CN107622473B - Image rendering method, device, terminal and computer readable storage medium - Google Patents

Abstract

The application discloses an image rendering method, an image rendering device, a terminal and a computer readable storage medium. The method comprises the following steps: acquiring a target rendering mode of a target image according to a machine learning model, wherein the target image is an image obtained by a photographing function; rendering the target image according to the target rendering mode; and outputting the rendered target image. According to the image rendering method provided by the embodiment of the application, firstly, a target rendering mode of a target image is obtained according to a machine learning model, and the target image is obtained by a photographing function; then rendering the target image according to the target rendering mode; and finally, outputting the rendered target image, so that the rendering efficiency of the rendering function can be improved, and the utilization rate of the rendering function can be improved.

Description

Image rendering method, device, terminal, and computer-readable storage medium

technical field

The embodiments of the present application relate to electronic device application technologies, and in particular, to an image rendering method, apparatus, terminal, and computer-readable storage medium.

Background technique

With the development of smart terminals, the camera function on the smart terminals is widely used by users. At present, the camera's photographing function is embedded with a rendering function. The rendering function is used to adjust the warm color of the picture, so as to make the photo appear retro, black and white, nostalgic and so on. The rendering function of the picture in the related art is manually selected by the user, that is, the user selects the desired rendering tone. However, for new users, they do not know the photo styles corresponding to the rendering functions with different names, and even after multiple tests to try different styles of rendering, they still cannot find a suitable rendering method. The rendering function will be abandoned, resulting in low utilization of the rendering function.

SUMMARY OF THE INVENTION

The present application provides an image rendering method, device, terminal and computer-readable storage medium, which can improve the rendering efficiency of the rendering function and the utilization rate of the rendering function.

In a first aspect, an embodiment of the present application provides an image rendering method, including:

A target rendering method for obtaining a target image according to the machine learning model, where the target image is an image obtained by a photographing function;

rendering the target image according to the target rendering mode;

Output the rendered target image.

In a second aspect, an embodiment of the present application further provides an image rendering apparatus, including:

A machine learning module, configured to obtain a target rendering method of a target image according to the machine learning model, where the target image is an image obtained by a photographing function;

a rendering module, configured to render the target image according to the target rendering mode obtained by the machine learning module;

The output module is configured to output the target image rendered by the rendering module.

In a third aspect, an embodiment of the present application further provides a terminal, where the terminal includes:

one or more processors;

storage means for storing one or more programs,

A data transceiver for data interaction with the server;

When the one or more programs are executed by the one or more processors, the one or more processors implement the image rendering method shown in the first aspect.

In a fourth aspect, embodiments of the present application further provide a computer-readable storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the image rendering method shown in the first aspect is implemented.

In the image rendering method provided by the embodiment of the present application, first, a target rendering method of a target image is obtained according to a machine learning model, and the target image is an image obtained by a photographing function; then the target image is rendered according to the target rendering method; finally Outputting the rendered target image can improve the rendering efficiency of the rendering function and improve the utilization rate of the rendering function.

Description of drawings

1 is a flowchart of an image rendering method in an embodiment of the present application;

2 is a flowchart of another image rendering method in the embodiment of the present application;

3 is a flowchart of another image rendering method in an embodiment of the present application;

4 is a flowchart of another image rendering method in the embodiment of the present application;

5 is a flowchart of another image rendering method in an embodiment of the present application;

6 is a schematic structural diagram of an image rendering apparatus in an embodiment of the present application;

7 is a schematic structural diagram of another image rendering apparatus in an embodiment of the present application;

FIG. 8 is a schematic structural diagram of a terminal in an embodiment of the present application.

Detailed ways

The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the convenience of description, the drawings only show some but not all the structures related to the present application.

At present, the camera function or the image processing application in the terminal can render the image, but which rendering mode to render the image needs to be manually selected by the user. However, users usually do not know the most suitable rendering method for the current scene, so users need to try different rendering methods many times, which is time-consuming and labor-intensive. Or users only use one rendering method that they are used to, and then ignore other better rendering methods. The present application provides an automatic image rendering method combined with machine learning, which provides suitable image rendering for users, and improves the rendering efficiency of the rendering function and the utilization rate of the image rendering function.

