to view more recommendations. When the display format is a list layout, the controller may be configured to execute S600 to: display at least one second recommended poster in the first display area of ​​the media resource recommendation interface; and display at least one second recommended text corresponding to the second recommended poster in the second display area of ​​the media resource recommendation interface.

[0212] In some embodiments, Fig.10 A schematic diagram of a first display provided in an embodiment of the present application showing a second media resource recommendation result on a media resource recommendation interface. Fig.10 As shown, multiple first display areas and multiple second display areas can be set on the media resource recommendation interface, the first display area is used to display the second recommendation poster, and the second display area is used to display the second recommendation text. The second display area is located below the first display area, and the second recommendation text in the second display area corresponds one-to-one to the second recommendation poster in the first display area. This layout method can effectively utilize the screen space while providing users with clear information display. In actual applications, the position, size, and other style attributes of the display area can be adjusted as needed to achieve the best visual effect and user experience.

[0213] When the display format is a list layout, the controller executing S600 can also be configured to: display at least one second recommended poster in the third display area of ​​the media recommendation interface; when the second recommended poster is selected as the focus of the media recommendation interface, display the second recommended text corresponding to the selected second recommended poster in the fourth display area of ​​the media recommendation interface.

[0214] In some embodiments, Fig.11 A schematic diagram of a second display provided in an embodiment of the present application showing a second media resource recommendation result on a media resource recommendation interface. Fig.11 As shown, the third display area is used to display at least one second recommended poster, and the fourth display area is used to display the second recommended text corresponding to the selected second recommended poster. In this way, the third display area can be set on the media resource recommendation interface to display the second recommended poster, and when the user focuses on a second recommended poster, the second recommended text corresponding to the selected second recommended poster is displayed in the fourth display area. This layout method can effectively utilize the screen space while providing users with clear information display. In actual applications, the position, size and other style attributes of the display area can be adjusted as needed to achieve the best visual effect and user experience. In actual applications, the layout and interaction details can be further adjusted and optimized as needed.

[0215] When the display format is a list layout, the controller executing S600 can also be configured to: display at least one second recommended poster in the fifth display area of ​​the media recommendation interface; when the second recommended poster is selected as the focus of the media recommendation interface, display a first pop-up window according to the position of the selected second recommended poster; the first pop-up window includes the second recommended text corresponding to the selected second recommended poster.

[0216] In some embodiments, Fig.12 A schematic diagram of a third display provided in an embodiment of the present application showing a second media resource recommendation result on a media resource recommendation interface. Fig.12 As shown, the fifth display area is used to display at least one second recommended poster, and the first pop-up window is used to display the second recommended text corresponding to the selected second recommended poster. In this way, the fifth display area can be set on the media resource recommendation interface to display the second recommended poster, and when the user focuses on a second recommended poster, the first pop-up window is displayed according to the position of the selected second recommended poster, and the pop-up window contains the third recommended text corresponding to the selected second recommended poster. Such a layout can increase the user's attention to the recommended content and enhance the user's interactive experience with the recommended content.

[0217] According to the above embodiment, by displaying the first media asset recommendation result on the media asset recommendation interface, after displaying the first media asset recommendation result, the user's real-time behavior data is collected within a preset time. According to the collected first media asset recommendation result and real-time behavior data, the real-time recommendation data corresponding to each first media asset data is generated. When the user issues a switching instruction, the first media asset recommendation result is updated to the second media asset recommendation result, and the second media asset recommendation result includes multiple second media asset data and their corresponding second recommendation data. If the second media asset data contains the same media asset data as the first media asset data, that is, the third media asset data, the real-time recommendation data corresponding to the third media asset data is used as the second recommendation data. Finally, the display is controlled to display the updated second media asset recommendation result on the media asset recommendation interface. This process collects the user's real-time behavior data, generates real-time recommendation data based on the real-time behavior data, and displays the real-time recommendation data when the media asset result is updated. It can dynamically adjust the recommendation data in the media asset recommendation result according to the real-time behavior data, thereby improving the user's viewing experience of the media asset recommendation result.

[0218] In some embodiments, Fig.13 A flow chart of updating media resource recommendation results according to the real-time behavior data of the user provided in the embodiment of the present application. Fig.13 As shown, the controller controls the display to display the first media resource recommendation result on the media resource recommendation interface. The specific implementation of this process can refer to the relevant description of S100 in the aforementioned embodiment, which will not be repeated here.

