Image processing method and system, product, equipment and storage medium

Abstract

The invention discloses an image processing method and system, a product, equipment and a storage medium, and relates to the field of image display, and the method comprises the steps: determining an interested role name of a target user based on collected attribute information and historical search records of the target user, and obtaining a drama and a drama description which meet a preset corresponding relation with the interested role name, and importing the drama and the drama description into a preset character motion graph generation model to obtain an animation character image corresponding to the name of the interested role, and displaying the animation character image in the display area of the paster advertisement. The animation character image is generated based on the drama and the drama description which meet the preset corresponding relation with the interested role name of the target user, so that the target user is interested in the animation character image, then the animation character image is displayed in the display area of the paster advertisement, the probability that the user views the content of the paster advertisement is improved, and the user experience is improved. And therefore, the purpose of improving the click rate of the paster advertisement is achieved.

Description

Technical Field

[0001] The present application relates to the field of image display technology, and in particular to an image processing method, system, product, device and storage medium. Background Art

[0002] As a form of advertising display when playing video media, pre-roll ads have been widely used by major video playback platforms. By playing the ad content in the display area of ​​the playback page before playing the video, the probability of users viewing and understanding the pre-roll ad content is increased.

[0003] However, since most existing patch ads are based on simple display of ad content, without considering the interests and preferences of different users, different users have different attention to the content of patch ads. Even when the content of patch ads is too monotonous, most users will not pay attention to the content of patch ads, which greatly affects the click-through rate of patch ads, which is unacceptable to advertisers. Therefore, how to improve the click-through rate of patch ads has become an urgent problem to be solved. Summary of the invention

[0004] In view of the above problems, this application provides an image processing method, system, product, device and storage medium to achieve the purpose of improving the click-through rate of patch ads. The specific solution is as follows:

[0005] The first aspect of the present application provides an image processing method, comprising:

[0006] Based on the collected attribute information and historical search records of the target user, determine the name of the character of interest to the target user, and obtain stills and stills descriptions that satisfy a preset correspondence relationship with the name of the character of interest;

[0007] Importing the stills and the still descriptions into a preset character animation generation model to obtain an animated character image corresponding to the name of the character of interest;

[0008] The animated character image is displayed in a display area of ​​the patch advertisement.

[0009] In a possible implementation, the training process of the preset character animation generation model includes:

[0010] Obtaining stills information of a plurality of characters, wherein the stills information includes stills of the characters and stills descriptions;

[0011] Constructing an initial character animation generation model including an initial image generation model and a preset aesthetic evaluation model, wherein the output of the image generation model is the input of the preset aesthetic evaluation model;

[0012] The initial image generation model in the initial character animation generation model is trained using the stills information of each of the characters as training data, the quality of the image output by the initial image generation model based on the training data is evaluated using the preset aesthetic evaluation model, and the model parameters of the initial image generation model are adjusted based on the result of the quality evaluation to obtain the preset character animation generation model, wherein the input of the preset character animation generation model is the stills and stills description corresponding to the name of the character of interest, and the output is the animated character image corresponding to the name of the character of interest.

[0013] In a possible implementation, displaying the animated character image in a display area of ​​a patch advertisement includes:

[0014] Scaling the animation character image according to the size parameter of the display area;

[0015] The scaled animated character image is displayed at a preset display position in the display area so that the pointing action of the animated character image points to a click area of ​​the patch advertisement, wherein the preset display position is an area in the display area that is adjacent to the click area and does not overlap with the patch advertisement.

[0016] In a possible implementation, determining the name of the role of interest to the target user based on the collected attribute information and historical search records of the target user includes:

[0017] Filtering the series type and character list of at least one series whose click rate is not less than a preset click rate threshold from the historical search records;

[0018] The attribute information, the drama type and the character list are input into a preset filtering algorithm, and the character names output by the preset filtering algorithm are determined as the character names of interest to the target user.

[0019] In a possible implementation, the training process of the preset filtering algorithm includes:

[0020] Collecting test data of multiple different test users as initial training data, the initial training data including: attribute information of the test users, the types of dramas they are interested in, and a list of characters;

[0021] Adding different weight labels to the names of the roles in the role list in the initial training data to obtain training data;

[0022] The initial filtering algorithm is trained using each of the training data to obtain the preset filtering algorithm, wherein the input of the preset filtering algorithm is the attribute information, the drama type and the character list, and the output is the name of the character of interest.

[0023] In a possible implementation, obtaining a still photo and a still photo description that satisfies a preset correspondence relationship with the name of the character of interest includes:

[0024] Obtaining the title of an episode in the character list that includes the name of the character of interest and whose play rate is not less than a preset threshold;

[0025] The stills and still descriptions corresponding to the name of the character of interest are extracted from a database corresponding to the name of the series.

[0026] A second aspect of the present application provides an image processing system, comprising:

[0027] A data acquisition module, for determining the name of the character of interest to the target user based on the collected attribute information and historical search records of the target user, and obtaining stills and stills descriptions that satisfy a preset correspondence relationship with the name of the character of interest;

[0028] An image generation module, used for importing the stills and the still descriptions into a preset character animation generation model to obtain an animated character image corresponding to the name of the character of interest;

[0029] The image display module is used to display the image of the animated character in the display area of ​​the patch advertisement.

