Display device, server and multimedia resource recommendation method

Abstract

The invention provides a display device, a server and a multimedia resource recommendation method. The method comprises the steps that user data and a multimedia resource candidate set are acquired, and the multimedia resource candidate set comprises a plurality of first resource posters; performing quality scoring on the first resource poster based on the user data to obtain a poster quality score of the first resource poster; based on the user data and the poster quality score, determining a multimedia resource recommendation result in the multimedia resource candidate set; the multimedia resource recommendation result comprises a plurality of second resource posters. According to the process, the poster quality score of the user for the first resource poster is determined through the user data, the multimedia resource recommendation result conforming to the user preference is obtained based on the poster quality score and the user data, and the watching experience of the user is improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a display device, a server, and a multimedia 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 user personalized recommendation systems. For example, TV terminals can be equipped with personalized recommendation systems to recommend multimedia resources to users. Existing personalized recommendation systems can collect user behavior data and basic information about users and recommend multimedia resource data based on the content of multimedia resources, such as subject matter, genre, director, actor and other information.

[0004] However, the recommendation method adopted by the above-mentioned personalized recommendation system can provide personalized suggestions based on the content of multimedia resources, but ignores personalized recommendations based on the visual characteristics of multimedia resources, such as image content, color and other elements, resulting in the recommendation results being unable to meet the user's visual preferences and affecting the user's overall experience of multimedia resource recommendations. Summary of the invention

[0005] The present application provides a display device, server and multimedia resource recommendation method, which scores and recommends resource posters based on user data, thereby making the recommendation results more in line with user needs, improving the visual presentation quality of resource posters, and thus improving the user's visual experience and better meeting user needs.

[0006] In a first aspect, the present application provides a display device, comprising: a display; and a controller coupled to the display and configured to:

[0007] Acquire user data and a multimedia resource candidate set, wherein the multimedia resource candidate set includes a plurality of first resource posters;

[0008] Performing a quality score on the first resource poster based on the user data to obtain a poster quality score of the first resource poster;

[0009] Determine a multimedia resource recommendation result in the multimedia resource candidate set based on the user data and the poster quality score; the multimedia resource recommendation result includes a plurality of second resource posters;

[0010] The display is controlled to display the multimedia resource recommendation result.

[0011] In some feasible embodiments, the controller performs quality scoring on the first resource poster based on the user data to obtain a poster quality score of the first resource poster, and is configured as follows:

[0012] Extracting a first user interest feature of the user data, wherein the first user interest feature includes the user's satisfaction with various resource posters;

[0013] Extracting a first image feature of the first resource poster, where the first image feature includes a first image quality feature and a first image content feature;

[0014] The first image quality feature, the first image content feature, and the first user interest feature are input into a pre-trained poster quality scoring model to obtain a poster quality score of the first resource poster.

[0015] In some feasible embodiments, before the controller inputs the first image quality feature, the first image content feature, and the first user interest feature into a pre-trained poster quality scoring model, the controller is further configured to:

[0016] Acquire a first training sample and annotated data of the first training sample, wherein the first training sample includes a second image quality feature and a second image content feature of a historical resource poster and a second user interest feature of historical user data, and the annotated data is quality score data of the historical resource poster;

[0017] The first training sample is used as input data, the annotated data is used as a data label, and the model parameters in the poster quality scoring model are iteratively updated until the loss function of the poster quality scoring model is less than a preset threshold, and it is determined that the training of the poster quality scoring model is completed.

[0018] In some feasible embodiments, the multimedia resource candidate set further includes a first multimedia resource corresponding to each of the first resource posters;

[0019] The controller determines the multimedia resource recommendation result in the multimedia resource candidate set based on the user data and the poster quality score, and is specifically configured as follows:

[0020] Extracting user portrait features of the user data, wherein the user portrait features at least include user age and user gender;

[0021] Extracting metadata features of the first multimedia resource, wherein the metadata features at least include subject matter, language, and country;

[0022] All of the user portrait features, all of the first user interest features, all of the metadata features and the poster quality score are input into a pre-trained multimedia resource recommendation model to obtain the multimedia resource recommendation result; wherein the multimedia resource recommendation result also includes the second multimedia resource corresponding to the second resource poster.

[0023] In some feasible embodiments, after the controller determines the multimedia resource recommendation result in the multimedia resource candidate set and before controlling the display to display the multimedia resource recommendation result, the controller is further configured to:

[0024] Based on the user data, performing image enhancement on each of the second resource posters to obtain a plurality of enhanced resource posters;

[0025] The controller controls the display to display the multimedia resource recommendation result, and is specifically configured to: control the display to display a plurality of the second multimedia resources and the enhanced resource poster corresponding to each of the second multimedia resources.

[0026] In some feasible embodiments, the controller performs image enhancement on each of the second resource posters based on the user data to obtain multiple enhanced resource posters, which is specifically configured as follows:

[0027] extracting a second image feature of each of the second resource posters;

[0028] Using at least one image enhancement model, based on the first user interest feature and the second image feature, obtain an initial image enhancement result corresponding to the image enhancement model;

[0029] The initial image enhancement results corresponding to all the image enhancement models are fused to obtain the enhanced resource poster.