[0219] Collect the user's real-time behavior data within a preset time period, and send the real-time behavior data and the first media asset data in the first media asset result to the text generation model and the poster generation model. The text generation model extracts the metadata features of the first media asset data, and extracts the user behavior features of the real-time behavior data, generates real-time recommendation text based on the metadata features and the user behavior features, and sends the real-time recommendation text to the media asset recommendation model. The poster generation model extracts the metadata features of the first media asset data, and extracts the user behavior features of the real-time behavior data, generates a real-time recommendation poster based on the metadata features and the user behavior features, and sends the real-time recommendation poster to the media asset recommendation model. The specific implementation of this process can refer to the relevant description of S300 in the aforementioned embodiment, which will not be repeated here.

[0220] When the controller receives a switching instruction from the user to update the media asset recommendation result, the controller controls the media asset recommendation model to update the media asset recommendation result and obtain the second media asset data. The media asset recommendation model sends the second media asset data to the text generation model and the poster generation model respectively to generate the corresponding second recommended text and second recommended poster. The specific implementation of this process can refer to the relevant description of S400 in the aforementioned embodiment, which will not be repeated here.

[0221] When the second media asset data contains the same media asset data as the first media asset data, the real-time recommendation text and the real-time recommendation poster corresponding to the media asset data are used as the second recommendation text and the second recommendation data for display. The specific implementation of this process can refer to the relevant description of S500 in the aforementioned embodiment, which will not be repeated here. The controller controls the display to display the second media asset recommendation result on the media asset recommendation interface. The specific implementation of this process can refer to the relevant description of S600 in the aforementioned embodiment, which will not be repeated here.

[0222] In some embodiments, Fig.14 A flow chart of communicating with a server to update media resource recommendation results based on real-time user behavior data provided by an embodiment of the present application. Fig.14 As shown, the present application provides a display device 200, including: a display 260; a communicator, configured to communicate with a server; a controller 250, configured to:

[0223] Controlling the display to display a first media asset recommendation result on the media asset recommendation interface, wherein the first media asset recommendation result includes first recommended data corresponding to the first media asset data, and the first recommended data includes a first recommended poster and a first recommended text;

[0224] After the first media resource recommendation result is displayed on the media resource recommendation interface, real-time behavior data of the user within a preset time period is collected;

[0225] Controlling the communicator to send the real-time behavior data to the server, so that the server obtains the real-time behavior data corresponding to the first media asset data according to the first media asset recommendation data and the real-time behavior data; the real-time recommendation data includes a real-time recommendation poster and a real-time recommendation text;

[0226] receiving a switching instruction, and controlling the communicator to send the switching instruction to the server, so that the server updates the first media asset recommendation result to a second media asset recommendation result according to the switching instruction; the second media asset recommendation result includes second recommendation data corresponding to a plurality of second media asset data, and the second recommendation data includes a second recommendation poster and a second recommendation text;

[0227] Controlling the communicator to receive a second media resource recommendation result;

[0228] The display is controlled to display the second media resource recommendation result on the media resource recommendation interface.

[0229] In some embodiments, the display device 200 may be a smart TV with high computing power, and may obtain the user's real-time behavior data through its own computing chip to update the media resource recommendation results. However, in some application scenarios, the display device 200 may be a low-computing device such as an advertising machine, and the low-computing terminal device generates a multimedia resource recommendation list slowly or cannot carry a computing model.

[0230] Based on the above problems, in some embodiments, the display device 200 can also interact with the server in real time to update the media asset recommendation results through the server, receive the media asset recommendation results sent by the server, and then display the updated media asset recommendation results through the display 260 connected to the display device 200. The server can be a server arranged in the cloud, a server arranged in the local network, or a server searched based on edge computing. The method of communicating with the server to obtain the multimedia resource recommendation list alleviates the problem that the display device 200 cannot update the media asset recommendation results in time according to the user's real-time behavior data due to insufficient computing power.