[0030] In a possible implementation, the image processing system further includes a model training module, and the model training module is configured in the training process of the preset character dynamic image generation model as follows:

[0031] Obtaining stills information of a plurality of characters, wherein the stills information includes stills of the characters and stills descriptions;

[0032] Constructing an initial character animation generation model including an initial image generation model and a preset aesthetic evaluation model, wherein the output of the image generation model is the input of the preset aesthetic evaluation model;

[0033] The initial image generation model in the initial character animation generation model is trained using the stills information of each of the characters as training data, the quality of the image output by the initial image generation model based on the training data is evaluated using the preset aesthetic evaluation model, and the model parameters of the initial image generation model are adjusted based on the result of the quality evaluation to obtain the preset character animation generation model, wherein the input of the preset character animation generation model is the stills and stills description corresponding to the name of the character of interest, and the output is the animated character image corresponding to the name of the character of interest.

[0034] In a possible implementation, the image display module is configured to:

[0035] Scaling the animation character image according to the size parameter of the display area;

[0036] The scaled animated character image is displayed at a preset display position in the display area so that the pointing action of the animated character image points to a click area of ​​the patch advertisement, wherein the preset display position is an area in the display area that is adjacent to the click area and does not overlap with the patch advertisement.

[0037] In a possible implementation, the data acquisition module is configured to:

[0038] Filtering the series type and character list of at least one series whose click rate is not less than a preset click rate threshold from the historical search records;

[0039] The attribute information, the drama type and the character list are input into a preset filtering algorithm, and the character names output by the preset filtering algorithm are determined as the character names of interest to the target user.

[0040] In a possible implementation, the data acquisition module further includes a model training submodule, and the model training submodule is set to:

[0041] Collecting test data of multiple different test users as initial training data, the initial training data including: attribute information of the test users, the types of dramas they are interested in, and a list of characters;

[0042] Adding different weight labels to the names of the roles in the role list in the initial training data to obtain training data;

[0043] The initial filtering algorithm is trained using each of the training data to obtain the preset filtering algorithm, wherein the input of the preset filtering algorithm is the attribute information, the drama type and the character list, and the output is the name of the character of interest.

[0044] In a possible implementation, when obtaining the stills and stills descriptions that satisfy a preset correspondence relationship with the name of the character of interest, the data acquisition module is configured to:

[0045] Obtaining the title of an episode in the character list that includes the name of the character of interest and whose play rate is not less than a preset threshold;

[0046] The stills and still descriptions corresponding to the name of the character of interest are extracted from a database corresponding to the name of the series.

[0047] A third aspect of the present application provides a computer program product, comprising computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the image processing method of the first aspect or any implementation of the first aspect.

[0048] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0049] The memory is used to store computer programs;

[0050] The processor is used to execute the computer program so that the electronic device can implement the image processing method of the first aspect or any implementation manner of the first aspect.

[0051] A fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the image processing method of the first aspect or any implementation of the first aspect.

[0052] By means of the above technical scheme, the present application provides an image processing method, system, product, device and storage medium, which determines the name of the character of interest of the target user through the collected attribute information and historical search records of the target user, and obtains the stills and stills descriptions that satisfy the preset correspondence relationship with the name of the character of interest. Then, by importing the stills and stills descriptions into the preset character animation generation model, the animated character image corresponding to the name of the character of interest is obtained, and the animated character image is displayed in the display area of ​​the patch advertisement. Since the animated character image is generated based on the stills and stills descriptions corresponding to the name of the character of interest of the target user, the probability of the target user viewing the animated character image is increased. In addition, by displaying the animated character image in the display area of ​​the patch advertisement, the probability of the user viewing the content of the patch advertisement when viewing the animated character image is increased, thereby increasing the user's click-through rate on the patch advertisement. It can be seen that the present application increases the user's click-through rate on the patch advertisement. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0054] Figure 1 A schematic diagram of a system architecture provided for this application;

[0055] Figure 2 A schematic diagram of the hardware structure of a terminal provided in this application;

[0056] Figure 3 A schematic diagram of the structure of a server provided for this application;

[0057] Figure 4 A flowchart of an image processing method provided in this application;

[0058] Figure 5 A flowchart of an image processing method provided for a possible implementation of the present application;

[0059] Figure 6 A schematic diagram of displaying an animated character image in a display area provided for a possible implementation of the present application;

[0060] Figure 7 A flowchart for determining the name of a role of interest of a target user provided for a possible implementation of the present application;

[0061] Figure 8 A flowchart for obtaining an animated character image corresponding to a character name of interest is provided for a possible implementation of the present application;

[0062] Fig. 9 A block diagram of an image processing system provided by the present application;

[0063] Fig.10 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0064] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0065] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0066] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0067] It is understandable that before using the technical solutions disclosed in the embodiments of this application, the type, scope of use, usage scenarios, etc. of the personal information involved in this application should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations, such as stills, user attribute information, search records, etc.

