Image processing method and device, equipment and medium

Abstract

The embodiment of the invention relates to an image processing method and device, equipment and a medium. The method comprises the following steps: receiving image retouching demand information for a to-be-processed first image; analyzing the picture retouching demand information by using a preset model so as to determine at least one target picture retouching function corresponding to the picture retouching demand information from a plurality of preset picture retouching functions; and editing the first image by using the target image retouching function to obtain a second image. According to the embodiment of the invention, the second image meeting the requirements of the user can be efficiently obtained, the image retouching time and energy of the user can be effectively saved, and the user experience can be well guaranteed.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technology, and in particular to an image processing method, device, equipment and medium. Background Art

[0002] The photo editing function has been widely used in various application scenarios such as image editing software, photo taking software, and video live broadcast platforms, and users can adjust the image according to their needs. However, the inventors have found through research that the user's photo editing needs are mostly subjective, abstract, or vague. For example, the user wants the portrait to be cuter or cooler, but the user usually does not know how to use the existing photo editing function to edit the image to achieve the desired effect. Therefore, they can only try to use different photo editing functions from the existing multiple photo editing functions to edit the image to meet the photo editing needs. However, this method is cumbersome and complicated for users, requires a high time cost, consumes user energy, and has a poor user experience. Summary of the invention

[0003] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides an image processing method, apparatus, device and medium.

[0004] An embodiment of the present disclosure provides an image processing method, which includes: receiving photo editing requirement information for a first image to be processed; parsing the photo editing requirement information using a preset model to determine at least one target photo editing function corresponding to the photo editing requirement information from a plurality of preset photo editing functions; and editing the first image using the target photo editing function to obtain a second image.

[0005] Optionally, the method further includes: displaying the second image in a preset manner; wherein the preset manner includes: displaying the second image alone, or displaying the second image simultaneously with the first image.

[0006] Optionally, the method further includes: displaying information of the target photo editing function.

[0007] Optionally, the method further includes: in response to receiving feedback information from a user regarding the second image, associating and storing the photo editing requirement information, information on the target photo editing function, the feedback information, the first image, and the second image.

[0008] Optionally, the method further includes: in response to receiving an edit request for the second image, using the second image as a new first image.

[0009] Optionally, the photo editing requirement information is parsed using a preset model to determine at least one target photo editing function corresponding to the photo editing requirement information from among a plurality of preset photo editing functions, including: based on information of a plurality of preset photo editing functions, the photo editing requirement information is parsed using a preset model to determine at least one target photo editing function corresponding to the photo editing requirement information from among the plurality of preset photo editing functions.

[0010] Optionally, the information based on the preset multiple photo editing functions utilizes a preset model to parse the photo editing requirement information to determine at least one target photo editing function corresponding to the photo editing requirement information from the multiple photo editing functions, including: generating model prompt information based on the preset multiple photo editing functions information; wherein the information of the multiple photo editing functions includes the first name of each of the multiple photo editing functions, and the model prompt information includes the second name of each of the multiple photo editing functions; inputting the model prompt information and the photo editing requirement information into a preset model, so that the model parses the photo editing requirement information based on the model prompt information, and outputs information of at least one target photo editing function corresponding to the photo editing requirement information.

[0011] Optionally, the method also includes: inputting the first name of the photo editing function into the preset model to obtain function definition information output by the model for the first name of the photo editing function; if the function definition information matches the photo editing function, determining that the second name of the photo editing function is the same as the first name; if the function definition information does not match the photo editing function, obtaining the second name of the photo editing function; wherein the function definition information output by the model for the second name of the photo editing function matches the photo editing function.

[0012] Optionally, the information of the multiple photo editing functions and the model prompt information both include the serial numbers of the multiple photo editing functions.

[0013] Optionally, the model prompt information also includes output format information corresponding to the model.

[0014] Optionally, the model includes a large language model.

[0015] The disclosed embodiment also provides an image processing device, including: an information receiving module, used to receive photo editing requirement information for a first image to be processed; a function determination module, used to parse the photo editing requirement information using a preset model to determine at least one target photo editing function corresponding to the photo editing requirement information from a plurality of preset photo editing functions; and an image editing module, used to edit the first image using the target photo editing function to obtain a second image.