FIG. 1 is a flowchart of an image rendering method provided by an embodiment of the present application. The method is applied to a terminal, and the terminal may be an electronic device with a photographing function or an image processing function, such as a smart phone, a wearable device, a tablet computer, and a notebook computer. equipment. This method is suitable for rendering images obtained by taking pictures, and specifically includes the following steps:

Step 110: Obtain the target rendering mode of the target image according to the machine learning model.

Wherein, the target image is the image obtained by the photographing function. Optionally, when the user inputs a photographing instruction, the terminal generates a target image, and when obtaining the target image, obtains a target rendering mode of the target image according to a machine learning model. Optionally, after generating the target image according to the photographing instruction input by the user, the target image is stored in the album. When a user browses images in an album or browses images using other image processing applications that include an image rendering function, a rendering operation can be performed on the images. When the user starts the rendering function, the target rendering mode of the target image is obtained according to the machine learning model.

Machine learning models can choose Artificial Neural Networks (ANNs). The way the images are rendered by multiple users can be obtained first, and then the artificial neural network can be optimized through machine learning.

In an implementation manner, image analysis is performed on the target image to obtain attribute information of the target image. The attribute information of the target image and the rendering method selected by the user are input into the artificial neural network. The attribute information may include one or more of the following information: image orientation, image color temperature, image brightness, image pixels, or image main body. When rendering the target image, image analysis is performed on the target image to obtain the attribute information of the target image, and then the attribute information of the target image is input into the obtained artificial neural network to obtain the target rendering method corresponding to the attribute information of the target image.

Step 120: Render the target image according to the target rendering mode.

Rendering styles include monochrome, tone, black and white, faded, chrome, print, age, or nostalgia, each of which is used to adjust the color, saturation, and color temperature of the target image.

Step 130: Output the rendered target image.

Optionally, when the target image is obtained by taking a photo, the image is rendered, and the rendered target image is displayed to the user. Optionally, when the target image is obtained by taking a photo, the image is rendered, and the rendered image is stored. When the user browses the target image through the album, the rendered target image is displayed.

Further, after step 130, the method further includes: receiving feedback information on the target image from the user; and adjusting the machine learning model according to the feedback information.

After the rendered target image is displayed, feedback information on the rendering result from the user is received. Feedback information can be save, delete or change the rendering method. The feedback information is input into the machine learning model, and the machine learning model can adjust the determination strategy of the rendering method according to the input feedback information.

In the image rendering method provided in this embodiment, a target rendering method of a target image is obtained according to a machine learning model, and the target image is an image obtained by a photographing function; the target image is rendered according to the target rendering method; and the rendered target image is output. Since machine learning can determine the target rendering method of the target image according to the historical rendering methods of the current user or other users, users can avoid blindly trying multiple rendering methods, and improve the rendering efficiency of the rendering function and the utilization rate of the image rendering function.

FIG. 2 is a flowchart of an image rendering method provided by an embodiment of the present application. As a further description of the above-mentioned embodiment, the method includes:

Step 210: Acquire the first position information of the plurality of first users when the first images are taken and the rendering mode of the first images.

Wherein, the first user includes the current user or other users other than the current user. The first image is any image obtained by the first user taking a photo. When the first image is obtained according to the photographing instruction input by the user, the first position information corresponding to the first image is obtained. The first location information may be coordinate information obtained through a global positioning system (Global Positioning System, GPS). Alternatively, the first location information may also be the identifier of the current scenic spot or the identifier of the current shop. The correspondence between the first position information and the first image is recorded when the first user provides feedback on the rendering mode of the first image.

Further, it is determined whether there is a character feature area in the first image. If there is a character feature area in the first image, perform machine learning on the first position information and rendering methods corresponding to the plurality of first users to obtain a first machine learning model. If there is no character feature area in the first image, the machine learning of the first location information and rendering mode corresponding to the first user is canceled.