[0068] See also Figure 1 , Figure 1 A schematic diagram of a system architecture is shown. The system may include a terminal 100 and a server 200. The server 200 may include one or more servers ( Figure 1 In the example, a server is included, and the server 200 can provide the method provided in the embodiment of the present application for one or more terminals.

[0069] Among them, an application can be installed on the terminal 100, and the above application and web page can provide an interface. The terminal 100 can receive relevant parameters entered by the user on the interface and send the above parameters to the server 200. The server 200 can obtain processing results based on the received parameters and return the processing results to the terminal 100.

[0070] It should be understood that in some optional implementations, the terminal 100 can also complete the action of obtaining the processing result based on the received parameters by itself without the cooperation of the server, and the embodiments of the present application are not limited to this.

[0071] Next describe Figure 1 The product form of the mid-terminal 100;

[0072] The terminal 100 in the embodiment of the present application can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc., and the embodiment of the present application does not impose any restrictions on this.

[0073] Figure 2 An optional hardware structure diagram of the terminal 100 is shown.

[0074] refer to Figure 2As shown, the terminal 100 may include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), a microphone 162 (optional), an earphone jack 163 (optional), a processor 170, an external interface 180, a power supply 190 and other components. Those skilled in the art will appreciate that Figure 2 These are merely examples of terminals or multi-function devices and do not constitute limitations on the terminals or multi-function devices, which may include more or fewer components than those shown in the figures, or combinations of certain components, or different components.

[0075] The input unit 130 can be used to receive input digital or character information, and generate key signal input related to the user settings and function control of the portable multifunctional device. Specifically, the input unit 130 may include a touch screen 131 (optional) and / or other input devices 132. The touch screen 131 can collect the user's touch operations on or near it (such as the user's operation on or near the touch screen using any suitable object such as fingers, joints, stylus, etc.), and drive the corresponding connection device according to a pre-set program. The touch screen can detect the user's touch action on the touch screen, convert the touch action into a touch signal and send it to the processor 170, and can receive and execute the command sent by the processor 170; the touch signal at least includes the touch point coordinate information. The touch screen 131 can provide an input interface and an output interface between the terminal 100 and the user. In addition, the touch screen can be implemented using multiple types such as resistive, capacitive, infrared and surface acoustic wave. In addition to the touch screen 131, the input unit 130 can also include other input devices. Specifically, other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, a joystick, and the like.

[0076] Among them, the input device 132 can receive input data and the like.

[0077] The display unit 140 can be used to display information input by the user or information provided to the user, various menus of the terminal 100, interactive interfaces, file display and / or playback of any multimedia file. In the embodiment of the present application, the display unit 140 can be used to display interfaces, processing results, etc.

[0078] The memory 120 can be used to store instructions and data. The memory 120 can mainly include an instruction storage area and a data storage area. The data storage area can store various data, such as multimedia files, texts, etc.; the instruction storage area can store software units such as operating systems, applications, instructions required for at least one function, or their subsets and extensions. It can also include a non-volatile random access memory; provide the processor 170 with hardware, software and data resources including management of computing and processing equipment, and support control software and applications. It is also used for the storage of multimedia files, and the storage of running programs and applications.

[0079] The processor 170 is the control center of the terminal 100. It uses various interfaces and lines to connect various parts of the entire terminal 100. By running or executing instructions stored in the memory 120 and calling data stored in the memory 120, it executes various functions of the terminal 100 and processes data, thereby controlling the terminal device as a whole. Optionally, the processor 170 may include one or more processing units; preferably, the processor 170 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application program, and the modem processor mainly processes wireless communication. It is understandable that the above-mentioned modem processor may not be integrated into the processor 170. In some embodiments, the processor and the memory may be implemented on a single chip, and in some embodiments, they may also be implemented separately on separate chips. The processor 170 may also be used to generate corresponding operation control signals, send them to corresponding components of the computing and processing device, read and process data in the software, especially read and process data and programs in the memory 120, so that each functional module therein performs corresponding functions, thereby controlling the corresponding components to act according to the requirements of the instructions.

[0080] Among them, the memory 120 can be used to store method-related software codes, the processor 170 can execute the steps of an image processing method provided in the present application, and can also schedule other units (such as the above-mentioned input unit 130 and display unit 140) to implement corresponding functions.

[0081] The radio frequency unit 110 (optional) can be used for receiving and sending information or receiving and sending signals during a call, for example, after receiving the downlink information of the base station, it is sent to the processor 170 for processing; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (Low Noise Amplifier, LNA), a duplexer, etc. In addition, the radio frequency unit 110 can also communicate with network devices and other devices through wireless communication. The wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile communication (Global System of Mobile communication, GSM), General Packet Radio Service (General Packet Radio Service, GPRS), Code Division Multiple Access (Code Division Multiple Access, CDMA), Wideband Code Division Multiple Access (Wideband Code Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution, LTE), email, Short Messaging Service (SMS), etc.

[0082] In this embodiment of the present application, the RF unit 110 can send data to the server 200 and receive processing results sent by the server 200.

[0083] It should be understood that the radio frequency unit 110 is optional and can be replaced by other communication interfaces, such as a network port.