[0030] In some feasible embodiments, before executing the acquisition of the multimedia resource candidate set, the controller is configured to:

[0031] Acquire multiple third multimedia resources and a third resource poster corresponding to each of the third multimedia resources in a multimedia resource library;

[0032] Review each of the third resource posters based on preset review rules;

[0033] Using a plurality of third resource posters approved in the multimedia resource library and third multimedia resources corresponding to the third resource posters as the first resource poster and the first multimedia resource;

[0034] The multimedia resource candidate set is constructed according to the first multimedia resource and the corresponding first resource poster.

[0035] In a second aspect, the present application provides another display device, comprising: a display; a communicator configured to communicate with a server; and a controller coupled to the display and the communicator, configured to:

[0036] Acquire user data, control the communicator to send the user data to the server, so that the server acquires the user data, and obtains a multimedia resource recommendation result based on the user data and a multimedia resource candidate set; wherein the multimedia resource candidate set includes a plurality of first resource posters; and the multimedia resource recommendation result includes a plurality of second resource posters;

[0037] Controlling the communicator to receive the multimedia resource recommendation result from the server;

[0038] The display is controlled to display the multimedia resource recommendation result.

[0039] In a third aspect, the present application provides a server, comprising: a communicator configured to be communicatively connected with a display device;

[0040] A processor is coupled to the communicator and is configured to:

[0041] Controlling the communicator to receive user data from the display device and obtain a multimedia resource candidate set, wherein the multimedia resource candidate set includes a plurality of first resource posters;

[0042] Performing a quality score on the first resource poster based on the user data to obtain a poster quality score of the first resource poster;

[0043] Determine a multimedia resource recommendation result in the multimedia resource candidate set based on the user data and the poster quality score; the multimedia resource recommendation result includes a plurality of second resource posters;

[0044] The communicator is controlled to send the multimedia resource recommendation result to the display device, so that the display of the display device displays the multimedia resource recommendation result.

[0045] In a fourth aspect, the present application provides a multimedia resource recommendation method, applied to a display device, comprising:

[0046] Acquire user data and a multimedia resource candidate set, wherein the multimedia resource candidate set includes a plurality of first resource posters;

[0047] Performing a quality score on the first resource poster based on the user data to obtain a poster quality score of the first resource poster;

[0048] Based on the user data and the poster quality score, a multimedia resource recommendation result in the multimedia resource candidate set is determined; the multimedia resource recommendation result includes a plurality of second resource posters.

[0049] As can be seen from the above technical content, the present application provides a display device, a server and a multimedia resource recommendation method. The method obtains user data and a multimedia resource candidate set, wherein the multimedia resource candidate set includes multiple first resource posters; the first resource poster is scored based on the user data to obtain a poster quality score of the first resource poster; based on the user data and the poster quality score, the multimedia resource recommendation result in the multimedia resource candidate set is determined; the multimedia resource recommendation result includes multiple second resource posters. The method can score and recommend resource posters based on user data, thereby making the recommendation results more in line with user needs, improving the visual presentation quality of resource posters, and thus improving the user's visual experience and better meeting user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] 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.

[0051] 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;

[0052] Figure 2 A hardware configuration block diagram of a display device provided in an embodiment of the present application;

[0053] Figure 3 A schematic diagram of software configuration of a display device provided in an embodiment of the present application;

[0054] Figure 4 A schematic diagram of a process for a display device provided in an embodiment of the present application to generate multimedia resource recommendation results based on user data and a multimedia resource candidate set;

[0055] Figure 5 A schematic diagram of a process flow of a resource poster review method provided in an embodiment of the present application;

[0056] Figure 6 A schematic diagram of a process for a display device provided in an embodiment of the present application to obtain a poster quality score of a first resource poster according to user data;

[0057] Figure 7 A schematic diagram of displaying multimedia resource recommendation results provided in an embodiment of the present application;

[0058] Figure 8 A schematic diagram of a process for determining multimedia resource recommendation results based on user data and poster quality scores provided in an embodiment of the present application;

[0059] Fig. 9 A schematic diagram of a process of performing image enhancement on a second resource poster based on user data provided in an embodiment of the present application;

[0060] Fig.10 A schematic diagram of a timing sequence of a display device according to an embodiment of the present application obtaining a recommendation result based on user data;

[0061] Fig.11 A schematic diagram of a flow chart of a display device and a server communicating with each other to generate multimedia resource recommendation results based on user data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] 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.

[0063] 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 common and usual meanings.

[0064] 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.

[0065] 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.

[0066] 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.

[0067] 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 .

[0068] 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.

[0069] 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.

[0070] 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 .

[0071] 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.

[0072] 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.

[0073] 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.

[0074] Figure 2 FIG. 1 shows a hardware configuration block diagram of a control device 100 according to some embodiments. Figure 2 As shown, the control device 100 includes a controller 250, a communication interface 130, a user input / output interface 140, a memory, and a power supply. The control device 100 can receive input operation instructions from the user, and convert the operation instructions into instructions that the display device 200 can recognize and respond to, playing the role of an interactive intermediary between the user and the display device 200.

[0075] 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.

[0076] 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.

[0077] 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.

[0078] 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.

[0079] 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.

[0080] 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.

[0081] In some embodiments, the external device interface 240 may include, but is not limited to, any one or more of the following: 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.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.).

[0091] 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.

[0092] 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.

[0093] The operating system can be divided into different modules or layers according to the functions implemented, such as 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.

[0094] 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.

[0095] 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.

[0096] Figure 3 A schematic diagram of the software configuration of the display device 200 provided in an embodiment of the present application.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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).