It is judged whether there is a face area or a person body area in the first image, and if so, there is a person feature area in the first image. A first machine learning model is obtained by performing machine learning on the rendering mode of the picture with the character feature area, so that the first machine learning model can perform more accurate rendering recommendation for the character image.

Step 220: Perform machine learning on the first location information and rendering modes corresponding to the plurality of first users to obtain a first machine learning model.

The first user may be any other user, or may be another user whose attributes are similar to the current user. User attributes include any of age, gender, or interests. Perform machine learning on the first position information and rendering mode corresponding to the first user, and the obtained first machine learning model can determine an appropriate rendering mode according to the position information.

In a usage scenario, when a user takes a photo at a certain scenic spot, different styles of rendering need to be performed for different scenic spots. For example, when taking a photo with a distant mountain peak, use rendering method A; when taking pictures of a cultural relic or collection, use rendering method B. Therefore, usually the sights that can be seen from one location in the scenic spot are unique, so the rendering method used for that location is also unique. Through the rendering mode selected by the first user at the same position, the rendering mode corresponding to the position can be determined.

Step 230: Obtain current position information, and substitute the current position information into the first machine learning model to obtain a target rendering mode corresponding to the current position.

When the current user triggers the photographing instruction, the current location information is obtained. The current position information is input (also referred to as substitution) into the first machine learning model to obtain the target rendering mode corresponding to the current position information.

Step 240: Render the target image according to the target rendering mode.

Step 240 is the same as step 120, and the description of step 120 can be referred to.

Step 250: Output the rendered target image.

Step 250 is the same as step 130, and the description of step 130 can be referred to.

The image rendering method provided in this embodiment can determine a target rendering mode suitable for the current position according to the user's position, and render the target image according to the target rendering mode, so as to realize the determination of the rendering mode according to the user's position and the machine learning model, so that the rendering mode is more Accurate and improve rendering efficiency.

FIG. 3 is a flowchart of an image rendering method provided by an embodiment of the present application. As a further description of the above-mentioned embodiment, the method includes:

Step 310: Acquire the first position information of the plurality of first users when shooting the first image and the rendering mode of the first image.

Step 320: Acquire the photographing time of the plurality of first users when photographing the first image.

The photographing time includes a photographing time period or a specific time of photographing. The photo time period can be morning, afternoon or evening. The specific time of taking a photo is year-month-day-hour-minute-second. The specific time of the photographing time can be obtained through the system clock. Determine the shooting time period according to the specific time.

Step 330: Perform machine learning on the first location information, the photographing time, and the rendering method corresponding to the plurality of first users to obtain a second machine learning model.

The second machine learning model can determine an appropriate rendering method according to the photographing position and the photographing time. For example, for the same scenic spot, you need to use rendering method A when shooting in the morning, and you need to use rendering mode B when shooting in the afternoon.

Step 340: Obtain current location information and current time information, and substitute the current location information and current time information into the second machine learning model to obtain a target rendering mode corresponding to the current location and current time information.

Get current location and current time information via GPS and system clock. Then, the target rendering mode corresponding to the current position information and the current time information is obtained by using the obtained second machine learning model.

Step 350: Render the target image according to the target rendering mode.

Step 350 is the same as step 120, and the description of step 120 can be referred to.

Step 360: Output the rendered target image.

Step 360 is the same as step 130 , and the description of step 130 may be referred to.

The image rendering method provided in this embodiment can combine the shooting position and the shooting time to generate a second machine learning model. When the user takes a photo, the target rendering mode applicable to the current time and the current position is determined according to the second machine learning model, and the target image is rendered according to the target rendering mode, so that the rendering mode is more accurate and the rendering efficiency is improved.

FIG. 4 is a flowchart of an image rendering method provided by an embodiment of the present application. As a further description of the foregoing embodiment, the method includes:

Step 410: Acquire position information of a plurality of first users when shooting the first image and the rendering mode of the first image.

Step 420: Acquire the weather information of the plurality of first users when the first images are taken.