[0084] The terminal 100 also includes a power supply 190 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 170 through a power management system, so that the power management system can manage functions such as charging, discharging, and power consumption.

[0085] The terminal 100 further includes an external interface 180 , which may be a standard Micro USB interface or a multi-pin connector, and may be used to connect the terminal 100 to communicate with other devices, or to connect a charger to charge the terminal 100 .

[0086] Although not shown, the terminal 100 may also include a flashlight, a wireless fidelity (WiFi) module, a Bluetooth module, sensors with different functions, etc., which are not described in detail here. Some or all of the methods described below may be applied in the following embodiments. Figure 2 In the terminal 100 shown.

[0087] Next describe Figure 1 The product form of the server 200;

[0088] Figure 3 A structural diagram of a server 200 is provided, such as Figure 3 As shown, the server 200 includes a bus 201, a processor 202, a communication interface 203, and a memory 204. The processor 202, the memory 204, and the communication interface 203 communicate with each other via the bus 201.

[0089] The bus 201 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0090] The processor 202 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0091] The memory 204 may include a volatile memory, such as a random access memory (RAM). The memory 204 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard drive (HDD), or a solid state drive (SSD).

[0092] Among them, the memory 204 can be used to store software codes related to an image processing method provided in the present application, and the processor 202 can execute the steps of the image processing method of the chip, and can also schedule other units to realize corresponding functions.

[0093] It should be understood that the above-mentioned terminal 100 and server 200 can be centralized or distributed devices, and the processors in the above-mentioned terminal 100 and server 200 (such as processor 170 and processor 202) can be hardware circuits (such as application specific integrated circuit (ASIC), field-programmable gate array (FPGA), general-purpose processor, digital signal processor (DSP), microprocessor or microcontroller, etc.), or a combination of these hardware circuits. For example, the processor can be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.

[0094] The first aspect of the present application provides an image processing method, such as Figure 4 As shown, including:

[0095] S401: Based on the collected attribute information and historical search records of the target user, determine the name of the character of interest to the target user, and obtain stills and stills descriptions that satisfy a preset correspondence relationship with the name of the character of interest.

[0096] It should be noted that, in actual application scenarios, the above attribute information may be information that characterizes the preference characteristics of the target user, including but not limited to gender, age, preference tags, etc.

[0097] It should be noted that, in actual application scenarios, the above historical search records can be search contents actively input by the target user in the historical period. Since the historical search records are the contents actively input by the target user, they represent the user's attention and preference for the information. Therefore, this application determines the names of the roles of interest to the target user based on the collected attribute information and historical search records of the target user, thereby ensuring that the names of the roles of interest obtained are the names of roles of high interest to the target user.

[0098] It should be noted that, in actual application scenarios, the above-mentioned preset correspondence relationship can be a screening condition for screening stills in the series that include the name of the character of interest in the character list. Since the character corresponding to a character name of interest may appear in the character list of multiple series, but the on-demand volume of different series varies, the user's interest in the character of the character name of interest in different series varies. Therefore, the present application obtains stills that meet the preset correspondence relationship with the name of the character of interest through configuration, thereby screening out the stills that the target user is most interested in, thereby increasing the user's attention to viewing the animated character images generated based on the stills.

[0099] In a possible implementation, the stills description may be a description text pre-generated by operation and maintenance personnel based on the stills, and the description text records various types of features of the characters in the stills, including but not limited to: expressions, clothing, actions, etc.

[0100] S402: Import the stills and still descriptions into a preset character animation generation model to obtain an animated character image corresponding to the name of the character of interest.

[0101] It should be noted that in actual application scenarios, the above-mentioned preset character animation generation model can be a model built based on generative artificial intelligence (AIGC). AIGC is a technology that generates relevant content with appropriate generalization capabilities through learning and recognition of existing data based on artificial intelligence technologies such as generative adversarial networks and large pre-trained models.

[0102] It should be noted that, in actual application scenarios, the above-mentioned animated character image can be a dynamic image generated by the above-mentioned preset character dynamic image generation model. Due to the masking effect of human vision and the physiological basis of the human visual system, the human visual system is more sensitive to moving images than static images. Therefore, by configuring the above-mentioned animated character image, the present application increases the probability that the animated character image is viewed by the target user.

[0103] In a possible implementation, the above-mentioned animated character image can be a cartoon image with the character features in the stills description, or a realistic image generated according to the character features in the stills description. Since the above-mentioned stills description is a description of the stills that satisfies a preset correspondence with the name of the character that the target user is interested in, the present application increases the probability of the animated character image being viewed by the target user by configuring the animated character image generated based on the stills and the stills description to be an image that the target user is interested in.

[0104] S403: Display the animated character image in the display area of ​​the patch advertisement.

[0105] It should be noted that, in actual application scenarios, since the above-mentioned animated character images are generated based on stills and stills descriptions that satisfy a preset correspondence relationship with the names of the characters that the target user is interested in, the target user will be interested in the animated character images, which increases the probability that the animated character images will be viewed by the target user. However, this application configures the display of the animated character images in the display area of ​​the patch advertisement to increase the probability that the user views the content of the display area of ​​the patch advertisement when viewing the animated character images, thereby increasing the user's click-through rate on the patch advertisement.