[0231] Based on this, in some embodiments, the present application further provides a server, including: a communicator, configured to communicate with a display device; a processor, coupled to the communicator, and configured to:

[0232] Controlling the communicator to receive the real-time behavior data from the display device, and generating real-time recommendation data corresponding to each first media asset data according to the first media asset recommendation result and the real-time behavior data; the real-time recommendation data includes a real-time recommendation poster and a real-time recommendation text;

[0233] Controlling the communicator to receive a switching instruction from the display device, and updating the first media asset recommendation result to a second media asset recommendation result in response to the switching instruction; the second media asset recommendation result includes second recommendation data corresponding to a plurality of second media asset data, and the second recommendation data includes a second recommendation poster and a second recommendation text;

[0234] When the second media asset data includes the third media asset data, the real-time recommended data corresponding to the third media asset data is used as the second recommended data corresponding to the third media asset data; the third media asset data is the same second media asset data as the first media asset data;

[0235] The communicator is controlled to send the second media resource recommendation result to the display device, so that the display of the display device displays the second media resource recommendation result on the media resource recommendation interface.

[0236] In some embodiments, the server may receive the real-time behavior data forwarded by the display device 200, and generate real-time recommendation data based on the real-time behavior data and the first media asset recommendation result, and upon receiving the switching instruction, update the first media asset recommendation result to the second media asset recommendation result, and when the second media asset data includes the third media asset data, use the real-time recommendation data corresponding to the third media asset data as the second recommendation data corresponding to the third media asset data, and send the second media asset recommendation result to the display device 200, so that the display device 200 displays the second media asset recommendation result for the user to select. This alleviates the problem that it is difficult for the low-computing-power display device 200 to generate the second media asset recommendation result.

[0237] In some embodiments, the present application further provides a media resource recommendation method, which is applied to a display device with high computing power, including:

[0238] Controlling the display to display a first media asset recommendation result on the media asset recommendation interface, wherein the first media asset recommendation result includes first recommended data corresponding to the first media asset data, and the first recommended data includes a first recommended poster and a first recommended text;

[0239] After the first media resource recommendation result is displayed on the media resource recommendation interface, real-time behavior data of the user within a preset time period is collected;

[0240] Generate real-time recommendation data corresponding to each first media asset data according to the first media asset recommendation result and the real-time behavior data; the real-time recommendation data includes a real-time recommendation poster and a real-time recommendation text;

[0241] In response to the switching instruction, the first media asset recommendation result is updated to a second media asset recommendation result; the second media asset recommendation result includes second recommendation data corresponding to a plurality of second media asset data, and the second recommendation data includes a second recommendation poster and a second recommendation text;

[0242] When the second media asset data includes the third media asset data, the real-time recommended data corresponding to the third media asset data is used as the second recommended data corresponding to the third media asset data; the third media asset data is the same second media asset data as the first media asset data;

[0243] The display is controlled to display the second media resource recommendation result on the media resource recommendation interface.

[0244] The method is applied to a display device 200 equipped with a computing chip with relatively high computing power, such as a display device 200 such as a smart TV and a computer.

[0245] It is understandable that in some embodiments, a media asset recommendation method for a display device with low computing power is also provided. The controller 250 of the display device 200 forwards the real-time behavior data to the server, and the server performs the process of generating real-time recommendation data and updating the media asset recommendation result, and sends the generated second media asset recommendation result to the display device 200. The display device 200 displays the second media asset recommendation result through the display 260.

[0246] It can be seen from the above technical content that the present application provides a display device, a server and a media asset recommendation method. The method collects the user's real-time behavior data within a preset time period after displaying the first media asset recommendation result on the media asset recommendation interface. Based on the real-time behavior data, real-time recommendation data corresponding to each first media asset data is generated. When the user issues a switching instruction, the first media asset recommendation result is updated to the second media asset recommendation result. If the second media asset data contains third media asset data that is the same as the first media asset data, the real-time recommendation data corresponding to the third media asset data is used as the second recommendation data, and the updated second media asset recommendation result is displayed on the media asset recommendation interface. This process collects the user's real-time behavior data, generates real-time recommendation data based on the real-time behavior data, and displays the real-time recommendation data when the media asset results are updated. It can dynamically adjust the recommendation data in the media asset recommendation results according to the real-time behavior data to improve the user experience.

[0247] Similar parts between the embodiments provided in this application can be referenced to each other. The specific implementation methods provided above are only a few examples under the general concept of this application and do not constitute a limitation on the protection scope of this application. For those skilled in the art, any other implementation methods expanded based on the scheme of this application without creative work belong to the protection scope of this application.