[0101] Native apps can support online or offline, message push or local resource access.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] Based on the above hardware framework and software framework, in some embodiments, the user can input instructions through the user interface to control the display device 200 to perform corresponding actions. For example, when the user wants to watch a short video, he can input a multimedia resource data search instruction in the short video search interface, and the display device 200 can display a multimedia resource data recommendation list for the user to select according to the multimedia resource data search instruction.

[0106] In the embodiment of the present application, the personalized recommendation system can analyze the user's viewing habits, preferences and other behavioral data to recommend TV programs, movies or other video content that the user may be interested in. The personalized recommendation system is usually integrated into smart TVs or streaming platforms to improve the user experience, making it easier for users to find content they may like, while increasing the user's stay time and interaction frequency on the platform.

[0107] The content that the personalized recommendation system can display includes, but is not limited to, similar content recommended based on the user's past viewing history, such as new works of similar genre or subject matter to films that have been watched before; related works of actors or directors that have appeared in the user's viewing history; other popular programs or movies of the same genre; related content recommended based on external factors such as time, weather, holidays, etc., such as special programs on weekends or specific holidays; the latest released or upcoming works in the services to which the user subscribes; and exclusive content or series customized to the user's personal preferences, such as documentary series or special programs.

[0108] Existing personalized recommendation systems usually make recommendations based on the characteristics of multimedia resource content, such as subject matter and genre, but may ignore the impact of visual presentation on user experience, such as the quality of multimedia resource posters. Poor-quality posters in personalized recommendation results may leave a bad first impression on users, thereby reducing their interest in the recommended content and affecting their viewing experience.

[0109] In view of the above problems, Figure 4 A flow chart of a display device according to an embodiment of the present application generating multimedia resource recommendation results based on user data and a multimedia resource candidate set. Figure 4 As shown, some embodiments of the present application provide a display device 200, which includes: a display 260 and a controller 250. The controller 250 is coupled to the display 260 and is configured to execute the following program steps:

[0110] S100: Acquire user data and a candidate set of multimedia resources.

[0111] Here, user data may include user behavior data and user portrait data. User behavior data is used to represent the specific activities of the user when using the display device 200, including but not limited to: viewing history, search history, interactive behavior, dwell time, click-through rate, feedback information, etc. Among them, interactive behaviors may include likes, comments, shares or favorites, etc., dwell time may include the length of time a user spends on a certain content, click-through rate is the probability that a user clicks on a certain recommended content, and feedback information is the user's feedback on the recommended content, including ratings, whether it has been watched in full, etc., but not limited to this. User portrait data is used to represent the user's background and preferences, and may include basic user information, such as age, gender, geographic location, etc., but not limited to this. The multimedia resource candidate set is a collection of multimedia resources obtained through review in the multimedia resource library, and the multimedia candidate set includes multiple first multimedia resources and a first resource poster corresponding to each multimedia resource.

[0112] In some embodiments, before executing the acquisition of the multimedia resource candidate set, the controller is configured to: acquire multiple third multimedia resources and a third resource poster corresponding to each third multimedia resource in the multimedia resource library; review each third resource poster based on preset review rules; use multiple third resource posters that have passed the review in the multimedia resource library and the third multimedia resources corresponding to the third resource posters as the first resource poster and the first multimedia resource; and construct a multimedia resource candidate set based on the first multimedia resource and the corresponding first resource poster.

[0113] The multimedia resource library contains a large number of third multimedia resources and their corresponding third resource posters. The multimedia resources may include files in various formats such as video, audio, and pictures. Each resource has its corresponding poster as a visual identifier. The multimedia resources in the embodiments of the present application are all used as video files to illustrate the technical solution.

[0114] In order to ensure that the third resource posters in the multimedia resource library comply with local laws and regulations and the suitability of the content of the third resource posters, the third resource posters can be subject to a security review based on preset review rules, and the approved third multimedia resources and corresponding third resource posters in the multimedia resource library can be used as the first multimedia resources and first resource posters to construct a multimedia resource candidate set for subsequent application of the approved first multimedia resources and first resource posters.

[0115] Figure 5 A flowchart of a resource poster review method provided in an embodiment of the present application.

[0116] like Figure 5 As shown, the method is applied to a controller and is configured to perform the following steps:

[0117] S501: According to preset audit rules, a security audit is performed on the text content and image content of the third multimedia resource poster to obtain a first audit result.

[0118] Here, the preset review rules may include poster text content review rules and poster image content review rules. Poster text content review rules may include checking the text content contained in the poster and filtering posters with inappropriate information. Among them, inappropriate information may include pornographic content, violent and bloody content, religious extremism information, ethnic discriminatory remarks, politically sensitive topics, illegal and illegal information, inappropriate language (dirty words, etc.), etc. In addition, all text information that violates the requirements of laws and regulations can be regarded as inappropriate information, and this application does not limit this.

[0119] The rules for reviewing the content of poster images include analyzing the content of poster images and filtering posters that contain inappropriate elements. Inappropriate elements include, but are not limited to, explicit pornographic images, violent and bloody images, image symbols involving hatred and discrimination, illegal and irregular image information (such as prohibition signs, etc.), religious extremist symbolic patterns, politically sensitive elements, and other inappropriate image content (such as uncomfortable image content, etc.).

[0120] Furthermore, the controller can set a text mark for inappropriate information in the poster text based on the poster text content review rules; and set an image mark for inappropriate elements in the poster image based on the poster image content review rules. Then, the posters with text marks and image marks are removed to obtain a first review result, which is a third resource poster that passes the preset review rules.