[0106] It should be noted that in actual application scenarios, the above Figure 1 Step S403 shown in FIG. Figure 1 The steps S401 and S402 shown may be implemented in different scenarios, and there may be many specific implementations, and an exemplary implementation is provided here:

[0107] like Figure 5 As shown, it is a flowchart of an image processing method, and the specific operation steps are as follows:

[0108] Step A1: When it is detected that the target user is in a logged-in state, the attribute information and historical search records of the target user are collected, and step A2 is triggered.

[0109] Step A2, based on the target user's attribute information and historical search records, determine the name of the character that the target user is interested in, and obtain stills and stills descriptions that meet a preset correspondence relationship with the name of the character that the target user is interested in, and trigger step A3.

[0110] Step A3, importing stills and stills descriptions into a preset character animation generation model, obtaining an animated character image corresponding to the name of the character of interest, and after establishing a corresponding relationship between the animated character image and the target user, storing the animated character image and the corresponding relationship, and triggering step A4.

[0111] Step A4, when it is detected that the target user is in a playback state, the display area of ​​the patch advertisement on the playback interface is obtained, and an animated character image corresponding to the target user is retrieved and displayed in the display area.

[0112] The step A4 can detect whether the target user is in the playback state by detecting whether a video playback request of the target user is received. The step A4 can obtain the display area of ​​the patch advertisement in the playback interface by accessing the background advertisement service system to query the position parameters of the display area in the playback interface.

[0113] This application determines the name of the character of interest to the target user by collecting the target user's attribute information and historical search records, and obtains stills and stills descriptions that satisfy a preset correspondence relationship with the name of the character of interest. Then, by importing the stills and stills descriptions into a preset character animation generation model, an animated character image corresponding to the name of the character of interest is obtained, and the animated character image is displayed in the display area of ​​the patch advertisement. Since the animated character image is generated based on the stills and stills descriptions corresponding to the name of the character of interest to the target user, the probability of the target user viewing the animated character image is increased. By displaying the animated character image in the display area of ​​the patch advertisement, the probability of the user viewing the content of the patch advertisement when viewing the animated character image is increased, thereby increasing the user's click-through rate on the patch advertisement. It can be seen that this application increases the user's click-through rate on the patch advertisement.

[0114] In a possible implementation, the training process of the preset character animation generation model includes:

[0115] Obtain stills information of multiple characters, including stills of the characters and stills descriptions;

[0116] Constructing an initial character animation generation model including an initial image generation model and a preset aesthetic evaluation model, wherein the output of the image generation model is the input of the preset aesthetic evaluation model;

[0117] The initial image generation model in the initial character animation generation model is trained using the stills information of each character as training data, the quality of the image output by the initial image generation model based on the training data is evaluated using a preset aesthetic evaluation model, and the model parameters of the initial image generation model are adjusted based on the result of the quality evaluation to obtain a preset character animation generation model. The input of the preset character animation generation model is the stills and stills description corresponding to the name of the character of interest, and the output is the animated character image corresponding to the name of the character of interest.

[0118] It should be noted that, in actual application scenarios, the above-mentioned initial image generation model can be an image generation model built based on AIGC. During the training process, the input data of the initial character animation generation model is the stills information of each character, and the output is the animation character image corresponding to each character.

[0119] It should be noted that, in actual application scenarios, the above-mentioned preset aesthetic evaluation model is a model for evaluating the quality of the animated character images output by the initial image generation model during the training process. Since the internal parameters of the above-mentioned initial image generation model before the completion of training are not optimal parameters, the quality of the animated character images output by the initial image generation model during the training process will be uneven. In order to improve the quality of the animated character images output by the initial image generation model so that the target user can accurately identify the characters of interest corresponding to the animated character images, this application evaluates the quality of the images output by the initial image generation model by configuring a preset aesthetic evaluation model, and adjusts the model parameters of the initial image generation model based on the evaluation results, thereby determining the optimal parameters of the initial image generation model, and then improving the quality of the animated character images output by the preset character animation generation model.

[0120] It can be understood by those skilled in the art that, in actual application scenarios, the above-mentioned preset aesthetic evaluation model can be a model constructed based on an aesthetic scorer (simulacra-aesthetic-models). The training process of the above-mentioned preset aesthetic evaluation model can be: adding labels with different contents to dynamic images of different qualities, the label content is the aesthetic score of the dynamic image, obtaining training data, using the training data to train the initial aesthetic evaluation model, and adjusting the parameters based on the output aesthetic score and the aesthetic score in the label to obtain the above-mentioned preset aesthetic evaluation model. After the training is completed, the input of the above-mentioned preset aesthetic evaluation model can be an animated character image, and the output is an evaluation result with the content of the aesthetic score of the animated character image. This application does not make too many restrictions and redundant descriptions on the specific construction process of the above-mentioned preset aesthetic evaluation model.