Claims

1. A display device, characterized in that: include: monitor; A controller is coupled to the display and is configured to: Controlling the display to display a first media asset recommendation result on a media asset recommendation interface, wherein the first media asset recommendation result includes first recommendation data corresponding to the first media asset data, and the first recommendation data includes a first recommendation poster and a first recommendation text; After the first media resource recommendation result is displayed on the media resource recommendation interface, real-time behavior data of the user within a preset time period is collected; Generating real-time recommendation data corresponding to each of the first media asset data according to the first media asset recommendation results and the real-time behavior data; The real-time recommendation data includes real-time recommendation posters and real-time recommendation texts; In response to the switching instruction, updating the first media resource recommendation result to a second media resource recommendation result; The second media asset recommendation result includes second recommendation data corresponding to a plurality of second media asset data, and the second recommendation data includes a second recommendation poster and a second recommendation text; When the second media asset data includes third media asset data, using the real-time recommended data corresponding to the third media asset data as the second recommended data corresponding to the third media asset data; The third media asset data is the same second media asset data as the first media asset data; The display is controlled to display the second media resource recommendation result on the media resource recommendation interface.

2. The display device according to claim 1, characterized in that The controller generates real-time recommendation data corresponding to each of the first media asset data according to the first media asset recommendation result and the real-time behavior data, and is specifically configured as follows: Determine, according to the first media asset recommendation result and the real-time behavior data, a poster recommendation prompt and a text recommendation prompt corresponding to the first media asset data; Processing the text recommendation prompt according to a text generation model to obtain the real-time recommended text corresponding to the first media asset data; The poster recommendation prompt is processed according to the poster generation model to obtain the real-time recommendation poster corresponding to the first media asset data.

3. The display device according to claim 2, characterized in that The controller determines the poster recommendation prompt and the text recommendation prompt corresponding to the first media resource data according to the first media resource recommendation result and the real-time behavior data, and is specifically configured as follows: Extracting user behavior features of the real-time behavior data; Extracting metadata features of each of the first media asset data, where the metadata features are used to characterize attributes of the first media asset data; The poster recommendation prompt and the text recommendation prompt are determined based on the user behavior characteristics, the metadata characteristics and a preset prompt template.

4. The display device according to claim 1, characterized in that The controller controls the display to display the second media resource recommendation result on the media resource recommendation interface, and is specifically configured as follows: Displaying at least one of the second recommended posters in the first display area of ​​the media resource recommendation interface; At least one second recommendation text corresponding to the second recommendation poster is displayed in the second display area of ​​the media resource recommendation interface.

5. The display device according to claim 1, characterized in that The controller controls the display to display the second media resource recommendation result on the media resource recommendation interface, and is specifically configured as follows: Displaying at least one of the second recommended posters in a third display area of ​​the media resource recommendation interface; When the second recommendation poster is selected in focus on the media resource recommendation interface, the second recommendation text corresponding to the selected second recommendation poster is displayed in the fourth display area of ​​the media resource recommendation interface.

6. The display device according to claim 1, characterized in that The controller controls the display to display the second media resource recommendation result on the media resource recommendation interface, and is specifically configured as follows: Displaying at least one of the second recommended posters in a fifth display area of ​​the media resource recommendation interface; When the second recommendation poster is selected as the focus of the media resource recommendation interface, a first pop-up window is displayed according to the position of the selected second recommendation poster; the first pop-up window includes the second recommendation text corresponding to the selected second recommendation poster.

7. The display device according to claim 1, characterized in that The controller controls the display to display the first media resource recommendation result on the media resource recommendation interface, and is specifically configured as follows: In the case where there is historical data of the user watching media assets, acquiring the historical data of the user watching media assets and a media asset database, wherein the media asset database includes a plurality of media asset data; Using a media asset recommendation model, the historical data and all the media asset data are processed to obtain a plurality of first media asset data to be recommended; Acquire a first media asset feature of the first media asset data; Obtain historical user portrait features and historical user behavior features of the historical data; Using a text generation model, the first media asset feature, the historical user portrait feature, and the historical user behavior feature are processed to obtain the first recommended text of the first media asset data; Using a poster generation model, the first media asset feature, the historical user portrait feature, and the user behavior feature are processed to obtain the first recommended poster for the first media asset data; taking all the first media asset data, the first recommended text corresponding to the first media asset data, and the first recommended poster as the first media asset recommendation result; The display is controlled to display the first media resource recommendation result on the media resource recommendation interface.