[0121] S502: Use a preset audit model to audit the first audit result to obtain a second audit result.

[0122] Here, a preset audit model such as a deep learning model can be used to audit the first audit result to obtain a second result. Specifically, natural language processing can be used to perform text audit on the third resource poster, and a preset language recognition model optimized by an attention mechanism such as a BERT (Bidirectional Encoder Representations from Transformer) model can be used to identify key words or phrases of inappropriate information in the third resource poster. Next, a preset topic model, such as an LDA (Latent Dirichlet Allocation) model, can be used to determine the text theme of the resource poster, and posters identified by the preset language model as containing inappropriate information and posters identified by the preset topic model as containing inappropriate information are eliminated to obtain a text content audit result, that is, the third resource poster whose text has passed the security audit in the first audit result.

[0123] Next, computer vision technology is used to review the image content of resource posters. Generative Adversarial Networks (GANs) can be used to generate similar resource posters, and CNN (Convolutional Neural Networks) can be used to identify the scene categories and specific objects in the resource posters. For example, it can be identified whether the resource poster contains violent scenes or inappropriate behaviors. Image description generation technology can also be used to convert the image content of resource posters into natural language descriptions, and then these descriptions are reviewed using NLP (Natural Language Processing) models to check whether they contain inappropriate words or content, and resource posters that include inappropriate elements are eliminated to obtain the image content review results, that is, the resource posters whose images have passed the security review in the first review results.

[0124] Finally, the resource posters that are the same in the text content review results and the image content review results are selected as the second review results. The above process further reviews the first review results based on the preset review model, and can further review complex or changeable content that cannot be reviewed by the preset review rules, thereby reducing the possibility of misjudgment or omission of review and maintaining a high review accuracy.

[0125] S503: Construct a knowledge graph based on the second review result, review the poster from a semantic level based on the knowledge graph, and obtain a third review result.

[0126] Specifically, determine the concepts and relationship instances in the audit field, and design an ontology model. Here, the audit field refers to the content and audit standards that may be involved in the ontology knowledge base, which may include sensitive content categories, content types, user behaviors, etc. Concepts are texts with entity types in the audit field, which may include "content", "user", "comment", "picture", etc. Relationship instances are specific concepts. For example, the relationship instance with the concept of "user" can be a specific user ID, and the relationship instance with the concept of "picture" can be a specific picture file. The specific features used for concepts and instances are used as attributes. Among them, attributes may include data attributes and object attributes. Data attributes may include, for example, the age of the user, the text content of the comment, etc., and object attributes may include that the user has posted a comment, the comment contains a picture, etc.

[0127] Furthermore, the concepts, relationship instances and attributes in the ontology are transformed into a knowledge graph. For example, entities such as users, comments, and pictures and their relationships are organized into a graph structure. Then, inference rules are defined, and the knowledge graph is inferred based on the inference rules. For example, the inference engine is used to identify and review the unsafe content hidden in the poster to obtain the third review result.

[0128] In some embodiments, the third audit result is the first resource poster that has passed the audit, and a multimedia resource candidate set can be constructed based on multiple first resource posters and the first multimedia resource corresponding to each first resource poster. The multi-level audit strategy of this process can maximize the accuracy and comprehensiveness of the audit.

[0129] S200: Performing a quality score on the first resource poster based on the user data to obtain a poster quality score of the first resource poster.

[0130] In the embodiment of the present application, the user behavior data in the user data can be used to quantitatively evaluate the quality of the first resource poster. The user behavior data can be used to evaluate the user's preference and degree of interaction with the poster, such as user feedback, click-through rate, viewing time, number of shares, etc. For example, the poster quality score of the first resource poster can be determined based on the user's viewing time of the multimedia resource.

[0131] In some embodiments, Figure 6 A flow chart of a display device according to an embodiment of the present application obtaining a poster quality score of a first resource poster according to user data. Figure 6 As shown, the controller executes step S200, and is specifically configured to execute the following steps:

[0132] S601: Extracting a first user interest feature from user data.

[0133] Here, the first user interest feature of the user behavior data in the user data can be extracted. Specifically, the user behavior data is preprocessed, including but not limited to cleaning invalid data, filling missing values, standardizing numerical data, etc., to ensure data quality. The first user interest feature of the preprocessed user behavior data is extracted. The first user interest feature is used to indicate the user's satisfaction with various resource posters, and may include the user's active time period, preferred type, viewing frequency, interactive behavior, etc.

[0134] S602: Extracting a first image feature of a first resource poster.

[0135] Here, a deep learning model, such as a pre-trained VGG (Visual Geometry Group), ResNet (Residual Network) or other neural network, may be used to extract the first image feature of the first resource poster. Here, the first image feature may include a first image quality feature and a first image content feature. The first image quality feature is used to represent the attribute feature of the first resource poster itself, including but not limited to: resolution, color saturation, contrast, sharpness, noise, etc. The first image content feature is used to represent the specific content contained in the image of the first resource poster, including but not limited to: subject, image scene, action of the subject in the image, emotion in the image, etc. Among them, the subject may include the main object or person in the image, such as a face, an animal, a building, etc.; the image scene may include urban scenery, natural scenery, indoor environment, etc.

[0136] S603: Inputting the first image quality feature, the first image content feature, and the first user interest feature into a pre-trained poster quality scoring model.

[0137] S604: Obtain a poster quality score of the first resource poster.