[0121] In a possible implementation, displaying the animated character image in the display area of ​​the patch advertisement includes:

[0122] Scale the animated character image according to the size parameters of the display area;

[0123] The scaled animated character image is displayed at a preset display position in the display area so that the pointing action of the animated character image points to the click area of ​​the patch advertisement, wherein the preset display position is an area in the display area adjacent to the click area and not overlapping with the patch advertisement.

[0124] It should be noted that in actual application scenarios, due to the differences in the display area sizes of different patch ads in the page, the size of the animated character image output by the above-mentioned preset character animation generation model is relatively fixed. When the gap between the size of the animated character image and the size of the display area is too large, there is a risk that the animated character image will block the content of the display area, or the animated character image will not be obvious in the display area, thereby affecting the target user's viewing probability of the patch ad content. Therefore, the present application configures the scaling of the animated character image according to the size parameters of the display area, thereby avoiding the risk that the animated character image blocks the content of the display area, or the animated character image is not obvious in the display area, and increases the user's viewing probability of the animated character image and the patch ad content, thereby increasing the click-through rate of the patch ad.

[0125] It should be noted that in actual application scenarios, in order to avoid users from frequently entering the ad details page due to accidental touches, existing patch ads usually demarcate an area in the display area as a click area, and only when the user clicks on the click area will the display operation of the ad details page be triggered. However, due to the unclear click area and the complicated content of the ad, the user is unable to accurately find and click on the above-mentioned click area, thereby reducing the click-through rate of the patch ad. Therefore, the present application configures a preset display position in the display area that is adjacent to the click area and does not overlap with the patch ad, and displays the scaled animated character image at the preset display position in the display area, so that the pointing action of the animated character image points to the click area of ​​the patch ad, thereby guiding the user to accurately find the click area through the pointing action of the animated character image, thereby improving the click-through rate of the patch ad.

[0126] It should be noted that, in actual application scenarios, the above-mentioned pointing action direction is set by the action instruction parameters in the preset character animation generation model, such as the prompt word (PROMPT) in AIGC. Specifically:

[0127] like Figure 6 As shown in FIG. 1 , it is a schematic diagram of displaying an animated character image in the display area of ​​a patch advertisement. Assume that all patch advertisements and their click areas on the target platform are located at Figure 6 To prevent the animated character image from blocking the patch ad, the preset display position is set to Figure 6 In order to utilize the prompt click area of ​​the animated character image, the prompt words in the preset character animation generation model are configured in advance so that the pointing action of each generated animated character image points to the upper right and swings within the range of angle A and angle B.

[0128] It should be noted that, in an actual application scenario, the implementation method of displaying the scaled animated character image at a preset display position in the display area may be:

[0129] After determining the preset display position based on the display area and click area of ​​the patch advertisement, a container is configured for the preset display position in the page code (HyperText Mark-up Language, HTML), and the data source address in the container is defined as the storage location of the animated character image corresponding to the target user. When it is detected that the target user loads the page, the container extracts the animated character image from the storage location corresponding to the target user and displays it.

[0130] In a possible implementation, based on the collected attribute information and historical search records of the target user, determining the name of the role of interest of the target user includes:

[0131] Filtering the series type and character list of at least one series whose click rate is not less than a preset click rate threshold from the historical search records;

[0132] The attribute information, the drama type, and the character list are input into a preset filtering algorithm, and the character names output by the preset filtering algorithm are determined as the names of the characters of interest to the target user.

[0133] Those skilled in the art can understand that, in actual application scenarios, there can be multiple types of the above-mentioned preset filtering algorithms, including but not limited to: collaborative filtering (CF) algorithm, content filtering (CBF) algorithm, deep neural network (DNN), etc. This application does not make too many restrictions and redundant descriptions on the specific construction process of the above-mentioned preset filtering algorithm.

[0134] It should be noted that in actual application scenarios, for a target user who does not have a historical search record, such as a new user or an old user who does not retain a search record, the implementation method for determining the name of the target user's interested role may include the following: Figure 7 Steps B1 to B3 shown:

[0135] Step B1, determining multiple user types based on existing user attribute information, and constructing sets of interested role names corresponding to different user types based on the existing user attribute information and historical search information;

[0136] Step B2, determining the target user type to which the target user belongs based on the attribute information of the target user for which there is no historical search record and the matching degree of each user type;

[0137] Step B3: Filter the most frequently used role name from the set of role names of interest corresponding to the target user type, and determine it as the role name of interest for the target user.

[0138] It should be noted that in actual application scenarios, in order to avoid the risk of reduced display efficiency of the animated character image due to image generation delay, the above-mentioned method of obtaining the animated character image corresponding to the name of the character of interest can also be:

[0139] like Figure 8 As shown in FIG. 1 , it is a flowchart for obtaining an animated character image corresponding to the name of the character of interest, and the specific operation steps are as follows:

[0140] Step C1, determining multiple user types based on the attribute information of each test user, constructing sets of interested role names corresponding to different user types based on the attribute information and historical search information of each test user, and triggering step C2.

[0141] Step C2, based on the stills and still descriptions with preset corresponding relationships between the names of the characters of interest in the set of names of the characters of interest, generate the corresponding animated character images for each name of interest, and based on the corresponding relationships between the animated character images, the names of the characters of interest and the user types, construct a set of animated character images, and trigger step C3.