Weather information can be obtained through a weather application or a weather server on the network side. The weather information includes temperature information, sunshine information or wind information. Temperature information includes maximum temperature, minimum temperature, and real-time temperature. The sunshine information includes sunrise time, sunset time, and sunshine intensity. The wind information includes wind direction information and wind strength information. Weather information also includes cloudy, sunny, cloudy, showers, light rain, moderate rain, heavy rain, etc.

Step 430: Perform machine learning on the first location information, weather information, and rendering methods corresponding to the plurality of first users to obtain a third machine learning model.

The third machine learning model can determine an appropriate rendering method according to the photographing location and photographing weather. Further, the location information, weather information, time information and rendering method may also be input into the machine learning model to obtain a third machine learning model. The third machine learning model can determine an appropriate rendering method based on the photographing time, the photographing location, and the weather information at the time of photographing.

Step 440: Obtain the current location information and the current weather information, and substitute the current location information and the current weather information into the third machine learning model to obtain the target rendering mode corresponding to the current location and the current weather information.

Step 450: Render the target image according to the target rendering mode.

Step 450 is the same as step 120, and the description of step 120 can be referred to.

Step 460: Output the rendered target image.

Step 460 is the same as step 130, and the description of step 130 can be referred to.

The image rendering method provided in this embodiment can determine a third machine learning model according to weather information and location information. When the user takes a photo, the target rendering method applicable to the current weather information and the current location is determined according to the third machine learning model, and the target image is rendered according to the target rendering method, so that the rendering method is more accurate and the rendering efficiency is improved.

FIG. 5 is a flowchart of an image rendering method provided by an embodiment of the present application. As a further description of the above-mentioned embodiment, the method includes:

Step 510: Acquire character attribute information of multiple first users and rendering modes of multiple first users.

Wherein, the character attribute information includes at least one or more of the following attribute information: age information, gender information, occupation information or interest information.

The personal attributes of the first user may be the same or different. The age information can be a specific age or an age group. Age groups can be teenagers, youth, adults, middle-aged, or old. Gender information includes male or female. Occupation information can be art, clerical, outdoor, etc. Interest information can include: sports, literature or politics, etc.

Step 520: Perform machine learning on the character attribute information and rendering methods corresponding to the plurality of first users to obtain a fourth machine learning model.

After the fourth machine learning model is trained, its corresponding rendering mode can be determined according to the input attribute information.

Step 530: Obtain the target attribute information of the current user, and substitute the target attribute information into the fourth machine learning model to obtain the target rendering mode corresponding to the target attribute information.

Step 540: Render the target image according to the target rendering mode.

Step 540 is the same as step 120, and the description of step 120 can be referred to.

Step 550: Output the rendered target image.

Step 550 is the same as step 130, and the description of step 130 can be referred to.

The image rendering method provided in this embodiment can determine the rendering mode according to the user's own attribute information, so that the rendering mode is more accurate and the rendering efficiency is improved.

6 is a schematic structural diagram of an image rendering apparatus provided by an embodiment of the present application. The apparatus is used to implement the above-mentioned method in the above-mentioned embodiment. The apparatus is located in a mobile terminal and includes:

The machine learning module 610 is used for obtaining the target rendering mode of the target image according to the machine learning model, and the target image is the image obtained by the photographing function;

A rendering module 620, configured to render the target image according to the target rendering method obtained by the machine learning module 610;

The output module 630 is configured to output the target image rendered by the rendering module 620 .

Further, the machine learning module 610 is also used for:

acquiring first position information of a plurality of first users when shooting a first image and a rendering mode of the first image;

performing machine learning on the first location information and the rendering mode corresponding to the plurality of first users to obtain a first machine learning model;

Acquire current position information, and substitute the current position information into the first machine learning model to obtain a target rendering mode corresponding to the current position.

Further, the machine learning module 610 is further configured to: obtain the photographing time of multiple first users when photographing the first image;

performing machine learning on the first location information, the photographing time and the rendering method corresponding to the plurality of first users to obtain a second machine learning model;

The current location information and the current time information are acquired, and the current location information and the current time information are substituted into the second machine learning model to obtain the target rendering mode corresponding to the current location and the current time information.