[0138] Here, a pre-trained poster quality scoring model may be used to obtain a poster quality score according to the first user interest feature of the user data and the first image feature of the first resource poster.

[0139] In some embodiments, before the controller executes step S603, it is also configured to: obtain a first training sample and annotated data of the first training sample, use the first training sample as input data and the annotated data as a data label, iteratively update the model parameters in the poster quality scoring model until the loss function of the poster quality scoring model is less than a preset threshold, and determine that the training of the poster quality scoring model is completed.

[0140] Here, the poster quality scoring model can be based on an integrated learning method such as XGBoost (eXtreme Gradient Boosting, extreme gradient boosting) to build a multi-objective optimization model, or it can be constructed based on deep learning, and this application does not impose any restrictions. The first training sample includes a second image quality feature and a second image content feature of a historical resource poster and a second user interest feature of historical user data. The annotated data is the quality score data of the historical resource poster. The annotated data can be the quality score data for the operator to score the historical resource poster based on user data, or it can be the quality score data for the user to score the historical resource poster according to a preset scoring dimension. Among them, the preset scoring dimensions may include the quality of the resource poster, the attractiveness of the resource poster to the user, the expressiveness of the resource poster, and the originality of the resource poster.

[0141] In some embodiments, real-time user data may also be obtained, including but not limited to the user's click behavior, the time spent on the page, whether the content is shared, etc. The poster quality scoring model may be updated in real time or regularly based on the real-time user data based on online learning mechanisms such as federated learning and incremental learning.

[0142] In some embodiments, the poster quality scoring model can also be updated in real time or regularly based on user feedback data. Specifically, a user feedback channel is established, and user feedback data on recommended posters is collected based on the user feedback channel, wherein the feedback data includes direct feedback and indirect feedback. Direct feedback can be a user's direct evaluation of the recommended poster (such as a like / dislike button), and indirect feedback can be collected through user behavior data such as click-through rate, dwell time, and sharing behavior.

[0143] In some embodiments, the user behavior patterns of real-time user data may be analyzed, and the user behavior patterns may include short-term behavior and long-term behavior. Short-term behavior is used to capture the user's current interest changes, which is the user's most recent behavior data, such as one hour or one day's behavior data. Long-term behavior is used to build a user's long-term interest model, which is the user's historical behavior data, such as one week or one month's behavior data. Then, the parameters of the quality scoring model can be dynamically adjusted according to the user's behavior pattern, and the adjusted parameters can be applied to the poster quality scoring model to achieve model updates. Specifically, the feature weights can be adjusted according to the user's short-term behavior so that the model pays more attention to the features that the user is currently interested in. The learning rate can be adjusted according to the user's long-term behavior to ensure that the model can converge smoothly during the long-term optimization process and ensure the overall quality of the recommendation results.

[0144] In some embodiments, contextual data in user data can also be collected, and scoring rules can be dynamically adjusted based on the contextual data. Specifically, contextual data can include time information (such as date, time period) when the user accesses the recommendation system, geographic location information (such as city, country) obtained from the user, and environmental information (such as weather, festivals, etc.) obtained from the user. The time weight, location weight, and environmental weight of the poster quality scoring model can be adjusted based on the above-mentioned contextual data, and then the scoring rules can be adjusted. For example, posters with a more festive atmosphere can be recommended during holidays to improve the timeliness and relevance of the recommendation.

[0145] In some embodiments, a rule configuration visualization interface can be provided so that operators can intuitively see the effects of the current scoring rules, including key indicators such as the score distribution of each dimension and user satisfaction, and can directly adjust the scoring parameters or add temporary rules, such as special scoring criteria for specific activities.

[0146] In some embodiments, the poster quality scoring model is updated by collecting real-time user data, establishing user feedback channels, and operators adjusting scoring rules based on a rule-based configuration visual interface. This not only enables accurate evaluation of poster quality from multiple dimensions, but also enables real-time adjustment of scoring strategies based on dynamic changes in user interests and market feedback, ensuring that recommended content is always close to user needs and improving user viewing experience.

[0147] S300: Determine a multimedia resource recommendation result in a multimedia resource candidate set based on user data and poster quality scores.

[0148] Here, the user data poster quality score may be input into a pre-trained multimedia resource recommendation model to obtain a multimedia resource recommendation result, which includes a plurality of second resource posters and second multimedia resources corresponding to the second resource posters.

[0149] S400: Control the display to display the multimedia resource recommendation result.

[0150] In some embodiments, Figure 7 A schematic diagram of displaying multimedia resource recommendation results provided in an embodiment of the present application, such as Figure 7 As shown, the multimedia resource recommendation result can be displayed on the UI interface of the display device for the user to select the multimedia resource he likes. The UI interface can include a recommended content area 701 and a service classification extension area 702.

[0151] Here, the recommended content area 1 is used to configure different classified TAB columns; you can choose to configure multimedia resources, special topics, etc. in the column; multimedia resources may include 2D movies, educational courses, travel, 3D, 360-degree panorama, live broadcast, 4K movies, program applications, games, travel and other businesses with multimedia resource content, and the column can choose different template styles, and can support the simultaneous recommendation and arrangement of multimedia resources and special topics.