[0016] An embodiment of the present disclosure also provides an electronic device, which includes: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the image processing method provided by the embodiment of the present disclosure.

[0017] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the image processing method provided by the embodiment of the present disclosure.

[0018] The above-mentioned technical solution provided by the embodiment of the present disclosure can, when receiving photo editing requirement information, automatically determine the target photo editing function corresponding to the photo editing requirement information from a variety of photo editing functions by adopting a model to parse the photo editing requirement information, and directly use the target photo editing function to edit the first image, so as to efficiently obtain the second image that meets the user's needs. The user does not need to repeatedly try to use different photo editing functions from the existing multiple photo editing functions to edit the image in order to meet the photo editing needs. Therefore, the user's photo editing time and energy can be effectively saved, and the user experience can be better guaranteed.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0022] Figure 1 A flowchart of an image processing method provided by an embodiment of the present disclosure;

[0023] Figure 2 A schematic diagram of an interface provided by an embodiment of the present disclosure;

[0024] Figure 3 A schematic diagram of an interface provided by an embodiment of the present disclosure;

[0025] Figure 4 A flowchart of an image processing method provided by an embodiment of the present disclosure;

[0026] Figure 5 A schematic diagram of the structure of an image processing device provided by an embodiment of the present disclosure;

[0027] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0029] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0030] Figure 1 The following is a flow chart of an image processing method provided by an embodiment of the present disclosure. The method can be executed by an image processing device, wherein the device can be implemented by software and / or hardware and can generally be integrated in an electronic device. Figure 1 As shown, the method mainly includes the following steps S102 to S106:

[0031] Step S102: receiving image retouching requirement information for a first image to be processed.

[0032] In actual applications, an information input port for inputting information on photo editing requirements and an upload port for the first image may be provided on the target interface for the user. The information input port may be, for example, a text input box, a voice input control, etc., which are not limited here. The user may upload the first image to be processed through the upload port, and input information on photo editing requirements for the first image through the information input port. The photo editing requirement information may be presented in the form of text or voice, and the disclosed embodiment does not limit the expression of the photo editing requirement information. The user does not need to express it in a specific format. The user may also use a colloquial expression according to the needs, such as "I want to look cooler", "I want to look more sunny", "make the facial features more three-dimensional", etc., which are not limited here.

[0033] Step S104: parse the photo editing requirement information using a preset model to determine at least one target photo editing function corresponding to the photo editing requirement information from among a plurality of preset photo editing functions.

[0034] When receiving the photo editing requirement information for the first image through the information input port, the embodiment of the present disclosure inputs the photo editing requirement information into the preset model, uses the preset model to parse the photo editing requirement information, and searches for a target photo editing function that can meet the photo editing requirement information from the preset multiple photo editing functions. Among them, the preset multiple photo editing functions may be photo editing functions of the current image editing software. Among them, the above model may be a neural network model. The embodiment of the present disclosure does not limit the model structure. In practical applications, the above model may be obtained through pre-training.

[0035] Exemplarily, the initial neural network model can be comprehensively trained using the sample information of the photo editing requirement and the information of the photo editing function that meets the sample information of the photo editing requirement among the various photo editing functions, until the function prediction result output by the initial neural network model meets expectations, such as when the photo editing function information output by the neural network model is consistent with the information of the photo editing function that actually meets the sample information of the photo editing requirement or the difference is less than a preset threshold, then the training ends. The neural network model that has been trained is the model preset in the embodiment of the present disclosure, which can accurately parse the photo editing requirement information, thereby having the ability to accurately and reliably determine the target photo editing function corresponding to the photo editing requirement information from the preset various photo editing functions. The above is only an example of a training model. In actual applications, the model training can also be comprehensively performed in combination with the first image sample to be adjusted, the sample information of the photo editing requirement, the information of the photo editing function that meets the sample information of the photo editing requirement among the various photo editing functions, and the second image sample obtained after the first image sample is retouched based on the photo editing function that meets the sample information of the photo editing requirement, etc., to fully ensure the reliability of the trained model.

[0036] In summary, in the embodiments disclosed herein, the target photo editing function corresponding to the photo editing requirement information can be directly determined from the preset multiple photo editing functions using a pre-trained neural network model based on artificial intelligence technology. That is, by using a neural network model with strong learning and processing capabilities, the target photo editing function that meets the user's needs can be efficiently and reliably determined from the multiple photo editing functions by parsing the photo editing requirement information. In practical applications, the number of target photo editing functions can be one or more, and is not limited here.