Further, the machine learning module 610 is also used for: judging whether there is a character feature area in the first image;

If there is a character feature area in the first image, perform machine learning on the first position information and the rendering manner corresponding to the plurality of first users to obtain a first machine learning model.

Further, the machine learning module 610 is further configured to: acquire weather information of multiple first users when shooting the first image;

performing machine learning on the first location information, the weather information and the rendering mode corresponding to the plurality of first users to obtain a third machine learning model;

The current location information and the current weather information are acquired, and the current location information and the current weather information are substituted into the third machine learning model to obtain the target rendering mode corresponding to the current location and the current weather information.

Further, the machine learning module 610 is further configured to: acquire character attribute information of multiple first users and rendering modes of the multiple first users, where the character attribute information includes at least one or more of the following attribute information : age information, gender information, occupational information or interest information;

performing machine learning on the character attribute information corresponding to the plurality of first users and the rendering mode to obtain a fourth machine learning model;

The target attribute information of the current user is acquired, the target attribute information is substituted into the fourth machine learning model, and the target rendering mode corresponding to the target attribute information is obtained.

Further, as shown in FIG. 7 , a feedback module 710 is also included, and the feedback module 710 is used for:

receiving user feedback information on the target image;

The machine learning model is adjusted according to the feedback information.

In the image rendering device provided in this embodiment, the machine learning module 610 obtains the target rendering method of the target image according to the machine learning model, and the target image is an image obtained by the photographing function; the rendering module 620 renders the target image according to the target rendering method; the output module 630 Output the rendered target image. Since machine learning can determine the target rendering method of the target image according to the historical rendering methods of the current user or other users, users can avoid blindly trying multiple rendering methods, and improve the rendering efficiency of the rendering function and the utilization rate of the image rendering function.

The above-mentioned apparatus can execute the methods provided by all the foregoing embodiments of the present application, and has corresponding functional modules and beneficial effects for executing the above-mentioned methods. For technical details not described in detail in this embodiment, reference may be made to the methods provided in all the foregoing embodiments of this application.

FIG. 8 is a schematic structural diagram of a terminal according to an embodiment of the present application. As shown in FIG. 4 , the terminal may include: a casing (not shown in the figure), a first memory 801 , and a first central processing unit (Central Processing Unit, CPU) 802 (also known as a first processor, hereinafter referred to as CPU for short) ), a computer program stored on the first memory 801 and executable on the first processor 802, a circuit board (not shown in the figure), and a power supply circuit (not shown in the figure). The above-mentioned circuit board is arranged inside the space enclosed by the above-mentioned housing; the above-mentioned CPU 802 and the above-mentioned first memory 801 are arranged on the above-mentioned circuit board; the above-mentioned power supply circuit is used to supply power to each circuit or device of the above-mentioned terminal; the above-mentioned first memory 801 , for storing executable program code; the above-mentioned CPU 802 runs the program corresponding to the above-mentioned executable program code by reading the executable program code stored in the above-mentioned first memory 801, so as to execute:

A target rendering method for obtaining a target image according to the machine learning model, where the target image is an image obtained by a photographing function;

rendering the target image according to the target rendering mode;

Output the rendered target image.

The above terminal further includes: peripheral interface 803, RF (Radio Frequency, radio frequency) circuit 805, audio circuit 806, speaker 811, power management chip 808, input/output (I/O) subsystem 809, touch screen 812, other input/output Control device 810 and external ports 804, these components communicate via one or more communication buses or signal lines 807.

In addition, the terminal also includes a camera and an RGB light sensor. The RGB light sensor is located next to the camera and can be placed adjacent to the camera. The camera can be either a front-facing camera or a rear-facing camera. The RGB light sensor can also be configured separately from the camera, for example, on the narrow side of the terminal.

It should be understood that the illustrated terminal 800 is merely an example of a terminal, and that the terminal 800 may have more or fewer components than those shown in the figure, may combine two or more components, or may have Different part configurations. The various components shown in the figures may be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and/or application specific integrated circuits.

The following describes the terminal provided in this embodiment in detail, and the terminal takes a smart phone as an example.