[0152] The business classification extension area 2 supports the configuration of extended categories of different categories. If there is a new business type, it supports the configuration of an independent TAB to display the corresponding page content. The extended categories in the business classification extension area 2 can also be sorted and adjusted and offline business operations can be performed. In some embodiments, the business classification extension area 2 may include the following content: film and television, education, travel, applications, and mine. In some embodiments, the business classification extension area 2 is configured to display a large business category TAB, and supports the configuration of more categories, and its icons support configuration display.

[0153] In some embodiments, Figure 8 A schematic diagram of a process for determining multimedia resource recommendation results based on user data and poster quality scores provided in an embodiment of the present application, such as Figure 8 As shown, the controller executes step S300 and is configured to execute the following program steps:

[0154] S801: Extract user portrait features from user data, where the user portrait features at least include user age and user gender.

[0155] Here, user portrait features of user portrait data in the user data may be extracted. The user portrait features are used to describe the user's personal information features, including at least the user's age, gender, geographic location, and occupation.

[0156] S802: Extract metadata features of a first multimedia resource.

[0157] Here, the metadata features of the first multimedia resource are used to describe the basic information of the first multimedia resource. The metadata features include but are not limited to subject matter, language, country, author, popularity, etc., where the subject matter is the theme or type involved in the multimedia resource, which may include action films, adventure films, comedies, romance films, etc. The language is the language of the multimedia resource, such as Chinese, Japanese, English, etc., and the country is the country that produced the multimedia resource, such as the United States.

[0158] S803: Input all user portrait features, all first user interest features, all metadata features, and poster quality scores into a pre-trained multimedia resource recommendation model.

[0159] S804: Obtain multimedia resource recommendation results.

[0160] Here, the multimedia resource recommendation model can adopt collaborative filtering, content recommendation or hybrid recommendation algorithm, combining the user portrait features of the user data and the metadata features of the first multimedia resource and the poster quality score of the first resource poster, to obtain the multimedia resource recommendation result based on the user portrait features and the poster quality score. Among them, the pre-trained multimedia resource recommendation model can be constructed by deep learning such as convolutional neural network (CNN) or recurrent neural network (RNN), and the multimedia resource recommendation result also includes a second resource poster corresponding to the second multimedia resource.

[0161] In some embodiments, user feedback data can also be collected based on the above user feedback channels to evaluate the recommendation effect of multimedia resources. Model parameters of the multimedia resource recommendation model can also be continuously optimized based on feedback data and A / B test results, and user portrait features and metadata features can be regularly updated to adapt to changes in user interests, which is conducive to the update of multimedia resource content.

[0162] In some embodiments, after the controller determines the multimedia resource recommendation results in the multimedia resource candidate set and before controlling the display to display the multimedia resource recommendation results, the controller is further configured to: based on user data, perform image enhancement on each second resource poster to obtain multiple enhanced resource posters.

[0163] Here, after obtaining the multimedia resource recommendation results, the multimedia resource recommendation results can also be enhanced according to user data, so that the resource posters in the multimedia resource recommendation results are more in line with user preferences, thereby enhancing the user's interest in and favorability of the recommended content.

[0164] In some embodiments, Fig. 9 This is a flow chart of performing image enhancement on a second resource poster based on user data provided in an embodiment of the present application. Fig. 9As shown, the controller performs image enhancement on each second resource poster based on user data to obtain multiple enhanced resource posters, and is specifically configured to perform the following steps:

[0165] S901: Extract the second image feature of each second resource poster.

[0166] Here, the second image feature of the second resource poster includes a third image quality feature and a third image content feature. The third image quality feature has the same content type as the second image quality feature, and the third image content feature has the same content type as the second image feature.

[0167] S902: Using at least one image enhancement model, based on the first user interest feature and the second image feature, obtain an initial image enhancement result corresponding to the image enhancement model.

[0168] Here, the quality of the second resource poster can be enhanced by using at least one image enhancement model according to the first user interest feature. The image enhancement model includes any one or more of the following: an image quality enhancement model for enhancing the image quality of the second resource poster, an image semantic segmentation model for locating a target element in the second resource poster, an image layout optimization model for adjusting the layout of the target element, a character proportion adjustment model for adjusting the proportion of the target character in the second resource poster, and an image style transfer model for adjusting the style of the second resource poster.

[0169] Specifically, the image quality model can be used to reconstruct the low-resolution or noisy second resource poster to generate a clearer and higher-resolution image quality enhancement result; the image semantic segmentation model can be used to perform pixel-level semantic segmentation on the second resource poster, and output the category label of each pixel to obtain the image semantic segmentation result; the image layout optimization model can be used to rearrange the elements in the second resource poster to obtain the image layout optimization result, making it more reasonable and beautiful; the character proportion adjustment model can be used to optimize the character's proportions, posture, etc. to obtain the character proportion adjustment result, making it more coordinated and dynamic; the image style transfer model can be used to convert the style of the second resource poster into a more fashionable and artistic style to obtain the image style transfer result.

[0170] S903 integrates the initial image enhancement results corresponding to all image enhancement models to obtain an enhanced resource poster.

[0171] Here, multiple initial image enhancement results can be obtained based on the above multiple image enhancement models, and the above initial image enhancement results are merged to obtain an enhanced resource poster. For example, by using the image quality model and the image layout optimization model to enhance the second resource poster, an enhanced resource poster with enhanced image quality and optimized image layout can be obtained.

[0172] In some embodiments, the controller controls the display to display the multimedia resource recommendation result, and is specifically configured to: control the display to display multiple second multimedia resources and an enhanced resource poster corresponding to each second multimedia resource. Here, the final multimedia resource recommendation result is multiple second multimedia resources and an enhanced resource poster corresponding to each second multimedia resource. The controller can control the display to display the above multimedia resource recommendation result on the user interface.