[0037] Step S106, using the target image editing function to edit the first image to obtain a second image.

[0038] In the disclosed embodiment, the target photo editing function can be directly called to edit the first image, without the user having to search one by one and use the target photo editing function to edit the image, which is very convenient and quick.

[0039] In summary, the above-mentioned technical solution provided by the embodiment of the present disclosure can, when receiving photo retouching requirement information, automatically determine the target photo retouching function corresponding to the photo retouching requirement information from a variety of photo retouching functions by adopting a model to parse the photo retouching requirement information, and directly use the target photo retouching function to edit the first image, so as to efficiently obtain the second image that meets the user's needs. The user does not need to repeatedly try to use different photo retouching functions from the existing multiple photo retouching functions to edit the image in order to meet the photo retouching needs. Therefore, the user's photo retouching time and energy can be effectively saved, and the user experience can be better guaranteed.

[0040] In actual applications, the embodiments of the present disclosure can display the second image in a preset manner; wherein the preset manner includes: displaying alone, or displaying together with the first image. That is, the second image can be displayed alone, or the second image can be displayed together with the first image. It should be noted that displaying the second image alone means that the image displayed on the interface is only the second image, and does not mean that other content is not displayed on the interface, such as other text, controls, etc. can also be displayed on the interface. The way in which the second image and the first image are displayed simultaneously can be in a side-by-side manner or in a top-to-bottom alignment manner, which is not limited here. The way in which the first image and the second image are displayed simultaneously helps the user to clearly compare the difference between the first image and the second image.

[0041] Furthermore, in order to facilitate the user to clearly know which photo editing function is used to achieve the effect of the second image, the method provided by the embodiment of the present disclosure further includes: displaying information of the target photo editing function. For example, the information of the target photo editing function may include the name of the target photo editing function, and may also include identifiers such as the serial number of the target photo editing function. By displaying the information of the target photo editing function on the interface, it is also helpful for the user to clearly know which photo editing function is used to edit the first image to obtain the second image.

[0042] In addition, the method provided by the embodiment of the present disclosure also includes: in response to receiving feedback information from the user for the second image, associating and storing the photo editing requirement information, the information of the target photo editing function, the feedback information, the first image and the second image. In practical applications, a feedback control for the user to input feedback information can be provided on the interface. The feedback control can be in the form of a text input box or in the form of a scoring option, which is not limited here. By obtaining feedback information, the photo editing requirement information, the information of the target photo editing function, the feedback information, the first image and the second image are associated and stored for subsequent analysis. For example, according to the photo editing requirement information, the information of the target photo editing function, the feedback information, the first image and the second image, the parameters of the neural network model used to determine the target photo editing function corresponding to the photo editing requirement information from the preset multiple photo editing functions are optimized and adjusted, so that the optimized neural network model can accurately and reliably determine the target photo editing function that meets the user's needs from the multiple photo editing functions in the future, which is also helpful to further improve the accuracy of determining the target photo editing function.

[0043] Considering that the user may have a need to continue adjusting the second image, the method provided in the embodiment of the present disclosure also includes: in response to receiving an edit request for the second image, using the second image as a new first image. In actual applications, an edit control for the second image can be provided to the user on the target interface, and when it is detected that the edit control is triggered, the second image is used as the new first image, that is, the second image is used to replace the original first image as the new first image, and then the user's photo editing requirement information for the new first image (that is, the second image generated previously) is obtained, so as to further perform photo editing based on the photo editing requirement information. In the above manner, the user can continuously adjust the photo editing effect of the image according to the needs, fully ensuring that the user can finally obtain an image that meets the needs.