The first memory 801, the above-mentioned first memory 801 can be accessed by the CPU 802, the peripheral interface 803, etc. The above-mentioned first memory 801 can include a high-speed random access first memory, and can also include a non-volatile first memory, such as one or A plurality of magnetic disk first storage devices, flash memory devices, or other volatile solid state first storage devices.

Peripheral interface 803 , the above-mentioned peripheral interface 803 can connect the input and output peripherals of the device to the CPU 802 and the first memory 801 .

I/O subsystem 809 , which can connect input and output peripherals on the device, such as touch screen 812 and other input/control devices 810 , to peripheral interface 803 . The I/O subsystem 809 may include a display controller 8091 and one or more input controllers 8092 for controlling other input/control devices 810 . Wherein, one or more input controllers 8092 receive electrical signals from or send electrical signals to other input/control devices 810, which may include physical buttons (push buttons, rocker buttons, etc. ), dial pad, slide switch, joystick, click wheel. Notably, the input controller 8092 can be connected to any of the following: a keyboard, an infrared port, a USB interface, and a pointing device such as a mouse. In addition, other input/control devices 810 may also include cameras, fingerprint sensors, gyroscopes, and the like.

Wherein, according to the working principle of the touch screen and the classification of the medium for transmitting information, the touch screen 812 may be a resistive type, a capacitive induction type, an infrared type or a surface acoustic wave type. According to the installation method, the touch screen 812 can be an external type, a built-in type or an integral type. Classified according to technical principles, the touch screen 812 may be: a vector pressure sensing technology touch screen, a resistive technology touch screen, a capacitive technology touch screen, an infrared technology touch screen or a surface acoustic wave technology touch screen.

The touch screen 812, which is an input interface and an output interface between the user terminal and the user, displays visual output to the user, and the visual output may include graphics, text, icons, videos, and the like. Optionally, the touch screen 812 sends an electrical signal triggered by a user on the touch screen (eg, an electrical signal on a contact surface) to the first processor 802 .

Display controller 8091 in I/O subsystem 809 receives electrical signals from touch screen 812 or sends electrical signals to touch screen 812 . The touch screen 812 detects the contact on the touch screen, and the display controller 8091 converts the detected contact into interaction with the user interface objects displayed on the touch screen 812, that is, to realize human-computer interaction, and the user interface objects displayed on the touch screen 812 can be run. Icons for games, icons for connecting to the corresponding network, etc. It is worth noting that the device may also include a light mouse, which is a touch-sensitive surface that does not display visual output, or an extension of the touch-sensitive surface formed by a touch screen.

The RF circuit 805 is mainly used to establish the communication between the smart speaker and the wireless network (ie, the network side), so as to realize the data reception and transmission between the smart speaker and the wireless network. Such as sending and receiving text messages, e-mails, etc.

The audio circuit 806 is mainly used to receive audio data from the peripheral interface 803 , convert the audio data into electrical signals, and send the electrical signals to the speaker 811 .

The speaker 811 is used to restore the voice signal received by the smart speaker from the wireless network through the RF circuit 805 into sound and play the sound to the user.

The power management chip 808 is used for power supply and power management for the hardware connected to the CPU 802, the I/O subsystem and the peripheral interface.

In this embodiment, the central first processor 802 is used for:

A target rendering method for obtaining a target image according to the machine learning model, where the target image is an image obtained by a photographing function;

rendering the target image according to the target rendering mode;

Output the rendered target image.

Further, the target rendering method for obtaining the target image according to the machine learning model includes:

acquiring first position information of a plurality of first users when shooting a first image and a rendering mode of the first image;

performing machine learning on the first location information and the rendering mode corresponding to the plurality of first users to obtain a first machine learning model;

Acquire current position information, and substitute the current position information into the first machine learning model to obtain a target rendering mode corresponding to the current position.

Further, after acquiring the position information of the multiple first users when shooting the first image and the rendering mode of the first image, the method further includes:

acquiring the photographing times of the multiple first users when photographing the first images;

performing machine learning on the first location information, the photographing time and the rendering method corresponding to the plurality of first users to obtain a second machine learning model;

The current location information and the current time information are acquired, and the current location information and the current time information are substituted into the second machine learning model to obtain the target rendering mode corresponding to the current location and the current time information.