[0173] In some embodiments, Fig.10 A timing diagram of a display device according to an embodiment of the present application obtaining a recommendation result based on user data. Fig.10 As shown, the display device includes a user data acquisition module, a page display module, a multimedia resource library, a security audit module, a quality scoring module, a recommendation service, and a poster enhancement service. The user data acquisition module can acquire user data and send the user data to the quality scoring module, the recommendation service, and the poster enhancement service. The multimedia resource library includes a variety of multimedia resources and media posters corresponding to the multimedia resources. The multimedia resource library sends resource posters to the audit module, the security audit module performs a security audit on the resource posters, and sends the resource posters that have passed the audit to the quality scoring module. The quality scoring module scores the resource posters based on the user data to obtain a poster quality score, and sends the poster quality score to the recommendation service. The recommendation service obtains the multimedia resource recommendation result based on the user data and the poster quality score, and sends the recommendation result to the poster enhancement service, and can also send the recommendation result to the page display module, and the recommendation result includes the recommended multimedia resources and the corresponding resource posters. The poster enhancement module enhances the posters in the recommendation result according to the user data to obtain an image enhancement poster, and sends the image enhancement poster and the corresponding multimedia resource to the page display module to recommend to the user.

[0174] In some embodiments, Fig.11 A flow chart of the communication between the display device and the server provided in the embodiment of the present application to generate multimedia resource recommendation results based on user data. Fig.11 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:

[0175] Acquire user data, control the communicator to send the user data to the server so that the server acquires the user data, and obtain a multimedia resource recommendation result based on the user data and the multimedia resource candidate set; wherein the multimedia resource candidate set includes a plurality of first resource posters; and the multimedia resource recommendation result includes a plurality of second resource posters;

[0176] Controlling the communicator to receive the multimedia resource recommendation result from the server;

[0177] Control the display to display the multimedia resource recommendation results.

[0178] The display device 200 may be a smart TV with high computing power, which can obtain user data and multimedia resource candidate sets and generate a multimedia resource recommendation list through its own computing chip. However, in some application scenarios, the display device 200 may be a low computing power device such as an advertising machine. The low computing power terminal device generates a multimedia resource recommendation list slowly or cannot carry a computing model.

[0179] Based on the above problems, in some embodiments, the display device 200 can also interact with the server in real time to generate a multimedia resource recommendation list through the server, receive the multimedia resource recommendation list sent by the server, and then display the multimedia resource recommendation list 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 multimedia resource recommendation list cannot be generated in time according to the user data and the multimedia resource candidate set due to insufficient computing power of the display device 200.

[0180] In some embodiments, the present application further provides a server, including: a communicator, configured to be communicatively connected with a display device; and a processor, coupled to the communicator and configured to:

[0181] Controlling the communicator to receive user data from the display device and obtain a multimedia resource candidate set, wherein the multimedia resource candidate set includes a plurality of first resource posters;

[0182] Performing a quality score on the first resource poster based on the user data to obtain a poster quality score of the first resource poster;

[0183] Determine a multimedia resource recommendation result in the multimedia resource candidate set based on the user data and the poster quality score; the multimedia resource recommendation result includes a plurality of second resource posters;

[0184] The communicator is controlled to send the multimedia resource recommendation result to the display device, so that the display of the display device displays the multimedia resource recommendation result.

[0185] The server may receive user data forwarded by the display device 200, and generate a multimedia resource recommendation list according to the user data and the multimedia resource candidate set. The generated multimedia resource recommendation list is sent to the display device 200, so that the display device 200 displays the multimedia resource recommendation list for the user to select. This alleviates the problem that it is difficult for the low-computing-power display device 200 to generate a multimedia resource recommendation list.

[0186] In some embodiments, the present application further provides a multimedia resource recommendation method, which is applied to a display device with high computing power, including:

[0187] Acquire user data and a multimedia resource candidate set, wherein the multimedia resource candidate set includes a plurality of first resource posters;

[0188] Performing a quality score on the first resource poster based on the user data to obtain a poster quality score of the first resource poster;

[0189] Based on the user data and the poster quality score, a multimedia resource recommendation result in the multimedia resource candidate set is determined; the multimedia resource recommendation result includes a plurality of second resource posters.

[0190] 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.

[0191] It is understandable that in some embodiments, a multimedia resource recommendation method for a display device with low computing power is also provided. The controller 250 of the display device 200 forwards the user data to the server, and the server performs the process of generating the multimedia resource recommendation result, and sends the generated multimedia resource recommendation result to the display device 200. The display device 200 displays the multimedia resource recommendation result through the display 260.

[0192] It can be seen from the above technical content that the present application provides a display device, a server and a multimedia resource recommendation method. The method obtains user data and a multimedia resource candidate set, wherein the multimedia resource candidate set includes multiple first resource posters; the first resource poster is scored based on the user data to obtain a poster quality score of the first resource poster; based on the user data and the poster quality score, the multimedia resource recommendation result in the multimedia resource candidate set is determined; the multimedia resource recommendation result includes multiple second resource posters; and the display is controlled to display the multimedia resource recommendation result. The process can obtain user data, score the first resource poster in the multimedia resource candidate set based on the user data, and obtain a poster quality score; use the poster quality score and user data to generate a multimedia resource recommendation result that better meets the user's preferences, thereby improving the user's viewing experience.