8. The display device according to claim 7, characterized in that The controller controls the display to display the first media resource recommendation result on the media resource recommendation interface, and is specifically configured as follows: In the absence of historical data of media resources watched by the user, obtaining a media resource database; the media resource database includes a plurality of media resource data; Using a media asset recommendation model, processing all the media asset data to obtain a plurality of first media asset data to be recommended; Acquire a first media asset feature of the first media asset data; Generate, by using a text generation model, first recommended texts corresponding to each of the first media asset data according to each of the first media asset features; Using the initial poster of the first media asset data as the first recommended poster; taking all the first media asset data, the first recommended text corresponding to the first media asset data, and the first recommended poster as the first media asset recommendation result; The display is controlled to display the first media resource recommendation result on the media resource recommendation interface.

9. A display device, characterized in that: include: monitor; A communicator configured to communicate with the server; A controller is coupled to the display and the communicator and is configured to: Controlling the display to display a first media asset recommendation result on a media asset recommendation interface, wherein the first media asset recommendation result includes first recommendation data corresponding to the first media asset data, and the first recommendation data includes a first recommendation poster and a first recommendation text; After the first media resource recommendation result is displayed on the media resource recommendation interface, real-time behavior data of the user within a preset time period is collected; Controlling the communicator to send real-time behavior data to a server, so that the server obtains the real-time behavior data corresponding to the first media asset data according to the first media asset recommendation data and the real-time behavior data; the real-time recommendation data includes a real-time recommendation poster and a real-time recommendation text; receiving a switching instruction, and controlling the communicator to send the switching instruction to the server, so that the server updates the first media resource recommendation result to the second media resource recommendation result according to the switching instruction; The second media asset recommendation result includes second recommendation data corresponding to a plurality of second media asset data, and the second recommendation data includes a second recommendation poster and a second recommendation text; Controlling the communicator to receive the second media resource recommendation result; The display is controlled to display the second media resource recommendation result on the media resource recommendation interface.

10. A server, characterized in that: include: A communicator configured to be communicatively connected with a display device; A processor is coupled to the communicator and is configured to: Controlling the communicator to receive the real-time behavior data from the display device, and generating real-time recommendation data corresponding to each of the first media asset data according to the first media asset recommendation result and the real-time behavior data; The real-time recommendation data includes real-time recommendation posters and real-time recommendation texts; Controlling the communicator to receive a switching instruction from the display device, and updating the first media asset recommendation result to a second media asset recommendation result in response to the switching instruction; The second media asset recommendation result includes second recommendation data corresponding to a plurality of second media asset data, and the second recommendation data includes a second recommendation poster and a second recommendation text; When the second media asset data includes third media asset data, using the real-time recommended data corresponding to the third media asset data as the second recommended data corresponding to the third media asset data; The third media asset data is the same second media asset data as the first media asset data; The communicator is controlled to send the second media resource recommendation result to the display device, so that the display of the display device displays the second media resource recommendation result on the media resource recommendation interface.

11. A media resource recommendation method, characterized in that: The media resource recommendation method is applied to a display device, wherein the display device includes a display and a controller, and is characterized in that it includes: Controlling the display to display a first media asset recommendation result on a media asset recommendation interface, wherein the first media asset recommendation result includes first recommendation data corresponding to the first media asset data, and the first recommendation data includes a first recommendation poster and a first recommendation text; After the first media resource recommendation result is displayed on the media resource recommendation interface, real-time behavior data of the user within a preset time period is collected; Generate real-time recommendation data corresponding to each of the first media asset data according to the first media asset recommendation results and the real-time behavior data; the real-time recommendation data includes a real-time recommendation poster and a real-time recommendation text; In response to the switching instruction, the first media asset recommendation result is updated to a second media asset recommendation result; the second media asset recommendation result includes second recommendation data corresponding to a plurality of second media asset data, and the second recommendation data includes a second recommendation poster and a second recommendation text; When the second media asset data includes third media asset data, the real-time recommended data corresponding to the third media asset data is used as the second recommended data corresponding to the third media asset data; the third media asset data is the same second media asset data as the first media asset data; The display is controlled to display the second media resource recommendation result on the media resource recommendation interface.

Images