[0044] For ease of understanding, the present disclosure provides an application example of the present disclosure. Figure 2 and Figure 3 A schematic diagram of the interface is shown respectively. Figure 2 In the figure, a picture editing request information input box is shown, and the first image uploaded by the user is shown below the input box. Figure 2 The figure also shows a clear control and a submit control. The user can delete the first image through the clear control, or submit the first image to the background for automatic editing through the submit control. Figure 3In the picture, not only the obtained second image is displayed side by side with the first image, but also the information of the target photo editing function used is clearly indicated. For example, when the photo editing requirement information is "I want to look cooler", the information of the target photo editing function can be: {"Ability": "Light face shape", "Serial number": "8"}{"Ability": "Adjust chin length", "Serial number": "21"}{"Ability": "Adjust cheekbones", "Serial number": "24"}{"Ability": "Adjust eyebrow height", "Serial number": "50"}{"Ability": "Remove dark circles", "Serial number": "79"}. Among them, the above-mentioned "ability" represents the photo editing function, and the "serial number" is the number of the photo editing function. In addition, in Figure 3 The interface shown also shows a "move to input" button. The "move to input" button is a control for instructing to continue editing the second image. When the user clicks the button, the second image can be directly used as the new first image to return to the previous state. Figure 2 The interface shown in the figure is displayed, and the user's photo editing requirement information for the first image at this time (that is, the second image obtained last time) is obtained again, and so on. No further details are given here. In the above manner, the user can quickly obtain the photo editing results that meet the requirements, and can also make multiple adjustments, effectively ensuring the user experience. In addition, Figure 3 The figure also shows three evaluation level buttons (excellent, average, and poor) and a comment input box for users to provide feedback information. Users can directly evaluate the second image through the evaluation level buttons and can also make text comments on the second image through the comment input box. The above is only a simple illustration and should not be regarded as a limitation. For example, in actual applications, more or fewer evaluation levels can be set or users can be directly provided with ratings, etc., which can be flexibly set.

[0045] It should be noted that Figure 2 and Figure 3 This is only an example application interface of the image processing method provided by an embodiment of the present disclosure. In actual applications, the interface style and interface elements can be flexibly set and are not limited here.

[0046] On the basis of the above, the embodiment of the present disclosure provides an implementation method of using a preset model to parse the photo editing demand information to determine at least one target photo editing function corresponding to the photo editing demand information from the preset multiple photo editing functions. For example, the preset model can be used to parse the photo editing demand information based on the information of the preset multiple photo editing functions to determine the target photo editing function corresponding to the photo editing demand information from the multiple photo editing functions. The above model can be a neural network model, that is, using a neural network model with strong learning ability and processing ability, the target photo editing function that meets the user's needs can be efficiently and reliably determined from the multiple photo editing functions. The embodiment of the present disclosure does not limit the structure of the neural network model. For example, the neural network model can be a language model, and further, the neural network model can be a large language model. The large language model refers to a deep learning model trained with a large amount of data, which can handle multiple natural language tasks and other tasks, has a strong information parsing ability, and can better parse the photo editing demand information. Further, the embodiment of the present disclosure can also provide the model with information of multiple existing photo editing functions, which can assist the model in further parsing the photo editing demand information, thereby determining the target photo editing function that meets the photo editing demand information.

[0047] In order to facilitate the model to determine the target photo retouching function more accurately and efficiently, or to reduce the difficulty of the model in determining the target photo retouching function, the following provides a specific example of using a preset model to parse the photo retouching requirement information based on information of multiple preset photo retouching functions to determine at least one target photo retouching function corresponding to the photo retouching requirement information from the multiple photo retouching functions, which can be performed with reference to the following steps A and B:

[0048] Step A, based on the information of the preset multiple photo editing functions, generate model prompt information; wherein the information of the multiple photo editing functions includes the first names of the multiple photo editing functions, and the model prompt information includes the second names of the multiple photo editing functions. The first name is the name of the photo editing function itself, and the embodiment of the present disclosure fully considers that the model may not accurately understand the name of the photo editing function. In order to avoid errors in the functions recommended by the model due to understanding deviations, the embodiment of the present disclosure can generate model prompt information for assisting the model in determining the target photo editing function, wherein the model prompt information at least includes the second names of the multiple photo editing functions, and the first name and the second name of the photo editing function may be the same or different. If the model can accurately understand the first name, such as the function of a photo editing function can be known based on the first name of the photo editing function, then the second name is the same as the first name; if the model cannot accurately understand the first name, such as the function of a photo editing function cannot be accurately known based on the first name of the photo editing function, then the second name is different from the first name, and the second name is a name that the model can accurately understand. In addition, the information of the photo editing function may also include description information of the photo editing function, etc., which is not limited here. For ease of understanding, the present disclosure provides a method for determining the second name of the photo editing function, which can be performed with reference to the following steps (1) to (3):

[0049] Step (1) inputs the first name of the photo editing function into a preset model to obtain function definition information output by the model for the first name of the photo editing function. The function definition information is a function description of the photo editing function output by the model based on the first name.