Further, performing machine learning on the first location information and the rendering mode corresponding to the multiple first users to obtain a first machine learning model, including:

judging whether there is a character feature area in the first image;

If there is a character feature area in the first image, perform machine learning on the first position information and the rendering manner corresponding to the plurality of first users to obtain a first machine learning model.

Further, after acquiring the position information of the multiple first users when shooting the first image and the rendering mode of the first image, the method further includes:

acquiring weather information of multiple first users when shooting the first images;

performing machine learning on the first location information, the weather information and the rendering mode corresponding to the plurality of first users to obtain a third machine learning model;

The current location information and the current weather information are acquired, and the current location information and the current weather information are substituted into the third machine learning model to obtain the target rendering mode corresponding to the current location and the current weather information.

Further, the target rendering method for obtaining the target image according to the machine learning model includes:

Obtain character attribute information of multiple first users and rendering methods of the multiple first users, where the character attribute information includes at least one or more of the following attribute information: age information, gender information, occupation information or interests information;

performing machine learning on the character attribute information corresponding to the plurality of first users and the rendering mode to obtain a fourth machine learning model;

The target attribute information of the current user is acquired, the target attribute information is substituted into the fourth machine learning model, and the target rendering mode corresponding to the target attribute information is obtained.

Further, after outputting the rendered target image, it also includes:

receiving user feedback information on the target image;

The machine learning model is adjusted according to the feedback information.

Embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the following steps can be implemented:

A target rendering method for obtaining a target image according to the machine learning model, where the target image is an image obtained by a photographing function;

rendering the target image according to the target rendering mode;

Output the rendered target image.

Further, the target rendering method for obtaining the target image according to the machine learning model includes:

acquiring first position information of a plurality of first users when shooting a first image and a rendering mode of the first image;

performing machine learning on the first location information and the rendering mode corresponding to the plurality of first users to obtain a first machine learning model;

Acquire current position information, and substitute the current position information into the first machine learning model to obtain a target rendering mode corresponding to the current position.

Further, after acquiring the position information of the multiple first users when shooting the first image and the rendering mode of the first image, the method further includes:

acquiring the photographing times of the multiple first users when photographing the first images;

performing machine learning on the first location information, the photographing time and the rendering method corresponding to the plurality of first users to obtain a second machine learning model;

The current location information and the current time information are acquired, and the current location information and the current time information are substituted into the second machine learning model to obtain the target rendering mode corresponding to the current location and the current time information.

Further, performing machine learning on the first location information and the rendering mode corresponding to the multiple first users to obtain a first machine learning model, including:

judging whether there is a character feature area in the first image;

If there is a character feature area in the first image, perform machine learning on the first position information and the rendering manner corresponding to the plurality of first users to obtain a first machine learning model.

Further, after acquiring the position information of the multiple first users when shooting the first image and the rendering mode of the first image, the method further includes:

acquiring weather information of multiple first users when shooting the first images;

performing machine learning on the first location information, the weather information and the rendering mode corresponding to the plurality of first users to obtain a third machine learning model;

The current location information and the current weather information are acquired, and the current location information and the current weather information are substituted into the third machine learning model to obtain the target rendering mode corresponding to the current location and the current weather information.

Further, the target rendering method for obtaining the target image according to the machine learning model includes:

Obtain character attribute information of multiple first users and rendering methods of the multiple first users, where the character attribute information includes at least one or more of the following attribute information: age information, gender information, occupation information or interests information;

performing machine learning on the character attribute information corresponding to the plurality of first users and the rendering mode to obtain a fourth machine learning model;

The target attribute information of the current user is acquired, the target attribute information is substituted into the fourth machine learning model, and the target rendering mode corresponding to the target attribute information is obtained.

Further, after outputting the rendered target image, it also includes:

receiving user feedback information on the target image;

The machine learning model is adjusted according to the feedback information.