[0193] 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: Acquire user data and a multimedia resource candidate set, wherein the multimedia resource candidate set includes a plurality of first resource posters; Performing a quality score on the first resource poster based on the user data to obtain a poster quality score of the first resource poster; Determine a multimedia resource recommendation result in the multimedia resource candidate set based on the user data and the poster quality score; the multimedia resource recommendation result includes a plurality of second resource posters; The display is controlled to display the multimedia resource recommendation result.

2. The display device according to claim 1, characterized in that The controller performs quality scoring on the first resource poster based on the user data to obtain a poster quality score of the first resource poster, and is configured to: Extracting a first user interest feature of the user data, wherein the first user interest feature includes the user's satisfaction with various resource posters; Extracting a first image feature of the first resource poster, where the first image feature includes a first image quality feature and a first image content feature; The first image quality feature, the first image content feature, and the first user interest feature are input into a pre-trained poster quality scoring model to obtain a poster quality score of the first resource poster.

3. The display device according to claim 2, characterized in that Before the controller inputs the first image quality feature, the first image content feature, and the first user interest feature into a pre-trained poster quality scoring model, the controller is further configured to: Acquire a first training sample and annotated data of the first training sample, wherein the first training sample includes a second image quality feature and a second image content feature of a historical resource poster and a second user interest feature of historical user data, and the annotated data is quality score data of the historical resource poster; The first training sample is used as input data, the annotated data is used as a data label, and the model parameters in the poster quality scoring model are iteratively updated until the loss function of the poster quality scoring model is less than a preset threshold, and it is determined that the training of the poster quality scoring model is completed.

4. The display device according to claim 2, characterized in that The multimedia resource candidate set also includes a first multimedia resource corresponding to each of the first resource posters; The controller determines the multimedia resource recommendation result in the multimedia resource candidate set based on the user data and the poster quality score, and is specifically configured as follows: Extracting user portrait features of the user data, where the user portrait features at least include user age and user gender; Extracting metadata features of the first multimedia resource, wherein the metadata features at least include subject matter, language, and country; All of the user portrait features, all of the first user interest features, all of the metadata features and the poster quality score are input into a pre-trained multimedia resource recommendation model to obtain the multimedia resource recommendation result; wherein the multimedia resource recommendation result also includes the second multimedia resource corresponding to the second resource poster.

5. The display device according to claim 4, characterized in that After the controller determines the multimedia resource recommendation result in the multimedia resource candidate set and before controlling the display to display the multimedia resource recommendation result, the controller is further configured to: Based on the user data, performing image enhancement on each of the second resource posters to obtain a plurality of enhanced resource posters; The controller controls the display to display the multimedia resource recommendation result, and is specifically configured to: control the display to display a plurality of the second multimedia resources and the enhanced resource poster corresponding to each of the second multimedia resources.

6. The display device according to claim 5, characterized in that The controller performs image enhancement on each of the second resource posters based on the user data to obtain a plurality of enhanced resource posters, and is specifically configured as follows: extracting a second image feature of each of the second resource posters; Using at least one image enhancement model, based on the first user interest feature and the second image feature, obtain an initial image enhancement result corresponding to the image enhancement model; The initial image enhancement results corresponding to all the image enhancement models are fused to obtain the enhanced resource poster.

7. The display device according to claim 1, characterized in that Before executing the acquisition of the multimedia resource candidate set, the controller is configured to: Acquire multiple third multimedia resources and a third resource poster corresponding to each of the third multimedia resources in a multimedia resource library; Review each of the third resource posters based on preset review rules; Using a plurality of third resource posters and third multimedia resources corresponding to the third resource posters that have been reviewed and approved in the multimedia resource library as the first resource poster and the first multimedia resource corresponding to the first resource poster; The multimedia resource candidate set is constructed according to the first multimedia resource and a first resource poster corresponding to the first multimedia resource.

8. A display device, characterized in that: include: monitor; A communicator configured to communicate with the server; A controller, coupled to the display and the communicator, is configured to: Acquire user data, control the communicator to send the user data to the server, so that the server acquires the user data, and obtains a multimedia resource recommendation result based on the user data and a multimedia resource candidate set; wherein the multimedia resource candidate set includes a plurality of first resource posters; and the multimedia resource recommendation result includes a plurality of second resource posters; Controlling the communicator to receive the multimedia resource recommendation result from the server; The display is controlled to display the multimedia resource recommendation result.

9. 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 user data from the display device and obtain a multimedia resource candidate set, wherein the multimedia resource candidate set includes a plurality of first resource posters; Performing a quality score on the first resource poster based on the user data to obtain a poster quality score of the first resource poster; Determine a multimedia resource recommendation result in the multimedia resource candidate set based on the user data and the poster quality score; the multimedia resource recommendation result includes a plurality of second resource posters; The communicator is controlled to send the multimedia resource recommendation result to the display device, so that the display of the display device displays the multimedia resource recommendation result.

10. A multimedia resource recommendation method, applied to a display device, characterized in that: include: Acquire user data and a multimedia resource candidate set, wherein the multimedia resource candidate set includes a plurality of first resource posters; Performing a quality score on the first resource poster based on the user data to obtain a poster quality score of the first resource poster; Based on the user data and the poster quality score, a multimedia resource recommendation result in the multimedia resource candidate set is determined; the multimedia resource recommendation result includes a plurality of second resource posters.

Images