[0050] Step (2), if the function definition information matches the photo editing function, then it is determined that the second name of the photo editing function is the same as the first name. If the function definition information matches the photo editing function, that is, the model's definition of the photo editing function is consistent with the actual function of the photo editing function, then it means that the model can accurately understand the first name, and in the model prompt information, the second name of the photo editing function input to the model is equal to the first name.

[0051] Step (3), if the function definition information does not match the photo editing function, then obtain the second name of the photo editing function; wherein the function definition information output by the model for the second name of the photo editing function matches the photo editing function. That is, if the model's definition of the photo editing function does not match the actual function of the photo editing function, then a new name can be obtained for the photo editing function, and the obtained second name can be accurately understood by the model, that is, the function definition information output by the model for the second name of the photo editing function matches the photo editing function. For example, assuming that the model does not understand the "adjustment of the upper face" in the first name, it can be changed to the second name "adjustment of the hairline area to the center of the eyebrows".

[0052] In actual applications, for each of the multiple preset photo editing functions, the above steps (1) to (3) are performed. In this way, it can be fully ensured that the model can accurately understand the meaning of each photo editing function and ensure the accuracy of the target photo editing function finally determined.

[0053] Further, considering that the model may have a "hallucination phenomenon", that is, in the "hallucination phenomenon" of the model, the target photo editing function output by the model may not exist or be inaccurate. For example, assuming that a total of 80 photo editing functions are preset, and most of them are face-related photo editing functions, and the photo editing requirement information input by the user is a body beauty requirement, then the target photo editing function output by the model may be other photo editing functions other than the above 80 photo editing functions, that is, a function that does not exist in the preset multiple photo editing functions may be fabricated. To improve this problem, the disclosed embodiment includes the serial numbers of the multiple photo editing functions in the information of the multiple photo editing functions and the model prompt information. That is, for each photo editing function, the name of the photo editing function corresponds to the serial number one by one. In the above manner, the name and serial number of the photo editing function are included in the model prompt information at the same time, which can not only alleviate the hallucination phenomenon of the model and improve the reliability of the model output results, but also help to detect whether the name and serial number of the target photo editing function output by the model correspond, doubly guaranteeing the accuracy of the model output results.

[0054] Furthermore, in order to ensure that the model can directly output a format that meets the requirements, the model prompt information can also include the output format information corresponding to the model. That is, the model needs to output the name, serial number, etc. of the target photo editing function according to the output format information. For example, the output format information includes: in accordance with the following json format, each key-value field (key value field) is enclosed in double quotes - "Capability": "Capability name", "Serial number": "Corresponding serial number of this capability", etc. In addition, it can also include other fields that may be needed and corresponding field explanations, such as capability recommendation strength (0-100 or mild / moderate / severe, etc.), which are not restricted here.

[0055] Step B: inputting the model prompt information and the photo editing requirement information into a preset model, so that the model parses the photo editing requirement information based on the model prompt information, and outputs information of at least one target photo editing function corresponding to the photo editing requirement information.

[0056] Through the above method, the model can accurately determine the target photo retouching function that matches the photo retouching requirement information based on the various photo retouching functions provided by the model prompt information, and determine the name, serial number and other information of the target photo retouching function according to the output format information provided by the model prompt information.

[0057] In actual applications, model prompt information and photo editing requirement information can be described in a preset language format and presented in the form of a preset script, and finally input into the model so that the model can convert the user's abstract requirements into specific photo editing solutions.

[0058] For ease of understanding, the present disclosure provides a Figure 4 The flowchart of the image processing method shown is a flowchart of the image processing method. In this method, the aforementioned model is a large language model. Specifically, the user's photo editing requirement information can be input into the prompt project, and the prompt project outputs model prompt information. The prompt project is mainly used to generate model prompt information that can be input into the large language model based on the existing multiple photo editing functions, and the model prompt information is input into the large language model. The large language model outputs a target photo editing function list (name and serial number), and the input first image is edited based on the target photo editing function list to obtain a second image. The user can evaluate based on the target photo editing function list and the second image to obtain the user's feedback information. The photo editing requirement information, feedback information, target photo editing function list, first image and second image can be further saved, which can be used for subsequent data analysis and model training, so as to further optimize the large language model.