The computer storage medium of the embodiments of the present application may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples (a non-exhaustive list) of computer readable storage media include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

A computer-readable signal medium may include a propagated data signal in baseband or as part of a carrier wave, with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .

Program code embodied on a computer readable medium may be transmitted using any suitable medium, including - but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out the operations of the present application may be written in one or more programming languages, including object-oriented programming languages—such as Java, Smalltalk, C++, but also conventional procedural languages, or a combination thereof. Programming Language - such as "C" language or similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider through Internet connection).

Note that the above are only preferred embodiments of the present application and applied technical principles. Those skilled in the art will understand that the present application is not limited to the specific embodiments described above, and various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present application. Therefore, although the present application has been described in detail through the above embodiments, the present application is not limited to the above embodiments, and can also include more other equivalent embodiments without departing from the concept of the present application. The scope is determined by the scope of the appended claims.

Claims (7)

1. an image rendering method, is characterized in that, comprises: The target rendering method for obtaining the target image according to the machine learning model includes: obtaining the character attribute information of a plurality of first users, the first position information of the plurality of first users when shooting the first image, the shooting time, and the first image. The first location information is coordinate information or location identification information; the character attribute information includes at least one or more of the following attribute information: age information, gender information, occupation information or interest information; the The target rendering mode is the historical rendering mode of the current user or other users; performing machine learning on the character attribute information, the first location information, the photographing time and the rendering method corresponding to the plurality of first users to obtain a second machine learning model; Obtain the target attribute information, current location information and current time information of the current user, and substitute the target attribute information, the current location information and the current time information into the second machine learning model to obtain the target attribute information, the target rendering mode corresponding to the current position and the current time information; Rendering the target image according to the target rendering method, where the target image is an image obtained by a photographing function; Output the rendered target image. 2 . The image rendering method according to claim 1 , wherein the character attribute information, the first location information, the photographing time, and the rendering corresponding to the plurality of first users are: 3 . Perform machine learning in this way to obtain a second machine learning model, including: judging whether there is a character feature area in the first image; If there is a character feature area in the first image, perform machine learning on the first location information, the photographing time and the rendering method corresponding to the multiple first users to obtain a second machine learning model. 3. The image rendering method according to claim 1, characterized in that, after acquiring the position information of a plurality of first users when shooting the first image, the shooting time and the rendering mode of the first image, the method further comprises: acquiring weather information of multiple first users when shooting the first images; performing machine learning on the first location information, the weather information and the rendering mode corresponding to the plurality of first users to obtain a third machine learning model; The current location information and the current weather information are acquired, and the current location information and the current weather information are substituted into the third machine learning model to obtain the target rendering mode corresponding to the current location and the current weather information. 4. The image rendering method according to claim 1, characterized in that, after outputting the rendered target image, further comprising: receiving user feedback information on the target image; The machine learning model is adjusted according to the feedback information. 5. An image rendering device, comprising: The machine learning module is used to obtain the target rendering method of the target image according to the machine learning model, including: obtaining the character attribute information of the plurality of first users, the first position information of the plurality of first users when shooting the first image, the shooting time and the rendering method of the first image, the first location information is coordinate information or location identification information; the character attribute information includes at least one or more of the following attribute information: age information, gender information, occupation information or interest information; the target rendering mode is the historical rendering mode of the current user or other users; performing machine learning on the character attribute information, the first location information, the photographing time and the rendering method corresponding to the plurality of first users to obtain a second machine learning model; Obtain the target attribute information, current location information and current time information of the current user, and substitute the target attribute information, the current location information and the current time information into the second machine learning model to obtain the target attribute information, the target rendering mode corresponding to the current position and the current time information; a rendering module, configured to render the target image according to the target rendering mode, where the target image is an image obtained by a photographing function; The output module is used for outputting the target image rendered by the rendering module. 6. A terminal, wherein the terminal comprises: one or more processors; storage means for storing one or more programs, A data transceiver for data interaction with the server; When the one or more programs are executed by the one or more processors, the one or more processors implement the image rendering method according to any one of claims 1-4. 7. A computer-readable storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the image rendering method according to any one of claims 1-4 is implemented.

Images