[0142] Step C3, determining the target user type to which the target user belongs according to the matching degree between the attribute information of the target user and each user type, and triggering step C4.

[0143] Step C4, determining the names of interest to the target user according to the attribute information and historical search records of the target user, and triggering step C5.

[0144] Step C5, determining whether there is an interested name in the set of interested role names corresponding to the target user type whose matching degree with the interested name of the target user is greater than a preset threshold. If yes, step C6 is triggered, if no, step C7 is triggered.

[0145] Step C6, according to the correspondence between the names of interest and the animated character images, the animated character images corresponding to the names of interest with a matching degree greater than a preset threshold in the animated character image set are determined as the animated character images corresponding to the names of interest of the target user.

[0146] Step C7, taking the animated character image corresponding to the name of interest with the highest call rate in the set of names of interest corresponding to the target user type in the animated character image set, and determining it as the animated character image corresponding to the name of interest of the target user.

[0147] This application is passed by the above Figure 8The configuration shown optimizes the system response speed and realizes rapid response and display of corresponding animated character images when the target user initiates a playback request in real time, thereby enhancing the user experience.

[0148] In a possible implementation, the training process of the preset filtering algorithm includes:

[0149] Collect test data of multiple different test users as initial training data, the initial training data includes: attribute information of the test users, the types of dramas they are interested in, and a list of characters;

[0150] Add different weight labels to the names of the roles in the role list in the initial training data to obtain training data;

[0151] The initial filtering algorithm is trained using the training data to obtain a preset filtering algorithm, the input of the preset filtering algorithm is the attribute information, the drama type and the character list, and the output is the name of the character of interest.

[0152] In a possible implementation, obtaining stills and stills descriptions that satisfy a preset correspondence relationship with the name of the character of interest includes:

[0153] Obtain the name of the drama that includes the name of the character of interest in the character list and whose play rate is not less than a preset threshold;

[0154] Stills and still descriptions corresponding to the names of the characters of interest are extracted from a database corresponding to the names of the series.

[0155] It should be noted that in actual application scenarios, since users pay close attention to the names of the characters of interest, the probability that users are interested in the series that contains the names of the characters of interest in the character list is high. The higher the play rate is, the higher the promotion of the series is, and the higher the probability that the target user pays attention to the series is. Therefore, this application configures the content as the series name of the series that includes the names of the characters of interest in the character list and whose play rate is not less than the preset threshold as the above-mentioned preset correspondence, thereby increasing the probability that the target user is interested in the characters in the stills that meet the preset correspondence with the names of the characters of interest, thereby increasing the probability that the target user views the animated character images generated based on the stills and the descriptions of the stills, thereby increasing the click-through rate of the patch advertisements.

[0156] A second aspect of the present application provides an image processing system, such as Fig. 9 As shown, including:

[0157] The data acquisition module 901 is used to determine the name of the character of interest to the target user based on the collected attribute information and historical search records of the target user, and obtain stills and stills descriptions that satisfy a preset correspondence relationship with the name of the character of interest;

[0158] An image generation module 902 is used to import stills and stills descriptions into a preset character animation generation model to obtain an animated character image corresponding to the name of the character of interest;

[0159] The image display module 903 is used to display the animation character image in the display area of ​​the patch advertisement.

[0160] In one possible implementation, the above Fig. 9 The image processing system shown also includes a model training module, and the model training module is set to:

[0161] Obtain stills information of multiple characters, including stills of the characters and stills descriptions;

[0162] Constructing an initial character animation generation model including an initial image generation model and a preset aesthetic evaluation model, wherein the output of the image generation model is the input of the preset aesthetic evaluation model;

[0163] The initial image generation model in the initial character animation generation model is trained using the stills information of each character as training data, the quality of the image output by the initial image generation model based on the training data is evaluated using a preset aesthetic evaluation model, and the model parameters of the initial image generation model are adjusted based on the result of the quality evaluation to obtain a preset character animation generation model. The input of the preset character animation generation model is the stills and stills description corresponding to the name of the character of interest, and the output is the animated character image corresponding to the name of the character of interest.

[0164] In a possible implementation, the image display module 903 is configured to:

[0165] Scale the animated character image according to the size parameters of the display area;

[0166] The scaled animated character image is displayed at a preset display position in the display area so that the pointing action of the animated character image points to the click area of ​​the patch advertisement, wherein the preset display position is an area in the display area adjacent to the click area and not overlapping with the patch advertisement.

[0167] In a possible implementation, the data acquisition module 901 is set to:

[0168] Filtering the series type and character list of at least one series whose click rate is not less than a preset click rate threshold from the historical search records;

[0169] The attribute information, the drama type, and the character list are input into a preset filtering algorithm, and the character names output by the preset filtering algorithm are determined as the names of the characters of interest to the target user.