[0059] To sum up, the above-mentioned image processing method provided by the embodiment of the present disclosure can, when receiving photo retouching requirement information, automatically determine the target photo retouching function corresponding to the photo retouching requirement information from a variety of photo retouching functions by adopting a model to parse the photo retouching requirement information, and directly use the target photo retouching function to edit the first image, so as to efficiently obtain the second image that meets the user's needs. The user does not need to repeatedly try to use different photo retouching functions from the existing multiple photo retouching functions to edit the image in order to meet the photo retouching needs. Therefore, the user's photo retouching time and energy can be effectively saved, and the user experience can be better guaranteed.

[0060] Corresponding to the aforementioned image processing method, the embodiment of the present disclosure further provides an image processing device, Figure 5 FIG. 1 is a schematic diagram of the structure of an image processing device provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware and can generally be integrated in an electronic device, such as Figure 5 As shown, the image processing device includes:

[0061] The information receiving module 502 is used to receive the image retouching requirement information for the first image to be processed;

[0062] A function determination module 504 is used to analyze the image retouching requirement information using a preset model to determine at least one target image retouching function corresponding to the image retouching requirement information from a plurality of preset image retouching functions;

[0063] The image editing module 506 is used to edit the first image using the target image editing function to obtain a second image.

[0064] In summary, the above-mentioned device provided by the embodiment of the present disclosure does not require the user to repeatedly try to use different photo editing functions from the existing multiple photo editing functions to edit the image in order to meet the photo editing needs. Therefore, it can effectively save the user's photo editing time and energy and better ensure the user experience.

[0065] In some embodiments, the device further includes an image display module, configured to display the second image in a preset manner; wherein the preset manner includes: displaying the second image alone, or displaying the second image simultaneously with the first image.

[0066] In some embodiments, the device further includes a function information display module for displaying information of the target photo editing function.

[0067] In some embodiments, the device also includes an associated storage module for associating and storing the photo editing requirement information, the information of the target photo editing function, the feedback information, the first image and the second image in response to receiving user feedback information regarding the second image.

[0068] In some embodiments, the apparatus further comprises an updating module, configured to, in response to receiving an editing request for the second image, use the second image as a new first image.

[0069] In some embodiments, the function determination module 504 is specifically used to: based on information of a plurality of preset photo editing functions, parse the photo editing requirement information using a preset model to determine at least one target photo editing function corresponding to the photo editing requirement information from the plurality of photo editing functions.

[0070] In some embodiments, the function determination module 504 is specifically used to: generate model prompt information based on information of multiple preset photo editing functions; wherein the information of the multiple photo editing functions includes the first name of each of the multiple photo editing functions, and the model prompt information includes the second name of each of the multiple photo editing functions; input the model prompt information and the photo editing requirement information into a preset model, so that the model parses the photo editing requirement information based on the model prompt information, and outputs information of at least one target photo editing function corresponding to the photo editing requirement information.

[0071] In some embodiments, the device also includes a name determination module, which is used to input the first name of the photo editing function into the preset model to obtain function definition information output by the model for the first name of the photo editing function; if the function definition information matches the photo editing function, it is determined that the second name of the photo editing function is the same as the first name; if the function definition information does not match the photo editing function, the second name of the photo editing function is obtained; wherein the function definition information output by the model for the second name of the photo editing function matches the photo editing function.

[0072] In some implementations, the information of the multiple photo editing functions and the model prompt information both include the serial numbers of the multiple photo editing functions.

[0073] In some implementations, the model prompt information also includes output format information corresponding to the model.

[0074] In some implementations, the model comprises a large language model.

[0075] The image processing device provided in the embodiments of the present disclosure can execute the image processing method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0076] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device embodiment can refer to the corresponding process in the method embodiment, and will not be repeated here.