[0170] In a possible implementation, the data acquisition module 901 further includes a model training submodule, and the model training submodule is set to:

[0171] Collect test data of multiple different test users as initial training data, the initial training data includes: attribute information of the test users, the types of dramas they are interested in, and a list of characters;

[0172] Add different weight labels to the names of the roles in the role list in the initial training data to obtain training data;

[0173] The initial filtering algorithm is trained using the training data to obtain a preset filtering algorithm, the input of the preset filtering algorithm is the attribute information, the drama type and the character list, and the output is the name of the character of interest.

[0174] In a possible implementation, the data acquisition module 901 is configured to:

[0175] Obtain the name of the drama that includes the name of the character of interest in the character list and whose play rate is not less than a preset threshold;

[0176] Stills and still descriptions corresponding to the names of the characters of interest are extracted from a database corresponding to the names of the series.

[0177] A third aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the image processing method of the first aspect or any implementation of the first aspect.

[0178] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0179] The memory is used to store computer programs;

[0180] The processor is used to execute a computer program so that the electronic device can implement the image processing method of the first aspect or any implementation manner of the first aspect.

[0181] In a possible implementation, the structural diagram of the electronic device provided in the fourth aspect of the present application is as follows: Fig.10The electronic devices in the embodiments of the present application may include but are not limited to fixed terminals such as mobile phones, notebook computers, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, and the like. Fig.10 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0182] like Fig.10 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1008 to a random access memory (RAM) 1003. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 1003. The processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0183] Typically, the following devices may be connected to the I / O interface 1005: input devices 1006 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 1007 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1008 including, for example, a memory card, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Fig.10 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0184] A fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the image processing method of the first aspect or any implementation of the first aspect.

[0185] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0186] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0187] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0188] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. An image processing method, characterized in that: include: Based on the collected attribute information and historical search records of the target user, determine the name of the character of interest to the target user, and obtain stills and stills descriptions that satisfy a preset correspondence relationship with the name of the character of interest; Importing the stills and the still descriptions into a preset character animation generation model to obtain an animated character image corresponding to the name of the character of interest; The animated character image is displayed in a display area of ​​the patch advertisement.

2. The image processing method according to claim 1, characterized in that: The training process of the preset character dynamic image generation model includes: Obtaining stills information of a plurality of characters, wherein the stills information includes stills of the characters and stills descriptions; Constructing an initial character animation generation model including an initial image generation model and a preset aesthetic evaluation model, wherein the output of the image generation model is the input of the preset aesthetic evaluation model; The initial image generation model in the initial character animation generation model is trained using the stills information of each of the characters as training data, the quality of the image output by the initial image generation model based on the training data is evaluated using the preset aesthetic evaluation model, and the model parameters of the initial image generation model are adjusted based on the result of the quality evaluation to obtain the preset character animation generation model, wherein the input of the preset character animation generation model is the stills and stills description corresponding to the name of the character of interest, and the output is the animated character image corresponding to the name of the character of interest.

3. The image processing method according to claim 1, characterized in that: The step of displaying the animated character image in the display area of ​​the patch advertisement includes: Scaling the animation character image according to the size parameter of the display area; The scaled animated character image is displayed at a preset display position in the display area so that the pointing action of the animated character image points to a click area of ​​the patch advertisement, wherein the preset display position is an area in the display area that is adjacent to the click area and does not overlap with the patch advertisement.

4. The image processing method according to claim 1, characterized in that: The determining the name of the role of interest to the target user based on the collected attribute information and historical search records of the target user includes: Filtering the series type and character list of at least one series whose click rate is not less than a preset click rate threshold from the historical search records; The attribute information, the drama type and the character list are input into a preset filtering algorithm, and the character names output by the preset filtering algorithm are determined as the character names of interest to the target user.

5. The image processing method according to claim 4, characterized in that: The training process of the preset filtering algorithm includes: Collecting test data of multiple different test users as initial training data, the initial training data including: attribute information of the test users, the types of dramas they are interested in, and a list of characters; Adding different weight labels to the names of the roles in the role list in the initial training data to obtain training data; The initial filtering algorithm is trained using each of the training data to obtain the preset filtering algorithm, wherein the input of the preset filtering algorithm is the attribute information, the drama type and the character list, and the output is the name of the character of interest.

6. The image processing method according to claim 1, characterized in that: The step of obtaining stills and stills descriptions that satisfy a preset correspondence relationship with the name of the character of interest includes: Obtaining the title of an episode in the character list that includes the name of the character of interest and whose play rate is not less than a preset threshold; The stills and still descriptions corresponding to the name of the character of interest are extracted from a database corresponding to the name of the series.

7. An image processing device, characterized in that: include: A data acquisition module, for determining the name of the character of interest to the target user based on the collected attribute information and historical search records of the target user, and obtaining stills and stills descriptions that satisfy a preset correspondence relationship with the name of the character of interest; An image generation module, used for importing the stills and the still descriptions into a preset character animation generation model to obtain an animated character image corresponding to the name of the character of interest; The image display module is used to display the image of the animated character in the display area of ​​the patch advertisement.

8. A computer program product, characterized in that The method comprises computer-readable instructions, and when the computer-readable instructions are executed on an electronic device, the electronic device implements the image processing method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the image processing method according to any one of claims 1 to 6.

10. A computer storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the image processing method as described in any one of claims 1 to 6.

Images