[0077] An embodiment of the present disclosure provides an electronic device, which includes: a storage device on which a computer program is stored; and a processing device for executing the computer program in the storage device to implement the steps of any method in the present disclosure.

[0078] Reference below Figure 6 , which shows a suitable method for implementing the embodiments of the present disclosure

[0079] Schematic diagram of the structure of the electronic device 600. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0080] like Figure 6As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0081] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, 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.

[0082] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0083] In addition to the above-mentioned methods and devices, the embodiments of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, cause the processor to perform the image processing method provided by the embodiments of the present disclosure. The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present disclosure, the programming languages ​​including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may be executed entirely on a user computing device, partially on a user device, as an independent software package, partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0084] In addition, the embodiment of the present disclosure may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the image processing method provided by the embodiment of the present disclosure.

[0085] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0086] The embodiment of the present disclosure further provides a computer program product, including a computer program / instruction, which implements the image processing method in the embodiment of the present disclosure when the computer program / instruction is executed by a processor.

[0087] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure 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.

[0088] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0089] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0090] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0091] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0092] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An image processing method, characterized in that: include: Receiving image retouching requirement information for a first image to be processed; Analyzing the image editing requirement information using a preset model to determine at least one target image editing function corresponding to the image editing requirement information from a plurality of preset image editing functions; The first image is edited using the target image editing function to obtain a second image.

2. The method according to claim 1, characterized in that The method further comprises: The second image is displayed in a preset manner; wherein the preset manner includes: displaying the second image alone, or displaying the second image together with the first image.

3. The method according to claim 1, characterized in that The method further comprises: Display information about the target image editing function.

4. The method according to claim 1, characterized in that: The method further comprises: In response to receiving user feedback information regarding the second image, the image retouching requirement information, the information of the target image retouching function, the feedback information, the first image, and the second image are stored in association.

5. The method according to claim 1, characterized in that The method further comprises: In response to receiving an edit request for the second image, the second image is used as a new first image.

6. The method according to any one of claims 1 to 5, characterized in that: The using a preset model to analyze the image editing requirement information to determine at least one target image editing function corresponding to the image editing requirement information from a plurality of preset image editing functions includes: Based on information of a plurality of preset photo editing functions, the photo editing requirement information is parsed using a preset model to determine at least one target photo editing function corresponding to the photo editing requirement information from the plurality of photo editing functions.

7. The method according to claim 6, characterized in that The step of parsing the picture retouching requirement information based on the information of the preset multiple picture retouching functions using a preset model to determine at least one target picture retouching function corresponding to the picture retouching requirement information from the multiple picture retouching functions includes: Generate model prompt information based on information of a plurality of preset photo editing functions; wherein the information of the plurality of photo editing functions includes first names of the plurality of photo editing functions, and the model prompt information includes second names of the plurality of photo editing functions; The model prompt information and the photo editing requirement information are input into a preset model, so that the model parses the photo editing requirement information based on the model prompt information, and outputs information of at least one target photo editing function corresponding to the photo editing requirement information.

8. The method according to claim 7, characterized in that The method further comprises: Inputting the first name of the photo retouching function into the preset model to obtain function definition information output by the model for the first name of the photo retouching function; If the function definition information matches the photo editing function, determining that the second name of the photo editing function is the same as the first name; If the function definition information does not match the photo editing function, a second name of the photo editing function is obtained; wherein the function definition information output by the model for the second name of the photo editing function matches the photo editing function.

9. The method according to claim 7, characterized in that: The information of the multiple photo editing functions and the model prompt information both include the serial numbers of the multiple photo editing functions.

10. The method according to claim 7, characterized in that The model prompt information also includes output format information corresponding to the model.

11. The method according to claim 6, characterized in that The model includes a large language model.

12. An image processing device, characterized in that: include: An information receiving module, used for receiving image retouching requirement information for a first image to be processed; a function determination module, configured to analyze the image retouching requirement information by using a preset model, so as to determine at least one target image retouching function corresponding to the image retouching requirement information from among a plurality of preset image retouching functions; The image editing module is used to edit the first image using the target image editing function to obtain a second image.

13. An electronic device, characterized in that: The electronic device comprises: a storage device having a computer program stored thereon; A processing device, used to execute the computer program in the storage device to implement the steps of the image processing method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the image processing method according to any one of claims 1 to 11.

Images